From 688d791fa024fe59dc04433f7f7b8d76d32a180a Mon Sep 17 00:00:00 2001 From: yujonglee Date: Fri, 2 Oct 2026 14:55:42 -0700 Subject: [PATCH] feat(traces): type queries and align read access with log visibility (#44228) * wip * wip * test(traces): separate root status from diagnostic error counts * test(traces): cover normalization precedence and fallbacks * chore(cache): remove stray comments from trace PR * test(traces): name lens test for shared query path * fix(traces): place query implementation before test module * test(traces): use unified read scope in migration tests * ci(rust): allow feature checks to finish * ci(mcp): allow dependency resolution to finish * fix(traces): preserve key visibility and safe spend attribution --- .../test-mcp-dependency-resolution.yml | 2 +- .github/workflows/test-rust.yml | 2 +- litellm-rust/Cargo.lock | 23 +- litellm-rust/Cargo.toml | 1 + litellm-rust/crates/python-bridge/Cargo.toml | 1 + .../crates/python-bridge/src/routes/traces.rs | 185 +- .../{README.md => AGENTS.md} | 2 +- .../crates/storage-clickhouse/Cargo.toml | 1 + .../crates/storage-clickhouse/src/error.rs | 2 + .../crates/storage-clickhouse/src/lib.rs | 2 +- .../crates/storage-clickhouse/src/read.rs | 50 +- .../storage-clickhouse/tests/transport.rs | 81 +- .../crates/traces-clickhouse/AGENTS.md | 7 + .../crates/traces-clickhouse/Cargo.toml | 31 + .../{traces => traces-clickhouse}/build.rs | 0 .../migrations/0001_otel_traces.sql | 0 .../migrations/0002_otel_traces_ttl.sql | 0 .../migrations/0003_agent_traces.sql | 0 .../migrations/0004_agent_traces_ttl.sql | 0 .../migrations/0005_agent_traces_mv.sql | 0 .../migrations/0006_spend_logs.sql | 0 .../migrations/0007_spend_logs_ttl.sql | 0 .../migrations/0008_trace_user.sql | 2 + .../0009_trace_rollup_ownership.sql | 3 + .../0010_trace_cost_completeness.sql | 22 + .../0011_otel_traces_framework.sql} | 0 .../query/lens_agents.sql | 0 .../query/lens_availability.sql | 0 .../query/lens_content.sql | 0 .../query/lens_evidence.sql | 0 .../query/lens_sample.sql | 0 .../query/list_traces.sql | 12 +- .../traces-clickhouse/query/span_detail.sql | 26 + .../query/span_error.sql | 6 +- .../query/spend_by_response_ids.sql | 11 + .../query/trace_identity.sql | 9 + .../query/trace_spans.sql | 8 +- .../src/config.rs | 5 +- .../crates/traces-clickhouse/src/error.rs | 37 + .../src/insert.rs | 6 +- .../crates/traces-clickhouse/src/lib.rs | 21 + .../crates/traces-clickhouse/src/query.rs | 362 + .../src/query/guide.rs | 0 .../traces-clickhouse/src/query/lens.rs | 173 + .../traces-clickhouse/src/query/named.rs | 320 + .../traces-clickhouse/src/query/number.rs | 44 + .../traces-clickhouse/src/query_access.rs | 237 + .../crates/traces-clickhouse/src/schema.rs | 136 + .../crates/traces-clickhouse/src/sql.rs | 83 + .../crates/traces-clickhouse/src/table.rs | 9 + .../templates/query_help.jinja | 6 +- .../tests/admin_sql.rs | 81 +- .../tests/fixtures/README.md | 15 + .../tests/fixtures/spend_logs.jsonl | 3 + .../tests/insert.rs | 5 +- .../tests/migrations.rs | 477 +- .../crates/traces-clickhouse/tests/queries.rs | 273 + .../tests/queries/failed_spans.expected.json | 30 + .../tests/queries/failed_spans.sql | 5 + .../queries/metadata_filters.expected.json | 30 + .../tests/queries/metadata_filters.sql | 5 + .../tests/queries/read_access.json | 6 + .../tests/queries/rollups.expected.json | 87 + .../tests/queries/rollups.sql | 10 + .../tests/queries/support.rs | 153 + .../tests/queries/trace_costs.expected.json | 40 + .../tests/queries/trace_costs.sql | 9 + .../traces-clickhouse/tests/query_access.rs | 268 + .../traces-clickhouse/tests/support/mod.rs | 36 + litellm-rust/crates/traces/AGENTS.md | 13 +- litellm-rust/crates/traces/Cargo.toml | 17 - litellm-rust/crates/traces/config/reader.xml | 32 - .../crates/traces/query/span_detail.sql | 19 - .../traces/query/spend_by_response_ids.sql | 9 - litellm-rust/crates/traces/src/error.rs | 26 +- litellm-rust/crates/traces/src/lib.rs | 22 +- .../traces/src/normalize/claude_code.rs | 12 +- .../crates/traces/src/normalize/genai.rs | 4 +- .../crates/traces/src/normalize/langsmith.rs | 4 +- .../crates/traces/src/normalize/mod.rs | 102 +- .../traces/src/normalize/openinference.rs | 4 +- .../crates/traces/src/otlp/attributes.rs | 10 +- litellm-rust/crates/traces/src/otlp/limits.rs | 35 +- litellm-rust/crates/traces/src/otlp/mod.rs | 7 +- litellm-rust/crates/traces/src/otlp/span.rs | 22 +- litellm-rust/crates/traces/src/otlp/wire.rs | 10 +- litellm-rust/crates/traces/src/query.rs | 359 +- litellm-rust/crates/traces/src/query/named.rs | 152 + .../crates/traces/src/query_access.rs | 191 +- litellm-rust/crates/traces/src/schema.rs | 70 - litellm-rust/crates/traces/src/sql.rs | 76 - .../tests/fixtures/deeplite_auth_error.json | 1614 +++ .../traces/tests/fixtures/deeplite_swarm.json | 9812 +++++++++++++++++ .../tests/fixtures/query_alternate.json | 39 + .../traces/tests/fixtures/query_children.json | 85 + .../tests/fixtures/query_other_team.json | 46 + .../traces/tests/fixtures/query_root.json | 46 + litellm-rust/crates/traces/tests/otlp.rs | 307 +- litellm-rust/crates/traces/tests/query.rs | 34 + .../crates/traces/tests/query/named.rs | 63 + .../crates/traces/tests/query_access.rs | 295 +- litellm/proxy/_types.py | 1 + litellm/proxy/auth/route_checks.py | 2 +- litellm/proxy/lens/sources.py | 175 +- .../proxy/spend_tracking/log_visibility.py | 44 + litellm/proxy/tracing_endpoints.py | 84 +- litellm/rust_bridge/_native.pyi | 4 +- litellm/rust_bridge/trace_queries.py | 320 + litellm/rust_bridge/trace_query_responses.py | 109 + litellm/rust_bridge/traces.py | 112 +- litellm/tracing/decode.py | 1 + litellm/tracing/receiver.py | 5 +- litellm/tracing/store.py | 217 +- litellm/tracing/types.py | 5 +- tests/test_litellm/tracing/test_receiver.py | 5 +- tests/test_litellm/tracing/test_store.py | 243 +- tests/test_litellm_rust/test_traces.py | 119 +- tests/unit/proxy/auth/test_route_checks.py | 16 + tests/unit/proxy/lens/test_sources.py | 61 +- .../spend_tracking/test_log_visibility.py | 47 + tests/unit/proxy/test_tracing_endpoints.py | 122 +- tests/unit/rust_bridge/test_trace_queries.py | 59 + ui/litellm-dashboard/src/lib/http/schema.d.ts | 156 +- .../src/lib/http/traceQueryTypes.test-d.ts | 20 + 124 files changed, 17105 insertions(+), 1820 deletions(-) rename litellm-rust/crates/storage-clickhouse/{README.md => AGENTS.md} (70%) create mode 100644 litellm-rust/crates/traces-clickhouse/AGENTS.md create mode 100644 litellm-rust/crates/traces-clickhouse/Cargo.toml rename litellm-rust/crates/{traces => traces-clickhouse}/build.rs (100%) rename litellm-rust/crates/{traces => traces-clickhouse}/migrations/0001_otel_traces.sql (100%) rename litellm-rust/crates/{traces => traces-clickhouse}/migrations/0002_otel_traces_ttl.sql (100%) rename litellm-rust/crates/{traces => traces-clickhouse}/migrations/0003_agent_traces.sql (100%) rename litellm-rust/crates/{traces => traces-clickhouse}/migrations/0004_agent_traces_ttl.sql (100%) rename litellm-rust/crates/{traces => traces-clickhouse}/migrations/0005_agent_traces_mv.sql (100%) rename litellm-rust/crates/{traces => traces-clickhouse}/migrations/0006_spend_logs.sql (100%) rename litellm-rust/crates/{traces => traces-clickhouse}/migrations/0007_spend_logs_ttl.sql (100%) create mode 100644 litellm-rust/crates/traces-clickhouse/migrations/0008_trace_user.sql create mode 100644 litellm-rust/crates/traces-clickhouse/migrations/0009_trace_rollup_ownership.sql create mode 100644 litellm-rust/crates/traces-clickhouse/migrations/0010_trace_cost_completeness.sql rename litellm-rust/crates/{traces/migrations/0008_otel_traces_framework.sql => traces-clickhouse/migrations/0011_otel_traces_framework.sql} (100%) rename litellm-rust/crates/{traces => traces-clickhouse}/query/lens_agents.sql (100%) rename litellm-rust/crates/{traces => traces-clickhouse}/query/lens_availability.sql (100%) rename litellm-rust/crates/{traces => traces-clickhouse}/query/lens_content.sql (100%) rename litellm-rust/crates/{traces => traces-clickhouse}/query/lens_evidence.sql (100%) rename litellm-rust/crates/{traces => traces-clickhouse}/query/lens_sample.sql (100%) rename litellm-rust/crates/{traces => traces-clickhouse}/query/list_traces.sql (78%) create mode 100644 litellm-rust/crates/traces-clickhouse/query/span_detail.sql rename litellm-rust/crates/{traces => traces-clickhouse}/query/span_error.sql (71%) create mode 100644 litellm-rust/crates/traces-clickhouse/query/spend_by_response_ids.sql create mode 100644 litellm-rust/crates/traces-clickhouse/query/trace_identity.sql rename litellm-rust/crates/{traces => traces-clickhouse}/query/trace_spans.sql (74%) rename litellm-rust/crates/{traces => traces-clickhouse}/src/config.rs (78%) create mode 100644 litellm-rust/crates/traces-clickhouse/src/error.rs rename litellm-rust/crates/{traces => traces-clickhouse}/src/insert.rs (98%) create mode 100644 litellm-rust/crates/traces-clickhouse/src/lib.rs create mode 100644 litellm-rust/crates/traces-clickhouse/src/query.rs rename litellm-rust/crates/{traces => traces-clickhouse}/src/query/guide.rs (100%) create mode 100644 litellm-rust/crates/traces-clickhouse/src/query/lens.rs create mode 100644 litellm-rust/crates/traces-clickhouse/src/query/named.rs create mode 100644 litellm-rust/crates/traces-clickhouse/src/query/number.rs create mode 100644 litellm-rust/crates/traces-clickhouse/src/query_access.rs create mode 100644 litellm-rust/crates/traces-clickhouse/src/schema.rs create mode 100644 litellm-rust/crates/traces-clickhouse/src/sql.rs create mode 100644 litellm-rust/crates/traces-clickhouse/src/table.rs rename litellm-rust/crates/{traces => traces-clickhouse}/templates/query_help.jinja (86%) rename litellm-rust/crates/{traces => traces-clickhouse}/tests/admin_sql.rs (84%) create mode 100644 litellm-rust/crates/traces-clickhouse/tests/fixtures/README.md create mode 100644 litellm-rust/crates/traces-clickhouse/tests/fixtures/spend_logs.jsonl rename litellm-rust/crates/{traces => traces-clickhouse}/tests/insert.rs (97%) rename litellm-rust/crates/{traces => traces-clickhouse}/tests/migrations.rs (78%) create mode 100644 litellm-rust/crates/traces-clickhouse/tests/queries.rs create mode 100644 litellm-rust/crates/traces-clickhouse/tests/queries/failed_spans.expected.json create mode 100644 litellm-rust/crates/traces-clickhouse/tests/queries/failed_spans.sql create mode 100644 litellm-rust/crates/traces-clickhouse/tests/queries/metadata_filters.expected.json create mode 100644 litellm-rust/crates/traces-clickhouse/tests/queries/metadata_filters.sql create mode 100644 litellm-rust/crates/traces-clickhouse/tests/queries/read_access.json create mode 100644 litellm-rust/crates/traces-clickhouse/tests/queries/rollups.expected.json create mode 100644 litellm-rust/crates/traces-clickhouse/tests/queries/rollups.sql create mode 100644 litellm-rust/crates/traces-clickhouse/tests/queries/support.rs create mode 100644 litellm-rust/crates/traces-clickhouse/tests/queries/trace_costs.expected.json create mode 100644 litellm-rust/crates/traces-clickhouse/tests/queries/trace_costs.sql create mode 100644 litellm-rust/crates/traces-clickhouse/tests/query_access.rs create mode 100644 litellm-rust/crates/traces-clickhouse/tests/support/mod.rs delete mode 100644 litellm-rust/crates/traces/config/reader.xml delete mode 100644 litellm-rust/crates/traces/query/span_detail.sql delete mode 100644 litellm-rust/crates/traces/query/spend_by_response_ids.sql create mode 100644 litellm-rust/crates/traces/src/query/named.rs delete mode 100644 litellm-rust/crates/traces/src/schema.rs delete mode 100644 litellm-rust/crates/traces/src/sql.rs create mode 100644 litellm-rust/crates/traces/tests/fixtures/deeplite_auth_error.json create mode 100644 litellm-rust/crates/traces/tests/fixtures/deeplite_swarm.json create mode 100644 litellm-rust/crates/traces/tests/fixtures/query_alternate.json create mode 100644 litellm-rust/crates/traces/tests/fixtures/query_children.json create mode 100644 litellm-rust/crates/traces/tests/fixtures/query_other_team.json create mode 100644 litellm-rust/crates/traces/tests/fixtures/query_root.json create mode 100644 litellm-rust/crates/traces/tests/query.rs create mode 100644 litellm-rust/crates/traces/tests/query/named.rs create mode 100644 litellm/proxy/spend_tracking/log_visibility.py create mode 100644 litellm/rust_bridge/trace_queries.py create mode 100644 litellm/rust_bridge/trace_query_responses.py create mode 100644 tests/unit/proxy/spend_tracking/test_log_visibility.py create mode 100644 tests/unit/rust_bridge/test_trace_queries.py create mode 100644 ui/litellm-dashboard/src/lib/http/traceQueryTypes.test-d.ts diff --git a/.github/workflows/test-mcp-dependency-resolution.yml b/.github/workflows/test-mcp-dependency-resolution.yml index 463d6a7e9e8..8f70375a181 100644 --- a/.github/workflows/test-mcp-dependency-resolution.yml +++ b/.github/workflows/test-mcp-dependency-resolution.yml @@ -17,7 +17,7 @@ concurrency: jobs: resolve: runs-on: ubuntu-latest - timeout-minutes: 15 + timeout-minutes: 25 strategy: fail-fast: false matrix: diff --git a/.github/workflows/test-rust.yml b/.github/workflows/test-rust.yml index b0935263d28..07e2c3f554c 100644 --- a/.github/workflows/test-rust.yml +++ b/.github/workflows/test-rust.yml @@ -89,7 +89,7 @@ jobs: rust-test: runs-on: ubuntu-latest - timeout-minutes: 20 + timeout-minutes: 30 defaults: run: working-directory: litellm-rust diff --git a/litellm-rust/Cargo.lock b/litellm-rust/Cargo.lock index 40552b19e43..54e814994b4 100644 --- a/litellm-rust/Cargo.lock +++ b/litellm-rust/Cargo.lock @@ -4156,6 +4156,7 @@ dependencies = [ "litellm-storage-clickhouse", "litellm-token-counter", "litellm-traces", + "litellm-traces-clickhouse", "litellm-tracing", "prost", "pyo3", @@ -4369,6 +4370,7 @@ dependencies = [ "thiserror 2.0.19", "tokio", "url", + "wiremock", ] [[package]] @@ -4451,19 +4453,30 @@ dependencies = [ name = "litellm-traces" version = "0.1.0" dependencies = [ - "askama", - "base64 0.22.1", "criterion", + "indexmap 2.14.0", + "opentelemetry-proto", + "prost", + "rstest", + "serde", + "serde_json", + "strum", + "thiserror 2.0.19", +] + +[[package]] +name = "litellm-traces-clickhouse" +version = "0.1.0" +dependencies = [ + "askama", "flate2", "futures-util", "hmac 0.12.1", - "indexmap 2.14.0", "litellm-http", "litellm-migrate", "litellm-storage-clickhouse", + "litellm-traces", "moka", - "opentelemetry-proto", - "prost", "rstest", "serde", "serde_json", diff --git a/litellm-rust/Cargo.toml b/litellm-rust/Cargo.toml index f4cb2ecbe59..7c32e82eb4c 100644 --- a/litellm-rust/Cargo.toml +++ b/litellm-rust/Cargo.toml @@ -13,6 +13,7 @@ litellm-config = { path = "crates/config" } litellm-router = { path = "crates/router" } litellm-tracing = { path = "crates/tracing" } litellm-traces = { path = "crates/traces" } +litellm-traces-clickhouse = { path = "crates/traces-clickhouse" } litellm-storage-clickhouse = { path = "crates/storage-clickhouse" } litellm-migrate = { path = "crates/migrate" } litellm-migrate-macros = { path = "crates/migrate-macros" } diff --git a/litellm-rust/crates/python-bridge/Cargo.toml b/litellm-rust/crates/python-bridge/Cargo.toml index 2b505f08eca..c3a86009111 100644 --- a/litellm-rust/crates/python-bridge/Cargo.toml +++ b/litellm-rust/crates/python-bridge/Cargo.toml @@ -22,6 +22,7 @@ tiktoken = ["litellm-token-counter/tiktoken"] fancy-regex.workspace = true litellm-tracing.workspace = true litellm-traces.workspace = true +litellm-traces-clickhouse.workspace = true litellm-storage-clickhouse.workspace = true litellm-host.workspace = true bytes.workspace = true diff --git a/litellm-rust/crates/python-bridge/src/routes/traces.rs b/litellm-rust/crates/python-bridge/src/routes/traces.rs index f81fc6a6d75..a8e7f441eff 100644 --- a/litellm-rust/crates/python-bridge/src/routes/traces.rs +++ b/litellm-rust/crates/python-bridge/src/routes/traces.rs @@ -2,10 +2,8 @@ use std::collections::BTreeMap; use litellm_host_python::{FromPythonCache, ToPythonCache}; use litellm_http::ClientVariant; -use litellm_traces::{ - Config, Error, InsertTable, Parameter, QueryAccessError, QueryReaders, QueryScope, ReadQuery, - Shared, -}; +use litellm_traces::{QueryScope, ReadQuery, Shared}; +use litellm_traces_clickhouse::{Config, Error, InsertTable, Parameter, QueryReaders}; use prost::Message; use pyo3::{ exceptions::{PyOverflowError, PyRuntimeError, PyValueError}, @@ -31,38 +29,56 @@ pub fn trace_encode_error<'py>(py: Python<'py>, message: &str) -> Bound<'py, PyB } fn map_error(error: Error) -> PyErr { + map_error_ref(&error) +} + +fn map_error_ref(error: &Error) -> PyErr { + use litellm_storage_clickhouse::Error as StorageError; + match error { Error::InvalidRow | Error::InvalidTable | Error::InvalidSchema - | Error::EmptySql - | Error::InvalidQuery => PyValueError::new_err(error.to_string()), + | Error::InvalidQuery + | Error::InvalidParameters + | Error::InvalidScope => PyValueError::new_err(error.to_string()), Error::InsertTooLarge => PyOverflowError::new_err(error.to_string()), - Error::InvalidUrl - | Error::QueryFailed(_) - | Error::InsertFailed(_) - | Error::SchemaFailed(_) - | Error::ResponseTooLarge - | Error::InvalidResponse - | Error::Transport => PyRuntimeError::new_err(error.to_string()), + Error::SchemaFailed(_) + | Error::SchemaTransport + | Error::MissingSecret + | Error::Busy + | Error::ProvisionFailed(_) + | Error::ProvisionTransport + | Error::InvalidResponse => PyRuntimeError::new_err(error.to_string()), + Error::Cached(source) => map_error_ref(source), + Error::Storage(source) => match source { + StorageError::InvalidRow + | StorageError::InvalidTable + | StorageError::InvalidSchema + | StorageError::EmptySql + | StorageError::InvalidParameters + | StorageError::InvalidQuery => PyValueError::new_err(error.to_string()), + StorageError::InsertTooLarge => PyOverflowError::new_err(error.to_string()), + StorageError::InvalidUrl + | StorageError::QueryFailed(_) + | StorageError::InsertFailed(_) + | StorageError::SchemaFailed(_) + | StorageError::ResponseTooLarge + | StorageError::InvalidResponse + | StorageError::Transport => PyRuntimeError::new_err(error.to_string()), + }, } } fn map_sql_error(error: Error) -> PyErr { match error { - Error::QueryFailed(400 | 404) => PyValueError::new_err(error.to_string()), + Error::Storage(litellm_storage_clickhouse::Error::QueryFailed(400 | 404)) => { + PyValueError::new_err(error.to_string()) + } error => map_error(error), } } -fn map_query_access_error(error: QueryAccessError) -> PyErr { - match error { - QueryAccessError::Storage(error) => map_sql_error(error), - QueryAccessError::InvalidScope => PyValueError::new_err(error.to_string()), - error => PyRuntimeError::new_err(error.to_string()), - } -} - #[pyclass(frozen)] pub struct NativeTraceConfig { inner: Config, @@ -105,7 +121,13 @@ impl NativeTraceStorage { crate::execution::run_async( py, async move { - litellm_traces::ensure_schema(&client, &connection, &database, retention_days).await + litellm_traces_clickhouse::ensure_schema( + &client, + &connection, + &database, + retention_days, + ) + .await }, map_error, ) @@ -115,7 +137,7 @@ impl NativeTraceStorage { &self, py: Python<'py>, table: &str, - #[pyo3(from_py_with = insert_rows_from_py)] rows: Vec, + #[pyo3(from_py_with = insert_rows_from_py)] rows: Vec, ) -> PyResult> { let table = InsertTable::parse(table).map_err(map_error)?; let client = crate::http::host_client(py, ClientVariant::NoRedirect)?; @@ -124,8 +146,14 @@ impl NativeTraceStorage { crate::execution::run_async( py, async move { - litellm_traces::insert_shared_rows(&client, &connection, &database, table, rows) - .await + litellm_traces_clickhouse::insert_shared_rows( + &client, + &connection, + &database, + table, + rows, + ) + .await }, map_error, ) @@ -139,7 +167,9 @@ impl NativeTraceStorage { secret: String, ) -> PyResult> { if sql.trim().is_empty() { - return Err(map_error(Error::EmptySql)); + return Err(map_error( + litellm_storage_clickhouse::Error::EmptySql.into(), + )); } let readers = self.query_readers.clone(); let client = crate::http::host_client(py, ClientVariant::NoRedirect)?; @@ -148,11 +178,9 @@ impl NativeTraceStorage { async move { let _permit = readers.acquire()?; let connection = readers.connection(&client, &scope, &secret).await?; - litellm_traces::query_sql(&client, &connection, &sql) - .await - .map_err(QueryAccessError::Storage) + litellm_traces_clickhouse::query_sql(&client, &connection, &sql).await }, - map_query_access_error, + map_sql_error, ) } @@ -169,32 +197,9 @@ impl NativeTraceStorage { async move { let _permit = readers.acquire()?; let connection = readers.connection(&client, &scope, &secret).await?; - litellm_traces::query_help(&client, &connection) - .await - .map_err(QueryAccessError::Storage) + litellm_traces_clickhouse::query_help(&client, &connection).await }, - map_query_access_error, - ) - } - - fn lens_query<'py>( - &self, - py: Python<'py>, - name: &str, - #[pyo3(from_py_with = litellm_host_python::from_py_argument)] parameters: BTreeMap< - String, - Parameter, - >, - ) -> PyResult> { - let query = litellm_traces::LensQuery::parse(name).map_err(map_error)?; - let connection = self.config.storage().reader().clone(); - let client = crate::http::host_client(py, ClientVariant::NoRedirect)?; - crate::execution::run_async( - py, - async move { - litellm_traces::execute_read(&client, &connection, query.sql(), ¶meters).await - }, - map_error, + map_sql_error, ) } @@ -207,13 +212,20 @@ impl NativeTraceStorage { Parameter, >, ) -> PyResult> { - let query = ReadQuery::parse(query).map_err(map_error)?; + let query = + ReadQuery::parse(query).map_err(|error| PyValueError::new_err(error.to_string()))?; let connection = self.config.storage().reader().clone(); let client = crate::http::host_client(py, ClientVariant::NoRedirect)?; crate::execution::run_async( py, async move { - litellm_traces::execute_named_read(&client, &connection, query, ¶meters).await + litellm_traces_clickhouse::execute_named_read( + &client, + &connection, + query, + ¶meters, + ) + .await }, map_error, ) @@ -229,13 +241,15 @@ pub fn trace_decode_otlp<'py>( let spans = py .detach(|| litellm_traces::decode_otlp(body, content_type)) .map_err(|error| match error { - litellm_traces::DecodeError::TooLarge => PyOverflowError::new_err(error.to_string()), + litellm_traces::Error::TooLarge => PyOverflowError::new_err(error.to_string()), _ => PyValueError::new_err(error.to_string()), })?; spans_to_py(py, &spans).map(Bound::into_any) } -fn insert_rows_from_py(value: &Bound<'_, PyAny>) -> PyResult> { +fn insert_rows_from_py( + value: &Bound<'_, PyAny>, +) -> PyResult> { let mut resources = FromPythonCache::default(); value .try_iter()? @@ -320,6 +334,54 @@ mod tests { use super::*; use rstest::rstest; + #[rstest] + #[case::row(Error::InvalidRow, "ValueError")] + #[case::insert_budget(Error::InsertTooLarge, "OverflowError")] + #[case::scope(Error::InvalidScope, "ValueError")] + #[case::schema(Error::SchemaFailed(503), "RuntimeError")] + #[case::reader(Error::MissingSecret, "RuntimeError")] + #[case::storage( + Error::Storage(litellm_storage_clickhouse::Error::InvalidUrl), + "RuntimeError" + )] + #[case::cached_scope(Error::Cached(std::sync::Arc::new(Error::InvalidScope)), "ValueError")] + fn trace_failures_preserve_public_exception_types( + #[case] error: Error, + #[case] exception_name: &str, + ) { + Python::initialize(); + Python::attach(|py| { + let message = error.to_string(); + let exception = map_error(error); + assert_eq!(exception.get_type(py).name().unwrap(), exception_name); + assert_eq!( + exception.value(py).str().unwrap().to_str().unwrap(), + message + ); + }); + } + + #[rstest] + #[case::invalid_sql(400, "ValueError")] + #[case::missing_table(404, "ValueError")] + #[case::unavailable(503, "RuntimeError")] + fn wrapped_query_status_preserves_public_exception_type( + #[case] status: u16, + #[case] exception_name: &str, + ) { + Python::initialize(); + Python::attach(|py| { + let error = Error::Storage(litellm_storage_clickhouse::Error::QueryFailed(status)); + let message = error.to_string(); + let exception = map_sql_error(error); + assert_eq!(exception.get_type(py).name().unwrap(), exception_name); + assert_eq!( + exception.value(py).str().unwrap().to_str().unwrap(), + message + ); + }); + } + #[rstest] fn insert_projection_preserves_identity_without_merging_equal_resources() { Python::initialize(); @@ -365,5 +427,6 @@ mod tests { #[pyfunction] pub fn trace_normalized_field_definitions<'py>(py: Python<'py>) -> PyResult> { - litellm_host_python::Pythonized(litellm_traces::NORMALIZED_FIELD_DEFINITIONS).into_pyobject(py) + litellm_host_python::Pythonized(litellm_traces_clickhouse::NORMALIZED_FIELD_DEFINITIONS) + .into_pyobject(py) } diff --git a/litellm-rust/crates/storage-clickhouse/README.md b/litellm-rust/crates/storage-clickhouse/AGENTS.md similarity index 70% rename from litellm-rust/crates/storage-clickhouse/README.md rename to litellm-rust/crates/storage-clickhouse/AGENTS.md index 676260f6043..959ffdffb88 100644 --- a/litellm-rust/crates/storage-clickhouse/README.md +++ b/litellm-rust/crates/storage-clickhouse/AGENTS.md @@ -2,4 +2,4 @@ `litellm-storage-clickhouse` exports `Storage`, a writer and bounded reader derived from one ClickHouse URL and database. It also exports bounded HTTP read and insert execution -The crate has no trace tables, OTLP types, or named trace queries. `litellm-traces` supplies those rules and uses this storage for both trace rows and spend rows +The crate has no trace tables, OTLP types, or named trace queries. `litellm-traces-clickhouse` supplies those rules and uses this storage for both trace rows and spend rows diff --git a/litellm-rust/crates/storage-clickhouse/Cargo.toml b/litellm-rust/crates/storage-clickhouse/Cargo.toml index f7f85c0dd8d..acce941f2c9 100644 --- a/litellm-rust/crates/storage-clickhouse/Cargo.toml +++ b/litellm-rust/crates/storage-clickhouse/Cargo.toml @@ -18,3 +18,4 @@ url.workspace = true litellm-http = { workspace = true, features = ["test-support"] } rstest.workspace = true tokio.workspace = true +wiremock.workspace = true diff --git a/litellm-rust/crates/storage-clickhouse/src/error.rs b/litellm-rust/crates/storage-clickhouse/src/error.rs index d283fb9021e..43202b8fa15 100644 --- a/litellm-rust/crates/storage-clickhouse/src/error.rs +++ b/litellm-rust/crates/storage-clickhouse/src/error.rs @@ -10,6 +10,8 @@ pub enum Error { InvalidSchema, #[error("SQL query must not be empty")] EmptySql, + #[error("invalid ClickHouse query parameters")] + InvalidParameters, #[error("unknown ClickHouse read query")] InvalidQuery, #[error("ClickHouse query failed with HTTP status {0}")] diff --git a/litellm-rust/crates/storage-clickhouse/src/lib.rs b/litellm-rust/crates/storage-clickhouse/src/lib.rs index 6a6a957d456..7cba0a11653 100644 --- a/litellm-rust/crates/storage-clickhouse/src/lib.rs +++ b/litellm-rust/crates/storage-clickhouse/src/lib.rs @@ -4,7 +4,7 @@ mod read; pub use error::Error; pub use insert::{insert_compressed_rows, insert_encoded_rows}; -pub use read::{Parameter, execute_read}; +pub use read::{Parameter, Query, execute_read, fetch, fetch_json}; use url::Url; #[derive(Clone)] diff --git a/litellm-rust/crates/storage-clickhouse/src/read.rs b/litellm-rust/crates/storage-clickhouse/src/read.rs index 99c6a5120f3..0dae94109bc 100644 --- a/litellm-rust/crates/storage-clickhouse/src/read.rs +++ b/litellm-rust/crates/storage-clickhouse/src/read.rs @@ -1,17 +1,19 @@ use std::{collections::BTreeMap, time::Duration}; use litellm_http::Client; -use serde::Deserialize; +use serde::{Deserialize, Serialize, de::DeserializeOwned}; use crate::{Connection, Error}; const MAX_RESPONSE_BYTES: usize = 4 * 1024 * 1024; -#[derive(Debug, Deserialize)] +#[derive(Debug, Deserialize, Serialize)] #[serde(untagged)] pub enum Parameter { Text(String), Integer(i64), + Unsigned(u64), + Float(f64), Strings(Vec), } @@ -20,6 +22,8 @@ impl Parameter { match self { Self::Text(value) => escaped(value), Self::Integer(value) => value.to_string(), + Self::Unsigned(value) => value.to_string(), + Self::Float(value) => value.to_string(), Self::Strings(values) => format!( "[{}]", values @@ -111,3 +115,45 @@ pub async fn execute_read( } String::from_utf8(body).map_err(|_| Error::InvalidResponse) } + +pub trait Query { + type Params: Serialize; + type Row: DeserializeOwned; + + const SQL: &'static str; +} + +#[derive(Deserialize)] +struct Rows { + data: Vec, +} + +fn parameters(params: &T) -> Result, Error> { + let value = serde_json::to_value(params).map_err(|_| Error::InvalidParameters)?; + serde_json::from_value(value).map_err(|_| Error::InvalidParameters) +} + +pub async fn fetch( + client: &Client, + connection: &Connection, + params: &Q::Params, +) -> Result, Error> { + let body = execute_read(client, connection, Q::SQL, ¶meters(params)?).await?; + decode_rows::(&body) +} + +pub async fn fetch_json( + client: &Client, + connection: &Connection, + params: &Q::Params, +) -> Result { + let body = execute_read(client, connection, Q::SQL, ¶meters(params)?).await?; + decode_rows::(&body)?; + Ok(body) +} + +fn decode_rows(body: &str) -> Result, Error> { + serde_json::from_str::>(body) + .map(|rows| rows.data) + .map_err(|_| Error::InvalidResponse) +} diff --git a/litellm-rust/crates/storage-clickhouse/tests/transport.rs b/litellm-rust/crates/storage-clickhouse/tests/transport.rs index 0c7ea233522..f58e52b4940 100644 --- a/litellm-rust/crates/storage-clickhouse/tests/transport.rs +++ b/litellm-rust/crates/storage-clickhouse/tests/transport.rs @@ -1,7 +1,7 @@ use std::collections::BTreeMap; use litellm_http::Client; -use litellm_storage_clickhouse::{Connection, Error, execute_read, insert_encoded_rows}; +use litellm_storage_clickhouse::{Connection, Error, Query, execute_read, insert_encoded_rows}; use rstest::rstest; #[rstest] @@ -32,3 +32,82 @@ async fn read_rejects_empty_sql() { Err(Error::EmptySql) )); } + +#[derive(serde::Serialize)] +struct QueryParams { + signed: i64, + unsigned: u64, + float: f64, + text: String, + strings: Vec, +} + +#[derive(Debug, serde::Deserialize, PartialEq)] +struct QueryRow { + answer: String, +} + +struct TypedQuery; + +impl litellm_storage_clickhouse::Query for TypedQuery { + type Params = QueryParams; + type Row = QueryRow; + const SQL: &'static str = "SELECT typed_parameters"; +} + +#[rstest] +#[case::valid( + r#"{"meta":[],"data":[{"answer":"ok"}],"rows":1,"statistics":{"elapsed":0.1}}"#, + true +)] +#[case::wrong_type(r#"{"data":[{"answer":1}]}"#, false)] +#[case::missing_column(r#"{"data":[{}]}"#, false)] +#[case::exception(r#"{"data":[],"exception":"failed"}"#, false)] +#[tokio::test] +async fn typed_fetch_encodes_parameters_and_validates_rows( + #[case] body: &str, + #[case] valid: bool, +) { + use litellm_storage_clickhouse::{fetch, fetch_json}; + use wiremock::{ + Mock, MockServer, ResponseTemplate, + matchers::{body_string, query_param}, + }; + + let server = MockServer::start().await; + Mock::given(body_string(TypedQuery::SQL)) + .and(query_param("param_signed", i64::MIN.to_string())) + .and(query_param("param_unsigned", u64::MAX.to_string())) + .and(query_param("param_float", "12.5")) + .and(query_param("param_text", "line\\nbreak")) + .and(query_param("param_strings", "['a\\'b','雪']")) + .and(query_param("readonly", "1")) + .and(query_param("max_result_rows", "1000")) + .respond_with(ResponseTemplate::new(200).set_body_string(body)) + .expect(2) + .mount(&server) + .await; + let client = Client::no_redirect_for_test(); + let connection = Connection::parse(&server.uri()).unwrap(); + let params = QueryParams { + signed: i64::MIN, + unsigned: u64::MAX, + float: 12.5, + text: "line\nbreak".into(), + strings: vec!["a'b".into(), "雪".into()], + }; + let rows = fetch::(&client, &connection, ¶ms).await; + let envelope = fetch_json::(&client, &connection, ¶ms).await; + if valid { + assert_eq!( + rows.unwrap(), + vec![QueryRow { + answer: "ok".into() + }] + ); + assert_eq!(envelope.unwrap(), body); + } else { + assert!(matches!(rows, Err(Error::InvalidResponse))); + assert!(matches!(envelope, Err(Error::InvalidResponse))); + } +} diff --git a/litellm-rust/crates/traces-clickhouse/AGENTS.md b/litellm-rust/crates/traces-clickhouse/AGENTS.md new file mode 100644 index 00000000000..ae0c1c8eeb9 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/AGENTS.md @@ -0,0 +1,7 @@ +- Own trace schema, row encoding, SQL query adapters and reader provisioning; consume domain types from `litellm-traces` +- Keep generic ClickHouse connections and HTTP execution in `litellm-storage-clickhouse`; keep PyO3 conversion in `python-bridge` +- Keep schema definitions only in `migrations/NNNN_description.sql`, embedded by `litellm_migrate::migrate!` +- Require typed query parameters and SELECT-only readers with server-side limits and tenant isolation +- Bound insert time and encoded bytes; preserve shared values and explicit retry deduplication +- Test storage behavior through the public API against ClickHouse +- Expose one top-level `Error` enum in `src/error.rs`; own trace failures and wrap storage errors with `#[from]` or `#[source]` diff --git a/litellm-rust/crates/traces-clickhouse/Cargo.toml b/litellm-rust/crates/traces-clickhouse/Cargo.toml new file mode 100644 index 00000000000..39edd786201 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/Cargo.toml @@ -0,0 +1,31 @@ +[package] +name = "litellm-traces-clickhouse" +version = "0.1.0" +edition.workspace = true +license.workspace = true +repository.workspace = true + +[dependencies] +askama.workspace = true +flate2.workspace = true +futures-util.workspace = true +hmac = "0.12.1" +litellm-http.workspace = true +litellm-migrate.workspace = true +litellm-storage-clickhouse.workspace = true +litellm-traces.workspace = true +moka.workspace = true +serde.workspace = true +serde_json.workspace = true +sha2.workspace = true +strum.workspace = true +thiserror.workspace = true +time = { workspace = true, features = ["formatting"] } +tokio.workspace = true +url.workspace = true + +[dev-dependencies] +litellm-http = { workspace = true, features = ["test-support"] } +rstest.workspace = true +testcontainers-modules = { version = "0.15.0", features = ["clickhouse"] } +wiremock.workspace = true diff --git a/litellm-rust/crates/traces/build.rs b/litellm-rust/crates/traces-clickhouse/build.rs similarity index 100% rename from litellm-rust/crates/traces/build.rs rename to litellm-rust/crates/traces-clickhouse/build.rs diff --git a/litellm-rust/crates/traces/migrations/0001_otel_traces.sql b/litellm-rust/crates/traces-clickhouse/migrations/0001_otel_traces.sql similarity index 100% rename from litellm-rust/crates/traces/migrations/0001_otel_traces.sql rename to litellm-rust/crates/traces-clickhouse/migrations/0001_otel_traces.sql diff --git a/litellm-rust/crates/traces/migrations/0002_otel_traces_ttl.sql b/litellm-rust/crates/traces-clickhouse/migrations/0002_otel_traces_ttl.sql similarity index 100% rename from litellm-rust/crates/traces/migrations/0002_otel_traces_ttl.sql rename to litellm-rust/crates/traces-clickhouse/migrations/0002_otel_traces_ttl.sql diff --git a/litellm-rust/crates/traces/migrations/0003_agent_traces.sql b/litellm-rust/crates/traces-clickhouse/migrations/0003_agent_traces.sql similarity index 100% rename from litellm-rust/crates/traces/migrations/0003_agent_traces.sql rename to litellm-rust/crates/traces-clickhouse/migrations/0003_agent_traces.sql diff --git a/litellm-rust/crates/traces/migrations/0004_agent_traces_ttl.sql b/litellm-rust/crates/traces-clickhouse/migrations/0004_agent_traces_ttl.sql similarity index 100% rename from litellm-rust/crates/traces/migrations/0004_agent_traces_ttl.sql rename to litellm-rust/crates/traces-clickhouse/migrations/0004_agent_traces_ttl.sql diff --git a/litellm-rust/crates/traces/migrations/0005_agent_traces_mv.sql b/litellm-rust/crates/traces-clickhouse/migrations/0005_agent_traces_mv.sql similarity index 100% rename from litellm-rust/crates/traces/migrations/0005_agent_traces_mv.sql rename to litellm-rust/crates/traces-clickhouse/migrations/0005_agent_traces_mv.sql diff --git a/litellm-rust/crates/traces/migrations/0006_spend_logs.sql b/litellm-rust/crates/traces-clickhouse/migrations/0006_spend_logs.sql similarity index 100% rename from litellm-rust/crates/traces/migrations/0006_spend_logs.sql rename to litellm-rust/crates/traces-clickhouse/migrations/0006_spend_logs.sql diff --git a/litellm-rust/crates/traces/migrations/0007_spend_logs_ttl.sql b/litellm-rust/crates/traces-clickhouse/migrations/0007_spend_logs_ttl.sql similarity index 100% rename from litellm-rust/crates/traces/migrations/0007_spend_logs_ttl.sql rename to litellm-rust/crates/traces-clickhouse/migrations/0007_spend_logs_ttl.sql diff --git a/litellm-rust/crates/traces-clickhouse/migrations/0008_trace_user.sql b/litellm-rust/crates/traces-clickhouse/migrations/0008_trace_user.sql new file mode 100644 index 00000000000..845c93aea21 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/migrations/0008_trace_user.sql @@ -0,0 +1,2 @@ +ALTER TABLE {database}.otel_traces + ADD COLUMN IF NOT EXISTS UserId String DEFAULT '' diff --git a/litellm-rust/crates/traces-clickhouse/migrations/0009_trace_rollup_ownership.sql b/litellm-rust/crates/traces-clickhouse/migrations/0009_trace_rollup_ownership.sql new file mode 100644 index 00000000000..fd696349cf5 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/migrations/0009_trace_rollup_ownership.sql @@ -0,0 +1,3 @@ +ALTER TABLE {database}.agent_traces_by_key + ADD COLUMN IF NOT EXISTS UserIds SimpleAggregateFunction(groupUniqArrayArray, Array(String)) DEFAULT [], + ADD COLUMN IF NOT EXISTS IdentifiedLlmCount SimpleAggregateFunction(sum, UInt64) DEFAULT 0 diff --git a/litellm-rust/crates/traces-clickhouse/migrations/0010_trace_cost_completeness.sql b/litellm-rust/crates/traces-clickhouse/migrations/0010_trace_cost_completeness.sql new file mode 100644 index 00000000000..af87a6bf40b --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/migrations/0010_trace_cost_completeness.sql @@ -0,0 +1,22 @@ +ALTER TABLE {database}.agent_traces_by_key_mv MODIFY QUERY +SELECT + TeamId, ApiKeyHash, TraceId, groupUniqArray(UserId) AS UserIds, + min(Timestamp) AS StartTs, + max(Timestamp + toIntervalNanosecond(Duration)) AS EndTs, + any(ServiceName) AS ServiceName, + anyLastIf(toNullable(SpanName), ParentSpanId = '') AS RootName, + anyLastIf(toNullable(InputPreview), ParentSpanId = '') AS RootInput, + anyLastIf(toNullable(StatusCode), ParentSpanId = '') AS RootStatus, + count() AS SpanCount, + countIf(ObservationType = 'agent') AS AgentCount, + countIf(ObservationType = 'llm') AS LlmCount, + countIf(ObservationType = 'llm' AND LiteLLMRequestId != '') AS IdentifiedLlmCount, + countIf(ObservationType = 'tool') AS ToolCount, + countIf(StatusCode = 'STATUS_CODE_ERROR') AS ErrorCount, + sum(InputTokens) AS InputTokens, + sum(OutputTokens) AS OutputTokens, + groupUniqArrayIf(toString(Model), Model != '') AS Models, + groupUniqArrayIf(SpanName, ObservationType = 'agent') AS AgentNames, + groupArrayIf(LiteLLMRequestId, ObservationType = 'llm' OR LiteLLMRequestId != '') AS RequestIds +FROM {database}.otel_traces +GROUP BY TeamId, ApiKeyHash, TraceId diff --git a/litellm-rust/crates/traces/migrations/0008_otel_traces_framework.sql b/litellm-rust/crates/traces-clickhouse/migrations/0011_otel_traces_framework.sql similarity index 100% rename from litellm-rust/crates/traces/migrations/0008_otel_traces_framework.sql rename to litellm-rust/crates/traces-clickhouse/migrations/0011_otel_traces_framework.sql diff --git a/litellm-rust/crates/traces/query/lens_agents.sql b/litellm-rust/crates/traces-clickhouse/query/lens_agents.sql similarity index 100% rename from litellm-rust/crates/traces/query/lens_agents.sql rename to litellm-rust/crates/traces-clickhouse/query/lens_agents.sql diff --git a/litellm-rust/crates/traces/query/lens_availability.sql b/litellm-rust/crates/traces-clickhouse/query/lens_availability.sql similarity index 100% rename from litellm-rust/crates/traces/query/lens_availability.sql rename to litellm-rust/crates/traces-clickhouse/query/lens_availability.sql diff --git a/litellm-rust/crates/traces/query/lens_content.sql b/litellm-rust/crates/traces-clickhouse/query/lens_content.sql similarity index 100% rename from litellm-rust/crates/traces/query/lens_content.sql rename to litellm-rust/crates/traces-clickhouse/query/lens_content.sql diff --git a/litellm-rust/crates/traces/query/lens_evidence.sql b/litellm-rust/crates/traces-clickhouse/query/lens_evidence.sql similarity index 100% rename from litellm-rust/crates/traces/query/lens_evidence.sql rename to litellm-rust/crates/traces-clickhouse/query/lens_evidence.sql diff --git a/litellm-rust/crates/traces/query/lens_sample.sql b/litellm-rust/crates/traces-clickhouse/query/lens_sample.sql similarity index 100% rename from litellm-rust/crates/traces/query/lens_sample.sql rename to litellm-rust/crates/traces-clickhouse/query/lens_sample.sql diff --git a/litellm-rust/crates/traces/query/list_traces.sql b/litellm-rust/crates/traces-clickhouse/query/list_traces.sql similarity index 78% rename from litellm-rust/crates/traces/query/list_traces.sql rename to litellm-rust/crates/traces-clickhouse/query/list_traces.sql index 740a05386e0..1598f04aba2 100644 --- a/litellm-rust/crates/traces/query/list_traces.sql +++ b/litellm-rust/crates/traces-clickhouse/query/list_traces.sql @@ -1,7 +1,7 @@ WITH page AS ( SELECT TraceId AS trace_id, hex(SHA256(concat(TeamId, char(0), ApiKeyHash, char(0), TraceId))) AS trace_ref, - TeamId AS team_id, ApiKeyHash AS api_key_hash, + if(length(groupUniqArrayArray(UserIds)) = 1, arrayElement(groupUniqArrayArray(UserIds), 1), '') AS user_id, TeamId AS team_id, ApiKeyHash AS api_key_hash, ifNull(any(RootName), '') AS name, any(ServiceName) AS service, ifNull(any(RootInput), '') AS input_preview, ifNull(any(RootStatus), '') AS status, toUnixTimestamp64Milli(min(StartTs)) AS start_ms, @@ -12,10 +12,14 @@ SELECT TraceId AS trace_id, sum(LlmCount) AS llm_calls, sum(ToolCount) AS tool_calls, sum(InputTokens) AS input_tokens, sum(OutputTokens) AS output_tokens, groupUniqArrayArray(Models) AS models, sum(ErrorCount) AS error_count, - arrayDistinct(groupArrayArray(RequestIds)) AS request_ids + arrayDistinct(if(sum(IdentifiedLlmCount) != sum(LlmCount), + arrayConcat(groupArrayArray(RequestIds), ['']), + groupArrayArray(RequestIds))) AS request_ids FROM agent_traces_by_key -WHERE (empty({team_ids:Array(String)}) OR TeamId IN {team_ids:Array(String)}) - AND ({api_key_hash:String} = '' OR ApiKeyHash = {api_key_hash:String}) +WHERE ({all_teams:UInt8} = 1 + OR ({user_id:String} != '' AND UserIds = [{user_id:String}]) + OR has({team_ids:Array(String)}, TeamId) + OR ({api_key_hash:String} != '' AND ApiKeyHash = {api_key_hash:String})) GROUP BY TeamId, ApiKeyHash, TraceId HAVING min(StartTs) >= fromUnixTimestamp64Milli({start_ms:Int64}) AND min(StartTs) < fromUnixTimestamp64Milli({end_ms:Int64}) diff --git a/litellm-rust/crates/traces-clickhouse/query/span_detail.sql b/litellm-rust/crates/traces-clickhouse/query/span_detail.sql new file mode 100644 index 00000000000..4da48e00d4b --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/query/span_detail.sql @@ -0,0 +1,26 @@ +SELECT o.SpanId AS span_id, o.Input AS input, + if(o.Output = '' AND o.ObservationType = 'agent', answer.output, o.Output) AS output, + o.SpanAttributes AS attributes +FROM otel_traces AS o +LEFT JOIN ( + SELECT TeamId, ApiKeyHash, ParentSpanId AS parent_span_id, argMax(Output, Timestamp) AS output + FROM otel_traces + WHERE TraceId = {trace_id:String} AND ParentSpanId = {span_id:String} + AND ObservationType = 'llm' AND Output != '' + AND ({all_teams:UInt8} = 1 + OR ({user_id:String} != '' AND UserId = {user_id:String}) + OR has({team_ids:Array(String)}, TeamId) + OR ({api_key_hash:String} != '' AND ApiKeyHash = {api_key_hash:String})) + AND ({trace_ref:String} = '' OR + hex(SHA256(concat(TeamId, char(0), ApiKeyHash, char(0), TraceId))) = {trace_ref:String}) + GROUP BY TeamId, ApiKeyHash, ParentSpanId +) AS answer ON answer.parent_span_id = o.SpanId + AND answer.TeamId = o.TeamId AND answer.ApiKeyHash = o.ApiKeyHash +WHERE o.TraceId = {trace_id:String} AND o.SpanId = {span_id:String} + AND ({all_teams:UInt8} = 1 + OR ({user_id:String} != '' AND o.UserId = {user_id:String}) + OR has({team_ids:Array(String)}, o.TeamId) + OR ({api_key_hash:String} != '' AND o.ApiKeyHash = {api_key_hash:String})) + AND ({trace_ref:String} = '' OR + hex(SHA256(concat(o.TeamId, char(0), o.ApiKeyHash, char(0), o.TraceId))) = {trace_ref:String}) +LIMIT 1 diff --git a/litellm-rust/crates/traces/query/span_error.sql b/litellm-rust/crates/traces-clickhouse/query/span_error.sql similarity index 71% rename from litellm-rust/crates/traces/query/span_error.sql rename to litellm-rust/crates/traces-clickhouse/query/span_error.sql index b4710006389..087962227a8 100644 --- a/litellm-rust/crates/traces/query/span_error.sql +++ b/litellm-rust/crates/traces-clickhouse/query/span_error.sql @@ -4,8 +4,10 @@ SELECT SpanId AS span_id, hex(SHA256(StatusMessage)) AS version FROM otel_traces WHERE TraceId = {trace_id:String} AND SpanId = {span_id:String} - AND (empty({team_ids:Array(String)}) OR TeamId IN {team_ids:Array(String)}) - AND ({api_key_hash:String} = '' OR ApiKeyHash = {api_key_hash:String}) + AND ({all_teams:UInt8} = 1 + OR ({user_id:String} != '' AND UserId = {user_id:String}) + OR has({team_ids:Array(String)}, TeamId) + OR ({api_key_hash:String} != '' AND ApiKeyHash = {api_key_hash:String})) AND ({trace_ref:String} = '' OR hex(SHA256(concat(TeamId, char(0), ApiKeyHash, char(0), TraceId))) = {trace_ref:String}) AND ({error_version:String} = '' OR hex(SHA256(StatusMessage)) = {error_version:String}) diff --git a/litellm-rust/crates/traces-clickhouse/query/spend_by_response_ids.sql b/litellm-rust/crates/traces-clickhouse/query/spend_by_response_ids.sql new file mode 100644 index 00000000000..eb132099ac5 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/query/spend_by_response_ids.sql @@ -0,0 +1,11 @@ +SELECT request_id, response_id, team_id, api_key, user, spend, + toUnixTimestamp64Milli(start_time) AS start_ms +FROM spend_logs FINAL +WHERE response_id IN {response_ids:Array(String)} + AND start_time >= fromUnixTimestamp64Milli({start_ms:Int64}) + AND start_time < fromUnixTimestamp64Milli({end_ms:Int64}) + AND ({all_teams:UInt8} = 1 + OR ({user_id:String} != '' AND user = {user_id:String}) + OR has({team_ids:Array(String)}, team_id) + OR ({api_key_hash:String} != '' AND api_key = {api_key_hash:String})) +ORDER BY start_time DESC diff --git a/litellm-rust/crates/traces-clickhouse/query/trace_identity.sql b/litellm-rust/crates/traces-clickhouse/query/trace_identity.sql new file mode 100644 index 00000000000..6b860065468 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/query/trace_identity.sql @@ -0,0 +1,9 @@ +SELECT hex(SHA256(concat(TeamId, char(0), ApiKeyHash, char(0), TraceId))) AS trace_ref +FROM otel_traces +WHERE TraceId = {trace_id:String} + AND ({all_teams:UInt8} = 1 + OR ({user_id:String} != '' AND UserId = {user_id:String}) + OR has({team_ids:Array(String)}, TeamId) + OR ({api_key_hash:String} != '' AND ApiKeyHash = {api_key_hash:String})) +GROUP BY TeamId, ApiKeyHash, TraceId +LIMIT 2 diff --git a/litellm-rust/crates/traces/query/trace_spans.sql b/litellm-rust/crates/traces-clickhouse/query/trace_spans.sql similarity index 74% rename from litellm-rust/crates/traces/query/trace_spans.sql rename to litellm-rust/crates/traces-clickhouse/query/trace_spans.sql index 24d227c4cac..ade1fdf0d86 100644 --- a/litellm-rust/crates/traces/query/trace_spans.sql +++ b/litellm-rust/crates/traces-clickhouse/query/trace_spans.sql @@ -7,11 +7,13 @@ SELECT o.SpanId AS span_id, o.ParentSpanId AS parent_span_id, o.SpanName AS name o.ServiceName AS service, o.InputPreview AS input_preview, o.Model AS model, o.InputTokens AS input_tokens, o.OutputTokens AS output_tokens, o.LiteLLMRequestId AS litellm_request_id, - o.TeamId AS team_id, o.ApiKeyHash AS api_key_hash + o.UserId AS user_id, o.TeamId AS team_id, o.ApiKeyHash AS api_key_hash FROM otel_traces AS o WHERE o.TraceId = {trace_id:String} - AND (empty({team_ids:Array(String)}) OR o.TeamId IN {team_ids:Array(String)}) - AND ({api_key_hash:String} = '' OR o.ApiKeyHash = {api_key_hash:String}) + AND ({all_teams:UInt8} = 1 + OR ({user_id:String} != '' AND o.UserId = {user_id:String}) + OR has({team_ids:Array(String)}, o.TeamId) + OR ({api_key_hash:String} != '' AND o.ApiKeyHash = {api_key_hash:String})) AND ({trace_ref:String} = '' OR hex(SHA256(concat(o.TeamId, char(0), o.ApiKeyHash, char(0), o.TraceId))) = {trace_ref:String}) ORDER BY o.Timestamp, o.EngineReceivedMs, o.StatusMessage diff --git a/litellm-rust/crates/traces/src/config.rs b/litellm-rust/crates/traces-clickhouse/src/config.rs similarity index 78% rename from litellm-rust/crates/traces/src/config.rs rename to litellm-rust/crates/traces-clickhouse/src/config.rs index ec88fca2e3f..362a0a88dc7 100644 --- a/litellm-rust/crates/traces/src/config.rs +++ b/litellm-rust/crates/traces-clickhouse/src/config.rs @@ -1,4 +1,5 @@ -use litellm_storage_clickhouse::{Error, Storage}; +use crate::Error; +use litellm_storage_clickhouse::Storage; #[derive(Clone)] pub struct Config { @@ -8,7 +9,7 @@ pub struct Config { impl Config { pub fn new(database: String, url: &str, retention_days: u32) -> Result { - crate::schema_statements(&database, retention_days)?; + super::schema_statements(&database, retention_days)?; Ok(Self { storage: Storage::new(database, url)?, retention_days, diff --git a/litellm-rust/crates/traces-clickhouse/src/error.rs b/litellm-rust/crates/traces-clickhouse/src/error.rs new file mode 100644 index 00000000000..1cdbedb5ff9 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/src/error.rs @@ -0,0 +1,37 @@ +#[derive(Debug, thiserror::Error)] +pub enum Error { + #[error("invalid ClickHouse insert row")] + InvalidRow, + #[error("invalid ClickHouse insert table")] + InvalidTable, + #[error("database must be a nonempty SQL identifier and retention must be positive")] + InvalidSchema, + #[error("unknown ClickHouse read query")] + InvalidQuery, + #[error("invalid ClickHouse query parameters")] + InvalidParameters, + #[error("ClickHouse returned an invalid or failed JSON query response")] + InvalidResponse, + #[error("ClickHouse insert exceeds the encoded size limit")] + InsertTooLarge, + #[error("ClickHouse schema setup failed with HTTP status {0}")] + SchemaFailed(u16), + #[error("ClickHouse schema setup transport failed")] + SchemaTransport, + #[error("trace SQL queries require a configured proxy master key")] + MissingSecret, + #[error("invalid trace query scope")] + InvalidScope, + #[error("trace SQL query concurrency limit exceeded")] + Busy, + #[error( + "ClickHouse reader provisioning failed with HTTP status {0}; the configured connection must be allowed to manage users, row policies, and SELECT grants on the trace tables" + )] + ProvisionFailed(u16), + #[error("ClickHouse reader provisioning transport failed")] + ProvisionTransport, + #[error(transparent)] + Storage(#[from] litellm_storage_clickhouse::Error), + #[error(transparent)] + Cached(#[from] std::sync::Arc), +} diff --git a/litellm-rust/crates/traces/src/insert.rs b/litellm-rust/crates/traces-clickhouse/src/insert.rs similarity index 98% rename from litellm-rust/crates/traces/src/insert.rs rename to litellm-rust/crates/traces-clickhouse/src/insert.rs index 01a1eecfd7b..ac9fb474ed0 100644 --- a/litellm-rust/crates/traces/src/insert.rs +++ b/litellm-rust/crates/traces-clickhouse/src/insert.rs @@ -12,7 +12,8 @@ use serde_json::Value; use sha2::{Digest, Sha256}; use time::{OffsetDateTime, format_description::well_known::Rfc3339}; -use crate::{Connection, Error, Shared}; +use super::{Connection, Error}; +use litellm_traces::Shared; const MAX_INSERT_BYTES: usize = 64 * 1024 * 1024; @@ -71,6 +72,7 @@ pub async fn insert_shared_rows( body, ) .await + .map_err(Error::from) } fn shared_rows(rows: Vec>) -> Vec { @@ -226,8 +228,8 @@ mod tests { use rstest::rstest; use serde_json::json; + use super::Error; use super::{shared_rows, write_rows}; - use crate::Error; #[rstest] fn encoded_limit_counts_utf8_bytes_across_rows() { diff --git a/litellm-rust/crates/traces-clickhouse/src/lib.rs b/litellm-rust/crates/traces-clickhouse/src/lib.rs new file mode 100644 index 00000000000..cd5877e4993 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/src/lib.rs @@ -0,0 +1,21 @@ +mod config; +mod error; +mod insert; +pub mod query; +mod query_access; +mod schema; +mod sql; +mod table; + +pub use config::Config; +pub use error::Error; +pub use insert::{InsertRow, InsertTable, encode_rows, insert_rows, insert_shared_rows}; +pub use litellm_storage_clickhouse::{Connection, Parameter}; +pub use litellm_traces::{QueryScope, ReadQuery}; +pub use query::{execute_read, query_help, query_sql}; +pub use query_access::QueryReaders; +pub use schema::{ + NORMALIZED_FIELD_DEFINITIONS, NormalizedFieldDefinition, ensure_schema, schema_statements, +}; +pub use sql::execute_named_read; +pub use table::TraceTable; diff --git a/litellm-rust/crates/traces-clickhouse/src/query.rs b/litellm-rust/crates/traces-clickhouse/src/query.rs new file mode 100644 index 00000000000..c862cebf556 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/src/query.rs @@ -0,0 +1,362 @@ +use std::collections::{BTreeMap, BTreeSet}; + +use crate::TraceTable; +use futures_util::{ + StreamExt, + stream::{self, TryStreamExt}, +}; +use litellm_http::Client; +use serde::{Deserialize, Serialize}; +use serde_json::{Value, json}; +use strum::IntoEnumIterator; + +use super::{Connection, Error, NORMALIZED_FIELD_DEFINITIONS, Parameter}; + +mod guide; +pub mod lens; +pub mod named; +mod number; + +const SAMPLE_ROWS: usize = 200; +const MAX_FIELDS: usize = 200; +const MAX_DEPTH: usize = 16; +const METADATA_SQL: &str = "SELECT metadata FROM spend_logs FINAL \ + WHERE start_time >= now() - INTERVAL 7 DAY AND length(metadata) <= 8192 \ + LIMIT 201"; +const METADATA_SCOPE: &str = "Up to 200 unordered rows from the last 7 days, excluding metadata larger than 8192 bytes; up to 200 paths and 16 levels. Missing paths may exist outside this sample. Array indexes are 1-based and describe sampled positions, not a fixed schema"; +const ATTRIBUTE_SCOPE: &str = "Distinct keys from up to 200 unordered spans in the last 7 days; up to 200 keys per map. Missing keys may exist outside this sample"; + +#[derive(Deserialize)] +struct Rows { + data: Vec, +} + +#[derive(Deserialize)] +struct MetadataRow { + metadata: String, +} + +#[derive(Deserialize)] +struct AttributeRow { + key: String, +} + +#[derive(Clone, Debug, Eq, Ord, PartialEq, PartialOrd, Serialize)] +#[serde(untagged)] +enum PathPart { + Key(String), + Index(usize), +} + +#[derive(Serialize)] +struct MetadataField { + path: Vec, + types: BTreeSet<&'static str>, + expression: String, +} + +#[derive(Deserialize, Serialize)] +struct ColumnSchema { + name: String, + #[serde(rename = "type")] + kind: String, + #[serde(flatten)] + details: BTreeMap, +} + +#[derive(Serialize)] +struct TableSchema { + name: &'static str, + columns: Vec, +} + +#[derive(Serialize)] +struct MetadataCatalog { + table: &'static str, + column: &'static str, + fields: Vec, + sampled_rows: usize, + invalid_json_rows: usize, + truncated: bool, + sample_sql: &'static str, + scope: &'static str, + #[serde(skip_serializing_if = "Option::is_none")] + error: Option, +} + +#[derive(Serialize)] +struct AttributeField { + key: String, + #[serde(rename = "type")] + kind: &'static str, + expression: String, +} + +#[derive(Serialize)] +struct AttributeCatalog { + table: &'static str, + column: &'static str, + fields: Vec, + truncated: bool, + discovery_sql: String, + scope: &'static str, + #[serde(skip_serializing_if = "Option::is_none")] + error: Option, +} + +pub async fn execute_read( + client: &Client, + connection: &Connection, + sql: &str, + parameters: &BTreeMap, +) -> Result { + litellm_storage_clickhouse::execute_read(client, connection, sql, parameters) + .await + .map_err(Error::from) +} + +pub async fn query_sql( + client: &Client, + connection: &Connection, + sql: &str, +) -> Result { + execute_read(client, connection, sql, &BTreeMap::new()).await +} + +async fn rows( + client: &Client, + connection: &Connection, + sql: &str, +) -> Result, Error> { + let body = query_sql(client, connection, sql).await?; + serde_json::from_str::>(&body) + .map(|result| result.data) + .map_err(|_| Error::InvalidResponse) +} + +fn literal(value: &str) -> String { + format!("'{}'", value.replace('\\', "\\\\").replace('\'', "\\'")) +} + +fn metadata_expression(path: &[PathPart]) -> String { + let arguments = path + .iter() + .map(|part| match part { + PathPart::Key(key) => literal(key), + PathPart::Index(index) => index.to_string(), + }) + .collect::>() + .join(", "); + format!("JSONExtractRaw(metadata, {arguments})") +} + +fn discover( + value: &Value, + path: Vec, + fields: &mut BTreeMap, BTreeSet<&'static str>>, +) -> bool { + if path.len() > MAX_DEPTH || (fields.len() >= MAX_FIELDS && !fields.contains_key(&path)) { + return true; + } + if !path.is_empty() { + let kind = match value { + Value::Null => "null", + Value::Bool(_) => "boolean", + Value::Number(number) if number.is_i64() || number.is_u64() => "integer", + Value::Number(_) => "number", + Value::String(_) => "string", + Value::Array(_) => "array", + Value::Object(_) => "object", + }; + fields.entry(path.clone()).or_default().insert(kind); + } + match value { + Value::Object(object) => object.iter().fold(false, |limited, (key, value)| { + let child = path + .iter() + .cloned() + .chain([PathPart::Key(key.clone())]) + .collect(); + discover(value, child, fields) | limited + }), + Value::Array(array) => array + .iter() + .enumerate() + .fold(false, |limited, (index, value)| { + let child = path + .iter() + .cloned() + .chain([PathPart::Index(index + 1)]) + .collect(); + discover(value, child, fields) | limited + }), + _ => false, + } +} + +fn metadata_catalog(sample: &[MetadataRow]) -> MetadataCatalog { + let (fields, limited, invalid_rows) = sample.iter().take(SAMPLE_ROWS).fold( + (BTreeMap::new(), sample.len() > SAMPLE_ROWS, 0), + |(fields, limited, invalid_rows), row| match serde_json::from_str::(&row.metadata) { + Ok(value) => { + let mut fields = fields; + let limited = limited | discover(&value, Vec::new(), &mut fields); + (fields, limited, invalid_rows) + } + Err(_) => (fields, limited, invalid_rows + 1), + }, + ); + let fields: Vec<_> = fields + .into_iter() + .map(|(path, types)| MetadataField { + expression: metadata_expression(&path), + path, + types, + }) + .collect(); + MetadataCatalog { + table: "spend_logs", + column: "metadata", + fields, + sampled_rows: sample.len().min(SAMPLE_ROWS), + invalid_json_rows: invalid_rows, + truncated: limited, + sample_sql: METADATA_SQL, + error: None, + scope: METADATA_SCOPE, + } +} + +pub async fn query_help(client: &Client, connection: &Connection) -> Result { + let tables = stream::iter(TraceTable::iter()) + .then(|table| async move { + Ok::<_, Error>(TableSchema { + name: table.into(), + columns: rows::( + client, + connection, + &format!("DESCRIBE TABLE {table}"), + ) + .await?, + }) + }) + .try_collect::>() + .await?; + let metadata = match rows::(client, connection, METADATA_SQL).await { + Ok(sample) => metadata_catalog(&sample), + Err(error) => MetadataCatalog { + error: Some(error.to_string()), + truncated: true, + ..metadata_catalog(&[]) + }, + }; + let attributes = stream::iter(["SpanAttributes", "ResourceAttributes"]) + .then(|column| async move { + let sql = format!( + "SELECT DISTINCT arrayJoin(mapKeys({column})) AS key FROM \ + (SELECT {column} FROM otel_traces WHERE Timestamp >= now() - INTERVAL 7 DAY \ + LIMIT 200) ORDER BY key LIMIT 201" + ); + let (keys, error) = match rows::(client, connection, &sql).await { + Ok(keys) => (keys, None), + Err(error) => (Vec::new(), Some(error.to_string())), + }; + let fields = keys + .iter() + .take(MAX_FIELDS) + .map(|row| AttributeField { + key: row.key.clone(), + kind: "String", + expression: format!("{column}[{}]", literal(&row.key)), + }) + .collect(); + AttributeCatalog { + table: "otel_traces", + column, + fields, + truncated: error.is_some() || keys.len() > MAX_FIELDS, + discovery_sql: sql, + scope: ATTRIBUTE_SCOPE, + error, + } + }) + .collect::>() + .await; + let guide = guide::QueryGuide { + tables: &tables, + normalized_fields: &NORMALIZED_FIELD_DEFINITIONS, + metadata: &metadata, + attributes: &attributes, + }; + Ok(json!({ + "dialect": "ClickHouse SQL", + "access": "Request-log visibility enforced by ClickHouse row policies; proxy admins see all rows, users see their own rows and permitted teams, and callers without user identity see their own key rows", + "response": "ClickHouse JSON envelope: meta, data, rows, statistics; 64-bit integers may be strings", + "tables": tables, + "normalized_fields": NORMALIZED_FIELD_DEFINITIONS.iter().map(|field| json!({ + "table": "otel_traces", "name": field.name, "column": field.clickhouse_column, + "type": field.clickhouse_type, "meaning": field.meaning + })).collect::>(), + "metadata": metadata, + "attributes": attributes, + "relationships": [{ + "left": "otel_traces.LiteLLMRequestId", "right": "spend_logs.response_id", + "additional_predicates": "otel_traces.TeamId = spend_logs.team_id AND (otel_traces.TeamId != '' OR (otel_traces.UserId != '' AND otel_traces.UserId = spend_logs.user) OR (otel_traces.ApiKeyHash != '' AND otel_traces.ApiKeyHash = spend_logs.api_key))", + "meaning": "The normalized ID is the response ID, not request_id. Cached requests can share response_id; joins may return multiple spend rows" + }], + "examples": guide.examples()?, + "gotchas": guide.gotchas()?, + "guide": guide::render(&guide)?, + }).to_string()) +} + +#[cfg(test)] +mod tests { + use super::*; + use rstest::rstest; + + #[rstest] + fn metadata_discovery_preserves_mixed_types_and_reports_invalid_rows() { + let sample = [ + MetadataRow { + metadata: r#"{"x": 1}"#.into(), + }, + MetadataRow { + metadata: r#"{"x": "one"}"#.into(), + }, + MetadataRow { + metadata: "invalid".into(), + }, + ]; + let catalog = json!(metadata_catalog(&sample)); + assert_eq!( + catalog["fields"], + json!([{ + "path": ["x"], "types": ["integer", "string"], "expression": "JSONExtractRaw(metadata, 'x')" + }]) + ); + assert_eq!(catalog["invalid_json_rows"], 1); + assert_eq!(catalog["sampled_rows"], sample.len()); + } + + #[rstest] + #[case::rows(SAMPLE_ROWS + 1, 1)] + #[case::paths(1, MAX_FIELDS + 1)] + fn metadata_discovery_reports_truncation(#[case] row_count: usize, #[case] field_count: usize) { + let metadata: BTreeMap<_, _> = (0..field_count) + .map(|index| (format!("field{index}"), index)) + .collect(); + let sample: Vec<_> = (0..row_count) + .map(|_| MetadataRow { + metadata: json!(metadata).to_string(), + }) + .collect(); + let catalog = json!(metadata_catalog(&sample)); + assert_eq!(catalog["truncated"], true); + assert_eq!(catalog["sampled_rows"], row_count.min(SAMPLE_ROWS)); + assert_eq!( + catalog["fields"].as_array().unwrap().len(), + field_count.min(MAX_FIELDS) + ); + } +} diff --git a/litellm-rust/crates/traces/src/query/guide.rs b/litellm-rust/crates/traces-clickhouse/src/query/guide.rs similarity index 100% rename from litellm-rust/crates/traces/src/query/guide.rs rename to litellm-rust/crates/traces-clickhouse/src/query/guide.rs diff --git a/litellm-rust/crates/traces-clickhouse/src/query/lens.rs b/litellm-rust/crates/traces-clickhouse/src/query/lens.rs new file mode 100644 index 00000000000..56242cc3c62 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/src/query/lens.rs @@ -0,0 +1,173 @@ +use litellm_storage_clickhouse::Query; +use serde::{Deserialize, Serialize}; + +#[derive(Debug, Deserialize, Serialize)] +pub struct LensAccessParams { + #[serde(deserialize_with = "super::number::deserialize")] + pub all_teams: u8, + pub team: String, + pub key_hash: String, +} + +pub struct LensAvailability; + +#[derive(Debug, Deserialize, Serialize)] +pub struct LensAvailabilityParams { + #[serde(flatten)] + pub access: LensAccessParams, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct LensAvailabilityRow { + #[serde(deserialize_with = "super::number::deserialize")] + pub traces: u8, + #[serde(deserialize_with = "super::number::deserialize")] + pub requests: u8, +} + +impl Query for LensAvailability { + type Params = LensAvailabilityParams; + type Row = LensAvailabilityRow; + + const SQL: &'static str = include_str!("../../query/lens_availability.sql"); +} + +pub struct LensAgents; + +#[derive(Debug, Deserialize, Serialize)] +pub struct LensAgentsParams { + #[serde(flatten)] + pub access: LensAccessParams, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct LensAgentsRow { + pub agent_name: String, +} + +impl Query for LensAgents { + type Params = LensAgentsParams; + type Row = LensAgentsRow; + + const SQL: &'static str = include_str!("../../query/lens_agents.sql"); +} + +pub struct LensSample; + +#[derive(Debug, Deserialize, Serialize)] +pub struct LensSampleParams { + #[serde(flatten)] + pub access: LensAccessParams, + pub source: String, + #[serde(deserialize_with = "super::number::deserialize")] + pub start: u64, + #[serde(deserialize_with = "super::number::deserialize")] + pub end: u64, + pub agent_name: String, + pub service: String, + pub filter_keys: Vec, + pub filter_values: Vec, + pub selected_team: String, + pub execution_ids: Vec, + #[serde(deserialize_with = "super::number::deserialize")] + pub sample_cap: u64, + #[serde(deserialize_with = "super::number::deserialize")] + pub sample_percent: f64, + #[serde(deserialize_with = "super::number::deserialize")] + pub preview: u8, + pub after: String, + #[serde(deserialize_with = "super::number::deserialize")] + pub limit: u32, + #[serde(deserialize_with = "super::number::deserialize")] + pub offset: u64, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct LensSampleRow { + pub source: String, + pub trace_id: String, + pub team_id: String, + pub trace_ref: String, + pub name: String, + pub start_time: String, + #[serde(deserialize_with = "super::number::deserialize")] + pub span_count: u64, + #[serde(deserialize_with = "super::number::deserialize")] + pub root_seen: u8, + pub service: String, + pub attributes: Vec<(String, String)>, + #[serde(deserialize_with = "super::number::deserialize")] + pub eligible: u64, + #[serde(deserialize_with = "super::number::deserialize")] + pub position: u64, + #[serde(deserialize_with = "super::number::deserialize")] + pub selected: f64, + pub selection_key: String, +} + +impl Query for LensSample { + type Params = LensSampleParams; + type Row = LensSampleRow; + + const SQL: &'static str = include_str!("../../query/lens_sample.sql"); +} + +pub struct LensContent; + +#[derive(Debug, Deserialize, Serialize)] +pub struct LensContentParams { + #[serde(flatten)] + pub access: LensAccessParams, + pub source: String, + pub id: String, + pub record_team: String, + pub trace_ref: String, + pub cursor: String, + #[serde(deserialize_with = "super::number::deserialize")] + pub offset: u32, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct LensContentRow { + pub span_id: String, + pub parent_span_id: String, + pub name: String, + pub kind: String, + pub content: String, + #[serde(deserialize_with = "super::number::deserialize")] + pub truncated: u8, +} + +impl Query for LensContent { + type Params = LensContentParams; + type Row = LensContentRow; + + const SQL: &'static str = include_str!("../../query/lens_content.sql"); +} + +pub struct LensEvidence; + +#[derive(Debug, Deserialize, Serialize)] +pub struct LensEvidenceParams { + #[serde(flatten)] + pub access: LensAccessParams, + pub source: String, + pub id: String, + pub record_team: String, + pub trace_ref: String, + pub span: String, + pub quote: String, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct LensEvidenceRow { + #[serde(deserialize_with = "super::number::deserialize")] + pub count: u64, +} + +impl Query for LensEvidence { + type Params = LensEvidenceParams; + type Row = LensEvidenceRow; + + const SQL: &'static str = include_str!("../../query/lens_evidence.sql"); +} diff --git a/litellm-rust/crates/traces-clickhouse/src/query/named.rs b/litellm-rust/crates/traces-clickhouse/src/query/named.rs new file mode 100644 index 00000000000..46ea339edd5 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/src/query/named.rs @@ -0,0 +1,320 @@ +use litellm_storage_clickhouse::Query; +use litellm_traces::query::named as contracts; +use serde::{Deserialize, Serialize}; + +pub use contracts::ReadAccessParams; + +#[derive(Deserialize, Serialize)] +#[serde(remote = "contracts::ListTracesParams")] +struct ListTracesParamsEncoding { + #[serde(flatten)] + pub access: contracts::ReadAccessParams, + #[serde(deserialize_with = "super::number::deserialize")] + pub start_ms: i64, + #[serde(deserialize_with = "super::number::deserialize")] + pub end_ms: i64, + #[serde(deserialize_with = "super::number::deserialize")] + pub cursor_ms: i64, + pub cursor_trace_id: String, + #[serde(deserialize_with = "super::number::deserialize")] + pub limit: u32, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct ListTracesParams( + #[serde(with = "ListTracesParamsEncoding")] pub contracts::ListTracesParams, +); + +impl From for ListTracesParams { + fn from(value: contracts::ListTracesParams) -> Self { + Self(value) + } +} + +#[derive(Deserialize, Serialize)] +#[serde(remote = "contracts::ListTracesRow")] +struct ListTracesRowEncoding { + pub trace_id: String, + pub trace_ref: String, + pub team_id: String, + pub api_key_hash: String, + pub user_id: String, + pub name: String, + pub service: String, + pub input_preview: String, + pub status: String, + #[serde(deserialize_with = "super::number::deserialize")] + pub start_ms: i64, + #[serde(deserialize_with = "super::number::deserialize")] + pub duration_ms: i64, + #[serde(deserialize_with = "super::number::deserialize")] + pub span_count: u64, + #[serde(deserialize_with = "super::number::deserialize")] + pub agent_count: u64, + #[serde(deserialize_with = "super::number::deserialize")] + pub agent_invocations: u64, + #[serde(default)] + pub agent_names: Vec, + #[serde(default)] + pub frameworks: Vec, + #[serde(deserialize_with = "super::number::deserialize")] + pub llm_calls: u64, + #[serde(deserialize_with = "super::number::deserialize")] + pub tool_calls: u64, + #[serde(deserialize_with = "super::number::deserialize")] + pub input_tokens: u64, + #[serde(deserialize_with = "super::number::deserialize")] + pub output_tokens: u64, + pub models: Vec, + #[serde(deserialize_with = "super::number::deserialize")] + pub error_count: u64, + pub request_ids: Vec, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct ListTracesRow(#[serde(with = "ListTracesRowEncoding")] pub contracts::ListTracesRow); + +pub use contracts::TraceSpansParams; + +#[derive(Deserialize, Serialize)] +#[serde(remote = "contracts::TraceSpansRow")] +struct TraceSpansRowEncoding { + pub span_id: String, + pub parent_span_id: String, + pub name: String, + #[serde(rename = "type")] + pub kind: String, + pub agent: String, + #[serde(default)] + pub framework: String, + pub status: String, + pub status_message: String, + #[serde(deserialize_with = "super::number::deserialize")] + pub error_truncated: u8, + #[serde(deserialize_with = "super::number::deserialize")] + pub start_ns: i64, + #[serde(deserialize_with = "super::number::deserialize")] + pub duration_ns: u64, + pub service: String, + pub input_preview: String, + pub model: String, + #[serde(deserialize_with = "super::number::deserialize")] + pub input_tokens: u32, + #[serde(deserialize_with = "super::number::deserialize")] + pub output_tokens: u32, + pub litellm_request_id: String, + pub team_id: String, + pub api_key_hash: String, + pub user_id: String, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct TraceSpansRow(#[serde(with = "TraceSpansRowEncoding")] pub contracts::TraceSpansRow); + +pub use contracts::SpanDetailParams; + +pub use contracts::SpanDetailRow; + +#[derive(Deserialize, Serialize)] +#[serde(remote = "contracts::SpanErrorParams")] +struct SpanErrorParamsEncoding { + #[serde(flatten)] + pub access: contracts::ReadAccessParams, + pub trace_id: String, + pub trace_ref: String, + pub span_id: String, + #[serde(deserialize_with = "super::number::deserialize")] + pub error_offset: u64, + pub error_version: String, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct SpanErrorParams( + #[serde(with = "SpanErrorParamsEncoding")] pub contracts::SpanErrorParams, +); + +impl From for SpanErrorParams { + fn from(value: contracts::SpanErrorParams) -> Self { + Self(value) + } +} + +#[derive(Deserialize, Serialize)] +#[serde(remote = "contracts::SpanErrorRow")] +struct SpanErrorRowEncoding { + pub span_id: String, + pub message: String, + #[serde(deserialize_with = "super::number::deserialize")] + pub total_chars: u64, + pub version: String, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct SpanErrorRow(#[serde(with = "SpanErrorRowEncoding")] pub contracts::SpanErrorRow); + +#[derive(Deserialize, Serialize)] +#[serde(remote = "contracts::SpendByResponseIdsParams")] +struct SpendByResponseIdsParamsEncoding { + #[serde(flatten)] + pub access: contracts::ReadAccessParams, + pub response_ids: Vec, + #[serde(deserialize_with = "super::number::deserialize")] + pub start_ms: i64, + #[serde(deserialize_with = "super::number::deserialize")] + pub end_ms: i64, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct SpendByResponseIdsParams( + #[serde(with = "SpendByResponseIdsParamsEncoding")] pub contracts::SpendByResponseIdsParams, +); + +impl From for SpendByResponseIdsParams { + fn from(value: contracts::SpendByResponseIdsParams) -> Self { + Self(value) + } +} + +#[derive(Deserialize, Serialize)] +#[serde(remote = "contracts::SpendByResponseIdsRow")] +struct SpendByResponseIdsRowEncoding { + pub request_id: String, + pub response_id: String, + pub team_id: String, + pub api_key: String, + pub user: String, + #[serde(deserialize_with = "super::number::deserialize")] + pub spend: f64, + #[serde(deserialize_with = "super::number::deserialize")] + pub start_ms: i64, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct SpendByResponseIdsRow( + #[serde(with = "SpendByResponseIdsRowEncoding")] pub contracts::SpendByResponseIdsRow, +); + +pub struct ListTraces; + +impl Query for ListTraces { + type Params = ListTracesParams; + type Row = ListTracesRow; + + const SQL: &'static str = include_str!("../../query/list_traces.sql"); +} + +pub struct TraceSpans; + +impl Query for TraceSpans { + type Params = TraceSpansParams; + type Row = TraceSpansRow; + + const SQL: &'static str = include_str!("../../query/trace_spans.sql"); +} + +pub struct SpanDetail; + +impl Query for SpanDetail { + type Params = SpanDetailParams; + type Row = SpanDetailRow; + + const SQL: &'static str = include_str!("../../query/span_detail.sql"); +} + +pub struct SpanError; + +impl Query for SpanError { + type Params = SpanErrorParams; + type Row = SpanErrorRow; + + const SQL: &'static str = include_str!("../../query/span_error.sql"); +} + +pub struct SpendByResponseIds; + +impl Query for SpendByResponseIds { + type Params = SpendByResponseIdsParams; + type Row = SpendByResponseIdsRow; + + const SQL: &'static str = include_str!("../../query/spend_by_response_ids.sql"); +} + +pub use contracts::{TraceIdentityParams, TraceIdentityRow}; + +pub struct TraceIdentity; + +impl Query for TraceIdentity { + type Params = TraceIdentityParams; + type Row = TraceIdentityRow; + const SQL: &'static str = include_str!("../../query/trace_identity.sql"); +} + +#[cfg(test)] +mod tests { + use super::*; + use rstest::rstest; + use serde_json::{Value, json}; + + fn round_trip(wire: Value, quoted: bool) { + let encoded = Value::Object( + wire.as_object() + .unwrap() + .iter() + .map(|(name, value)| { + let encoded = if quoted && value.is_number() && name != "all_teams" { + json!(value.to_string()) + } else { + value.clone() + }; + (name.clone(), encoded) + }) + .collect(), + ); + let decoded: T = serde_json::from_value(encoded).unwrap(); + assert_eq!(serde_json::to_value(decoded).unwrap(), wire); + } + + #[rstest] + #[case::unquoted(false)] + #[case::quoted(true)] + fn rows_decode_into_neutral_contracts(#[case] quoted: bool) { + round_trip::( + json!({"trace_id": "trace", "trace_ref": "ref", "team_id": "team", "api_key_hash": "key", "user_id": "user", "name": "agent", "service": "service", "input_preview": "input", "status": "ok", "start_ms": -1, "duration_ms": 20, "span_count": u64::MAX, "agent_count": 1, "agent_invocations": 2, "agent_names": ["agent"], "frameworks": ["claude-agent-sdk"], "llm_calls": 3, "tool_calls": 4, "input_tokens": 5, "output_tokens": 6, "models": ["model"], "error_count": 0, "request_ids": ["request"]}), + quoted, + ); + round_trip::( + json!({"span_id": "span", "parent_span_id": "parent", "name": "agent", "type": "agent", "agent": "agent", "framework": "claude-agent-sdk", "status": "error", "status_message": "error", "error_truncated": 1, "start_ns": -1, "duration_ns": u64::MAX, "service": "service", "input_preview": "input", "model": "model", "input_tokens": u32::MAX, "output_tokens": 6, "litellm_request_id": "request", "team_id": "team", "api_key_hash": "key", "user_id": "user"}), + quoted, + ); + round_trip::( + json!({"span_id": "span", "input": "input", "output": "output", "attributes": {"count": "42"}}), + quoted, + ); + round_trip::( + json!({"span_id": "span", "message": "error", "total_chars": u64::MAX, "version": "version"}), + quoted, + ); + round_trip::( + json!({"request_id": "request", "response_id": "response", "team_id": "team", "api_key": "key", "user": "user", "spend": 0.125, "start_ms": -1}), + quoted, + ); + } + + #[rstest] + #[case::unquoted(false)] + #[case::quoted(true)] + fn parameters_preserve_flattened_multi_team_access(#[case] quoted: bool) { + round_trip::( + json!({"all_teams": 0, "user_id": "user", "team_ids": ["team-a", "team-b"], "api_key_hash": "key", "start_ms": -1, "end_ms": 10, "cursor_ms": 0, "cursor_trace_id": "", "limit": u32::MAX}), + quoted, + ); + round_trip::( + json!({"all_teams": 0, "user_id": "", "team_ids": [], "api_key_hash": "key", "trace_id": "trace", "trace_ref": "ref", "span_id": "span", "error_offset": u64::MAX, "error_version": "version"}), + quoted, + ); + round_trip::( + json!({"all_teams": 0, "user_id": "user", "team_ids": ["team-a", "team-b"], "api_key_hash": "", "response_ids": ["response"], "start_ms": -1, "end_ms": 10}), + quoted, + ); + } +} diff --git a/litellm-rust/crates/traces-clickhouse/src/query/number.rs b/litellm-rust/crates/traces-clickhouse/src/query/number.rs new file mode 100644 index 00000000000..f6af195e7a3 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/src/query/number.rs @@ -0,0 +1,44 @@ +use serde::{Deserialize, Deserializer, de::DeserializeOwned}; + +pub(super) fn deserialize<'de, D, T>(deserializer: D) -> Result +where + D: Deserializer<'de>, + T: DeserializeOwned, +{ + #[derive(Deserialize)] + #[serde(untagged)] + enum Number { + Quoted(String), + Unquoted(serde_json::Number), + } + match Number::deserialize(deserializer)? { + Number::Quoted(value) => serde_json::from_str(&value), + Number::Unquoted(value) => serde_json::from_value(serde_json::Value::Number(value)), + } + .map_err(serde::de::Error::custom) +} + +#[cfg(test)] +mod tests { + use crate::query::named::SpanErrorRow; + use rstest::rstest; + + #[rstest] + #[case::quoted_max(serde_json::json!(u64::MAX.to_string()), Some(u64::MAX))] + #[case::unquoted_max(serde_json::json!(u64::MAX), Some(u64::MAX))] + #[case::overflow(serde_json::json!("18446744073709551616"), None)] + #[case::negative(serde_json::json!(-1), None)] + #[case::fraction(serde_json::json!(1.5), None)] + fn numeric_rows_enforce_integer_range( + #[case] value: serde_json::Value, + #[case] expected: Option, + ) { + let row = serde_json::from_value::(serde_json::json!({ + "span_id": "span", "message": "error", "total_chars": value, "version": "hash" + })); + match expected { + Some(value) => assert_eq!(row.unwrap().0.total_chars, value), + None => assert!(row.is_err()), + } + } +} diff --git a/litellm-rust/crates/traces-clickhouse/src/query_access.rs b/litellm-rust/crates/traces-clickhouse/src/query_access.rs new file mode 100644 index 00000000000..94ead18dd94 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/src/query_access.rs @@ -0,0 +1,237 @@ +use std::{sync::Arc, time::Duration}; + +use hmac::{Hmac, Mac}; +use litellm_http::Client; +use litellm_traces::QueryScope; +use moka::future::Cache; +use strum::IntoEnumIterator; + +use sha2::{Digest, Sha256}; +use tokio::sync::{OwnedSemaphorePermit, Semaphore}; + +use super::{Connection, Error, TraceTable}; + +#[derive(Clone)] +pub struct QueryReaders { + writer: Connection, + database: String, + readers: Cache, + slots: Arc, +} + +impl QueryReaders { + pub fn new(writer: Connection, database: String) -> Self { + Self { + writer, + database, + readers: Cache::builder().max_capacity(1024).build(), + slots: Arc::new(Semaphore::new(8)), + } + } + + pub fn acquire(&self) -> Result { + self.slots + .clone() + .try_acquire_owned() + .map_err(|_| Error::Busy) + } + + pub async fn connection( + &self, + client: &Client, + scope: &QueryScope, + secret: &str, + ) -> Result { + scope.validate().map_err(|_| Error::InvalidScope)?; + if secret.is_empty() { + return Err(Error::MissingSecret); + } + let identity = serde_json::to_vec(&("litellm_trace_reader_v1", &self.database, scope)) + .map_err(|_| Error::InvalidScope)?; + let user = format!("litellm_traces_{:x}", Sha256::digest(&identity)); + let password = credential(secret, b"password", &identity)?; + self.readers + .try_get_with( + user.clone(), + self.provision(client, scope, &user, &password), + ) + .await + .map_err(Error::Cached) + } + + async fn provision( + &self, + client: &Client, + scope: &QueryScope, + user: &str, + password: &str, + ) -> Result { + let database = &self.database; + if database.is_empty() + || !database + .bytes() + .all(|c| c.is_ascii_alphanumeric() || c == b'_') + { + return Err(Error::InvalidScope); + } + let password_hash = format!("{:x}", Sha256::digest(password)); + self.execute( + client, + format!( + "CREATE USER IF NOT EXISTS {user} IDENTIFIED WITH sha256_hash BY '{password_hash}' \ + SETTINGS readonly = 1 CONST, max_execution_time = 10 CONST, \ + max_result_rows = 1000 CONST, max_result_bytes = 4194304 CONST, \ + result_overflow_mode = 'throw' CONST, max_memory_usage = 268435456 CONST, \ + max_threads = 2 CONST, max_concurrent_queries_for_user = 8 CONST" + ), + ) + .await?; + self.execute( + client, + format!("ALTER USER {user} IDENTIFIED WITH sha256_hash BY '{password_hash}'"), + ) + .await?; + for table in TraceTable::iter() { + let predicate = predicate(scope, table); + self.execute( + client, + format!( + "CREATE ROW POLICY IF NOT EXISTS {user}_allow ON `{database}`.{table} \ + USING 1 TO {user}" + ), + ) + .await?; + self.execute( + client, + format!( + "CREATE ROW POLICY IF NOT EXISTS {user}_scope ON `{database}`.{table} \ + AS RESTRICTIVE USING {predicate} TO {user}" + ), + ) + .await?; + } + for table in TraceTable::iter() { + self.execute( + client, + format!("GRANT SELECT ON `{database}`.{table} TO {user}"), + ) + .await?; + } + Connection::configured( + &self.writer.url()[..url::Position::AfterPath], + database, + user, + password, + ) + .map_err(Error::Storage) + } + + async fn execute(&self, client: &Client, sql: String) -> Result<(), Error> { + let response = client + .post(self.writer.url().clone()) + .timeout(Duration::from_secs(15)) + .body(sql) + .send() + .await + .map_err(|_| Error::ProvisionTransport)?; + if !response.status().is_success() { + return Err(Error::ProvisionFailed(response.status().as_u16())); + } + Ok(()) + } +} + +fn predicate(scope: &QueryScope, table: TraceTable) -> String { + let (team, key) = match table { + TraceTable::OtelTraces | TraceTable::AgentTracesByKey => ("TeamId", "ApiKeyHash"), + TraceTable::SpendLogs => ("team_id", "api_key"), + }; + match scope { + QueryScope::Admin => "1".to_owned(), + QueryScope::Logs { + user_id, + team_ids, + api_key_hash, + } => { + let owner = literal(user_id); + let user_clause = match table { + TraceTable::OtelTraces => format!("UserId = {owner}"), + TraceTable::AgentTracesByKey => format!("UserIds = [{owner}]"), + TraceTable::SpendLogs => format!("user = {owner}"), + }; + let teams = team_ids + .iter() + .map(|value| literal(value)) + .collect::>() + .join(", "); + let team_clause = if team_ids.is_empty() { + "0".to_owned() + } else { + format!("{team} IN ({teams})") + }; + format!( + "({owner} != '' AND {user_clause}) OR ({team_clause}) OR ({hash} != '' AND {key} = {hash})", + owner = owner, + hash = literal(api_key_hash), + ) + } + QueryScope::Team { team_id } => format!("{team} = {}", literal(team_id)), + QueryScope::Key { + team_id, + api_key_hash, + } => format!( + "{team} = {} AND {key} = {}", + literal(team_id), + literal(api_key_hash) + ), + } +} + +fn credential(secret: &str, purpose: &[u8], identity: &[u8]) -> Result { + let mut mac = + Hmac::::new_from_slice(secret.as_bytes()).map_err(|_| Error::MissingSecret)?; + mac.update(purpose); + mac.update(identity); + Ok(format!("{:x}", mac.finalize().into_bytes())) +} + +fn literal(value: &str) -> String { + format!("'{}'", value.replace('\\', "\\\\").replace('\'', "\\'")) +} + +#[cfg(test)] +mod tests { + use super::*; + use rstest::rstest; + + #[rstest] + #[case::otel(TraceTable::OtelTraces, "TeamId", "ApiKeyHash")] + #[case::agent(TraceTable::AgentTracesByKey, "TeamId", "ApiKeyHash")] + #[case::spend(TraceTable::SpendLogs, "team_id", "api_key")] + fn predicates_preserve_scope_and_escape_values( + #[case] table: TraceTable, + #[case] team: &str, + #[case] key: &str, + ) { + assert_eq!(predicate(&QueryScope::Admin, table), "1"); + assert_eq!( + predicate( + &QueryScope::Team { + team_id: "team'\\".into() + }, + table + ), + format!("{team} = 'team\\'\\\\'") + ); + assert_eq!( + predicate( + &QueryScope::Key { + team_id: "".into(), + api_key_hash: "key'\\".into() + }, + table + ), + format!("{team} = '' AND {key} = 'key\\'\\\\'") + ); + } +} diff --git a/litellm-rust/crates/traces-clickhouse/src/schema.rs b/litellm-rust/crates/traces-clickhouse/src/schema.rs new file mode 100644 index 00000000000..4ebfbbf595f --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/src/schema.rs @@ -0,0 +1,136 @@ +use litellm_http::Client; +use litellm_migrate::Migration; +use serde::Serialize; +use std::time::Duration; + +use super::Connection; +use super::Error; + +const SCHEMA_REQUEST_TIMEOUT: Duration = Duration::from_secs(30); + +const MIGRATIONS: &[Migration] = litellm_migrate::migrate!("migrations"); + +pub fn schema_statements(database: &str, retention_days: u32) -> Result, Error> { + if database.is_empty() + || !database + .bytes() + .all(|c| c.is_ascii_alphanumeric() || c == b'_') + || retention_days == 0 + { + return Err(Error::InvalidSchema); + } + let database = format!("`{database}`"); + Ok( + std::iter::once(format!("CREATE DATABASE IF NOT EXISTS {database}")) + .chain(MIGRATIONS.iter().map(|migration| { + migration + .sql + .replace("{database}", &database) + .replace("{retention_days}", &retention_days.to_string()) + })) + .collect(), + ) +} + +pub async fn ensure_schema( + client: &Client, + connection: &Connection, + database: &str, + retention_days: u32, +) -> Result<(), Error> { + ensure_schema_with_timeout( + client, + connection, + database, + retention_days, + SCHEMA_REQUEST_TIMEOUT, + ) + .await +} + +async fn ensure_schema_with_timeout( + client: &Client, + connection: &Connection, + database: &str, + retention_days: u32, + request_timeout: Duration, +) -> Result<(), Error> { + for statement in schema_statements(database, retention_days)? { + let response = client + .post(connection.url().clone()) + .timeout(request_timeout) + .body(statement) + .send() + .await + .map_err(|_| Error::SchemaTransport)?; + if !response.status().is_success() { + return Err(Error::SchemaFailed(response.status().as_u16())); + } + } + Ok(()) +} + +#[derive(Clone, Copy, Debug, Eq, PartialEq, Serialize)] +pub struct NormalizedFieldDefinition { + pub name: &'static str, + pub clickhouse_column: &'static str, + pub clickhouse_type: &'static str, + pub meaning: &'static str, +} + +pub const NORMALIZED_FIELD_DEFINITIONS: [NormalizedFieldDefinition; 9] = [ + NormalizedFieldDefinition { + name: "observation_type", + clickhouse_column: "ObservationType", + clickhouse_type: "LowCardinality(String)", + meaning: "Agent, LLM, tool, chain, or framework span", + }, + NormalizedFieldDefinition { + name: "agent_name", + clickhouse_column: "AgentName", + clickhouse_type: "LowCardinality(String)", + meaning: "Agent associated with this span", + }, + NormalizedFieldDefinition { + name: "framework", + clickhouse_column: "Framework", + clickhouse_type: "LowCardinality(String)", + meaning: "Agent framework or SDK that emitted this span, e.g. claude-agent-sdk", + }, + NormalizedFieldDefinition { + name: "litellm_request_id", + clickhouse_column: "LiteLLMRequestId", + clickhouse_type: "String", + meaning: "LiteLLM response ID used to link a span to a spend log", + }, + NormalizedFieldDefinition { + name: "model", + clickhouse_column: "Model", + clickhouse_type: "LowCardinality(String)", + meaning: "Model used by this span", + }, + NormalizedFieldDefinition { + name: "input_tokens", + clickhouse_column: "InputTokens", + clickhouse_type: "UInt32", + meaning: "Input token count", + }, + NormalizedFieldDefinition { + name: "output_tokens", + clickhouse_column: "OutputTokens", + clickhouse_type: "UInt32", + meaning: "Output token count", + }, + NormalizedFieldDefinition { + name: "input", + clickhouse_column: "Input", + clickhouse_type: "String", + meaning: "Normalized input payload", + }, + NormalizedFieldDefinition { + name: "output", + clickhouse_column: "Output", + clickhouse_type: "String", + meaning: "Normalized output payload", + }, +]; diff --git a/litellm-rust/crates/traces-clickhouse/src/sql.rs b/litellm-rust/crates/traces-clickhouse/src/sql.rs new file mode 100644 index 00000000000..0f739314418 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/src/sql.rs @@ -0,0 +1,83 @@ +use std::collections::BTreeMap; + +use litellm_http::Client; +use litellm_traces::ReadQuery; + +use super::query::{lens::*, named::*}; +use super::{Connection, Error, Parameter}; +use litellm_storage_clickhouse::{Query, fetch_json}; + +pub async fn execute_named_read( + client: &Client, + connection: &Connection, + query: ReadQuery, + parameters: &BTreeMap, +) -> Result { + match query { + ReadQuery::ListTraces => named_json::(client, connection, parameters).await, + ReadQuery::TraceIdentity => { + named_json::(client, connection, parameters).await + } + ReadQuery::TraceSpans => named_json::(client, connection, parameters).await, + ReadQuery::SpanDetail => named_json::(client, connection, parameters).await, + ReadQuery::SpanError => named_json::(client, connection, parameters).await, + ReadQuery::SpendByResponseIds => { + named_json::(client, connection, parameters).await + } + ReadQuery::Availability => { + named_json::(client, connection, parameters).await + } + ReadQuery::Agents => named_json::(client, connection, parameters).await, + ReadQuery::Sample => named_json::(client, connection, parameters).await, + ReadQuery::Content => named_json::(client, connection, parameters).await, + ReadQuery::Evidence => named_json::(client, connection, parameters).await, + } +} + +async fn named_json( + client: &Client, + connection: &Connection, + parameters: &BTreeMap, +) -> Result +where + Q::Params: serde::de::DeserializeOwned, +{ + let value = serde_json::to_value(parameters).map_err(|_| Error::InvalidParameters)?; + let params = + serde_json::from_value::(value).map_err(|_| Error::InvalidParameters)?; + fetch_json::(client, connection, ¶ms) + .await + .map_err(Error::from) +} + +#[cfg(test)] +mod tests { + use super::*; + use rstest::rstest; + + #[rstest] + #[case::missing_span(serde_json::json!({}))] + #[case::negative_offset(serde_json::json!({"span_id": "span", "error_offset": -1, "error_version": ""}))] + #[case::overflow(serde_json::json!({"span_id": "span", "error_offset": "18446744073709551616", "error_version": ""}))] + #[tokio::test] + async fn named_read_rejects_invalid_parameters_before_transport( + #[case] specific: serde_json::Value, + ) { + let common = serde_json::json!({ + "all_teams": 1, "user_id": "", "team_ids": [], "api_key_hash": "", "trace_id": "trace", "trace_ref": "" + }); + let parameters: BTreeMap = common + .as_object() + .unwrap() + .iter() + .chain(specific.as_object().unwrap().iter()) + .map(|(name, value)| (name.clone(), serde_json::from_value(value.clone()).unwrap())) + .collect(); + let client = Client::no_redirect_for_test(); + let connection = Connection::parse("http://127.0.0.1:1").unwrap(); + assert!(matches!( + execute_named_read(&client, &connection, ReadQuery::SpanError, ¶meters).await, + Err(Error::InvalidParameters) + )); + } +} diff --git a/litellm-rust/crates/traces-clickhouse/src/table.rs b/litellm-rust/crates/traces-clickhouse/src/table.rs new file mode 100644 index 00000000000..5e3fe83fa82 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/src/table.rs @@ -0,0 +1,9 @@ +#[derive( + Clone, Copy, Debug, strum::Display, strum::AsRefStr, strum::EnumIter, strum::IntoStaticStr, +)] +#[strum(serialize_all = "snake_case")] +pub enum TraceTable { + OtelTraces, + AgentTracesByKey, + SpendLogs, +} diff --git a/litellm-rust/crates/traces/templates/query_help.jinja b/litellm-rust/crates/traces-clickhouse/templates/query_help.jinja similarity index 86% rename from litellm-rust/crates/traces/templates/query_help.jinja rename to litellm-rust/crates/traces-clickhouse/templates/query_help.jinja index 4bded74588c..a79342c8343 100644 --- a/litellm-rust/crates/traces/templates/query_help.jinja +++ b/litellm-rust/crates/traces-clickhouse/templates/query_help.jinja @@ -35,7 +35,7 @@ Examples {% block nested_metadata_sql %}SELECT request_id, JSONType(metadata, 'labels', 'priority') AS type, JSONExtractRaw(metadata, 'labels', 'priority') AS value FROM spend_logs FINAL WHERE start_time >= now() - INTERVAL 1 DAY AND JSONHas(metadata, 'labels', 'priority') LIMIT 100{% endblock %} {% block correlated_calls_name %}Traces correlated with LLM call metadata{% endblock %} -{% block correlated_calls_sql %}SELECT t.TraceId, t.SpanId, s.request_id, s.spend, s.metadata FROM otel_traces AS t INNER JOIN (SELECT * FROM spend_logs FINAL WHERE start_time >= now() - INTERVAL 1 DAY) AS s ON t.LiteLLMRequestId = s.response_id AND t.TeamId = s.team_id AND t.ApiKeyHash = s.api_key WHERE t.Timestamp >= now() - INTERVAL 1 DAY AND t.LiteLLMRequestId != '' AND JSONExtractString(s.metadata, 'project') = 'example' LIMIT 100{% endblock %} +{% block correlated_calls_sql %}SELECT t.TraceId, t.SpanId, s.request_id, s.spend, s.metadata FROM otel_traces AS t INNER JOIN (SELECT * FROM spend_logs FINAL WHERE start_time >= now() - INTERVAL 1 DAY) AS s ON t.LiteLLMRequestId = s.response_id AND t.TeamId = s.team_id AND (t.TeamId != '' OR (t.UserId != '' AND t.UserId = s.user) OR (t.ApiKeyHash != '' AND t.ApiKeyHash = s.api_key)) WHERE t.Timestamp >= now() - INTERVAL 1 DAY AND t.LiteLLMRequestId != '' AND JSONExtractString(s.metadata, 'project') = 'example' LIMIT 100{% endblock %} {% block discover_keys_name %}Discover metadata keys over a different window{% endblock %} {% block discover_keys_sql %}SELECT DISTINCT arrayJoin(JSONExtractKeys(metadata)) AS key FROM spend_logs FINAL WHERE start_time >= now() - INTERVAL 30 DAY ORDER BY key LIMIT 200{% endblock %} @@ -46,7 +46,7 @@ Gotchas {% block reader_limits %}The reader enforces 1000 result rows, 4 MiB response bytes, 256 MiB memory and a 10 second query limit; exceeding limits fails instead of returning partial results{% endblock %} -{% block reader_profile %}LiteLLM provisions SELECT-only readers from the configured ClickHouse connection and enforces authenticated team scope through row policies. Project-bound and teamless keys see only their own rows. Provisioning requires CREATE USER, ALTER USER, CREATE ROW POLICY, and GRANT SELECT permissions{% endblock %} +{% block reader_profile %}LiteLLM provisions SELECT-only readers from the configured ClickHouse connection and enforces request-log visibility through row policies. Callers see their own user rows and permitted teams, or their own key rows when no user identity is available. Provisioning requires CREATE USER, ALTER USER, CREATE ROW POLICY, and GRANT SELECT permissions{% endblock %} {% block output_format %}Do not add FORMAT clauses; the endpoint requires ClickHouse JSON output{% endblock %} @@ -58,7 +58,7 @@ Gotchas {% block time_units %}Duration is nanoseconds; Timestamp has nanosecond precision, spend start_time has millisecond precision{% endblock %} -{% block spend_totals %}Use spend_logs FINAL to collapse replacement rows before totals. Shared response IDs and multiple spans can multiply costs in joins; aggregate spend separately{% endblock %} +{% block spend_totals %}Use spend_logs FINAL to collapse replacement rows before totals. Shared response IDs and multiple spans can multiply costs in joins; require one spend match per response ID and ownership before aggregating. Missing IDs or costs leave totals unknown{% endblock %} {% block trace_rollups %}agent_traces_by_key uses SimpleAggregateFunction columns; group by TeamId, ApiKeyHash and TraceId, using min(StartTs), max(EndTs), sum(SpanCount) and groupUniqArrayArray(Models). Do not use Merge combinators{% endblock %} diff --git a/litellm-rust/crates/traces/tests/admin_sql.rs b/litellm-rust/crates/traces-clickhouse/tests/admin_sql.rs similarity index 84% rename from litellm-rust/crates/traces/tests/admin_sql.rs rename to litellm-rust/crates/traces-clickhouse/tests/admin_sql.rs index ab0eb873a28..614dad7a35a 100644 --- a/litellm-rust/crates/traces/tests/admin_sql.rs +++ b/litellm-rust/crates/traces-clickhouse/tests/admin_sql.rs @@ -1,18 +1,16 @@ use litellm_http::Client; -use litellm_traces::{Connection, Error, Parameter, execute_read}; +use litellm_traces_clickhouse::{ + Connection, Error, Parameter, QueryReaders, QueryScope, execute_read, +}; use rstest::{fixture, rstest}; use serde_json::Value; use std::collections::BTreeMap; -use testcontainers_modules::{ - clickhouse::ClickHouse, - testcontainers::{ContainerAsync, ImageExt, runners::AsyncRunner}, -}; +mod support; -const CLICKHOUSE_TAG: &str = - "26.9.6.6@sha256:eb4870e7ca7ed70c259eebfcfbee6cf797017f6b5436c2926bbbfe3d4d28486e"; +use support::{ClickHouseDatabase, database as start_database}; struct Database { - _container: ContainerAsync, + _database: ClickHouseDatabase, url: String, admin_url: String, client: Client, @@ -20,22 +18,9 @@ struct Database { #[fixture] async fn database() -> Result> { - let container = ClickHouse::default() - .with_tag(CLICKHOUSE_TAG) - .with_env_var("CLICKHOUSE_SKIP_USER_SETUP", "1") - .with_env_var("LITELLM_TRACES_READER_PASSWORD", "test_password") - .with_copy_to( - "/etc/clickhouse-server/users.d/litellm-traces-reader.xml", - include_bytes!("../config/reader.xml").to_vec(), - ) - .start() - .await?; - let admin_url = format!( - "http://{}:{}", - container.get_host().await?, - container.get_host_port_ipv4(8123).await?, - ); - let client = Client::no_redirect_for_test(); + let instance = start_database().await?; + let admin_url = instance.url.clone(); + let client = instance.client.clone(); for sql in [ "CREATE DATABASE litellm", "CREATE TABLE litellm.otel_traces (n UInt8) ENGINE = Memory", @@ -54,12 +39,13 @@ async fn database() -> Result> { .await? .error_for_status()?; } - let url = format!( - "{}?database=litellm", - admin_url.replacen("http://", "http://litellm_traces_reader:test_password@", 1) - ); + let readers = QueryReaders::new(Connection::writer(&admin_url)?, "litellm".into()); + let connection = readers + .connection(&client, &QueryScope::Admin, "test-secret") + .await?; + let url = connection.url().to_string(); Ok(Database { - _container: container, + _database: instance, url, admin_url, client, @@ -120,7 +106,15 @@ async fn reader_rejects_writes_and_privilege_escalation( let result = read(&database.client, &connection, sql).await; - assert!(matches!(result, Err(Error::QueryFailed(_))), "{result:?}"); + assert!( + matches!( + result, + Err(Error::Storage( + litellm_storage_clickhouse::Error::QueryFailed(_) + )) + ), + "{result:?}" + ); let rows = read(&database.client, &connection, "SELECT n FROM otel_traces").await?; let json: Value = serde_json::from_str(&rows)?; assert_eq!(json["data"], serde_json::json!([{ "n": 1 }])); @@ -147,7 +141,12 @@ async fn admin_sql_rejects_errors_after_output_starts( .await; assert!( - matches!(result, Err(Error::InvalidResponse)), + matches!( + result, + Err(Error::Storage( + litellm_storage_clickhouse::Error::InvalidResponse + )) + ), "expected an error embedded in a successful HTTP response: {result:?}" ); Ok(()) @@ -171,7 +170,15 @@ async fn admin_sql_enforces_result_row_limit( ) .await; - assert!(matches!(result, Err(Error::QueryFailed(_))), "{result:?}"); + assert!( + matches!( + result, + Err(Error::Storage( + litellm_storage_clickhouse::Error::QueryFailed(_) + )) + ), + "{result:?}" + ); Ok(()) } @@ -190,7 +197,15 @@ async fn admin_sql_enforces_response_byte_limit( ) .await; - assert!(matches!(result, Err(Error::ResponseTooLarge)), "{result:?}"); + assert!( + matches!( + result, + Err(Error::Storage( + litellm_storage_clickhouse::Error::ResponseTooLarge + )) + ), + "{result:?}" + ); Ok(()) } diff --git a/litellm-rust/crates/traces-clickhouse/tests/fixtures/README.md b/litellm-rust/crates/traces-clickhouse/tests/fixtures/README.md new file mode 100644 index 00000000000..560f919d867 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/tests/fixtures/README.md @@ -0,0 +1,15 @@ +# ClickHouse query fixtures + +Run `cargo test -p litellm-traces-clickhouse --test queries --locked -- --test-threads=2` from `litellm-rust` with Docker running + +Raw OTLP exports live in `crates/traces/tests/fixtures/query_*.json`. The seeded fixture decodes and normalizes them through `litellm_traces::decode_otlp` at test startup, then projects the decoded fields into ClickHouse columns. Team and key identities come from fixture setup rather than exporter claims. Root and child exports are inserted separately through the public insert API so materialized views process multiple blocks + +`crates/traces/tests/fixtures/deeplite_auth_error.json` and `deeplite_swarm.json` were captured from Deeplite runs against the local proxy on 2026-10-02. The first contains a failed model call. The second contains successful model calls, searches, handoff attempts, and virtual filesystem writes. Credentials, workspace identifiers, and local user paths were redacted, and the protobuf exports were converted to OTLP JSON. Their round-trip tests check span identities, parent links, timestamps, durations, token counts, and statuses without pinning the provider's error wording + +The swarm capture has handoff spans marked ERROR with `ParentCommand` exception events and a root with UNSET status. These are exported diagnostic statuses, which do not establish a failed execution. The tests preserve incoming statuses and check root status separately from the count of error spans, deriving both from the decoded export. They do not infer an execution outcome from exception text, framework names, successful model calls, or output presence. Framework-specific interpretation of control-flow exceptions belongs in the instrumentation integration + +`spend_logs.jsonl` contains spend insert rows with millisecond timestamps, including two versions of one request. Replace this small placeholder dataset when the actual data is available. The query fixture applies production migrations, then removes TTL from its isolated database so fixed timestamps do not expire. Background merges are stopped so rollup aggregation and `FINAL` deduplication are exercised on unmerged data. Retention behavior stays covered by the migration tests + +Curated SQL lives in `tests/queries/*.sql`. Each query has a matching `.expected.json` containing ordered result rows for `admin`, `team`, `key`, and `other_team` readers. Update the exports and expected results together. Add a named case in `tests/queries.rs` for each new query. Assertions compare only result data, excluding server statistics and execution timing + +Typed query tests execute the production SQL through `litellm_storage_clickhouse::fetch` using contracts from `litellm-traces`. The fixture projection is test setup, so this suite covers the Rust decoder, normalization, inserts, schema, readers, and queries. Python ingress transformations, including payload truncation and exception-event fallback, remain covered by the Python tests diff --git a/litellm-rust/crates/traces-clickhouse/tests/fixtures/spend_logs.jsonl b/litellm-rust/crates/traces-clickhouse/tests/fixtures/spend_logs.jsonl new file mode 100644 index 00000000000..d798df19aa4 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/tests/fixtures/spend_logs.jsonl @@ -0,0 +1,3 @@ +{"request_id":"request-a","response_id":"response-shared","team_id":"team-a","api_key":"key-a","user":"user-a","spend":0.125,"start_time":1735689600100,"end_time":1735689600500,"metadata":"{\"labels\":{\"priority\":\"obsolete\"}}"} +{"request_id":"request-a","response_id":"response-shared","team_id":"team-a","api_key":"key-a","user":"user-a","spend":0.5,"start_time":1735689600100,"end_time":1735689600600,"metadata":"{\"labels\":{\"priority\":\"high\"}}"} +{"request_id":"request-b","response_id":"response-shared","team_id":"team-b","api_key":"key-b","user":"user-b","spend":0.25,"start_time":1735689602000,"end_time":1735689602500,"metadata":"{\"labels\":{\"priority\":\"low\"}}"} diff --git a/litellm-rust/crates/traces/tests/insert.rs b/litellm-rust/crates/traces-clickhouse/tests/insert.rs similarity index 97% rename from litellm-rust/crates/traces/tests/insert.rs rename to litellm-rust/crates/traces-clickhouse/tests/insert.rs index 9dcb9cddf1f..2d1c98668e2 100644 --- a/litellm-rust/crates/traces/tests/insert.rs +++ b/litellm-rust/crates/traces-clickhouse/tests/insert.rs @@ -5,8 +5,9 @@ use std::{ use flate2::read::GzDecoder; use litellm_http::Client; -use litellm_traces::{ - Connection, Error, InsertRow, InsertTable, Shared, encode_rows, insert_shared_rows, +use litellm_traces::Shared; +use litellm_traces_clickhouse::{ + Connection, Error, InsertRow, InsertTable, encode_rows, insert_shared_rows, }; use rstest::{fixture, rstest}; use serde_json::{Value, json}; diff --git a/litellm-rust/crates/traces/tests/migrations.rs b/litellm-rust/crates/traces-clickhouse/tests/migrations.rs similarity index 78% rename from litellm-rust/crates/traces/tests/migrations.rs rename to litellm-rust/crates/traces-clickhouse/tests/migrations.rs index 1db3bb2cbb6..dff7d8d5940 100644 --- a/litellm-rust/crates/traces/tests/migrations.rs +++ b/litellm-rust/crates/traces-clickhouse/tests/migrations.rs @@ -1,45 +1,14 @@ use std::{collections::BTreeMap, time::Duration}; use litellm_http::Client; -use litellm_traces::{ +use litellm_traces_clickhouse::{ Connection, Error, InsertTable, NORMALIZED_FIELD_DEFINITIONS, Parameter, ReadQuery, encode_rows, ensure_schema, execute_named_read, execute_read, schema_statements, }; -use rstest::{fixture, rstest}; -use testcontainers_modules::{ - clickhouse::ClickHouse, - testcontainers::{ContainerAsync, ImageExt, runners::AsyncRunner}, -}; +use rstest::rstest; +mod support; -const CLICKHOUSE_TAG: &str = - "26.9.6.6@sha256:eb4870e7ca7ed70c259eebfcfbee6cf797017f6b5436c2926bbbfe3d4d28486e"; - -type TestResult = Result>; - -struct ClickHouseDatabase { - _container: ContainerAsync, - url: String, - client: Client, -} - -#[fixture] -async fn database() -> TestResult { - let container = ClickHouse::default() - .with_tag(CLICKHOUSE_TAG) - .with_env_var("CLICKHOUSE_SKIP_USER_SETUP", "1") - .start() - .await?; - let url = format!( - "http://{}:{}", - container.get_host().await?, - container.get_host_port_ipv4(8123).await? - ); - Ok(ClickHouseDatabase { - _container: container, - url, - client: Client::no_redirect_for_test(), - }) -} +use support::{ClickHouseDatabase, TestResult, database}; async fn insert_rows( database: &ClickHouseDatabase, @@ -115,7 +84,7 @@ async fn schema_supports_span_rollups_and_spend_joins( let span = serde_json::from_value(serde_json::json!({ "Timestamp": timestamp, "TraceId": "trace-1", "SpanId": "span-1", "ParentSpanId": "", "ServiceName": "proxy", "SpanName": "request", "Input": "hello world", - "ResourceAttributes": {"litellm.team_id": "team-1", "litellm.api_key_hash": "hash-1"}, + "ResourceAttributes": {"litellm.team_id": "team-1", "litellm.api_key_hash": "hash-1", "litellm.user_id": "exporter-claim"}, "SpanAttributes": {"gen_ai.response.id": "response-1", "gen_ai.usage.input_tokens": "12"} }))?; let spend = serde_json::from_value(serde_json::json!({ @@ -126,7 +95,29 @@ async fn schema_supports_span_rollups_and_spend_joins( insert_rows(&database, "otel_traces", vec![span]).await?; insert_rows(&database, "spend_logs", vec![spend]).await?; let reader = Connection::reader(&database.url, "trace_test")?; + let detail = + litellm_storage_clickhouse::fetch::( + &database.client, + &reader, + &litellm_traces_clickhouse::query::named::SpanDetailParams { + access: litellm_traces_clickhouse::query::named::ReadAccessParams { + all_teams: 0, + user_id: String::new(), + team_ids: vec!["team-1".into()], + api_key_hash: String::new(), + }, + trace_id: "trace-1".into(), + trace_ref: String::new(), + span_id: "span-1".into(), + }, + ) + .await?; + assert_eq!(detail.len(), 1); + assert_eq!(detail[0].input, "hello world"); + assert_eq!(detail[0].attributes["gen_ai.response.id"], "response-1"); let list_parameters = BTreeMap::from([ + ("all_teams".into(), Parameter::Integer(0)), + ("user_id".into(), Parameter::Text(String::new())), ("team_ids".into(), Parameter::Strings(vec!["team-1".into()])), ("api_key_hash".into(), Parameter::Text(String::new())), ( @@ -159,6 +150,8 @@ async fn schema_supports_span_rollups_and_spend_joins( "response_ids".into(), Parameter::Strings(vec!["response-1".into()]), ), + ("all_teams".into(), Parameter::Integer(0)), + ("user_id".into(), Parameter::Text(String::new())), ("team_ids".into(), Parameter::Strings(vec!["team-1".into()])), ("api_key_hash".into(), Parameter::Text(String::new())), ( @@ -182,7 +175,7 @@ async fn schema_supports_span_rollups_and_spend_joins( assert_eq!(matched["data"][0]["spend"], 0.125); let body = read_json( &database, - "SELECT o.TeamId, o.ApiKeyHash, o.ObservationType, o.InputPreview, s.spend, \ + "SELECT o.TeamId, o.ApiKeyHash, o.UserId, o.ObservationType, o.InputPreview, s.spend, \ toString(toUnixTimestamp64Nano(o.Timestamp)) AS timestamp_ns, \ toString(toUnixTimestamp64Milli(s.start_time)) AS start_ms \ FROM trace_test.otel_traces o JOIN trace_test.spend_logs s \ @@ -192,7 +185,7 @@ async fn schema_supports_span_rollups_and_spend_joins( assert_eq!( body["data"], serde_json::json!([{ - "TeamId": "team-1", "ApiKeyHash": "hash-1", "ObservationType": "agent", + "TeamId": "team-1", "ApiKeyHash": "hash-1", "UserId": "", "ObservationType": "agent", "InputPreview": "hello world", "spend": 0.125, "timestamp_ns": timestamp.to_string(), "start_ms": (timestamp / 1_000_000).to_string() }]) @@ -269,7 +262,7 @@ async fn insert_rejects_unknown_columns_even_if_url_requests_skipping_them( ]); assert!(matches!( - litellm_traces::insert_rows( + litellm_traces_clickhouse::insert_rows( &database.client, &writer, "trace_test", @@ -277,7 +270,9 @@ async fn insert_rejects_unknown_columns_even_if_url_requests_skipping_them( vec![row] ) .await, - Err(Error::InsertFailed(_)) + Err(Error::Storage( + litellm_storage_clickhouse::Error::InsertFailed(_) + )) )); assert_eq!(table_rows(&database, "otel_traces").await?, 0); Ok(()) @@ -297,7 +292,7 @@ async fn retried_trace_insert_does_not_inflate_rollup( "TeamId": "team-1", "ApiKeyHash": "key-1", "SpanName": "root", "InputTokens": 7 }))?; for _ in 0..2 { - litellm_traces::insert_rows( + litellm_traces_clickhouse::insert_rows( &database.client, &writer, "trace_test", @@ -412,7 +407,7 @@ async fn listed_agent_names_preserve_scope_and_cursor( ), ( "beta", - "one", + "other", "shared", "other_agent", "root", @@ -446,7 +441,9 @@ async fn listed_agent_names_preserve_scope_and_cursor( insert_rows(&database, "otel_traces", historical_rows).await?; let connection = Connection::configured(&database.url, "trace_test", "default", "")?; let parameters = BTreeMap::from([ - ("team_ids".into(), Parameter::Strings(vec!["alpha".into()])), + ("all_teams".into(), Parameter::Integer(0)), + ("user_id".into(), Parameter::Text(String::new())), + ("team_ids".into(), Parameter::Strings(vec![])), ("api_key_hash".into(), Parameter::Text("one".into())), ( "start_ms".into(), @@ -596,6 +593,8 @@ async fn rollup_merges_spans_across_days_without_losing_root_fields( ); let connection = Connection::configured(&database.url, "trace_test", "default", "")?; let parameters = BTreeMap::from([ + ("all_teams".into(), Parameter::Integer(0)), + ("user_id".into(), Parameter::Text(String::new())), ("team_ids".into(), Parameter::Strings(vec!["team-1".into()])), ("api_key_hash".into(), Parameter::Text(String::new())), ( @@ -768,7 +767,10 @@ async fn schema_statement_timeout_maps_to_transport_error() -> TestResult { ) .await; server.abort(); - assert!(matches!(result, Ok(Err(Error::Transport))), "{result:?}"); + assert!( + matches!(result, Ok(Err(Error::SchemaTransport))), + "{result:?}" + ); Ok(()) } @@ -785,7 +787,7 @@ fn schema_rejects_invalid_configuration(#[case] database: &str, #[case] retentio async fn lens_filters_reads_and_evidence_keep_reused_trace_ids_separate( #[future(awt)] database: TestResult, ) -> TestResult { - use litellm_traces::{LensQuery, Parameter}; + use litellm_traces_clickhouse::{Parameter, ReadQuery}; let database = database?; let writer = Connection::writer(&database.url)?; ensure_schema(&database.client, &writer, "trace_test", 7).await?; @@ -831,10 +833,10 @@ async fn lens_filters_reads_and_evidence_keep_reused_trace_ids_separate( ("execution_ids".into(), Parameter::Strings(vec![])), ]); let sample: serde_json::Value = serde_json::from_str( - &execute_read( + &execute_named_read( &database.client, &connection, - LensQuery::Sample.sql(), + ReadQuery::Sample, ¶meters, ) .await?, @@ -842,6 +844,44 @@ async fn lens_filters_reads_and_evidence_keep_reused_trace_ids_separate( let rows = sample["data"].as_array().expect("sample rows"); assert_eq!(rows.len(), 2); assert_ne!(rows[0]["trace_ref"], rows[1]["trace_ref"]); + let identity_params = BTreeMap::from([ + ("trace_id".into(), Parameter::Text("shared".into())), + ("all_teams".into(), Parameter::Integer(0)), + ("user_id".into(), Parameter::Text(String::new())), + ("team_ids".into(), Parameter::Strings(vec!["team".into()])), + ("api_key_hash".into(), Parameter::Text(String::new())), + ]); + let identities: serde_json::Value = serde_json::from_str( + &execute_named_read( + &database.client, + &connection, + ReadQuery::TraceIdentity, + &identity_params, + ) + .await?, + )?; + assert_eq!(identities["data"].as_array().map(Vec::len), Some(2)); + let key_params = identity_params + .into_iter() + .chain([ + ("team_ids".into(), Parameter::Strings(vec![])), + ("api_key_hash".into(), Parameter::Text("one".into())), + ]) + .collect(); + let identity: serde_json::Value = serde_json::from_str( + &execute_named_read( + &database.client, + &connection, + ReadQuery::TraceIdentity, + &key_params, + ) + .await?, + )?; + assert_eq!(identity["data"].as_array().map(Vec::len), Some(1)); + assert!( + rows.iter() + .any(|row| row["trace_ref"] == identity["data"][0]["trace_ref"]) + ); let first_ref = rows[0]["trace_ref"].as_str().expect("reference"); let read_parameters: BTreeMap<_, _> = parameters .into_iter() @@ -855,10 +895,10 @@ async fn lens_filters_reads_and_evidence_keep_reused_trace_ids_separate( ]) .collect(); let content: serde_json::Value = serde_json::from_str( - &execute_read( + &execute_named_read( &database.client, &connection, - LensQuery::Content.sql(), + ReadQuery::Content, &read_parameters, ) .await?, @@ -875,10 +915,10 @@ async fn lens_filters_reads_and_evidence_keep_reused_trace_ids_separate( .chain([("quote".into(), Parameter::Text(opposite.into()))]) .collect(); let evidence: serde_json::Value = serde_json::from_str( - &execute_read( + &execute_named_read( &database.client, &connection, - LensQuery::Evidence.sql(), + ReadQuery::Evidence, &evidence_parameters, ) .await?, @@ -892,7 +932,7 @@ async fn lens_filters_reads_and_evidence_keep_reused_trace_ids_separate( async fn lens_request_sample_does_not_trust_caller_tags( #[future(awt)] database: TestResult, ) -> TestResult { - use litellm_traces::{LensQuery, Parameter}; + use litellm_traces_clickhouse::{Parameter, ReadQuery}; let database = database?; let writer = Connection::writer(&database.url)?; ensure_schema(&database.client, &writer, "trace_test", 7).await?; @@ -927,10 +967,10 @@ async fn lens_request_sample_does_not_trust_caller_tags( ("execution_ids".into(), Parameter::Strings(vec![])), ]); let sample: serde_json::Value = serde_json::from_str( - &execute_read( + &execute_named_read( &database.client, &connection, - LensQuery::Sample.sql(), + ReadQuery::Sample, ¶meters, ) .await?, @@ -957,7 +997,7 @@ async fn lens_selection_pages_without_losing_or_repeating_runs( #[case] page_size: usize, #[case] changing: bool, ) -> TestResult { - use litellm_traces::LensQuery; + use litellm_traces_clickhouse::ReadQuery; let database = database?; ensure_schema( &database.client, @@ -996,10 +1036,10 @@ async fn lens_selection_pages_without_losing_or_repeating_runs( ("selected_team".into(), Parameter::Text(String::new())), ("execution_ids".into(), Parameter::Strings(vec![])), ]); - let body = execute_read( + let body = execute_named_read( &database.client, &connection, - LensQuery::Sample.sql(), + ReadQuery::Sample, ¶meters, ) .await?; @@ -1037,7 +1077,7 @@ async fn lens_content_keeps_output_visible_after_long_input( #[future(awt)] database: TestResult, #[case] input_length: usize, ) -> TestResult { - use litellm_traces::LensQuery; + use litellm_traces_clickhouse::ReadQuery; let database = database?; ensure_schema( &database.client, @@ -1061,10 +1101,10 @@ async fn lens_content_keeps_output_visible_after_long_input( ("cursor".into(), Parameter::Text(String::new())), ("offset".into(), Parameter::Integer(1)), ]); - let body = execute_read( + let body = execute_named_read( &database.client, &connection, - LensQuery::Content.sql(), + ReadQuery::Content, ¶meters, ) .await?; @@ -1083,10 +1123,10 @@ async fn lens_content_keeps_output_visible_after_long_input( let mut recovered = String::new(); for offset in (2..original.len() + 2).step_by(8000) { parameters.insert("offset".into(), Parameter::Integer(offset as i64)); - let body = execute_read( + let body = execute_named_read( &database.client, &connection, - LensQuery::Content.sql(), + ReadQuery::Content, ¶meters, ) .await?; @@ -1127,6 +1167,8 @@ async fn trace_error_previews_preserve_paginated_diagnostics( "trace_id".into(), Parameter::Text("diagnostic-trace".into()), ), + ("all_teams".into(), Parameter::Integer(1)), + ("user_id".into(), Parameter::Text(String::new())), ("team_ids".into(), Parameter::Strings(vec![])), ("api_key_hash".into(), Parameter::Text(String::new())), ("trace_ref".into(), Parameter::Text(String::new())), @@ -1174,6 +1216,7 @@ async fn trace_error_previews_preserve_paginated_diagnostics( } } assert_eq!(recovered, message); + parameters.insert("all_teams".into(), Parameter::Integer(0)); parameters.insert( "api_key_hash".into(), Parameter::Text("unrelated-key".into()), @@ -1219,6 +1262,8 @@ async fn duplicate_span_preview_matches_diagnostic( let parameters = BTreeMap::from([ ("trace_id".into(), Parameter::Text("duplicate-trace".into())), ("span_id".into(), Parameter::Text("duplicate-span".into())), + ("all_teams".into(), Parameter::Integer(1)), + ("user_id".into(), Parameter::Text(String::new())), ("team_ids".into(), Parameter::Strings(vec![])), ("api_key_hash".into(), Parameter::Text(String::new())), ("trace_ref".into(), Parameter::Text(String::new())), @@ -1257,7 +1302,7 @@ fn schema_includes_every_migration_file() -> TestResult { async fn lens_agent_discovery_and_selection_preserve_scope( #[future] database: TestResult, ) -> TestResult { - use litellm_traces::LensQuery; + use litellm_traces_clickhouse::ReadQuery; let database = database.await?; let writer = Connection::writer(&database.url)?; ensure_schema(&database.client, &writer, "trace_test", 7).await?; @@ -1288,10 +1333,10 @@ async fn lens_agent_discovery_and_selection_preserve_scope( ("key_hash".into(), Parameter::Text("one".into())), ]); let agents: serde_json::Value = serde_json::from_str( - &execute_read( + &execute_named_read( &database.client, &connection, - LensQuery::Agents.sql(), + ReadQuery::Agents, &scope_parameters, ) .await?, @@ -1332,10 +1377,10 @@ async fn lens_agent_discovery_and_selection_preserve_scope( ]) .collect::>(); let sample: serde_json::Value = serde_json::from_str( - &execute_read( + &execute_named_read( &database.client, &connection, - LensQuery::Sample.sql(), + ReadQuery::Sample, ¶meters, ) .await?, @@ -1344,10 +1389,10 @@ async fn lens_agent_discovery_and_selection_preserve_scope( assert_eq!(sample["data"][0]["trace_id"], "research"); assert_eq!(sample["data"][0]["span_count"], 2); let available: serde_json::Value = serde_json::from_str( - &execute_read( + &execute_named_read( &database.client, &connection, - LensQuery::Availability.sql(), + ReadQuery::Availability, ¶meters, ) .await?, @@ -1422,8 +1467,9 @@ async fn query_help_discovers_live_schema_and_runs_its_examples( ) .await?; } - let help: serde_json::Value = - serde_json::from_str(&litellm_traces::query_help(&database.client, &reader).await?)?; + let help: serde_json::Value = serde_json::from_str( + &litellm_traces_clickhouse::query_help(&database.client, &reader).await?, + )?; let keys: std::collections::BTreeSet<_> = help .as_object() .ok_or("missing help object")? @@ -1533,7 +1579,8 @@ async fn query_help_discovers_live_schema_and_runs_its_examples( "missing plain-text expression: {expression}" ); let sql = format!("SELECT {expression} AS value FROM spend_logs FINAL"); - let body = litellm_traces::query_sql(&database.client, &reader, &sql).await?; + let body = + litellm_traces_clickhouse::query_sql(&database.client, &reader, &sql).await?; let values: serde_json::Value = serde_json::from_str(&body)?; assert_ne!(values["data"][0]["value"], ""); } @@ -1551,7 +1598,7 @@ async fn query_help_discovers_live_schema_and_runs_its_examples( .collect::>(), std::collections::BTreeSet::from(["name", "sql"]) ); - let body = litellm_traces::query_sql(&database.client, &reader, sql).await?; + let body = litellm_traces_clickhouse::query_sql(&database.client, &reader, sql).await?; let values: serde_json::Value = serde_json::from_str(&body)?; assert_eq!( values["data"].as_array().ok_or("missing data")?.is_empty(), @@ -1607,8 +1654,9 @@ async fn query_help_preserves_schema_and_guide_when_discovery_hits_reader_limits }))).collect::, _>>()?; insert_rows(&database, "otel_traces", spans).await?; let reader = Connection::configured(&database.url, "trace_test", "help_reader", "")?; - let help: serde_json::Value = - serde_json::from_str(&litellm_traces::query_help(&database.client, &reader).await?)?; + let help: serde_json::Value = serde_json::from_str( + &litellm_traces_clickhouse::query_help(&database.client, &reader).await?, + )?; assert_eq!(help["tables"].as_array().ok_or("tables")?.len(), 3); assert!(!help["examples"].as_array().ok_or("examples")?.is_empty()); assert_eq!( @@ -1642,3 +1690,282 @@ async fn query_help_preserves_schema_and_guide_when_discovery_hits_reader_limits } Ok(()) } + +#[rstest] +fn field_definitions_match_serialized_normalized_span() { + use litellm_traces::decode_otlp; + use std::collections::BTreeSet; + let spans = decode_otlp( + br#"{"resourceSpans":[{"scopeSpans":[{"spans":[{"traceId":"11111111111111111111111111111111","spanId":"2222222222222222","name":"root"}]}]}]}"#, + Some("application/json"), + ) + .expect("valid OTLP"); + let fields = &spans[0].normalized; + let serialized = serde_json::to_value(fields).expect("serializable fields"); + let keys: BTreeSet<_> = serialized + .as_object() + .expect("field object") + .keys() + .map(String::as_str) + .collect(); + let mapped: BTreeSet<_> = NORMALIZED_FIELD_DEFINITIONS + .iter() + .map(|field| field.name) + .collect(); + assert_eq!(keys, mapped); +} + +#[rstest] +#[case::own_user("owner", vec![], "", vec!["own"])] +#[case::own_user_and_permitted_team("owner", vec!["permitted"], "", vec!["own", "team"])] +#[case::key_only("", vec![], "request-key", vec!["own"])] +#[case::no_identity("", vec![], "", vec![])] +#[tokio::test] +async fn named_and_sql_readers_share_request_log_visibility( + #[future(awt)] database: TestResult, + #[case] user: &str, + #[case] teams: Vec<&str>, + #[case] key: &str, + #[case] expected: Vec<&str>, +) -> TestResult { + use litellm_traces_clickhouse::query::named::{ + ReadAccessParams, SpendByResponseIds, SpendByResponseIdsParams, + }; + use litellm_traces_clickhouse::{QueryReaders, QueryScope}; + + let database = database?; + let writer = Connection::writer(&database.url)?; + ensure_schema(&database.client, &writer, "trace_test", 7).await?; + let timestamp = time::OffsetDateTime::now_utc().unix_timestamp_nanos() as i64; + let rows = [("own", "unpermitted", "owner", "request-key"), ("team", "permitted", "other", "other-key"), ("foreign", "foreign", "other", "foreign-key")] + .into_iter() + .map(|(id, team, owner, api_key)| serde_json::from_value(serde_json::json!({ + "request_id": id, "response_id": "shared-response", "team_id": team, "user": owner, + "api_key": api_key, "spend": 0.25, "start_time": timestamp / 1_000_000, "end_time": timestamp / 1_000_000, + }))) + .collect::>, _>>()?; + insert_rows(&database, "spend_logs", rows).await?; + let reader = Connection::reader(&database.url, "trace_test")?; + let params = + SpendByResponseIdsParams::from(litellm_traces::query::named::SpendByResponseIdsParams { + access: ReadAccessParams { + all_teams: 0, + user_id: user.into(), + team_ids: teams.iter().map(|team| (*team).into()).collect(), + api_key_hash: key.into(), + }, + response_ids: vec!["shared-response".into()], + start_ms: timestamp / 1_000_000 - 1, + end_ms: timestamp / 1_000_000 + 1, + }); + let spend = + litellm_storage_clickhouse::fetch::(&database.client, &reader, ¶ms) + .await?; + let actual: std::collections::BTreeSet<_> = + spend.iter().map(|row| row.0.request_id.as_str()).collect(); + let expected: std::collections::BTreeSet<_> = expected.into_iter().collect(); + assert_eq!(actual, expected); + let scope = QueryScope::Logs { + user_id: user.into(), + team_ids: teams.into_iter().map(str::to_owned).collect(), + api_key_hash: key.into(), + }; + if user.is_empty() && scope.validate().is_err() { + assert!( + QueryReaders::new(writer, "trace_test".into()) + .connection(&database.client, &scope, "secret") + .await + .is_err() + ); + return Ok(()); + } + let scoped = QueryReaders::new(writer, "trace_test".into()) + .connection(&database.client, &scope, "secret") + .await?; + let result: serde_json::Value = serde_json::from_str( + &litellm_traces_clickhouse::query_sql( + &database.client, + &scoped, + "SELECT request_id FROM spend_logs FINAL ORDER BY request_id", + ) + .await?, + )?; + assert_eq!( + result["data"], + serde_json::json!( + expected + .into_iter() + .map(|id| serde_json::json!({"request_id": id})) + .collect::>() + ) + ); + Ok(()) +} + +#[rstest] +#[tokio::test] +async fn rollup_cost_completeness_preserves_missing_ids_and_fails_closed_for_historical_rows( + #[future(awt)] database: TestResult, +) -> TestResult { + let database = database?; + let writer = Connection::writer(&database.url)?; + ensure_schema(&database.client, &writer, "trace_test", 7).await?; + let initial_mutations = mutation_rows(&database).await?; + let timestamp = time::OffsetDateTime::now_utc().unix_timestamp_nanos() as i64; + let rows = [("complete", "llm", "response"), ("complete", "llm", "response"), ("complete", "agent", ""), ("missing", "llm", "response"), ("missing", "llm", ""), ("missing", "agent", "extra-id"), ("mixed", "llm", "mine"), ("mixed", "llm", "other")] + .into_iter().enumerate().map(|(index, (trace, kind, id))| serde_json::from_value(serde_json::json!({ + "Timestamp": timestamp, "TraceId": trace, "SpanId": index.to_string(), "TeamId": "team", "ApiKeyHash": "export", + "UserId": if id == "other" { "other" } else { "owner" }, "ObservationType": kind, "LiteLLMRequestId": id, + }))).collect::>, _>>()?; + insert_rows(&database, "otel_traces", rows).await?; + execute_write(&database, &format!( + "INSERT INTO trace_test.agent_traces_by_key (TeamId, ApiKeyHash, TraceId, StartTs, EndTs, LlmCount, RequestIds) \ + VALUES ('team', 'export', 'historical', fromUnixTimestamp64Nano({timestamp}), fromUnixTimestamp64Nano({timestamp}), 2, ['response', 'non-llm-id'])" + )).await?; + ensure_schema(&database.client, &writer, "trace_test", 7).await?; + let params = litellm_traces_clickhouse::query::named::ListTracesParams::from( + litellm_traces::query::named::ListTracesParams { + access: litellm_traces::query::named::ReadAccessParams { + all_teams: 0, + user_id: "".into(), + team_ids: vec!["team".into()], + api_key_hash: "".into(), + }, + start_ms: timestamp / 1_000_000 - 1, + end_ms: timestamp / 1_000_000 + 1, + cursor_ms: 0, + cursor_trace_id: "".into(), + limit: 10, + }, + ); + let reader = Connection::reader(&database.url, "trace_test")?; + let listed = litellm_storage_clickhouse::fetch::< + litellm_traces_clickhouse::query::named::ListTraces, + >(&database.client, &reader, ¶ms) + .await?; + assert_eq!(listed.len(), 4); + let owned_params = litellm_traces_clickhouse::query::named::ListTracesParams::from( + litellm_traces::query::named::ListTracesParams { + access: litellm_traces::query::named::ReadAccessParams { + user_id: "owner".into(), + team_ids: vec![], + all_teams: 0, + api_key_hash: String::new(), + }, + ..params.0 + }, + ); + let owned = litellm_storage_clickhouse::fetch::< + litellm_traces_clickhouse::query::named::ListTraces, + >(&database.client, &reader, &owned_params) + .await?; + assert_eq!(owned.len(), 2); + assert!( + owned + .iter() + .all(|row| ["complete", "missing"].contains(&row.0.trace_id.as_str())) + ); + for row in listed { + match row.0.trace_id.as_str() { + "complete" => { + assert_eq!(row.0.user_id, "owner"); + assert_eq!(row.0.request_ids, ["response"]); + assert_eq!(row.0.llm_calls, 2); + } + "missing" | "historical" => assert!(row.0.request_ids.iter().any(String::is_empty)), + "mixed" => assert!(row.0.user_id.is_empty()), + id => panic!("unexpected trace {id}"), + } + } + assert_eq!(mutation_rows(&database).await?, initial_mutations); + Ok(()) +} + +#[rstest] +#[case::admin(1, "", vec![], "", "own answer")] +#[case::user(0, "owner", vec![], "", "own answer")] +#[case::team(0, "", vec!["alpha"], "", "own answer")] +#[case::key(0, "", vec![], "one", "own answer")] +#[case::no_identity(0, "", vec![], "", "")] +#[tokio::test] +async fn agent_final_answer_preserves_visibility_and_trace_ownership( + #[future(awt)] database: TestResult, + #[case] all_teams: u8, + #[case] user: &str, + #[case] teams: Vec<&str>, + #[case] key: &str, + #[case] expected: &str, +) -> TestResult { + use litellm_traces_clickhouse::query::named::{ReadAccessParams, SpanDetail, SpanDetailParams}; + + let database = database?; + let writer = Connection::writer(&database.url)?; + ensure_schema(&database.client, &writer, "trace_test", 7).await?; + let timestamp = time::OffsetDateTime::now_utc().unix_timestamp_nanos() as i64; + let rows = [ + ("alpha", "one", "owner", "root", "", "agent", ""), + ( + "alpha", + "one", + "owner", + "child", + "root", + "llm", + "own answer", + ), + ( + "alpha", + "two", + "other", + "child", + "root", + "llm", + "other key answer", + ), + ( + "beta", + "one", + "other", + "child", + "root", + "llm", + "other team answer", + ), + ] + .into_iter() + .enumerate() + .map(|(index, (team, key, user, span, parent, kind, output))| { + serde_json::from_value(serde_json::json!({ + "Timestamp": timestamp + index as i64, "TraceId": "shared", "SpanId": span, + "ParentSpanId": parent, "TeamId": team, "ApiKeyHash": key, "UserId": user, + "ObservationType": kind, "Input": "prompt", "Output": output, + })) + }) + .collect::, _>>()?; + insert_rows(&database, "otel_traces", rows).await?; + let reader = Connection::reader(&database.url, "trace_test")?; + let details = litellm_storage_clickhouse::fetch::( + &database.client, + &reader, + &SpanDetailParams { + access: ReadAccessParams { + all_teams, + user_id: user.into(), + team_ids: teams.into_iter().map(str::to_owned).collect(), + api_key_hash: key.into(), + }, + trace_id: "shared".into(), + trace_ref: String::new(), + span_id: "root".into(), + }, + ) + .await?; + if expected.is_empty() { + assert!(details.is_empty()); + } else { + assert_eq!(details.len(), 1); + assert_eq!(details[0].input, "prompt"); + assert_eq!(details[0].output, expected); + } + Ok(()) +} diff --git a/litellm-rust/crates/traces-clickhouse/tests/queries.rs b/litellm-rust/crates/traces-clickhouse/tests/queries.rs new file mode 100644 index 00000000000..3b9f108af94 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/tests/queries.rs @@ -0,0 +1,273 @@ +use std::collections::BTreeMap; + +use litellm_storage_clickhouse::fetch; +use litellm_traces::query::named as contracts; +use litellm_traces_clickhouse::{ + QueryScope, + query::named::{ListTraces, ListTracesParams, TraceSpans, TraceSpansParams}, + query_sql, +}; +use rstest::{fixture, rstest}; +use serde::Deserialize; +use serde_json::Value; + +#[path = "queries/support.rs"] +mod fixtures; +mod support; + +use fixtures::{SeededDatabase, insert_export, migrated_database, seeded_database}; +use support::TestResult; + +#[derive(Clone, Copy, strum::AsRefStr)] +#[strum(serialize_all = "snake_case")] +enum ScopeCase { + Admin, + Team, + Key, + OtherTeam, +} + +impl ScopeCase { + fn scope(self) -> QueryScope { + match self { + Self::Admin => QueryScope::Admin, + Self::Team => QueryScope::Team { + team_id: "team-a".into(), + }, + Self::Key => QueryScope::Key { + team_id: "team-a".into(), + api_key_hash: "key-a".into(), + }, + Self::OtherTeam => QueryScope::Team { + team_id: "team-b".into(), + }, + } + } +} + +#[derive(Deserialize)] +struct QueryResult { + data: Vec, +} + +#[rstest] +#[case::rollups(include_str!("queries/rollups.sql"), include_str!("queries/rollups.expected.json"))] +#[case::costs(include_str!("queries/trace_costs.sql"), include_str!("queries/trace_costs.expected.json"))] +#[case::errors(include_str!("queries/failed_spans.sql"), include_str!("queries/failed_spans.expected.json"))] +#[case::metadata(include_str!("queries/metadata_filters.sql"), include_str!("queries/metadata_filters.expected.json"))] +#[tokio::test] +async fn curated_queries_return_expected_rows( + #[future(awt)] seeded_database: TestResult, + #[case] sql: &str, + #[case] expected_json: &str, + #[values( + ScopeCase::Admin, + ScopeCase::Team, + ScopeCase::Key, + ScopeCase::OtherTeam + )] + scope: ScopeCase, +) -> TestResult { + let fixture = seeded_database?; + let reader = fixture + .readers + .connection(&fixture.database.client, &scope.scope(), "fixture-secret") + .await?; + let result: QueryResult = + serde_json::from_str(&query_sql(&fixture.database.client, &reader, sql).await?)?; + let expected: BTreeMap> = serde_json::from_str(expected_json)?; + assert_eq!( + &result.data, + expected + .get(scope.as_ref()) + .ok_or("missing expected scope")?, + "{}: {sql}", + scope.as_ref() + ); + Ok(()) +} + +#[fixture] +fn admin_access() -> TestResult { + Ok(serde_json::from_str(include_str!( + "queries/read_access.json" + ))?) +} + +#[rstest] +#[tokio::test] +async fn typed_queries_read_normalized_spans_and_keep_trace_identities_separate( + #[future(awt)] seeded_database: TestResult, + admin_access: TestResult, +) -> TestResult { + let fixture = seeded_database?; + let reader = fixture + .readers + .connection( + &fixture.database.client, + &QueryScope::Admin, + "fixture-secret", + ) + .await?; + let params = ListTracesParams::from(contracts::ListTracesParams { + access: admin_access?, + start_ms: 0, + end_ms: i64::MAX / 1_000_000, + cursor_ms: 0, + cursor_trace_id: String::new(), + limit: 10, + }); + let traces = fetch::(&fixture.database.client, &reader, ¶ms).await?; + assert_eq!( + traces + .iter() + .map(|row| row.0.api_key_hash.as_str()) + .collect::>(), + ["key-b", "key-alt", "key-a"] + ); + let trace = &traces[2].0; + assert_eq!( + ( + trace.span_count, + trace.llm_calls, + trace.tool_calls, + trace.error_count + ), + (3, 1, 1, 1) + ); + assert_eq!((trace.input_tokens, trace.output_tokens), (12, 6)); + assert_eq!(trace.input_preview, "Review the change"); + let span_params = TraceSpansParams { + access: params.0.access, + trace_id: trace.trace_id.clone(), + trace_ref: trace.trace_ref.clone(), + }; + let spans = fetch::(&fixture.database.client, &reader, &span_params).await?; + assert_eq!( + spans + .iter() + .map(|row| row.0.name.as_str()) + .collect::>(), + ["review", "completion", "lookup"] + ); + assert!( + spans + .iter() + .all(|row| row.0.api_key_hash == trace.api_key_hash) + ); + assert_eq!( + ( + spans[1].0.kind.as_str(), + spans[1].0.input_tokens, + spans[1].0.output_tokens + ), + ("llm", 12, 6) + ); + assert_eq!(spans[2].0.status_message, "lookup timed out"); + Ok(()) +} + +#[rstest] +#[tokio::test] +async fn typed_trace_cursor_returns_the_next_fixture_trace( + #[future(awt)] seeded_database: TestResult, + admin_access: TestResult, +) -> TestResult { + let fixture = seeded_database?; + let reader = fixture + .readers + .connection( + &fixture.database.client, + &QueryScope::Admin, + "fixture-secret", + ) + .await?; + let params = ListTracesParams::from(contracts::ListTracesParams { + access: admin_access?, + start_ms: 0, + end_ms: i64::MAX / 1_000_000, + cursor_ms: 0, + cursor_trace_id: String::new(), + limit: 1, + }); + let first = fetch::(&fixture.database.client, &reader, ¶ms).await?; + assert_eq!(first.len(), 1); + assert_eq!(first[0].0.api_key_hash, "key-b"); + let next_params = ListTracesParams::from(contracts::ListTracesParams { + cursor_ms: first[0].0.start_ms, + cursor_trace_id: first[0].0.trace_ref.clone(), + ..params.0 + }); + let next = fetch::(&fixture.database.client, &reader, &next_params).await?; + assert_eq!(next.len(), 1); + assert_eq!(next[0].0.api_key_hash, "key-alt"); + assert_ne!(first[0].0.trace_ref, next[0].0.trace_ref); + Ok(()) +} + +#[rstest] +#[case::authentication_error(include_bytes!("../../traces/tests/fixtures/deeplite_auth_error.json"))] +#[case::swarm(include_bytes!("../../traces/tests/fixtures/deeplite_swarm.json"))] +#[tokio::test] +async fn captured_deeplite_exports_round_trip_through_clickhouse( + #[future(awt)] migrated_database: TestResult, + admin_access: TestResult, + #[case] export: &[u8], +) -> TestResult { + let fixture = migrated_database?; + let decoded = insert_export(&fixture, export, "team-a", "key-a").await?; + let reader = fixture + .readers + .connection( + &fixture.database.client, + &QueryScope::Admin, + "fixture-secret", + ) + .await?; + let params = TraceSpansParams { + access: admin_access?, + trace_id: decoded[0].trace_id.clone(), + trace_ref: String::new(), + }; + let stored = fetch::(&fixture.database.client, &reader, ¶ms).await?; + assert_eq!(stored.len(), decoded.len()); + let list_params = ListTracesParams::from(contracts::ListTracesParams { + access: params.access, + start_ms: 0, + end_ms: i64::MAX / 1_000_000, + cursor_ms: 0, + cursor_trace_id: String::new(), + limit: 10, + }); + let traces = fetch::(&fixture.database.client, &reader, &list_params).await?; + assert_eq!(traces.len(), 1); + let roots = decoded + .iter() + .filter(|span| span.parent_span_id.is_empty()) + .collect::>(); + assert_eq!(roots.len(), 1); + assert_eq!(traces[0].0.status, roots[0].status_code); + assert_eq!( + traces[0].0.error_count, + decoded + .iter() + .filter(|span| span.status_code == "STATUS_CODE_ERROR") + .count() as u64 + ); + let by_id: BTreeMap<_, _> = stored + .iter() + .map(|row| (row.0.span_id.as_str(), &row.0)) + .collect(); + for span in &decoded { + let row = by_id + .get(span.span_id.as_str()) + .ok_or("missing captured span")?; + assert_eq!(row.parent_span_id, span.parent_span_id); + assert_eq!(row.start_ns as u64, span.start_ns); + assert_eq!(row.duration_ns, span.end_ns - span.start_ns); + assert_eq!(row.input_tokens, span.normalized.input_tokens); + assert_eq!(row.output_tokens, span.normalized.output_tokens); + assert_eq!(row.status, span.status_code); + } + Ok(()) +} diff --git a/litellm-rust/crates/traces-clickhouse/tests/queries/failed_spans.expected.json b/litellm-rust/crates/traces-clickhouse/tests/queries/failed_spans.expected.json new file mode 100644 index 00000000000..df5dfb1c254 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/tests/queries/failed_spans.expected.json @@ -0,0 +1,30 @@ +{ + "admin": [ + { + "team": "team-a", + "api_key": "key-a", + "trace_id": "01010101010101010101010101010101", + "span_id": "0303030303030303", + "message": "lookup timed out" + } + ], + "team": [ + { + "team": "team-a", + "api_key": "key-a", + "trace_id": "01010101010101010101010101010101", + "span_id": "0303030303030303", + "message": "lookup timed out" + } + ], + "key": [ + { + "team": "team-a", + "api_key": "key-a", + "trace_id": "01010101010101010101010101010101", + "span_id": "0303030303030303", + "message": "lookup timed out" + } + ], + "other_team": [] +} diff --git a/litellm-rust/crates/traces-clickhouse/tests/queries/failed_spans.sql b/litellm-rust/crates/traces-clickhouse/tests/queries/failed_spans.sql new file mode 100644 index 00000000000..72db132e198 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/tests/queries/failed_spans.sql @@ -0,0 +1,5 @@ +SELECT TeamId AS team, ApiKeyHash AS api_key, TraceId AS trace_id, + SpanId AS span_id, StatusMessage AS message +FROM otel_traces +WHERE StatusCode = 'STATUS_CODE_ERROR' +ORDER BY team, api_key, trace_id, span_id diff --git a/litellm-rust/crates/traces-clickhouse/tests/queries/metadata_filters.expected.json b/litellm-rust/crates/traces-clickhouse/tests/queries/metadata_filters.expected.json new file mode 100644 index 00000000000..791948f60a0 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/tests/queries/metadata_filters.expected.json @@ -0,0 +1,30 @@ +{ + "admin": [ + { + "team": "team-a", + "api_key": "key-a", + "request_id": "request-a", + "spend": 0.5, + "priority": "high" + } + ], + "team": [ + { + "team": "team-a", + "api_key": "key-a", + "request_id": "request-a", + "spend": 0.5, + "priority": "high" + } + ], + "key": [ + { + "team": "team-a", + "api_key": "key-a", + "request_id": "request-a", + "spend": 0.5, + "priority": "high" + } + ], + "other_team": [] +} diff --git a/litellm-rust/crates/traces-clickhouse/tests/queries/metadata_filters.sql b/litellm-rust/crates/traces-clickhouse/tests/queries/metadata_filters.sql new file mode 100644 index 00000000000..a9c88b33c74 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/tests/queries/metadata_filters.sql @@ -0,0 +1,5 @@ +SELECT team_id AS team, api_key, request_id, spend, + JSONExtractString(metadata, 'labels', 'priority') AS priority +FROM spend_logs FINAL +WHERE JSONExtractString(metadata, 'labels', 'priority') = 'high' +ORDER BY team, api_key, request_id diff --git a/litellm-rust/crates/traces-clickhouse/tests/queries/read_access.json b/litellm-rust/crates/traces-clickhouse/tests/queries/read_access.json new file mode 100644 index 00000000000..a743b382c20 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/tests/queries/read_access.json @@ -0,0 +1,6 @@ +{ + "all_teams": 1, + "user_id": "", + "team_ids": ["team-a", "team-b"], + "api_key_hash": "" +} diff --git a/litellm-rust/crates/traces-clickhouse/tests/queries/rollups.expected.json b/litellm-rust/crates/traces-clickhouse/tests/queries/rollups.expected.json new file mode 100644 index 00000000000..af24543bab3 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/tests/queries/rollups.expected.json @@ -0,0 +1,87 @@ +{ + "admin": [ + { + "team": "team-a", + "api_key": "key-a", + "trace_id": "01010101010101010101010101010101", + "name": "review", + "spans": 3, + "llm_calls": 1, + "errors": 1, + "input_tokens": 12, + "output_tokens": 6 + }, + { + "team": "team-a", + "api_key": "key-alt", + "trace_id": "01010101010101010101010101010101", + "name": "alternate", + "spans": 1, + "llm_calls": 0, + "errors": 0, + "input_tokens": 0, + "output_tokens": 0 + }, + { + "team": "team-b", + "api_key": "key-b", + "trace_id": "01010101010101010101010101010101", + "name": "other-team", + "spans": 1, + "llm_calls": 0, + "errors": 0, + "input_tokens": 0, + "output_tokens": 0 + } + ], + "team": [ + { + "team": "team-a", + "api_key": "key-a", + "trace_id": "01010101010101010101010101010101", + "name": "review", + "spans": 3, + "llm_calls": 1, + "errors": 1, + "input_tokens": 12, + "output_tokens": 6 + }, + { + "team": "team-a", + "api_key": "key-alt", + "trace_id": "01010101010101010101010101010101", + "name": "alternate", + "spans": 1, + "llm_calls": 0, + "errors": 0, + "input_tokens": 0, + "output_tokens": 0 + } + ], + "key": [ + { + "team": "team-a", + "api_key": "key-a", + "trace_id": "01010101010101010101010101010101", + "name": "review", + "spans": 3, + "llm_calls": 1, + "errors": 1, + "input_tokens": 12, + "output_tokens": 6 + } + ], + "other_team": [ + { + "team": "team-b", + "api_key": "key-b", + "trace_id": "01010101010101010101010101010101", + "name": "other-team", + "spans": 1, + "llm_calls": 0, + "errors": 0, + "input_tokens": 0, + "output_tokens": 0 + } + ] +} diff --git a/litellm-rust/crates/traces-clickhouse/tests/queries/rollups.sql b/litellm-rust/crates/traces-clickhouse/tests/queries/rollups.sql new file mode 100644 index 00000000000..9c470f0d355 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/tests/queries/rollups.sql @@ -0,0 +1,10 @@ +SELECT TeamId AS team, ApiKeyHash AS api_key, TraceId AS trace_id, + ifNull(any(RootName), '') AS name, + toUInt32(sum(SpanCount)) AS spans, + toUInt32(sum(LlmCount)) AS llm_calls, + toUInt32(sum(ErrorCount)) AS errors, + toUInt32(sum(InputTokens)) AS input_tokens, + toUInt32(sum(OutputTokens)) AS output_tokens +FROM agent_traces_by_key +GROUP BY TeamId, ApiKeyHash, TraceId +ORDER BY team, api_key, trace_id diff --git a/litellm-rust/crates/traces-clickhouse/tests/queries/support.rs b/litellm-rust/crates/traces-clickhouse/tests/queries/support.rs new file mode 100644 index 00000000000..1039d761e23 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/tests/queries/support.rs @@ -0,0 +1,153 @@ +use std::collections::BTreeMap; + +use litellm_traces::{DecodedSpan, decode_otlp}; +use litellm_traces_clickhouse::{ + Connection, InsertTable, QueryReaders, ensure_schema, insert_rows, +}; +use rstest::fixture; +use serde_json::{Value, json}; + +use crate::support::{ClickHouseDatabase, TestResult, database}; + +pub const DATABASE: &str = "trace_test"; + +pub struct SeededDatabase { + pub database: ClickHouseDatabase, + pub readers: QueryReaders, +} + +#[fixture] +pub async fn migrated_database( + #[future(awt)] database: TestResult, +) -> TestResult { + let database = database?; + let writer = Connection::writer(&database.url)?; + ensure_schema(&database.client, &writer, DATABASE, 7).await?; + for table in ["otel_traces", "agent_traces_by_key", "spend_logs"] { + database + .client + .post(writer.url().clone()) + .body(format!("ALTER TABLE {DATABASE}.{table} REMOVE TTL")) + .send() + .await? + .error_for_status()?; + database + .client + .post(writer.url().clone()) + .body(format!("SYSTEM STOP MERGES {DATABASE}.{table}")) + .send() + .await? + .error_for_status()?; + } + let readers = QueryReaders::new(writer, DATABASE.to_owned()); + Ok(SeededDatabase { database, readers }) +} + +#[fixture] +pub async fn seeded_database( + #[future(awt)] migrated_database: TestResult, +) -> TestResult { + let fixture = migrated_database?; + let writer = Connection::writer(&fixture.database.url)?; + for (contents, team, key) in [ + ( + include_bytes!("../../../traces/tests/fixtures/query_root.json").as_slice(), + "team-a", + "key-a", + ), + ( + include_bytes!("../../../traces/tests/fixtures/query_children.json").as_slice(), + "team-a", + "key-a", + ), + ( + include_bytes!("../../../traces/tests/fixtures/query_alternate.json").as_slice(), + "team-a", + "key-alt", + ), + ( + include_bytes!("../../../traces/tests/fixtures/query_other_team.json").as_slice(), + "team-b", + "key-b", + ), + ] { + insert_export(&fixture, contents, team, key).await?; + } + let spend_rows = include_str!("../fixtures/spend_logs.jsonl") + .lines() + .map(serde_json::from_str::>) + .collect::, _>>()?; + insert_rows( + &fixture.database.client, + &writer, + DATABASE, + InsertTable::SpendLogs, + spend_rows, + ) + .await?; + Ok(fixture) +} + +pub async fn insert_export( + fixture: &SeededDatabase, + contents: &[u8], + team: &str, + key: &str, +) -> TestResult> { + let spans = decode_otlp(contents, Some("application/json"))?; + let writer = Connection::writer(&fixture.database.url)?; + let rows = spans.iter().map(|span| span_row(span, team, key)).collect(); + insert_rows( + &fixture.database.client, + &writer, + DATABASE, + InsertTable::OtelTraces, + rows, + ) + .await?; + Ok(spans) +} + +fn span_row(span: &DecodedSpan, team: &str, key: &str) -> BTreeMap { + BTreeMap::from([ + ("Timestamp".into(), json!(span.start_ns)), + ("TraceId".into(), json!(span.trace_id)), + ("SpanId".into(), json!(span.span_id)), + ("ParentSpanId".into(), json!(span.parent_span_id)), + ("TraceState".into(), json!(span.trace_state)), + ("SpanName".into(), json!(span.name)), + ("SpanKind".into(), json!(span.kind)), + ( + "ServiceName".into(), + json!( + span.resource_attributes + .get("service.name") + .map(String::as_str) + .unwrap_or_default() + ), + ), + ("ResourceAttributes".into(), json!(span.resource_attributes)), + ("ScopeName".into(), json!(span.scope_name)), + ("ScopeVersion".into(), json!(span.scope_version)), + ("SpanAttributes".into(), json!(span.attributes)), + ("Duration".into(), json!(span.end_ns - span.start_ns)), + ("StatusCode".into(), json!(span.status_code)), + ("StatusMessage".into(), json!(span.status_message)), + ("TeamId".into(), json!(team)), + ("ApiKeyHash".into(), json!(key)), + ( + "ObservationType".into(), + json!(span.normalized.observation_type), + ), + ("AgentName".into(), json!(span.normalized.agent_name)), + ("Model".into(), json!(span.normalized.model)), + ( + "LiteLLMRequestId".into(), + json!(span.normalized.litellm_request_id), + ), + ("InputTokens".into(), json!(span.normalized.input_tokens)), + ("OutputTokens".into(), json!(span.normalized.output_tokens)), + ("Input".into(), json!(span.normalized.input)), + ("Output".into(), json!(span.normalized.output)), + ]) +} diff --git a/litellm-rust/crates/traces-clickhouse/tests/queries/trace_costs.expected.json b/litellm-rust/crates/traces-clickhouse/tests/queries/trace_costs.expected.json new file mode 100644 index 00000000000..314981b76b8 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/tests/queries/trace_costs.expected.json @@ -0,0 +1,40 @@ +{ + "admin": [ + { + "team": "team-a", + "api_key": "key-a", + "trace_id": "01010101010101010101010101010101", + "spend": 0.5 + }, + { + "team": "team-b", + "api_key": "key-b", + "trace_id": "01010101010101010101010101010101", + "spend": 0.25 + } + ], + "team": [ + { + "team": "team-a", + "api_key": "key-a", + "trace_id": "01010101010101010101010101010101", + "spend": 0.5 + } + ], + "key": [ + { + "team": "team-a", + "api_key": "key-a", + "trace_id": "01010101010101010101010101010101", + "spend": 0.5 + } + ], + "other_team": [ + { + "team": "team-b", + "api_key": "key-b", + "trace_id": "01010101010101010101010101010101", + "spend": 0.25 + } + ] +} diff --git a/litellm-rust/crates/traces-clickhouse/tests/queries/trace_costs.sql b/litellm-rust/crates/traces-clickhouse/tests/queries/trace_costs.sql new file mode 100644 index 00000000000..42ee655229e --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/tests/queries/trace_costs.sql @@ -0,0 +1,9 @@ +SELECT o.TeamId AS team, o.ApiKeyHash AS api_key, o.TraceId AS trace_id, + sum(s.spend) AS spend +FROM otel_traces AS o +INNER JOIN (SELECT * FROM spend_logs FINAL) AS s + ON o.TeamId = s.team_id + AND o.ApiKeyHash = s.api_key + AND o.LiteLLMRequestId = s.response_id +GROUP BY o.TeamId, o.ApiKeyHash, o.TraceId +ORDER BY team, api_key, trace_id diff --git a/litellm-rust/crates/traces-clickhouse/tests/query_access.rs b/litellm-rust/crates/traces-clickhouse/tests/query_access.rs new file mode 100644 index 00000000000..d4c7c886bd0 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/tests/query_access.rs @@ -0,0 +1,268 @@ +use std::collections::BTreeMap; + +use litellm_http::Client; +use litellm_traces_clickhouse::{ + Connection, Error, QueryReaders, QueryScope, ensure_schema, query_help, query_sql, +}; +use rstest::{fixture, rstest}; +use serde_json::{Value, json}; +mod support; + +use support::{ClickHouseDatabase, database as start_database}; + +struct Database { + _database: ClickHouseDatabase, + client: Client, + writer: Connection, + readers: QueryReaders, +} + +#[fixture] +async fn database() -> Result> { + let instance = start_database().await?; + let url = instance.url.clone(); + let client = instance.client.clone(); + let writer = Connection::parse(&url)?; + ensure_schema(&client, &writer, "trace_test", 7).await?; + for sql in [ + "INSERT INTO trace_test.otel_traces (TeamId, ApiKeyHash, TraceId, SpanId, Timestamp, SpanAttributes, UserId) VALUES ('team-a', 'key-a1', 'shared-trace', 'a1', now(), map('visible', 'a'), 'owner'), ('team-a', 'key-a2', 'shared-trace', 'a2', now(), map('visible', 'a'), 'other'), ('team-b', 'key-b', 'shared-trace', 'b', now(), map('secret-b', 'b'), 'owner'), ('', 'key-teamless', 'shared-trace', 'teamless', now(), map('visible', 'teamless'), ''), ('', 'key-other', 'shared-trace', 'other-teamless', now(), map('visible', 'other'), '')", + "INSERT INTO trace_test.spend_logs (team_id, api_key, request_id, start_time, end_time, metadata, user) VALUES ('team-a', 'key-a1', 'a1', now(), now(), '{\"visible\":1}', 'owner'), ('team-a', 'key-a2', 'a2', now(), now(), '{\"visible\":1}', 'other'), ('team-b', 'key-b', 'b', now(), now(), '{\"secret_b\":1}', 'owner'), ('', 'key-teamless', 'teamless', now(), now(), '{}', ''), ('', 'key-other', 'other-teamless', now(), now(), '{}', '')", + "CREATE TABLE trace_test.private_data (secret String) ENGINE = Memory", + "INSERT INTO trace_test.private_data VALUES ('hidden')", + ] { + let response = client.post(writer.url().clone()).body(sql).send().await?; + assert!(response.status().is_success(), "{}", response.text().await?); + } + let readers = QueryReaders::new(writer.clone(), "trace_test".to_owned()); + Ok(Database { + _database: instance, + client, + writer, + readers, + }) +} + +#[rstest] +#[case::own_user(QueryScope::Logs { user_id: "owner".into(), team_ids: vec![], api_key_hash: "".into() }, vec!["a1", "b"])] +#[case::own_user_and_permitted_team(QueryScope::Logs { user_id: "owner".into(), team_ids: vec!["team-a".into()], api_key_hash: "".into() }, vec!["a1", "a2", "b"])] +#[case::key_only_logs(QueryScope::Logs { user_id: "".into(), team_ids: vec![], api_key_hash: "key-teamless".into() }, vec!["teamless"])] +#[case::quoted_user(QueryScope::Logs { user_id: "owner' OR 1=1 --".into(), team_ids: vec![], api_key_hash: "".into() }, vec![])] +#[case::team(QueryScope::Team { team_id: "team-a".to_owned() }, vec!["a1", "a2"])] +#[case::project_key(QueryScope::Key { team_id: "team-a".to_owned(), api_key_hash: "key-a1".to_owned() }, vec!["a1"])] +#[case::teamless_key(QueryScope::Key { team_id: "".to_owned(), api_key_hash: "key-teamless".to_owned() }, vec!["teamless"])] +#[case::admin(QueryScope::Admin, vec!["a1", "a2", "b", "other-teamless", "teamless"])] +#[case::quoted_team(QueryScope::Team { team_id: "team-a' OR 1=1 --\\".to_owned() }, vec![])] +#[tokio::test] +async fn queries_and_help_are_scoped_by_the_database( + #[future(awt)] database: Result>, + #[case] scope: QueryScope, + #[case] expected: Vec<&str>, +) -> Result<(), Box> { + let database = database?; + let reader = database + .readers + .connection(&database.client, &scope, "test-master-secret") + .await?; + let queries = [ + "SELECT SpanId AS id FROM otel_traces ORDER BY id", + "SELECT SpanId AS id FROM trace_test.otel_traces WHERE 1 = 1 ORDER BY id", + "SELECT SpanId AS id FROM merge('trace_test', '^otel_traces$') ORDER BY id", + "WITH source AS (SELECT * FROM trace_test.otel_traces) SELECT SpanId AS id FROM source ORDER BY id", + "SELECT id FROM (SELECT SpanId AS id FROM otel_traces UNION DISTINCT SELECT SpanId AS id FROM trace_test.otel_traces) ORDER BY id", + "SELECT t.SpanId AS id FROM otel_traces t INNER JOIN spend_logs s ON t.SpanId = s.request_id ORDER BY id", + "SELECT request_id AS id FROM spend_logs FINAL ORDER BY id", + ]; + for sql in queries { + let body: Value = serde_json::from_str(&query_sql(&database.client, &reader, sql).await?)?; + assert_eq!( + body["data"], + json!( + expected + .iter() + .map(|id| json!({"id": id})) + .collect::>() + ), + "{sql}" + ); + } + let summary: Value = serde_json::from_str( + &query_sql( + &database.client, + &reader, + "SELECT sum(SpanCount) AS count FROM agent_traces_by_key", + ) + .await?, + )?; + assert_eq!(summary["data"][0]["count"], json!(expected.len())); + let help = query_help(&database.client, &reader).await?; + assert_eq!(help.contains("secret_b"), expected.contains(&"b")); + assert_eq!(help.contains("secret-b"), expected.contains(&"b")); + let recreated = QueryReaders::new(database.writer.clone(), "trace_test".to_owned()); + let repeated = recreated + .connection(&database.client, &scope, "test-master-secret") + .await?; + assert_eq!(reader.url(), repeated.url()); + Ok(()) +} + +#[rstest] +#[tokio::test] +async fn rotating_master_secret_revokes_previous_reader_credentials( + #[future(awt)] database: Result>, +) -> Result<(), Box> { + let database = database?; + let scope = QueryScope::Team { + team_id: "team-a".to_owned(), + }; + let old_reader = database + .readers + .connection(&database.client, &scope, "old-master-secret") + .await?; + let old_result = query_sql( + &database.client, + &old_reader, + "SELECT SpanId AS id FROM otel_traces ORDER BY id", + ) + .await?; + let old_rows: Value = serde_json::from_str(&old_result)?; + assert_eq!(old_rows["data"], json!([{ "id": "a1" }, { "id": "a2" }])); + + let rotated_readers = QueryReaders::new(database.writer.clone(), "trace_test".into()); + let new_reader = rotated_readers + .connection(&database.client, &scope, "new-master-secret") + .await?; + assert!( + query_sql( + &database.client, + &old_reader, + "SELECT SpanId AS id FROM otel_traces ORDER BY id", + ) + .await + .is_err() + ); + let new_result = query_sql( + &database.client, + &new_reader, + "SELECT SpanId AS id FROM otel_traces ORDER BY id", + ) + .await?; + let new_rows: Value = serde_json::from_str(&new_result)?; + assert_eq!(new_rows["data"], json!([{ "id": "a1" }, { "id": "a2" }])); + assert_eq!(old_reader.url().username(), new_reader.url().username()); + assert_ne!(old_reader.url().password(), new_reader.url().password()); + Ok(()) +} + +#[rstest] +#[tokio::test] +async fn managed_reader_rejects_privilege_and_scope_bypasses( + #[future(awt)] database: Result>, +) -> Result<(), Box> { + let database = database?; + let scope = QueryScope::Team { + team_id: "team-a".to_owned(), + }; + let reader = database + .readers + .connection(&database.client, &scope, "test-master-secret") + .await?; + for sql in [ + "INSERT INTO otel_traces (TraceId) VALUES ('injected')", + "DROP TABLE otel_traces", + "SELECT * FROM private_data", + "SELECT * FROM otel_traces SETTINGS readonly = 0", + "SELECT * FROM otel_traces SETTINGS max_memory_usage = 0", + "SELECT * FROM otel_traces SETTINGS max_execution_time = 0", + "CREATE USER scope_bypass", + "CREATE NAMED COLLECTION scope_bypass AS host = 'localhost'", + "BACKUP TABLE otel_traces TO Disk('default', 'scope-bypass')", + "SELECT * FROM url('http://127.0.0.1:1/', 'LineAsString', 'line String')", + "SELECT * FROM remote('127.0.0.1', 'trace_test', 'otel_traces')", + ] { + assert!( + matches!( + query_sql(&database.client, &reader, sql).await, + Err(Error::Storage( + litellm_storage_clickhouse::Error::QueryFailed(_) + )) + ), + "{sql}" + ); + } + let roles: Value = serde_json::from_str( + &query_sql(&database.client, &reader, "SELECT enabledRoles() AS roles").await?, + )?; + assert_eq!(roles["data"], json!([{ "roles": [] }])); + let rows: Value = serde_json::from_str( + &query_sql( + &database.client, + &reader, + "SELECT DISTINCT TeamId FROM otel_traces", + ) + .await?, + )?; + assert_eq!(rows["data"], json!([{ "TeamId": "team-a" }])); + Ok(()) +} + +#[rstest] +#[tokio::test] +async fn provisioning_failure_never_returns_a_writer_connection( + #[future(awt)] database: Result>, +) -> Result<(), Box> { + let database = database?; + let reader = database + .readers + .connection(&database.client, &QueryScope::Admin, "test-master-secret") + .await?; + let no_provision_privileges = QueryReaders::new(reader, "trace_test".to_owned()); + let result = no_provision_privileges + .connection( + &database.client, + &QueryScope::Team { + team_id: "team-a".to_owned(), + }, + "other-secret", + ) + .await; + assert!(matches!( + result, + Err(Error::Cached(source)) if matches!(source.as_ref(), Error::ProvisionFailed(_)) + )); + assert!(matches!( + database + .readers + .connection(&database.client, &QueryScope::Admin, "") + .await, + Err(Error::MissingSecret) + )); + assert!(matches!( + database + .readers + .connection( + &database.client, + &QueryScope::Team { + team_id: String::new() + }, + "test-master-secret" + ) + .await, + Err(Error::InvalidScope) + )); + let permits = (0..8) + .map(|_| database.readers.acquire()) + .collect::, _>>()?; + assert!(matches!(database.readers.acquire(), Err(Error::Busy))); + drop(permits); + assert!(database.readers.acquire().is_ok()); + let rows = litellm_traces_clickhouse::execute_read( + &database.client, + &database.writer, + "SELECT count() AS count FROM trace_test.otel_traces", + &BTreeMap::new(), + ) + .await?; + let rows: Value = serde_json::from_str(&rows)?; + assert_eq!(rows["data"][0]["count"], 5); + Ok(()) +} diff --git a/litellm-rust/crates/traces-clickhouse/tests/support/mod.rs b/litellm-rust/crates/traces-clickhouse/tests/support/mod.rs new file mode 100644 index 00000000000..a27e30c6806 --- /dev/null +++ b/litellm-rust/crates/traces-clickhouse/tests/support/mod.rs @@ -0,0 +1,36 @@ +use litellm_http::Client; +use rstest::fixture; +use testcontainers_modules::{ + clickhouse::ClickHouse, + testcontainers::{ContainerAsync, ImageExt, runners::AsyncRunner}, +}; + +const CLICKHOUSE_TAG: &str = + "26.9.6.6@sha256:eb4870e7ca7ed70c259eebfcfbee6cf797017f6b5436c2926bbbfe3d4d28486e"; + +pub type TestResult = Result>; + +pub struct ClickHouseDatabase { + _container: ContainerAsync, + pub url: String, + pub client: Client, +} + +#[fixture] +pub async fn database() -> TestResult { + let container = ClickHouse::default() + .with_tag(CLICKHOUSE_TAG) + .with_env_var("CLICKHOUSE_SKIP_USER_SETUP", "1") + .start() + .await?; + let url = format!( + "http://{}:{}", + container.get_host().await?, + container.get_host_port_ipv4(8123).await? + ); + Ok(ClickHouseDatabase { + _container: container, + url, + client: Client::no_redirect_for_test(), + }) +} diff --git a/litellm-rust/crates/traces/AGENTS.md b/litellm-rust/crates/traces/AGENTS.md index d0181c53308..a9249f31aa8 100644 --- a/litellm-rust/crates/traces/AGENTS.md +++ b/litellm-rust/crates/traces/AGENTS.md @@ -1,7 +1,6 @@ -- Keep OTLP decoding, trace schema, row encoding and named query selection here. Generic ClickHouse connections and HTTP execution belong in `litellm-storage-clickhouse` -- Keep this crate independent of Python; PyO3 conversion and public Python exceptions belong in `python-bridge` -- Keep the SQL migrations here as the only ClickHouse schema definition, as `migrations/NNNN_description.sql` files embedded by `litellm_migrate::migrate!`; adding a file is the only step -- Use typed query parameters and a dedicated SELECT-only reader with server-side limits -- Keep `config/reader.xml` grants on the database the schema is created in (CLICKHOUSE_DATABASE, default `litellm`) -- Bound insert time and encoded bytes; make retry deduplication behavior explicit for supported ClickHouse versions -- Test storage behavior through the crate's public API against ClickHouse +- Own OTLP decoding, normalization, shared authorization and named query contracts; remain independent of storage and Python +- Never depend on `litellm-traces-clickhouse` or `litellm-storage-clickhouse` +- Preserve decoding limits, normalization precedence and shared resource identity +- Keep ClickHouse schema, row encoding and queries in `litellm-traces-clickhouse`; keep PyO3 conversion in `python-bridge` +- Test decoding and normalization through the public API +- Expose one top-level `Error` enum in `src/error.rs` for decoding and normalization failures diff --git a/litellm-rust/crates/traces/Cargo.toml b/litellm-rust/crates/traces/Cargo.toml index 5e3b41e719a..1949eb2a260 100644 --- a/litellm-rust/crates/traces/Cargo.toml +++ b/litellm-rust/crates/traces/Cargo.toml @@ -6,34 +6,17 @@ license.workspace = true repository.workspace = true [dependencies] -askama.workspace = true -base64.workspace = true -flate2.workspace = true -futures-util.workspace = true -hmac = "0.12.1" indexmap = { version = "2", features = ["serde"] } -moka.workspace = true opentelemetry-proto = { workspace = true, features = ["gen-tonic-messages", "trace", "with-serde"] } prost.workspace = true -time = { workspace = true, features = ["formatting"] } -litellm-http.workspace = true -litellm-migrate.workspace = true -litellm-storage-clickhouse.workspace = true -sha2.workspace = true serde = { workspace = true, features = ["rc"] } serde_json.workspace = true strum.workspace = true thiserror.workspace = true -tokio.workspace = true -url.workspace = true [dev-dependencies] criterion.workspace = true -litellm-http = { workspace = true, features = ["test-support"] } rstest.workspace = true -testcontainers-modules = { version = "0.15.0", features = ["clickhouse"] } -tokio.workspace = true -wiremock.workspace = true [[bench]] name = "resource-fanout" diff --git a/litellm-rust/crates/traces/config/reader.xml b/litellm-rust/crates/traces/config/reader.xml deleted file mode 100644 index 3ab337a13fc..00000000000 --- a/litellm-rust/crates/traces/config/reader.xml +++ /dev/null @@ -1,32 +0,0 @@ - - - - 1 - 10 - 1000 - 4194304 - throw - 268435456 - - - - - - - - - - - - - - ::/0 - litellm_traces_reader - - GRANT SELECT ON litellm.otel_traces - GRANT SELECT ON litellm.agent_traces_by_key - GRANT SELECT ON litellm.spend_logs - - - - diff --git a/litellm-rust/crates/traces/query/span_detail.sql b/litellm-rust/crates/traces/query/span_detail.sql deleted file mode 100644 index ddc1f08b5d2..00000000000 --- a/litellm-rust/crates/traces/query/span_detail.sql +++ /dev/null @@ -1,19 +0,0 @@ -SELECT o.SpanId AS span_id, o.Input AS input, - if(o.Output = '' AND o.ObservationType = 'agent', answer.output, o.Output) AS output, - o.SpanAttributes AS attributes -FROM otel_traces AS o -LEFT JOIN ( - SELECT ParentSpanId AS parent_span_id, argMax(Output, Timestamp) AS output - FROM otel_traces - WHERE TraceId = {trace_id:String} AND ParentSpanId = {span_id:String} - AND ObservationType = 'llm' AND Output != '' - AND (empty({team_ids:Array(String)}) OR TeamId IN {team_ids:Array(String)}) - AND ({api_key_hash:String} = '' OR ApiKeyHash = {api_key_hash:String}) - GROUP BY ParentSpanId -) AS answer ON answer.parent_span_id = o.SpanId -WHERE o.TraceId = {trace_id:String} AND o.SpanId = {span_id:String} - AND (empty({team_ids:Array(String)}) OR o.TeamId IN {team_ids:Array(String)}) - AND ({api_key_hash:String} = '' OR o.ApiKeyHash = {api_key_hash:String}) - AND ({trace_ref:String} = '' OR - hex(SHA256(concat(o.TeamId, char(0), o.ApiKeyHash, char(0), o.TraceId))) = {trace_ref:String}) -LIMIT 1 diff --git a/litellm-rust/crates/traces/query/spend_by_response_ids.sql b/litellm-rust/crates/traces/query/spend_by_response_ids.sql deleted file mode 100644 index 285e9235629..00000000000 --- a/litellm-rust/crates/traces/query/spend_by_response_ids.sql +++ /dev/null @@ -1,9 +0,0 @@ -SELECT request_id, response_id, team_id, api_key, spend, - toUnixTimestamp64Milli(start_time) AS start_ms -FROM spend_logs FINAL -WHERE response_id IN {response_ids:Array(String)} - AND start_time >= fromUnixTimestamp64Milli({start_ms:Int64}) - AND start_time < fromUnixTimestamp64Milli({end_ms:Int64}) - AND (empty({team_ids:Array(String)}) OR team_id IN {team_ids:Array(String)}) - AND ({api_key_hash:String} = '' OR api_key = {api_key_hash:String}) -ORDER BY start_time DESC diff --git a/litellm-rust/crates/traces/src/error.rs b/litellm-rust/crates/traces/src/error.rs index c677e73e96f..b45ff21140c 100644 --- a/litellm-rust/crates/traces/src/error.rs +++ b/litellm-rust/crates/traces/src/error.rs @@ -1,5 +1,5 @@ #[derive(Debug, thiserror::Error)] -pub enum DecodeError { +pub enum Error { #[error("invalid OTLP trace payload")] InvalidPayload, #[error("OTLP trace payload exceeds the decoding budget")] @@ -9,21 +9,9 @@ pub enum DecodeError { } #[derive(Debug, thiserror::Error)] -pub enum QueryAccessError { - #[error("trace SQL queries require a configured proxy master key")] - MissingSecret, - #[error("invalid trace query scope")] - InvalidScope, - #[error("trace SQL query concurrency limit exceeded")] - Busy, - #[error( - "ClickHouse reader provisioning failed with HTTP status {0}; the configured connection must be allowed to manage users, row policies, and SELECT grants on the trace tables" - )] - ProvisionFailed(u16), - #[error("ClickHouse reader provisioning transport failed")] - ProvisionTransport, - #[error(transparent)] - Storage(#[from] litellm_storage_clickhouse::Error), - #[error(transparent)] - Cached(#[from] std::sync::Arc), -} +#[error("invalid trace query scope")] +pub struct InvalidScope; + +#[derive(Debug, thiserror::Error)] +#[error("unknown ClickHouse read query")] +pub struct InvalidQuery; diff --git a/litellm-rust/crates/traces/src/lib.rs b/litellm-rust/crates/traces/src/lib.rs index 05b56c7ea46..369a0adb403 100644 --- a/litellm-rust/crates/traces/src/lib.rs +++ b/litellm-rust/crates/traces/src/lib.rs @@ -1,25 +1,13 @@ -mod config; mod error; -mod insert; mod normalize; mod otlp; -mod query; +pub mod query; mod query_access; -mod schema; mod shared; -mod sql; -pub use config::Config; -pub use error::{DecodeError, QueryAccessError}; -pub use insert::{InsertRow, InsertTable, encode_rows, insert_rows, insert_shared_rows}; -pub use litellm_storage_clickhouse::{Connection, Error, Parameter, execute_read}; -pub use normalize::{ - NORMALIZED_FIELD_DEFINITIONS, NormalizedFieldDefinition, NormalizedSpan, ObservationType, -}; +pub use error::{Error, InvalidQuery, InvalidScope}; +pub use normalize::{NormalizedSpan, ObservationType}; pub use otlp::{DecodedSpan, decode_otlp}; -pub use query_access::{QueryReaders, QueryScope}; -pub use schema::{ensure_schema, schema_statements}; +pub use query::ReadQuery; +pub use query_access::QueryScope; pub use shared::{Shared, SharedIdentity}; -pub use sql::{LensQuery, ReadQuery, execute_named_read}; - -pub use query::{query_help, query_sql}; diff --git a/litellm-rust/crates/traces/src/normalize/claude_code.rs b/litellm-rust/crates/traces/src/normalize/claude_code.rs index 3fb9a1767ed..513702d2f34 100644 --- a/litellm-rust/crates/traces/src/normalize/claude_code.rs +++ b/litellm-rust/crates/traces/src/normalize/claude_code.rs @@ -3,7 +3,7 @@ use std::collections::BTreeMap; use serde_json::{Map, Value, json}; use super::{NormalizedSpan, ObservationType, SpanNormalizer, attr, first, tokens}; -use crate::{DecodeError, otlp::DecodedEvent}; +use crate::{Error, otlp::DecodedEvent}; pub(crate) const CLAUDE_CODE_SCOPE: &str = "com.anthropic.claude_code.tracing"; pub(crate) const CLAUDE_CODE_AGENT: &str = "claude-code"; @@ -144,13 +144,13 @@ fn llm_output(attributes: &BTreeMap) -> String { } } -fn input_tokens(attributes: &BTreeMap) -> Result { +fn input_tokens(attributes: &BTreeMap) -> Result { ["input_tokens", "cache_read_tokens", "cache_creation_tokens"] .into_iter() .try_fold(0u32, |total, key| { total .checked_add(tokens(attributes, key)?) - .ok_or(DecodeError::TokenCountOutOfRange) + .ok_or(Error::TokenCountOutOfRange) }) } @@ -180,7 +180,7 @@ impl SpanNormalizer for ClaudeCodeNormalizer { _parent_span_id: &str, attributes: &BTreeMap, events: &[DecodedEvent], - ) -> Result { + ) -> Result { let base = NormalizedSpan { observation_type: ObservationType::Framework, agent_name: CLAUDE_CODE_AGENT.to_owned(), @@ -228,7 +228,7 @@ mod tests { use serde_json::Value; use super::{CLAUDE_CODE_SCOPE, ClaudeCodeNormalizer, SpanNormalizer}; - use crate::{DecodeError, normalize::ObservationType, otlp::DecodedEvent}; + use crate::{Error, normalize::ObservationType, otlp::DecodedEvent}; fn attributes(pairs: &[(&str, &str)]) -> BTreeMap { pairs @@ -341,7 +341,7 @@ mod tests { ]), &[], ); - assert!(matches!(result, Err(DecodeError::TokenCountOutOfRange))); + assert!(matches!(result, Err(Error::TokenCountOutOfRange))); } #[rstest] diff --git a/litellm-rust/crates/traces/src/normalize/genai.rs b/litellm-rust/crates/traces/src/normalize/genai.rs index cb52f1e55ff..f5460a5a014 100644 --- a/litellm-rust/crates/traces/src/normalize/genai.rs +++ b/litellm-rust/crates/traces/src/normalize/genai.rs @@ -1,7 +1,7 @@ use std::collections::BTreeMap; use super::{NormalizedSpan, ObservationType, SpanNormalizer, attr, first, usage_tokens}; -use crate::{DecodeError, otlp::DecodedEvent}; +use crate::{Error, otlp::DecodedEvent}; pub(super) struct GenAiNormalizer; @@ -31,7 +31,7 @@ impl SpanNormalizer for GenAiNormalizer { parent_span_id: &str, attributes: &BTreeMap, _events: &[DecodedEvent], - ) -> Result { + ) -> Result { let (input_tokens, output_tokens) = usage_tokens(attributes)?; let observation_type = match attr(attributes, "gen_ai.operation.name") { "invoke_agent" => ObservationType::Agent, diff --git a/litellm-rust/crates/traces/src/normalize/langsmith.rs b/litellm-rust/crates/traces/src/normalize/langsmith.rs index 60c6bc974c8..7e5d84362f0 100644 --- a/litellm-rust/crates/traces/src/normalize/langsmith.rs +++ b/litellm-rust/crates/traces/src/normalize/langsmith.rs @@ -5,7 +5,7 @@ use serde::{Deserialize, Deserializer, Serialize, de::DeserializeOwned}; use serde_json::{Value, ser::Formatter}; use super::{NormalizedSpan, ObservationType, SpanNormalizer, attr, usage_tokens}; -use crate::{DecodeError, otlp::DecodedEvent}; +use crate::{Error, otlp::DecodedEvent}; pub(super) struct LangSmithNormalizer; @@ -405,7 +405,7 @@ impl SpanNormalizer for LangSmithNormalizer { parent_span_id: &str, attributes: &BTreeMap, _events: &[DecodedEvent], - ) -> Result { + ) -> Result { let (input_tokens, output_tokens) = usage_tokens(attributes)?; let observation_type = span_type(name, parent_span_id, attributes); let io = span_io(observation_type, attributes); diff --git a/litellm-rust/crates/traces/src/normalize/mod.rs b/litellm-rust/crates/traces/src/normalize/mod.rs index 38191e705fc..8b6cc5fa372 100644 --- a/litellm-rust/crates/traces/src/normalize/mod.rs +++ b/litellm-rust/crates/traces/src/normalize/mod.rs @@ -1,6 +1,6 @@ use std::collections::BTreeMap; -use crate::{DecodeError, otlp::DecodedEvent}; +use crate::{Error, otlp::DecodedEvent}; use serde::{Deserialize, Serialize}; #[derive(Clone, Copy, Debug, Eq, PartialEq, Serialize)] @@ -32,71 +32,6 @@ pub(crate) struct Normalization { pub consumed_attributes: [&'static str; 2], } -#[derive(Clone, Copy, Debug, Eq, PartialEq, Serialize)] -pub struct NormalizedFieldDefinition { - pub name: &'static str, - pub clickhouse_column: &'static str, - pub clickhouse_type: &'static str, - pub meaning: &'static str, -} - -pub const NORMALIZED_FIELD_DEFINITIONS: [NormalizedFieldDefinition; 9] = [ - NormalizedFieldDefinition { - name: "observation_type", - clickhouse_column: "ObservationType", - clickhouse_type: "LowCardinality(String)", - meaning: "Agent, LLM, tool, chain, or framework span", - }, - NormalizedFieldDefinition { - name: "agent_name", - clickhouse_column: "AgentName", - clickhouse_type: "LowCardinality(String)", - meaning: "Agent associated with this span", - }, - NormalizedFieldDefinition { - name: "framework", - clickhouse_column: "Framework", - clickhouse_type: "LowCardinality(String)", - meaning: "Agent framework or SDK that emitted this span, e.g. claude-agent-sdk", - }, - NormalizedFieldDefinition { - name: "litellm_request_id", - clickhouse_column: "LiteLLMRequestId", - clickhouse_type: "String", - meaning: "LiteLLM response ID used to link a span to a spend log", - }, - NormalizedFieldDefinition { - name: "model", - clickhouse_column: "Model", - clickhouse_type: "LowCardinality(String)", - meaning: "Model used by this span", - }, - NormalizedFieldDefinition { - name: "input_tokens", - clickhouse_column: "InputTokens", - clickhouse_type: "UInt32", - meaning: "Input token count", - }, - NormalizedFieldDefinition { - name: "output_tokens", - clickhouse_column: "OutputTokens", - clickhouse_type: "UInt32", - meaning: "Output token count", - }, - NormalizedFieldDefinition { - name: "input", - clickhouse_column: "Input", - clickhouse_type: "String", - meaning: "Normalized input payload", - }, - NormalizedFieldDefinition { - name: "output", - clickhouse_column: "Output", - clickhouse_type: "String", - meaning: "Normalized output payload", - }, -]; - trait SpanNormalizer { fn matches(&self, scope_name: &str, attributes: &BTreeMap) -> bool; fn consumed_attributes(&self, attributes: &BTreeMap) -> [&'static str; 2]; @@ -106,7 +41,7 @@ trait SpanNormalizer { parent_span_id: &str, attributes: &BTreeMap, events: &[DecodedEvent], - ) -> Result; + ) -> Result; fn display_name(&self, _attributes: &BTreeMap) -> Option { None } @@ -136,27 +71,27 @@ fn first<'a>(attributes: &'a BTreeMap, left: &str, right: &str) } } -fn tokens(attributes: &BTreeMap, key: &str) -> Result { +fn tokens(attributes: &BTreeMap, key: &str) -> Result { let value = attr(attributes, key).trim(); if value.is_empty() { return Ok(0); } match value.parse::() { Ok(number) if (0..=u32::MAX as i128).contains(&number) => Ok(number as u32), - Ok(_) => Err(DecodeError::TokenCountOutOfRange), + Ok(_) => Err(Error::TokenCountOutOfRange), Err(_) if value .trim_start_matches(['+', '-']) .bytes() .all(|byte| byte.is_ascii_digit()) => { - Err(DecodeError::TokenCountOutOfRange) + Err(Error::TokenCountOutOfRange) } Err(_) => Ok(0), } } -fn usage_tokens(attributes: &BTreeMap) -> Result<(u32, u32), DecodeError> { +fn usage_tokens(attributes: &BTreeMap) -> Result<(u32, u32), Error> { Ok(( tokens(attributes, "gen_ai.usage.input_tokens")?, tokens(attributes, "gen_ai.usage.output_tokens")?, @@ -223,7 +158,7 @@ pub fn normalize( parent_span_id: &str, attributes: &BTreeMap, events: &[DecodedEvent], -) -> Result { +) -> Result { let normalizers: [&dyn SpanNormalizer; 4] = [ &ClaudeCodeNormalizer, &LangSmithNormalizer, @@ -257,11 +192,11 @@ pub fn normalize( #[cfg(test)] mod tests { - use std::collections::{BTreeMap, BTreeSet}; + use std::collections::BTreeMap; use rstest::rstest; - use super::{NORMALIZED_FIELD_DEFINITIONS, ObservationType, normalize}; + use super::{ObservationType, normalize}; #[rstest] #[case::langsmith("langsmith", [("langsmith.span.kind", "llm"), ("openinference.span.kind", "TOOL")], ObservationType::Llm)] @@ -286,25 +221,6 @@ mod tests { } } - #[rstest] - fn field_definitions_match_serialized_normalized_span() { - let fields = normalize("", "root", "", &BTreeMap::new(), &[]) - .expect("valid tokens") - .span; - let serialized = serde_json::to_value(fields).expect("serializable fields"); - let keys: BTreeSet<_> = serialized - .as_object() - .expect("field object") - .keys() - .map(String::as_str) - .collect(); - let mapped: BTreeSet<_> = NORMALIZED_FIELD_DEFINITIONS - .iter() - .map(|field| field.name) - .collect(); - assert_eq!(keys, mapped); - } - #[rstest] fn token_counts_accept_surrounding_whitespace() { let attributes = diff --git a/litellm-rust/crates/traces/src/normalize/openinference.rs b/litellm-rust/crates/traces/src/normalize/openinference.rs index 68d986a3f9f..e8c222020a1 100644 --- a/litellm-rust/crates/traces/src/normalize/openinference.rs +++ b/litellm-rust/crates/traces/src/normalize/openinference.rs @@ -1,7 +1,7 @@ use std::collections::BTreeMap; use super::{NormalizedSpan, ObservationType, SpanNormalizer, attr, tokens, usage_tokens}; -use crate::{DecodeError, otlp::DecodedEvent}; +use crate::{Error, otlp::DecodedEvent}; pub(super) struct OpenInferenceNormalizer; @@ -20,7 +20,7 @@ impl SpanNormalizer for OpenInferenceNormalizer { parent_span_id: &str, attributes: &BTreeMap, _events: &[DecodedEvent], - ) -> Result { + ) -> Result { let (usage_input, usage_output) = usage_tokens(attributes)?; let observation_type = match attr(attributes, "openinference.span.kind") .to_ascii_uppercase() diff --git a/litellm-rust/crates/traces/src/otlp/attributes.rs b/litellm-rust/crates/traces/src/otlp/attributes.rs index 50e063e4582..fb3f627697a 100644 --- a/litellm-rust/crates/traces/src/otlp/attributes.rs +++ b/litellm-rust/crates/traces/src/otlp/attributes.rs @@ -9,7 +9,7 @@ use serde::{ }; use super::limits::{Budget, MAX_ATTRIBUTES}; -use crate::DecodeError; +use crate::Error; struct AttributeWriter<'a> { body: Vec, @@ -32,9 +32,9 @@ impl Write for AttributeWriter<'_> { pub(super) fn attributes( values: Vec, budget: &mut Budget, -) -> Result, DecodeError> { +) -> Result, Error> { if values.len() > MAX_ATTRIBUTES { - return Err(DecodeError::TooLarge); + return Err(Error::TooLarge); } values .into_iter() @@ -59,8 +59,8 @@ pub(super) fn attributes( budget, }; serde_json::to_writer(&mut writer, &AttributeJson(value.as_ref())) - .map_err(|_| DecodeError::TooLarge)?; - String::from_utf8(writer.body).map_err(|_| DecodeError::InvalidPayload)? + .map_err(|_| Error::TooLarge)?; + String::from_utf8(writer.body).map_err(|_| Error::InvalidPayload)? } }; Ok((entry.key, text)) diff --git a/litellm-rust/crates/traces/src/otlp/limits.rs b/litellm-rust/crates/traces/src/otlp/limits.rs index f6b56ccf12d..ca1ac144346 100644 --- a/litellm-rust/crates/traces/src/otlp/limits.rs +++ b/litellm-rust/crates/traces/src/otlp/limits.rs @@ -3,7 +3,7 @@ use std::fmt; use prost::encoding::{DecodeContext, WireType, decode_key, decode_varint, skip_field}; use serde::de::{DeserializeSeed, MapAccess, SeqAccess, Visitor}; -use crate::{DecodeError, Shared}; +use crate::{Error, Shared}; pub(super) const MAX_DEPTH: usize = 32; pub(super) const MAX_NODES: usize = 65_536; @@ -12,7 +12,7 @@ pub(super) const MAX_ATTRIBUTES: usize = 256; pub(super) const MAX_EVENTS: usize = 256; pub(super) const MAX_DECODED_SPAN_BYTES: usize = 16 * 1024 * 1024; -pub(super) fn json_preflight(payload: &[u8]) -> Result<(), DecodeError> { +pub(super) fn json_preflight(payload: &[u8]) -> Result<(), Error> { let mut nodes = 0; let mut exceeded = false; let mut decoder = serde_json::Deserializer::from_slice(payload); @@ -24,9 +24,9 @@ pub(super) fn json_preflight(payload: &[u8]) -> Result<(), DecodeError> { .deserialize(&mut decoder) .and_then(|()| decoder.end()); if exceeded { - return Err(DecodeError::TooLarge); + return Err(Error::TooLarge); } - result.map_err(|_| DecodeError::InvalidPayload) + result.map_err(|_| Error::InvalidPayload) } struct JsonBudget<'a> { @@ -146,7 +146,7 @@ impl MessageKind { } } -pub(super) fn protobuf_preflight(payload: &[u8]) -> Result<(), DecodeError> { +pub(super) fn protobuf_preflight(payload: &[u8]) -> Result<(), Error> { scan_message(payload, MessageKind::Export, 0, &mut 0) } @@ -155,27 +155,27 @@ fn scan_message( kind: MessageKind, depth: usize, nodes: &mut usize, -) -> Result<(), DecodeError> { +) -> Result<(), Error> { if depth > MAX_DEPTH { - return Err(DecodeError::TooLarge); + return Err(Error::TooLarge); } while !payload.is_empty() { *nodes += 1; if *nodes > MAX_NODES { - return Err(DecodeError::TooLarge); + return Err(Error::TooLarge); } - let (tag, wire) = decode_key(&mut payload).map_err(|_| DecodeError::InvalidPayload)?; + let (tag, wire) = decode_key(&mut payload).map_err(|_| Error::InvalidPayload)?; if let (WireType::LengthDelimited, Some(child)) = (wire, kind.child(tag)) { - let length = decode_varint(&mut payload).map_err(|_| DecodeError::InvalidPayload)?; - let length = usize::try_from(length).map_err(|_| DecodeError::InvalidPayload)?; + let length = decode_varint(&mut payload).map_err(|_| Error::InvalidPayload)?; + let length = usize::try_from(length).map_err(|_| Error::InvalidPayload)?; let (message, rest) = payload .split_at_checked(length) - .ok_or(DecodeError::InvalidPayload)?; + .ok_or(Error::InvalidPayload)?; scan_message(message, child, depth + 1, nodes)?; payload = rest; } else { skip_field(wire, tag, &mut payload, DecodeContext::default()) - .map_err(|_| DecodeError::InvalidPayload)?; + .map_err(|_| Error::InvalidPayload)?; } } Ok(()) @@ -194,7 +194,7 @@ impl Budget { &mut self, value: &Shared, allocated_bytes: impl FnOnce(&T) -> usize, - ) -> Result, DecodeError> { + ) -> Result, Error> { let cloned = value.clone(); if !value.shares_storage_with(&cloned) { self.consume(allocated_bytes(value))?; @@ -202,11 +202,8 @@ impl Budget { Ok(cloned) } - pub(super) fn consume(&mut self, bytes: usize) -> Result<(), DecodeError> { - self.remaining = self - .remaining - .checked_sub(bytes) - .ok_or(DecodeError::TooLarge)?; + pub(super) fn consume(&mut self, bytes: usize) -> Result<(), Error> { + self.remaining = self.remaining.checked_sub(bytes).ok_or(Error::TooLarge)?; Ok(()) } } diff --git a/litellm-rust/crates/traces/src/otlp/mod.rs b/litellm-rust/crates/traces/src/otlp/mod.rs index 1beef48fe2c..e11047fe2ca 100644 --- a/litellm-rust/crates/traces/src/otlp/mod.rs +++ b/litellm-rust/crates/traces/src/otlp/mod.rs @@ -6,7 +6,7 @@ mod wire; use serde::Serialize; use std::collections::BTreeMap; -use crate::{DecodeError, NormalizedSpan, Shared}; +use crate::{Error, NormalizedSpan, Shared}; #[derive(Serialize)] pub struct DecodedEvent { @@ -35,10 +35,7 @@ pub struct DecodedSpan { pub consumed_attributes: [&'static str; 2], } -pub fn decode_otlp( - body: &[u8], - content_type: Option<&str>, -) -> Result, DecodeError> { +pub fn decode_otlp(body: &[u8], content_type: Option<&str>) -> Result, Error> { let request = wire::decode(body, content_type)?; span::flatten(request) } diff --git a/litellm-rust/crates/traces/src/otlp/span.rs b/litellm-rust/crates/traces/src/otlp/span.rs index c05a3e7ea66..003ffeb9edc 100644 --- a/litellm-rust/crates/traces/src/otlp/span.rs +++ b/litellm-rust/crates/traces/src/otlp/span.rs @@ -11,11 +11,11 @@ use super::{ limits::{Budget, MAX_ATTRIBUTES, MAX_DECODED_SPAN_BYTES, MAX_EVENTS, MAX_SPANS}, }; use crate::{ - DecodeError, Shared, + Error, Shared, normalize::{CLAUDE_CODE_AGENT, CLAUDE_CODE_SCOPE, normalize}, }; -pub(super) fn flatten(request: ExportTraceServiceRequest) -> Result, DecodeError> { +pub(super) fn flatten(request: ExportTraceServiceRequest) -> Result, Error> { let mut budget = Budget::new(MAX_DECODED_SPAN_BYTES); let mut spans = Vec::new(); for resource in request.resource_spans { @@ -28,7 +28,7 @@ fn append_resource( resource: ResourceSpans, budget: &mut Budget, spans: &mut Vec, -) -> Result<(), DecodeError> { +) -> Result<(), Error> { let attributes = Shared::new(attributes( resource .resource @@ -47,17 +47,17 @@ fn append_scope( resource: &Shared>, budget: &mut Budget, spans: &mut Vec, -) -> Result<(), DecodeError> { +) -> Result<(), Error> { let scope = scope_spans.scope.unwrap_or_default(); if scope.attributes.len() > MAX_ATTRIBUTES { - return Err(DecodeError::TooLarge); + return Err(Error::TooLarge); } budget.consume(scope.name.len() + scope.version.len())?; let scope_name: Shared = scope.name.into(); let scope_version: Shared = scope.version.into(); for span in scope_spans.spans { if spans.len() >= MAX_SPANS { - return Err(DecodeError::TooLarge); + return Err(Error::TooLarge); } validate_span(&span)?; budget.consume( @@ -85,7 +85,7 @@ fn valid_id(value: &[u8], length: usize) -> bool { value.len() == length && value.iter().any(|byte| *byte != 0) } -fn validate_span(span: &Span) -> Result<(), DecodeError> { +fn validate_span(span: &Span) -> Result<(), Error> { if !valid_id(&span.trace_id, 16) || !valid_id(&span.span_id, 8) || (!span.parent_span_id.is_empty() && !valid_id(&span.parent_span_id, 8)) @@ -97,7 +97,7 @@ fn validate_span(span: &Span) -> Result<(), DecodeError> { .iter() .any(|link| !valid_id(&link.trace_id, 16) || !valid_id(&link.span_id, 8)) { - return Err(DecodeError::InvalidPayload); + return Err(Error::InvalidPayload); } if span.events.len() > MAX_EVENTS || span.links.len() > MAX_EVENTS @@ -111,7 +111,7 @@ fn validate_span(span: &Span) -> Result<(), DecodeError> { .iter() .any(|event| event.attributes.len() > MAX_ATTRIBUTES) { - return Err(DecodeError::TooLarge); + return Err(Error::TooLarge); } Ok(()) } @@ -126,7 +126,7 @@ fn decoded_span( scope_name: &Shared, scope_version: &Shared, budget: &mut Budget, -) -> Result { +) -> Result { let status = span.status.unwrap_or_default(); let parent_span_id = hex_bytes(&span.parent_span_id); let span_attributes = attributes(span.attributes, budget)?; @@ -140,7 +140,7 @@ fn decoded_span( attributes: attributes(event.attributes, budget)?, }) }) - .collect::, DecodeError>>()?; + .collect::, Error>>()?; let normalization = normalize( scope_name.as_ref(), &span.name, diff --git a/litellm-rust/crates/traces/src/otlp/wire.rs b/litellm-rust/crates/traces/src/otlp/wire.rs index bac29ba49e4..2330ac12be3 100644 --- a/litellm-rust/crates/traces/src/otlp/wire.rs +++ b/litellm-rust/crates/traces/src/otlp/wire.rs @@ -2,7 +2,7 @@ use opentelemetry_proto::tonic::collector::trace::v1::ExportTraceServiceRequest; use prost::Message; use super::limits::{json_preflight, protobuf_preflight}; -use crate::DecodeError; +use crate::Error; #[derive(strum::EnumString)] #[strum(ascii_case_insensitive)] @@ -19,7 +19,7 @@ enum OtlpMediaType { pub(super) fn decode( body: &[u8], content_type: Option<&str>, -) -> Result { +) -> Result { let media_type = content_type .unwrap_or("application/x-protobuf") .split(';') @@ -27,16 +27,16 @@ pub(super) fn decode( .unwrap_or_default() .trim() .parse::() - .map_err(|_| DecodeError::InvalidPayload)?; + .map_err(|_| Error::InvalidPayload)?; let request = match media_type { OtlpMediaType::Json => { json_preflight(body)?; - serde_json::from_slice(body).map_err(|_| DecodeError::InvalidPayload)? + serde_json::from_slice(body).map_err(|_| Error::InvalidPayload)? } OtlpMediaType::Protobuf => { protobuf_preflight(body)?; - ExportTraceServiceRequest::decode(body).map_err(|_| DecodeError::InvalidPayload)? + ExportTraceServiceRequest::decode(body).map_err(|_| Error::InvalidPayload)? } }; Ok(request) diff --git a/litellm-rust/crates/traces/src/query.rs b/litellm-rust/crates/traces/src/query.rs index b2e8ddd8702..825878159fc 100644 --- a/litellm-rust/crates/traces/src/query.rs +++ b/litellm-rust/crates/traces/src/query.rs @@ -1,346 +1,23 @@ -use std::collections::{BTreeMap, BTreeSet}; +pub mod named; -use futures_util::{ - StreamExt, - stream::{self, TryStreamExt}, -}; -use litellm_http::Client; -use serde::{Deserialize, Serialize}; -use serde_json::{Value, json}; - -use crate::{Connection, Error, NORMALIZED_FIELD_DEFINITIONS, execute_read}; - -mod guide; - -const SAMPLE_ROWS: usize = 200; -const MAX_FIELDS: usize = 200; -const MAX_DEPTH: usize = 16; -const METADATA_SQL: &str = "SELECT metadata FROM spend_logs FINAL \ - WHERE start_time >= now() - INTERVAL 7 DAY AND length(metadata) <= 8192 \ - LIMIT 201"; -const METADATA_SCOPE: &str = "Up to 200 unordered rows from the last 7 days, excluding metadata larger than 8192 bytes; up to 200 paths and 16 levels. Missing paths may exist outside this sample. Array indexes are 1-based and describe sampled positions, not a fixed schema"; -const ATTRIBUTE_SCOPE: &str = "Distinct keys from up to 200 unordered spans in the last 7 days; up to 200 keys per map. Missing keys may exist outside this sample"; - -#[derive(Deserialize)] -struct Rows { - data: Vec, +#[derive(Clone, Copy, Debug, Eq, PartialEq, strum::EnumString, strum::Display, strum::AsRefStr)] +#[strum(serialize_all = "snake_case")] +pub enum ReadQuery { + ListTraces, + TraceSpans, + TraceIdentity, + SpanDetail, + SpanError, + SpendByResponseIds, + Availability, + Agents, + Sample, + Content, + Evidence, } -#[derive(Deserialize)] -struct MetadataRow { - metadata: String, -} - -#[derive(Deserialize)] -struct AttributeRow { - key: String, -} - -#[derive(Clone, Debug, Eq, Ord, PartialEq, PartialOrd, Serialize)] -#[serde(untagged)] -enum PathPart { - Key(String), - Index(usize), -} - -#[derive(Serialize)] -struct MetadataField { - path: Vec, - types: BTreeSet<&'static str>, - expression: String, -} - -#[derive(Deserialize, Serialize)] -struct ColumnSchema { - name: String, - #[serde(rename = "type")] - kind: String, - #[serde(flatten)] - details: BTreeMap, -} - -#[derive(Serialize)] -struct TableSchema { - name: &'static str, - columns: Vec, -} - -#[derive(Serialize)] -struct MetadataCatalog { - table: &'static str, - column: &'static str, - fields: Vec, - sampled_rows: usize, - invalid_json_rows: usize, - truncated: bool, - sample_sql: &'static str, - scope: &'static str, - #[serde(skip_serializing_if = "Option::is_none")] - error: Option, -} - -#[derive(Serialize)] -struct AttributeField { - key: String, - #[serde(rename = "type")] - kind: &'static str, - expression: String, -} - -#[derive(Serialize)] -struct AttributeCatalog { - table: &'static str, - column: &'static str, - fields: Vec, - truncated: bool, - discovery_sql: String, - scope: &'static str, - #[serde(skip_serializing_if = "Option::is_none")] - error: Option, -} - -pub async fn query_sql( - client: &Client, - connection: &Connection, - sql: &str, -) -> Result { - execute_read(client, connection, sql, &BTreeMap::new()).await -} - -async fn rows( - client: &Client, - connection: &Connection, - sql: &str, -) -> Result, Error> { - let body = query_sql(client, connection, sql).await?; - serde_json::from_str::>(&body) - .map(|result| result.data) - .map_err(|_| Error::InvalidResponse) -} - -fn literal(value: &str) -> String { - format!("'{}'", value.replace('\\', "\\\\").replace('\'', "\\'")) -} - -fn metadata_expression(path: &[PathPart]) -> String { - let arguments = path - .iter() - .map(|part| match part { - PathPart::Key(key) => literal(key), - PathPart::Index(index) => index.to_string(), - }) - .collect::>() - .join(", "); - format!("JSONExtractRaw(metadata, {arguments})") -} - -fn discover( - value: &Value, - path: Vec, - fields: &mut BTreeMap, BTreeSet<&'static str>>, -) -> bool { - if path.len() > MAX_DEPTH || (fields.len() >= MAX_FIELDS && !fields.contains_key(&path)) { - return true; - } - if !path.is_empty() { - let kind = match value { - Value::Null => "null", - Value::Bool(_) => "boolean", - Value::Number(number) if number.is_i64() || number.is_u64() => "integer", - Value::Number(_) => "number", - Value::String(_) => "string", - Value::Array(_) => "array", - Value::Object(_) => "object", - }; - fields.entry(path.clone()).or_default().insert(kind); - } - match value { - Value::Object(object) => object.iter().fold(false, |limited, (key, value)| { - let child = path - .iter() - .cloned() - .chain([PathPart::Key(key.clone())]) - .collect(); - discover(value, child, fields) | limited - }), - Value::Array(array) => array - .iter() - .enumerate() - .fold(false, |limited, (index, value)| { - let child = path - .iter() - .cloned() - .chain([PathPart::Index(index + 1)]) - .collect(); - discover(value, child, fields) | limited - }), - _ => false, - } -} - -fn metadata_catalog(sample: &[MetadataRow]) -> MetadataCatalog { - let (fields, limited, invalid_rows) = sample.iter().take(SAMPLE_ROWS).fold( - (BTreeMap::new(), sample.len() > SAMPLE_ROWS, 0), - |(fields, limited, invalid_rows), row| match serde_json::from_str::(&row.metadata) { - Ok(value) => { - let mut fields = fields; - let limited = limited | discover(&value, Vec::new(), &mut fields); - (fields, limited, invalid_rows) - } - Err(_) => (fields, limited, invalid_rows + 1), - }, - ); - let fields: Vec<_> = fields - .into_iter() - .map(|(path, types)| MetadataField { - expression: metadata_expression(&path), - path, - types, - }) - .collect(); - MetadataCatalog { - table: "spend_logs", - column: "metadata", - fields, - sampled_rows: sample.len().min(SAMPLE_ROWS), - invalid_json_rows: invalid_rows, - truncated: limited, - sample_sql: METADATA_SQL, - error: None, - scope: METADATA_SCOPE, - } -} - -pub async fn query_help(client: &Client, connection: &Connection) -> Result { - let tables = stream::iter(["otel_traces", "agent_traces_by_key", "spend_logs"]) - .then(|table| async move { - Ok::<_, Error>(TableSchema { - name: table, - columns: rows::( - client, - connection, - &format!("DESCRIBE TABLE {table}"), - ) - .await?, - }) - }) - .try_collect::>() - .await?; - let metadata = match rows::(client, connection, METADATA_SQL).await { - Ok(sample) => metadata_catalog(&sample), - Err(error) => MetadataCatalog { - error: Some(error.to_string()), - truncated: true, - ..metadata_catalog(&[]) - }, - }; - let attributes = stream::iter(["SpanAttributes", "ResourceAttributes"]) - .then(|column| async move { - let sql = format!( - "SELECT DISTINCT arrayJoin(mapKeys({column})) AS key FROM \ - (SELECT {column} FROM otel_traces WHERE Timestamp >= now() - INTERVAL 7 DAY \ - LIMIT 200) ORDER BY key LIMIT 201" - ); - let (keys, error) = match rows::(client, connection, &sql).await { - Ok(keys) => (keys, None), - Err(error) => (Vec::new(), Some(error.to_string())), - }; - let fields = keys - .iter() - .take(MAX_FIELDS) - .map(|row| AttributeField { - key: row.key.clone(), - kind: "String", - expression: format!("{column}[{}]", literal(&row.key)), - }) - .collect(); - AttributeCatalog { - table: "otel_traces", - column, - fields, - truncated: error.is_some() || keys.len() > MAX_FIELDS, - discovery_sql: sql, - scope: ATTRIBUTE_SCOPE, - error, - } - }) - .collect::>() - .await; - let guide = guide::QueryGuide { - tables: &tables, - normalized_fields: &NORMALIZED_FIELD_DEFINITIONS, - metadata: &metadata, - attributes: &attributes, - }; - Ok(json!({ - "dialect": "ClickHouse SQL", - "access": "Authenticated team scope enforced by ClickHouse row policies; proxy admins can read all teams, while project-bound and teamless keys can read only their own rows", - "response": "ClickHouse JSON envelope: meta, data, rows, statistics; 64-bit integers may be strings", - "tables": tables, - "normalized_fields": NORMALIZED_FIELD_DEFINITIONS.iter().map(|field| json!({ - "table": "otel_traces", "name": field.name, "column": field.clickhouse_column, - "type": field.clickhouse_type, "meaning": field.meaning - })).collect::>(), - "metadata": metadata, - "attributes": attributes, - "relationships": [{ - "left": "otel_traces.LiteLLMRequestId", "right": "spend_logs.response_id", - "additional_predicates": "otel_traces.TeamId = spend_logs.team_id AND otel_traces.ApiKeyHash = spend_logs.api_key", - "meaning": "The normalized ID is the response ID, not request_id. Cached requests can share response_id; joins may return multiple spend rows" - }], - "examples": guide.examples()?, - "gotchas": guide.gotchas()?, - "guide": guide::render(&guide)?, - }).to_string()) -} - -#[cfg(test)] -mod tests { - use super::*; - use rstest::rstest; - - #[rstest] - fn metadata_discovery_preserves_mixed_types_and_reports_invalid_rows() { - let sample = [ - MetadataRow { - metadata: r#"{"x": 1}"#.into(), - }, - MetadataRow { - metadata: r#"{"x": "one"}"#.into(), - }, - MetadataRow { - metadata: "invalid".into(), - }, - ]; - let catalog = json!(metadata_catalog(&sample)); - assert_eq!( - catalog["fields"], - json!([{ - "path": ["x"], "types": ["integer", "string"], "expression": "JSONExtractRaw(metadata, 'x')" - }]) - ); - assert_eq!(catalog["invalid_json_rows"], 1); - assert_eq!(catalog["sampled_rows"], sample.len()); - } - - #[rstest] - #[case::rows(SAMPLE_ROWS + 1, 1)] - #[case::paths(1, MAX_FIELDS + 1)] - fn metadata_discovery_reports_truncation(#[case] row_count: usize, #[case] field_count: usize) { - let metadata: BTreeMap<_, _> = (0..field_count) - .map(|index| (format!("field{index}"), index)) - .collect(); - let sample: Vec<_> = (0..row_count) - .map(|_| MetadataRow { - metadata: json!(metadata).to_string(), - }) - .collect(); - let catalog = json!(metadata_catalog(&sample)); - assert_eq!(catalog["truncated"], true); - assert_eq!(catalog["sampled_rows"], row_count.min(SAMPLE_ROWS)); - assert_eq!( - catalog["fields"].as_array().unwrap().len(), - field_count.min(MAX_FIELDS) - ); +impl ReadQuery { + pub fn parse(value: &str) -> Result { + value.parse().map_err(|_| crate::InvalidQuery) } } diff --git a/litellm-rust/crates/traces/src/query/named.rs b/litellm-rust/crates/traces/src/query/named.rs new file mode 100644 index 00000000000..b39c44d49cb --- /dev/null +++ b/litellm-rust/crates/traces/src/query/named.rs @@ -0,0 +1,152 @@ +use serde::{Deserialize, Serialize}; +use std::collections::BTreeMap; + +#[derive(Debug, Deserialize, Serialize)] +pub struct ReadAccessParams { + pub all_teams: u8, + pub user_id: String, + pub team_ids: Vec, + pub api_key_hash: String, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct ListTracesParams { + #[serde(flatten)] + pub access: ReadAccessParams, + pub start_ms: i64, + pub end_ms: i64, + pub cursor_ms: i64, + pub cursor_trace_id: String, + pub limit: u32, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct ListTracesRow { + pub trace_id: String, + pub trace_ref: String, + pub team_id: String, + pub api_key_hash: String, + pub user_id: String, + pub name: String, + pub service: String, + pub input_preview: String, + pub status: String, + pub start_ms: i64, + pub duration_ms: i64, + pub span_count: u64, + pub agent_count: u64, + pub agent_invocations: u64, + #[serde(default)] + pub agent_names: Vec, + #[serde(default)] + pub frameworks: Vec, + pub llm_calls: u64, + pub tool_calls: u64, + pub input_tokens: u64, + pub output_tokens: u64, + pub models: Vec, + pub error_count: u64, + pub request_ids: Vec, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct TraceSpansParams { + #[serde(flatten)] + pub access: ReadAccessParams, + pub trace_id: String, + pub trace_ref: String, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct TraceSpansRow { + pub span_id: String, + pub parent_span_id: String, + pub name: String, + #[serde(rename = "type")] + pub kind: String, + pub agent: String, + #[serde(default)] + pub framework: String, + pub status: String, + pub status_message: String, + pub error_truncated: u8, + pub start_ns: i64, + pub duration_ns: u64, + pub service: String, + pub input_preview: String, + pub model: String, + pub input_tokens: u32, + pub output_tokens: u32, + pub litellm_request_id: String, + pub team_id: String, + pub api_key_hash: String, + pub user_id: String, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct SpanDetailParams { + #[serde(flatten)] + pub access: ReadAccessParams, + pub trace_id: String, + pub trace_ref: String, + pub span_id: String, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct SpanDetailRow { + pub span_id: String, + pub input: String, + pub output: String, + pub attributes: BTreeMap, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct SpanErrorParams { + #[serde(flatten)] + pub access: ReadAccessParams, + pub trace_id: String, + pub trace_ref: String, + pub span_id: String, + pub error_offset: u64, + pub error_version: String, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct SpanErrorRow { + pub span_id: String, + pub message: String, + pub total_chars: u64, + pub version: String, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct SpendByResponseIdsParams { + #[serde(flatten)] + pub access: ReadAccessParams, + pub response_ids: Vec, + pub start_ms: i64, + pub end_ms: i64, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct SpendByResponseIdsRow { + pub request_id: String, + pub response_id: String, + pub team_id: String, + pub api_key: String, + pub user: String, + pub spend: f64, + pub start_ms: i64, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct TraceIdentityParams { + #[serde(flatten)] + pub access: ReadAccessParams, + pub trace_id: String, +} + +#[derive(Debug, Deserialize, Serialize)] +pub struct TraceIdentityRow { + pub trace_ref: String, +} diff --git a/litellm-rust/crates/traces/src/query_access.rs b/litellm-rust/crates/traces/src/query_access.rs index 881b609177d..51bb5c6a097 100644 --- a/litellm-rust/crates/traces/src/query_access.rs +++ b/litellm-rust/crates/traces/src/query_access.rs @@ -1,15 +1,6 @@ -use std::{sync::Arc, time::Duration}; - -use hmac::{Hmac, Mac}; -use litellm_http::Client; -use moka::future::Cache; use serde::{Deserialize, Serialize}; -use sha2::{Digest, Sha256}; -use tokio::sync::{OwnedSemaphorePermit, Semaphore}; -use crate::{Connection, QueryAccessError}; - -const TABLES: [&str; 3] = ["otel_traces", "agent_traces_by_key", "spend_logs"]; +use crate::InvalidScope; #[derive(Clone, Debug, Deserialize, Serialize)] #[serde(tag = "kind", rename_all = "snake_case", deny_unknown_fields)] @@ -18,6 +9,11 @@ pub enum QueryScope { Team { team_id: String, }, + Logs { + user_id: String, + team_ids: Vec, + api_key_hash: String, + }, Key { team_id: String, api_key_hash: String, @@ -25,176 +21,21 @@ pub enum QueryScope { } impl QueryScope { - fn validate(&self) -> Result<(), QueryAccessError> { + pub fn validate(&self) -> Result<(), InvalidScope> { match self { Self::Admin => Ok(()), Self::Team { team_id } if !team_id.is_empty() => Ok(()), Self::Key { api_key_hash, .. } if !api_key_hash.is_empty() => Ok(()), - _ => Err(QueryAccessError::InvalidScope), - } - } - - fn predicate(&self, table: &str) -> String { - let (team, key) = if table == "spend_logs" { - ("team_id", "api_key") - } else { - ("TeamId", "ApiKeyHash") - }; - match self { - Self::Admin => "1".to_owned(), - Self::Team { team_id } => format!("{team} = {}", literal(team_id)), - Self::Key { - team_id, + Self::Logs { + user_id, + team_ids, api_key_hash, - } => format!( - "{team} = {} AND {key} = {}", - literal(team_id), - literal(api_key_hash) - ), + } if (!user_id.is_empty() || !team_ids.is_empty() || !api_key_hash.is_empty()) + && team_ids.iter().all(|team| !team.is_empty()) => + { + Ok(()) + } + _ => Err(InvalidScope), } } } - -#[derive(Clone)] -pub struct QueryReaders { - writer: Connection, - database: String, - readers: Cache, - slots: Arc, -} - -impl QueryReaders { - pub fn new(writer: Connection, database: String) -> Self { - Self { - writer, - database, - readers: Cache::builder().max_capacity(1024).build(), - slots: Arc::new(Semaphore::new(8)), - } - } - - pub fn acquire(&self) -> Result { - self.slots - .clone() - .try_acquire_owned() - .map_err(|_| QueryAccessError::Busy) - } - - pub async fn connection( - &self, - client: &Client, - scope: &QueryScope, - secret: &str, - ) -> Result { - scope.validate()?; - if secret.is_empty() { - return Err(QueryAccessError::MissingSecret); - } - let identity = serde_json::to_vec(&("litellm_trace_reader_v1", &self.database, scope)) - .map_err(|_| QueryAccessError::InvalidScope)?; - let user = format!("litellm_traces_{:x}", Sha256::digest(&identity)); - let password = credential(secret, b"password", &identity)?; - self.readers - .try_get_with( - user.clone(), - self.provision(client, scope, &user, &password), - ) - .await - .map_err(QueryAccessError::Cached) - } - - async fn provision( - &self, - client: &Client, - scope: &QueryScope, - user: &str, - password: &str, - ) -> Result { - let database = &self.database; - if database.is_empty() - || !database - .bytes() - .all(|c| c.is_ascii_alphanumeric() || c == b'_') - { - return Err(QueryAccessError::InvalidScope); - } - let password_hash = format!("{:x}", Sha256::digest(password)); - self.execute( - client, - format!( - "CREATE USER IF NOT EXISTS {user} IDENTIFIED WITH sha256_hash BY '{password_hash}' \ - SETTINGS readonly = 1 CONST, max_execution_time = 10 CONST, \ - max_result_rows = 1000 CONST, max_result_bytes = 4194304 CONST, \ - result_overflow_mode = 'throw' CONST, max_memory_usage = 268435456 CONST, \ - max_threads = 2 CONST, max_concurrent_queries_for_user = 8 CONST" - ), - ) - .await?; - self.execute( - client, - format!("ALTER USER {user} IDENTIFIED WITH sha256_hash BY '{password_hash}'"), - ) - .await?; - for table in TABLES { - let predicate = scope.predicate(table); - self.execute( - client, - format!( - "CREATE ROW POLICY IF NOT EXISTS {user}_allow ON `{database}`.{table} \ - USING 1 TO {user}" - ), - ) - .await?; - self.execute( - client, - format!( - "CREATE ROW POLICY IF NOT EXISTS {user}_scope ON `{database}`.{table} \ - AS RESTRICTIVE USING {predicate} TO {user}" - ), - ) - .await?; - } - for table in TABLES { - self.execute( - client, - format!("GRANT SELECT ON `{database}`.{table} TO {user}"), - ) - .await?; - } - Connection::configured( - &self.writer.url()[..url::Position::AfterPath], - database, - user, - password, - ) - .map_err(QueryAccessError::Storage) - } - - async fn execute(&self, client: &Client, sql: String) -> Result<(), QueryAccessError> { - let response = client - .post(self.writer.url().clone()) - .timeout(Duration::from_secs(15)) - .body(sql) - .send() - .await - .map_err(|_| QueryAccessError::ProvisionTransport)?; - if !response.status().is_success() { - return Err(QueryAccessError::ProvisionFailed( - response.status().as_u16(), - )); - } - Ok(()) - } -} - -fn credential(secret: &str, purpose: &[u8], identity: &[u8]) -> Result { - let mut mac = Hmac::::new_from_slice(secret.as_bytes()) - .map_err(|_| QueryAccessError::MissingSecret)?; - mac.update(purpose); - mac.update(identity); - Ok(format!("{:x}", mac.finalize().into_bytes())) -} - -fn literal(value: &str) -> String { - format!("'{}'", value.replace('\\', "\\\\").replace('\'', "\\'")) -} diff --git a/litellm-rust/crates/traces/src/schema.rs b/litellm-rust/crates/traces/src/schema.rs deleted file mode 100644 index c52db1523cc..00000000000 --- a/litellm-rust/crates/traces/src/schema.rs +++ /dev/null @@ -1,70 +0,0 @@ -use litellm_http::Client; -use litellm_migrate::Migration; -use std::time::Duration; - -use crate::Connection; -use crate::Error; - -const SCHEMA_REQUEST_TIMEOUT: Duration = Duration::from_secs(30); - -const MIGRATIONS: &[Migration] = litellm_migrate::migrate!("migrations"); - -pub fn schema_statements(database: &str, retention_days: u32) -> Result, Error> { - if database.is_empty() - || !database - .bytes() - .all(|c| c.is_ascii_alphanumeric() || c == b'_') - || retention_days == 0 - { - return Err(Error::InvalidSchema); - } - let database = format!("`{database}`"); - Ok( - std::iter::once(format!("CREATE DATABASE IF NOT EXISTS {database}")) - .chain(MIGRATIONS.iter().map(|migration| { - migration - .sql - .replace("{database}", &database) - .replace("{retention_days}", &retention_days.to_string()) - })) - .collect(), - ) -} - -pub async fn ensure_schema( - client: &Client, - connection: &Connection, - database: &str, - retention_days: u32, -) -> Result<(), Error> { - ensure_schema_with_timeout( - client, - connection, - database, - retention_days, - SCHEMA_REQUEST_TIMEOUT, - ) - .await -} - -async fn ensure_schema_with_timeout( - client: &Client, - connection: &Connection, - database: &str, - retention_days: u32, - request_timeout: Duration, -) -> Result<(), Error> { - for statement in schema_statements(database, retention_days)? { - let response = client - .post(connection.url().clone()) - .timeout(request_timeout) - .body(statement) - .send() - .await - .map_err(|_| Error::Transport)?; - if !response.status().is_success() { - return Err(Error::SchemaFailed(response.status().as_u16())); - } - } - Ok(()) -} diff --git a/litellm-rust/crates/traces/src/sql.rs b/litellm-rust/crates/traces/src/sql.rs deleted file mode 100644 index 51632066fdd..00000000000 --- a/litellm-rust/crates/traces/src/sql.rs +++ /dev/null @@ -1,76 +0,0 @@ -use std::collections::BTreeMap; - -use litellm_http::Client; - -use crate::{Connection, Error, Parameter, execute_read}; - -pub enum ReadQuery { - ListTraces, - TraceSpans, - SpanDetail, - SpanError, - SpendByResponseIds, -} - -impl ReadQuery { - pub fn parse(value: &str) -> Result { - match value { - "list_traces" => Ok(Self::ListTraces), - "trace_spans" => Ok(Self::TraceSpans), - "span_detail" => Ok(Self::SpanDetail), - "span_error" => Ok(Self::SpanError), - "spend_by_response_ids" => Ok(Self::SpendByResponseIds), - _ => Err(Error::InvalidQuery), - } - } - - fn sql(&self) -> &'static str { - match self { - Self::ListTraces => include_str!("../query/list_traces.sql"), - Self::TraceSpans => include_str!("../query/trace_spans.sql"), - Self::SpanDetail => include_str!("../query/span_detail.sql"), - Self::SpanError => include_str!("../query/span_error.sql"), - Self::SpendByResponseIds => include_str!("../query/spend_by_response_ids.sql"), - } - } -} - -#[derive(Clone, Copy)] -pub enum LensQuery { - Availability, - Agents, - Sample, - Content, - Evidence, -} - -impl LensQuery { - pub fn parse(name: &str) -> Result { - match name { - "availability" => Ok(Self::Availability), - "agents" => Ok(Self::Agents), - "sample" => Ok(Self::Sample), - "content" => Ok(Self::Content), - "evidence" => Ok(Self::Evidence), - _ => Err(Error::InvalidQuery), - } - } - pub fn sql(self) -> &'static str { - match self { - Self::Availability => include_str!("../query/lens_availability.sql"), - Self::Agents => include_str!("../query/lens_agents.sql"), - Self::Sample => include_str!("../query/lens_sample.sql"), - Self::Content => include_str!("../query/lens_content.sql"), - Self::Evidence => include_str!("../query/lens_evidence.sql"), - } - } -} - -pub async fn execute_named_read( - client: &Client, - connection: &Connection, - query: ReadQuery, - parameters: &BTreeMap, -) -> Result { - execute_read(client, connection, query.sql(), parameters).await -} diff --git a/litellm-rust/crates/traces/tests/fixtures/deeplite_auth_error.json b/litellm-rust/crates/traces/tests/fixtures/deeplite_auth_error.json new file mode 100644 index 00000000000..ef207be9358 --- /dev/null +++ b/litellm-rust/crates/traces/tests/fixtures/deeplite_auth_error.json @@ -0,0 +1,1614 @@ +{ + "resourceSpans": [ + { + "resource": { + "attributes": [ + { + "key": "telemetry.sdk.language", + "value": { + "stringValue": "python" + } + }, + { + "key": "telemetry.sdk.name", + "value": { + "stringValue": "opentelemetry" + } + }, + { + "key": "telemetry.sdk.version", + "value": { + "stringValue": "1.45.0" + } + }, + { + "key": "service.instance.id", + "value": { + "stringValue": "cedd2594-abc5-48f2-a9d1-b892921fadfd" + } + }, + { + "key": "service.name", + "value": { + "stringValue": "deeplite" + } + } + ] + }, + "scopeSpans": [ + { + "scope": { + "name": "langsmith" + }, + "spans": [ + { + "traceId": "7b787d5c997d768a725a3a2f0278e857", + "spanId": "93886a81b22f3dab", + "parentSpanId": "11f6195c25249ab1", + "name": "__start__", + "kind": 1, + "startTimeUnixNano": "1790967512073597952", + "endTimeUnixNano": "1790967512075591936", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "__start__" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langgraph" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "0" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "__start__" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__start__\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"__start__\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "__start__:af3b0b0a-9397-3b9d-0717-b11174443ca9" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:0, langsmith:hidden" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "eyJtZXNzYWdlcyI6W3sicm9sZSI6InVzZXIiLCJjb250ZW50IjoiRm9yIGEgc3ludGhldGljIHRyYWNpbmcgZml4dHVyZSwgZXhwbGFpbiBQeXRob24gdHVwbGUgdmVyc3VzIGxpc3QgaW1tdXRhYmlsaXR5IGluIGF0IG1vc3QgMTIwIHdvcmRzLiBVc2Ugb25seSBvZmZpY2lhbCBQeXRob24gZG9jdW1lbnRhdGlvbiBpZiB5b3Ugc2VhcmNoLiBIYXZlIHRoZSBza2VwdGljIGFuZCB2ZXJpZmllciBjaGVjayBpdCwgdGhlbiBoYXZlIHRoZSBlZGl0b3Igd3JpdGUgL2Fuc3dlci5tZC4gS2VlcCB0aGUgcnVuIHNob3J0IGFuZCBkbyBub3QgYXNrIGZvbGxvdy11cCBxdWVzdGlvbnMuIn1dfQ==" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "eyJtZXNzYWdlcyI6W3sicm9sZSI6InVzZXIiLCJjb250ZW50IjoiRm9yIGEgc3ludGhldGljIHRyYWNpbmcgZml4dHVyZSwgZXhwbGFpbiBQeXRob24gdHVwbGUgdmVyc3VzIGxpc3QgaW1tdXRhYmlsaXR5IGluIGF0IG1vc3QgMTIwIHdvcmRzLiBVc2Ugb25seSBvZmZpY2lhbCBQeXRob24gZG9jdW1lbnRhdGlvbiBpZiB5b3Ugc2VhcmNoLiBIYXZlIHRoZSBza2VwdGljIGFuZCB2ZXJpZmllciBjaGVjayBpdCwgdGhlbiBoYXZlIHRoZSBlZGl0b3Igd3JpdGUgL2Fuc3dlci5tZC4gS2VlcCB0aGUgcnVuIHNob3J0IGFuZCBkbyBub3QgYXNrIGZvbGxvdy11cCBxdWVzdGlvbnMuIn1dfQ==" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "7b787d5c997d768a725a3a2f0278e857", + "spanId": "aa1eaf69717f1df1", + "parentSpanId": "93886a81b22f3dab", + "name": "route_to_active_agent", + "kind": 1, + "startTimeUnixNano": "1790967512074637056", + "endTimeUnixNano": "1790967512075297024", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "route_to_active_agent" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langgraph" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "0" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "__start__" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__start__\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"__start__\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "__start__:af3b0b0a-9397-3b9d-0717-b11174443ca9" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "langsmith:hidden, seq:step:2" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "eyJvdXRwdXQiOiJyZXNlYXJjaGVyIn0=" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "7b787d5c997d768a725a3a2f0278e857", + "spanId": "88d2e1bce2887a89", + "parentSpanId": "b580832fc04b0921", + "name": "ChatAnthropic", + "kind": 1, + "startTimeUnixNano": "1790967512090679808", + "endTimeUnixNano": "1790967512605561856", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chat" + } + }, + { + "key": "gen_ai.serialized.name", + "value": { + "stringValue": "ChatAnthropic" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "llm" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "ChatAnthropic" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "anthropic" + } + }, + { + "key": "gen_ai.request.model", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "gen_ai.tool.definitions", + "value": { + "stringValue": "[{\"name\":\"ls\",\"input_schema\":{\"properties\":{\"path\":{\"description\":\"Absolute path to the directory to list. Must be absolute, not relative.\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"description\":\"Lists all files in a directory.\\n\\nThis is useful for exploring the filesystem and finding the right file to read or edit.\\nYou should almost ALWAYS use this tool before using the read_file or edit_file tools.\"},{\"name\":\"read_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path to the file to read. Must be absolute, not relative.\",\"type\":\"string\"},\"offset\":{\"default\":0,\"description\":\"Line number to start reading from (0-indexed). Use for pagination of large files.\",\"type\":\"integer\"},\"limit\":{\"default\":100,\"description\":\"Maximum number of lines to read. Use for pagination of large files.\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"description\":\"Reads a file from the filesystem. Assume any path the user provides is valid; reading a missing file returns an error.\\n\\nUsage:\\n- By default, it reads up to 100 lines starting from the beginning of the file. Use `offset`/`limit` to page through large files instead of reading them whole.\\n- A status header, `@@ field | field | ... @@`, sits above the file content, and every line after it is verbatim file content. When content is truncated, there may be an explanation before the header. Never include the header when editing.\\n- Speculatively batch multiple `read_file` calls in one response when several files may be useful.\\n- An empty file returns a system-reminder warning in place of contents.\\n- Large tool results may be offloaded to a file; the tool message gives the path. Read that path here, paging with `offset`/`limit`.\\n- Images (`.png`, `.jpg`, etc.), audio, video, and PDFs return multimodal content blocks (https://docs.langchain.com/oss/python/langchain/messages#multimodal).\\n- For images and PDFs, pagination via `offset`/`limit` is text-only - supply `file_path` only\\n- Always read a file before editing it.\"},{\"name\":\"glob\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Glob pattern to match files (e.g., '*.py', '**/*.py', '/subdir/**/*.md'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path; a leading '/' anchors to the search root ('/*.py' matches only top-level files). Leading-dot names are excluded unless the pattern segment starts with '.', so prefer the bare form '*.py' over '**/*.py' -- '**' will not descend into dot-directories like '.github'.\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Base directory to search from. Defaults to the backend's default root.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Find files matching a glob pattern, returning absolute paths.\\n\\nSupports `*` (any characters within a path segment), `**` (any directories), `?` (single character), `[abc]` (one character from a set), and `{a,b}` (alternatives), e.g. `*.py`, `src/**/*.py`, `*.{yml,yaml}`.\\n\\nA pattern without `/` matches the file name at any depth under the search root (`*.py` matches `src/app/main.py`). A pattern containing `/` matches the search-root-relative path (`src/**/*.py`). A leading `/` anchors to the search root (`/*.py` matches only top-level Python files).\\n\\nLeading-dot names are only matched when the pattern segment itself starts with `.` (use `.env`, or `.github/**/*.yml`). Because `**` will not descend into dot-directories, the bare form `*.yml` is *broader* than `**/*.yml` and is usually what you want.\"},{\"name\":\"grep\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Text pattern to search for (literal string, not regex).\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Directory to search in. Defaults to current working directory.\"},\"glob\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Glob pattern (NOT regex) limiting which files are searched (e.g. '*.py', '*.ts'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path (e.g. 'src/**/*.py'). This is an in-tool file filter, not a call to the separate glob tool. Brace expansion (e.g. '*.{ts,tsx}') is not supported on all backends; run a separate search per extension for reliable results.\"},\"output_mode\":{\"default\":\"files_with_matches\",\"description\":\"Shape of the returned text. 'files_with_matches' (default): newline-separated matching file paths. 'content': matching lines grouped by file under a ':' header, each line indented and formatted ': ' (only the matched line, no surrounding context). 'count': one ': ' line per file.\",\"enum\":[\"files_with_matches\",\"content\",\"count\"],\"type\":\"string\"},\"max_count\":{\"anyOf\":[{\"exclusiveMinimum\":0,\"type\":\"integer\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Optional cap on the total number of matches returned across all files. Leave unset to use the configured default. When the cap is hit, results are truncated and a note says so; narrow the pattern or path to see the rest.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Search for a LITERAL text pattern across files (NOT regex).\\n\\nThe pattern is matched verbatim: regex metacharacters are ordinary characters, not operators. To match any of several strings, run a separate grep for each; `grep(pattern=\\\"foo|bar\\\")` searches for the literal text \\\"foo|bar\\\", and `.*` or `\\\\.` match those characters literally.\\n\\nReturns matching files or content per `output_mode`. Offloaded large tool results live under the artifacts root (`/large_tool_results/` by default); grep that directory to search them when you do not know the exact path.\"},{\"name\":\"web_search\",\"input_schema\":{\"properties\":{\"query\":{\"type\":\"string\"}},\"required\":[\"query\"],\"type\":\"object\"},\"description\":\"Search the web with Exa for current facts and return excerpts with source URLs\"},{\"name\":\"transfer_to_skeptic\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send findings to the skeptic for critique\"},{\"name\":\"transfer_to_verifier\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send revised findings for source verification\"}]" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_chat_model" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd|model:2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd" + } + }, + { + "key": "langsmith.metadata.ls_provider", + "value": { + "stringValue": "anthropic" + } + }, + { + "key": "langsmith.metadata.ls_model_name", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "langsmith.metadata.ls_model_type", + "value": { + "stringValue": "chat" + } + }, + { + "key": "langsmith.metadata.ls_max_tokens", + "value": { + "intValue": "4096" + } + }, + { + "key": "langsmith.metadata.lc_versions", + "value": { + "stringValue": "{\"langchain-core\":\"1.6.6\",\"langchain\":\"1.4.3\",\"langchain-anthropic\":\"1.7.5\"}" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.model", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "langsmith.metadata.max_tokens", + "value": { + "intValue": "4096" + } + }, + { + "key": "langsmith.metadata.model_kwargs", + "value": { + "stringValue": "{}" + } + }, + { + "key": "langsmith.metadata.streaming", + "value": { + "boolValue": false + } + }, + { + "key": "langsmith.metadata.max_retries", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata._type", + "value": { + "stringValue": "anthropic-chat" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "seq:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "events": [ + { + "timeUnixNano": "1790967512686323000", + "name": "exception", + "attributes": [ + { + "key": "exception.type", + "value": { + "stringValue": "Exception" + } + }, + { + "key": "exception.message", + "value": { + "stringValue": "AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\n\n\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\n\nThe above exception was the direct cause of the following exception:\n\n\n\nTraceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\n\n\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}" + } + }, + { + "key": "exception.stacktrace", + "value": { + "stringValue": "Exception: AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\n\n\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\n\nThe above exception was the direct cause of the following exception:\n\n\n\nTraceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\n\n\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n" + } + }, + { + "key": "exception.escaped", + "value": { + "stringValue": "False" + } + } + ] + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "7b787d5c997d768a725a3a2f0278e857", + "spanId": "b580832fc04b0921", + "parentSpanId": "382ca31426f8f943", + "name": "UnsupportedContentMiddleware.wrap_model_call", + "kind": 1, + "startTimeUnixNano": "1790967512081928960", + "endTimeUnixNano": "1790967512610889984", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "UnsupportedContentMiddleware.wrap_model_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd|model:2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "eyJvdXRwdXQiOm51bGx9" + } + } + ], + "events": [ + { + "timeUnixNano": "1790967512686465000", + "name": "exception", + "attributes": [ + { + "key": "exception.type", + "value": { + "stringValue": "Exception" + } + }, + { + "key": "exception.message", + "value": { + "stringValue": "AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')\n\nTraceback (most recent call last):\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n" + } + }, + { + "key": "exception.stacktrace", + "value": { + "stringValue": "Exception: AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')\n\nTraceback (most recent call last):\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n" + } + }, + { + "key": "exception.escaped", + "value": { + "stringValue": "False" + } + } + ] + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "7b787d5c997d768a725a3a2f0278e857", + "spanId": "382ca31426f8f943", + "parentSpanId": "e247cc846cdbc99e", + "name": "FilesystemMiddleware.wrap_model_call", + "kind": 1, + "startTimeUnixNano": "1790967512080943104", + "endTimeUnixNano": "1790967512614221056", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "FilesystemMiddleware.wrap_model_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd|model:2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "eyJvdXRwdXQiOm51bGx9" + } + } + ], + "events": [ + { + "timeUnixNano": "1790967512686562000", + "name": "exception", + "attributes": [ + { + "key": "exception.type", + "value": { + "stringValue": "Exception" + } + }, + { + "key": "exception.message", + "value": { + "stringValue": "AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')\n\nTraceback (most recent call last):\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n" + } + }, + { + "key": "exception.stacktrace", + "value": { + "stringValue": "Exception: AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')\n\nTraceback (most recent call last):\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n" + } + }, + { + "key": "exception.escaped", + "value": { + "stringValue": "False" + } + } + ] + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "7b787d5c997d768a725a3a2f0278e857", + "spanId": "e247cc846cdbc99e", + "parentSpanId": "77a5ba07fbe8fb8b", + "name": "model", + "kind": 1, + "startTimeUnixNano": "1790967512077792000", + "endTimeUnixNano": "1790967512617573888", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd|model:2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + } + ], + "events": [ + { + "timeUnixNano": "1790967512686704000", + "name": "exception", + "attributes": [ + { + "key": "exception.type", + "value": { + "stringValue": "Exception" + } + }, + { + "key": "exception.message", + "value": { + "stringValue": "AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\n\n\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\n\nThe above exception was the direct cause of the following exception:\n\n\n\nTraceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1543, in model_node\n result = wrap_model_call_handler(request, _execute_model_sync)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 357, in composed\n outer_result = outer(request, inner_handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\n\n\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}" + } + }, + { + "key": "exception.stacktrace", + "value": { + "stringValue": "Exception: AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\n\n\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\n\nThe above exception was the direct cause of the following exception:\n\n\n\nTraceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1543, in model_node\n result = wrap_model_call_handler(request, _execute_model_sync)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 357, in composed\n outer_result = outer(request, inner_handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\n\n\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n" + } + }, + { + "key": "exception.escaped", + "value": { + "stringValue": "False" + } + } + ] + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "7b787d5c997d768a725a3a2f0278e857", + "spanId": "77a5ba07fbe8fb8b", + "parentSpanId": "7b77a08f725c2a60", + "name": "researcher", + "kind": 1, + "startTimeUnixNano": "1790967512076764160", + "endTimeUnixNano": "1790967512623192064", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:researcher\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"researcher\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "seq:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + } + ], + "events": [ + { + "timeUnixNano": "1790967512687171000", + "name": "exception", + "attributes": [ + { + "key": "exception.type", + "value": { + "stringValue": "Exception" + } + }, + { + "key": "exception.message", + "value": { + "stringValue": "AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\n\n\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\n\nThe above exception was the direct cause of the following exception:\n\n\n\nTraceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1543, in model_node\n result = wrap_model_call_handler(request, _execute_model_sync)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 357, in composed\n outer_result = outer(request, inner_handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\n\n\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\nDuring task with name 'model' and id '2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31'" + } + }, + { + "key": "exception.stacktrace", + "value": { + "stringValue": "Exception: AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\n\n\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\n\nThe above exception was the direct cause of the following exception:\n\n\n\nTraceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1543, in model_node\n result = wrap_model_call_handler(request, _execute_model_sync)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 357, in composed\n outer_result = outer(request, inner_handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\n\n\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\nDuring task with name 'model' and id '2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31'\n" + } + }, + { + "key": "exception.escaped", + "value": { + "stringValue": "False" + } + } + ] + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "7b787d5c997d768a725a3a2f0278e857", + "spanId": "7b77a08f725c2a60", + "parentSpanId": "11f6195c25249ab1", + "name": "researcher", + "kind": 1, + "startTimeUnixNano": "1790967512076327168", + "endTimeUnixNano": "1790967512626224128", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langgraph" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:researcher\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"researcher\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:816a3f65-9150-0b6d-54aa-920fdcfe25cd" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + } + ], + "events": [ + { + "timeUnixNano": "1790967512687277000", + "name": "exception", + "attributes": [ + { + "key": "exception.type", + "value": { + "stringValue": "Exception" + } + }, + { + "key": "exception.message", + "value": { + "stringValue": "AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\n\n\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\n\nThe above exception was the direct cause of the following exception:\n\n\n\nTraceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1543, in model_node\n result = wrap_model_call_handler(request, _execute_model_sync)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 357, in composed\n outer_result = outer(request, inner_handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\n\n\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\nDuring task with name 'model' and id '2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31'" + } + }, + { + "key": "exception.stacktrace", + "value": { + "stringValue": "Exception: AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\n\n\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\n\nThe above exception was the direct cause of the following exception:\n\n\n\nTraceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1543, in model_node\n result = wrap_model_call_handler(request, _execute_model_sync)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 357, in composed\n outer_result = outer(request, inner_handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\n\n\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\nDuring task with name 'model' and id '2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31'\n" + } + }, + { + "key": "exception.escaped", + "value": { + "stringValue": "False" + } + } + ] + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "7b787d5c997d768a725a3a2f0278e857", + "spanId": "11f6195c25249ab1", + "parentSpanId": "9e65698af98970b0", + "name": "LangGraph", + "kind": 1, + "startTimeUnixNano": "1790967512019313152", + "endTimeUnixNano": "1790967512630693888", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "LangGraph" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langgraph" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "eyJtZXNzYWdlcyI6W3sicm9sZSI6InVzZXIiLCJjb250ZW50IjoiRm9yIGEgc3ludGhldGljIHRyYWNpbmcgZml4dHVyZSwgZXhwbGFpbiBQeXRob24gdHVwbGUgdmVyc3VzIGxpc3QgaW1tdXRhYmlsaXR5IGluIGF0IG1vc3QgMTIwIHdvcmRzLiBVc2Ugb25seSBvZmZpY2lhbCBQeXRob24gZG9jdW1lbnRhdGlvbiBpZiB5b3Ugc2VhcmNoLiBIYXZlIHRoZSBza2VwdGljIGFuZCB2ZXJpZmllciBjaGVjayBpdCwgdGhlbiBoYXZlIHRoZSBlZGl0b3Igd3JpdGUgL2Fuc3dlci5tZC4gS2VlcCB0aGUgcnVuIHNob3J0IGFuZCBkbyBub3QgYXNrIGZvbGxvdy11cCBxdWVzdGlvbnMuIn1dfQ==" + } + } + ], + "events": [ + { + "timeUnixNano": "1790967512687350000", + "name": "exception", + "attributes": [ + { + "key": "exception.type", + "value": { + "stringValue": "Exception" + } + }, + { + "key": "exception.message", + "value": { + "stringValue": "AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\n\n\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\n\nThe above exception was the direct cause of the following exception:\n\n\n\nTraceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1543, in model_node\n result = wrap_model_call_handler(request, _execute_model_sync)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 357, in composed\n outer_result = outer(request, inner_handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\n\n\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\nDuring task with name 'model' and id '2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31'\n\n\nDuring task with name 'researcher' and id '816a3f65-9150-0b6d-54aa-920fdcfe25cd'" + } + }, + { + "key": "exception.stacktrace", + "value": { + "stringValue": "Exception: AnthropicAuthenticationError('Error code: 401 - {\\'type\\': \\'error\\', \\'error\\': {\\'type\\': \\'authentication_error\\', \\'message\\': \\'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\\\n\\\\nLiteLLM: model group \\\\\\'claude-sonnet\\\\\\' failed with the error above. No fallback was attempted.\\'}}')Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\n\n\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\n\nThe above exception was the direct cause of the following exception:\n\n\n\nTraceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1543, in model_node\n result = wrap_model_call_handler(request, _execute_model_sync)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 357, in composed\n outer_result = outer(request, inner_handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\n\n\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\n\nDuring task with name 'model' and id '2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31'\n\n\nDuring task with name 'researcher' and id '816a3f65-9150-0b6d-54aa-920fdcfe25cd'\n" + } + }, + { + "key": "exception.escaped", + "value": { + "stringValue": "False" + } + } + ] + } + ], + "status": { + "code": 1 + }, + "flags": 256 + } + ] + }, + { + "scope": { + "name": "deeplite" + }, + "spans": [ + { + "traceId": "7b787d5c997d768a725a3a2f0278e857", + "spanId": "9e65698af98970b0", + "name": "deeplite.run", + "kind": 1, + "startTimeUnixNano": "1790967512013991000", + "endTimeUnixNano": "1790967512696195000", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "input.value", + "value": { + "stringValue": "For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions." + } + } + ], + "events": [ + { + "timeUnixNano": "1790967512696180000", + "name": "exception", + "attributes": [ + { + "key": "exception.type", + "value": { + "stringValue": "langchain_anthropic.chat_models.AnthropicAuthenticationError" + } + }, + { + "key": "exception.message", + "value": { + "stringValue": "Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}" + } + }, + { + "key": "exception.stacktrace", + "value": { + "stringValue": "Traceback (most recent call last):\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2597, in _generate\n raw_response = self._create(payload)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2176, in _create\n return self._client.messages.with_raw_response.create(**payload)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_response.py\", line 797, in wrapped\n return cast(APIResponse[R], func(*args, **kwargs))\n ~~~~^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_utils/_utils.py\", line 294, in wrapper\n return func(*args, **kwargs)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/resources/messages/messages.py\", line 1027, in create\n return self._post(\n ~~~~~~~~~~^\n \"/v1/messages\",\n ^^^^^^^^^^^^^^^\n ...<23 lines>...\n stream_cls=Stream[RawMessageStreamEvent],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1543, in post\n return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))\n ~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/anthropic/_base_client.py\", line 1208, in request\n raise self._make_status_error_from_response(response) from None\nanthropic.AuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\n\nThe above exception was the direct cause of the following exception:\n\nTraceback (most recent call last):\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/opentelemetry/trace/__init__.py\", line 602, in use_span\n yield span\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/opentelemetry/sdk/trace/__init__.py\", line 1136, in start_as_current_span\n yield span\n File \"/workspace/deeplite/src/deeplite/cli.py\", line 22, in run_task\n result: Final = agent.invoke(\n ~~~~~~~~~~~~^\n {\"messages\": [{\"role\": \"user\", \"content\": task}]}, config={\"recursion_limit\": 40}\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1543, in model_node\n result = wrap_model_call_handler(request, _execute_model_sync)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 357, in composed\n outer_result = outer(request, inner_handler)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/filesystem.py\", line 3218, in wrap_model_call\n response = handler(request)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 347, in inner_handler\n inner_result = inner(req, handler)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/deepagents/middleware/unsupported_content.py\", line 191, in wrap_model_call\n return handler(self._filter_request(request))\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain/agents/factory.py\", line 1506, in _execute_model_sync\n output = model_.invoke(messages)\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/runnables/base.py\", line 6014, in invoke\n return self.bound.invoke(\n ~~~~~~~~~~~~~~~~~^\n input,\n ^^^^^^\n self._merge_configs(config),\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n **{**self.kwargs, **kwargs},\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 488, in invoke\n self.generate_prompt(\n ~~~~~~~~~~~~~~~~~~~~^\n [self._convert_input(input)],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<6 lines>...\n **kwargs,\n ^^^^^^^^^\n ).generations[0][0],\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1877, in generate_prompt\n return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)\n ~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 1684, in generate\n self._generate_with_cache(\n ~~~~~~~~~~~~~~~~~~~~~~~~~^\n m,\n ^^\n ...<2 lines>...\n **kwargs,\n ^^^^^^^^^\n )\n ^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_core/language_models/chat_models.py\", line 2022, in _generate_with_cache\n result = self._generate(\n messages, stop=stop, run_manager=run_manager, **kwargs\n )\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 2601, in _generate\n _handle_anthropic_api_error(e)\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langchain_anthropic/chat_models.py\", line 1295, in _handle_anthropic_api_error\n raise AnthropicAuthenticationError(\n message=e.message, response=e.response, body=e.body\n ) from e\nlangchain_anthropic.chat_models.AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}\nDuring task with name 'model' and id '2e4e0d8e-70a5-697c-c7f4-e1f685fb1a31'\nDuring task with name 'researcher' and id '816a3f65-9150-0b6d-54aa-920fdcfe25cd'\n" + } + }, + { + "key": "exception.escaped", + "value": { + "stringValue": "False" + } + } + ] + } + ], + "status": { + "message": "AnthropicAuthenticationError: Error code: 401 - {'type': 'error', 'error': {'type': 'authentication_error', 'message': 'litellm.AuthenticationError: AnthropicException - {\"type\":\"error\",\"error\":{\"type\":\"authentication_error\",\"message\":\"API key is invalid.\"},\"request_id\":null}\\n\\nLiteLLM: model group \\'claude-sonnet\\' failed with the error above. No fallback was attempted.'}}", + "code": 2 + }, + "flags": 256 + } + ] + } + ] + } + ] +} diff --git a/litellm-rust/crates/traces/tests/fixtures/deeplite_swarm.json b/litellm-rust/crates/traces/tests/fixtures/deeplite_swarm.json new file mode 100644 index 00000000000..19351078af8 --- /dev/null +++ b/litellm-rust/crates/traces/tests/fixtures/deeplite_swarm.json @@ -0,0 +1,9812 @@ +{ + "resourceSpans": [ + { + "resource": { + "attributes": [ + { + "key": "telemetry.sdk.language", + "value": { + "stringValue": "python" + } + }, + { + "key": "telemetry.sdk.name", + "value": { + "stringValue": "opentelemetry" + } + }, + { + "key": "telemetry.sdk.version", + "value": { + "stringValue": "1.45.0" + } + }, + { + "key": "service.instance.id", + "value": { + "stringValue": "b873df4c-5106-4097-a20b-b9380724f4d9" + } + }, + { + "key": "service.name", + "value": { + "stringValue": "deeplite" + } + } + ] + }, + "scopeSpans": [ + { + "scope": { + "name": "langsmith" + }, + "spans": [ + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "1b73fdc79da730c3", + "parentSpanId": "04ffc0db9ce0f358", + "name": "__start__", + "kind": 1, + "startTimeUnixNano": "1790968013211052032", + "endTimeUnixNano": "1790968013212278016", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "__start__" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langgraph" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "0" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "__start__" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__start__\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"__start__\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "__start__:a08efee1-6b20-6c11-d2f1-f04016499ab0" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "langsmith:hidden, graph:step:0" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "eyJtZXNzYWdlcyI6W3sicm9sZSI6InVzZXIiLCJjb250ZW50IjoiRm9yIGEgc3ludGhldGljIHRyYWNpbmcgZml4dHVyZSwgZXhwbGFpbiBQeXRob24gdHVwbGUgdmVyc3VzIGxpc3QgaW1tdXRhYmlsaXR5IGluIGF0IG1vc3QgMTIwIHdvcmRzLiBVc2Ugb25seSBvZmZpY2lhbCBQeXRob24gZG9jdW1lbnRhdGlvbiBpZiB5b3Ugc2VhcmNoLiBIYXZlIHRoZSBza2VwdGljIGFuZCB2ZXJpZmllciBjaGVjayBpdCwgdGhlbiBoYXZlIHRoZSBlZGl0b3Igd3JpdGUgL2Fuc3dlci5tZC4gS2VlcCB0aGUgcnVuIHNob3J0IGFuZCBkbyBub3QgYXNrIGZvbGxvdy11cCBxdWVzdGlvbnMuIn1dfQ==" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "eyJtZXNzYWdlcyI6W3sicm9sZSI6InVzZXIiLCJjb250ZW50IjoiRm9yIGEgc3ludGhldGljIHRyYWNpbmcgZml4dHVyZSwgZXhwbGFpbiBQeXRob24gdHVwbGUgdmVyc3VzIGxpc3QgaW1tdXRhYmlsaXR5IGluIGF0IG1vc3QgMTIwIHdvcmRzLiBVc2Ugb25seSBvZmZpY2lhbCBQeXRob24gZG9jdW1lbnRhdGlvbiBpZiB5b3Ugc2VhcmNoLiBIYXZlIHRoZSBza2VwdGljIGFuZCB2ZXJpZmllciBjaGVjayBpdCwgdGhlbiBoYXZlIHRoZSBlZGl0b3Igd3JpdGUgL2Fuc3dlci5tZC4gS2VlcCB0aGUgcnVuIHNob3J0IGFuZCBkbyBub3QgYXNrIGZvbGxvdy11cCBxdWVzdGlvbnMuIn1dfQ==" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "42058e9b69a517f4", + "parentSpanId": "1b73fdc79da730c3", + "name": "route_to_active_agent", + "kind": 1, + "startTimeUnixNano": "1790968013211607808", + "endTimeUnixNano": "1790968013211869952", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "route_to_active_agent" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langgraph" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "0" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "__start__" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__start__\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"__start__\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "__start__:a08efee1-6b20-6c11-d2f1-f04016499ab0" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "langsmith:hidden, seq:step:2" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "eyJvdXRwdXQiOiJyZXNlYXJjaGVyIn0=" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + } + ] + } + ] + }, + { + "resource": { + "attributes": [ + { + "key": "telemetry.sdk.language", + "value": { + "stringValue": "python" + } + }, + { + "key": "telemetry.sdk.name", + "value": { + "stringValue": "opentelemetry" + } + }, + { + "key": "telemetry.sdk.version", + "value": { + "stringValue": "1.45.0" + } + }, + { + "key": "service.instance.id", + "value": { + "stringValue": "b873df4c-5106-4097-a20b-b9380724f4d9" + } + }, + { + "key": "service.name", + "value": { + "stringValue": "deeplite" + } + } + ] + }, + "scopeSpans": [ + { + "scope": { + "name": "langsmith" + }, + "spans": [ + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "57b096e0e89c429f", + "parentSpanId": "08f0feca38b72d47", + "name": "model", + "kind": 1, + "startTimeUnixNano": "1790968013213167872", + "endTimeUnixNano": "1790968018770104832", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|model:8421bdfe-880b-cb10-d152-84cb9d9551f4" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "3535364df77cec3a", + "parentSpanId": "57b096e0e89c429f", + "name": "FilesystemMiddleware.wrap_model_call", + "kind": 1, + "startTimeUnixNano": "1790968013214705920", + "endTimeUnixNano": "1790968018769807104", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "FilesystemMiddleware.wrap_model_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|model:8421bdfe-880b-cb10-d152-84cb9d9551f4" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "005fac1918b863b6", + "parentSpanId": "3535364df77cec3a", + "name": "UnsupportedContentMiddleware.wrap_model_call", + "kind": 1, + "startTimeUnixNano": "1790968013215195904", + "endTimeUnixNano": "1790968018769697792", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "UnsupportedContentMiddleware.wrap_model_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|model:8421bdfe-880b-cb10-d152-84cb9d9551f4" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "3baa483880660b3b", + "parentSpanId": "005fac1918b863b6", + "name": "ChatAnthropic", + "kind": 1, + "startTimeUnixNano": "1790968013219345920", + "endTimeUnixNano": "1790968018769428992", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chat" + } + }, + { + "key": "gen_ai.serialized.name", + "value": { + "stringValue": "ChatAnthropic" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "llm" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "ChatAnthropic" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "anthropic" + } + }, + { + "key": "gen_ai.request.model", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "gen_ai.tool.definitions", + "value": { + "stringValue": "[{\"name\":\"ls\",\"input_schema\":{\"properties\":{\"path\":{\"description\":\"Absolute path to the directory to list. Must be absolute, not relative.\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"description\":\"Lists all files in a directory.\\n\\nThis is useful for exploring the filesystem and finding the right file to read or edit.\\nYou should almost ALWAYS use this tool before using the read_file or edit_file tools.\"},{\"name\":\"read_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path to the file to read. Must be absolute, not relative.\",\"type\":\"string\"},\"offset\":{\"default\":0,\"description\":\"Line number to start reading from (0-indexed). Use for pagination of large files.\",\"type\":\"integer\"},\"limit\":{\"default\":100,\"description\":\"Maximum number of lines to read. Use for pagination of large files.\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"description\":\"Reads a file from the filesystem. Assume any path the user provides is valid; reading a missing file returns an error.\\n\\nUsage:\\n- By default, it reads up to 100 lines starting from the beginning of the file. Use `offset`/`limit` to page through large files instead of reading them whole.\\n- A status header, `@@ field | field | ... @@`, sits above the file content, and every line after it is verbatim file content. When content is truncated, there may be an explanation before the header. Never include the header when editing.\\n- Speculatively batch multiple `read_file` calls in one response when several files may be useful.\\n- An empty file returns a system-reminder warning in place of contents.\\n- Large tool results may be offloaded to a file; the tool message gives the path. Read that path here, paging with `offset`/`limit`.\\n- Images (`.png`, `.jpg`, etc.), audio, video, and PDFs return multimodal content blocks (https://docs.langchain.com/oss/python/langchain/messages#multimodal).\\n- For images and PDFs, pagination via `offset`/`limit` is text-only - supply `file_path` only\\n- Always read a file before editing it.\"},{\"name\":\"glob\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Glob pattern to match files (e.g., '*.py', '**/*.py', '/subdir/**/*.md'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path; a leading '/' anchors to the search root ('/*.py' matches only top-level files). Leading-dot names are excluded unless the pattern segment starts with '.', so prefer the bare form '*.py' over '**/*.py' -- '**' will not descend into dot-directories like '.github'.\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Base directory to search from. Defaults to the backend's default root.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Find files matching a glob pattern, returning absolute paths.\\n\\nSupports `*` (any characters within a path segment), `**` (any directories), `?` (single character), `[abc]` (one character from a set), and `{a,b}` (alternatives), e.g. `*.py`, `src/**/*.py`, `*.{yml,yaml}`.\\n\\nA pattern without `/` matches the file name at any depth under the search root (`*.py` matches `src/app/main.py`). A pattern containing `/` matches the search-root-relative path (`src/**/*.py`). A leading `/` anchors to the search root (`/*.py` matches only top-level Python files).\\n\\nLeading-dot names are only matched when the pattern segment itself starts with `.` (use `.env`, or `.github/**/*.yml`). Because `**` will not descend into dot-directories, the bare form `*.yml` is *broader* than `**/*.yml` and is usually what you want.\"},{\"name\":\"grep\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Text pattern to search for (literal string, not regex).\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Directory to search in. Defaults to current working directory.\"},\"glob\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Glob pattern (NOT regex) limiting which files are searched (e.g. '*.py', '*.ts'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path (e.g. 'src/**/*.py'). This is an in-tool file filter, not a call to the separate glob tool. Brace expansion (e.g. '*.{ts,tsx}') is not supported on all backends; run a separate search per extension for reliable results.\"},\"output_mode\":{\"default\":\"files_with_matches\",\"description\":\"Shape of the returned text. 'files_with_matches' (default): newline-separated matching file paths. 'content': matching lines grouped by file under a ':' header, each line indented and formatted ': ' (only the matched line, no surrounding context). 'count': one ': ' line per file.\",\"enum\":[\"files_with_matches\",\"content\",\"count\"],\"type\":\"string\"},\"max_count\":{\"anyOf\":[{\"exclusiveMinimum\":0,\"type\":\"integer\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Optional cap on the total number of matches returned across all files. Leave unset to use the configured default. When the cap is hit, results are truncated and a note says so; narrow the pattern or path to see the rest.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Search for a LITERAL text pattern across files (NOT regex).\\n\\nThe pattern is matched verbatim: regex metacharacters are ordinary characters, not operators. To match any of several strings, run a separate grep for each; `grep(pattern=\\\"foo|bar\\\")` searches for the literal text \\\"foo|bar\\\", and `.*` or `\\\\.` match those characters literally.\\n\\nReturns matching files or content per `output_mode`. Offloaded large tool results live under the artifacts root (`/large_tool_results/` by default); grep that directory to search them when you do not know the exact path.\"},{\"name\":\"web_search\",\"input_schema\":{\"properties\":{\"query\":{\"type\":\"string\"}},\"required\":[\"query\"],\"type\":\"object\"},\"description\":\"Search the web with Exa for current facts and return excerpts with source URLs\"},{\"name\":\"transfer_to_skeptic\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send findings to the skeptic for critique\"},{\"name\":\"transfer_to_verifier\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send revised findings for source verification\"}]" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_chat_model" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|model:8421bdfe-880b-cb10-d152-84cb9d9551f4" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" + } + }, + { + "key": "langsmith.metadata.ls_provider", + "value": { + "stringValue": "anthropic" + } + }, + { + "key": "langsmith.metadata.ls_model_name", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "langsmith.metadata.ls_model_type", + "value": { + "stringValue": "chat" + } + }, + { + "key": "langsmith.metadata.ls_max_tokens", + "value": { + "intValue": "4096" + } + }, + { + "key": "langsmith.metadata.lc_versions", + "value": { + "stringValue": "{\"langchain-core\":\"1.6.6\",\"langchain\":\"1.4.3\",\"langchain-anthropic\":\"1.7.5\"}" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.model", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "langsmith.metadata.max_tokens", + "value": { + "intValue": "4096" + } + }, + { + "key": "langsmith.metadata.model_kwargs", + "value": { + "stringValue": "{\"extra_body\":{\"extra_headers\":{\"anthropic-workspace-id\":\"[redacted workspace]\"}}}" + } + }, + { + "key": "langsmith.metadata.streaming", + "value": { + "boolValue": false + } + }, + { + "key": "langsmith.metadata.max_retries", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata._type", + "value": { + "stringValue": "anthropic-chat" + } + }, + { + "key": "langsmith.metadata.usage_metadata", + "value": { + "stringValue": "{\"input_tokens\":2845,\"output_tokens\":73,\"total_tokens\":2918,\"input_token_details\":{\"cache_read\":0,\"cache_creation\":0,\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_token_details\":{\"reasoning\":0}}" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "seq:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + }, + { + "key": "gen_ai.usage.input_tokens", + "value": { + "intValue": "2845" + } + }, + { + "key": "gen_ai.usage.output_tokens", + "value": { + "intValue": "73" + } + }, + { + "key": "gen_ai.usage.total_tokens", + "value": { + "intValue": "2918" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "cdef663fc44a4582", + "parentSpanId": "48b7b97682a8fe08", + "name": "FilesystemMiddleware.wrap_tool_call", + "kind": 1, + "startTimeUnixNano": "1790968018771259904", + "endTimeUnixNano": "1790968020179634944", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "FilesystemMiddleware.wrap_tool_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__pregel_push\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_push\",0,false]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|tools:377cb0ac-b4a5-3ad6-f00b-9afdc4d589a0" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "556c2690603624cc", + "parentSpanId": "cdef663fc44a4582", + "name": "web_search", + "kind": 1, + "startTimeUnixNano": "1790968018771609088", + "endTimeUnixNano": "1790968020179266816", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "execute_tool" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "tool" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "web_search" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "gen_ai.tool.name", + "value": { + "stringValue": "web_search" + } + }, + { + "key": "gen_ai.tool.call.id", + "value": { + "stringValue": "toolu_01B2LfHGDjYSFJhmiXNj4CuQ" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__pregel_push\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_push\",0,false]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|tools:377cb0ac-b4a5-3ad6-f00b-9afdc4d589a0" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "seq:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "eyJxdWVyeSI6ImRvY3MucHl0aG9uLm9yZyB0dXBsZXMgaW1tdXRhYmxlIHNlcXVlbmNlcyBsaXN0cyBtdXRhYmxlIGRhdGEgc3RydWN0dXJlcyB0dXRvcmlhbCJ9" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "48b7b97682a8fe08", + "parentSpanId": "08f0feca38b72d47", + "name": "tools", + "kind": 1, + "startTimeUnixNano": "1790968018770586112", + "endTimeUnixNano": "1790968020180293120", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__pregel_push\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_push\",0,false]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|tools:377cb0ac-b4a5-3ad6-f00b-9afdc4d589a0" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:2" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "eyJpbnB1dCI6W3sibmFtZSI6IndlYl9zZWFyY2giLCJhcmdzIjp7InF1ZXJ5IjoiZG9jcy5weXRob24ub3JnIHR1cGxlcyBpbW11dGFibGUgc2VxdWVuY2VzIGxpc3RzIG11dGFibGUgZGF0YSBzdHJ1Y3R1cmVzIHR1dG9yaWFsIn0sImlkIjoidG9vbHVfMDFCMkxmSEdEallTRkpobWlYTmo0Q3VRIiwidHlwZSI6InRvb2xfY2FsbCJ9XX0=" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + } + ] + } + ] + }, + { + "resource": { + "attributes": [ + { + "key": "telemetry.sdk.language", + "value": { + "stringValue": "python" + } + }, + { + "key": "telemetry.sdk.name", + "value": { + "stringValue": "opentelemetry" + } + }, + { + "key": "telemetry.sdk.version", + "value": { + "stringValue": "1.45.0" + } + }, + { + "key": "service.instance.id", + "value": { + "stringValue": "b873df4c-5106-4097-a20b-b9380724f4d9" + } + }, + { + "key": "service.name", + "value": { + "stringValue": "deeplite" + } + } + ] + }, + "scopeSpans": [ + { + "scope": { + "name": "langsmith" + }, + "spans": [ + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "248062b114d67a66", + "parentSpanId": "08f0feca38b72d47", + "name": "tools", + "kind": 1, + "startTimeUnixNano": "1790968023765523968", + "endTimeUnixNano": "1790968023774028032", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "4" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__pregel_push\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_push\",0,false]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|tools:ed0001c5-0402-bf5e-ceed-69e43e82ae5e" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:4" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "eyJpbnB1dCI6W3sibmFtZSI6InRyYW5zZmVyX3RvX3NrZXB0aWMiLCJhcmdzIjp7fSwiaWQiOiJ0b29sdV8wMVhqajNhUmRXeWhCSmZQbVRKQnhRYTkiLCJ0eXBlIjoidG9vbF9jYWxsIn1dfQ==" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "e30=" + } + } + ], + "events": [ + { + "timeUnixNano": "1790968023840499000", + "name": "exception", + "attributes": [ + { + "key": "exception.type", + "value": { + "stringValue": "Exception" + } + }, + { + "key": "exception.message", + "value": { + "stringValue": "ParentCommand(Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic')" + } + }, + { + "key": "exception.stacktrace", + "value": { + "stringValue": "Exception: ParentCommand(Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic')\n" + } + }, + { + "key": "exception.escaped", + "value": { + "stringValue": "False" + } + } + ] + } + ], + "status": { + "code": 2 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "1fd1c862b3a50355", + "parentSpanId": "248062b114d67a66", + "name": "FilesystemMiddleware.wrap_tool_call", + "kind": 1, + "startTimeUnixNano": "1790968023765999104", + "endTimeUnixNano": "1790968023766906112", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "FilesystemMiddleware.wrap_tool_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "4" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__pregel_push\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_push\",0,false]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|tools:ed0001c5-0402-bf5e-ceed-69e43e82ae5e" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "d92a848281469e5a", + "parentSpanId": "1fd1c862b3a50355", + "name": "transfer_to_skeptic", + "kind": 1, + "startTimeUnixNano": "1790968023766263040", + "endTimeUnixNano": "1790968023766625792", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "tool" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "transfer_to_skeptic" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "execute_tool" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "gen_ai.tool.name", + "value": { + "stringValue": "transfer_to_skeptic" + } + }, + { + "key": "gen_ai.tool.call.id", + "value": { + "stringValue": "toolu_01Xjj3aRdWyhBJfPmTJBxQa9" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "4" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__pregel_push\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_push\",0,false]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|tools:ed0001c5-0402-bf5e-ceed-69e43e82ae5e" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" + } + }, + { + "key": "langsmith.metadata.__handoff_destination", + "value": { + "stringValue": "skeptic" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "seq:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "9cc6e8991d091c19", + "parentSpanId": "08f0feca38b72d47", + "name": "model", + "kind": 1, + "startTimeUnixNano": "1790968020180871936", + "endTimeUnixNano": "1790968023765219072", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "3" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|model:c92c732a-60d5-e72e-21dd-29893acbe69a" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:3" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "95614a9848c5f7d5", + "parentSpanId": "9cc6e8991d091c19", + "name": "FilesystemMiddleware.wrap_model_call", + "kind": 1, + "startTimeUnixNano": "1790968020181624832", + "endTimeUnixNano": "1790968023765062144", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "FilesystemMiddleware.wrap_model_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "3" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|model:c92c732a-60d5-e72e-21dd-29893acbe69a" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "25a7cd951117a4e0", + "parentSpanId": "95614a9848c5f7d5", + "name": "UnsupportedContentMiddleware.wrap_model_call", + "kind": 1, + "startTimeUnixNano": "1790968020182045952", + "endTimeUnixNano": "1790968023764993024", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "UnsupportedContentMiddleware.wrap_model_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "3" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|model:c92c732a-60d5-e72e-21dd-29893acbe69a" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "eyJvdXRwdXQiOnsicmVzdWx0IjpbeyJjb250ZW50IjpbeyJpZCI6InRvb2x1XzAxWGpqM2FSZFd5aEJKZlBtVEpCeFFhOSIsImNhbGxlciI6eyJ0eXBlIjoiZGlyZWN0In0sImlucHV0Ijp7fSwibmFtZSI6InRyYW5zZmVyX3RvX3NrZXB0aWMiLCJ0eXBlIjoidG9vbF91c2UiLCJ0b29sc2V0X25hbWUiOm51bGx9XSwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6eyJpZCI6Im1zZ18wMTFDZmR3QTZGNGNDTjV5aEQ0Q3JzOU0iLCJjb250YWluZXIiOm51bGwsImRpYWdub3N0aWNzIjpudWxsLCJtb2RlbCI6ImNsYXVkZS1zb25uZXQiLCJzdG9wX2RldGFpbHMiOm51bGwsInN0b3BfcmVhc29uIjoidG9vbF91c2UiLCJzdG9wX3NlcXVlbmNlIjpudWxsLCJ1c2FnZSI6eyJjYWNoZV9jcmVhdGlvbiI6eyJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowfSwiY2FjaGVfY3JlYXRpb25faW5wdXRfdG9rZW5zIjowLCJjYWNoZV9yZWFkX2lucHV0X3Rva2VucyI6MCwiaW5mZXJlbmNlX2dlbyI6Imdsb2JhbCIsImlucHV0X3Rva2VucyI6NzM3OCwib3V0cHV0X3Rva2VucyI6MzMsIm91dHB1dF90b2tlbnNfZGV0YWlscyI6eyJ0aGlua2luZ190b2tlbnMiOjB9LCJzZXJ2ZXJfdG9vbF91c2UiOm51bGwsInNlcnZpY2VfdGllciI6InN0YW5kYXJkIn0sIm1vZGVsX25hbWUiOiJjbGF1ZGUtc29ubmV0IiwibW9kZWxfcHJvdmlkZXIiOiJhbnRocm9waWMifSwidHlwZSI6ImFpIiwibmFtZSI6InJlc2VhcmNoZXIiLCJpZCI6ImxjX3J1bi0tMDFhMGZlMDMtM2NkOC03OWYxLTg4YTEtY2U2Y2VlMjk0ZTc5LTAiLCJ0b29sX2NhbGxzIjpbeyJuYW1lIjoidHJhbnNmZXJfdG9fc2tlcHRpYyIsImFyZ3MiOnt9LCJpZCI6InRvb2x1XzAxWGpqM2FSZFd5aEJKZlBtVEpCeFFhOSIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6NzM3OCwib3V0cHV0X3Rva2VucyI6MzMsInRvdGFsX3Rva2VucyI6NzQxMSwiaW5wdXRfdG9rZW5fZGV0YWlscyI6eyJjYWNoZV9yZWFkIjowLCJjYWNoZV9jcmVhdGlvbiI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MH0sIm91dHB1dF90b2tlbl9kZXRhaWxzIjp7InJlYXNvbmluZyI6MH19fV0sInN0cnVjdHVyZWRfcmVzcG9uc2UiOm51bGx9fQ==" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "0d31577e2d5562cc", + "parentSpanId": "25a7cd951117a4e0", + "name": "ChatAnthropic", + "kind": 1, + "startTimeUnixNano": "1790968020184427008", + "endTimeUnixNano": "1790968023764837120", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chat" + } + }, + { + "key": "gen_ai.serialized.name", + "value": { + "stringValue": "ChatAnthropic" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "llm" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "ChatAnthropic" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "anthropic" + } + }, + { + "key": "gen_ai.request.model", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "gen_ai.tool.definitions", + "value": { + "stringValue": "[{\"name\":\"ls\",\"input_schema\":{\"properties\":{\"path\":{\"description\":\"Absolute path to the directory to list. Must be absolute, not relative.\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"description\":\"Lists all files in a directory.\\n\\nThis is useful for exploring the filesystem and finding the right file to read or edit.\\nYou should almost ALWAYS use this tool before using the read_file or edit_file tools.\"},{\"name\":\"read_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path to the file to read. Must be absolute, not relative.\",\"type\":\"string\"},\"offset\":{\"default\":0,\"description\":\"Line number to start reading from (0-indexed). Use for pagination of large files.\",\"type\":\"integer\"},\"limit\":{\"default\":100,\"description\":\"Maximum number of lines to read. Use for pagination of large files.\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"description\":\"Reads a file from the filesystem. Assume any path the user provides is valid; reading a missing file returns an error.\\n\\nUsage:\\n- By default, it reads up to 100 lines starting from the beginning of the file. Use `offset`/`limit` to page through large files instead of reading them whole.\\n- A status header, `@@ field | field | ... @@`, sits above the file content, and every line after it is verbatim file content. When content is truncated, there may be an explanation before the header. Never include the header when editing.\\n- Speculatively batch multiple `read_file` calls in one response when several files may be useful.\\n- An empty file returns a system-reminder warning in place of contents.\\n- Large tool results may be offloaded to a file; the tool message gives the path. Read that path here, paging with `offset`/`limit`.\\n- Images (`.png`, `.jpg`, etc.), audio, video, and PDFs return multimodal content blocks (https://docs.langchain.com/oss/python/langchain/messages#multimodal).\\n- For images and PDFs, pagination via `offset`/`limit` is text-only - supply `file_path` only\\n- Always read a file before editing it.\"},{\"name\":\"glob\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Glob pattern to match files (e.g., '*.py', '**/*.py', '/subdir/**/*.md'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path; a leading '/' anchors to the search root ('/*.py' matches only top-level files). Leading-dot names are excluded unless the pattern segment starts with '.', so prefer the bare form '*.py' over '**/*.py' -- '**' will not descend into dot-directories like '.github'.\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Base directory to search from. Defaults to the backend's default root.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Find files matching a glob pattern, returning absolute paths.\\n\\nSupports `*` (any characters within a path segment), `**` (any directories), `?` (single character), `[abc]` (one character from a set), and `{a,b}` (alternatives), e.g. `*.py`, `src/**/*.py`, `*.{yml,yaml}`.\\n\\nA pattern without `/` matches the file name at any depth under the search root (`*.py` matches `src/app/main.py`). A pattern containing `/` matches the search-root-relative path (`src/**/*.py`). A leading `/` anchors to the search root (`/*.py` matches only top-level Python files).\\n\\nLeading-dot names are only matched when the pattern segment itself starts with `.` (use `.env`, or `.github/**/*.yml`). Because `**` will not descend into dot-directories, the bare form `*.yml` is *broader* than `**/*.yml` and is usually what you want.\"},{\"name\":\"grep\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Text pattern to search for (literal string, not regex).\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Directory to search in. Defaults to current working directory.\"},\"glob\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Glob pattern (NOT regex) limiting which files are searched (e.g. '*.py', '*.ts'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path (e.g. 'src/**/*.py'). This is an in-tool file filter, not a call to the separate glob tool. Brace expansion (e.g. '*.{ts,tsx}') is not supported on all backends; run a separate search per extension for reliable results.\"},\"output_mode\":{\"default\":\"files_with_matches\",\"description\":\"Shape of the returned text. 'files_with_matches' (default): newline-separated matching file paths. 'content': matching lines grouped by file under a ':' header, each line indented and formatted ': ' (only the matched line, no surrounding context). 'count': one ': ' line per file.\",\"enum\":[\"files_with_matches\",\"content\",\"count\"],\"type\":\"string\"},\"max_count\":{\"anyOf\":[{\"exclusiveMinimum\":0,\"type\":\"integer\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Optional cap on the total number of matches returned across all files. Leave unset to use the configured default. When the cap is hit, results are truncated and a note says so; narrow the pattern or path to see the rest.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Search for a LITERAL text pattern across files (NOT regex).\\n\\nThe pattern is matched verbatim: regex metacharacters are ordinary characters, not operators. To match any of several strings, run a separate grep for each; `grep(pattern=\\\"foo|bar\\\")` searches for the literal text \\\"foo|bar\\\", and `.*` or `\\\\.` match those characters literally.\\n\\nReturns matching files or content per `output_mode`. Offloaded large tool results live under the artifacts root (`/large_tool_results/` by default); grep that directory to search them when you do not know the exact path.\"},{\"name\":\"web_search\",\"input_schema\":{\"properties\":{\"query\":{\"type\":\"string\"}},\"required\":[\"query\"],\"type\":\"object\"},\"description\":\"Search the web with Exa for current facts and return excerpts with source URLs\"},{\"name\":\"transfer_to_skeptic\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send findings to the skeptic for critique\"},{\"name\":\"transfer_to_verifier\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send revised findings for source verification\"}]" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_chat_model" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "3" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828|model:c92c732a-60d5-e72e-21dd-29893acbe69a" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" + } + }, + { + "key": "langsmith.metadata.ls_provider", + "value": { + "stringValue": "anthropic" + } + }, + { + "key": "langsmith.metadata.ls_model_name", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "langsmith.metadata.ls_model_type", + "value": { + "stringValue": "chat" + } + }, + { + "key": "langsmith.metadata.ls_max_tokens", + "value": { + "intValue": "4096" + } + }, + { + "key": "langsmith.metadata.lc_versions", + "value": { + "stringValue": "{\"langchain-core\":\"1.6.6\",\"langchain\":\"1.4.3\",\"langchain-anthropic\":\"1.7.5\"}" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.model", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "langsmith.metadata.max_tokens", + "value": { + "intValue": "4096" + } + }, + { + "key": "langsmith.metadata.model_kwargs", + "value": { + "stringValue": "{\"extra_body\":{\"extra_headers\":{\"anthropic-workspace-id\":\"[redacted workspace]\"}}}" + } + }, + { + "key": "langsmith.metadata.streaming", + "value": { + "boolValue": false + } + }, + { + "key": "langsmith.metadata.max_retries", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata._type", + "value": { + "stringValue": "anthropic-chat" + } + }, + { + "key": "langsmith.metadata.usage_metadata", + "value": { + "stringValue": "{\"input_tokens\":7378,\"output_tokens\":33,\"total_tokens\":7411,\"input_token_details\":{\"cache_read\":0,\"cache_creation\":0,\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_token_details\":{\"reasoning\":0}}" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "seq:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + }, + { + "key": "gen_ai.usage.input_tokens", + "value": { + "intValue": "7378" + } + }, + { + "key": "gen_ai.usage.output_tokens", + "value": { + "intValue": "33" + } + }, + { + "key": "gen_ai.usage.total_tokens", + "value": { + "intValue": "7411" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "08f0feca38b72d47", + "parentSpanId": "e2830d2d0406001a", + "name": "researcher", + "kind": 1, + "startTimeUnixNano": "1790968013212771840", + "endTimeUnixNano": "1790968023777713152", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:researcher\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"researcher\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "seq:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + } + ], + "events": [ + { + "timeUnixNano": "1790968023841631000", + "name": "exception", + "attributes": [ + { + "key": "exception.type", + "value": { + "stringValue": "Exception" + } + }, + { + "key": "exception.message", + "value": { + "stringValue": "ParentCommand(Command(graph='researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic')" + } + }, + { + "key": "exception.stacktrace", + "value": { + "stringValue": "Exception: ParentCommand(Command(graph='researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic')\n" + } + }, + { + "key": "exception.escaped", + "value": { + "stringValue": "False" + } + } + ] + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "e2830d2d0406001a", + "parentSpanId": "04ffc0db9ce0f358", + "name": "researcher", + "kind": 1, + "startTimeUnixNano": "1790968013212549888", + "endTimeUnixNano": "1790968023779422976", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langgraph" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "researcher" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:researcher\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"researcher\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + } + ], + "events": [ + { + "timeUnixNano": "1790968023841736000", + "name": "exception", + "attributes": [ + { + "key": "exception.type", + "value": { + "stringValue": "Exception" + } + }, + { + "key": "exception.message", + "value": { + "stringValue": "ParentCommand(Command(graph='researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic')" + } + }, + { + "key": "exception.stacktrace", + "value": { + "stringValue": "Exception: ParentCommand(Command(graph='researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='researcher:9227aa30-2ab0-7e70-70d0-d760f3ff5828', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9')], 'active_agent': 'skeptic'}, goto='skeptic')\n" + } + }, + { + "key": "exception.escaped", + "value": { + "stringValue": "False" + } + } + ] + } + ], + "status": { + "code": 1 + }, + "flags": 256 + } + ] + } + ] + }, + { + "resource": { + "attributes": [ + { + "key": "telemetry.sdk.language", + "value": { + "stringValue": "python" + } + }, + { + "key": "telemetry.sdk.name", + "value": { + "stringValue": "opentelemetry" + } + }, + { + "key": "telemetry.sdk.version", + "value": { + "stringValue": "1.45.0" + } + }, + { + "key": "service.instance.id", + "value": { + "stringValue": "b873df4c-5106-4097-a20b-b9380724f4d9" + } + }, + { + "key": "service.name", + "value": { + "stringValue": "deeplite" + } + } + ] + }, + "scopeSpans": [ + { + "scope": { + "name": "langsmith" + }, + "spans": [ + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "3049adb48476557c", + "parentSpanId": "419c86d999598365", + "name": "tools", + "kind": 1, + "startTimeUnixNano": "1790968030835418880", + "endTimeUnixNano": "1790968030840750848", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__pregel_push\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_push\",0,false]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8|tools:e52223df-38bd-4e1b-4faf-e72de38488d4" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "skeptic" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:2" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "eyJpbnB1dCI6W3sibmFtZSI6InRyYW5zZmVyX3RvX3ZlcmlmaWVyIiwiYXJncyI6e30sImlkIjoidG9vbHVfMDFINmZWOEp2UkpOdlh5NDdlUm5kM2pIIiwidHlwZSI6InRvb2xfY2FsbCJ9XX0=" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "e30=" + } + } + ], + "events": [ + { + "timeUnixNano": "1790968030907778000", + "name": "exception", + "attributes": [ + { + "key": "exception.type", + "value": { + "stringValue": "Exception" + } + }, + { + "key": "exception.message", + "value": { + "stringValue": "ParentCommand(Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': 'CAQS/REKEQgSGAI4AUIJbmFycmF0aW9uEgwFh3AVJZP3s8y1Hq0aDG76uhHONaScXAGShiIwGgjLXHUx1yZrkLPljjzTOQycpLJiKVwXcxm/EzKJm1s8M5WxuREWEldXcoaN0/msKpkRMT+eLb5ih9rAHULTomUNsUwJeu0jrJe4GLazy7sP5KtjEOEBKQsXUfoQ7fDkZOQUHZi9zzQN4hFNmYJUf3OVqf9TQNdC1+m//HAZPfWmAy6HtDvm7kgBJkCEoiFnm7tn/PX1hXGPRgWc6BTXUMr2WA8aKyqggRUbMH2+JYv5iWZddCc1up1Nbr3sF7WPcot9ZBhyHQXr692zeJk6SJgygIVrASbMly2bBxTWJB623gVgzpCmVSLZFpkKXgPcp8hGyDKOvF6SiQSHqGRxQofr7Vs1aPhfZixROJGD+MlrkggVAnGMyYIDUZpavtCeiU1JmBSz0084bXPtT/tnpsKOnSPYZQo3B0BXKbqA/WsKng8/V3Z8Uuajo6IVZ2hgA1WDduqQOQkExGU6pFuLhebIjuWxSNI/DffvR//LNqCfvdnf0hvoPtDxfx/SawIx4/spq9xbwFzHtLgoHg1F2wFw7clPDlg1PyD/v2yJG3V9T8GL6jGPE6rhfil/u4HNvf7BW0dQzCTTXcqZy4nByy0+p+S7ZxfMl4Kpxa2gOhhSNjfpfuX0QpL4kME8J1nliFN1d8KqEPuDI18BQHUhD/UfY29oA0x510FjM/BsLZ4n5sppkoIi7CFoQq2aAKVNfC1KilhIpRD+1dyDtZQklN8gZpOESHw6ML1TtU0yfAcbmqoxJ6hhjzwH6CMsTQEEy8MbRBM+QKKkIRdRCPHGFW2LkuR50+J0pF/tr6pqVvJeozfiMnrEilB27TZP4nKTJG8rd//vCWen0y7CA/8dBJ9gdp5tx7NVA45k1gdcxER1gYouNX3n1vG3/B1F4+93wXW9Mqo6Us59TQmrb9Nqa7pSQNSrH06w1GxyBAlkFfqAlafk16aMpq416TJYpGy43WCUiCcLWlhiWgz2sgOLAXP9a5weWAKRC8J6jkcUkDeXnW+HFSiPM6+9Bo6kVhLUhN5rc4mHZOZpF7ptPpsQN4XCqLPsqpRH/8o5XpyC6ZneTeF2ExtjhwZVjXDwMbIzVYIbw1y2PPGw8dC7pc4sIVSnI4oQAH0v650ghfhmMevWW4h4Pylbw/DG4fdeT3+8z0f8MOSTtfipx05/QttHlAvODRxa5yDCvOz6n3f1BO0N/4MbGyOM27qW4x8mBVoryUZWfsmhfi0/GfNvB8+ylTGbYNX27OcEF5WZtNqbWEy7V5GbmZUSxspcg7FBZ3j3/3L7muvZXoZi1f5erq4y3lSH+oF7qPFnvieyLOCwubcQy+oyowj4cD0idRecnp+s+52D7+mzF1gpW+f+cJasoxigbxkOloS4yeiKvgM4nWSpGEj12RPx5o80EmziXN9t4zJzW1htA5hXJJeFympMYtyCUCevRWVmrRYktQ7UnCa6tL/AVPi1ni5XCXHfLOuqfK5KLYxjwVtdhhfmCLvpaKVNCEOCf4nNGHqD98wUb0ejWNwDYBnJGkBRw9RVspfwNdoWoVcn2qv8ywGUp7yc/sk2LpI6VziRyvWqbGNG1ZJqVVutRc46+sOE4VSeS2/CTNKNa6NMCf/hxxaUVsYfKdP+S1Lc4ianKp0sUugPpmtoydC0CP2RwjnHLcnzxCnvqxlLQWXMNPTsu2yBcHlWJLtcmdg/McLagy7l5kG6sN7ZxJLD/kAx8E6uqohP+K/jMSrYuQJnhr4tf4biWFY3Jzf/KpAYyVSq+pbfFKXMbL9nHEoZQT15Wyabd6DMAq3QZOthM5pUzdNqUXkcrI1PwjASAg4dVU/2o+98mTXnyhP7VlEkTnddpwyJF+YCCc01pqa6ZX99pnR+YOpIrb5DtPcKq0t5cFCDyQxN1lUuqZcYujvX/GC7+6IpRTz/NkEY/5cntOfZJyd6SkUx/JR5AJIRPCNeib0rcWnnFn0XK8s22x40wLjEtufXDO9+yraf4kHxlBI3SB0meMjepX50CJhAx7NekkRFnwoecLfqIyrjXrgAZsTMPiX94snjdrzisAXtBKanulilSxOfW2HSmfnk0L2GXHJJ3S+vCbgREml9dekfmHhmwEYtv3kfhth7ERIwVT8j69OtIBCmeTIJuA7o73PXc1LJ2whuZK7FZe6NTOs61MP7JVlIc6tbhtOBk3NXU8pBPOCY6Q55d63FtpUU/KCbQ0K2WQ9o5jNGwNNJ6Cw5FDCt+x5YJeP1d2QzDSiq+cSZqwqCZVcNoAftGGzgrRZ4vkpbP0xQZHCtWsUwHVTjrY4NfRDjHdVPRn8J9Xtooc/hIWkqzFaczYTlapu2RCJqe8aEo3jzWZCEJ7AiBzBYraYDgOfeiQyeJUsbbXHdGKiiw22Bdp4M+Yz671MZ0ie9EWRks0Q2DHGUTne9S4tAAJPGbUf4xtCMoJ40Q4QW05QLSZy3wNFAUFYmXE4ECDFB8+IEeNFFF/tgAnfh8GvFh/1xY+LE+ozMminjSRwhq09zQAEkNFyu0IKgvDkyOI+iccF7doWLTUasPxLH1xGPBSKkeWCnSoX/4C2c9du66BbRXamHqae+VCiS6BN953iYKOu8rMkneW+TFjV0CzAf8PNG9LBayUgY5Uw9x0Sap6zI4PpaZKH4d9ktkFU+91yBbN5SRtdd8/EQatJXmBNfw7kRrll+LjwZweWLEb0jT1RpGuDqHLdLTMMgowSczrp2zCsJdQH/seaYrpwkCFR8dRjM7JRUkVa1A0SvdZAX75vuBvvLBzN2c+Rbt5oqy93lqIBIjKb7w2UkRTb4pBWcNKNPUgt3az/PxQxEasaltdmuyvsXYbur3VPNn8JzN/6J5N+QCnz571TccapCmkPvFE+gayXU+UF1VKYyFcUvlev7lsQlmjqzK2QA8X7Q3TzFapqhvJKlt7dzBHraqZBgPgb9N4oKNayi8FZT71+kaYhIhFrESKYRHfHkj5n3kfhgLy+x+jLDbKxMggkgHnJz9RuEHZXBWtkYAQ==', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier')" + } + }, + { + "key": "exception.stacktrace", + "value": { + "stringValue": "Exception: ParentCommand(Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier')\n" + } + }, + { + "key": "exception.escaped", + "value": { + "stringValue": "False" + } + } + ] + } + ], + "status": { + "code": 2 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "3ed306e7faadc279", + "parentSpanId": "3049adb48476557c", + "name": "FilesystemMiddleware.wrap_tool_call", + "kind": 1, + "startTimeUnixNano": "1790968030836527104", + "endTimeUnixNano": "1790968030838146048", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "FilesystemMiddleware.wrap_tool_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__pregel_push\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_push\",0,false]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8|tools:e52223df-38bd-4e1b-4faf-e72de38488d4" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "skeptic" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "343bcf62767e113c", + "parentSpanId": "3ed306e7faadc279", + "name": "transfer_to_verifier", + "kind": 1, + "startTimeUnixNano": "1790968030837124096", + "endTimeUnixNano": "1790968030837764096", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "tool" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "transfer_to_verifier" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "execute_tool" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "gen_ai.tool.name", + "value": { + "stringValue": "transfer_to_verifier" + } + }, + { + "key": "gen_ai.tool.call.id", + "value": { + "stringValue": "toolu_01H6fV8JvRJNvXy47eRnd3jH" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__pregel_push\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_push\",0,false]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8|tools:e52223df-38bd-4e1b-4faf-e72de38488d4" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "skeptic" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8" + } + }, + { + "key": "langsmith.metadata.__handoff_destination", + "value": { + "stringValue": "verifier" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "seq:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "709919ff60557ac4", + "parentSpanId": "419c86d999598365", + "name": "model", + "kind": 1, + "startTimeUnixNano": "1790968023780810240", + "endTimeUnixNano": "1790968030834845952", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8|model:41713ca4-d95b-3dfd-185e-53f884946d93" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "skeptic" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "eyJvdXRwdXQiOlt7ImdyYXBoIjpudWxsLCJ1cGRhdGUiOnsibWVzc2FnZXMiOlt7ImNvbnRlbnQiOlt7InNpZ25hdHVyZSI6IkNBUVMxUWdLRUFnU0dBSTRBVUlJZEdocGJtdHBibWNTRE42VGZVNk5ETTk3MWxFYnp4b012UlVBMUo5b3gzZkpRWVQ5SWpBckNRUUdIQlA0cFJIUGF2WHpSbGJNYmFZSEM1N1lqK0dieGdyMGhlbHZkMk9JTC9vNlJidDRQRkEzRmFJRlVsZ3E4Z2M3S1FJOUZ0R252U0FrTEJSeklzVXAvMmQ1UmQyemdFc2ZrRlZlWHNuOFdZWVpraW5BUVZWeTZBN0IzTGFFSlcweGIveDg4RGk2N2ZlZHd4MFErRmxadHdjbVQzRGNhYTExSnZleUhScjNkbSt6R1NaUDZDWGVYTko4bnJUWjdXMVlSVHlzRDZ3N283THA4aDFSd3E0ZjRvOGorUVVmWTB2amUrekpac3hIUG1RTnQzeWtlS2g5OWhnbjZkYml6Ni9FSHFtYkhqU0F1MU00U3FFRGZxSUtUaEhZZW5hbUFabWNRNFhBT282bWRRNis3N1ZncFYxbEMxL2s1MklpVW9KamtHbFFybkxDdnV0aUk3S04rc2dLOGMyKzJLQ0pyUFJDdlZWK0JrU3R2UDVqV1dxenl0cEtRK25IemhMNDQ4T3JJQTlnZEpDMzlDOGVEclhlUm5JN3Q0RnFsa1hHb01sWkFWOVVNY3JRSFJ4T01pOHRPeVR6aTlveUJGRFRTc1ErTEpxZXIwdHoxRnQ5Z2VrNnZ6ZzUwU3BWQUZRZExFUnY4UjFZcU1hZUkreHN2VEFFVzlNUmd2Uk1rekx1elJUMmd1dzNqRCtGamlwMzd4Z0s1UUkwUitDc09BbVFQb1RaaXp6Y0l5QVVBdUNKRkNncS9nRC9DaWJMeG95bWlWVUkxYW45U250M0twTlJvV2R2V0luZTMzVjBwdjhQSGc5eVcySnVMT3FRR2lsTENzSy9RM29RcjN1cEVNWHhYR2pDTDdXVWl6dlJaR0ZFRVYrVnBsWXQ3djR0S1pNajVwazN2ZGVNME1KNVhaZzdQdlVzUnp5Y3hjbnJUM0tub2MzcU0rdHRxWmZUc2I4ZDZVL3BRaWZxN0d1YWhGT0hydnJvcWdKTGorLzgxWXkxcFpGa2pmSmdZMFhrbHpBbkE2Q0ZxL1lUMGd4YlYrVEg1SVMrV2FZT1V6SzM2UzhzNXFxTXdobmd2NEl6RTNjdFhYcW5oSVpYTnpueVZCcWJZYS9HeDJiQ2pjRWoybjVSeUdZUlMvK01jdWxnTEJ6blE5TWtHMkQ3UVAzTXEvbndIWEtNSWFMUzhWSzhoRzNkMHJBamx2bmF1WFNoTnJKeHRrajRxa3dueEQ0THJFamsxdWUrUExjYkxxWVd3QXI4bjBzKzQxanJzSVBWeXlLOXZGYUVackE5S2FCeGtKeWlxeDUwR1pObjdja3grbWtJMThnSDUyaXlWUHRVOEZLTVhqdWdDbDZtUExpSFlpRFFkK0c2M0x1ZG1PS3lzOWl0Vm5CREJOTVAyYi9JNytiSVZSbGhlR2FaV3I2TUFUS2w4NkIzeSswa3VPckxSTXlXY2RpYmMyaVFrWm0rOGY3ZFRVd2JLYkJKc0tPRlk3My84bmxML0ppWXBqejZuVUlrK0lxU2phRnlLNlhGbENjdWtXcFdIcERKblN2YkV6ZXk3cUh5Q3FKK0krb244aVA4R090ZW1wUWFTMC80a1pHU3dsckU2eE9qNkV3R3BmamJEWktIa1AvMlJBZE5ZUFFxM3o3YmRWSk1KTm5GTXo2ZTM3bXpNcENCaWh3UGRTRlRSRTNTQ1k2Nnd2VGdKekdDVXloSGJTaTVpMWF6ek9YZDh1SENTcFQvNkwxbzZWVTBwam9SOEthYTR3Q1dIR2Y3UC9XRWQrYXZ5cDAySm51MWNtcFcwK0dxK3ZLOWgwdGRiMklDbE0vZU5mZG91UVArZXA4TUpVanJhRFJJQ21BSlFZNW9iUzcxdm5pT28rcmVhRnkwelJnQiIsInRoaW5raW5nIjoiIiwidHlwZSI6InRoaW5raW5nIn0seyJzaWduYXR1cmUiOiJDQVFTL1JFS0VRZ1NHQUk0QVVJSmJtRnljbUYwYVc5dUVnd0ZoM0FWSlpQM3M4eTFIcTBhREc3NnVoSE9OYVNjWEFHU2hpSXdHZ2pMWEhVeDF5WnJrTFBsamp6VE9ReWNwTEppS1Z3WGN4bS9FektKbTFzOE01V3h1UkVXRWxkWGNvYU4wL21zS3BrUk1UK2VMYjVpaDlyQUhVTFRvbVVOc1V3SmV1MGpySmU0R0xhenk3c1A1S3RqRU9FQktRc1hVZm9RN2ZEa1pPUVVIWmk5enpRTjRoRk5tWUpVZjNPVnFmOVRRTmRDMSttLy9IQVpQZldtQXk2SHREdm03a2dCSmtDRW9pRm5tN3RuL1BYMWhYR1BSZ1djNkJUWFVNcjJXQThhS3lxZ2dSVWJNSDIrSll2NWlXWmRkQ2MxdXAxTmJyM3NGN1dQY290OVpCaHlIUVhyNjkyemVKazZTSmd5Z0lWckFTYk1seTJiQnhUV0pCNjIzZ1ZnenBDbVZTTFpGcGtLWGdQY3A4aEd5REtPdkY2U2lRU0hxR1J4UW9mcjdWczFhUGhmWml4Uk9KR0QrTWxya2dnVkFuR015WUlEVVpwYXZ0Q2VpVTFKbUJTejAwODRiWFB0VC90bnBzS09uU1BZWlFvM0IwQlhLYnFBL1dzS25nOC9WM1o4VXVham82SVZaMmhnQTFXRGR1cVFPUWtFeEdVNnBGdUxoZWJJanVXeFNOSS9EZmZ2Ui8vTE5xQ2Z2ZG5mMGh2b1B0RHhmeC9TYXdJeDQvc3BxOXhid0Z6SHRMZ29IZzFGMndGdzdjbFBEbGcxUHlEL3YyeUpHM1Y5VDhHTDZqR1BFNnJoZmlsL3U0SE52ZjdCVzBkUXpDVFRYY3FaeTRuQnl5MCtwK1M3WnhmTWw0S3B4YTJnT2hoU05qZnBmdVgwUXBMNGtNRThKMW5saUZOMWQ4S3FFUHVESTE4QlFIVWhEL1VmWTI5b0EweDUxMEZqTS9Cc0xaNG41c3Bwa29JaTdDRm9RcTJhQUtWTmZDMUtpbGhJcFJEKzFkeUR0WlFrbE44Z1pwT0VTSHc2TUwxVHRVMHlmQWNibXFveEo2aGhqendINkNNc1RRRUV5OE1iUkJNK1FLS2tJUmRSQ1BIR0ZXMkxrdVI1MCtKMHBGL3RyNnBxVnZKZW96ZmlNbnJFaWxCMjdUWlA0bktUSkc4cmQvL3ZDV2VuMHk3Q0EvOGRCSjlnZHA1dHg3TlZBNDVrMWdkY3hFUjFnWW91TlgzbjF2RzMvQjFGNCs5M3dYVzlNcW82VXM1OVRRbXJiOU5xYTdwU1FOU3JIMDZ3MUd4eUJBbGtGZnFBbGFmazE2YU1wcTQxNlRKWXBHeTQzV0NVaUNjTFdsaGlXZ3oyc2dPTEFYUDlhNXdlV0FLUkM4SjZqa2NVa0RlWG5XK0hGU2lQTTYrOUJvNmtWaExVaE41cmM0bUhaT1pwRjdwdFBwc1FONFhDcUxQc3FwUkgvOG81WHB5QzZabmVUZUYyRXh0amh3WlZqWER3TWJJelZZSWJ3MXkyUFBHdzhkQzdwYzRzSVZTbkk0b1FBSDB2NjUwZ2hmaG1NZXZXVzRoNFB5bGJ3L0RHNGZkZVQzKzh6MGY4TU9TVHRmaXB4MDUvUXR0SGxBdk9EUnhhNXlEQ3ZPejZuM2YxQk8wTi80TWJHeU9NMjdxVzR4OG1CVm9yeVVaV2ZzbWhmaTAvR2ZOdkI4K3lsVEdiWU5YMjdPY0VGNVdadE5xYldFeTdWNUdibVpVU3hzcGNnN0ZCWjNqMy8zTDdtdXZaWG9aaTFmNWVycTR5M2xTSCtvRjdxUEZudmlleUxPQ3d1YmNReStveW93ajRjRDBpZFJlY25wK3MrNTJENyttekYxZ3BXK2YrY0phc294aWdieGtPbG9TNHllaUt2Z000bldTcEdFajEyUlB4NW84MEVtemlYTjl0NHpKelcxaHRBNWhYSkplRnltcE1ZdHlDVUNldlJXVm1yUllrdFE3VW5DYTZ0TC9BVlBpMW5pNVhDWEhmTE91cWZLNUtMWXhqd1Z0ZGhoZm1DTHZwYUtWTkNFT0NmNG5OR0hxRDk4d1ViMGVqV053RFlCbkpHa0JSdzlSVnNwZndOZG9Xb1ZjbjJxdjh5d0dVcDd5Yy9zazJMcEk2VnppUnl2V3FiR05HMVpKcVZWdXRSYzQ2K3NPRTRWU2VTMi9DVE5LTmE2Tk1DZi9oeHhhVVZzWWZLZFArUzFMYzRpYW5LcDBzVXVnUHBtdG95ZEMwQ1AyUndqbkhMY256eENudnF4bExRV1hNTlBUc3UyeUJjSGxXSkx0Y21kZy9NY0xhZ3k3bDVrRzZzTjdaeEpMRC9rQXg4RTZ1cW9oUCtLL2pNU3JZdVFKbmhyNHRmNGJpV0ZZM0p6Zi9LcEFZeVZTcStwYmZGS1hNYkw5bkhFb1pRVDE1V3lhYmQ2RE1BcTNRWk90aE01cFV6ZE5xVVhrY3JJMVB3akFTQWc0ZFZVLzJvKzk4bVRYbnloUDdWbEVrVG5kZHB3eUpGK1lDQ2MwMXBxYTZaWDk5cG5SK1lPcElyYjVEdFBjS3EwdDVjRkNEeVF4TjFsVXVxWmNZdWp2WC9HQzcrNklwUlR6L05rRVkvNWNudE9mWkp5ZDZTa1V4L0pSNUFKSVJQQ05laWIwcmNXbm5GbjBYSzhzMjJ4NDB3TGpFdHVmWERPOSt5cmFmNGtIeGxCSTNTQjBtZU1qZXBYNTBDSmhBeDdOZWtrUkZud29lY0xmcUl5cmpYcmdBWnNUTVBpWDk0c25qZHJ6aXNBWHRCS2FudWxpbFN4T2ZXMkhTbWZuazBMMkdYSEpKM1MrdkNiZ1JFbWw5ZGVrZm1IaG13RVl0djNrZmh0aDdFUkl3VlQ4ajY5T3RJQkNtZVRJSnVBN283M1BYYzFMSjJ3aHVaSzdGWmU2TlRPczYxTVA3SlZsSWM2dGJodE9CazNOWFU4cEJQT0NZNlE1NWQ2M0Z0cFVVL0tDYlEwSzJXUTlvNWpOR3dOTko2Q3c1RkRDdCt4NVlKZVAxZDJRekRTaXErY1NacXdxQ1pWY05vQWZ0R0d6Z3JSWjR2a3BiUDB4UVpIQ3RXc1V3SFZUanJZNE5mUkRqSGRWUFJuOEo5WHRvb2MvaElXa3F6RmFjellUbGFwdTJSQ0pxZThhRW8zanpXWkNFSjdBaUJ6QllyYVlEZ09mZWlReWVKVXNiYlhIZEdLaWl3MjJCZHA0TStZejY3MU1aMGllOUVXUmtzMFEyREhHVVRuZTlTNHRBQUpQR2JVZjR4dENNb0o0MFE0UVcwNVFMU1p5M3dORkFVRlltWEU0RUNERkI4K0lFZU5GRkYvdGdBbmZoOEd2RmgvMXhZK0xFK296TW1pbmpTUndocTA5elFBRWtORnl1MElLZ3ZEa3lPSStpY2NGN2RvV0xUVWFzUHhMSDF4R1BCU0trZVdDblNvWC80QzJjOWR1NjZCYlJYYW1IcWFlK1ZDaVM2Qk45NTNpWUtPdThyTWtuZVcrVEZqVjBDekFmOFBORzlMQmF5VWdZNVV3OXgwU2FwNnpJNFBwYVpLSDRkOWt0a0ZVKzkxeUJiTjVTUnRkZDgvRVFhdEpYbUJOZnc3a1JybGwrTGp3WndlV0xFYjBqVDFScEd1RHFITGRMVE1NZ293U2N6cnAyekNzSmRRSC9zZWFZcnB3a0NGUjhkUmpNN0pSVWtWYTFBMFN2ZFpBWDc1dnVCdnZMQnpOMmMrUmJ0NW9xeTkzbHFJQklqS2I3dzJVa1JUYjRwQldjTktOUFVndDNhei9QeFF4RWFzYWx0ZG11eXZzWFlidXIzVlBObjhKek4vNko1TitRQ256NTcxVGNjYXBDbWtQdkZFK2dheVhVK1VGMVZLWXlGY1V2bGV2N2xzUWxtanF6SzJRQThYN1EzVHpGYXBxaHZKS2x0N2R6QkhyYXFaQmdQZ2I5TjRvS05heWk4RlpUNzEra2FZaEloRnJFU0tZUkhmSGtqNW4za2ZoZ0x5K3grakxEYkt4TWdna2dIbkp6OVJ1RUhaWEJXdGtZQVE9PSIsInRoaW5raW5nIjoiIiwidHlwZSI6InRoaW5raW5nIn0seyJpZCI6InRvb2x1XzAxSDZmVjhKdlJKTnZYeTQ3ZVJuZDNqSCIsImNhbGxlciI6eyJ0eXBlIjoiZGlyZWN0In0sImlucHV0Ijp7fSwibmFtZSI6InRyYW5zZmVyX3RvX3ZlcmlmaWVyIiwidHlwZSI6InRvb2xfdXNlIiwidG9vbHNldF9uYW1lIjpudWxsfV0sImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnsiaWQiOiJtc2dfMDExQ2Zkd0FNUmRTMjFGZUpmelFoTTNzIiwiY29udGFpbmVyIjpudWxsLCJkaWFnbm9zdGljcyI6bnVsbCwibW9kZWwiOiJjbGF1ZGUtc29ubmV0Iiwic3RvcF9kZXRhaWxzIjpudWxsLCJzdG9wX3JlYXNvbiI6InRvb2xfdXNlIiwic3RvcF9zZXF1ZW5jZSI6bnVsbCwidXNhZ2UiOnsiY2FjaGVfY3JlYXRpb24iOnsiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MH0sImNhY2hlX2NyZWF0aW9uX2lucHV0X3Rva2VucyI6MCwiY2FjaGVfcmVhZF9pbnB1dF90b2tlbnMiOjAsImluZmVyZW5jZV9nZW8iOiJnbG9iYWwiLCJpbnB1dF90b2tlbnMiOjczOTYsIm91dHB1dF90b2tlbnMiOjc3MCwib3V0cHV0X3Rva2Vuc19kZXRhaWxzIjp7InRoaW5raW5nX3Rva2VucyI6NzM5fSwic2VydmVyX3Rvb2xfdXNlIjpudWxsLCJzZXJ2aWNlX3RpZXIiOiJzdGFuZGFyZCJ9LCJtb2RlbF9uYW1lIjoiY2xhdWRlLXNvbm5ldCIsIm1vZGVsX3Byb3ZpZGVyIjoiYW50aHJvcGljIn0sInR5cGUiOiJhaSIsIm5hbWUiOiJza2VwdGljIiwiaWQiOiJsY19ydW4tLTAxYTBmZTAzLTRhZTktNzZjMC04OWE2LTRmMGIxMTRlMzAzMC0wIiwidG9vbF9jYWxscyI6W3sibmFtZSI6InRyYW5zZmVyX3RvX3ZlcmlmaWVyIiwiYXJncyI6e30sImlkIjoidG9vbHVfMDFINmZWOEp2UkpOdlh5NDdlUm5kM2pIIiwidHlwZSI6InRvb2xfY2FsbCJ9XSwiaW52YWxpZF90b29sX2NhbGxzIjpbXSwidXNhZ2VfbWV0YWRhdGEiOnsiaW5wdXRfdG9rZW5zIjo3Mzk2LCJvdXRwdXRfdG9rZW5zIjo3NzAsInRvdGFsX3Rva2VucyI6ODE2NiwiaW5wdXRfdG9rZW5fZGV0YWlscyI6eyJjYWNoZV9yZWFkIjowLCJjYWNoZV9jcmVhdGlvbiI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MH0sIm91dHB1dF90b2tlbl9kZXRhaWxzIjp7InJlYXNvbmluZyI6NzM5fX19XX0sInJlc3VtZSI6bnVsbCwiZ290byI6W119XX0=" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "87fbd88889f37ec8", + "parentSpanId": "709919ff60557ac4", + "name": "FilesystemMiddleware.wrap_model_call", + "kind": 1, + "startTimeUnixNano": "1790968023781179904", + "endTimeUnixNano": "1790968030834503936", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "FilesystemMiddleware.wrap_model_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8|model:41713ca4-d95b-3dfd-185e-53f884946d93" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "skeptic" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "381fc39d7d99fceb", + "parentSpanId": "87fbd88889f37ec8", + "name": "UnsupportedContentMiddleware.wrap_model_call", + "kind": 1, + "startTimeUnixNano": "1790968023781553152", + "endTimeUnixNano": "1790968030834259968", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "UnsupportedContentMiddleware.wrap_model_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8|model:41713ca4-d95b-3dfd-185e-53f884946d93" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "skeptic" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "f2bbd85b9e41b171", + "parentSpanId": "381fc39d7d99fceb", + "name": "ChatAnthropic", + "kind": 1, + "startTimeUnixNano": "1790968023785360128", + "endTimeUnixNano": "1790968030833796864", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chat" + } + }, + { + "key": "gen_ai.serialized.name", + "value": { + "stringValue": "ChatAnthropic" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "llm" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "ChatAnthropic" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "anthropic" + } + }, + { + "key": "gen_ai.request.model", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "gen_ai.tool.definitions", + "value": { + "stringValue": "[{\"name\":\"ls\",\"input_schema\":{\"properties\":{\"path\":{\"description\":\"Absolute path to the directory to list. Must be absolute, not relative.\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"description\":\"Lists all files in a directory.\\n\\nThis is useful for exploring the filesystem and finding the right file to read or edit.\\nYou should almost ALWAYS use this tool before using the read_file or edit_file tools.\"},{\"name\":\"read_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path to the file to read. Must be absolute, not relative.\",\"type\":\"string\"},\"offset\":{\"default\":0,\"description\":\"Line number to start reading from (0-indexed). Use for pagination of large files.\",\"type\":\"integer\"},\"limit\":{\"default\":100,\"description\":\"Maximum number of lines to read. Use for pagination of large files.\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"description\":\"Reads a file from the filesystem. Assume any path the user provides is valid; reading a missing file returns an error.\\n\\nUsage:\\n- By default, it reads up to 100 lines starting from the beginning of the file. Use `offset`/`limit` to page through large files instead of reading them whole.\\n- A status header, `@@ field | field | ... @@`, sits above the file content, and every line after it is verbatim file content. When content is truncated, there may be an explanation before the header. Never include the header when editing.\\n- Speculatively batch multiple `read_file` calls in one response when several files may be useful.\\n- An empty file returns a system-reminder warning in place of contents.\\n- Large tool results may be offloaded to a file; the tool message gives the path. Read that path here, paging with `offset`/`limit`.\\n- Images (`.png`, `.jpg`, etc.), audio, video, and PDFs return multimodal content blocks (https://docs.langchain.com/oss/python/langchain/messages#multimodal).\\n- For images and PDFs, pagination via `offset`/`limit` is text-only - supply `file_path` only\\n- Always read a file before editing it.\"},{\"name\":\"glob\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Glob pattern to match files (e.g., '*.py', '**/*.py', '/subdir/**/*.md'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path; a leading '/' anchors to the search root ('/*.py' matches only top-level files). Leading-dot names are excluded unless the pattern segment starts with '.', so prefer the bare form '*.py' over '**/*.py' -- '**' will not descend into dot-directories like '.github'.\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Base directory to search from. Defaults to the backend's default root.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Find files matching a glob pattern, returning absolute paths.\\n\\nSupports `*` (any characters within a path segment), `**` (any directories), `?` (single character), `[abc]` (one character from a set), and `{a,b}` (alternatives), e.g. `*.py`, `src/**/*.py`, `*.{yml,yaml}`.\\n\\nA pattern without `/` matches the file name at any depth under the search root (`*.py` matches `src/app/main.py`). A pattern containing `/` matches the search-root-relative path (`src/**/*.py`). A leading `/` anchors to the search root (`/*.py` matches only top-level Python files).\\n\\nLeading-dot names are only matched when the pattern segment itself starts with `.` (use `.env`, or `.github/**/*.yml`). Because `**` will not descend into dot-directories, the bare form `*.yml` is *broader* than `**/*.yml` and is usually what you want.\"},{\"name\":\"grep\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Text pattern to search for (literal string, not regex).\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Directory to search in. Defaults to current working directory.\"},\"glob\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Glob pattern (NOT regex) limiting which files are searched (e.g. '*.py', '*.ts'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path (e.g. 'src/**/*.py'). This is an in-tool file filter, not a call to the separate glob tool. Brace expansion (e.g. '*.{ts,tsx}') is not supported on all backends; run a separate search per extension for reliable results.\"},\"output_mode\":{\"default\":\"files_with_matches\",\"description\":\"Shape of the returned text. 'files_with_matches' (default): newline-separated matching file paths. 'content': matching lines grouped by file under a ':' header, each line indented and formatted ': ' (only the matched line, no surrounding context). 'count': one ': ' line per file.\",\"enum\":[\"files_with_matches\",\"content\",\"count\"],\"type\":\"string\"},\"max_count\":{\"anyOf\":[{\"exclusiveMinimum\":0,\"type\":\"integer\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Optional cap on the total number of matches returned across all files. Leave unset to use the configured default. When the cap is hit, results are truncated and a note says so; narrow the pattern or path to see the rest.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Search for a LITERAL text pattern across files (NOT regex).\\n\\nThe pattern is matched verbatim: regex metacharacters are ordinary characters, not operators. To match any of several strings, run a separate grep for each; `grep(pattern=\\\"foo|bar\\\")` searches for the literal text \\\"foo|bar\\\", and `.*` or `\\\\.` match those characters literally.\\n\\nReturns matching files or content per `output_mode`. Offloaded large tool results live under the artifacts root (`/large_tool_results/` by default); grep that directory to search them when you do not know the exact path.\"},{\"name\":\"transfer_to_researcher\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Ask the researcher to address a concrete gap\"},{\"name\":\"transfer_to_verifier\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send critique for independent verification\"},{\"name\":\"transfer_to_red_team\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send checked claims for adversarial review\"}]" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_chat_model" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8|model:41713ca4-d95b-3dfd-185e-53f884946d93" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "skeptic" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8" + } + }, + { + "key": "langsmith.metadata.ls_provider", + "value": { + "stringValue": "anthropic" + } + }, + { + "key": "langsmith.metadata.ls_model_name", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "langsmith.metadata.ls_model_type", + "value": { + "stringValue": "chat" + } + }, + { + "key": "langsmith.metadata.ls_max_tokens", + "value": { + "intValue": "4096" + } + }, + { + "key": "langsmith.metadata.lc_versions", + "value": { + "stringValue": "{\"langchain-core\":\"1.6.6\",\"langchain\":\"1.4.3\",\"langchain-anthropic\":\"1.7.5\"}" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.model", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "langsmith.metadata.max_tokens", + "value": { + "intValue": "4096" + } + }, + { + "key": "langsmith.metadata.model_kwargs", + "value": { + "stringValue": "{\"extra_body\":{\"extra_headers\":{\"anthropic-workspace-id\":\"[redacted workspace]\"}}}" + } + }, + { + "key": "langsmith.metadata.streaming", + "value": { + "boolValue": false + } + }, + { + "key": "langsmith.metadata.max_retries", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata._type", + "value": { + "stringValue": "anthropic-chat" + } + }, + { + "key": "langsmith.metadata.usage_metadata", + "value": { + "stringValue": "{\"input_tokens\":7396,\"output_tokens\":770,\"total_tokens\":8166,\"input_token_details\":{\"cache_read\":0,\"cache_creation\":0,\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_token_details\":{\"reasoning\":739}}" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "seq:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + }, + { + "key": "gen_ai.usage.input_tokens", + "value": { + "intValue": "7396" + } + }, + { + "key": "gen_ai.usage.output_tokens", + "value": { + "intValue": "770" + } + }, + { + "key": "gen_ai.usage.total_tokens", + "value": { + "intValue": "8166" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "419c86d999598365", + "parentSpanId": "0ff4846461350af9", + "name": "skeptic", + "kind": 1, + "startTimeUnixNano": "1790968023780292096", + "endTimeUnixNano": "1790968030843193088", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "skeptic" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "skeptic" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:skeptic\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"skeptic\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "skeptic" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "seq:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "eyJtZXNzYWdlcyI6W3siY29udGVudCI6IkZvciBhIHN5bnRoZXRpYyB0cmFjaW5nIGZpeHR1cmUsIGV4cGxhaW4gUHl0aG9uIHR1cGxlIHZlcnN1cyBsaXN0IGltbXV0YWJpbGl0eSBpbiBhdCBtb3N0IDEyMCB3b3Jkcy4gVXNlIG9ubHkgb2ZmaWNpYWwgUHl0aG9uIGRvY3VtZW50YXRpb24gaWYgeW91IHNlYXJjaC4gSGF2ZSB0aGUgc2tlcHRpYyBhbmQgdmVyaWZpZXIgY2hlY2sgaXQsIHRoZW4gaGF2ZSB0aGUgZWRpdG9yIHdyaXRlIC9hbnN3ZXIubWQuIEtlZXAgdGhlIHJ1biBzaG9ydCBhbmQgZG8gbm90IGFzayBmb2xsb3ctdXAgcXVlc3Rpb25zLiIsImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnt9LCJ0eXBlIjoiaHVtYW4iLCJpZCI6IjQ2MjA0MzA1LWY4ZWUtNDM4NC05Y2U4LWZjZDgwYmZjZGY3NSJ9LHsiY29udGVudCI6W3siaWQiOiJ0b29sdV8wMUIyTGZIR0RqWVNGSmhtaVhOajRDdVEiLCJjYWxsZXIiOnsidHlwZSI6ImRpcmVjdCJ9LCJpbnB1dCI6eyJxdWVyeSI6ImRvY3MucHl0aG9uLm9yZyB0dXBsZXMgaW1tdXRhYmxlIHNlcXVlbmNlcyBsaXN0cyBtdXRhYmxlIGRhdGEgc3RydWN0dXJlcyB0dXRvcmlhbCJ9LCJuYW1lIjoid2ViX3NlYXJjaCIsInR5cGUiOiJ0b29sX3VzZSIsInRvb2xzZXRfbmFtZSI6bnVsbH1dLCJhZGRpdGlvbmFsX2t3YXJncyI6e30sInJlc3BvbnNlX21ldGFkYXRhIjp7ImlkIjoibXNnXzAxMUNmZHc5YVc5YnJlblBxZ3liZk53UCIsImNvbnRhaW5lciI6bnVsbCwiZGlhZ25vc3RpY3MiOm51bGwsIm1vZGVsIjoiY2xhdWRlLXNvbm5ldCIsInN0b3BfZGV0YWlscyI6bnVsbCwic3RvcF9yZWFzb24iOiJ0b29sX3VzZSIsInN0b3Bfc2VxdWVuY2UiOm51bGwsInVzYWdlIjp7ImNhY2hlX2NyZWF0aW9uIjp7ImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjB9LCJjYWNoZV9jcmVhdGlvbl9pbnB1dF90b2tlbnMiOjAsImNhY2hlX3JlYWRfaW5wdXRfdG9rZW5zIjowLCJpbmZlcmVuY2VfZ2VvIjoiZ2xvYmFsIiwiaW5wdXRfdG9rZW5zIjoyODQ1LCJvdXRwdXRfdG9rZW5zIjo3Mywib3V0cHV0X3Rva2Vuc19kZXRhaWxzIjp7InRoaW5raW5nX3Rva2VucyI6MH0sInNlcnZlcl90b29sX3VzZSI6bnVsbCwic2VydmljZV90aWVyIjoic3RhbmRhcmQifSwibW9kZWxfbmFtZSI6ImNsYXVkZS1zb25uZXQiLCJtb2RlbF9wcm92aWRlciI6ImFudGhyb3BpYyJ9LCJ0eXBlIjoiYWkiLCJuYW1lIjoicmVzZWFyY2hlciIsImlkIjoibGNfcnVuLS0wMWEwZmUwMy0yMWEzLTcwMDAtYTM4MS0yODRhNmEwYzAzZjctMCIsInRvb2xfY2FsbHMiOlt7Im5hbWUiOiJ3ZWJfc2VhcmNoIiwiYXJncyI6eyJxdWVyeSI6ImRvY3MucHl0aG9uLm9yZyB0dXBsZXMgaW1tdXRhYmxlIHNlcXVlbmNlcyBsaXN0cyBtdXRhYmxlIGRhdGEgc3RydWN0dXJlcyB0dXRvcmlhbCJ9LCJpZCI6InRvb2x1XzAxQjJMZkhHRGpZU0ZKaG1pWE5qNEN1USIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6Mjg0NSwib3V0cHV0X3Rva2VucyI6NzMsInRvdGFsX3Rva2VucyI6MjkxOCwiaW5wdXRfdG9rZW5fZGV0YWlscyI6eyJjYWNoZV9yZWFkIjowLCJjYWNoZV9jcmVhdGlvbiI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MH0sIm91dHB1dF90b2tlbl9kZXRhaWxzIjp7InJlYXNvbmluZyI6MH19fSx7ImNvbnRlbnQiOiJbe1widGl0bGVcIjogXCI1LiBEYXRhIFN0cnVjdHVyZXMgXFx1MjAxNCBQeXRob24gMy4xNC41IGRvY3VtZW50YXRpb25cIiwgXCJ1cmxcIjogXCJodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL3R1dG9yaWFsL2RhdGFzdHJ1Y3R1cmVzLmh0bWxcIiwgXCJoaWdobGlnaHRzXCI6IFtcIllvdSBtaWdodCBoYXZlIG5vdGljZWQgdGhhdCBtZXRob2RzIGxpa2VgaW5zZXJ0YCxgcmVtb3ZlYCBvcmBzb3J0YCB0aGF0IG9ubHkgbW9kaWZ5IHRoZSBsaXN0IGhhdmUgbm8gcmV0dXJuIHZhbHVlIHByaW50ZWQgXFx1MjAxMyB0aGV5IHJldHVybiB0aGUgZGVmYXVsdGBOb25lYC4gWzFdIFRoaXMgaXMgYSBkZXNpZ24gcHJpbmNpcGxlIGZvciBhbGwgbXV0YWJsZSBkYXRhIHN0cnVjdHVyZXMgaW4gUHl0aG9uLlxcbi4uLlxcbiMjIDUuMy4gVHVwbGVzIGFuZCBTZXF1ZW5jZXNcXHUwMGI2XFxuXFxuV2Ugc2F3IHRoYXQgbGlzdHMgYW5kIHN0cmluZ3MgaGF2ZSBtYW55IGNvbW1vbiBwcm9wZXJ0aWVzLCBzdWNoIGFzIGluZGV4aW5nIGFuZCBzbGljaW5nIG9wZXJhdGlvbnMuIFRoZXkgYXJlIHR3byBleGFtcGxlcyBvZiBzZXF1ZW5jZSBkYXRhIHR5cGVzIChzZWUgU2VxdWVuY2UgVHlwZXMgXFx1MjAxNCBsaXN0LCB0dXBsZSwgcmFuZ2UpLiBTaW5jZSBQeXRob24gaXMgYW4gZXZvbHZpbmcgbGFuZ3VhZ2UsIG90aGVyIHNlcXVlbmNlIGRhdGEgdHlwZXMgbWF5IGJlIGFkZGVkLiBUaGVyZSBpcyBhbHNvIGFub3RoZXIgc3RhbmRhcmQgc2VxdWVuY2UgZGF0YSB0eXBlOiB0aGUgdHVwbGUuXFxuXFxuQSB0dXBsZSBjb25zaXN0cyBvZiBhIG51bWJlciBvZiB2YWx1ZXMgc2VwYXJhdGVkIGJ5IGNvbW1hcywgZm9yIGluc3RhbmNlOlxcbi4uLlxcbj4+PiAjIFR1cGxlcyBhcmUgaW1tdXRhYmxlOlxcbj4+PiB0WzBdID0gODg4ODhcXG5UcmFjZWJhY2sgKG1vc3QgcmVjZW50IGNhbGwgbGFzdCk6XFxuICBGaWxlIFxcXCI8c3RkaW4+XFxcIiwgbGluZSAxLCBpbiA8bW9kdWxlPlxcblR5cGVFcnJvcjogJ3R1cGxlJyBvYmplY3QgZG9lcyBub3Qgc3VwcG9ydCBpdGVtIGFzc2lnbm1lbnRcXG4+Pj4gIyBidXQgdGhleSBjYW4gY29udGFpbiBtdXRhYmxlIG9iamVjdHM6XFxuPj4+IHYgPSAoWzEsIDIsIDNdLCBbMywgMiwgMV0pXFxuPj4+IHZcXG4oWzEsIDIsIDNdLCBbMywgMiwgMV0pXFxuLi4uXFxuQXMgeW91IHNlZSwgb24gb3V0cHV0IHR1cGxlcyBhcmUgYWx3YXlzIGVuY2xvc2VkIGluIHBhcmVudGhlc2VzLCBzbyB0aGF0IG5lc3RlZCB0dXBsZXMgYXJlIGludGVycHJldGVkIGNvcnJlY3RseTsgdGhleSBtYXkgYmUgaW5wdXQgd2l0aCBvciB3aXRob3V0IHN1cnJvdW5kaW5nIHBhcmVudGhlc2VzLCBhbHRob3VnaCBvZnRlbiBwYXJlbnRoZXNlcyBhcmUgbmVjZXNzYXJ5IGFueXdheSAoaWYgdGhlIHR1cGxlIGlzIHBhcnQgb2YgYSBsYXJnZXIgZXhwcmVzc2lvbikuIEl0IGlzIG5vdCBwb3NzaWJsZSB0byBhc3NpZ24gdG8gdGhlIGluZGl2aWR1YWwgaXRlbXMgb2YgYSB0dXBsZSwgaG93ZXZlciBpdCBpcyBwb3NzaWJsZSB0byBjcmVhdGUgdHVwbGVzIHdoaWNoIGNvbnRhaW4gbXV0YWJsZSBvYmplY3RzLCBzdWNoIGFzIGxpc3RzLlxcblxcblRob3VnaCB0dXBsZXMgbWF5IHNlZW0gc2ltaWxhciB0byBsaXN0cywgdGhleSBhcmUgb2Z0ZW4gdXNlZCBpbiBkaWZmZXJlbnQgc2l0dWF0aW9ucyBhbmQgZm9yIGRpZmZlcmVudCBwdXJwb3Nlcy4gVHVwbGVzIGFyZSBpbW11dGFibGUsIGFuZCB1c3VhbGx5IGNvbnRhaW4gYSBoZXRlcm9nZW5lb3VzIHNlcXVlbmNlIG9mIGVsZW1lbnRzIHRoYXQgYXJlIGFjY2Vzc2VkIHZpYSB1bnBhY2tpbmcgKHNlZSBsYXRlciBpbiB0aGlzIHNlY3Rpb24pIG9yIGluZGV4aW5nIChvciBldmVuIGJ5IGF0dHJpYnV0ZSBpbiB0aGUgY2FzZSBvZiBuYW1lZHR1cGxlcykuIExpc3RzIGFyZSBtdXRhYmxlLCBhbmQgdGhlaXIgZWxlbWVudHMgYXJlIHVzdWFsbHkgaG9tb2dlbmVvdXMgYW5kIGFyZSBhY2Nlc3NlZCBieSBpdGVyYXRpbmcgb3ZlciB0aGUgbGlzdC5cXG4uLi5cXG5Bbm90aGVyIHVzZWZ1bCBkYXRhIHR5cGUgYnVpbHQgaW50byBQeXRob24gaXMgdGhlIGRpY3Rpb25hcnkgKHNlZSBNYXBwaW5nIFR5cGVzIFxcdTIwMTQgZGljdCkuIERpY3Rpb25hcmllcyBhcmUgc29tZXRpbWVzIGZvdW5kIGluIG90aGVyIGxhbmd1YWdlcyBhcyBcXHUyMDFjYXNzb2NpYXRpdmUgbWVtb3JpZXNcXHUyMDFkIG9yIFxcdTIwMWNhc3NvY2lhdGl2ZSBhcnJheXNcXHUyMDFkLiBVbmxpa2Ugc2VxdWVuY2VzLCB3aGljaCBhcmUgaW5kZXhlZCBieSBhIHJhbmdlIG9mIG51bWJlcnMsIGRpY3Rpb25hcmllcyBhcmUgaW5kZXhlZCBieSBrZXlzLCB3aGljaCBjYW4gYmUgYW55IGltbXV0YWJsZSB0eXBlOyBzdHJpbmdzIGFuZCBudW1iZXJzIGNhbiBhbHdheXMgYmUga2V5cy4gVHVwbGVzIGNhbiBiZSB1c2VkIGFzIGtleXMgaWYgdGhleSBjb250YWluIG9ubHkgc3RyaW5ncywgbnVtYmVycywgb3IgdHVwbGVzOyBpZiBhIHR1cGxlIGNvbnRhaW5zIGFueSBtdXRhYmxlIG9iamVjdCBlaXRoZXIgZGlyZWN0bHkgb3IgaW5kaXJlY3RseSwgaXQgY2Fubm90IGJlIHVzZWQgYXMgYSBrZXkuIFlvdSBjYW5cXHUyMDE5dCB1c2UgbGlzdHMgYXMga2V5cywgc2luY2UgbGlzdHMgY2FuIGJlIG1vZGlmaWVkIGluIHBsYWNlIHVzaW5nIGluZGV4IGFzc2lnbm1lbnRzLCBzbGljZSBhc3NpZ25tZW50cywgb3IgbWV0aG9kcyBsaWtlIGFwcGVuZCgpIGFuZCBleHRlbmQoKS5cIl19LCB7XCJ0aXRsZVwiOiBcIjMuIERhdGEgbW9kZWwgXFx1MjAxNCBQeXRob24gMy4xNC41IGRvY3VtZW50YXRpb25cIiwgXCJ1cmxcIjogXCJodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL3JlZmVyZW5jZS9kYXRhbW9kZWwuaHRtbFwiLCBcImhpZ2hsaWdodHNcIjogW1wiVGhlIHZhbHVlIG9mIHNvbWUgb2JqZWN0cyBjYW4gY2hhbmdlLiBPYmplY3RzIHdob3NlIHZhbHVlIGNhbiBjaGFuZ2UgYXJlIHNhaWQgdG8gYmUgbXV0YWJsZTsgb2JqZWN0cyB3aG9zZSB2YWx1ZSBpcyB1bmNoYW5nZWFibGUgb25jZSB0aGV5IGFyZSBjcmVhdGVkIGFyZSBjYWxsZWQgaW1tdXRhYmxlLiAoVGhlIHZhbHVlIG9mIGFuIGltbXV0YWJsZSBjb250YWluZXIgb2JqZWN0IHRoYXQgY29udGFpbnMgYSByZWZlcmVuY2UgdG8gYSBtdXRhYmxlIG9iamVjdCBjYW4gY2hhbmdlIHdoZW4gdGhlIGxhdHRlclxcdTIwMTlzIHZhbHVlIGlzIGNoYW5nZWQ7IGhvd2V2ZXIgdGhlIGNvbnRhaW5lciBpcyBzdGlsbCBjb25zaWRlcmVkIGltbXV0YWJsZSwgYmVjYXVzZSB0aGUgY29sbGVjdGlvbiBvZiBvYmplY3RzIGl0IGNvbnRhaW5zIGNhbm5vdCBiZSBjaGFuZ2VkLiBTbywgaW1tdXRhYmlsaXR5IGlzIG5vdCBzdHJpY3RseSB0aGUgc2FtZSBhcyBoYXZpbmcgYW4gdW5jaGFuZ2VhYmxlIHZhbHVlLCBpdCBpcyBtb3JlIHN1YnRsZS4pIEFuIG9iamVjdFxcdTIwMTlzIG11dGFiaWxpdHkgaXMgZGV0ZXJtaW5lZCBieSBpdHMgdHlwZTsgZm9yIGluc3RhbmNlLCBudW1iZXJzLCBzdHJpbmdzIGFuZCB0dXBsZXMgYXJlIGltbXV0YWJsZSwgd2hpbGUgZGljdGlvbmFyaWVzIGFuZCBsaXN0cyBhcmUgbXV0YWJsZS5cXG4uLi5cXG5Tb21lIG9iamVjdHMgY29udGFpbiByZWZlcmVuY2VzIHRvIG90aGVyIG9iamVjdHM7IHRoZXNlIGFyZSBjYWxsZWQgY29udGFpbmVycy4gRXhhbXBsZXMgb2YgY29udGFpbmVycyBhcmUgdHVwbGVzLCBsaXN0cyBhbmQgZGljdGlvbmFyaWVzLiBUaGUgcmVmZXJlbmNlcyBhcmUgcGFydCBvZiBhIGNvbnRhaW5lclxcdTIwMTlzIHZhbHVlLiBJbiBtb3N0IGNhc2VzLCB3aGVuIHdlIHRhbGsgYWJvdXQgdGhlIHZhbHVlIG9mIGEgY29udGFpbmVyLCB3ZSBpbXBseSB0aGUgdmFsdWVzLCBub3QgdGhlIGlkZW50aXRpZXMgb2YgdGhlIGNvbnRhaW5lZCBvYmplY3RzOyBob3dldmVyLCB3aGVuIHdlIHRhbGsgYWJvdXQgdGhlIG11dGFiaWxpdHkgb2YgYSBjb250YWluZXIsIG9ubHkgdGhlIGlkZW50aXRpZXMgb2YgdGhlIGltbWVkaWF0ZWx5IGNvbnRhaW5lZCBvYmplY3RzIGFyZSBpbXBsaWVkLiBTbywgaWYgYW4gaW1tdXRhYmxlIGNvbnRhaW5lciAobGlrZSBhIHR1cGxlKSBjb250YWlucyBhIHJlZmVyZW5jZSB0byBhIG11dGFibGUgb2JqZWN0LCBpdHMgdmFsdWUgY2hhbmdlcyBpZiB0aGF0IG11dGFibGUgb2JqZWN0IGlzIGNoYW5nZWQuXFxuLi4uXFxuIyMjIDMuMi41LiBTZXF1ZW5jZXNcXHUwMGI2XFxuLi4uXFxuIyMjIyAzLjIuNS4xLiBJbW11dGFibGUgc2VxdWVuY2VzXFx1MDBiNlxcblxcbkFuIG9iamVjdCBvZiBhbiBpbW11dGFibGUgc2VxdWVuY2UgdHlwZSBjYW5ub3QgY2hhbmdlIG9uY2UgaXQgaXMgY3JlYXRlZC4gKElmIHRoZSBvYmplY3QgY29udGFpbnMgcmVmZXJlbmNlcyB0byBvdGhlciBvYmplY3RzLCB0aGVzZSBvdGhlciBvYmplY3RzIG1heSBiZSBtdXRhYmxlIGFuZCBtYXkgYmUgY2hhbmdlZDsgaG93ZXZlciwgdGhlIGNvbGxlY3Rpb24gb2Ygb2JqZWN0cyBkaXJlY3RseSByZWZlcmVuY2VkIGJ5IGFuIGltbXV0YWJsZSBvYmplY3QgY2Fubm90IGNoYW5nZS4pXFxuXFxuVGhlIGZvbGxvd2luZyB0eXBlcyBhcmUgaW1tdXRhYmxlIHNlcXVlbmNlczpcXG4uLi5cXG5UdXBsZXNcXG46IFRoZSBpdGVtcyBvZiBhIGB0dXBsZWAgYXJlIGFyYml0cmFyeSBQeXRob24gb2JqZWN0cy4gVHVwbGVzIG9mIHR3byBvciBtb3JlIGl0ZW1zIGFyZSBmb3JtZWQgYnkgY29tbWEtc2VwYXJhdGVkIGxpc3RzIG9mIGV4cHJlc3Npb25zLiBBIHR1cGxlIG9mIG9uZSBpdGVtIChhIFxcdTIwMThzaW5nbGV0b25cXHUyMDE5KSBjYW4gYmUgZm9ybWVkIGJ5IGFmZml4aW5nIGEgY29tbWEgdG8gYW4gZXhwcmVzc2lvbiAoYW4gZXhwcmVzc2lvbiBieSBpdHNlbGYgZG9lcyBub3QgY3JlYXRlIGEgdHVwbGUsIHNpbmNlIHBhcmVudGhlc2VzIG11c3QgYmUgdXNhYmxlIGZvciBncm91cGluZyBvZiBleHByZXNzaW9ucykuIEFuIGVtcHR5IHR1cGxlIGNhbiBiZSBmb3JtZWQgYnkgYW4gZW1wdHkgcGFpciBvZiBwYXJlbnRoZXNlcy5cXG4uLi5cXG4jIyMjIDMuMi41LjIuIE11dGFibGUgc2VxdWVuY2VzXFx1MDBiNlxcblxcbk11dGFibGUgc2VxdWVuY2VzIGNhbiBiZSBjaGFuZ2VkIGFmdGVyIHRoZXkgYXJlIGNyZWF0ZWQuIFRoZSBzdWJzY3JpcHRpb24gYW5kIHNsaWNpbmcgbm90YXRpb25zIGNhbiBiZSB1c2VkIGFzIHRoZSB0YXJnZXQgb2YgYXNzaWdubWVudCBhbmQgYGRlbGAgKGRlbGV0ZSkgc3RhdGVtZW50cy5cXG4uLi5cXG5UaGVyZSBhcmUgY3VycmVudGx5IHR3byBpbnRyaW5zaWMgbXV0YWJsZSBzZXF1ZW5jZSB0eXBlczpcXG5cXG5MaXN0c1xcbjogVGhlIGl0ZW1zIG9mIGEgbGlzdCBhcmUgYXJiaXRyYXJ5IFB5dGhvbiBvYmplY3RzLiBMaXN0cyBhcmUgZm9ybWVkIGJ5IHBsYWNpbmcgYSBjb21tYS1zZXBhcmF0ZWQgbGlzdCBvZiBleHByZXNzaW9ucyBpbiBzcXVhcmUgYnJhY2tldHMuIChOb3RlIHRoYXQgdGhlcmUgYXJlIG5vIHNwZWNpYWwgY2FzZXMgbmVlZGVkIHRvIGZvcm0gbGlzdHMgb2YgbGVuZ3RoIDAgb3IgMS4pXCJdfSwge1widGl0bGVcIjogXCJCdWlsdC1pbiBUeXBlcyBcXHUyMDE0IFB5dGhvbiAzLjE0LjcgZG9jdW1lbnRhdGlvblwiLCBcInVybFwiOiBcImh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvYnVpbHRpbnMvc3RkdHlwZXMuaHRtbFwiLCBcImhpZ2hsaWdodHNcIjogW1wiY29sbGVjdGlvbiBjbGFzc2VzIGFyZSBtdXRhYmxlLiBUaGUgbWV0aG9kcyB0aGF0IGFkZCwgc3VidHJhY3QsIG9yIHJlYXJyYW5nZSB0aGVpciAuLi4gaW4gcGxhY2UsIGFuZCBkb25cXHUyMDE5dCByZXR1cm4gYSAuLi4gLCBuZXZlciByZXR1cm4gdGhlIGNvbGxlY3Rpb24gaW5zdGFuY2UgaXRzZWxmIGJ1dCBgTm9uZWAuXFxuLi4uXFxuIyMgU2VxdWVuY2UgVHlwZXMgXFx1MjAxNCBgbGlzdGAsIGB0dXBsZWAsIGByYW5nZWBcXHUwMGI2XFxuXFxuVGhlcmUgYXJlIHRocmVlIGJhc2ljIHNlcXVlbmNlIHR5cGVzOiBsaXN0cywgdHVwbGVzLCBhbmQgcmFuZ2Ugb2JqZWN0cy4gQWRkaXRpb25hbCBzZXF1ZW5jZSB0eXBlcyB0YWlsb3JlZCBmb3IgcHJvY2Vzc2luZyBvZiBiaW5hcnkgZGF0YSBhbmQgdGV4dCBzdHJpbmdzIGFyZSBkZXNjcmliZWQgaW4gZGVkaWNhdGVkIHNlY3Rpb25zLlxcbi4uLlxcblRoZSBvcGVyYXRpb25zIGluIHRoZSBmb2xsb3dpbmcgdGFibGUgLi4uIG11dGFibGUgYW5kIGltbXV0YWJsZS4gVGhlIGBjb2xsZWN0aW9ucy4gLi4uIGlzIHByb3ZpZGVkIHRvIG1ha2UgLi4uIGVhc2llciB0byBjb3JyZWN0bHkgaW1wbGVtZW50IHRoZXNlIG9wZXJhdGlvbnMgb24gY3VzdG9tIHNlcXVlbmNlIHR5cGVzXFxuLi4uXFxuIyMjIEltbXV0YWJsZSBTZXF1ZW5jZSBUeXBlc1xcdTAwYjZcXG4uLi5cXG5tdXRhYmxlIHNlcXVlbmNlIHR5cGVzIGlzXFxuLi4uXFxuc3VwcG9ydCBhbGxvd3MgaW1tdXRhYmxlIHNlcXVlbmNlcywgLi4uICwgdG8gYmUgdXNlZCBhcyBgZGljdGAga2V5cyBhbmQgc3RvcmVkIGluIC4uLiBlbnNldGAgaW5zdGFuY2VzXFxuLi4uXFxuIyMjIE11dGFibGUgU2VxdWVuY2UgVHlwZXNcXHUwMGI2XFxuLi4uXFxuIyMjIExpc3RzXFx1MDBiNlxcblxcbkxpc3RzIGFyZSBtdXRhYmxlIHNlcXVlbmNlcywgdHlwaWNhbGx5IHVzZWQgdG8gc3RvcmUgY29sbGVjdGlvbnMgb2YgaG9tb2dlbmVvdXMgaXRlbXMgKHdoZXJlIHRoZSBwcmVjaXNlIGRlZ3JlZSBvZiBzaW1pbGFyaXR5IHdpbGwgdmFyeSBieSBhcHBsaWNhdGlvbikuXFxuLi4uXFxuIyMjIFR1cGxlc1xcdTAwYjZcXG5cXG5UdXBsZXMgYXJlIGltbXV0YWJsZSBzZXF1ZW5jZXMsIHR5cGljYWxseSB1c2VkIHRvIHN0b3JlIGNvbGxlY3Rpb25zIG9mIGhldGVyb2dlbmVvdXMgZGF0YSAoc3VjaCBhcyB0aGUgMi10dXBsZXMgcHJvZHVjZWQgYnkgdGhlIGBlbnVtZXJhdGUoKWAgYnVpbHQtaW4pLiBUdXBsZXMgYXJlIGFsc28gdXNlZCBmb3IgY2FzZXMgd2hlcmUgYW4gaW1tdXRhYmxlIHNlcXVlbmNlIG9mIGhvbW9nZW5lb3VzIGRhdGEgaXMgbmVlZGVkIChzdWNoIGFzIGFsbG93aW5nIHN0b3JhZ2UgaW4gYSBgc2V0YCBvciBgZGljdGAgaW5zdGFuY2UpLlxcbi4uLlxcbnR1cGxlKGl0ZXJhYmxlPVxcbi4uLlxcblRoZSBjb25zdHJ1Y3RvciBidWlsZHMgYSB0dXBsZSB3aG9zZSBpdGVtcyBhcmUgdGhlIHNhbWUgYW5kIGluIHRoZSBzYW1lIG9yZGVyIGFzIGl0ZXJhYmxlXFx1MjAxOXMgaXRlbXMuIGl0ZXJhYmxlIG1heSBiZSBlaXRoZXIgYSBzZXF1ZW5jZSwgYSBjb250YWluZXIgdGhhdCBzdXBwb3J0cyBpdGVyYXRpb24sIG9yIGFuIGl0ZXJhdG9yIG9iamVjdC4gSWYgaXRlcmFibGUgaXMgYWxyZWFkeSBhIHR1cGxlLCBpdCBpcyByZXR1cm5lZCB1bmNoYW5nZWQuIEZvciBleGFtcGxlLCBgdHVwbGUoJ2FiYycpYCByZXR1cm5zIGAoJ2EnLCAnYicsICdjJylgIGFuZCBgdHVwbGUoIFsxLCAyLCAzXSApYCByZXR1cm5zIGAoMSwgMiwgMylgLiBJZiBubyBhcmd1bWVudCBpcyBnaXZlbiwgdGhlIGNvbnN0cnVjdG9yIGNyZWF0ZXMgYSBuZXcgZW1wdHkgdHVwbGUsIGAoKWAuXFxuLi4uXFxuVHVwbGVzIGltcGxlbWVudCBhbGwgb2YgdGhlIGNvbW1vbiBzZXF1ZW5jZSBvcGVyYXRpb25zLlxcbi4uLlxcbkZvciBoZXRlcm9nZW5lb3VzIGNvbGxlY3Rpb25zIG9mIGRhdGEgd2hlcmUgYWNjZXNzIGJ5IG5hbWUgaXMgY2xlYXJlciB0aGFuIGFjY2VzcyBieSBpbmRleCwgYGNvbGxlY3Rpb25zLm5hbWVkdHVwbGUoKWAgbWF5IGJlIGEgbW9yZSBhcHByb3ByaWF0ZSBjaG9pY2UgdGhhbiBhIHNpbXBsZSB0dXBsZSBvYmplY3QuXCJdfSwge1widGl0bGVcIjogXCJCdWlsdC1pbiBUeXBlcyBcXHUyMDE0IFB5dGhvbiAzLjE0LjUgZG9jdW1lbnRhdGlvblwiLCBcInVybFwiOiBcImh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvbGlicmFyeS9zdGR0eXBlcy5odG1sXCIsIFwiaGlnaGxpZ2h0c1wiOiBbXCJTb21lIGNvbGxlY3Rpb24gY2xhc3NlcyBhcmUgbXV0YWJsZS4gVGhlIG1ldGhvZHMgdGhhdCBhZGQsIHN1YnRyYWN0LCBvciByZWFycmFuZ2UgdGhlaXIgLi4uIGluIHBsYWNlLCBhbmQgZG9uXFx1MjAxOXQgcmV0dXJuIGEgLi4uICwgbmV2ZXIgcmV0dXJuIHRoZSBjb2xsZWN0aW9uIGluc3RhbmNlIGl0c2VsZiBidXQgYE5vbmVgLlxcbi4uLlxcbiMjIFNlcXVlbmNlIFR5cGVzIFxcdTIwMTQgYGxpc3RgLCBgdHVwbGVgLCBgcmFuZ2VgXFx1MDBiNlxcblxcblRoZXJlIGFyZSB0aHJlZSBiYXNpYyBzZXF1ZW5jZSB0eXBlczogbGlzdHMsIHR1cGxlcywgYW5kIC4uLiBvYmplY3RzLiBBZGRpdGlvbmFsIHNlcXVlbmNlIHR5cGVzIHRhaWxvcmVkIGZvciBwcm9jZXNzaW5nIG9mIGJpbmFyeSBkYXRhIGFuZCB0ZXh0IHN0cmluZ3MgYXJlIGRlc2NyaWJlZCBpbiBkZWRpY2F0ZWQgc2VjdGlvbnMuXFxuLi4uXFxuVGhlIG9wZXJhdGlvbnMgaW4gdGhlIGZvbGxvd2luZyB0YWJsZSAuLi4gaW1tdXRhYmxlLiBUaGUgYCAuLi4gaXMgcHJvdmlkZWQgdG8gbWFrZSAuLi4gZWFzaWVyIHRvIGNvcnJlY3RseSBpbXBsZW1lbnQgdGhlc2Ugb3BlcmF0aW9ucyBvbiBjdXN0b20gc2VxdWVuY2UgdHlwZXNcXG4uLi5cXG4jIyMgSW1tdXRhYmxlIFNlcXVlbmNlIFR5cGVzXFx1MDBiNlxcbi4uLlxcbm9wZXJhdGlvbiB0aGF0IGltbXV0YWJsZSBzZXF1ZW5jZSAuLi4gYnkgbXV0YWJsZSBzZXF1ZW5jZSB0eXBlcyBpcyAuLi4gYGhhc2goKWBcXG4uLi5cXG5UaGlzIHN1cHBvcnQgYWxsb3dzIGltbXV0YWJsZSBzZXF1ZW5jZXMsIHN1Y2ggYXMgYHR1cGxlYCBpbnN0YW5jZXMsIHRvIGJlIHVzZWQgYXMgYGRpY3RgIGtleXMgYW5kIHN0b3JlZCBpbiBgc2V0YCBhbmQgYGZyb3plbnNldGAgaW5zdGFuY2VzLlxcbi4uLlxcbiMjIyBNdXRhYmxlIFNlcXVlbmNlIFR5cGVzXFx1MDBiNlxcbi4uLlxcbiMjIyBMaXN0c1xcdTAwYjZcXG5cXG5MaXN0cyBhcmUgbXV0YWJsZSBzZXF1ZW5jZXMsIHR5cGljYWxseSB1c2VkIHRvIHN0b3JlIGNvbGxlY3Rpb25zIG9mIGhvbW9nZW5lb3VzIGl0ZW1zICh3aGVyZSB0aGUgcHJlY2lzZSBkZWdyZWUgb2Ygc2ltaWxhcml0eSB3aWxsIHZhcnkgYnkgYXBwbGljYXRpb24pLlxcbi4uLlxcbiMjIyBUdXBsZXNcXHUwMGI2XFxuXFxuVHVwbGVzIGFyZSBpbW11dGFibGUgc2VxdWVuY2VzLCB0eXBpY2FsbHkgdXNlZCB0byBzdG9yZSBjb2xsZWN0aW9ucyBvZiBoZXRlcm9nZW5lb3VzIGRhdGEgKHN1Y2ggYXMgdGhlIDItdHVwbGVzIHByb2R1Y2VkIGJ5IHRoZSBgZW51bWVyYXRlKClgIGJ1aWx0LWluKS4gVHVwbGVzIGFyZSBhbHNvIHVzZWQgZm9yIGNhc2VzIHdoZXJlIGFuIGltbXV0YWJsZSBzZXF1ZW5jZSBvZiBob21vZ2VuZW91cyBkYXRhIGlzIG5lZWRlZCAoc3VjaCBhcyBhbGxvd2luZyBzdG9yYWdlIGluIGEgYHNldGAgb3IgYGRpY3RgIGluc3RhbmNlKS5cXG4uLi5cXG5UaGUgY29uc3RydWN0b3IgYnVpbGRzIGEgdHVwbGUgd2hvc2UgaXRlbXMgYXJlIHRoZSBzYW1lIGFuZCBpbiB0aGUgc2FtZSBvcmRlciBhcyBpdGVyYWJsZVxcdTIwMTlzIGl0ZW1zLiBpdGVyYWJsZSBtYXkgYmUgZWl0aGVyIGEgc2VxdWVuY2UsIGEgY29udGFpbmVyIHRoYXQgc3VwcG9ydHMgaXRlcmF0aW9uLCBvciBhbiBpdGVyYXRvciBvYmplY3QuIElmIGl0ZXJhYmxlIGlzIGFscmVhZHkgYSB0dXBsZSwgaXQgaXMgcmV0dXJuZWQgdW5jaGFuZ2VkLiBGb3IgZXhhbXBsZSwgYHR1cGxlKCdhYmMnKWAgcmV0dXJucyBgKCdhJywgJ2InLCAnYycpYCBhbmQgYHR1cGxlKCBbMSwgMiwgM10gKWAgcmV0dXJucyBgKDEsIDIsIDMpYC4gSWYgbm8gYXJndW1lbnQgaXMgZ2l2ZW4sIHRoZSBjb25zdHJ1Y3RvciBjcmVhdGVzIGEgbmV3IGVtcHR5IHR1cGxlLCBgKClgLlxcbi4uLlxcblR1cGxlcyBpbXBsZW1lbnQgYWxsIG9mIHRoZSBjb21tb24gc2VxdWVuY2Ugb3BlcmF0aW9ucy5cXG4uLi5cXG5Gb3IgaGV0ZXJvZ2VuZW91cyBjb2xsZWN0aW9ucyBvZiBkYXRhIHdoZXJlIGFjY2VzcyBieSBuYW1lIGlzIGNsZWFyZXIgdGhhbiBhY2Nlc3MgYnkgaW5kZXgsIGBjb2xsZWN0aW9ucy5uYW1lZHR1cGxlKClgIG1heSBiZSBhIG1vcmUgYXBwcm9wcmlhdGUgY2hvaWNlIHRoYW4gYSBzaW1wbGUgdHVwbGUgb2JqZWN0LlwiXX0sIHtcInRpdGxlXCI6IFwiNS4gRGF0YSBTdHJ1Y3R1cmVzIFxcdTIwMTQgUHl0aG9uIDMuMTAuMjAgZG9jdW1lbnRhdGlvblwiLCBcInVybFwiOiBcImh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMuMTAvdHV0b3JpYWwvZGF0YXN0cnVjdHVyZXMuaHRtbFwiLCBcImhpZ2hsaWdodHNcIjogW1wiWW91IG1pZ2h0IGhhdmUgbm90aWNlZCB0aGF0IG1ldGhvZHMgbGlrZSBgaW5zZXJ0YCwgYHJlbW92ZWAgb3IgYHNvcnRgIHRoYXQgb25seSBtb2RpZnkgdGhlIGxpc3QgaGF2ZSBubyByZXR1cm4gdmFsdWUgcHJpbnRlZCBcXHUyMDEzIHRoZXkgcmV0dXJuIHRoZSBkZWZhdWx0IGBOb25lYC4gMSBUaGlzIGlzIGEgZGVzaWduIHByaW5jaXBsZSBmb3IgYWxsIG11dGFibGUgZGF0YSBzdHJ1Y3R1cmVzIGluIFB5dGhvbi5cXG4uLi5cXG4jIyA1LjMuIFR1cGxlcyBhbmQgU2VxdWVuY2VzXFx1MDBiNlxcblxcbldlIHNhdyB0aGF0IGxpc3RzIGFuZCBzdHJpbmdzIGhhdmUgbWFueSBjb21tb24gcHJvcGVydGllcywgc3VjaCBhcyBpbmRleGluZyBhbmQgc2xpY2luZyBvcGVyYXRpb25zLiBUaGV5IGFyZSB0d28gZXhhbXBsZXMgb2Ygc2VxdWVuY2UgZGF0YSB0eXBlcyAoc2VlIFNlcXVlbmNlIFR5cGVzIFxcdTIwMTQgbGlzdCwgdHVwbGUsIHJhbmdlKS4gU2luY2UgUHl0aG9uIGlzIGFuIGV2b2x2aW5nIGxhbmd1YWdlLCBvdGhlciBzZXF1ZW5jZSBkYXRhIHR5cGVzIG1heSBiZSBhZGRlZC4gVGhlcmUgaXMgYWxzbyBhbm90aGVyIHN0YW5kYXJkIHNlcXVlbmNlIGRhdGEgdHlwZTogdGhlIHR1cGxlLlxcblxcbkEgdHVwbGUgY29uc2lzdHMgb2YgYSBudW1iZXIgb2YgdmFsdWVzIHNlcGFyYXRlZCBieSBjb21tYXMsIGZvciBpbnN0YW5jZTpcXG4uLi5cXG4+Pj4gIyBUdXBsZXMgYXJlIGltbXV0YWJsZTpcXG4uLi4gdFswXSA9IDg4ODg4XFxuVHJhY2ViYWNrIChtb3N0IHJlY2VudCBjYWxsIGxhc3QpOlxcbiAgRmlsZSBcXFwiPHN0ZGluPlxcXCIsIGxpbmUgMSwgaW4gPG1vZHVsZT5cXG5UeXBlRXJyb3I6ICd0dXBsZScgb2JqZWN0IGRvZXMgbm90IHN1cHBvcnQgaXRlbSBhc3NpZ25tZW50XFxuPj4+ICMgYnV0IHRoZXkgY2FuIGNvbnRhaW4gbXV0YWJsZSBvYmplY3RzOlxcbi4uLiB2ID0gKFsxLCAyLCAzXSwgWzMsIDIsIDFdKVxcbj4+PiB2XFxuKFsxLCAyLCAzXSwgWzMsIDIsIDFdKVxcbi4uLlxcbkFzIHlvdSBzZWUsIG9uIG91dHB1dCB0dXBsZXMgYXJlIGFsd2F5cyBlbmNsb3NlZCBpbiBwYXJlbnRoZXNlcywgc28gdGhhdCBuZXN0ZWQgdHVwbGVzIGFyZSBpbnRlcnByZXRlZCBjb3JyZWN0bHk7IHRoZXkgbWF5IGJlIGlucHV0IHdpdGggb3Igd2l0aG91dCBzdXJyb3VuZGluZyBwYXJlbnRoZXNlcywgYWx0aG91Z2ggb2Z0ZW4gcGFyZW50aGVzZXMgYXJlIG5lY2Vzc2FyeSBhbnl3YXkgKGlmIHRoZSB0dXBsZSBpcyBwYXJ0IG9mIGEgbGFyZ2VyIGV4cHJlc3Npb24pLiBJdCBpcyBub3QgcG9zc2libGUgdG8gYXNzaWduIHRvIHRoZSBpbmRpdmlkdWFsIGl0ZW1zIG9mIGEgdHVwbGUsIGhvd2V2ZXIgaXQgaXMgcG9zc2libGUgdG8gY3JlYXRlIHR1cGxlcyB3aGljaCBjb250YWluIG11dGFibGUgb2JqZWN0cywgc3VjaCBhcyBsaXN0cy5cXG5cXG5UaG91Z2ggdHVwbGVzIG1heSBzZWVtIHNpbWlsYXIgdG8gbGlzdHMsIHRoZXkgYXJlIG9mdGVuIHVzZWQgaW4gZGlmZmVyZW50IHNpdHVhdGlvbnMgYW5kIGZvciBkaWZmZXJlbnQgcHVycG9zZXMuIFR1cGxlcyBhcmUgaW1tdXRhYmxlLCBhbmQgdXN1YWxseSBjb250YWluIGEgaGV0ZXJvZ2VuZW91cyBzZXF1ZW5jZSBvZiBlbGVtZW50cyB0aGF0IGFyZSBhY2Nlc3NlZCB2aWEgdW5wYWNraW5nIChzZWUgbGF0ZXIgaW4gdGhpcyBzZWN0aW9uKSBvciBpbmRleGluZyAob3IgZXZlbiBieSBhdHRyaWJ1dGUgaW4gdGhlIGNhc2Ugb2YgYG5hbWVkdHVwbGVzYCkuIExpc3RzIGFyZSBtdXRhYmxlLCBhbmQgdGhlaXIgZWxlbWVudHMgYXJlIHVzdWFsbHkgaG9tb2dlbmVvdXMgYW5kIGFyZSBhY2Nlc3NlZCBieSBpdGVyYXRpbmcgb3ZlciB0aGUgbGlzdC5cXG4uLi5cXG4jIyA1LjQuXFxuLi4uXFxuLiBTZXQgb2JqZWN0c1xcbi4uLlxcbiMjIDUuNS4gRGljdGlvbmFyaWVzXFx1MDBiNlxcblxcbkFub3RoZXIgdXNlZnVsIGRhdGEgdHlwZSBidWlsdCBpbnRvIFB5dGhvbiBpcyB0aGUgZGljdGlvbmFyeSAoc2VlIE1hcHBpbmcgVHlwZXMgXFx1MjAxNCBkaWN0KS4gRGljdGlvbmFyaWVzIGFyZSBzb21ldGltZXMgZm91bmQgaW4gb3RoZXIgbGFuZ3VhZ2VzIGFzIFxcdTIwMWNhc3NvY2lhdGl2ZSBtZW1vcmllc1xcdTIwMWQgb3IgXFx1MjAxY2Fzc29jaWF0aXZlIGFycmF5c1xcdTIwMWQuIFVubGlrZSBzZXF1ZW5jZXMsIHdoaWNoIGFyZSBpbmRleGVkIGJ5IGEgcmFuZ2Ugb2YgbnVtYmVycywgZGljdGlvbmFyaWVzIGFyZSBpbmRleGVkIGJ5IGtleXMsIHdoaWNoIGNhbiBiZSBhbnkgaW1tdXRhYmxlIHR5cGU7IHN0cmluZ3MgYW5kIG51bWJlcnMgY2FuIGFsd2F5cyBiZSBrZXlzLiBUdXBsZXMgY2FuIGJlIHVzZWQgYXMga2V5cyBpZiB0aGV5IGNvbnRhaW4gb25seSBzdHJpbmdzLCBudW1iZXJzLCBvciB0dXBsZXM7IGlmIGEgdHVwbGUgY29udGFpbnMgYW55IG11dGFibGUgb2JqZWN0IGVpdGhlciBkaXJlY3RseSBvciBpbmRpcmVjdGx5LCBpdCBjYW5ub3QgYmUgdXNlZCBhcyBhIGtleS4gWW91IGNhblxcdTIwMTl0IHVzZSBsaXN0cyBhcyBrZXlzLCBzaW5jZSBsaXN0cyBjYW4gYmUgbW9kaWZpZWQgaW4gcGxhY2UgdXNpbmcgaW5kZXggYXNzaWdubWVudHMsIHNsaWNlIGFzc2lnbm1lbnRzLCBvciBtZXRob2RzIGxpa2UgYGFwcGVuZCgpYCBhbmQgYGV4dGVuZCgpYC5cIl19XSIsImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnt9LCJ0eXBlIjoidG9vbCIsIm5hbWUiOiJ3ZWJfc2VhcmNoIiwiaWQiOiI2ZTUxMjVhYy0zMTY0LTRhNzYtOWM1Mi1hYzM0NjBjZTM2ZTQiLCJ0b29sX2NhbGxfaWQiOiJ0b29sdV8wMUIyTGZIR0RqWVNGSmhtaVhOajRDdVEiLCJzdGF0dXMiOiJzdWNjZXNzIn0seyJjb250ZW50IjpbeyJpZCI6InRvb2x1XzAxWGpqM2FSZFd5aEJKZlBtVEpCeFFhOSIsImNhbGxlciI6eyJ0eXBlIjoiZGlyZWN0In0sImlucHV0Ijp7fSwibmFtZSI6InRyYW5zZmVyX3RvX3NrZXB0aWMiLCJ0eXBlIjoidG9vbF91c2UiLCJ0b29sc2V0X25hbWUiOm51bGx9XSwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6eyJpZCI6Im1zZ18wMTFDZmR3QTZGNGNDTjV5aEQ0Q3JzOU0iLCJjb250YWluZXIiOm51bGwsImRpYWdub3N0aWNzIjpudWxsLCJtb2RlbCI6ImNsYXVkZS1zb25uZXQiLCJzdG9wX2RldGFpbHMiOm51bGwsInN0b3BfcmVhc29uIjoidG9vbF91c2UiLCJzdG9wX3NlcXVlbmNlIjpudWxsLCJ1c2FnZSI6eyJjYWNoZV9jcmVhdGlvbiI6eyJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowfSwiY2FjaGVfY3JlYXRpb25faW5wdXRfdG9rZW5zIjowLCJjYWNoZV9yZWFkX2lucHV0X3Rva2VucyI6MCwiaW5mZXJlbmNlX2dlbyI6Imdsb2JhbCIsImlucHV0X3Rva2VucyI6NzM3OCwib3V0cHV0X3Rva2VucyI6MzMsIm91dHB1dF90b2tlbnNfZGV0YWlscyI6eyJ0aGlua2luZ190b2tlbnMiOjB9LCJzZXJ2ZXJfdG9vbF91c2UiOm51bGwsInNlcnZpY2VfdGllciI6InN0YW5kYXJkIn0sIm1vZGVsX25hbWUiOiJjbGF1ZGUtc29ubmV0IiwibW9kZWxfcHJvdmlkZXIiOiJhbnRocm9waWMifSwidHlwZSI6ImFpIiwibmFtZSI6InJlc2VhcmNoZXIiLCJpZCI6ImxjX3J1bi0tMDFhMGZlMDMtM2NkOC03OWYxLTg4YTEtY2U2Y2VlMjk0ZTc5LTAiLCJ0b29sX2NhbGxzIjpbeyJuYW1lIjoidHJhbnNmZXJfdG9fc2tlcHRpYyIsImFyZ3MiOnt9LCJpZCI6InRvb2x1XzAxWGpqM2FSZFd5aEJKZlBtVEpCeFFhOSIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6NzM3OCwib3V0cHV0X3Rva2VucyI6MzMsInRvdGFsX3Rva2VucyI6NzQxMSwiaW5wdXRfdG9rZW5fZGV0YWlscyI6eyJjYWNoZV9yZWFkIjowLCJjYWNoZV9jcmVhdGlvbiI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MH0sIm91dHB1dF90b2tlbl9kZXRhaWxzIjp7InJlYXNvbmluZyI6MH19fSx7ImNvbnRlbnQiOiJTdWNjZXNzZnVsbHkgdHJhbnNmZXJyZWQgdG8gc2tlcHRpYyIsImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnt9LCJ0eXBlIjoidG9vbCIsIm5hbWUiOiJ0cmFuc2Zlcl90b19za2VwdGljIiwiaWQiOiIzODkwNThkMS0wODNmLTQ2MzItYmJjNS0wOWJmZDNhMGZmZDIiLCJ0b29sX2NhbGxfaWQiOiJ0b29sdV8wMVhqajNhUmRXeWhCSmZQbVRKQnhRYTkiLCJzdGF0dXMiOiJzdWNjZXNzIn1dLCJhY3RpdmVfYWdlbnQiOiJza2VwdGljIn0=" + } + } + ], + "events": [ + { + "timeUnixNano": "1790968030909441000", + "name": "exception", + "attributes": [ + { + "key": "exception.type", + "value": { + "stringValue": "Exception" + } + }, + { + "key": "exception.message", + "value": { + "stringValue": "ParentCommand(Command(graph='skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier')" + } + }, + { + "key": "exception.stacktrace", + "value": { + "stringValue": "Exception: ParentCommand(Command(graph='skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': 'CAQS1QgKEAgSGAI4AUIIdGhpbmtpbmcSDN6TfU6NDM971lEbzxoMvRUA1J9ox3fJQYT9IjArCQQGHBP4pRHPavXzRlbMbaYHC57Yj+Gbxgr0helvd2OIL/o6Rbt4PFA3FaIFUlgq8gc7KQI9FtGnvSAkLBRzIsUp/2d5Rd2zgEsfkFVeXsn8WYYZkinAQVVy6A7B3LaEJW0xb/x88Di67fedwx0Q+FlZtwcmT3Dcaa11JveyHRr3dm+zGSZP6CXeXNJ8nrTZ7W1YRTysD6w7o7Lp8h1Rwq4f4o8j+QUfY0vje+zJZsxHPmQNt3ykeKh99hgn6dbiz6/EHqmbHjSAu1M4SqEDfqIKThHYenamAZmcQ4XAOo6mdQ6+77VgpV1lC1/k52IiUoJjkGlQrnLCvutiI7KN+sgK8c2+2KCJrPRCvVV+BkStvP5jWWqzytpKQ+nHzhL448OrIA9gdJC39C8eDrXeRnI7t4FqlkXGoMlZAV9UMcrQHRxOMi8tOyTzi9oyBFDTSsQ+LJqer0tz1Ft9gek6vzg50SpVAFQdLERv8R1YqMaeI+xsvTAEW9MRgvRMkzLuzRT2guw3jD+Fjip37xgK5QI0R+CsOAmQPoTZizzcIyAUAuCJFCgq/gD/CibLxoymiVUI1an9Snt3KpNRoWdvWIne33V0pv8PHg9yW2JuLOqQGilLCsK/Q3oQr3upEMXxXGjCL7WUizvRZGFEEV+VplYt7v4tKZMj5pk3vdeM0MJ5XZg7PvUsRzycxcnrT3Knoc3qM+ttqZfTsb8d6U/pQifq7GuahFOHrvroqgJLj+/81Yy1pZFkjfJgY0XklzAnA6CFq/YT0gxbV+TH5IS+WaYOUzK36S8s5qqMwhngv4IzE3ctXXqnhIZXNznyVBqbYa/Gx2bCjcEj2n5RyGYRS/+MculgLBznQ9MkG2D7QP3Mq/nwHXKMIaLS8VK8hG3d0rAjlvnauXShNrJxtkj4qkwnxD4LrEjk1ue+PLcbLqYWwAr8n0s+41jrsIPVyyK9vFaEZrA9KaBxkJyiqx50GZNn7ckx+mkI18gH52iyVPtU8FKMXjugCl6mPLiHYiDQd+G63LudmOKys9itVnBDBNMP2b/I7+bIVRlheGaZWr6MATKl86B3y+0kuOrLRMyWcdibc2iQkZm+8f7dTUwbKbBJsKOFY73/8nlL/JiYpjz6nUIk+IqSjaFyK6XFlCcukWpWHpDJnSvbEzey7qHyCqJ+I+on8iP8GOtempQaS0/4kZGSwlrE6xOj6EwGpfjbDZKHkP/2RAdNYPQq3z7bdVJMJNnFMz6e37mzMpCBihwPdSFTRE3SCY66wvTgJzGCUyhHbSi5i1azzOXd8uHCSpT/6L1o6VU0pjoR8Kaa4wCWHGf7P/WEd+avyp02Jnu1cmpW0+Gq+vK9h0tdb2IClM/eNfdouQP+ep8MJUjraDRICmAJQY5obS71vniOo+reaFy0zRgB', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': 'CAQS1QgKEAgSGAI4AUIIdGhpbmtpbmcSDN6TfU6NDM971lEbzxoMvRUA1J9ox3fJQYT9IjArCQQGHBP4pRHPavXzRlbMbaYHC57Yj+Gbxgr0helvd2OIL/o6Rbt4PFA3FaIFUlgq8gc7KQI9FtGnvSAkLBRzIsUp/2d5Rd2zgEsfkFVeXsn8WYYZkinAQVVy6A7B3LaEJW0xb/x88Di67fedwx0Q+FlZtwcmT3Dcaa11JveyHRr3dm+zGSZP6CXeXNJ8nrTZ7W1YRTysD6w7o7Lp8h1Rwq4f4o8j+QUfY0vje+zJZsxHPmQNt3ykeKh99hgn6dbiz6/EHqmbHjSAu1M4SqEDfqIKThHYenamAZmcQ4XAOo6mdQ6+77VgpV1lC1/k52IiUoJjkGlQrnLCvutiI7KN+sgK8c2+2KCJrPRCvVV+BkStvP5jWWqzytpKQ+nHzhL448OrIA9gdJC39C8eDrXeRnI7t4FqlkXGoMlZAV9UMcrQHRxOMi8tOyTzi9oyBFDTSsQ+LJqer0tz1Ft9gek6vzg50SpVAFQdLERv8R1YqMaeI+xsvTAEW9MRgvRMkzLuzRT2guw3jD+Fjip37xgK5QI0R+CsOAmQPoTZizzcIyAUAuCJFCgq/gD/CibLxoymiVUI1an9Snt3KpNRoWdvWIne33V0pv8PHg9yW2JuLOqQGilLCsK/Q3oQr3upEMXxXGjCL7WUizvRZGFEEV+VplYt7v4tKZMj5pk3vdeM0MJ5XZg7PvUsRzycxcnrT3Knoc3qM+ttqZfTsb8d6U/pQifq7GuahFOHrvroqgJLj+/81Yy1pZFkjfJgY0XklzAnA6CFq/YT0gxbV+TH5IS+WaYOUzK36S8s5qqMwhngv4IzE3ctXXqnhIZXNznyVBqbYa/Gx2bCjcEj2n5RyGYRS/+MculgLBznQ9MkG2D7QP3Mq/nwHXKMIaLS8VK8hG3d0rAjlvnauXShNrJxtkj4qkwnxD4LrEjk1ue+PLcbLqYWwAr8n0s+41jrsIPVyyK9vFaEZrA9KaBxkJyiqx50GZNn7ckx+mkI18gH52iyVPtU8FKMXjugCl6mPLiHYiDQd+G63LudmOKys9itVnBDBNMP2b/I7+bIVRlheGaZWr6MATKl86B3y+0kuOrLRMyWcdibc2iQkZm+8f7dTUwbKbBJsKOFY73/8nlL/JiYpjz6nUIk+IqSjaFyK6XFlCcukWpWHpDJnSvbEzey7qHyCqJ+I+on8iP8GOtempQaS0/4kZGSwlrE6xOj6EwGpfjbDZKHkP/2RAdNYPQq3z7bdVJMJNnFMz6e37mzMpCBihwPdSFTRE3SCY66wvTgJzGCUyhHbSi5i1azzOXd8uHCSpT/6L1o6VU0pjoR8Kaa4wCWHGf7P/WEd+avyp02Jnu1cmpW0+Gq+vK9h0tdb2IClM/eNfdouQP+ep8MJUjraDRICmAJQY5obS71vniOo+reaFy0zRgB', 'thinking': '', 'type': 'thinking'}, {'signature': 'CAQS/REKEQgSGAI4AUIJbmFycmF0aW9uEgwFh3AVJZP3s8y1Hq0aDG76uhHONaScXAGShiIwGgjLXHUx1yZrkLPljjzTOQycpLJiKVwXcxm/EzKJm1s8M5WxuREWEldXcoaN0/msKpkRMT+eLb5ih9rAHULTomUNsUwJeu0jrJe4GLazy7sP5KtjEOEBKQsXUfoQ7fDkZOQUHZi9zzQN4hFNmYJUf3OVqf9TQNdC1+m//HAZPfWmAy6HtDvm7kgBJkCEoiFnm7tn/PX1hXGPRgWc6BTXUMr2WA8aKyqggRUbMH2+JYv5iWZddCc1up1Nbr3sF7WPcot9ZBhyHQXr692zeJk6SJgygIVrASbMly2bBxTWJB623gVgzpCmVSLZFpkKXgPcp8hGyDKOvF6SiQSHqGRxQofr7Vs1aPhfZixROJGD+MlrkggVAnGMyYIDUZpavtCeiU1JmBSz0084bXPtT/tnpsKOnSPYZQo3B0BXKbqA/WsKng8/V3Z8Uuajo6IVZ2hgA1WDduqQOQkExGU6pFuLhebIjuWxSNI/DffvR//LNqCfvdnf0hvoPtDxfx/SawIx4/spq9xbwFzHtLgoHg1F2wFw7clPDlg1PyD/v2yJG3V9T8GL6jGPE6rhfil/u4HNvf7BW0dQzCTTXcqZy4nByy0+p+S7ZxfMl4Kpxa2gOhhSNjfpfuX0QpL4kME8J1nliFN1d8KqEPuDI18BQHUhD/UfY29oA0x510FjM/BsLZ4n5sppkoIi7CFoQq2aAKVNfC1KilhIpRD+1dyDtZQklN8gZpOESHw6ML1TtU0yfAcbmqoxJ6hhjzwH6CMsTQEEy8MbRBM+QKKkIRdRCPHGFW2LkuR50+J0pF/tr6pqVvJeozfiMnrEilB27TZP4nKTJG8rd//vCWen0y7CA/8dBJ9gdp5tx7NVA45k1gdcxER1gYouNX3n1vG3/B1F4+93wXW9Mqo6Us59TQmrb9Nqa7pSQNSrH06w1GxyBAlkFfqAlafk16aMpq416TJYpGy43WCUiCcLWlhiWgz2sgOLAXP9a5weWAKRC8J6jkcUkDeXnW+HFSiPM6+9Bo6kVhLUhN5rc4mHZOZpF7ptPpsQN4XCqLPsqpRH/8o5XpyC6ZneTeF2ExtjhwZVjXDwMbIzVYIbw1y2PPGw8dC7pc4sIVSnI4oQAH0v650ghfhmMevWW4h4Pylbw/DG4fdeT3+8z0f8MOSTtfipx05/QttHlAvODRxa5yDCvOz6n3f1BO0N/4MbGyOM27qW4x8mBVoryUZWfsmhfi0/GfNvB8+ylTGbYNX27OcEF5WZtNqbWEy7V5GbmZUSxspcg7FBZ3j3/3L7muvZXoZi1f5erq4y3lSH+oF7qPFnvieyLOCwubcQy+oyowj4cD0idRecnp+s+52D7+mzF1gpW+f+cJasoxigbxkOloS4yeiKvgM4nWSpGEj12RPx5o80EmziXN9t4zJzW1htA5hXJJeFympMYtyCUCevRWVmrRYktQ7UnCa6tL/AVPi1ni5XCXHfLOuqfK5KLYxjwVtdhhfmCLvpaKVNCEOCf4nNGHqD98wUb0ejWNwDYBnJGkBRw9RVspfwNdoWoVcn2qv8ywGUp7yc/sk2LpI6VziRyvWqbGNG1ZJqVVutRc46+sOE4VSeS2/CTNKNa6NMCf/hxxaUVsYfKdP+S1Lc4ianKp0sUugPpmtoydC0CP2RwjnHLcnzxCnvqxlLQWXMNPTsu2yBcHlWJLtcmdg/McLagy7l5kG6sN7ZxJLD/kAx8E6uqohP+K/jMSrYuQJnhr4tf4biWFY3Jzf/KpAYyVSq+pbfFKXMbL9nHEoZQT15Wyabd6DMAq3QZOthM5pUzdNqUXkcrI1PwjASAg4dVU/2o+98mTXnyhP7VlEkTnddpwyJF+YCCc01pqa6ZX99pnR+YOpIrb5DtPcKq0t5cFCDyQxN1lUuqZcYujvX/GC7+6IpRTz/NkEY/5cntOfZJyd6SkUx/JR5AJIRPCNeib0rcWnnFn0XK8s22x40wLjEtufXDO9+yraf4kHxlBI3SB0meMjepX50CJhAx7NekkRFnwoecLfqIyrjXrgAZsTMPiX94snjdrzisAXtBKanulilSxOfW2HSmfnk0L2GXHJJ3S+vCbgREml9dekfmHhmwEYtv3kfhth7ERIwVT8j69OtIBCmeTIJuA7o73PXc1LJ2whuZK7FZe6NTOs61MP7JVlIc6tbhtOBk3NXU8pBPOCY6Q55d63FtpUU/KCbQ0K2WQ9o5jNGwNNJ6Cw5FDCt+x5YJeP1d2QzDSiq+cSZqwqCZVcNoAftGGzgrRZ4vkpbP0xQZHCtWsUwHVTjrY4NfRDjHdVPRn8J9Xtooc/hIWkqzFaczYTlapu2RCJqe8aEo3jzWZCEJ7AiBzBYraYDgOfeiQyeJUsbbXHdGKiiw22Bdp4M+Yz671MZ0ie9EWRks0Q2DHGUTne9S4tAAJPGbUf4xtCMoJ40Q4QW05QLSZy3wNFAUFYmXE4ECDFB8+IEeNFFF/tgAnfh8GvFh/1xY+LE+ozMminjSRwhq09zQAEkNFyu0IKgvDkyOI+iccF7doWLTUasPxLH1xGPBSKkeWCnSoX/4C2c9du66BbRXamHqae+VCiS6BN953iYKOu8rMkneW+TFjV0CzAf8PNG9LBayUgY5Uw9x0Sap6zI4PpaZKH4d9ktkFU+91yBbN5SRtdd8/EQatJXmBNfw7kRrll+LjwZweWLEb0jT1RpGuDqHLdLTMMgowSczrp2zCsJdQH/seaYrpwkCFR8dRjM7JRUkVa1A0SvdZAX75vuBvvLBzN2c+Rbt5oqy93lqIBIjKb7w2UkRTb4pBWcNKNPUgt3az/PxQxEasaltdmuyvsXYbur3VPNn8JzN/6J5N+QCnz571TccapCmkPvFE+gayXU+UF1VKYyFcUvlev7lsQlmjqzK2QA8X7Q3TzFapqhvJKlt7dzBHraqZBgPgb9N4oKNayi8FZT71+kaYhIhFrESKYRHfHkj5n3kfhgLy+x+jLDbKxMggkgHnJz9RuEHZXBWtkYAQ==', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier')\n" + } + }, + { + "key": "exception.escaped", + "value": { + "stringValue": "False" + } + } + ] + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "0ff4846461350af9", + "parentSpanId": "04ffc0db9ce0f358", + "name": "skeptic", + "kind": 1, + "startTimeUnixNano": "1790968023779922944", + "endTimeUnixNano": "1790968030845179136", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "skeptic" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langgraph" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "skeptic" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:skeptic\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"skeptic\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:2" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + } + ], + "events": [ + { + "timeUnixNano": "1790968030909679000", + "name": "exception", + "attributes": [ + { + "key": "exception.type", + "value": { + "stringValue": "Exception" + } + }, + { + "key": "exception.message", + "value": { + "stringValue": "ParentCommand(Command(graph='skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': 'CAQS1QgKEAgSGAI4AUIIdGhpbmtpbmcSDN6TfU6NDM971lEbzxoMvRUA1J9ox3fJQYT9IjArCQQGHBP4pRHPavXzRlbMbaYHC57Yj+Gbxgr0helvd2OIL/o6Rbt4PFA3FaIFUlgq8gc7KQI9FtGnvSAkLBRzIsUp/2d5Rd2zgEsfkFVeXsn8WYYZkinAQVVy6A7B3LaEJW0xb/x88Di67fedwx0Q+FlZtwcmT3Dcaa11JveyHRr3dm+zGSZP6CXeXNJ8nrTZ7W1YRTysD6w7o7Lp8h1Rwq4f4o8j+QUfY0vje+zJZsxHPmQNt3ykeKh99hgn6dbiz6/EHqmbHjSAu1M4SqEDfqIKThHYenamAZmcQ4XAOo6mdQ6+77VgpV1lC1/k52IiUoJjkGlQrnLCvutiI7KN+sgK8c2+2KCJrPRCvVV+BkStvP5jWWqzytpKQ+nHzhL448OrIA9gdJC39C8eDrXeRnI7t4FqlkXGoMlZAV9UMcrQHRxOMi8tOyTzi9oyBFDTSsQ+LJqer0tz1Ft9gek6vzg50SpVAFQdLERv8R1YqMaeI+xsvTAEW9MRgvRMkzLuzRT2guw3jD+Fjip37xgK5QI0R+CsOAmQPoTZizzcIyAUAuCJFCgq/gD/CibLxoymiVUI1an9Snt3KpNRoWdvWIne33V0pv8PHg9yW2JuLOqQGilLCsK/Q3oQr3upEMXxXGjCL7WUizvRZGFEEV+VplYt7v4tKZMj5pk3vdeM0MJ5XZg7PvUsRzycxcnrT3Knoc3qM+ttqZfTsb8d6U/pQifq7GuahFOHrvroqgJLj+/81Yy1pZFkjfJgY0XklzAnA6CFq/YT0gxbV+TH5IS+WaYOUzK36S8s5qqMwhngv4IzE3ctXXqnhIZXNznyVBqbYa/Gx2bCjcEj2n5RyGYRS/+MculgLBznQ9MkG2D7QP3Mq/nwHXKMIaLS8VK8hG3d0rAjlvnauXShNrJxtkj4qkwnxD4LrEjk1ue+PLcbLqYWwAr8n0s+41jrsIPVyyK9vFaEZrA9KaBxkJyiqx50GZNn7ckx+mkI18gH52iyVPtU8FKMXjugCl6mPLiHYiDQd+G63LudmOKys9itVnBDBNMP2b/I7+bIVRlheGaZWr6MATKl86B3y+0kuOrLRMyWcdibc2iQkZm+8f7dTUwbKbBJsKOFY73/8nlL/JiYpjz6nUIk+IqSjaFyK6XFlCcukWpWHpDJnSvbEzey7qHyCqJ+I+on8iP8GOtempQaS0/4kZGSwlrE6xOj6EwGpfjbDZKHkP/2RAdNYPQq3z7bdVJMJNnFMz6e37mzMpCBihwPdSFTRE3SCY66wvTgJzGCUyhHbSi5i1azzOXd8uHCSpT/6L1o6VU0pjoR8Kaa4wCWHGf7P/WEd+avyp02Jnu1cmpW0+Gq+vK9h0tdb2IClM/eNfdouQP+ep8MJUjraDRICmAJQY5obS71vniOo+reaFy0zRgB', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': 'CAQS1QgKEAgSGAI4AUIIdGhpbmtpbmcSDN6TfU6NDM971lEbzxoMvRUA1J9ox3fJQYT9IjArCQQGHBP4pRHPavXzRlbMbaYHC57Yj+Gbxgr0helvd2OIL/o6Rbt4PFA3FaIFUlgq8gc7KQI9FtGnvSAkLBRzIsUp/2d5Rd2zgEsfkFVeXsn8WYYZkinAQVVy6A7B3LaEJW0xb/x88Di67fedwx0Q+FlZtwcmT3Dcaa11JveyHRr3dm+zGSZP6CXeXNJ8nrTZ7W1YRTysD6w7o7Lp8h1Rwq4f4o8j+QUfY0vje+zJZsxHPmQNt3ykeKh99hgn6dbiz6/EHqmbHjSAu1M4SqEDfqIKThHYenamAZmcQ4XAOo6mdQ6+77VgpV1lC1/k52IiUoJjkGlQrnLCvutiI7KN+sgK8c2+2KCJrPRCvVV+BkStvP5jWWqzytpKQ+nHzhL448OrIA9gdJC39C8eDrXeRnI7t4FqlkXGoMlZAV9UMcrQHRxOMi8tOyTzi9oyBFDTSsQ+LJqer0tz1Ft9gek6vzg50SpVAFQdLERv8R1YqMaeI+xsvTAEW9MRgvRMkzLuzRT2guw3jD+Fjip37xgK5QI0R+CsOAmQPoTZizzcIyAUAuCJFCgq/gD/CibLxoymiVUI1an9Snt3KpNRoWdvWIne33V0pv8PHg9yW2JuLOqQGilLCsK/Q3oQr3upEMXxXGjCL7WUizvRZGFEEV+VplYt7v4tKZMj5pk3vdeM0MJ5XZg7PvUsRzycxcnrT3Knoc3qM+ttqZfTsb8d6U/pQifq7GuahFOHrvroqgJLj+/81Yy1pZFkjfJgY0XklzAnA6CFq/YT0gxbV+TH5IS+WaYOUzK36S8s5qqMwhngv4IzE3ctXXqnhIZXNznyVBqbYa/Gx2bCjcEj2n5RyGYRS/+MculgLBznQ9MkG2D7QP3Mq/nwHXKMIaLS8VK8hG3d0rAjlvnauXShNrJxtkj4qkwnxD4LrEjk1ue+PLcbLqYWwAr8n0s+41jrsIPVyyK9vFaEZrA9KaBxkJyiqx50GZNn7ckx+mkI18gH52iyVPtU8FKMXjugCl6mPLiHYiDQd+G63LudmOKys9itVnBDBNMP2b/I7+bIVRlheGaZWr6MATKl86B3y+0kuOrLRMyWcdibc2iQkZm+8f7dTUwbKbBJsKOFY73/8nlL/JiYpjz6nUIk+IqSjaFyK6XFlCcukWpWHpDJnSvbEzey7qHyCqJ+I+on8iP8GOtempQaS0/4kZGSwlrE6xOj6EwGpfjbDZKHkP/2RAdNYPQq3z7bdVJMJNnFMz6e37mzMpCBihwPdSFTRE3SCY66wvTgJzGCUyhHbSi5i1azzOXd8uHCSpT/6L1o6VU0pjoR8Kaa4wCWHGf7P/WEd+avyp02Jnu1cmpW0+Gq+vK9h0tdb2IClM/eNfdouQP+ep8MJUjraDRICmAJQY5obS71vniOo+reaFy0zRgB', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier')" + } + }, + { + "key": "exception.stacktrace", + "value": { + "stringValue": "Exception: ParentCommand(Command(graph='skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': 'CAQS1QgKEAgSGAI4AUIIdGhpbmtpbmcSDN6TfU6NDM971lEbzxoMvRUA1J9ox3fJQYT9IjArCQQGHBP4pRHPavXzRlbMbaYHC57Yj+Gbxgr0helvd2OIL/o6Rbt4PFA3FaIFUlgq8gc7KQI9FtGnvSAkLBRzIsUp/2d5Rd2zgEsfkFVeXsn8WYYZkinAQVVy6A7B3LaEJW0xb/x88Di67fedwx0Q+FlZtwcmT3Dcaa11JveyHRr3dm+zGSZP6CXeXNJ8nrTZ7W1YRTysD6w7o7Lp8h1Rwq4f4o8j+QUfY0vje+zJZsxHPmQNt3ykeKh99hgn6dbiz6/EHqmbHjSAu1M4SqEDfqIKThHYenamAZmcQ4XAOo6mdQ6+77VgpV1lC1/k52IiUoJjkGlQrnLCvutiI7KN+sgK8c2+2KCJrPRCvVV+BkStvP5jWWqzytpKQ+nHzhL448OrIA9gdJC39C8eDrXeRnI7t4FqlkXGoMlZAV9UMcrQHRxOMi8tOyTzi9oyBFDTSsQ+LJqer0tz1Ft9gek6vzg50SpVAFQdLERv8R1YqMaeI+xsvTAEW9MRgvRMkzLuzRT2guw3jD+Fjip37xgK5QI0R+CsOAmQPoTZizzcIyAUAuCJFCgq/gD/CibLxoymiVUI1an9Snt3KpNRoWdvWIne33V0pv8PHg9yW2JuLOqQGilLCsK/Q3oQr3upEMXxXGjCL7WUizvRZGFEEV+VplYt7v4tKZMj5pk3vdeM0MJ5XZg7PvUsRzycxcnrT3Knoc3qM+ttqZfTsb8d6U/pQifq7GuahFOHrvroqgJLj+/81Yy1pZFkjfJgY0XklzAnA6CFq/YT0gxbV+TH5IS+WaYOUzK36S8s5qqMwhngv4IzE3ctXXqnhIZXNznyVBqbYa/Gx2bCjcEj2n5RyGYRS/+MculgLBznQ9MkG2D7QP3Mq/nwHXKMIaLS8VK8hG3d0rAjlvnauXShNrJxtkj4qkwnxD4LrEjk1ue+PLcbLqYWwAr8n0s+41jrsIPVyyK9vFaEZrA9KaBxkJyiqx50GZNn7ckx+mkI18gH52iyVPtU8FKMXjugCl6mPLiHYiDQd+G63LudmOKys9itVnBDBNMP2b/I7+bIVRlheGaZWr6MATKl86B3y+0kuOrLRMyWcdibc2iQkZm+8f7dTUwbKbBJsKOFY73/8nlL/JiYpjz6nUIk+IqSjaFyK6XFlCcukWpWHpDJnSvbEzey7qHyCqJ+I+on8iP8GOtempQaS0/4kZGSwlrE6xOj6EwGpfjbDZKHkP/2RAdNYPQq3z7bdVJMJNnFMz6e37mzMpCBihwPdSFTRE3SCY66wvTgJzGCUyhHbSi5i1azzOXd8uHCSpT/6L1o6VU0pjoR8Kaa4wCWHGf7P/WEd+avyp02Jnu1cmpW0+Gq+vK9h0tdb2IClM/eNfdouQP+ep8MJUjraDRICmAJQY5obS71vniOo+reaFy0zRgB', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='skeptic:3dfc4328-0d19-e1ea-bcda-3d3d36d7cda8', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH')], 'active_agent': 'verifier'}, goto='verifier')\n" + } + }, + { + "key": "exception.escaped", + "value": { + "stringValue": "False" + } + } + ] + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "8e84b2f5d3c9d733", + "parentSpanId": "4862a8dc9e239ae2", + "name": "tools", + "kind": 1, + "startTimeUnixNano": "1790968032471715072", + "endTimeUnixNano": "1790968032476058880", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__pregel_push\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_push\",0,false]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9|tools:74348550-0598-498b-1732-6675e778549b" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "verifier" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:2" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "eyJpbnB1dCI6W3sibmFtZSI6InRyYW5zZmVyX3RvX3JlZF90ZWFtIiwiYXJncyI6e30sImlkIjoidG9vbHVfMDFYRUF1aFFIQ0JkeUN3dHltWndGZkRpIiwidHlwZSI6InRvb2xfY2FsbCJ9XX0=" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "e30=" + } + } + ], + "events": [ + { + "timeUnixNano": "1790968032542335000", + "name": "exception", + "attributes": [ + { + "key": "exception.type", + "value": { + "stringValue": "Exception" + } + }, + { + "key": "exception.message", + "value": { + "stringValue": "ParentCommand(Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team')" + } + }, + { + "key": "exception.stacktrace", + "value": { + "stringValue": "Exception: ParentCommand(Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team')\n" + } + }, + { + "key": "exception.escaped", + "value": { + "stringValue": "False" + } + } + ] + } + ], + "status": { + "code": 2 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "4127f167d1d653d6", + "parentSpanId": "8e84b2f5d3c9d733", + "name": "FilesystemMiddleware.wrap_tool_call", + "kind": 1, + "startTimeUnixNano": "1790968032472590080", + "endTimeUnixNano": "1790968032473856000", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "FilesystemMiddleware.wrap_tool_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__pregel_push\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_push\",0,false]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9|tools:74348550-0598-498b-1732-6675e778549b" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "verifier" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "b2daa1c17359fac2", + "parentSpanId": "4127f167d1d653d6", + "name": "transfer_to_red_team", + "kind": 1, + "startTimeUnixNano": "1790968032472979968", + "endTimeUnixNano": "1790968032473444864", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "tool" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "transfer_to_red_team" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "execute_tool" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "gen_ai.tool.name", + "value": { + "stringValue": "transfer_to_red_team" + } + }, + { + "key": "gen_ai.tool.call.id", + "value": { + "stringValue": "toolu_01XEAuhQHCBdyCwtymZwFfDi" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__pregel_push\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_push\",0,false]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9|tools:74348550-0598-498b-1732-6675e778549b" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "verifier" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9" + } + }, + { + "key": "langsmith.metadata.__handoff_destination", + "value": { + "stringValue": "red_team" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "seq:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "38a909e757fa3574", + "parentSpanId": "4862a8dc9e239ae2", + "name": "model", + "kind": 1, + "startTimeUnixNano": "1790968030846537984", + "endTimeUnixNano": "1790968032470715136", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9|model:6b48cacc-ef10-0459-49d7-052bc435753c" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "verifier" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "eyJvdXRwdXQiOlt7ImdyYXBoIjpudWxsLCJ1cGRhdGUiOnsibWVzc2FnZXMiOlt7ImNvbnRlbnQiOlt7InNpZ25hdHVyZSI6IkNBUVM5Z1VLRUFnU0dBSTRBVUlJZEdocGJtdHBibWNTREdGeUoxTVhvWStBaTZOa2J4b01SZDJUclVmVVU3V3JQcEEySWpEZ3k4ZFVwbGNaS2M3RG5Kd05MVEJmSDVVTlIrbkduYWtTUFFpYThVVkl6cmprT25KMmZMcldVc0Eyb0VPOHlSc3Frd1hra0RDc3loQjk3ZHdqNTdSTXQ5MVh6Z1doTDlsdU5FR085MnlXMHJORkdvTVNVVk94UElyRmM1Ump5cmhLRWMzKzFSbnB4Q2t5bHErTE5sUTVORnhMbjZ2MmNGNUR6cXB2QkhOUjdYQWlnK3VySklVM2dYeWRDa2FHWlpEZXRKdFFPVU9YZ1ppOXo5MTAwTnBkQUVrWERvMklDSENHVEdwVmMwSi9wYlh4V1JCeGI2QjEvR2wwWWpuNjhWNkhsZXNIN0lvQzdHUi8zSHdSdTlOU0RCRzR0dGZRakVXY2crUGVBZWE0Um43anp4K1RtOUg3TDFqb1RLVmdEYlFnNWlLTUxmanZQcWxua3NDTHRYT3Q4alNJUzVPWUxON2EvN1RYNi93NWQzNHZudzh2UERtVTFVWWkwUTcycVVXaFVhMnZ3OE9YTnBjS0w3QnAwbE5mQlM4cnZIWSt2Qlk4L2hhQW9UTDN3dkxGVTFmVCs0ei92QTNCY3NpZ1pEWWxmSmVEWWN4WG1SdXF4enhFR3BYQ1JlOXMxSFd0SUQrNDFwSHU2bHBaSGtYYWdocGM2VFpITHhOd2NWaFRiNmZNUTdRbysyTDZQdmtsaDFtMzJwZW9keGVnMllpUGhkcGwzdy94a09FdTUvSkVGN1pCeHBkVUwrdTN3a081cFVsc3FmZ1g3dWh6djdIQzJXcFNXVmltcndpUXdRT1V4MCtKUHJMdHcrbFlmcTdJM2pydW8wR1cwZ3VXdm51ZjdKTTNZTGo4NHErSmdIb21uU1Nabm5abXJMMFVhUnZyVnlMbzg3N0YzOWNjTFM3WG9abm51aThKNFA1OFpUbWlMa0VKZUdjeDFJdWFnMmUzMzMzOU83WWV3LzU5dExiUXRJR2g5VldNd0hCbkZ4MzlTOC80TEVGcks1SGxkUFFoT3Jsb3lUdGtSczY2aVFSS3R4TUtTMFZJNlFUS1pEQWJzN2E3SDF5QnYrbUppOVhnNHVLbXlVNnFubjd6RUtqalkyYklsQ3dleng0TExHUDVIRDNacjZmWnNtZEcxVUh6RHNCdllHMm9DSTBvcUVLTSt2YWxzVDZoVThNUmpiUUJEL0pKOEpKTi9pQkdsaEJBVUhvMFVtaGh0UjJldVRWcFpXbE1uaG1wWEFkS0RYU2ZQZGFQb2hnQiIsInRoaW5raW5nIjoiIiwidHlwZSI6InRoaW5raW5nIn0seyJpZCI6InRvb2x1XzAxWEVBdWhRSENCZHlDd3R5bVp3RmZEaSIsImNhbGxlciI6eyJ0eXBlIjoiZGlyZWN0In0sImlucHV0Ijp7fSwibmFtZSI6InRyYW5zZmVyX3RvX3JlZF90ZWFtIiwidHlwZSI6InRvb2xfdXNlIiwidG9vbHNldF9uYW1lIjpudWxsfV0sImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnsiaWQiOiJtc2dfMDExQ2Zkd0FzYWJEcXVlZ0hpNllVcENuIiwiY29udGFpbmVyIjpudWxsLCJkaWFnbm9zdGljcyI6bnVsbCwibW9kZWwiOiJjbGF1ZGUtc29ubmV0Iiwic3RvcF9kZXRhaWxzIjpudWxsLCJzdG9wX3JlYXNvbiI6InRvb2xfdXNlIiwic3RvcF9zZXF1ZW5jZSI6bnVsbCwidXNhZ2UiOnsiY2FjaGVfY3JlYXRpb24iOnsiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MH0sImNhY2hlX2NyZWF0aW9uX2lucHV0X3Rva2VucyI6MCwiY2FjaGVfcmVhZF9pbnB1dF90b2tlbnMiOjAsImluZmVyZW5jZV9nZW8iOiJnbG9iYWwiLCJpbnB1dF90b2tlbnMiOjc1MDksIm91dHB1dF90b2tlbnMiOjg4LCJvdXRwdXRfdG9rZW5zX2RldGFpbHMiOnsidGhpbmtpbmdfdG9rZW5zIjo1NX0sInNlcnZlcl90b29sX3VzZSI6bnVsbCwic2VydmljZV90aWVyIjoic3RhbmRhcmQifSwibW9kZWxfbmFtZSI6ImNsYXVkZS1zb25uZXQiLCJtb2RlbF9wcm92aWRlciI6ImFudGhyb3BpYyJ9LCJ0eXBlIjoiYWkiLCJuYW1lIjoidmVyaWZpZXIiLCJpZCI6ImxjX3J1bi0tMDFhMGZlMDMtNjY4Mi03ZDIxLThjMTUtZmZiY2U5NDIyYzlmLTAiLCJ0b29sX2NhbGxzIjpbeyJuYW1lIjoidHJhbnNmZXJfdG9fcmVkX3RlYW0iLCJhcmdzIjp7fSwiaWQiOiJ0b29sdV8wMVhFQXVoUUhDQmR5Q3d0eW1ad0ZmRGkiLCJ0eXBlIjoidG9vbF9jYWxsIn1dLCJpbnZhbGlkX3Rvb2xfY2FsbHMiOltdLCJ1c2FnZV9tZXRhZGF0YSI6eyJpbnB1dF90b2tlbnMiOjc1MDksIm91dHB1dF90b2tlbnMiOjg4LCJ0b3RhbF90b2tlbnMiOjc1OTcsImlucHV0X3Rva2VuX2RldGFpbHMiOnsiY2FjaGVfcmVhZCI6MCwiY2FjaGVfY3JlYXRpb24iOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjB9LCJvdXRwdXRfdG9rZW5fZGV0YWlscyI6eyJyZWFzb25pbmciOjU1fX19XX0sInJlc3VtZSI6bnVsbCwiZ290byI6W119XX0=" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "0676be444516237c", + "parentSpanId": "38a909e757fa3574", + "name": "FilesystemMiddleware.wrap_model_call", + "kind": 1, + "startTimeUnixNano": "1790968030846874880", + "endTimeUnixNano": "1790968032470281984", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "FilesystemMiddleware.wrap_model_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9|model:6b48cacc-ef10-0459-49d7-052bc435753c" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "verifier" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "5846c65e1a0fba02", + "parentSpanId": "0676be444516237c", + "name": "UnsupportedContentMiddleware.wrap_model_call", + "kind": 1, + "startTimeUnixNano": "1790968030847229952", + "endTimeUnixNano": "1790968032470125056", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "UnsupportedContentMiddleware.wrap_model_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9|model:6b48cacc-ef10-0459-49d7-052bc435753c" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "verifier" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "7d9bd24669f22c02", + "parentSpanId": "5846c65e1a0fba02", + "name": "ChatAnthropic", + "kind": 1, + "startTimeUnixNano": "1790968030850436096", + "endTimeUnixNano": "1790968032469747968", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chat" + } + }, + { + "key": "gen_ai.serialized.name", + "value": { + "stringValue": "ChatAnthropic" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "llm" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "ChatAnthropic" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "anthropic" + } + }, + { + "key": "gen_ai.request.model", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "gen_ai.tool.definitions", + "value": { + "stringValue": "[{\"name\":\"ls\",\"input_schema\":{\"properties\":{\"path\":{\"description\":\"Absolute path to the directory to list. Must be absolute, not relative.\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"description\":\"Lists all files in a directory.\\n\\nThis is useful for exploring the filesystem and finding the right file to read or edit.\\nYou should almost ALWAYS use this tool before using the read_file or edit_file tools.\"},{\"name\":\"read_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path to the file to read. Must be absolute, not relative.\",\"type\":\"string\"},\"offset\":{\"default\":0,\"description\":\"Line number to start reading from (0-indexed). Use for pagination of large files.\",\"type\":\"integer\"},\"limit\":{\"default\":100,\"description\":\"Maximum number of lines to read. Use for pagination of large files.\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"description\":\"Reads a file from the filesystem. Assume any path the user provides is valid; reading a missing file returns an error.\\n\\nUsage:\\n- By default, it reads up to 100 lines starting from the beginning of the file. Use `offset`/`limit` to page through large files instead of reading them whole.\\n- A status header, `@@ field | field | ... @@`, sits above the file content, and every line after it is verbatim file content. When content is truncated, there may be an explanation before the header. Never include the header when editing.\\n- Speculatively batch multiple `read_file` calls in one response when several files may be useful.\\n- An empty file returns a system-reminder warning in place of contents.\\n- Large tool results may be offloaded to a file; the tool message gives the path. Read that path here, paging with `offset`/`limit`.\\n- Images (`.png`, `.jpg`, etc.), audio, video, and PDFs return multimodal content blocks (https://docs.langchain.com/oss/python/langchain/messages#multimodal).\\n- For images and PDFs, pagination via `offset`/`limit` is text-only - supply `file_path` only\\n- Always read a file before editing it.\"},{\"name\":\"glob\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Glob pattern to match files (e.g., '*.py', '**/*.py', '/subdir/**/*.md'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path; a leading '/' anchors to the search root ('/*.py' matches only top-level files). Leading-dot names are excluded unless the pattern segment starts with '.', so prefer the bare form '*.py' over '**/*.py' -- '**' will not descend into dot-directories like '.github'.\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Base directory to search from. Defaults to the backend's default root.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Find files matching a glob pattern, returning absolute paths.\\n\\nSupports `*` (any characters within a path segment), `**` (any directories), `?` (single character), `[abc]` (one character from a set), and `{a,b}` (alternatives), e.g. `*.py`, `src/**/*.py`, `*.{yml,yaml}`.\\n\\nA pattern without `/` matches the file name at any depth under the search root (`*.py` matches `src/app/main.py`). A pattern containing `/` matches the search-root-relative path (`src/**/*.py`). A leading `/` anchors to the search root (`/*.py` matches only top-level Python files).\\n\\nLeading-dot names are only matched when the pattern segment itself starts with `.` (use `.env`, or `.github/**/*.yml`). Because `**` will not descend into dot-directories, the bare form `*.yml` is *broader* than `**/*.yml` and is usually what you want.\"},{\"name\":\"grep\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Text pattern to search for (literal string, not regex).\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Directory to search in. Defaults to current working directory.\"},\"glob\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Glob pattern (NOT regex) limiting which files are searched (e.g. '*.py', '*.ts'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path (e.g. 'src/**/*.py'). This is an in-tool file filter, not a call to the separate glob tool. Brace expansion (e.g. '*.{ts,tsx}') is not supported on all backends; run a separate search per extension for reliable results.\"},\"output_mode\":{\"default\":\"files_with_matches\",\"description\":\"Shape of the returned text. 'files_with_matches' (default): newline-separated matching file paths. 'content': matching lines grouped by file under a ':' header, each line indented and formatted ': ' (only the matched line, no surrounding context). 'count': one ': ' line per file.\",\"enum\":[\"files_with_matches\",\"content\",\"count\"],\"type\":\"string\"},\"max_count\":{\"anyOf\":[{\"exclusiveMinimum\":0,\"type\":\"integer\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Optional cap on the total number of matches returned across all files. Leave unset to use the configured default. When the cap is hit, results are truncated and a note says so; narrow the pattern or path to see the rest.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Search for a LITERAL text pattern across files (NOT regex).\\n\\nThe pattern is matched verbatim: regex metacharacters are ordinary characters, not operators. To match any of several strings, run a separate grep for each; `grep(pattern=\\\"foo|bar\\\")` searches for the literal text \\\"foo|bar\\\", and `.*` or `\\\\.` match those characters literally.\\n\\nReturns matching files or content per `output_mode`. Offloaded large tool results live under the artifacts root (`/large_tool_results/` by default); grep that directory to search them when you do not know the exact path.\"},{\"name\":\"web_search\",\"input_schema\":{\"properties\":{\"query\":{\"type\":\"string\"}},\"required\":[\"query\"],\"type\":\"object\"},\"description\":\"Search the web with Exa for current facts and return excerpts with source URLs\"},{\"name\":\"transfer_to_researcher\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Request a correction from the researcher\"},{\"name\":\"transfer_to_red_team\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send verified evidence for adversarial review\"},{\"name\":\"transfer_to_editor\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send verified findings to the editor\"}]" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_chat_model" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9|model:6b48cacc-ef10-0459-49d7-052bc435753c" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "verifier" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9" + } + }, + { + "key": "langsmith.metadata.ls_provider", + "value": { + "stringValue": "anthropic" + } + }, + { + "key": "langsmith.metadata.ls_model_name", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "langsmith.metadata.ls_model_type", + "value": { + "stringValue": "chat" + } + }, + { + "key": "langsmith.metadata.ls_max_tokens", + "value": { + "intValue": "4096" + } + }, + { + "key": "langsmith.metadata.lc_versions", + "value": { + "stringValue": "{\"langchain-core\":\"1.6.6\",\"langchain\":\"1.4.3\",\"langchain-anthropic\":\"1.7.5\"}" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.model", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "langsmith.metadata.max_tokens", + "value": { + "intValue": "4096" + } + }, + { + "key": "langsmith.metadata.model_kwargs", + "value": { + "stringValue": "{\"extra_body\":{\"extra_headers\":{\"anthropic-workspace-id\":\"[redacted workspace]\"}}}" + } + }, + { + "key": "langsmith.metadata.streaming", + "value": { + "boolValue": false + } + }, + { + "key": "langsmith.metadata.max_retries", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata._type", + "value": { + "stringValue": "anthropic-chat" + } + }, + { + "key": "langsmith.metadata.usage_metadata", + "value": { + "stringValue": "{\"input_tokens\":7509,\"output_tokens\":88,\"total_tokens\":7597,\"input_token_details\":{\"cache_read\":0,\"cache_creation\":0,\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_token_details\":{\"reasoning\":55}}" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "seq:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + }, + { + "key": "gen_ai.usage.input_tokens", + "value": { + "intValue": "7509" + } + }, + { + "key": "gen_ai.usage.output_tokens", + "value": { + "intValue": "88" + } + }, + { + "key": "gen_ai.usage.total_tokens", + "value": { + "intValue": "7597" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "4862a8dc9e239ae2", + "parentSpanId": "0b1303d7a7aa229b", + "name": "verifier", + "kind": 1, + "startTimeUnixNano": "1790968030846055936", + "endTimeUnixNano": "1790968032478449152", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "verifier" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "3" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "verifier" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:verifier\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"verifier\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "verifier" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "seq:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + } + ], + "events": [ + { + "timeUnixNano": "1790968032543667000", + "name": "exception", + "attributes": [ + { + "key": "exception.type", + "value": { + "stringValue": "Exception" + } + }, + { + "key": "exception.message", + "value": { + "stringValue": "ParentCommand(Command(graph='verifier:544dea40-e16b-458c-1464-128e1b9b10a9', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': 'CAQS1QgKEAgSGAI4AUIIdGhpbmtpbmcSDN6TfU6NDM971lEbzxoMvRUA1J9ox3fJQYT9IjArCQQGHBP4pRHPavXzRlbMbaYHC57Yj+Gbxgr0helvd2OIL/o6Rbt4PFA3FaIFUlgq8gc7KQI9FtGnvSAkLBRzIsUp/2d5Rd2zgEsfkFVeXsn8WYYZkinAQVVy6A7B3LaEJW0xb/x88Di67fedwx0Q+FlZtwcmT3Dcaa11JveyHRr3dm+zGSZP6CXeXNJ8nrTZ7W1YRTysD6w7o7Lp8h1Rwq4f4o8j+QUfY0vje+zJZsxHPmQNt3ykeKh99hgn6dbiz6/EHqmbHjSAu1M4SqEDfqIKThHYenamAZmcQ4XAOo6mdQ6+77VgpV1lC1/k52IiUoJjkGlQrnLCvutiI7KN+sgK8c2+2KCJrPRCvVV+BkStvP5jWWqzytpKQ+nHzhL448OrIA9gdJC39C8eDrXeRnI7t4FqlkXGoMlZAV9UMcrQHRxOMi8tOyTzi9oyBFDTSsQ+LJqer0tz1Ft9gek6vzg50SpVAFQdLERv8R1YqMaeI+xsvTAEW9MRgvRMkzLuzRT2guw3jD+Fjip37xgK5QI0R+CsOAmQPoTZizzcIyAUAuCJFCgq/gD/CibLxoymiVUI1an9Snt3KpNRoWdvWIne33V0pv8PHg9yW2JuLOqQGilLCsK/Q3oQr3upEMXxXGjCL7WUizvRZGFEEV+VplYt7v4tKZMj5pk3vdeM0MJ5XZg7PvUsRzycxcnrT3Knoc3qM+ttqZfTsb8d6U/pQifq7GuahFOHrvroqgJLj+/81Yy1pZFkjfJgY0XklzAnA6CFq/YT0gxbV+TH5IS+WaYOUzK36S8s5qqMwhngv4IzE3ctXXqnhIZXNznyVBqbYa/Gx2bCjcEj2n5RyGYRS/+MculgLBznQ9MkG2D7QP3Mq/nwHXKMIaLS8VK8hG3d0rAjlvnauXShNrJxtkj4qkwnxD4LrEjk1ue+PLcbLqYWwAr8n0s+41jrsIPVyyK9vFaEZrA9KaBxkJyiqx50GZNn7ckx+mkI18gH52iyVPtU8FKMXjugCl6mPLiHYiDQd+G63LudmOKys9itVnBDBNMP2b/I7+bIVRlheGaZWr6MATKl86B3y+0kuOrLRMyWcdibc2iQkZm+8f7dTUwbKbBJsKOFY73/8nlL/JiYpjz6nUIk+IqSjaFyK6XFlCcukWpWHpDJnSvbEzey7qHyCqJ+I+on8iP8GOtempQaS0/4kZGSwlrE6xOj6EwGpfjbDZKHkP/2RAdNYPQq3z7bdVJMJNnFMz6e37mzMpCBihwPdSFTRE3SCY66wvTgJzGCUyhHbSi5i1azzOXd8uHCSpT/6L1o6VU0pjoR8Kaa4wCWHGf7P/WEd+avyp02Jnu1cmpW0+Gq+vK9h0tdb2IClM/eNfdouQP+ep8MJUjraDRICmAJQY5obS71vniOo+reaFy0zRgB', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='verifier:544dea40-e16b-458c-1464-128e1b9b10a9', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team')" + } + }, + { + "key": "exception.stacktrace", + "value": { + "stringValue": "Exception: ParentCommand(Command(graph='verifier:544dea40-e16b-458c-1464-128e1b9b10a9', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='verifier:544dea40-e16b-458c-1464-128e1b9b10a9', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team')\n" + } + }, + { + "key": "exception.escaped", + "value": { + "stringValue": "False" + } + } + ] + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "0b1303d7a7aa229b", + "parentSpanId": "04ffc0db9ce0f358", + "name": "verifier", + "kind": 1, + "startTimeUnixNano": "1790968030845710080", + "endTimeUnixNano": "1790968032481081856", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "verifier" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langgraph" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "3" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "verifier" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:verifier\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"verifier\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "verifier:544dea40-e16b-458c-1464-128e1b9b10a9" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:3" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + } + ], + "events": [ + { + "timeUnixNano": "1790968032543832000", + "name": "exception", + "attributes": [ + { + "key": "exception.type", + "value": { + "stringValue": "Exception" + } + }, + { + "key": "exception.message", + "value": { + "stringValue": "ParentCommand(Command(graph='verifier:544dea40-e16b-458c-1464-128e1b9b10a9', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': 'CAQS9gUKEAgSGAI4AUIIdGhpbmtpbmcSDGFyJ1MXoY+Ai6NkbxoMRd2TrUfUU7WrPpA2IjDgy8dUplcZKc7DnJwNLTBfH5UNR+nGnakSPQia8UVIzrjkOnJ2fLrWUsA2oEO8yRsqkwXkkDCsyhB97dwj57RMt91XzgWhL9luNEGO92yW0rNFGoMSUVOxPIrFc5RjyrhKEc3+1RnpxCkylq+LNlQ5NFxLn6v2cF5DzqpvBHNR7XAig+urJIU3gXydCkaGZZDetJtQOUOXgZi9z9100NpdAEkXDo2ICHCGTGpVc0J/pbXxWRBxb6B1/Gl0Yjn68V6HlesH7IoC7GR/3HwRu9NSDBG4ttfQjEWcg+PeAea4Rn7jzx+Tm9H7L1joTKVgDbQg5iKMLfjvPqlnksCLtXOt8jSIS5OYLN7a/7TX6/w5d34vnw8vPDmU1UYi0Q72qUWhUa2vw8OXNpcKL7Bp0lNfBS8rvHY+vBY8/haAoTL3wvLFU1fT+4z/vA3BcsigZDYlfJeDYcxXmRuqxzxEGpXCRe9s1HWtID+41pHu6lpZHkXaghpc6TZHLxNwcVhTb6fMQ7Qo+2L6Pvklh1m32peodxeg2YiPhdpl3w/xkOEu5/JEF7ZBxpdUL+u3wkO5pUlsqfgX7uhzv7HC2WpSWVimrwiQwQOUx0+JPrLtw+lYfq7I3jruo0GW0guWvnuf7JM3YLj84q+JgHomnSSZnnZmrL0UaRvrVyLo877F39ccLS7XoZnnui8J4P58ZTmiLkEJeGcx1Iuag2e33339O7Yew/59tLbQtIGh9VWMwHBnFx39S8/4LEFrK5HldPQhOrloyTtkRs66iQRKtxMKS0VI6QTKZDAbs7a7H1yBv+mJi9Xg4uKmyU6qnn7zEKjjY2bIlCwezx4LLGP5HD3Zr6fZsmdG1UHzDsBvYG2oCI0oqEKM+valsT6hU8MRjbQBD/JJ8JJN/iBGlhBAUHo0UmhhtR2euTVpZWlMnhmpXAdKDXSfPdaPohgB', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='verifier:544dea40-e16b-458c-1464-128e1b9b10a9', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team')" + } + }, + { + "key": "exception.stacktrace", + "value": { + "stringValue": "Exception: ParentCommand(Command(graph='verifier:544dea40-e16b-458c-1464-128e1b9b10a9', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='verifier:544dea40-e16b-458c-1464-128e1b9b10a9', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': 'CAQS1QgKEAgSGAI4AUIIdGhpbmtpbmcSDN6TfU6NDM971lEbzxoMvRUA1J9ox3fJQYT9IjArCQQGHBP4pRHPavXzRlbMbaYHC57Yj+Gbxgr0helvd2OIL/o6Rbt4PFA3FaIFUlgq8gc7KQI9FtGnvSAkLBRzIsUp/2d5Rd2zgEsfkFVeXsn8WYYZkinAQVVy6A7B3LaEJW0xb/x88Di67fedwx0Q+FlZtwcmT3Dcaa11JveyHRr3dm+zGSZP6CXeXNJ8nrTZ7W1YRTysD6w7o7Lp8h1Rwq4f4o8j+QUfY0vje+zJZsxHPmQNt3ykeKh99hgn6dbiz6/EHqmbHjSAu1M4SqEDfqIKThHYenamAZmcQ4XAOo6mdQ6+77VgpV1lC1/k52IiUoJjkGlQrnLCvutiI7KN+sgK8c2+2KCJrPRCvVV+BkStvP5jWWqzytpKQ+nHzhL448OrIA9gdJC39C8eDrXeRnI7t4FqlkXGoMlZAV9UMcrQHRxOMi8tOyTzi9oyBFDTSsQ+LJqer0tz1Ft9gek6vzg50SpVAFQdLERv8R1YqMaeI+xsvTAEW9MRgvRMkzLuzRT2guw3jD+Fjip37xgK5QI0R+CsOAmQPoTZizzcIyAUAuCJFCgq/gD/CibLxoymiVUI1an9Snt3KpNRoWdvWIne33V0pv8PHg9yW2JuLOqQGilLCsK/Q3oQr3upEMXxXGjCL7WUizvRZGFEEV+VplYt7v4tKZMj5pk3vdeM0MJ5XZg7PvUsRzycxcnrT3Knoc3qM+ttqZfTsb8d6U/pQifq7GuahFOHrvroqgJLj+/81Yy1pZFkjfJgY0XklzAnA6CFq/YT0gxbV+TH5IS+WaYOUzK36S8s5qqMwhngv4IzE3ctXXqnhIZXNznyVBqbYa/Gx2bCjcEj2n5RyGYRS/+MculgLBznQ9MkG2D7QP3Mq/nwHXKMIaLS8VK8hG3d0rAjlvnauXShNrJxtkj4qkwnxD4LrEjk1ue+PLcbLqYWwAr8n0s+41jrsIPVyyK9vFaEZrA9KaBxkJyiqx50GZNn7ckx+mkI18gH52iyVPtU8FKMXjugCl6mPLiHYiDQd+G63LudmOKys9itVnBDBNMP2b/I7+bIVRlheGaZWr6MATKl86B3y+0kuOrLRMyWcdibc2iQkZm+8f7dTUwbKbBJsKOFY73/8nlL/JiYpjz6nUIk+IqSjaFyK6XFlCcukWpWHpDJnSvbEzey7qHyCqJ+I+on8iP8GOtempQaS0/4kZGSwlrE6xOj6EwGpfjbDZKHkP/2RAdNYPQq3z7bdVJMJNnFMz6e37mzMpCBihwPdSFTRE3SCY66wvTgJzGCUyhHbSi5i1azzOXd8uHCSpT/6L1o6VU0pjoR8Kaa4wCWHGf7P/WEd+avyp02Jnu1cmpW0+Gq+vK9h0tdb2IClM/eNfdouQP+ep8MJUjraDRICmAJQY5obS71vniOo+reaFy0zRgB', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': 'CAQS9gUKEAgSGAI4AUIIdGhpbmtpbmcSDGFyJ1MXoY+Ai6NkbxoMRd2TrUfUU7WrPpA2IjDgy8dUplcZKc7DnJwNLTBfH5UNR+nGnakSPQia8UVIzrjkOnJ2fLrWUsA2oEO8yRsqkwXkkDCsyhB97dwj57RMt91XzgWhL9luNEGO92yW0rNFGoMSUVOxPIrFc5RjyrhKEc3+1RnpxCkylq+LNlQ5NFxLn6v2cF5DzqpvBHNR7XAig+urJIU3gXydCkaGZZDetJtQOUOXgZi9z9100NpdAEkXDo2ICHCGTGpVc0J/pbXxWRBxb6B1/Gl0Yjn68V6HlesH7IoC7GR/3HwRu9NSDBG4ttfQjEWcg+PeAea4Rn7jzx+Tm9H7L1joTKVgDbQg5iKMLfjvPqlnksCLtXOt8jSIS5OYLN7a/7TX6/w5d34vnw8vPDmU1UYi0Q72qUWhUa2vw8OXNpcKL7Bp0lNfBS8rvHY+vBY8/haAoTL3wvLFU1fT+4z/vA3BcsigZDYlfJeDYcxXmRuqxzxEGpXCRe9s1HWtID+41pHu6lpZHkXaghpc6TZHLxNwcVhTb6fMQ7Qo+2L6Pvklh1m32peodxeg2YiPhdpl3w/xkOEu5/JEF7ZBxpdUL+u3wkO5pUlsqfgX7uhzv7HC2WpSWVimrwiQwQOUx0+JPrLtw+lYfq7I3jruo0GW0guWvnuf7JM3YLj84q+JgHomnSSZnnZmrL0UaRvrVyLo877F39ccLS7XoZnnui8J4P58ZTmiLkEJeGcx1Iuag2e33339O7Yew/59tLbQtIGh9VWMwHBnFx39S8/4LEFrK5HldPQhOrloyTtkRs66iQRKtxMKS0VI6QTKZDAbs7a7H1yBv+mJi9Xg4uKmyU6qnn7zEKjjY2bIlCwezx4LLGP5HD3Zr6fZsmdG1UHzDsBvYG2oCI0oqEKM+valsT6hU8MRjbQBD/JJ8JJN/iBGlhBAUHo0UmhhtR2euTVpZWlMnhmpXAdKDXSfPdaPohgB', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi')], 'active_agent': 'red_team'}, goto='red_team')\n" + } + }, + { + "key": "exception.escaped", + "value": { + "stringValue": "False" + } + } + ] + } + ], + "status": { + "code": 1 + }, + "flags": 256 + } + ] + } + ] + }, + { + "resource": { + "attributes": [ + { + "key": "telemetry.sdk.language", + "value": { + "stringValue": "python" + } + }, + { + "key": "telemetry.sdk.name", + "value": { + "stringValue": "opentelemetry" + } + }, + { + "key": "telemetry.sdk.version", + "value": { + "stringValue": "1.45.0" + } + }, + { + "key": "service.instance.id", + "value": { + "stringValue": "b873df4c-5106-4097-a20b-b9380724f4d9" + } + }, + { + "key": "service.name", + "value": { + "stringValue": "deeplite" + } + } + ] + }, + "scopeSpans": [ + { + "scope": { + "name": "langsmith" + }, + "spans": [ + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "916b875f8575ff2d", + "parentSpanId": "59d91c7c0791b7de", + "name": "tools", + "kind": 1, + "startTimeUnixNano": "1790968035030605056", + "endTimeUnixNano": "1790968035036314112", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__pregel_push\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_push\",0,false]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b|tools:f216a445-733e-fcc8-6fba-de3530aa90b7" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "red_team" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:2" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "eyJpbnB1dCI6W3sibmFtZSI6InRyYW5zZmVyX3RvX2VkaXRvciIsImFyZ3MiOnt9LCJpZCI6InRvb2x1XzAxVkJyV2RXRVdZZ2l0NGtOWWVoQk1VNSIsInR5cGUiOiJ0b29sX2NhbGwifV19" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "e30=" + } + } + ], + "events": [ + { + "timeUnixNano": "1790968035107514000", + "name": "exception", + "attributes": [ + { + "key": "exception.type", + "value": { + "stringValue": "Exception" + } + }, + { + "key": "exception.message", + "value": { + "stringValue": "ParentCommand(Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': 'CAQSwgcKEAgSGAI4AUIIdGhpbmtpbmcSDORXge9uL1832RMQwBoMjQwAwAHb9iP1ojPGIjDDScal486beCJbtG8/D2Y9g9S5xIPfjoHg/dxwX5HypSQEBbjFiTSbPECXSFzV6YIq3wbLcmyPbvusGnDexFgx+3sIXzvqyFV/69xhihMnSpfTCHy0+0zSu1WpYU/WUpIfoaSXTcTa1qkM8x8Ek/y/1jkKMZUfDFa93uhUJxOC4+QgPWBl/+Xy2t82L2x/ebq7QLQTqtR0jXeaURQm3Co6JvOgWmDvMpEdTeTWE3fDh1tzzVKsflum4d89b6CaKtn8nlQd7RhN99vNQMQHG5V4OuVNdrHPZZpFOuhdejsMFWXyB+55slGAd8wEXgFKbI/knOXVGzL/NDF8Gty1tNZlu2fdSCAsYWMsFQP1cbwLeQGszyXzJMVZJ2I9xBPkyz1HOXCPyh5F+j2gRTPikVB3ARC6tfB/lDSUeKBVZPQS8pY/B4eCs+IjjaBNWruLzfqCsc6xL0CuQPSYyQXaYFjYrSRNcC70WQBWT5VVhp0mA9yZDGYbRZt9I5OK9QkQmuJ5zDFaMEOXzSrsC4lteP6MdimiMijvsH3iq+c6WUYolRj3neI88EaHIzLAGRq64BNCLzdAYL2pEU2sb5uG78PKVoUUCbVJL5jpDOhLOTO1bQsTuoUpnRRrLQD/kIzV+ljpVBwwfJcyq75TJA/CtPr/xr2SZ9B1b2sbjG6jD0lhtoCddeDgcqgl/LSSkcuaYY8xPWCy+LtNhcqThfmfvnHLJIpL6gjbjW/OQpRfVUwfw1jOb9bWVwcgHhNYfKYGPtM8oth5xwLYRRVgzqMKOvs7falXRhVzZ2SP6Iw0BMmAAZ6HjfCl9L+tPqJNlnQQOHpoWjum4B+XsYldFEKGQWQqsd59iNPvao9p/sCOt7rGqCozcmgiEm4w66ez/QIDyb46n0+tcNJPUcoBKvQ/jDwE6VwmkQ/nECjFp3UdDT+kWYQSNd8j8VBZOpG8LlqUYrEZCv0q7Bs1vcNrdYiaFoS32osaynWk+Ht3OHuFWbEF8JlsFTQAO05VvYkecf0V/oTHsG5hyOOs7UEaDFq7uaJuzWVhh5pAojIaBcR8fVln2PLRTX7is2nsA+QrdidePcZtFtgxAiKYe1i2sSFi4vm8EOkCbQ63wdQeY4Urr5PuoMEwxUULjgKagiAmsJDq4RrVm7sO4+6YuA9j6l2uylkOEc67vf/5fkXuCsiApNL6keb8c+vL0n4FXGdzj+apSDfFGBgB', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor')" + } + }, + { + "key": "exception.stacktrace", + "value": { + "stringValue": "Exception: ParentCommand(Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='__parent__', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor')\n" + } + }, + { + "key": "exception.escaped", + "value": { + "stringValue": "False" + } + } + ] + } + ], + "status": { + "code": 2 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "783b8087e857fd50", + "parentSpanId": "916b875f8575ff2d", + "name": "FilesystemMiddleware.wrap_tool_call", + "kind": 1, + "startTimeUnixNano": "1790968035031665920", + "endTimeUnixNano": "1790968035033541888", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "FilesystemMiddleware.wrap_tool_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__pregel_push\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_push\",0,false]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b|tools:f216a445-733e-fcc8-6fba-de3530aa90b7" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "red_team" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "54441d892eb866e9", + "parentSpanId": "783b8087e857fd50", + "name": "transfer_to_editor", + "kind": 1, + "startTimeUnixNano": "1790968035032363008", + "endTimeUnixNano": "1790968035033051904", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "tool" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "transfer_to_editor" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "execute_tool" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "gen_ai.tool.name", + "value": { + "stringValue": "transfer_to_editor" + } + }, + { + "key": "gen_ai.tool.call.id", + "value": { + "stringValue": "toolu_01VBrWdWEWYgit4kNYehBMU5" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__pregel_push\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_push\",0,false]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b|tools:f216a445-733e-fcc8-6fba-de3530aa90b7" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "red_team" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b" + } + }, + { + "key": "langsmith.metadata.__handoff_destination", + "value": { + "stringValue": "editor" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "seq:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "1723d5322674ec35", + "parentSpanId": "59d91c7c0791b7de", + "name": "model", + "kind": 1, + "startTimeUnixNano": "1790968032482510080", + "endTimeUnixNano": "1790968035029985792", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b|model:04f09f43-f066-c110-818d-1a33d3ba1569" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "red_team" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "028f466e9c7e011c", + "parentSpanId": "1723d5322674ec35", + "name": "FilesystemMiddleware.wrap_model_call", + "kind": 1, + "startTimeUnixNano": "1790968032482876160", + "endTimeUnixNano": "1790968035029612032", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "FilesystemMiddleware.wrap_model_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b|model:04f09f43-f066-c110-818d-1a33d3ba1569" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "red_team" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "ee45871111076e7a", + "parentSpanId": "028f466e9c7e011c", + "name": "UnsupportedContentMiddleware.wrap_model_call", + "kind": 1, + "startTimeUnixNano": "1790968032483560192", + "endTimeUnixNano": "1790968035029467136", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "UnsupportedContentMiddleware.wrap_model_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b|model:04f09f43-f066-c110-818d-1a33d3ba1569" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "red_team" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "28bebc087f4f6678", + "parentSpanId": "ee45871111076e7a", + "name": "ChatAnthropic", + "kind": 1, + "startTimeUnixNano": "1790968032486740992", + "endTimeUnixNano": "1790968035029083136", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chat" + } + }, + { + "key": "gen_ai.serialized.name", + "value": { + "stringValue": "ChatAnthropic" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "llm" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "ChatAnthropic" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "anthropic" + } + }, + { + "key": "gen_ai.request.model", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "gen_ai.tool.definitions", + "value": { + "stringValue": "[{\"name\":\"ls\",\"input_schema\":{\"properties\":{\"path\":{\"description\":\"Absolute path to the directory to list. Must be absolute, not relative.\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"description\":\"Lists all files in a directory.\\n\\nThis is useful for exploring the filesystem and finding the right file to read or edit.\\nYou should almost ALWAYS use this tool before using the read_file or edit_file tools.\"},{\"name\":\"read_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path to the file to read. Must be absolute, not relative.\",\"type\":\"string\"},\"offset\":{\"default\":0,\"description\":\"Line number to start reading from (0-indexed). Use for pagination of large files.\",\"type\":\"integer\"},\"limit\":{\"default\":100,\"description\":\"Maximum number of lines to read. Use for pagination of large files.\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"description\":\"Reads a file from the filesystem. Assume any path the user provides is valid; reading a missing file returns an error.\\n\\nUsage:\\n- By default, it reads up to 100 lines starting from the beginning of the file. Use `offset`/`limit` to page through large files instead of reading them whole.\\n- A status header, `@@ field | field | ... @@`, sits above the file content, and every line after it is verbatim file content. When content is truncated, there may be an explanation before the header. Never include the header when editing.\\n- Speculatively batch multiple `read_file` calls in one response when several files may be useful.\\n- An empty file returns a system-reminder warning in place of contents.\\n- Large tool results may be offloaded to a file; the tool message gives the path. Read that path here, paging with `offset`/`limit`.\\n- Images (`.png`, `.jpg`, etc.), audio, video, and PDFs return multimodal content blocks (https://docs.langchain.com/oss/python/langchain/messages#multimodal).\\n- For images and PDFs, pagination via `offset`/`limit` is text-only - supply `file_path` only\\n- Always read a file before editing it.\"},{\"name\":\"glob\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Glob pattern to match files (e.g., '*.py', '**/*.py', '/subdir/**/*.md'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path; a leading '/' anchors to the search root ('/*.py' matches only top-level files). Leading-dot names are excluded unless the pattern segment starts with '.', so prefer the bare form '*.py' over '**/*.py' -- '**' will not descend into dot-directories like '.github'.\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Base directory to search from. Defaults to the backend's default root.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Find files matching a glob pattern, returning absolute paths.\\n\\nSupports `*` (any characters within a path segment), `**` (any directories), `?` (single character), `[abc]` (one character from a set), and `{a,b}` (alternatives), e.g. `*.py`, `src/**/*.py`, `*.{yml,yaml}`.\\n\\nA pattern without `/` matches the file name at any depth under the search root (`*.py` matches `src/app/main.py`). A pattern containing `/` matches the search-root-relative path (`src/**/*.py`). A leading `/` anchors to the search root (`/*.py` matches only top-level Python files).\\n\\nLeading-dot names are only matched when the pattern segment itself starts with `.` (use `.env`, or `.github/**/*.yml`). Because `**` will not descend into dot-directories, the bare form `*.yml` is *broader* than `**/*.yml` and is usually what you want.\"},{\"name\":\"grep\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Text pattern to search for (literal string, not regex).\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Directory to search in. Defaults to current working directory.\"},\"glob\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Glob pattern (NOT regex) limiting which files are searched (e.g. '*.py', '*.ts'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path (e.g. 'src/**/*.py'). This is an in-tool file filter, not a call to the separate glob tool. Brace expansion (e.g. '*.{ts,tsx}') is not supported on all backends; run a separate search per extension for reliable results.\"},\"output_mode\":{\"default\":\"files_with_matches\",\"description\":\"Shape of the returned text. 'files_with_matches' (default): newline-separated matching file paths. 'content': matching lines grouped by file under a ':' header, each line indented and formatted ': ' (only the matched line, no surrounding context). 'count': one ': ' line per file.\",\"enum\":[\"files_with_matches\",\"content\",\"count\"],\"type\":\"string\"},\"max_count\":{\"anyOf\":[{\"exclusiveMinimum\":0,\"type\":\"integer\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Optional cap on the total number of matches returned across all files. Leave unset to use the configured default. When the cap is hit, results are truncated and a note says so; narrow the pattern or path to see the rest.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Search for a LITERAL text pattern across files (NOT regex).\\n\\nThe pattern is matched verbatim: regex metacharacters are ordinary characters, not operators. To match any of several strings, run a separate grep for each; `grep(pattern=\\\"foo|bar\\\")` searches for the literal text \\\"foo|bar\\\", and `.*` or `\\\\.` match those characters literally.\\n\\nReturns matching files or content per `output_mode`. Offloaded large tool results live under the artifacts root (`/large_tool_results/` by default); grep that directory to search them when you do not know the exact path.\"},{\"name\":\"transfer_to_skeptic\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Return an unresolved objection to the skeptic\"},{\"name\":\"transfer_to_editor\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Send adversarial findings to the editor\"}]" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_chat_model" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b|model:04f09f43-f066-c110-818d-1a33d3ba1569" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "red_team" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b" + } + }, + { + "key": "langsmith.metadata.ls_provider", + "value": { + "stringValue": "anthropic" + } + }, + { + "key": "langsmith.metadata.ls_model_name", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "langsmith.metadata.ls_model_type", + "value": { + "stringValue": "chat" + } + }, + { + "key": "langsmith.metadata.ls_max_tokens", + "value": { + "intValue": "4096" + } + }, + { + "key": "langsmith.metadata.lc_versions", + "value": { + "stringValue": "{\"langchain-core\":\"1.6.6\",\"langchain\":\"1.4.3\",\"langchain-anthropic\":\"1.7.5\"}" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.model", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "langsmith.metadata.max_tokens", + "value": { + "intValue": "4096" + } + }, + { + "key": "langsmith.metadata.model_kwargs", + "value": { + "stringValue": "{\"extra_body\":{\"extra_headers\":{\"anthropic-workspace-id\":\"[redacted workspace]\"}}}" + } + }, + { + "key": "langsmith.metadata.streaming", + "value": { + "boolValue": false + } + }, + { + "key": "langsmith.metadata.max_retries", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata._type", + "value": { + "stringValue": "anthropic-chat" + } + }, + { + "key": "langsmith.metadata.usage_metadata", + "value": { + "stringValue": "{\"input_tokens\":7416,\"output_tokens\":151,\"total_tokens\":7567,\"input_token_details\":{\"cache_read\":0,\"cache_creation\":0,\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_token_details\":{\"reasoning\":119}}" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "seq:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "eyJtZXNzYWdlcyI6W1t7ImxjIjoxLCJ0eXBlIjoiY29uc3RydWN0b3IiLCJpZCI6WyJsYW5nY2hhaW4iLCJzY2hlbWEiLCJtZXNzYWdlcyIsIlN5c3RlbU1lc3NhZ2UiXSwia3dhcmdzIjp7ImNvbnRlbnQiOiJZb3UgYXJlIHJlZF90ZWFtLiBGaW5kIHRoZSBzdHJvbmdlc3QgcmVtYWluaW5nIG9iamVjdGlvbiB0byB0aGUgdmVyaWZpZWQgZmluZGluZ3MuIFNlbmQgdW5yZXNvbHZlZCBpc3N1ZXMgdG8gdGhlIHNrZXB0aWMsIG9yIHNlbmQgeW91ciBhc3Nlc3NtZW50IHRvIHRoZSBlZGl0b3IuIERvIG5vdCBnaXZlIHRoZSBmaW5hbCBhbnN3ZXIuIiwidHlwZSI6InN5c3RlbSJ9fSx7ImxjIjoxLCJ0eXBlIjoiY29uc3RydWN0b3IiLCJpZCI6WyJsYW5nY2hhaW4iLCJzY2hlbWEiLCJtZXNzYWdlcyIsIkh1bWFuTWVzc2FnZSJdLCJrd2FyZ3MiOnsiY29udGVudCI6IkZvciBhIHN5bnRoZXRpYyB0cmFjaW5nIGZpeHR1cmUsIGV4cGxhaW4gUHl0aG9uIHR1cGxlIHZlcnN1cyBsaXN0IGltbXV0YWJpbGl0eSBpbiBhdCBtb3N0IDEyMCB3b3Jkcy4gVXNlIG9ubHkgb2ZmaWNpYWwgUHl0aG9uIGRvY3VtZW50YXRpb24gaWYgeW91IHNlYXJjaC4gSGF2ZSB0aGUgc2tlcHRpYyBhbmQgdmVyaWZpZXIgY2hlY2sgaXQsIHRoZW4gaGF2ZSB0aGUgZWRpdG9yIHdyaXRlIC9hbnN3ZXIubWQuIEtlZXAgdGhlIHJ1biBzaG9ydCBhbmQgZG8gbm90IGFzayBmb2xsb3ctdXAgcXVlc3Rpb25zLiIsInR5cGUiOiJodW1hbiIsImlkIjoiNDYyMDQzMDUtZjhlZS00Mzg0LTljZTgtZmNkODBiZmNkZjc1In19LHsibGMiOjEsInR5cGUiOiJjb25zdHJ1Y3RvciIsImlkIjpbImxhbmdjaGFpbiIsInNjaGVtYSIsIm1lc3NhZ2VzIiwiQUlNZXNzYWdlIl0sImt3YXJncyI6eyJjb250ZW50IjpbeyJpZCI6InRvb2x1XzAxQjJMZkhHRGpZU0ZKaG1pWE5qNEN1USIsImNhbGxlciI6eyJ0eXBlIjoiZGlyZWN0In0sImlucHV0Ijp7InF1ZXJ5IjoiZG9jcy5weXRob24ub3JnIHR1cGxlcyBpbW11dGFibGUgc2VxdWVuY2VzIGxpc3RzIG11dGFibGUgZGF0YSBzdHJ1Y3R1cmVzIHR1dG9yaWFsIn0sIm5hbWUiOiJ3ZWJfc2VhcmNoIiwidHlwZSI6InRvb2xfdXNlIiwidG9vbHNldF9uYW1lIjpudWxsfV0sInJlc3BvbnNlX21ldGFkYXRhIjp7ImlkIjoibXNnXzAxMUNmZHc5YVc5YnJlblBxZ3liZk53UCIsImNvbnRhaW5lciI6bnVsbCwiZGlhZ25vc3RpY3MiOm51bGwsIm1vZGVsIjoiY2xhdWRlLXNvbm5ldCIsInN0b3BfZGV0YWlscyI6bnVsbCwic3RvcF9yZWFzb24iOiJ0b29sX3VzZSIsInN0b3Bfc2VxdWVuY2UiOm51bGwsInVzYWdlIjp7ImNhY2hlX2NyZWF0aW9uIjp7ImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjB9LCJjYWNoZV9jcmVhdGlvbl9pbnB1dF90b2tlbnMiOjAsImNhY2hlX3JlYWRfaW5wdXRfdG9rZW5zIjowLCJpbmZlcmVuY2VfZ2VvIjoiZ2xvYmFsIiwiaW5wdXRfdG9rZW5zIjoyODQ1LCJvdXRwdXRfdG9rZW5zIjo3Mywib3V0cHV0X3Rva2Vuc19kZXRhaWxzIjp7InRoaW5raW5nX3Rva2VucyI6MH0sInNlcnZlcl90b29sX3VzZSI6bnVsbCwic2VydmljZV90aWVyIjoic3RhbmRhcmQifSwibW9kZWxfbmFtZSI6ImNsYXVkZS1zb25uZXQiLCJtb2RlbF9wcm92aWRlciI6ImFudGhyb3BpYyJ9LCJ0eXBlIjoiYWkiLCJuYW1lIjoicmVzZWFyY2hlciIsImlkIjoibGNfcnVuLS0wMWEwZmUwMy0yMWEzLTcwMDAtYTM4MS0yODRhNmEwYzAzZjctMCIsInRvb2xfY2FsbHMiOlt7Im5hbWUiOiJ3ZWJfc2VhcmNoIiwiYXJncyI6eyJxdWVyeSI6ImRvY3MucHl0aG9uLm9yZyB0dXBsZXMgaW1tdXRhYmxlIHNlcXVlbmNlcyBsaXN0cyBtdXRhYmxlIGRhdGEgc3RydWN0dXJlcyB0dXRvcmlhbCJ9LCJpZCI6InRvb2x1XzAxQjJMZkhHRGpZU0ZKaG1pWE5qNEN1USIsInR5cGUiOiJ0b29sX2NhbGwifV0sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6Mjg0NSwib3V0cHV0X3Rva2VucyI6NzMsInRvdGFsX3Rva2VucyI6MjkxOCwiaW5wdXRfdG9rZW5fZGV0YWlscyI6eyJjYWNoZV9yZWFkIjowLCJjYWNoZV9jcmVhdGlvbiI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MH0sIm91dHB1dF90b2tlbl9kZXRhaWxzIjp7InJlYXNvbmluZyI6MH19LCJpbnZhbGlkX3Rvb2xfY2FsbHMiOltdfX0seyJsYyI6MSwidHlwZSI6ImNvbnN0cnVjdG9yIiwiaWQiOlsibGFuZ2NoYWluIiwic2NoZW1hIiwibWVzc2FnZXMiLCJUb29sTWVzc2FnZSJdLCJrd2FyZ3MiOnsiY29udGVudCI6Ilt7XCJ0aXRsZVwiOiBcIjUuIERhdGEgU3RydWN0dXJlcyBcXHUyMDE0IFB5dGhvbiAzLjE0LjUgZG9jdW1lbnRhdGlvblwiLCBcInVybFwiOiBcImh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvdHV0b3JpYWwvZGF0YXN0cnVjdHVyZXMuaHRtbFwiLCBcImhpZ2hsaWdodHNcIjogW1wiWW91IG1pZ2h0IGhhdmUgbm90aWNlZCB0aGF0IG1ldGhvZHMgbGlrZWBpbnNlcnRgLGByZW1vdmVgIG9yYHNvcnRgIHRoYXQgb25seSBtb2RpZnkgdGhlIGxpc3QgaGF2ZSBubyByZXR1cm4gdmFsdWUgcHJpbnRlZCBcXHUyMDEzIHRoZXkgcmV0dXJuIHRoZSBkZWZhdWx0YE5vbmVgLiBbMV0gVGhpcyBpcyBhIGRlc2lnbiBwcmluY2lwbGUgZm9yIGFsbCBtdXRhYmxlIGRhdGEgc3RydWN0dXJlcyBpbiBQeXRob24uXFxuLi4uXFxuIyMgNS4zLiBUdXBsZXMgYW5kIFNlcXVlbmNlc1xcdTAwYjZcXG5cXG5XZSBzYXcgdGhhdCBsaXN0cyBhbmQgc3RyaW5ncyBoYXZlIG1hbnkgY29tbW9uIHByb3BlcnRpZXMsIHN1Y2ggYXMgaW5kZXhpbmcgYW5kIHNsaWNpbmcgb3BlcmF0aW9ucy4gVGhleSBhcmUgdHdvIGV4YW1wbGVzIG9mIHNlcXVlbmNlIGRhdGEgdHlwZXMgKHNlZSBTZXF1ZW5jZSBUeXBlcyBcXHUyMDE0IGxpc3QsIHR1cGxlLCByYW5nZSkuIFNpbmNlIFB5dGhvbiBpcyBhbiBldm9sdmluZyBsYW5ndWFnZSwgb3RoZXIgc2VxdWVuY2UgZGF0YSB0eXBlcyBtYXkgYmUgYWRkZWQuIFRoZXJlIGlzIGFsc28gYW5vdGhlciBzdGFuZGFyZCBzZXF1ZW5jZSBkYXRhIHR5cGU6IHRoZSB0dXBsZS5cXG5cXG5BIHR1cGxlIGNvbnNpc3RzIG9mIGEgbnVtYmVyIG9mIHZhbHVlcyBzZXBhcmF0ZWQgYnkgY29tbWFzLCBmb3IgaW5zdGFuY2U6XFxuLi4uXFxuPj4+ICMgVHVwbGVzIGFyZSBpbW11dGFibGU6XFxuPj4+IHRbMF0gPSA4ODg4OFxcblRyYWNlYmFjayAobW9zdCByZWNlbnQgY2FsbCBsYXN0KTpcXG4gIEZpbGUgXFxcIjxzdGRpbj5cXFwiLCBsaW5lIDEsIGluIDxtb2R1bGU+XFxuVHlwZUVycm9yOiAndHVwbGUnIG9iamVjdCBkb2VzIG5vdCBzdXBwb3J0IGl0ZW0gYXNzaWdubWVudFxcbj4+PiAjIGJ1dCB0aGV5IGNhbiBjb250YWluIG11dGFibGUgb2JqZWN0czpcXG4+Pj4gdiA9IChbMSwgMiwgM10sIFszLCAyLCAxXSlcXG4+Pj4gdlxcbihbMSwgMiwgM10sIFszLCAyLCAxXSlcXG4uLi5cXG5BcyB5b3Ugc2VlLCBvbiBvdXRwdXQgdHVwbGVzIGFyZSBhbHdheXMgZW5jbG9zZWQgaW4gcGFyZW50aGVzZXMsIHNvIHRoYXQgbmVzdGVkIHR1cGxlcyBhcmUgaW50ZXJwcmV0ZWQgY29ycmVjdGx5OyB0aGV5IG1heSBiZSBpbnB1dCB3aXRoIG9yIHdpdGhvdXQgc3Vycm91bmRpbmcgcGFyZW50aGVzZXMsIGFsdGhvdWdoIG9mdGVuIHBhcmVudGhlc2VzIGFyZSBuZWNlc3NhcnkgYW55d2F5IChpZiB0aGUgdHVwbGUgaXMgcGFydCBvZiBhIGxhcmdlciBleHByZXNzaW9uKS4gSXQgaXMgbm90IHBvc3NpYmxlIHRvIGFzc2lnbiB0byB0aGUgaW5kaXZpZHVhbCBpdGVtcyBvZiBhIHR1cGxlLCBob3dldmVyIGl0IGlzIHBvc3NpYmxlIHRvIGNyZWF0ZSB0dXBsZXMgd2hpY2ggY29udGFpbiBtdXRhYmxlIG9iamVjdHMsIHN1Y2ggYXMgbGlzdHMuXFxuXFxuVGhvdWdoIHR1cGxlcyBtYXkgc2VlbSBzaW1pbGFyIHRvIGxpc3RzLCB0aGV5IGFyZSBvZnRlbiB1c2VkIGluIGRpZmZlcmVudCBzaXR1YXRpb25zIGFuZCBmb3IgZGlmZmVyZW50IHB1cnBvc2VzLiBUdXBsZXMgYXJlIGltbXV0YWJsZSwgYW5kIHVzdWFsbHkgY29udGFpbiBhIGhldGVyb2dlbmVvdXMgc2VxdWVuY2Ugb2YgZWxlbWVudHMgdGhhdCBhcmUgYWNjZXNzZWQgdmlhIHVucGFja2luZyAoc2VlIGxhdGVyIGluIHRoaXMgc2VjdGlvbikgb3IgaW5kZXhpbmcgKG9yIGV2ZW4gYnkgYXR0cmlidXRlIGluIHRoZSBjYXNlIG9mIG5hbWVkdHVwbGVzKS4gTGlzdHMgYXJlIG11dGFibGUsIGFuZCB0aGVpciBlbGVtZW50cyBhcmUgdXN1YWxseSBob21vZ2VuZW91cyBhbmQgYXJlIGFjY2Vzc2VkIGJ5IGl0ZXJhdGluZyBvdmVyIHRoZSBsaXN0Llxcbi4uLlxcbkFub3RoZXIgdXNlZnVsIGRhdGEgdHlwZSBidWlsdCBpbnRvIFB5dGhvbiBpcyB0aGUgZGljdGlvbmFyeSAoc2VlIE1hcHBpbmcgVHlwZXMgXFx1MjAxNCBkaWN0KS4gRGljdGlvbmFyaWVzIGFyZSBzb21ldGltZXMgZm91bmQgaW4gb3RoZXIgbGFuZ3VhZ2VzIGFzIFxcdTIwMWNhc3NvY2lhdGl2ZSBtZW1vcmllc1xcdTIwMWQgb3IgXFx1MjAxY2Fzc29jaWF0aXZlIGFycmF5c1xcdTIwMWQuIFVubGlrZSBzZXF1ZW5jZXMsIHdoaWNoIGFyZSBpbmRleGVkIGJ5IGEgcmFuZ2Ugb2YgbnVtYmVycywgZGljdGlvbmFyaWVzIGFyZSBpbmRleGVkIGJ5IGtleXMsIHdoaWNoIGNhbiBiZSBhbnkgaW1tdXRhYmxlIHR5cGU7IHN0cmluZ3MgYW5kIG51bWJlcnMgY2FuIGFsd2F5cyBiZSBrZXlzLiBUdXBsZXMgY2FuIGJlIHVzZWQgYXMga2V5cyBpZiB0aGV5IGNvbnRhaW4gb25seSBzdHJpbmdzLCBudW1iZXJzLCBvciB0dXBsZXM7IGlmIGEgdHVwbGUgY29udGFpbnMgYW55IG11dGFibGUgb2JqZWN0IGVpdGhlciBkaXJlY3RseSBvciBpbmRpcmVjdGx5LCBpdCBjYW5ub3QgYmUgdXNlZCBhcyBhIGtleS4gWW91IGNhblxcdTIwMTl0IHVzZSBsaXN0cyBhcyBrZXlzLCBzaW5jZSBsaXN0cyBjYW4gYmUgbW9kaWZpZWQgaW4gcGxhY2UgdXNpbmcgaW5kZXggYXNzaWdubWVudHMsIHNsaWNlIGFzc2lnbm1lbnRzLCBvciBtZXRob2RzIGxpa2UgYXBwZW5kKCkgYW5kIGV4dGVuZCgpLlwiXX0sIHtcInRpdGxlXCI6IFwiMy4gRGF0YSBtb2RlbCBcXHUyMDE0IFB5dGhvbiAzLjE0LjUgZG9jdW1lbnRhdGlvblwiLCBcInVybFwiOiBcImh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvcmVmZXJlbmNlL2RhdGFtb2RlbC5odG1sXCIsIFwiaGlnaGxpZ2h0c1wiOiBbXCJUaGUgdmFsdWUgb2Ygc29tZSBvYmplY3RzIGNhbiBjaGFuZ2UuIE9iamVjdHMgd2hvc2UgdmFsdWUgY2FuIGNoYW5nZSBhcmUgc2FpZCB0byBiZSBtdXRhYmxlOyBvYmplY3RzIHdob3NlIHZhbHVlIGlzIHVuY2hhbmdlYWJsZSBvbmNlIHRoZXkgYXJlIGNyZWF0ZWQgYXJlIGNhbGxlZCBpbW11dGFibGUuIChUaGUgdmFsdWUgb2YgYW4gaW1tdXRhYmxlIGNvbnRhaW5lciBvYmplY3QgdGhhdCBjb250YWlucyBhIHJlZmVyZW5jZSB0byBhIG11dGFibGUgb2JqZWN0IGNhbiBjaGFuZ2Ugd2hlbiB0aGUgbGF0dGVyXFx1MjAxOXMgdmFsdWUgaXMgY2hhbmdlZDsgaG93ZXZlciB0aGUgY29udGFpbmVyIGlzIHN0aWxsIGNvbnNpZGVyZWQgaW1tdXRhYmxlLCBiZWNhdXNlIHRoZSBjb2xsZWN0aW9uIG9mIG9iamVjdHMgaXQgY29udGFpbnMgY2Fubm90IGJlIGNoYW5nZWQuIFNvLCBpbW11dGFiaWxpdHkgaXMgbm90IHN0cmljdGx5IHRoZSBzYW1lIGFzIGhhdmluZyBhbiB1bmNoYW5nZWFibGUgdmFsdWUsIGl0IGlzIG1vcmUgc3VidGxlLikgQW4gb2JqZWN0XFx1MjAxOXMgbXV0YWJpbGl0eSBpcyBkZXRlcm1pbmVkIGJ5IGl0cyB0eXBlOyBmb3IgaW5zdGFuY2UsIG51bWJlcnMsIHN0cmluZ3MgYW5kIHR1cGxlcyBhcmUgaW1tdXRhYmxlLCB3aGlsZSBkaWN0aW9uYXJpZXMgYW5kIGxpc3RzIGFyZSBtdXRhYmxlLlxcbi4uLlxcblNvbWUgb2JqZWN0cyBjb250YWluIHJlZmVyZW5jZXMgdG8gb3RoZXIgb2JqZWN0czsgdGhlc2UgYXJlIGNhbGxlZCBjb250YWluZXJzLiBFeGFtcGxlcyBvZiBjb250YWluZXJzIGFyZSB0dXBsZXMsIGxpc3RzIGFuZCBkaWN0aW9uYXJpZXMuIFRoZSByZWZlcmVuY2VzIGFyZSBwYXJ0IG9mIGEgY29udGFpbmVyXFx1MjAxOXMgdmFsdWUuIEluIG1vc3QgY2FzZXMsIHdoZW4gd2UgdGFsayBhYm91dCB0aGUgdmFsdWUgb2YgYSBjb250YWluZXIsIHdlIGltcGx5IHRoZSB2YWx1ZXMsIG5vdCB0aGUgaWRlbnRpdGllcyBvZiB0aGUgY29udGFpbmVkIG9iamVjdHM7IGhvd2V2ZXIsIHdoZW4gd2UgdGFsayBhYm91dCB0aGUgbXV0YWJpbGl0eSBvZiBhIGNvbnRhaW5lciwgb25seSB0aGUgaWRlbnRpdGllcyBvZiB0aGUgaW1tZWRpYXRlbHkgY29udGFpbmVkIG9iamVjdHMgYXJlIGltcGxpZWQuIFNvLCBpZiBhbiBpbW11dGFibGUgY29udGFpbmVyIChsaWtlIGEgdHVwbGUpIGNvbnRhaW5zIGEgcmVmZXJlbmNlIHRvIGEgbXV0YWJsZSBvYmplY3QsIGl0cyB2YWx1ZSBjaGFuZ2VzIGlmIHRoYXQgbXV0YWJsZSBvYmplY3QgaXMgY2hhbmdlZC5cXG4uLi5cXG4jIyMgMy4yLjUuIFNlcXVlbmNlc1xcdTAwYjZcXG4uLi5cXG4jIyMjIDMuMi41LjEuIEltbXV0YWJsZSBzZXF1ZW5jZXNcXHUwMGI2XFxuXFxuQW4gb2JqZWN0IG9mIGFuIGltbXV0YWJsZSBzZXF1ZW5jZSB0eXBlIGNhbm5vdCBjaGFuZ2Ugb25jZSBpdCBpcyBjcmVhdGVkLiAoSWYgdGhlIG9iamVjdCBjb250YWlucyByZWZlcmVuY2VzIHRvIG90aGVyIG9iamVjdHMsIHRoZXNlIG90aGVyIG9iamVjdHMgbWF5IGJlIG11dGFibGUgYW5kIG1heSBiZSBjaGFuZ2VkOyBob3dldmVyLCB0aGUgY29sbGVjdGlvbiBvZiBvYmplY3RzIGRpcmVjdGx5IHJlZmVyZW5jZWQgYnkgYW4gaW1tdXRhYmxlIG9iamVjdCBjYW5ub3QgY2hhbmdlLilcXG5cXG5UaGUgZm9sbG93aW5nIHR5cGVzIGFyZSBpbW11dGFibGUgc2VxdWVuY2VzOlxcbi4uLlxcblR1cGxlc1xcbjogVGhlIGl0ZW1zIG9mIGEgYHR1cGxlYCBhcmUgYXJiaXRyYXJ5IFB5dGhvbiBvYmplY3RzLiBUdXBsZXMgb2YgdHdvIG9yIG1vcmUgaXRlbXMgYXJlIGZvcm1lZCBieSBjb21tYS1zZXBhcmF0ZWQgbGlzdHMgb2YgZXhwcmVzc2lvbnMuIEEgdHVwbGUgb2Ygb25lIGl0ZW0gKGEgXFx1MjAxOHNpbmdsZXRvblxcdTIwMTkpIGNhbiBiZSBmb3JtZWQgYnkgYWZmaXhpbmcgYSBjb21tYSB0byBhbiBleHByZXNzaW9uIChhbiBleHByZXNzaW9uIGJ5IGl0c2VsZiBkb2VzIG5vdCBjcmVhdGUgYSB0dXBsZSwgc2luY2UgcGFyZW50aGVzZXMgbXVzdCBiZSB1c2FibGUgZm9yIGdyb3VwaW5nIG9mIGV4cHJlc3Npb25zKS4gQW4gZW1wdHkgdHVwbGUgY2FuIGJlIGZvcm1lZCBieSBhbiBlbXB0eSBwYWlyIG9mIHBhcmVudGhlc2VzLlxcbi4uLlxcbiMjIyMgMy4yLjUuMi4gTXV0YWJsZSBzZXF1ZW5jZXNcXHUwMGI2XFxuXFxuTXV0YWJsZSBzZXF1ZW5jZXMgY2FuIGJlIGNoYW5nZWQgYWZ0ZXIgdGhleSBhcmUgY3JlYXRlZC4gVGhlIHN1YnNjcmlwdGlvbiBhbmQgc2xpY2luZyBub3RhdGlvbnMgY2FuIGJlIHVzZWQgYXMgdGhlIHRhcmdldCBvZiBhc3NpZ25tZW50IGFuZCBgZGVsYCAoZGVsZXRlKSBzdGF0ZW1lbnRzLlxcbi4uLlxcblRoZXJlIGFyZSBjdXJyZW50bHkgdHdvIGludHJpbnNpYyBtdXRhYmxlIHNlcXVlbmNlIHR5cGVzOlxcblxcbkxpc3RzXFxuOiBUaGUgaXRlbXMgb2YgYSBsaXN0IGFyZSBhcmJpdHJhcnkgUHl0aG9uIG9iamVjdHMuIExpc3RzIGFyZSBmb3JtZWQgYnkgcGxhY2luZyBhIGNvbW1hLXNlcGFyYXRlZCBsaXN0IG9mIGV4cHJlc3Npb25zIGluIHNxdWFyZSBicmFja2V0cy4gKE5vdGUgdGhhdCB0aGVyZSBhcmUgbm8gc3BlY2lhbCBjYXNlcyBuZWVkZWQgdG8gZm9ybSBsaXN0cyBvZiBsZW5ndGggMCBvciAxLilcIl19LCB7XCJ0aXRsZVwiOiBcIkJ1aWx0LWluIFR5cGVzIFxcdTIwMTQgUHl0aG9uIDMuMTQuNyBkb2N1bWVudGF0aW9uXCIsIFwidXJsXCI6IFwiaHR0cHM6Ly9kb2NzLnB5dGhvbi5vcmcvMy9idWlsdGlucy9zdGR0eXBlcy5odG1sXCIsIFwiaGlnaGxpZ2h0c1wiOiBbXCJjb2xsZWN0aW9uIGNsYXNzZXMgYXJlIG11dGFibGUuIFRoZSBtZXRob2RzIHRoYXQgYWRkLCBzdWJ0cmFjdCwgb3IgcmVhcnJhbmdlIHRoZWlyIC4uLiBpbiBwbGFjZSwgYW5kIGRvblxcdTIwMTl0IHJldHVybiBhIC4uLiAsIG5ldmVyIHJldHVybiB0aGUgY29sbGVjdGlvbiBpbnN0YW5jZSBpdHNlbGYgYnV0IGBOb25lYC5cXG4uLi5cXG4jIyBTZXF1ZW5jZSBUeXBlcyBcXHUyMDE0IGBsaXN0YCwgYHR1cGxlYCwgYHJhbmdlYFxcdTAwYjZcXG5cXG5UaGVyZSBhcmUgdGhyZWUgYmFzaWMgc2VxdWVuY2UgdHlwZXM6IGxpc3RzLCB0dXBsZXMsIGFuZCByYW5nZSBvYmplY3RzLiBBZGRpdGlvbmFsIHNlcXVlbmNlIHR5cGVzIHRhaWxvcmVkIGZvciBwcm9jZXNzaW5nIG9mIGJpbmFyeSBkYXRhIGFuZCB0ZXh0IHN0cmluZ3MgYXJlIGRlc2NyaWJlZCBpbiBkZWRpY2F0ZWQgc2VjdGlvbnMuXFxuLi4uXFxuVGhlIG9wZXJhdGlvbnMgaW4gdGhlIGZvbGxvd2luZyB0YWJsZSAuLi4gbXV0YWJsZSBhbmQgaW1tdXRhYmxlLiBUaGUgYGNvbGxlY3Rpb25zLiAuLi4gaXMgcHJvdmlkZWQgdG8gbWFrZSAuLi4gZWFzaWVyIHRvIGNvcnJlY3RseSBpbXBsZW1lbnQgdGhlc2Ugb3BlcmF0aW9ucyBvbiBjdXN0b20gc2VxdWVuY2UgdHlwZXNcXG4uLi5cXG4jIyMgSW1tdXRhYmxlIFNlcXVlbmNlIFR5cGVzXFx1MDBiNlxcbi4uLlxcbm11dGFibGUgc2VxdWVuY2UgdHlwZXMgaXNcXG4uLi5cXG5zdXBwb3J0IGFsbG93cyBpbW11dGFibGUgc2VxdWVuY2VzLCAuLi4gLCB0byBiZSB1c2VkIGFzIGBkaWN0YCBrZXlzIGFuZCBzdG9yZWQgaW4gLi4uIGVuc2V0YCBpbnN0YW5jZXNcXG4uLi5cXG4jIyMgTXV0YWJsZSBTZXF1ZW5jZSBUeXBlc1xcdTAwYjZcXG4uLi5cXG4jIyMgTGlzdHNcXHUwMGI2XFxuXFxuTGlzdHMgYXJlIG11dGFibGUgc2VxdWVuY2VzLCB0eXBpY2FsbHkgdXNlZCB0byBzdG9yZSBjb2xsZWN0aW9ucyBvZiBob21vZ2VuZW91cyBpdGVtcyAod2hlcmUgdGhlIHByZWNpc2UgZGVncmVlIG9mIHNpbWlsYXJpdHkgd2lsbCB2YXJ5IGJ5IGFwcGxpY2F0aW9uKS5cXG4uLi5cXG4jIyMgVHVwbGVzXFx1MDBiNlxcblxcblR1cGxlcyBhcmUgaW1tdXRhYmxlIHNlcXVlbmNlcywgdHlwaWNhbGx5IHVzZWQgdG8gc3RvcmUgY29sbGVjdGlvbnMgb2YgaGV0ZXJvZ2VuZW91cyBkYXRhIChzdWNoIGFzIHRoZSAyLXR1cGxlcyBwcm9kdWNlZCBieSB0aGUgYGVudW1lcmF0ZSgpYCBidWlsdC1pbikuIFR1cGxlcyBhcmUgYWxzbyB1c2VkIGZvciBjYXNlcyB3aGVyZSBhbiBpbW11dGFibGUgc2VxdWVuY2Ugb2YgaG9tb2dlbmVvdXMgZGF0YSBpcyBuZWVkZWQgKHN1Y2ggYXMgYWxsb3dpbmcgc3RvcmFnZSBpbiBhIGBzZXRgIG9yIGBkaWN0YCBpbnN0YW5jZSkuXFxuLi4uXFxudHVwbGUoaXRlcmFibGU9XFxuLi4uXFxuVGhlIGNvbnN0cnVjdG9yIGJ1aWxkcyBhIHR1cGxlIHdob3NlIGl0ZW1zIGFyZSB0aGUgc2FtZSBhbmQgaW4gdGhlIHNhbWUgb3JkZXIgYXMgaXRlcmFibGVcXHUyMDE5cyBpdGVtcy4gaXRlcmFibGUgbWF5IGJlIGVpdGhlciBhIHNlcXVlbmNlLCBhIGNvbnRhaW5lciB0aGF0IHN1cHBvcnRzIGl0ZXJhdGlvbiwgb3IgYW4gaXRlcmF0b3Igb2JqZWN0LiBJZiBpdGVyYWJsZSBpcyBhbHJlYWR5IGEgdHVwbGUsIGl0IGlzIHJldHVybmVkIHVuY2hhbmdlZC4gRm9yIGV4YW1wbGUsIGB0dXBsZSgnYWJjJylgIHJldHVybnMgYCgnYScsICdiJywgJ2MnKWAgYW5kIGB0dXBsZSggWzEsIDIsIDNdIClgIHJldHVybnMgYCgxLCAyLCAzKWAuIElmIG5vIGFyZ3VtZW50IGlzIGdpdmVuLCB0aGUgY29uc3RydWN0b3IgY3JlYXRlcyBhIG5ldyBlbXB0eSB0dXBsZSwgYCgpYC5cXG4uLi5cXG5UdXBsZXMgaW1wbGVtZW50IGFsbCBvZiB0aGUgY29tbW9uIHNlcXVlbmNlIG9wZXJhdGlvbnMuXFxuLi4uXFxuRm9yIGhldGVyb2dlbmVvdXMgY29sbGVjdGlvbnMgb2YgZGF0YSB3aGVyZSBhY2Nlc3MgYnkgbmFtZSBpcyBjbGVhcmVyIHRoYW4gYWNjZXNzIGJ5IGluZGV4LCBgY29sbGVjdGlvbnMubmFtZWR0dXBsZSgpYCBtYXkgYmUgYSBtb3JlIGFwcHJvcHJpYXRlIGNob2ljZSB0aGFuIGEgc2ltcGxlIHR1cGxlIG9iamVjdC5cIl19LCB7XCJ0aXRsZVwiOiBcIkJ1aWx0LWluIFR5cGVzIFxcdTIwMTQgUHl0aG9uIDMuMTQuNSBkb2N1bWVudGF0aW9uXCIsIFwidXJsXCI6IFwiaHR0cHM6Ly9kb2NzLnB5dGhvbi5vcmcvMy9saWJyYXJ5L3N0ZHR5cGVzLmh0bWxcIiwgXCJoaWdobGlnaHRzXCI6IFtcIlNvbWUgY29sbGVjdGlvbiBjbGFzc2VzIGFyZSBtdXRhYmxlLiBUaGUgbWV0aG9kcyB0aGF0IGFkZCwgc3VidHJhY3QsIG9yIHJlYXJyYW5nZSB0aGVpciAuLi4gaW4gcGxhY2UsIGFuZCBkb25cXHUyMDE5dCByZXR1cm4gYSAuLi4gLCBuZXZlciByZXR1cm4gdGhlIGNvbGxlY3Rpb24gaW5zdGFuY2UgaXRzZWxmIGJ1dCBgTm9uZWAuXFxuLi4uXFxuIyMgU2VxdWVuY2UgVHlwZXMgXFx1MjAxNCBgbGlzdGAsIGB0dXBsZWAsIGByYW5nZWBcXHUwMGI2XFxuXFxuVGhlcmUgYXJlIHRocmVlIGJhc2ljIHNlcXVlbmNlIHR5cGVzOiBsaXN0cywgdHVwbGVzLCBhbmQgLi4uIG9iamVjdHMuIEFkZGl0aW9uYWwgc2VxdWVuY2UgdHlwZXMgdGFpbG9yZWQgZm9yIHByb2Nlc3Npbmcgb2YgYmluYXJ5IGRhdGEgYW5kIHRleHQgc3RyaW5ncyBhcmUgZGVzY3JpYmVkIGluIGRlZGljYXRlZCBzZWN0aW9ucy5cXG4uLi5cXG5UaGUgb3BlcmF0aW9ucyBpbiB0aGUgZm9sbG93aW5nIHRhYmxlIC4uLiBpbW11dGFibGUuIFRoZSBgIC4uLiBpcyBwcm92aWRlZCB0byBtYWtlIC4uLiBlYXNpZXIgdG8gY29ycmVjdGx5IGltcGxlbWVudCB0aGVzZSBvcGVyYXRpb25zIG9uIGN1c3RvbSBzZXF1ZW5jZSB0eXBlc1xcbi4uLlxcbiMjIyBJbW11dGFibGUgU2VxdWVuY2UgVHlwZXNcXHUwMGI2XFxuLi4uXFxub3BlcmF0aW9uIHRoYXQgaW1tdXRhYmxlIHNlcXVlbmNlIC4uLiBieSBtdXRhYmxlIHNlcXVlbmNlIHR5cGVzIGlzIC4uLiBgaGFzaCgpYFxcbi4uLlxcblRoaXMgc3VwcG9ydCBhbGxvd3MgaW1tdXRhYmxlIHNlcXVlbmNlcywgc3VjaCBhcyBgdHVwbGVgIGluc3RhbmNlcywgdG8gYmUgdXNlZCBhcyBgZGljdGAga2V5cyBhbmQgc3RvcmVkIGluIGBzZXRgIGFuZCBgZnJvemVuc2V0YCBpbnN0YW5jZXMuXFxuLi4uXFxuIyMjIE11dGFibGUgU2VxdWVuY2UgVHlwZXNcXHUwMGI2XFxuLi4uXFxuIyMjIExpc3RzXFx1MDBiNlxcblxcbkxpc3RzIGFyZSBtdXRhYmxlIHNlcXVlbmNlcywgdHlwaWNhbGx5IHVzZWQgdG8gc3RvcmUgY29sbGVjdGlvbnMgb2YgaG9tb2dlbmVvdXMgaXRlbXMgKHdoZXJlIHRoZSBwcmVjaXNlIGRlZ3JlZSBvZiBzaW1pbGFyaXR5IHdpbGwgdmFyeSBieSBhcHBsaWNhdGlvbikuXFxuLi4uXFxuIyMjIFR1cGxlc1xcdTAwYjZcXG5cXG5UdXBsZXMgYXJlIGltbXV0YWJsZSBzZXF1ZW5jZXMsIHR5cGljYWxseSB1c2VkIHRvIHN0b3JlIGNvbGxlY3Rpb25zIG9mIGhldGVyb2dlbmVvdXMgZGF0YSAoc3VjaCBhcyB0aGUgMi10dXBsZXMgcHJvZHVjZWQgYnkgdGhlIGBlbnVtZXJhdGUoKWAgYnVpbHQtaW4pLiBUdXBsZXMgYXJlIGFsc28gdXNlZCBmb3IgY2FzZXMgd2hlcmUgYW4gaW1tdXRhYmxlIHNlcXVlbmNlIG9mIGhvbW9nZW5lb3VzIGRhdGEgaXMgbmVlZGVkIChzdWNoIGFzIGFsbG93aW5nIHN0b3JhZ2UgaW4gYSBgc2V0YCBvciBgZGljdGAgaW5zdGFuY2UpLlxcbi4uLlxcblRoZSBjb25zdHJ1Y3RvciBidWlsZHMgYSB0dXBsZSB3aG9zZSBpdGVtcyBhcmUgdGhlIHNhbWUgYW5kIGluIHRoZSBzYW1lIG9yZGVyIGFzIGl0ZXJhYmxlXFx1MjAxOXMgaXRlbXMuIGl0ZXJhYmxlIG1heSBiZSBlaXRoZXIgYSBzZXF1ZW5jZSwgYSBjb250YWluZXIgdGhhdCBzdXBwb3J0cyBpdGVyYXRpb24sIG9yIGFuIGl0ZXJhdG9yIG9iamVjdC4gSWYgaXRlcmFibGUgaXMgYWxyZWFkeSBhIHR1cGxlLCBpdCBpcyByZXR1cm5lZCB1bmNoYW5nZWQuIEZvciBleGFtcGxlLCBgdHVwbGUoJ2FiYycpYCByZXR1cm5zIGAoJ2EnLCAnYicsICdjJylgIGFuZCBgdHVwbGUoIFsxLCAyLCAzXSApYCByZXR1cm5zIGAoMSwgMiwgMylgLiBJZiBubyBhcmd1bWVudCBpcyBnaXZlbiwgdGhlIGNvbnN0cnVjdG9yIGNyZWF0ZXMgYSBuZXcgZW1wdHkgdHVwbGUsIGAoKWAuXFxuLi4uXFxuVHVwbGVzIGltcGxlbWVudCBhbGwgb2YgdGhlIGNvbW1vbiBzZXF1ZW5jZSBvcGVyYXRpb25zLlxcbi4uLlxcbkZvciBoZXRlcm9nZW5lb3VzIGNvbGxlY3Rpb25zIG9mIGRhdGEgd2hlcmUgYWNjZXNzIGJ5IG5hbWUgaXMgY2xlYXJlciB0aGFuIGFjY2VzcyBieSBpbmRleCwgYGNvbGxlY3Rpb25zLm5hbWVkdHVwbGUoKWAgbWF5IGJlIGEgbW9yZSBhcHByb3ByaWF0ZSBjaG9pY2UgdGhhbiBhIHNpbXBsZSB0dXBsZSBvYmplY3QuXCJdfSwge1widGl0bGVcIjogXCI1LiBEYXRhIFN0cnVjdHVyZXMgXFx1MjAxNCBQeXRob24gMy4xMC4yMCBkb2N1bWVudGF0aW9uXCIsIFwidXJsXCI6IFwiaHR0cHM6Ly9kb2NzLnB5dGhvbi5vcmcvMy4xMC90dXRvcmlhbC9kYXRhc3RydWN0dXJlcy5odG1sXCIsIFwiaGlnaGxpZ2h0c1wiOiBbXCJZb3UgbWlnaHQgaGF2ZSBub3RpY2VkIHRoYXQgbWV0aG9kcyBsaWtlIGBpbnNlcnRgLCBgcmVtb3ZlYCBvciBgc29ydGAgdGhhdCBvbmx5IG1vZGlmeSB0aGUgbGlzdCBoYXZlIG5vIHJldHVybiB2YWx1ZSBwcmludGVkIFxcdTIwMTMgdGhleSByZXR1cm4gdGhlIGRlZmF1bHQgYE5vbmVgLiAxIFRoaXMgaXMgYSBkZXNpZ24gcHJpbmNpcGxlIGZvciBhbGwgbXV0YWJsZSBkYXRhIHN0cnVjdHVyZXMgaW4gUHl0aG9uLlxcbi4uLlxcbiMjIDUuMy4gVHVwbGVzIGFuZCBTZXF1ZW5jZXNcXHUwMGI2XFxuXFxuV2Ugc2F3IHRoYXQgbGlzdHMgYW5kIHN0cmluZ3MgaGF2ZSBtYW55IGNvbW1vbiBwcm9wZXJ0aWVzLCBzdWNoIGFzIGluZGV4aW5nIGFuZCBzbGljaW5nIG9wZXJhdGlvbnMuIFRoZXkgYXJlIHR3byBleGFtcGxlcyBvZiBzZXF1ZW5jZSBkYXRhIHR5cGVzIChzZWUgU2VxdWVuY2UgVHlwZXMgXFx1MjAxNCBsaXN0LCB0dXBsZSwgcmFuZ2UpLiBTaW5jZSBQeXRob24gaXMgYW4gZXZvbHZpbmcgbGFuZ3VhZ2UsIG90aGVyIHNlcXVlbmNlIGRhdGEgdHlwZXMgbWF5IGJlIGFkZGVkLiBUaGVyZSBpcyBhbHNvIGFub3RoZXIgc3RhbmRhcmQgc2VxdWVuY2UgZGF0YSB0eXBlOiB0aGUgdHVwbGUuXFxuXFxuQSB0dXBsZSBjb25zaXN0cyBvZiBhIG51bWJlciBvZiB2YWx1ZXMgc2VwYXJhdGVkIGJ5IGNvbW1hcywgZm9yIGluc3RhbmNlOlxcbi4uLlxcbj4+PiAjIFR1cGxlcyBhcmUgaW1tdXRhYmxlOlxcbi4uLiB0WzBdID0gODg4ODhcXG5UcmFjZWJhY2sgKG1vc3QgcmVjZW50IGNhbGwgbGFzdCk6XFxuICBGaWxlIFxcXCI8c3RkaW4+XFxcIiwgbGluZSAxLCBpbiA8bW9kdWxlPlxcblR5cGVFcnJvcjogJ3R1cGxlJyBvYmplY3QgZG9lcyBub3Qgc3VwcG9ydCBpdGVtIGFzc2lnbm1lbnRcXG4+Pj4gIyBidXQgdGhleSBjYW4gY29udGFpbiBtdXRhYmxlIG9iamVjdHM6XFxuLi4uIHYgPSAoWzEsIDIsIDNdLCBbMywgMiwgMV0pXFxuPj4+IHZcXG4oWzEsIDIsIDNdLCBbMywgMiwgMV0pXFxuLi4uXFxuQXMgeW91IHNlZSwgb24gb3V0cHV0IHR1cGxlcyBhcmUgYWx3YXlzIGVuY2xvc2VkIGluIHBhcmVudGhlc2VzLCBzbyB0aGF0IG5lc3RlZCB0dXBsZXMgYXJlIGludGVycHJldGVkIGNvcnJlY3RseTsgdGhleSBtYXkgYmUgaW5wdXQgd2l0aCBvciB3aXRob3V0IHN1cnJvdW5kaW5nIHBhcmVudGhlc2VzLCBhbHRob3VnaCBvZnRlbiBwYXJlbnRoZXNlcyBhcmUgbmVjZXNzYXJ5IGFueXdheSAoaWYgdGhlIHR1cGxlIGlzIHBhcnQgb2YgYSBsYXJnZXIgZXhwcmVzc2lvbikuIEl0IGlzIG5vdCBwb3NzaWJsZSB0byBhc3NpZ24gdG8gdGhlIGluZGl2aWR1YWwgaXRlbXMgb2YgYSB0dXBsZSwgaG93ZXZlciBpdCBpcyBwb3NzaWJsZSB0byBjcmVhdGUgdHVwbGVzIHdoaWNoIGNvbnRhaW4gbXV0YWJsZSBvYmplY3RzLCBzdWNoIGFzIGxpc3RzLlxcblxcblRob3VnaCB0dXBsZXMgbWF5IHNlZW0gc2ltaWxhciB0byBsaXN0cywgdGhleSBhcmUgb2Z0ZW4gdXNlZCBpbiBkaWZmZXJlbnQgc2l0dWF0aW9ucyBhbmQgZm9yIGRpZmZlcmVudCBwdXJwb3Nlcy4gVHVwbGVzIGFyZSBpbW11dGFibGUsIGFuZCB1c3VhbGx5IGNvbnRhaW4gYSBoZXRlcm9nZW5lb3VzIHNlcXVlbmNlIG9mIGVsZW1lbnRzIHRoYXQgYXJlIGFjY2Vzc2VkIHZpYSB1bnBhY2tpbmcgKHNlZSBsYXRlciBpbiB0aGlzIHNlY3Rpb24pIG9yIGluZGV4aW5nIChvciBldmVuIGJ5IGF0dHJpYnV0ZSBpbiB0aGUgY2FzZSBvZiBgbmFtZWR0dXBsZXNgKS4gTGlzdHMgYXJlIG11dGFibGUsIGFuZCB0aGVpciBlbGVtZW50cyBhcmUgdXN1YWxseSBob21vZ2VuZW91cyBhbmQgYXJlIGFjY2Vzc2VkIGJ5IGl0ZXJhdGluZyBvdmVyIHRoZSBsaXN0Llxcbi4uLlxcbiMjIDUuNC5cXG4uLi5cXG4uIFNldCBvYmplY3RzXFxuLi4uXFxuIyMgNS41LiBEaWN0aW9uYXJpZXNcXHUwMGI2XFxuXFxuQW5vdGhlciB1c2VmdWwgZGF0YSB0eXBlIGJ1aWx0IGludG8gUHl0aG9uIGlzIHRoZSBkaWN0aW9uYXJ5IChzZWUgTWFwcGluZyBUeXBlcyBcXHUyMDE0IGRpY3QpLiBEaWN0aW9uYXJpZXMgYXJlIHNvbWV0aW1lcyBmb3VuZCBpbiBvdGhlciBsYW5ndWFnZXMgYXMgXFx1MjAxY2Fzc29jaWF0aXZlIG1lbW9yaWVzXFx1MjAxZCBvciBcXHUyMDFjYXNzb2NpYXRpdmUgYXJyYXlzXFx1MjAxZC4gVW5saWtlIHNlcXVlbmNlcywgd2hpY2ggYXJlIGluZGV4ZWQgYnkgYSByYW5nZSBvZiBudW1iZXJzLCBkaWN0aW9uYXJpZXMgYXJlIGluZGV4ZWQgYnkga2V5cywgd2hpY2ggY2FuIGJlIGFueSBpbW11dGFibGUgdHlwZTsgc3RyaW5ncyBhbmQgbnVtYmVycyBjYW4gYWx3YXlzIGJlIGtleXMuIFR1cGxlcyBjYW4gYmUgdXNlZCBhcyBrZXlzIGlmIHRoZXkgY29udGFpbiBvbmx5IHN0cmluZ3MsIG51bWJlcnMsIG9yIHR1cGxlczsgaWYgYSB0dXBsZSBjb250YWlucyBhbnkgbXV0YWJsZSBvYmplY3QgZWl0aGVyIGRpcmVjdGx5IG9yIGluZGlyZWN0bHksIGl0IGNhbm5vdCBiZSB1c2VkIGFzIGEga2V5LiBZb3UgY2FuXFx1MjAxOXQgdXNlIGxpc3RzIGFzIGtleXMsIHNpbmNlIGxpc3RzIGNhbiBiZSBtb2RpZmllZCBpbiBwbGFjZSB1c2luZyBpbmRleCBhc3NpZ25tZW50cywgc2xpY2UgYXNzaWdubWVudHMsIG9yIG1ldGhvZHMgbGlrZSBgYXBwZW5kKClgIGFuZCBgZXh0ZW5kKClgLlwiXX1dIiwidHlwZSI6InRvb2wiLCJuYW1lIjoid2ViX3NlYXJjaCIsImlkIjoiNmU1MTI1YWMtMzE2NC00YTc2LTljNTItYWMzNDYwY2UzNmU0IiwidG9vbF9jYWxsX2lkIjoidG9vbHVfMDFCMkxmSEdEallTRkpobWlYTmo0Q3VRIiwic3RhdHVzIjoic3VjY2VzcyJ9fSx7ImxjIjoxLCJ0eXBlIjoiY29uc3RydWN0b3IiLCJpZCI6WyJsYW5nY2hhaW4iLCJzY2hlbWEiLCJtZXNzYWdlcyIsIkFJTWVzc2FnZSJdLCJrd2FyZ3MiOnsiY29udGVudCI6W3siaWQiOiJ0b29sdV8wMVhqajNhUmRXeWhCSmZQbVRKQnhRYTkiLCJjYWxsZXIiOnsidHlwZSI6ImRpcmVjdCJ9LCJpbnB1dCI6e30sIm5hbWUiOiJ0cmFuc2Zlcl90b19za2VwdGljIiwidHlwZSI6InRvb2xfdXNlIiwidG9vbHNldF9uYW1lIjpudWxsfV0sInJlc3BvbnNlX21ldGFkYXRhIjp7ImlkIjoibXNnXzAxMUNmZHdBNkY0Y0NONXloRDRDcnM5TSIsImNvbnRhaW5lciI6bnVsbCwiZGlhZ25vc3RpY3MiOm51bGwsIm1vZGVsIjoiY2xhdWRlLXNvbm5ldCIsInN0b3BfZGV0YWlscyI6bnVsbCwic3RvcF9yZWFzb24iOiJ0b29sX3VzZSIsInN0b3Bfc2VxdWVuY2UiOm51bGwsInVzYWdlIjp7ImNhY2hlX2NyZWF0aW9uIjp7ImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjB9LCJjYWNoZV9jcmVhdGlvbl9pbnB1dF90b2tlbnMiOjAsImNhY2hlX3JlYWRfaW5wdXRfdG9rZW5zIjowLCJpbmZlcmVuY2VfZ2VvIjoiZ2xvYmFsIiwiaW5wdXRfdG9rZW5zIjo3Mzc4LCJvdXRwdXRfdG9rZW5zIjozMywib3V0cHV0X3Rva2Vuc19kZXRhaWxzIjp7InRoaW5raW5nX3Rva2VucyI6MH0sInNlcnZlcl90b29sX3VzZSI6bnVsbCwic2VydmljZV90aWVyIjoic3RhbmRhcmQifSwibW9kZWxfbmFtZSI6ImNsYXVkZS1zb25uZXQiLCJtb2RlbF9wcm92aWRlciI6ImFudGhyb3BpYyJ9LCJ0eXBlIjoiYWkiLCJuYW1lIjoicmVzZWFyY2hlciIsImlkIjoibGNfcnVuLS0wMWEwZmUwMy0zY2Q4LTc5ZjEtODhhMS1jZTZjZWUyOTRlNzktMCIsInRvb2xfY2FsbHMiOlt7Im5hbWUiOiJ0cmFuc2Zlcl90b19za2VwdGljIiwiYXJncyI6e30sImlkIjoidG9vbHVfMDFYamozYVJkV3loQkpmUG1USkJ4UWE5IiwidHlwZSI6InRvb2xfY2FsbCJ9XSwidXNhZ2VfbWV0YWRhdGEiOnsiaW5wdXRfdG9rZW5zIjo3Mzc4LCJvdXRwdXRfdG9rZW5zIjozMywidG90YWxfdG9rZW5zIjo3NDExLCJpbnB1dF90b2tlbl9kZXRhaWxzIjp7ImNhY2hlX3JlYWQiOjAsImNhY2hlX2NyZWF0aW9uIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowfSwib3V0cHV0X3Rva2VuX2RldGFpbHMiOnsicmVhc29uaW5nIjowfX0sImludmFsaWRfdG9vbF9jYWxscyI6W119fSx7ImxjIjoxLCJ0eXBlIjoiY29uc3RydWN0b3IiLCJpZCI6WyJsYW5nY2hhaW4iLCJzY2hlbWEiLCJtZXNzYWdlcyIsIlRvb2xNZXNzYWdlIl0sImt3YXJncyI6eyJjb250ZW50IjoiU3VjY2Vzc2Z1bGx5IHRyYW5zZmVycmVkIHRvIHNrZXB0aWMiLCJ0eXBlIjoidG9vbCIsIm5hbWUiOiJ0cmFuc2Zlcl90b19za2VwdGljIiwiaWQiOiIzODkwNThkMS0wODNmLTQ2MzItYmJjNS0wOWJmZDNhMGZmZDIiLCJ0b29sX2NhbGxfaWQiOiJ0b29sdV8wMVhqajNhUmRXeWhCSmZQbVRKQnhRYTkiLCJzdGF0dXMiOiJzdWNjZXNzIn19LHsibGMiOjEsInR5cGUiOiJjb25zdHJ1Y3RvciIsImlkIjpbImxhbmdjaGFpbiIsInNjaGVtYSIsIm1lc3NhZ2VzIiwiQUlNZXNzYWdlIl0sImt3YXJncyI6eyJjb250ZW50IjpbeyJzaWduYXR1cmUiOiJDQVFTMVFnS0VBZ1NHQUk0QVVJSWRHaHBibXRwYm1jU0RONlRmVTZORE05NzFsRWJ6eG9NdlJVQTFKOW94M2ZKUVlUOUlqQXJDUVFHSEJQNHBSSFBhdlh6UmxiTWJhWUhDNTdZaitHYnhncjBoZWx2ZDJPSUwvbzZSYnQ0UEZBM0ZhSUZVbGdxOGdjN0tRSTlGdEdudlNBa0xCUnpJc1VwLzJkNVJkMnpnRXNma0ZWZVhzbjhXWVlaa2luQVFWVnk2QTdCM0xhRUpXMHhiL3g4OERpNjdmZWR3eDBRK0ZsWnR3Y21UM0RjYWExMUp2ZXlIUnIzZG0rekdTWlA2Q1hlWE5KOG5yVFo3VzFZUlR5c0Q2dzdvN0xwOGgxUndxNGY0bzhqK1FVZlkwdmplK3pKWnN4SFBtUU50M3lrZUtoOTloZ242ZGJpejYvRUhxbWJIalNBdTFNNFNxRURmcUlLVGhIWWVuYW1BWm1jUTRYQU9vNm1kUTYrNzdWZ3BWMWxDMS9rNTJJaVVvSmprR2xRcm5MQ3Z1dGlJN0tOK3NnSzhjMisyS0NKclBSQ3ZWVitCa1N0dlA1aldXcXp5dHBLUStuSHpoTDQ0OE9ySUE5Z2RKQzM5QzhlRHJYZVJuSTd0NEZxbGtYR29NbFpBVjlVTWNyUUhSeE9NaTh0T3lUemk5b3lCRkRUU3NRK0xKcWVyMHR6MUZ0OWdlazZ2emc1MFNwVkFGUWRMRVJ2OFIxWXFNYWVJK3hzdlRBRVc5TVJndlJNa3pMdXpSVDJndXczakQrRmppcDM3eGdLNVFJMFIrQ3NPQW1RUG9UWml6emNJeUFVQXVDSkZDZ3EvZ0QvQ2liTHhveW1pVlVJMWFuOVNudDNLcE5Sb1dkdldJbmUzM1YwcHY4UEhnOXlXMkp1TE9xUUdpbExDc0svUTNvUXIzdXBFTVh4WEdqQ0w3V1VpenZSWkdGRUVWK1ZwbFl0N3Y0dEtaTWo1cGszdmRlTTBNSjVYWmc3UHZVc1J6eWN4Y25yVDNLbm9jM3FNK3R0cVpmVHNiOGQ2VS9wUWlmcTdHdWFoRk9IcnZyb3FnSkxqKy84MVl5MXBaRmtqZkpnWTBYa2x6QW5BNkNGcS9ZVDBneGJWK1RINUlTK1dhWU9VekszNlM4czVxcU13aG5ndjRJekUzY3RYWHFuaElaWE56bnlWQnFiWWEvR3gyYkNqY0VqMm41UnlHWVJTLytNY3VsZ0xCem5ROU1rRzJEN1FQM01xL253SFhLTUlhTFM4Vks4aEczZDByQWpsdm5hdVhTaE5ySnh0a2o0cWt3bnhENExyRWprMXVlK1BMY2JMcVlXd0FyOG4wcys0MWpyc0lQVnl5Szl2RmFFWnJBOUthQnhrSnlpcXg1MEdaTm43Y2t4K21rSTE4Z0g1Mml5VlB0VThGS01YanVnQ2w2bVBMaUhZaURRZCtHNjNMdWRtT0t5czlpdFZuQkRCTk1QMmIvSTcrYklWUmxoZUdhWldyNk1BVEtsODZCM3krMGt1T3JMUk15V2NkaWJjMmlRa1ptKzhmN2RUVXdiS2JCSnNLT0ZZNzMvOG5sTC9KaVlwano2blVJaytJcVNqYUZ5SzZYRmxDY3VrV3BXSHBESm5TdmJFemV5N3FIeUNxSitJK29uOGlQOEdPdGVtcFFhUzAvNGtaR1N3bHJFNnhPajZFd0dwZmpiRFpLSGtQLzJSQWROWVBRcTN6N2JkVkpNSk5uRk16NmUzN216TXBDQmlod1BkU0ZUUkUzU0NZNjZ3dlRnSnpHQ1V5aEhiU2k1aTFhenpPWGQ4dUhDU3BULzZMMW82VlUwcGpvUjhLYWE0d0NXSEdmN1AvV0VkK2F2eXAwMkpudTFjbXBXMCtHcSt2SzloMHRkYjJJQ2xNL2VOZmRvdVFQK2VwOE1KVWpyYURSSUNtQUpRWTVvYlM3MXZuaU9vK3JlYUZ5MHpSZ0IiLCJ0aGlua2luZyI6IiIsInR5cGUiOiJ0aGlua2luZyJ9LHsic2lnbmF0dXJlIjoiQ0FRUy9SRUtFUWdTR0FJNEFVSUpibUZ5Y21GMGFXOXVFZ3dGaDNBVkpaUDNzOHkxSHEwYURHNzZ1aEhPTmFTY1hBR1NoaUl3R2dqTFhIVXgxeVpya0xQbGpqelRPUXljcExKaUtWd1hjeG0vRXpLSm0xczhNNVd4dVJFV0VsZFhjb2FOMC9tc0twa1JNVCtlTGI1aWg5ckFIVUxUb21VTnNVd0pldTBqckplNEdMYXp5N3NQNUt0akVPRUJLUXNYVWZvUTdmRGtaT1FVSFppOXp6UU40aEZObVlKVWYzT1ZxZjlUUU5kQzErbS8vSEFaUGZXbUF5Nkh0RHZtN2tnQkprQ0VvaUZubTd0bi9QWDFoWEdQUmdXYzZCVFhVTXIyV0E4YUt5cWdnUlViTUgyK0pZdjVpV1pkZENjMXVwMU5icjNzRjdXUGNvdDlaQmh5SFFYcjY5MnplSms2U0pneWdJVnJBU2JNbHkyYkJ4VFdKQjYyM2dWZ3pwQ21WU0xaRnBrS1hnUGNwOGhHeURLT3ZGNlNpUVNIcUdSeFFvZnI3VnMxYVBoZlppeFJPSkdEK01scmtnZ1ZBbkdNeVlJRFVacGF2dENlaVUxSm1CU3owMDg0YlhQdFQvdG5wc0tPblNQWVpRbzNCMEJYS2JxQS9Xc0tuZzgvVjNaOFV1YWpvNklWWjJoZ0ExV0RkdXFRT1FrRXhHVTZwRnVMaGViSWp1V3hTTkkvRGZmdlIvL0xOcUNmdmRuZjBodm9QdER4ZngvU2F3SXg0L3NwcTl4YndGekh0TGdvSGcxRjJ3Rnc3Y2xQRGxnMVB5RC92MnlKRzNWOVQ4R0w2akdQRTZyaGZpbC91NEhOdmY3QlcwZFF6Q1RUWGNxWnk0bkJ5eTArcCtTN1p4Zk1sNEtweGEyZ09oaFNOamZwZnVYMFFwTDRrTUU4SjFubGlGTjFkOEtxRVB1REkxOEJRSFVoRC9VZlkyOW9BMHg1MTBGak0vQnNMWjRuNXNwcGtvSWk3Q0ZvUXEyYUFLVk5mQzFLaWxoSXBSRCsxZHlEdFpRa2xOOGdacE9FU0h3Nk1MMVR0VTB5ZkFjYm1xb3hKNmhoanp3SDZDTXNUUUVFeThNYlJCTStRS0trSVJkUkNQSEdGVzJMa3VSNTArSjBwRi90cjZwcVZ2SmVvemZpTW5yRWlsQjI3VFpQNG5LVEpHOHJkLy92Q1dlbjB5N0NBLzhkQko5Z2RwNXR4N05WQTQ1azFnZGN4RVIxZ1lvdU5YM24xdkczL0IxRjQrOTN3WFc5TXFvNlVzNTlUUW1yYjlOcWE3cFNRTlNySDA2dzFHeHlCQWxrRmZxQWxhZmsxNmFNcHE0MTZUSllwR3k0M1dDVWlDY0xXbGhpV2d6MnNnT0xBWFA5YTV3ZVdBS1JDOEo2amtjVWtEZVhuVytIRlNpUE02KzlCbzZrVmhMVWhONXJjNG1IWk9acEY3cHRQcHNRTjRYQ3FMUHNxcFJILzhvNVhweUM2Wm5lVGVGMkV4dGpod1pWalhEd01iSXpWWUlidzF5MlBQR3c4ZEM3cGM0c0lWU25JNG9RQUgwdjY1MGdoZmhtTWV2V1c0aDRQeWxidy9ERzRmZGVUMys4ejBmOE1PU1R0ZmlweDA1L1F0dEhsQXZPRFJ4YTV5REN2T3o2bjNmMUJPME4vNE1iR3lPTTI3cVc0eDhtQlZvcnlVWldmc21oZmkwL0dmTnZCOCt5bFRHYllOWDI3T2NFRjVXWnROcWJXRXk3VjVHYm1aVVN4c3BjZzdGQlozajMvM0w3bXV2WlhvWmkxZjVlcnE0eTNsU0grb0Y3cVBGbnZpZXlMT0N3dWJjUXkrb3lvd2o0Y0QwaWRSZWNucCtzKzUyRDcrbXpGMWdwVytmK2NKYXNveGlnYnhrT2xvUzR5ZWlLdmdNNG5XU3BHRWoxMlJQeDVvODBFbXppWE45dDR6SnpXMWh0QTVoWEpKZUZ5bXBNWXR5Q1VDZXZSV1ZtclJZa3RRN1VuQ2E2dEwvQVZQaTFuaTVYQ1hIZkxPdXFmSzVLTFl4andWdGRoaGZtQ0x2cGFLVk5DRU9DZjRuTkdIcUQ5OHdVYjBlaldOd0RZQm5KR2tCUnc5UlZzcGZ3TmRvV29WY24ycXY4eXdHVXA3eWMvc2syTHBJNlZ6aVJ5dldxYkdORzFaSnFWVnV0UmM0NitzT0U0VlNlUzIvQ1ROS05hNk5NQ2YvaHh4YVVWc1lmS2RQK1MxTGM0aWFuS3Awc1V1Z1BwbXRveWRDMENQMlJ3am5ITGNuenhDbnZxeGxMUVdYTU5QVHN1MnlCY0hsV0pMdGNtZGcvTWNMYWd5N2w1a0c2c043WnhKTEQva0F4OEU2dXFvaFArSy9qTVNyWXVRSm5ocjR0ZjRiaVdGWTNKemYvS3BBWXlWU3ErcGJmRktYTWJMOW5IRW9aUVQxNVd5YWJkNkRNQXEzUVpPdGhNNXBVemROcVVYa2NySTFQd2pBU0FnNGRWVS8ybys5OG1UWG55aFA3VmxFa1RuZGRwd3lKRitZQ0NjMDFwcWE2Wlg5OXBuUitZT3BJcmI1RHRQY0txMHQ1Y0ZDRHlReE4xbFV1cVpjWXVqdlgvR0M3KzZJcFJUei9Oa0VZLzVjbnRPZlpKeWQ2U2tVeC9KUjVBSklSUENOZWliMHJjV25uRm4wWEs4czIyeDQwd0xqRXR1ZlhETzkreXJhZjRrSHhsQkkzU0IwbWVNamVwWDUwQ0poQXg3TmVra1JGbndvZWNMZnFJeXJqWHJnQVpzVE1QaVg5NHNuamRyemlzQVh0QkthbnVsaWxTeE9mVzJIU21mbmswTDJHWEhKSjNTK3ZDYmdSRW1sOWRla2ZtSGhtd0VZdHYza2ZodGg3RVJJd1ZUOGo2OU90SUJDbWVUSUp1QTdvNzNQWGMxTEoyd2h1Wks3RlplNk5UT3M2MU1QN0pWbEljNnRiaHRPQmszTlhVOHBCUE9DWTZRNTVkNjNGdHBVVS9LQ2JRMEsyV1E5bzVqTkd3Tk5KNkN3NUZEQ3QreDVZSmVQMWQyUXpEU2lxK2NTWnF3cUNaVmNOb0FmdEdHemdyUlo0dmtwYlAweFFaSEN0V3NVd0hWVGpyWTROZlJEakhkVlBSbjhKOVh0b29jL2hJV2txekZhY3pZVGxhcHUyUkNKcWU4YUVvM2p6V1pDRUo3QWlCekJZcmFZRGdPZmVpUXllSlVzYmJYSGRHS2lpdzIyQmRwNE0rWXo2NzFNWjBpZTlFV1JrczBRMkRIR1VUbmU5UzR0QUFKUEdiVWY0eHRDTW9KNDBRNFFXMDVRTFNaeTN3TkZBVUZZbVhFNEVDREZCOCtJRWVORkZGL3RnQW5maDhHdkZoLzF4WStMRStvek1taW5qU1J3aHEwOXpRQUVrTkZ5dTBJS2d2RGt5T0kraWNjRjdkb1dMVFVhc1B4TEgxeEdQQlNLa2VXQ25Tb1gvNEMyYzlkdTY2QmJSWGFtSHFhZStWQ2lTNkJOOTUzaVlLT3U4ck1rbmVXK1RGalYwQ3pBZjhQTkc5TEJheVVnWTVVdzl4MFNhcDZ6STRQcGFaS0g0ZDlrdGtGVSs5MXlCYk41U1J0ZGQ4L0VRYXRKWG1CTmZ3N2tScmxsK0xqd1p3ZVdMRWIwalQxUnBHdURxSExkTFRNTWdvd1NjenJwMnpDc0pkUUgvc2VhWXJwd2tDRlI4ZFJqTTdKUlVrVmExQTBTdmRaQVg3NXZ1QnZ2TEJ6TjJjK1JidDVvcXk5M2xxSUJJaktiN3cyVWtSVGI0cEJXY05LTlBVZ3QzYXovUHhReEVhc2FsdGRtdXl2c1hZYnVyM1ZQTm44SnpOLzZKNU4rUUNuejU3MVRjY2FwQ21rUHZGRStnYXlYVStVRjFWS1l5RmNVdmxldjdsc1FsbWpxeksyUUE4WDdRM1R6RmFwcWh2SktsdDdkekJIcmFxWkJnUGdiOU40b0tOYXlpOEZaVDcxK2thWWhJaEZyRVNLWVJIZkhrajVuM2tmaGdMeSt4K2pMRGJLeE1nZ2tnSG5KejlSdUVIWlhCV3RrWUFRPT0iLCJ0aGlua2luZyI6IiIsInR5cGUiOiJ0aGlua2luZyJ9LHsiaWQiOiJ0b29sdV8wMUg2ZlY4SnZSSk52WHk0N2VSbmQzakgiLCJjYWxsZXIiOnsidHlwZSI6ImRpcmVjdCJ9LCJpbnB1dCI6e30sIm5hbWUiOiJ0cmFuc2Zlcl90b192ZXJpZmllciIsInR5cGUiOiJ0b29sX3VzZSIsInRvb2xzZXRfbmFtZSI6bnVsbH1dLCJyZXNwb25zZV9tZXRhZGF0YSI6eyJpZCI6Im1zZ18wMTFDZmR3QU1SZFMyMUZlSmZ6UWhNM3MiLCJjb250YWluZXIiOm51bGwsImRpYWdub3N0aWNzIjpudWxsLCJtb2RlbCI6ImNsYXVkZS1zb25uZXQiLCJzdG9wX2RldGFpbHMiOm51bGwsInN0b3BfcmVhc29uIjoidG9vbF91c2UiLCJzdG9wX3NlcXVlbmNlIjpudWxsLCJ1c2FnZSI6eyJjYWNoZV9jcmVhdGlvbiI6eyJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowfSwiY2FjaGVfY3JlYXRpb25faW5wdXRfdG9rZW5zIjowLCJjYWNoZV9yZWFkX2lucHV0X3Rva2VucyI6MCwiaW5mZXJlbmNlX2dlbyI6Imdsb2JhbCIsImlucHV0X3Rva2VucyI6NzM5Niwib3V0cHV0X3Rva2VucyI6NzcwLCJvdXRwdXRfdG9rZW5zX2RldGFpbHMiOnsidGhpbmtpbmdfdG9rZW5zIjo3Mzl9LCJzZXJ2ZXJfdG9vbF91c2UiOm51bGwsInNlcnZpY2VfdGllciI6InN0YW5kYXJkIn0sIm1vZGVsX25hbWUiOiJjbGF1ZGUtc29ubmV0IiwibW9kZWxfcHJvdmlkZXIiOiJhbnRocm9waWMifSwidHlwZSI6ImFpIiwibmFtZSI6InNrZXB0aWMiLCJpZCI6ImxjX3J1bi0tMDFhMGZlMDMtNGFlOS03NmMwLTg5YTYtNGYwYjExNGUzMDMwLTAiLCJ0b29sX2NhbGxzIjpbeyJuYW1lIjoidHJhbnNmZXJfdG9fdmVyaWZpZXIiLCJhcmdzIjp7fSwiaWQiOiJ0b29sdV8wMUg2ZlY4SnZSSk52WHk0N2VSbmQzakgiLCJ0eXBlIjoidG9vbF9jYWxsIn1dLCJ1c2FnZV9tZXRhZGF0YSI6eyJpbnB1dF90b2tlbnMiOjczOTYsIm91dHB1dF90b2tlbnMiOjc3MCwidG90YWxfdG9rZW5zIjo4MTY2LCJpbnB1dF90b2tlbl9kZXRhaWxzIjp7ImNhY2hlX3JlYWQiOjAsImNhY2hlX2NyZWF0aW9uIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowfSwib3V0cHV0X3Rva2VuX2RldGFpbHMiOnsicmVhc29uaW5nIjo3Mzl9fSwiaW52YWxpZF90b29sX2NhbGxzIjpbXX19LHsibGMiOjEsInR5cGUiOiJjb25zdHJ1Y3RvciIsImlkIjpbImxhbmdjaGFpbiIsInNjaGVtYSIsIm1lc3NhZ2VzIiwiVG9vbE1lc3NhZ2UiXSwia3dhcmdzIjp7ImNvbnRlbnQiOiJTdWNjZXNzZnVsbHkgdHJhbnNmZXJyZWQgdG8gdmVyaWZpZXIiLCJ0eXBlIjoidG9vbCIsIm5hbWUiOiJ0cmFuc2Zlcl90b192ZXJpZmllciIsImlkIjoiYzA2NDU2M2EtOTc0Zi00ZjBmLWFiNGEtMDgwZTYzYzAxY2Y1IiwidG9vbF9jYWxsX2lkIjoidG9vbHVfMDFINmZWOEp2UkpOdlh5NDdlUm5kM2pIIiwic3RhdHVzIjoic3VjY2VzcyJ9fSx7ImxjIjoxLCJ0eXBlIjoiY29uc3RydWN0b3IiLCJpZCI6WyJsYW5nY2hhaW4iLCJzY2hlbWEiLCJtZXNzYWdlcyIsIkFJTWVzc2FnZSJdLCJrd2FyZ3MiOnsiY29udGVudCI6W3sic2lnbmF0dXJlIjoiQ0FRUzlnVUtFQWdTR0FJNEFVSUlkR2hwYm10cGJtY1NER0Z5SjFNWG9ZK0FpNk5rYnhvTVJkMlRyVWZVVTdXclBwQTJJakRneThkVXBsY1pLYzdEbkp3TkxUQmZINVVOUituR25ha1NQUWlhOFVWSXpyamtPbkoyZkxyV1VzQTJvRU84eVJzcWt3WGtrRENzeWhCOTdkd2o1N1JNdDkxWHpnV2hMOWx1TkVHTzkyeVcwck5GR29NU1VWT3hQSXJGYzVSanlyaEtFYzMrMVJucHhDa3lscStMTmxRNU5GeExuNnYyY0Y1RHpxcHZCSE5SN1hBaWcrdXJKSVUzZ1h5ZENrYUdaWkRldEp0UU9VT1hnWmk5ejkxMDBOcGRBRWtYRG8ySUNIQ0dUR3BWYzBKL3BiWHhXUkJ4YjZCMS9HbDBZam42OFY2SGxlc0g3SW9DN0dSLzNId1J1OU5TREJHNHR0ZlFqRVdjZytQZUFlYTRSbjdqengrVG05SDdMMWpvVEtWZ0RiUWc1aUtNTGZqdlBxbG5rc0NMdFhPdDhqU0lTNU9ZTE43YS83VFg2L3c1ZDM0dm53OHZQRG1VMVVZaTBRNzJxVVdoVWEydnc4T1hOcGNLTDdCcDBsTmZCUzhydkhZK3ZCWTgvaGFBb1RMM3d2TEZVMWZUKzR6L3ZBM0Jjc2lnWkRZbGZKZURZY3hYbVJ1cXh6eEVHcFhDUmU5czFIV3RJRCs0MXBIdTZscFpIa1hhZ2hwYzZUWkhMeE53Y1ZoVGI2Zk1RN1FvKzJMNlB2a2xoMW0zMnBlb2R4ZWcyWWlQaGRwbDN3L3hrT0V1NS9KRUY3WkJ4cGRVTCt1M3drTzVwVWxzcWZnWDd1aHp2N0hDMldwU1dWaW1yd2lRd1FPVXgwK0pQckx0dytsWWZxN0kzanJ1bzBHVzBndVd2bnVmN0pNM1lMajg0cStKZ0hvbW5TU1publptckwwVWFSdnJWeUxvODc3RjM5Y2NMUzdYb1pubnVpOEo0UDU4WlRtaUxrRUplR2N4MUl1YWcyZTMzMzM5TzdZZXcvNTl0TGJRdElHaDlWV013SEJuRngzOVM4LzRMRUZySzVIbGRQUWhPcmxveVR0a1JzNjZpUVJLdHhNS1MwVkk2UVRLWkRBYnM3YTdIMXlCdittSmk5WGc0dUtteVU2cW5uN3pFS2pqWTJiSWxDd2V6eDRMTEdQNUhEM1pyNmZac21kRzFVSHpEc0J2WUcyb0NJMG9xRUtNK3ZhbHNUNmhVOE1SamJRQkQvSko4SkpOL2lCR2xoQkFVSG8wVW1oaHRSMmV1VFZwWldsTW5obXBYQWRLRFhTZlBkYVBvaGdCIiwidGhpbmtpbmciOiIiLCJ0eXBlIjoidGhpbmtpbmcifSx7ImlkIjoidG9vbHVfMDFYRUF1aFFIQ0JkeUN3dHltWndGZkRpIiwiY2FsbGVyIjp7InR5cGUiOiJkaXJlY3QifSwiaW5wdXQiOnt9LCJuYW1lIjoidHJhbnNmZXJfdG9fcmVkX3RlYW0iLCJ0eXBlIjoidG9vbF91c2UiLCJ0b29sc2V0X25hbWUiOm51bGx9XSwicmVzcG9uc2VfbWV0YWRhdGEiOnsiaWQiOiJtc2dfMDExQ2Zkd0FzYWJEcXVlZ0hpNllVcENuIiwiY29udGFpbmVyIjpudWxsLCJkaWFnbm9zdGljcyI6bnVsbCwibW9kZWwiOiJjbGF1ZGUtc29ubmV0Iiwic3RvcF9kZXRhaWxzIjpudWxsLCJzdG9wX3JlYXNvbiI6InRvb2xfdXNlIiwic3RvcF9zZXF1ZW5jZSI6bnVsbCwidXNhZ2UiOnsiY2FjaGVfY3JlYXRpb24iOnsiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MH0sImNhY2hlX2NyZWF0aW9uX2lucHV0X3Rva2VucyI6MCwiY2FjaGVfcmVhZF9pbnB1dF90b2tlbnMiOjAsImluZmVyZW5jZV9nZW8iOiJnbG9iYWwiLCJpbnB1dF90b2tlbnMiOjc1MDksIm91dHB1dF90b2tlbnMiOjg4LCJvdXRwdXRfdG9rZW5zX2RldGFpbHMiOnsidGhpbmtpbmdfdG9rZW5zIjo1NX0sInNlcnZlcl90b29sX3VzZSI6bnVsbCwic2VydmljZV90aWVyIjoic3RhbmRhcmQifSwibW9kZWxfbmFtZSI6ImNsYXVkZS1zb25uZXQiLCJtb2RlbF9wcm92aWRlciI6ImFudGhyb3BpYyJ9LCJ0eXBlIjoiYWkiLCJuYW1lIjoidmVyaWZpZXIiLCJpZCI6ImxjX3J1bi0tMDFhMGZlMDMtNjY4Mi03ZDIxLThjMTUtZmZiY2U5NDIyYzlmLTAiLCJ0b29sX2NhbGxzIjpbeyJuYW1lIjoidHJhbnNmZXJfdG9fcmVkX3RlYW0iLCJhcmdzIjp7fSwiaWQiOiJ0b29sdV8wMVhFQXVoUUhDQmR5Q3d0eW1ad0ZmRGkiLCJ0eXBlIjoidG9vbF9jYWxsIn1dLCJ1c2FnZV9tZXRhZGF0YSI6eyJpbnB1dF90b2tlbnMiOjc1MDksIm91dHB1dF90b2tlbnMiOjg4LCJ0b3RhbF90b2tlbnMiOjc1OTcsImlucHV0X3Rva2VuX2RldGFpbHMiOnsiY2FjaGVfcmVhZCI6MCwiY2FjaGVfY3JlYXRpb24iOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjB9LCJvdXRwdXRfdG9rZW5fZGV0YWlscyI6eyJyZWFzb25pbmciOjU1fX0sImludmFsaWRfdG9vbF9jYWxscyI6W119fSx7ImxjIjoxLCJ0eXBlIjoiY29uc3RydWN0b3IiLCJpZCI6WyJsYW5nY2hhaW4iLCJzY2hlbWEiLCJtZXNzYWdlcyIsIlRvb2xNZXNzYWdlIl0sImt3YXJncyI6eyJjb250ZW50IjoiU3VjY2Vzc2Z1bGx5IHRyYW5zZmVycmVkIHRvIHJlZF90ZWFtIiwidHlwZSI6InRvb2wiLCJuYW1lIjoidHJhbnNmZXJfdG9fcmVkX3RlYW0iLCJpZCI6Ijk4MmMwMTI2LWU2YWItNDU4YS05MjJlLTdiMjY2ZTgzYzJiMiIsInRvb2xfY2FsbF9pZCI6InRvb2x1XzAxWEVBdWhRSENCZHlDd3R5bVp3RmZEaSIsInN0YXR1cyI6InN1Y2Nlc3MifX1dXX0=" + } + }, + { + "key": "gen_ai.usage.input_tokens", + "value": { + "intValue": "7416" + } + }, + { + "key": "gen_ai.usage.output_tokens", + "value": { + "intValue": "151" + } + }, + { + "key": "gen_ai.usage.total_tokens", + "value": { + "intValue": "7567" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "59d91c7c0791b7de", + "parentSpanId": "ad48a4e078446202", + "name": "red_team", + "kind": 1, + "startTimeUnixNano": "1790968032481995008", + "endTimeUnixNano": "1790968035039021056", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "red_team" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "4" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "red_team" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:red_team\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"red_team\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "red_team" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "seq:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + } + ], + "events": [ + { + "timeUnixNano": "1790968035109079000", + "name": "exception", + "attributes": [ + { + "key": "exception.type", + "value": { + "stringValue": "Exception" + } + }, + { + "key": "exception.message", + "value": { + "stringValue": "ParentCommand(Command(graph='red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': 'CAQSwgcKEAgSGAI4AUIIdGhpbmtpbmcSDORXge9uL1832RMQwBoMjQwAwAHb9iP1ojPGIjDDScal486beCJbtG8/D2Y9g9S5xIPfjoHg/dxwX5HypSQEBbjFiTSbPECXSFzV6YIq3wbLcmyPbvusGnDexFgx+3sIXzvqyFV/69xhihMnSpfTCHy0+0zSu1WpYU/WUpIfoaSXTcTa1qkM8x8Ek/y/1jkKMZUfDFa93uhUJxOC4+QgPWBl/+Xy2t82L2x/ebq7QLQTqtR0jXeaURQm3Co6JvOgWmDvMpEdTeTWE3fDh1tzzVKsflum4d89b6CaKtn8nlQd7RhN99vNQMQHG5V4OuVNdrHPZZpFOuhdejsMFWXyB+55slGAd8wEXgFKbI/knOXVGzL/NDF8Gty1tNZlu2fdSCAsYWMsFQP1cbwLeQGszyXzJMVZJ2I9xBPkyz1HOXCPyh5F+j2gRTPikVB3ARC6tfB/lDSUeKBVZPQS8pY/B4eCs+IjjaBNWruLzfqCsc6xL0CuQPSYyQXaYFjYrSRNcC70WQBWT5VVhp0mA9yZDGYbRZt9I5OK9QkQmuJ5zDFaMEOXzSrsC4lteP6MdimiMijvsH3iq+c6WUYolRj3neI88EaHIzLAGRq64BNCLzdAYL2pEU2sb5uG78PKVoUUCbVJL5jpDOhLOTO1bQsTuoUpnRRrLQD/kIzV+ljpVBwwfJcyq75TJA/CtPr/xr2SZ9B1b2sbjG6jD0lhtoCddeDgcqgl/LSSkcuaYY8xPWCy+LtNhcqThfmfvnHLJIpL6gjbjW/OQpRfVUwfw1jOb9bWVwcgHhNYfKYGPtM8oth5xwLYRRVgzqMKOvs7falXRhVzZ2SP6Iw0BMmAAZ6HjfCl9L+tPqJNlnQQOHpoWjum4B+XsYldFEKGQWQqsd59iNPvao9p/sCOt7rGqCozcmgiEm4w66ez/QIDyb46n0+tcNJPUcoBKvQ/jDwE6VwmkQ/nECjFp3UdDT+kWYQSNd8j8VBZOpG8LlqUYrEZCv0q7Bs1vcNrdYiaFoS32osaynWk+Ht3OHuFWbEF8JlsFTQAO05VvYkecf0V/oTHsG5hyOOs7UEaDFq7uaJuzWVhh5pAojIaBcR8fVln2PLRTX7is2nsA+QrdidePcZtFtgxAiKYe1i2sSFi4vm8EOkCbQ63wdQeY4Urr5PuoMEwxUULjgKagiAmsJDq4RrVm7sO4+6YuA9j6l2uylkOEc67vf/5fkXuCsiApNL6keb8c+vL0n4FXGdzj+apSDfFGBgB', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor')" + } + }, + { + "key": "exception.stacktrace", + "value": { + "stringValue": "Exception: ParentCommand(Command(graph='red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor')\n" + } + }, + { + "key": "exception.escaped", + "value": { + "stringValue": "False" + } + } + ] + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "ad48a4e078446202", + "parentSpanId": "04ffc0db9ce0f358", + "name": "red_team", + "kind": 1, + "startTimeUnixNano": "1790968032481682176", + "endTimeUnixNano": "1790968035042222080", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "red_team" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langgraph" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "4" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "red_team" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:red_team\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"red_team\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:4" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + } + ], + "events": [ + { + "timeUnixNano": "1790968035109279000", + "name": "exception", + "attributes": [ + { + "key": "exception.type", + "value": { + "stringValue": "Exception" + } + }, + { + "key": "exception.message", + "value": { + "stringValue": "ParentCommand(Command(graph='red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor')" + } + }, + { + "key": "exception.stacktrace", + "value": { + "stringValue": "Exception: ParentCommand(Command(graph='red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': 'CAQS/REKEQgSGAI4AUIJbmFycmF0aW9uEgwFh3AVJZP3s8y1Hq0aDG76uhHONaScXAGShiIwGgjLXHUx1yZrkLPljjzTOQycpLJiKVwXcxm/EzKJm1s8M5WxuREWEldXcoaN0/msKpkRMT+eLb5ih9rAHULTomUNsUwJeu0jrJe4GLazy7sP5KtjEOEBKQsXUfoQ7fDkZOQUHZi9zzQN4hFNmYJUf3OVqf9TQNdC1+m//HAZPfWmAy6HtDvm7kgBJkCEoiFnm7tn/PX1hXGPRgWc6BTXUMr2WA8aKyqggRUbMH2+JYv5iWZddCc1up1Nbr3sF7WPcot9ZBhyHQXr692zeJk6SJgygIVrASbMly2bBxTWJB623gVgzpCmVSLZFpkKXgPcp8hGyDKOvF6SiQSHqGRxQofr7Vs1aPhfZixROJGD+MlrkggVAnGMyYIDUZpavtCeiU1JmBSz0084bXPtT/tnpsKOnSPYZQo3B0BXKbqA/WsKng8/V3Z8Uuajo6IVZ2hgA1WDduqQOQkExGU6pFuLhebIjuWxSNI/DffvR//LNqCfvdnf0hvoPtDxfx/SawIx4/spq9xbwFzHtLgoHg1F2wFw7clPDlg1PyD/v2yJG3V9T8GL6jGPE6rhfil/u4HNvf7BW0dQzCTTXcqZy4nByy0+p+S7ZxfMl4Kpxa2gOhhSNjfpfuX0QpL4kME8J1nliFN1d8KqEPuDI18BQHUhD/UfY29oA0x510FjM/BsLZ4n5sppkoIi7CFoQq2aAKVNfC1KilhIpRD+1dyDtZQklN8gZpOESHw6ML1TtU0yfAcbmqoxJ6hhjzwH6CMsTQEEy8MbRBM+QKKkIRdRCPHGFW2LkuR50+J0pF/tr6pqVvJeozfiMnrEilB27TZP4nKTJG8rd//vCWen0y7CA/8dBJ9gdp5tx7NVA45k1gdcxER1gYouNX3n1vG3/B1F4+93wXW9Mqo6Us59TQmrb9Nqa7pSQNSrH06w1GxyBAlkFfqAlafk16aMpq416TJYpGy43WCUiCcLWlhiWgz2sgOLAXP9a5weWAKRC8J6jkcUkDeXnW+HFSiPM6+9Bo6kVhLUhN5rc4mHZOZpF7ptPpsQN4XCqLPsqpRH/8o5XpyC6ZneTeF2ExtjhwZVjXDwMbIzVYIbw1y2PPGw8dC7pc4sIVSnI4oQAH0v650ghfhmMevWW4h4Pylbw/DG4fdeT3+8z0f8MOSTtfipx05/QttHlAvODRxa5yDCvOz6n3f1BO0N/4MbGyOM27qW4x8mBVoryUZWfsmhfi0/GfNvB8+ylTGbYNX27OcEF5WZtNqbWEy7V5GbmZUSxspcg7FBZ3j3/3L7muvZXoZi1f5erq4y3lSH+oF7qPFnvieyLOCwubcQy+oyowj4cD0idRecnp+s+52D7+mzF1gpW+f+cJasoxigbxkOloS4yeiKvgM4nWSpGEj12RPx5o80EmziXN9t4zJzW1htA5hXJJeFympMYtyCUCevRWVmrRYktQ7UnCa6tL/AVPi1ni5XCXHfLOuqfK5KLYxjwVtdhhfmCLvpaKVNCEOCf4nNGHqD98wUb0ejWNwDYBnJGkBRw9RVspfwNdoWoVcn2qv8ywGUp7yc/sk2LpI6VziRyvWqbGNG1ZJqVVutRc46+sOE4VSeS2/CTNKNa6NMCf/hxxaUVsYfKdP+S1Lc4ianKp0sUugPpmtoydC0CP2RwjnHLcnzxCnvqxlLQWXMNPTsu2yBcHlWJLtcmdg/McLagy7l5kG6sN7ZxJLD/kAx8E6uqohP+K/jMSrYuQJnhr4tf4biWFY3Jzf/KpAYyVSq+pbfFKXMbL9nHEoZQT15Wyabd6DMAq3QZOthM5pUzdNqUXkcrI1PwjASAg4dVU/2o+98mTXnyhP7VlEkTnddpwyJF+YCCc01pqa6ZX99pnR+YOpIrb5DtPcKq0t5cFCDyQxN1lUuqZcYujvX/GC7+6IpRTz/NkEY/5cntOfZJyd6SkUx/JR5AJIRPCNeib0rcWnnFn0XK8s22x40wLjEtufXDO9+yraf4kHxlBI3SB0meMjepX50CJhAx7NekkRFnwoecLfqIyrjXrgAZsTMPiX94snjdrzisAXtBKanulilSxOfW2HSmfnk0L2GXHJJ3S+vCbgREml9dekfmHhmwEYtv3kfhth7ERIwVT8j69OtIBCmeTIJuA7o73PXc1LJ2whuZK7FZe6NTOs61MP7JVlIc6tbhtOBk3NXU8pBPOCY6Q55d63FtpUU/KCbQ0K2WQ9o5jNGwNNJ6Cw5FDCt+x5YJeP1d2QzDSiq+cSZqwqCZVcNoAftGGzgrRZ4vkpbP0xQZHCtWsUwHVTjrY4NfRDjHdVPRn8J9Xtooc/hIWkqzFaczYTlapu2RCJqe8aEo3jzWZCEJ7AiBzBYraYDgOfeiQyeJUsbbXHdGKiiw22Bdp4M+Yz671MZ0ie9EWRks0Q2DHGUTne9S4tAAJPGbUf4xtCMoJ40Q4QW05QLSZy3wNFAUFYmXE4ECDFB8+IEeNFFF/tgAnfh8GvFh/1xY+LE+ozMminjSRwhq09zQAEkNFyu0IKgvDkyOI+iccF7doWLTUasPxLH1xGPBSKkeWCnSoX/4C2c9du66BbRXamHqae+VCiS6BN953iYKOu8rMkneW+TFjV0CzAf8PNG9LBayUgY5Uw9x0Sap6zI4PpaZKH4d9ktkFU+91yBbN5SRtdd8/EQatJXmBNfw7kRrll+LjwZweWLEb0jT1RpGuDqHLdLTMMgowSczrp2zCsJdQH/seaYrpwkCFR8dRjM7JRUkVa1A0SvdZAX75vuBvvLBzN2c+Rbt5oqy93lqIBIjKb7w2UkRTb4pBWcNKNPUgt3az/PxQxEasaltdmuyvsXYbur3VPNn8JzN/6J5N+QCnz571TccapCmkPvFE+gayXU+UF1VKYyFcUvlev7lsQlmjqzK2QA8X7Q3TzFapqhvJKlt7dzBHraqZBgPgb9N4oKNayi8FZT71+kaYhIhFrESKYRHfHkj5n3kfhgLy+x+jLDbKxMggkgHnJz9RuEHZXBWtkYAQ==', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': 'CAQSwgcKEAgSGAI4AUIIdGhpbmtpbmcSDORXge9uL1832RMQwBoMjQwAwAHb9iP1ojPGIjDDScal486beCJbtG8/D2Y9g9S5xIPfjoHg/dxwX5HypSQEBbjFiTSbPECXSFzV6YIq3wbLcmyPbvusGnDexFgx+3sIXzvqyFV/69xhihMnSpfTCHy0+0zSu1WpYU/WUpIfoaSXTcTa1qkM8x8Ek/y/1jkKMZUfDFa93uhUJxOC4+QgPWBl/+Xy2t82L2x/ebq7QLQTqtR0jXeaURQm3Co6JvOgWmDvMpEdTeTWE3fDh1tzzVKsflum4d89b6CaKtn8nlQd7RhN99vNQMQHG5V4OuVNdrHPZZpFOuhdejsMFWXyB+55slGAd8wEXgFKbI/knOXVGzL/NDF8Gty1tNZlu2fdSCAsYWMsFQP1cbwLeQGszyXzJMVZJ2I9xBPkyz1HOXCPyh5F+j2gRTPikVB3ARC6tfB/lDSUeKBVZPQS8pY/B4eCs+IjjaBNWruLzfqCsc6xL0CuQPSYyQXaYFjYrSRNcC70WQBWT5VVhp0mA9yZDGYbRZt9I5OK9QkQmuJ5zDFaMEOXzSrsC4lteP6MdimiMijvsH3iq+c6WUYolRj3neI88EaHIzLAGRq64BNCLzdAYL2pEU2sb5uG78PKVoUUCbVJL5jpDOhLOTO1bQsTuoUpnRRrLQD/kIzV+ljpVBwwfJcyq75TJA/CtPr/xr2SZ9B1b2sbjG6jD0lhtoCddeDgcqgl/LSSkcuaYY8xPWCy+LtNhcqThfmfvnHLJIpL6gjbjW/OQpRfVUwfw1jOb9bWVwcgHhNYfKYGPtM8oth5xwLYRRVgzqMKOvs7falXRhVzZ2SP6Iw0BMmAAZ6HjfCl9L+tPqJNlnQQOHpoWjum4B+XsYldFEKGQWQqsd59iNPvao9p/sCOt7rGqCozcmgiEm4w66ez/QIDyb46n0+tcNJPUcoBKvQ/jDwE6VwmkQ/nECjFp3UdDT+kWYQSNd8j8VBZOpG8LlqUYrEZCv0q7Bs1vcNrdYiaFoS32osaynWk+Ht3OHuFWbEF8JlsFTQAO05VvYkecf0V/oTHsG5hyOOs7UEaDFq7uaJuzWVhh5pAojIaBcR8fVln2PLRTX7is2nsA+QrdidePcZtFtgxAiKYe1i2sSFi4vm8EOkCbQ63wdQeY4Urr5PuoMEwxUULjgKagiAmsJDq4RrVm7sO4+6YuA9j6l2uylkOEc67vf/5fkXuCsiApNL6keb8c+vL0n4FXGdzj+apSDfFGBgB', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor'))Traceback (most recent call last):\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 707, in invoke\n input = context.run(step.invoke, input, config, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 3913, in invoke\n for chunk in self.stream(\n ~~~~~~~~~~~^\n input,\n ^^^^^^\n ...<11 lines>...\n **kwargs,\n ^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/main.py\", line 2967, in stream\n for _ in runner.tick(\n ~~~~~~~~~~~^\n [t for t in loop.tasks.values() if not t.writes],\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ...<2 lines>...\n schedule_task=loop.accept_push,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n ):\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_runner.py\", line 207, in tick\n run_with_retry(\n ~~~~~~~~~~~~~~^\n t,\n ^^\n ...<10 lines>...\n },\n ^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_retry.py\", line 617, in run_with_retry\n return task.proc.invoke(task.input, config)\n ~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 709, in invoke\n input = step.invoke(input, config)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/_internal/_runnable.py\", line 447, in invoke\n ret = self.func(*args, **kwargs)\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 84, in _write\n self.do_write(\n ~~~~~~~~~~~~~^\n config,\n ^^^^^^^\n writes,\n ^^^^^^^\n )\n ^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 126, in do_write\n write(_assemble_writes(writes))\n ~~~~~~~~~~~~~~~~^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/pregel/_write.py\", line 181, in _assemble_writes\n if ww := w.mapper(w.value):\n ~~~~~~~~^^^^^^^^^\n\n\n File \"/workspace/deeplite/.venv/lib/python3.13/site-packages/langgraph/graph/state.py\", line 1762, in _control_branch\n raise ParentCommand(command)\n\n\nlanggraph.errors.ParentCommand: Command(graph='red_team:15ccef64-4162-9e02-e87c-4cb0eb6ea16b', update={'messages': [HumanMessage(content='For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions.', additional_kwargs={}, response_metadata={}, id='46204305-f8ee-4384-9ce8-fcd80bfcdf75'), AIMessage(content=[{'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'caller': {'type': 'direct'}, 'input': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'name': 'web_search', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011Cfdw9aW9brenPqgybfNwP', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 2845, 'output_tokens': 73, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-21a3-7000-a381-284a6a0c03f7-0', tool_calls=[{'name': 'web_search', 'args': {'query': 'docs.python.org tuples immutable sequences lists mutable data structures tutorial'}, 'id': 'toolu_01B2LfHGDjYSFJhmiXNj4CuQ', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 2845, 'output_tokens': 73, 'total_tokens': 2918, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='[{\"title\": \"5. Data Structures \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like`insert`,`remove` or`sort` that only modify the list have no return value printed \\\\u2013 they return the default`None`. [1] This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n>>> t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n>>> v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of namedtuples). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like append() and extend().\"]}, {\"title\": \"3. Data model \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/reference/datamodel.html\", \"highlights\": [\"The value of some objects can change. Objects whose value can change are said to be mutable; objects whose value is unchangeable once they are created are called immutable. (The value of an immutable container object that contains a reference to a mutable object can change when the latter\\\\u2019s value is changed; however the container is still considered immutable, because the collection of objects it contains cannot be changed. So, immutability is not strictly the same as having an unchangeable value, it is more subtle.) An object\\\\u2019s mutability is determined by its type; for instance, numbers, strings and tuples are immutable, while dictionaries and lists are mutable.\\\\n...\\\\nSome objects contain references to other objects; these are called containers. Examples of containers are tuples, lists and dictionaries. The references are part of a container\\\\u2019s value. In most cases, when we talk about the value of a container, we imply the values, not the identities of the contained objects; however, when we talk about the mutability of a container, only the identities of the immediately contained objects are implied. So, if an immutable container (like a tuple) contains a reference to a mutable object, its value changes if that mutable object is changed.\\\\n...\\\\n### 3.2.5. Sequences\\\\u00b6\\\\n...\\\\n#### 3.2.5.1. Immutable sequences\\\\u00b6\\\\n\\\\nAn object of an immutable sequence type cannot change once it is created. (If the object contains references to other objects, these other objects may be mutable and may be changed; however, the collection of objects directly referenced by an immutable object cannot change.)\\\\n\\\\nThe following types are immutable sequences:\\\\n...\\\\nTuples\\\\n: The items of a `tuple` are arbitrary Python objects. Tuples of two or more items are formed by comma-separated lists of expressions. A tuple of one item (a \\\\u2018singleton\\\\u2019) can be formed by affixing a comma to an expression (an expression by itself does not create a tuple, since parentheses must be usable for grouping of expressions). An empty tuple can be formed by an empty pair of parentheses.\\\\n...\\\\n#### 3.2.5.2. Mutable sequences\\\\u00b6\\\\n\\\\nMutable sequences can be changed after they are created. The subscription and slicing notations can be used as the target of assignment and `del` (delete) statements.\\\\n...\\\\nThere are currently two intrinsic mutable sequence types:\\\\n\\\\nLists\\\\n: The items of a list are arbitrary Python objects. Lists are formed by placing a comma-separated list of expressions in square brackets. (Note that there are no special cases needed to form lists of length 0 or 1.)\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.7 documentation\", \"url\": \"https://docs.python.org/3/builtins/stdtypes.html\", \"highlights\": [\"collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and range objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... mutable and immutable. The `collections. ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\nmutable sequence types is\\\\n...\\\\nsupport allows immutable sequences, ... , to be used as `dict` keys and stored in ... enset` instances\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\ntuple(iterable=\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"Built-in Types \\\\u2014 Python 3.14.5 documentation\", \"url\": \"https://docs.python.org/3/library/stdtypes.html\", \"highlights\": [\"Some collection classes are mutable. The methods that add, subtract, or rearrange their ... in place, and don\\\\u2019t return a ... , never return the collection instance itself but `None`.\\\\n...\\\\n## Sequence Types \\\\u2014 `list`, `tuple`, `range`\\\\u00b6\\\\n\\\\nThere are three basic sequence types: lists, tuples, and ... objects. Additional sequence types tailored for processing of binary data and text strings are described in dedicated sections.\\\\n...\\\\nThe operations in the following table ... immutable. The ` ... is provided to make ... easier to correctly implement these operations on custom sequence types\\\\n...\\\\n### Immutable Sequence Types\\\\u00b6\\\\n...\\\\noperation that immutable sequence ... by mutable sequence types is ... `hash()`\\\\n...\\\\nThis support allows immutable sequences, such as `tuple` instances, to be used as `dict` keys and stored in `set` and `frozenset` instances.\\\\n...\\\\n### Mutable Sequence Types\\\\u00b6\\\\n...\\\\n### Lists\\\\u00b6\\\\n\\\\nLists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application).\\\\n...\\\\n### Tuples\\\\u00b6\\\\n\\\\nTuples are immutable sequences, typically used to store collections of heterogeneous data (such as the 2-tuples produced by the `enumerate()` built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a `set` or `dict` instance).\\\\n...\\\\nThe constructor builds a tuple whose items are the same and in the same order as iterable\\\\u2019s items. iterable may be either a sequence, a container that supports iteration, or an iterator object. If iterable is already a tuple, it is returned unchanged. For example, `tuple(\\'abc\\')` returns `(\\'a\\', \\'b\\', \\'c\\')` and `tuple( [1, 2, 3] )` returns `(1, 2, 3)`. If no argument is given, the constructor creates a new empty tuple, `()`.\\\\n...\\\\nTuples implement all of the common sequence operations.\\\\n...\\\\nFor heterogeneous collections of data where access by name is clearer than access by index, `collections.namedtuple()` may be a more appropriate choice than a simple tuple object.\"]}, {\"title\": \"5. Data Structures \\\\u2014 Python 3.10.20 documentation\", \"url\": \"https://docs.python.org/3.10/tutorial/datastructures.html\", \"highlights\": [\"You might have noticed that methods like `insert`, `remove` or `sort` that only modify the list have no return value printed \\\\u2013 they return the default `None`. 1 This is a design principle for all mutable data structures in Python.\\\\n...\\\\n## 5.3. Tuples and Sequences\\\\u00b6\\\\n\\\\nWe saw that lists and strings have many common properties, such as indexing and slicing operations. They are two examples of sequence data types (see Sequence Types \\\\u2014 list, tuple, range). Since Python is an evolving language, other sequence data types may be added. There is also another standard sequence data type: the tuple.\\\\n\\\\nA tuple consists of a number of values separated by commas, for instance:\\\\n...\\\\n>>> # Tuples are immutable:\\\\n... t[0] = 88888\\\\nTraceback (most recent call last):\\\\n File \\\\\"\\\\\", line 1, in \\\\nTypeError: \\'tuple\\' object does not support item assignment\\\\n>>> # but they can contain mutable objects:\\\\n... v = ([1, 2, 3], [3, 2, 1])\\\\n>>> v\\\\n([1, 2, 3], [3, 2, 1])\\\\n...\\\\nAs you see, on output tuples are always enclosed in parentheses, so that nested tuples are interpreted correctly; they may be input with or without surrounding parentheses, although often parentheses are necessary anyway (if the tuple is part of a larger expression). It is not possible to assign to the individual items of a tuple, however it is possible to create tuples which contain mutable objects, such as lists.\\\\n\\\\nThough tuples may seem similar to lists, they are often used in different situations and for different purposes. Tuples are immutable, and usually contain a heterogeneous sequence of elements that are accessed via unpacking (see later in this section) or indexing (or even by attribute in the case of `namedtuples`). Lists are mutable, and their elements are usually homogeneous and are accessed by iterating over the list.\\\\n...\\\\n## 5.4.\\\\n...\\\\n. Set objects\\\\n...\\\\n## 5.5. Dictionaries\\\\u00b6\\\\n\\\\nAnother useful data type built into Python is the dictionary (see Mapping Types \\\\u2014 dict). Dictionaries are sometimes found in other languages as \\\\u201cassociative memories\\\\u201d or \\\\u201cassociative arrays\\\\u201d. Unlike sequences, which are indexed by a range of numbers, dictionaries are indexed by keys, which can be any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can\\\\u2019t use lists as keys, since lists can be modified in place using index assignments, slice assignments, or methods like `append()` and `extend()`.\"]}]', name='web_search', id='6e5125ac-3164-4a76-9c52-ac3460ce36e4', tool_call_id='toolu_01B2LfHGDjYSFJhmiXNj4CuQ'), AIMessage(content=[{'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_skeptic', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwA6F4cCN5yhD4Crs9M', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7378, 'output_tokens': 33, 'output_tokens_details': {'thinking_tokens': 0}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='researcher', id='lc_run--01a0fe03-3cd8-79f1-88a1-ce6cee294e79-0', tool_calls=[{'name': 'transfer_to_skeptic', 'args': {}, 'id': 'toolu_01Xjj3aRdWyhBJfPmTJBxQa9', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7378, 'output_tokens': 33, 'total_tokens': 7411, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 0}}), ToolMessage(content='Successfully transferred to skeptic', name='transfer_to_skeptic', id='389058d1-083f-4632-bbc5-09bfd3a0ffd2', tool_call_id='toolu_01Xjj3aRdWyhBJfPmTJBxQa9'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_verifier', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAMRdS21FeJfzQhM3s', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7396, 'output_tokens': 770, 'output_tokens_details': {'thinking_tokens': 739}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='skeptic', id='lc_run--01a0fe03-4ae9-76c0-89a6-4f0b114e3030-0', tool_calls=[{'name': 'transfer_to_verifier', 'args': {}, 'id': 'toolu_01H6fV8JvRJNvXy47eRnd3jH', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7396, 'output_tokens': 770, 'total_tokens': 8166, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 739}}), ToolMessage(content='Successfully transferred to verifier', name='transfer_to_verifier', id='c064563a-974f-4f0f-ab4a-080e63c01cf5', tool_call_id='toolu_01H6fV8JvRJNvXy47eRnd3jH'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_red_team', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAsabDquegHi6YUpCn', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7509, 'output_tokens': 88, 'output_tokens_details': {'thinking_tokens': 55}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='verifier', id='lc_run--01a0fe03-6682-7d21-8c15-ffbce9422c9f-0', tool_calls=[{'name': 'transfer_to_red_team', 'args': {}, 'id': 'toolu_01XEAuhQHCBdyCwtymZwFfDi', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7509, 'output_tokens': 88, 'total_tokens': 7597, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 55}}), ToolMessage(content='Successfully transferred to red_team', name='transfer_to_red_team', id='982c0126-e6ab-458a-922e-7b266e83c2b2', tool_call_id='toolu_01XEAuhQHCBdyCwtymZwFfDi'), AIMessage(content=[{'signature': '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', 'thinking': '', 'type': 'thinking'}, {'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'caller': {'type': 'direct'}, 'input': {}, 'name': 'transfer_to_editor', 'type': 'tool_use', 'toolset_name': None}], additional_kwargs={}, response_metadata={'id': 'msg_011CfdwAzfjqUopoEmZLaqm1', 'container': None, 'diagnostics': None, 'model': 'claude-sonnet', 'stop_details': None, 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'cache_creation': {'ephemeral_1h_input_tokens': 0, 'ephemeral_5m_input_tokens': 0}, 'cache_creation_input_tokens': 0, 'cache_read_input_tokens': 0, 'inference_geo': 'global', 'input_tokens': 7416, 'output_tokens': 151, 'output_tokens_details': {'thinking_tokens': 119}, 'server_tool_use': None, 'service_tier': 'standard'}, 'model_name': 'claude-sonnet', 'model_provider': 'anthropic'}, name='red_team', id='lc_run--01a0fe03-6ce6-7251-b796-4f64333f67c6-0', tool_calls=[{'name': 'transfer_to_editor', 'args': {}, 'id': 'toolu_01VBrWdWEWYgit4kNYehBMU5', 'type': 'tool_call'}], invalid_tool_calls=[], usage_metadata={'input_tokens': 7416, 'output_tokens': 151, 'total_tokens': 7567, 'input_token_details': {'cache_read': 0, 'cache_creation': 0, 'ephemeral_5m_input_tokens': 0, 'ephemeral_1h_input_tokens': 0}, 'output_token_details': {'reasoning': 119}}), ToolMessage(content='Successfully transferred to editor', name='transfer_to_editor', tool_call_id='toolu_01VBrWdWEWYgit4kNYehBMU5')], 'active_agent': 'editor'}, goto='editor')\n" + } + }, + { + "key": "exception.escaped", + "value": { + "stringValue": "False" + } + } + ] + } + ], + "status": { + "code": 1 + }, + "flags": 256 + } + ] + } + ] + }, + { + "resource": { + "attributes": [ + { + "key": "telemetry.sdk.language", + "value": { + "stringValue": "python" + } + }, + { + "key": "telemetry.sdk.name", + "value": { + "stringValue": "opentelemetry" + } + }, + { + "key": "telemetry.sdk.version", + "value": { + "stringValue": "1.45.0" + } + }, + { + "key": "service.instance.id", + "value": { + "stringValue": "b873df4c-5106-4097-a20b-b9380724f4d9" + } + }, + { + "key": "service.name", + "value": { + "stringValue": "deeplite" + } + } + ] + }, + "scopeSpans": [ + { + "scope": { + "name": "langsmith" + }, + "spans": [ + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "47f7607ab58c542f", + "parentSpanId": "4809a44f637a7046", + "name": "tools", + "kind": 1, + "startTimeUnixNano": "1790968039092067840", + "endTimeUnixNano": "1790968039095913984", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__pregel_push\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_push\",0,false]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|tools:4fd8a45a-13d9-1c55-5033-6f6d90c107c0" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "editor" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:2" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "eyJtZXNzYWdlcyI6W3siY29udGVudCI6IlVwZGF0ZWQgZmlsZSAvYW5zd2VyLm1kIiwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6e30sInR5cGUiOiJ0b29sIiwibmFtZSI6IndyaXRlX2ZpbGUiLCJpZCI6ImUzNDkyZTA4LWM4NjktNDdlYy1hNWY3LWNjNTdlYTVmNjQwMyIsInRvb2xfY2FsbF9pZCI6InRvb2x1XzAxQm04QVU5RXNRVXdxb1ZMWXB4S0E3NyIsInN0YXR1cyI6InN1Y2Nlc3MifV19" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "848c01c3433c72af", + "parentSpanId": "47f7607ab58c542f", + "name": "FilesystemMiddleware.wrap_tool_call", + "kind": 1, + "startTimeUnixNano": "1790968039093334016", + "endTimeUnixNano": "1790968039095428096", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "FilesystemMiddleware.wrap_tool_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__pregel_push\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_push\",0,false]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|tools:4fd8a45a-13d9-1c55-5033-6f6d90c107c0" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "editor" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "eyJjb250ZW50IjoiVXBkYXRlZCBmaWxlIC9hbnN3ZXIubWQiLCJhZGRpdGlvbmFsX2t3YXJncyI6e30sInJlc3BvbnNlX21ldGFkYXRhIjp7fSwidHlwZSI6InRvb2wiLCJuYW1lIjoid3JpdGVfZmlsZSIsInRvb2xfY2FsbF9pZCI6InRvb2x1XzAxQm04QVU5RXNRVXdxb1ZMWXB4S0E3NyIsInN0YXR1cyI6InN1Y2Nlc3MifQ==" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "cfb36a1a28ffc485", + "parentSpanId": "848c01c3433c72af", + "name": "write_file", + "kind": 1, + "startTimeUnixNano": "1790968039094265088", + "endTimeUnixNano": "1790968039095307008", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "tool" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "write_file" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "execute_tool" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "gen_ai.tool.name", + "value": { + "stringValue": "write_file" + } + }, + { + "key": "gen_ai.tool.call.id", + "value": { + "stringValue": "toolu_01Bm8AU9EsQUwqoVLYpxKA77" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "tools" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"__pregel_push\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_push\",0,false]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|tools:4fd8a45a-13d9-1c55-5033-6f6d90c107c0" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "editor" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "seq:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "eyJmaWxlX3BhdGgiOiIvYW5zd2VyLm1kIiwiY29udGVudCI6IioqVHVwbGUgdnMuIGxpc3QgaW1tdXRhYmlsaXR5IChQeXRob24pKipcblxuQSB0dXBsZSBpcyBpbW11dGFibGU6IG9uY2UgY3JlYXRlZCwgeW91IGNhbid0IGFzc2lnbiB0byBpdHMgaXRlbXMsIGFuZCB0aGUgY29sbGVjdGlvbiBvZiBvYmplY3RzIGl0IHJlZmVyZW5jZXMgY2FuJ3QgY2hhbmdlLiBgdFswXSA9IDFgIHJhaXNlcyBgVHlwZUVycm9yYC4gQSBsaXN0IGlzIG11dGFibGU6IHlvdSBjYW4gY2hhbmdlIGl0IGluIHBsYWNlIHdpdGggaW5kZXggb3Igc2xpY2UgYXNzaWdubWVudCwgYGFwcGVuZCgpYCwgYGV4dGVuZCgpYCwgYHNvcnQoKWAgYW5kIHNpbWlsYXIgbWV0aG9kcy5cblxuVHVwbGUgaW1tdXRhYmlsaXR5IGlzIHNoYWxsb3cuIElmIGEgdHVwbGUgaG9sZHMgYSBtdXRhYmxlIG9iamVjdCwgc3VjaCBhcyBhIGxpc3QsIHRoYXQgaW5uZXIgb2JqZWN0IGNhbiBzdGlsbCBjaGFuZ2UsIGFuZCBzbyB0aGUgdHVwbGUncyB2YWx1ZSBjaGFuZ2VzLiBCZWNhdXNlIG9mIHRoaXMsIGEgdHVwbGUgY2FuIGJlIGEgYGRpY3RgIGtleSBvciBgc2V0YCBtZW1iZXIgb25seSBpZiBldmVyeXRoaW5nIGluc2lkZSBpdCBpcyBoYXNoYWJsZS4gQSBsaXN0IGNhbiBuZXZlciBiZSBhIGtleS5cblxuU291cmNlczpcbi0gaHR0cHM6Ly9kb2NzLnB5dGhvbi5vcmcvMy90dXRvcmlhbC9kYXRhc3RydWN0dXJlcy5odG1sXG4tIGh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvcmVmZXJlbmNlL2RhdGFtb2RlbC5odG1sXG4tIGh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvbGlicmFyeS9zdGR0eXBlcy5odG1sXG4ifQ==" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "eyJvdXRwdXQiOnsiY29udGVudCI6IlVwZGF0ZWQgZmlsZSAvYW5zd2VyLm1kIiwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6e30sInR5cGUiOiJ0b29sIiwibmFtZSI6IndyaXRlX2ZpbGUiLCJ0b29sX2NhbGxfaWQiOiJ0b29sdV8wMUJtOEFVOUVzUVV3cW9WTFlweEtBNzciLCJzdGF0dXMiOiJzdWNjZXNzIn19" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "d1e910014914b0a2", + "parentSpanId": "4809a44f637a7046", + "name": "model", + "kind": 1, + "startTimeUnixNano": "1790968035043832064", + "endTimeUnixNano": "1790968039091361024", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|model:5f0cee1e-bfe5-1171-9153-91c4b775587c" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "editor" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "fc98979761fe2c4e", + "parentSpanId": "d1e910014914b0a2", + "name": "FilesystemMiddleware.wrap_model_call", + "kind": 1, + "startTimeUnixNano": "1790968035044310016", + "endTimeUnixNano": "1790968039090991104", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "FilesystemMiddleware.wrap_model_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|model:5f0cee1e-bfe5-1171-9153-91c4b775587c" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "editor" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "eyJvdXRwdXQiOnsicmVzdWx0IjpbeyJjb250ZW50IjpbeyJzaWduYXR1cmUiOiJDQVFTNWdZS0VBZ1NHQUk0QVVJSWRHaHBibXRwYm1jU0RJNFFJYjdMMnc1YVczY00vUm9NTGkyd0V4RGtxaHV4SkRpWUlqQXFHeE00V1V3aXE0dVpIcmlDYnVDNGtWd2E3aWdkVUxvb2NaYmk1ZmV2S2Jmd3FIU2JyTE5UNTFOR1g0WHNMdHNxZ3dZL3RhYkhqbGx6cXU3blJXdjgrRno0UjZuOWphN0NwajI0WnV4RnVLa2tRT0JtQTRUZjFhcGszUlBxY0VRK2ord2VkdTBsTytyZEVDeWQzbFhoZmdFUkZGcWNNNmF1Y3hlbDRSYnc1b0FIWHU5K1hlVHR6bCtOOHRBZVo5aUdaMlhUdFU1T2I4YVBUMUt1WCt1cDhrUTRWVVhrQlRmZDJmNUpQOVJ4WkVxOXdTWWFac3lIZHYwbisxVTQ2QU9zdktabXA5UVhCd28yZjRPOTBqUDhlZ2lyZW05RWJaYm1hWU9KOFdLN0N0S1JWYlkyeTQrOXhSVUowNG5zZEl6NUY1RkZLRXh4Tk9yQjRtYy9ORTgzYWIzWjY0aVd6T3dxb1VHQUdRU2thSDBkNWNFdW1abzRmWlpBaFB5dUplUUR4dWxNQ2V3bjdFR0NucEp3L256aTB3b3lFYVFMNFk3aDk5UDdhWHhGcjI4cDVLQ3lKRUpURGVmZUlwVmxBd01DQWp6K3hDNjlBQUxtd3lUUStjRkVNK0tBZ2VJU3BoTFZ5OEFQcjJGU2hheEJOclhRZ3oxczlzMmRoTFpRT0Jpd3poeG1FZ2RLNys4SmFxaEIwZUVFZC8xUlZBdUlZZGV6QTVIQnJ3RTlEeVFpQ2wzVU9zYlNuTkVWZStnckhwNXAzdG1NQnE2OGdMVjgyb0F6RllabCtDZXd4NzF2NWRQRk92S1BFSFV6cFFZT1ZMcm5CMUVaUllyWno3Mm4yd2ZTVnhCT3pwVGNuQnhWNkhlZENQeUl6S1haTTkreUVlVEppOFF0dlZnWjF3K3YwaG1DRkdwbm1aTjdtWGxncUwxczZNWFZ5ZHBQT0tQbE0zTmE3Q2RIblBGWWl3cjJ6THZra2NJTTdDc2svQzMrWk1BV1RLK0M5QjF2Ykd4UGx0RTNPdjhrTzk4UGdTWG0xQUp1RWJYeStyM2EzRDNRbFpKM2RFS2UyTE5kQUJ5clBNaFNjS1U4R2xmSC85TnRncmh0YWtnbGxEL01mQWxUc2JOd05EclV0V1J4bUR1Si8wWitoa2svWU53RURZQVphOFRtd1ZvV09kQkhwUlBIdlo5RTl1c2V1bHRtYStKazFnUkxEdHZFWmtxWFVFU2tNY3FVdFZ3WU01YWpKQTVONTJjTmlaMTVCVGY4WGpHaEtXZE9WNDArOEgwUE9TeE0ySmlmd0NPMEM1eEZXNUJvM0lpSU52MFVPdFk1ZjhrdlBkTTNQamtoYU9ySzF5VEE4ZUVFNDR2dW5MOVBrb0dlY2JZbStYRTVLekwzUXNFbjJZMUlKd085dzB4SFhRWkVlaVA1KzB1M1luRGM4cTlkQkxoR1czRnkzMGdZQVE9PSIsInRoaW5raW5nIjoiIiwidHlwZSI6InRoaW5raW5nIn0seyJpZCI6InRvb2x1XzAxQm04QVU5RXNRVXdxb1ZMWXB4S0E3NyIsImNhbGxlciI6eyJ0eXBlIjoiZGlyZWN0In0sImlucHV0Ijp7ImZpbGVfcGF0aCI6Ii9hbnN3ZXIubWQiLCJjb250ZW50IjoiKipUdXBsZSB2cy4gbGlzdCBpbW11dGFiaWxpdHkgKFB5dGhvbikqKlxuXG5BIHR1cGxlIGlzIGltbXV0YWJsZTogb25jZSBjcmVhdGVkLCB5b3UgY2FuJ3QgYXNzaWduIHRvIGl0cyBpdGVtcywgYW5kIHRoZSBjb2xsZWN0aW9uIG9mIG9iamVjdHMgaXQgcmVmZXJlbmNlcyBjYW4ndCBjaGFuZ2UuIGB0WzBdID0gMWAgcmFpc2VzIGBUeXBlRXJyb3JgLiBBIGxpc3QgaXMgbXV0YWJsZTogeW91IGNhbiBjaGFuZ2UgaXQgaW4gcGxhY2Ugd2l0aCBpbmRleCBvciBzbGljZSBhc3NpZ25tZW50LCBgYXBwZW5kKClgLCBgZXh0ZW5kKClgLCBgc29ydCgpYCBhbmQgc2ltaWxhciBtZXRob2RzLlxuXG5UdXBsZSBpbW11dGFiaWxpdHkgaXMgc2hhbGxvdy4gSWYgYSB0dXBsZSBob2xkcyBhIG11dGFibGUgb2JqZWN0LCBzdWNoIGFzIGEgbGlzdCwgdGhhdCBpbm5lciBvYmplY3QgY2FuIHN0aWxsIGNoYW5nZSwgYW5kIHNvIHRoZSB0dXBsZSdzIHZhbHVlIGNoYW5nZXMuIEJlY2F1c2Ugb2YgdGhpcywgYSB0dXBsZSBjYW4gYmUgYSBgZGljdGAga2V5IG9yIGBzZXRgIG1lbWJlciBvbmx5IGlmIGV2ZXJ5dGhpbmcgaW5zaWRlIGl0IGlzIGhhc2hhYmxlLiBBIGxpc3QgY2FuIG5ldmVyIGJlIGEga2V5LlxuXG5Tb3VyY2VzOlxuLSBodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL3R1dG9yaWFsL2RhdGFzdHJ1Y3R1cmVzLmh0bWxcbi0gaHR0cHM6Ly9kb2NzLnB5dGhvbi5vcmcvMy9yZWZlcmVuY2UvZGF0YW1vZGVsLmh0bWxcbi0gaHR0cHM6Ly9kb2NzLnB5dGhvbi5vcmcvMy9saWJyYXJ5L3N0ZHR5cGVzLmh0bWxcbiJ9LCJuYW1lIjoid3JpdGVfZmlsZSIsInR5cGUiOiJ0b29sX3VzZSIsInRvb2xzZXRfbmFtZSI6bnVsbH1dLCJhZGRpdGlvbmFsX2t3YXJncyI6e30sInJlc3BvbnNlX21ldGFkYXRhIjp7ImlkIjoibXNnXzAxMUNmZHdCQmFhOWdqTUNjZTE2VFVlbiIsImNvbnRhaW5lciI6bnVsbCwiZGlhZ25vc3RpY3MiOm51bGwsIm1vZGVsIjoiY2xhdWRlLXNvbm5ldCIsInN0b3BfZGV0YWlscyI6bnVsbCwic3RvcF9yZWFzb24iOiJ0b29sX3VzZSIsInN0b3Bfc2VxdWVuY2UiOm51bGwsInVzYWdlIjp7ImNhY2hlX2NyZWF0aW9uIjp7ImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjB9LCJjYWNoZV9jcmVhdGlvbl9pbnB1dF90b2tlbnMiOjAsImNhY2hlX3JlYWRfaW5wdXRfdG9rZW5zIjowLCJpbmZlcmVuY2VfZ2VvIjoiZ2xvYmFsIiwiaW5wdXRfdG9rZW5zIjo4MTI3LCJvdXRwdXRfdG9rZW5zIjo0MzMsIm91dHB1dF90b2tlbnNfZGV0YWlscyI6eyJ0aGlua2luZ190b2tlbnMiOjc5fSwic2VydmVyX3Rvb2xfdXNlIjpudWxsLCJzZXJ2aWNlX3RpZXIiOiJzdGFuZGFyZCJ9LCJtb2RlbF9uYW1lIjoiY2xhdWRlLXNvbm5ldCIsIm1vZGVsX3Byb3ZpZGVyIjoiYW50aHJvcGljIn0sInR5cGUiOiJhaSIsIm5hbWUiOiJlZGl0b3IiLCJpZCI6ImxjX3J1bi0tMDFhMGZlMDMtNzZlOS03Y2EzLWE1ZmYtNjNkZTY2ZGQ4ZGQxLTAiLCJ0b29sX2NhbGxzIjpbeyJuYW1lIjoid3JpdGVfZmlsZSIsImFyZ3MiOnsiZmlsZV9wYXRoIjoiL2Fuc3dlci5tZCIsImNvbnRlbnQiOiIqKlR1cGxlIHZzLiBsaXN0IGltbXV0YWJpbGl0eSAoUHl0aG9uKSoqXG5cbkEgdHVwbGUgaXMgaW1tdXRhYmxlOiBvbmNlIGNyZWF0ZWQsIHlvdSBjYW4ndCBhc3NpZ24gdG8gaXRzIGl0ZW1zLCBhbmQgdGhlIGNvbGxlY3Rpb24gb2Ygb2JqZWN0cyBpdCByZWZlcmVuY2VzIGNhbid0IGNoYW5nZS4gYHRbMF0gPSAxYCByYWlzZXMgYFR5cGVFcnJvcmAuIEEgbGlzdCBpcyBtdXRhYmxlOiB5b3UgY2FuIGNoYW5nZSBpdCBpbiBwbGFjZSB3aXRoIGluZGV4IG9yIHNsaWNlIGFzc2lnbm1lbnQsIGBhcHBlbmQoKWAsIGBleHRlbmQoKWAsIGBzb3J0KClgIGFuZCBzaW1pbGFyIG1ldGhvZHMuXG5cblR1cGxlIGltbXV0YWJpbGl0eSBpcyBzaGFsbG93LiBJZiBhIHR1cGxlIGhvbGRzIGEgbXV0YWJsZSBvYmplY3QsIHN1Y2ggYXMgYSBsaXN0LCB0aGF0IGlubmVyIG9iamVjdCBjYW4gc3RpbGwgY2hhbmdlLCBhbmQgc28gdGhlIHR1cGxlJ3MgdmFsdWUgY2hhbmdlcy4gQmVjYXVzZSBvZiB0aGlzLCBhIHR1cGxlIGNhbiBiZSBhIGBkaWN0YCBrZXkgb3IgYHNldGAgbWVtYmVyIG9ubHkgaWYgZXZlcnl0aGluZyBpbnNpZGUgaXQgaXMgaGFzaGFibGUuIEEgbGlzdCBjYW4gbmV2ZXIgYmUgYSBrZXkuXG5cblNvdXJjZXM6XG4tIGh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvdHV0b3JpYWwvZGF0YXN0cnVjdHVyZXMuaHRtbFxuLSBodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL3JlZmVyZW5jZS9kYXRhbW9kZWwuaHRtbFxuLSBodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL2xpYnJhcnkvc3RkdHlwZXMuaHRtbFxuIn0sImlkIjoidG9vbHVfMDFCbThBVTlFc1FVd3FvVkxZcHhLQTc3IiwidHlwZSI6InRvb2xfY2FsbCJ9XSwiaW52YWxpZF90b29sX2NhbGxzIjpbXSwidXNhZ2VfbWV0YWRhdGEiOnsiaW5wdXRfdG9rZW5zIjo4MTI3LCJvdXRwdXRfdG9rZW5zIjo0MzMsInRvdGFsX3Rva2VucyI6ODU2MCwiaW5wdXRfdG9rZW5fZGV0YWlscyI6eyJjYWNoZV9yZWFkIjowLCJjYWNoZV9jcmVhdGlvbiI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MH0sIm91dHB1dF90b2tlbl9kZXRhaWxzIjp7InJlYXNvbmluZyI6Nzl9fX1dLCJzdHJ1Y3R1cmVkX3Jlc3BvbnNlIjpudWxsfX0=" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "4bd8ddfd6bc728ed", + "parentSpanId": "fc98979761fe2c4e", + "name": "UnsupportedContentMiddleware.wrap_model_call", + "kind": 1, + "startTimeUnixNano": "1790968035044775936", + "endTimeUnixNano": "1790968039090832896", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "UnsupportedContentMiddleware.wrap_model_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|model:5f0cee1e-bfe5-1171-9153-91c4b775587c" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "editor" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "e90628af060558bc", + "parentSpanId": "4bd8ddfd6bc728ed", + "name": "ChatAnthropic", + "kind": 1, + "startTimeUnixNano": "1790968035049609984", + "endTimeUnixNano": "1790968039090351104", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chat" + } + }, + { + "key": "gen_ai.serialized.name", + "value": { + "stringValue": "ChatAnthropic" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "llm" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "ChatAnthropic" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "anthropic" + } + }, + { + "key": "gen_ai.request.model", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "gen_ai.tool.definitions", + "value": { + "stringValue": "[{\"name\":\"ls\",\"input_schema\":{\"properties\":{\"path\":{\"description\":\"Absolute path to the directory to list. Must be absolute, not relative.\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"description\":\"Lists all files in a directory.\\n\\nThis is useful for exploring the filesystem and finding the right file to read or edit.\\nYou should almost ALWAYS use this tool before using the read_file or edit_file tools.\"},{\"name\":\"read_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path to the file to read. Must be absolute, not relative.\",\"type\":\"string\"},\"offset\":{\"default\":0,\"description\":\"Line number to start reading from (0-indexed). Use for pagination of large files.\",\"type\":\"integer\"},\"limit\":{\"default\":100,\"description\":\"Maximum number of lines to read. Use for pagination of large files.\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"description\":\"Reads a file from the filesystem. Assume any path the user provides is valid; reading a missing file returns an error.\\n\\nUsage:\\n- By default, it reads up to 100 lines starting from the beginning of the file. Use `offset`/`limit` to page through large files instead of reading them whole.\\n- A status header, `@@ field | field | ... @@`, sits above the file content, and every line after it is verbatim file content. When content is truncated, there may be an explanation before the header. Never include the header when editing.\\n- Speculatively batch multiple `read_file` calls in one response when several files may be useful.\\n- An empty file returns a system-reminder warning in place of contents.\\n- Large tool results may be offloaded to a file; the tool message gives the path. Read that path here, paging with `offset`/`limit`.\\n- Images (`.png`, `.jpg`, etc.), audio, video, and PDFs return multimodal content blocks (https://docs.langchain.com/oss/python/langchain/messages#multimodal).\\n- For images and PDFs, pagination via `offset`/`limit` is text-only - supply `file_path` only\\n- Always read a file before editing it.\"},{\"name\":\"write_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path where the file should be written. Must be absolute, not relative.\",\"type\":\"string\"},\"content\":{\"description\":\"The text content to write to the file. This parameter is required.\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"description\":\"Writes content to a file. Creates the file if it does not exist; replaces it entirely if it does.\\n\\nUsage:\\n- Use this tool when you intend to create a new file or replace the whole file. You do not need to read the file first.\\n- Prefer to edit existing files (with the edit_file tool) over creating new ones when possible.\"},{\"name\":\"edit_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path to the file to edit. Must be absolute, not relative.\",\"type\":\"string\"},\"old_string\":{\"description\":\"The exact text to find and replace. Must be unique in the file unless replace_all is True.\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace old_string with. Must be different from old_string.\",\"type\":\"string\"},\"replace_all\":{\"default\":false,\"description\":\"If True, replace all occurrences of old_string. If False (default), old_string must be unique.\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"description\":\"Performs exact string replacements in files.\\n\\nUsage:\\n- You must read the file before editing; this tool errors otherwise.\\n- Preserve the exact source indentation from the read output, and never include the read status header in old_string or new_string.\\n- Prefer editing an existing file over creating a new one.\\n- Only use emojis if the user explicitly requests it.\"},{\"name\":\"glob\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Glob pattern to match files (e.g., '*.py', '**/*.py', '/subdir/**/*.md'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path; a leading '/' anchors to the search root ('/*.py' matches only top-level files). Leading-dot names are excluded unless the pattern segment starts with '.', so prefer the bare form '*.py' over '**/*.py' -- '**' will not descend into dot-directories like '.github'.\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Base directory to search from. Defaults to the backend's default root.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Find files matching a glob pattern, returning absolute paths.\\n\\nSupports `*` (any characters within a path segment), `**` (any directories), `?` (single character), `[abc]` (one character from a set), and `{a,b}` (alternatives), e.g. `*.py`, `src/**/*.py`, `*.{yml,yaml}`.\\n\\nA pattern without `/` matches the file name at any depth under the search root (`*.py` matches `src/app/main.py`). A pattern containing `/` matches the search-root-relative path (`src/**/*.py`). A leading `/` anchors to the search root (`/*.py` matches only top-level Python files).\\n\\nLeading-dot names are only matched when the pattern segment itself starts with `.` (use `.env`, or `.github/**/*.yml`). Because `**` will not descend into dot-directories, the bare form `*.yml` is *broader* than `**/*.yml` and is usually what you want.\"},{\"name\":\"grep\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Text pattern to search for (literal string, not regex).\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Directory to search in. Defaults to current working directory.\"},\"glob\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Glob pattern (NOT regex) limiting which files are searched (e.g. '*.py', '*.ts'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path (e.g. 'src/**/*.py'). This is an in-tool file filter, not a call to the separate glob tool. Brace expansion (e.g. '*.{ts,tsx}') is not supported on all backends; run a separate search per extension for reliable results.\"},\"output_mode\":{\"default\":\"files_with_matches\",\"description\":\"Shape of the returned text. 'files_with_matches' (default): newline-separated matching file paths. 'content': matching lines grouped by file under a ':' header, each line indented and formatted ': ' (only the matched line, no surrounding context). 'count': one ': ' line per file.\",\"enum\":[\"files_with_matches\",\"content\",\"count\"],\"type\":\"string\"},\"max_count\":{\"anyOf\":[{\"exclusiveMinimum\":0,\"type\":\"integer\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Optional cap on the total number of matches returned across all files. Leave unset to use the configured default. When the cap is hit, results are truncated and a note says so; narrow the pattern or path to see the rest.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Search for a LITERAL text pattern across files (NOT regex).\\n\\nThe pattern is matched verbatim: regex metacharacters are ordinary characters, not operators. To match any of several strings, run a separate grep for each; `grep(pattern=\\\"foo|bar\\\")` searches for the literal text \\\"foo|bar\\\", and `.*` or `\\\\.` match those characters literally.\\n\\nReturns matching files or content per `output_mode`. Offloaded large tool results live under the artifacts root (`/large_tool_results/` by default); grep that directory to search them when you do not know the exact path.\"},{\"name\":\"transfer_to_researcher\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Request missing evidence from the researcher\"},{\"name\":\"transfer_to_skeptic\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Request another critique from the skeptic\"},{\"name\":\"transfer_to_verifier\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Request another source check from the verifier\"}]" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_chat_model" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "1" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|model:5f0cee1e-bfe5-1171-9153-91c4b775587c" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "editor" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" + } + }, + { + "key": "langsmith.metadata.ls_provider", + "value": { + "stringValue": "anthropic" + } + }, + { + "key": "langsmith.metadata.ls_model_name", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "langsmith.metadata.ls_model_type", + "value": { + "stringValue": "chat" + } + }, + { + "key": "langsmith.metadata.ls_max_tokens", + "value": { + "intValue": "4096" + } + }, + { + "key": "langsmith.metadata.lc_versions", + "value": { + "stringValue": "{\"langchain-core\":\"1.6.6\",\"langchain\":\"1.4.3\",\"langchain-anthropic\":\"1.7.5\"}" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.model", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "langsmith.metadata.max_tokens", + "value": { + "intValue": "4096" + } + }, + { + "key": "langsmith.metadata.model_kwargs", + "value": { + "stringValue": "{\"extra_body\":{\"extra_headers\":{\"anthropic-workspace-id\":\"[redacted workspace]\"}}}" + } + }, + { + "key": "langsmith.metadata.streaming", + "value": { + "boolValue": false + } + }, + { + "key": "langsmith.metadata.max_retries", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata._type", + "value": { + "stringValue": "anthropic-chat" + } + }, + { + "key": "langsmith.metadata.usage_metadata", + "value": { + "stringValue": "{\"input_tokens\":8127,\"output_tokens\":433,\"total_tokens\":8560,\"input_token_details\":{\"cache_read\":0,\"cache_creation\":0,\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_token_details\":{\"reasoning\":79}}" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "seq:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + }, + { + "key": "gen_ai.usage.input_tokens", + "value": { + "intValue": "8127" + } + }, + { + "key": "gen_ai.usage.output_tokens", + "value": { + "intValue": "433" + } + }, + { + "key": "gen_ai.usage.total_tokens", + "value": { + "intValue": "8560" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "04ffc0db9ce0f358", + "parentSpanId": "e8da3a18a9815276", + "name": "LangGraph", + "kind": 1, + "startTimeUnixNano": "1790968013178249984", + "endTimeUnixNano": "1790968042919047168", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "LangGraph" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langgraph" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "eyJtZXNzYWdlcyI6W3sicm9sZSI6InVzZXIiLCJjb250ZW50IjoiRm9yIGEgc3ludGhldGljIHRyYWNpbmcgZml4dHVyZSwgZXhwbGFpbiBQeXRob24gdHVwbGUgdmVyc3VzIGxpc3QgaW1tdXRhYmlsaXR5IGluIGF0IG1vc3QgMTIwIHdvcmRzLiBVc2Ugb25seSBvZmZpY2lhbCBQeXRob24gZG9jdW1lbnRhdGlvbiBpZiB5b3Ugc2VhcmNoLiBIYXZlIHRoZSBza2VwdGljIGFuZCB2ZXJpZmllciBjaGVjayBpdCwgdGhlbiBoYXZlIHRoZSBlZGl0b3Igd3JpdGUgL2Fuc3dlci5tZC4gS2VlcCB0aGUgcnVuIHNob3J0IGFuZCBkbyBub3QgYXNrIGZvbGxvdy11cCBxdWVzdGlvbnMuIn1dfQ==" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "41a84418436b8795", + "parentSpanId": "04ffc0db9ce0f358", + "name": "editor", + "kind": 1, + "startTimeUnixNano": "1790968035042877952", + "endTimeUnixNano": "1790968042918639872", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "editor" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langgraph" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "5" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "editor" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:editor\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"editor\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:5" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "eyJtZXNzYWdlcyI6W3siY29udGVudCI6IkZvciBhIHN5bnRoZXRpYyB0cmFjaW5nIGZpeHR1cmUsIGV4cGxhaW4gUHl0aG9uIHR1cGxlIHZlcnN1cyBsaXN0IGltbXV0YWJpbGl0eSBpbiBhdCBtb3N0IDEyMCB3b3Jkcy4gVXNlIG9ubHkgb2ZmaWNpYWwgUHl0aG9uIGRvY3VtZW50YXRpb24gaWYgeW91IHNlYXJjaC4gSGF2ZSB0aGUgc2tlcHRpYyBhbmQgdmVyaWZpZXIgY2hlY2sgaXQsIHRoZW4gaGF2ZSB0aGUgZWRpdG9yIHdyaXRlIC9hbnN3ZXIubWQuIEtlZXAgdGhlIHJ1biBzaG9ydCBhbmQgZG8gbm90IGFzayBmb2xsb3ctdXAgcXVlc3Rpb25zLiIsImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnt9LCJ0eXBlIjoiaHVtYW4iLCJpZCI6IjQ2MjA0MzA1LWY4ZWUtNDM4NC05Y2U4LWZjZDgwYmZjZGY3NSJ9LHsiY29udGVudCI6W3siaWQiOiJ0b29sdV8wMUIyTGZIR0RqWVNGSmhtaVhOajRDdVEiLCJjYWxsZXIiOnsidHlwZSI6ImRpcmVjdCJ9LCJpbnB1dCI6eyJxdWVyeSI6ImRvY3MucHl0aG9uLm9yZyB0dXBsZXMgaW1tdXRhYmxlIHNlcXVlbmNlcyBsaXN0cyBtdXRhYmxlIGRhdGEgc3RydWN0dXJlcyB0dXRvcmlhbCJ9LCJuYW1lIjoid2ViX3NlYXJjaCIsInR5cGUiOiJ0b29sX3VzZSIsInRvb2xzZXRfbmFtZSI6bnVsbH1dLCJhZGRpdGlvbmFsX2t3YXJncyI6e30sInJlc3BvbnNlX21ldGFkYXRhIjp7ImlkIjoibXNnXzAxMUNmZHc5YVc5YnJlblBxZ3liZk53UCIsImNvbnRhaW5lciI6bnVsbCwiZGlhZ25vc3RpY3MiOm51bGwsIm1vZGVsIjoiY2xhdWRlLXNvbm5ldCIsInN0b3BfZGV0YWlscyI6bnVsbCwic3RvcF9yZWFzb24iOiJ0b29sX3VzZSIsInN0b3Bfc2VxdWVuY2UiOm51bGwsInVzYWdlIjp7ImNhY2hlX2NyZWF0aW9uIjp7ImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjB9LCJjYWNoZV9jcmVhdGlvbl9pbnB1dF90b2tlbnMiOjAsImNhY2hlX3JlYWRfaW5wdXRfdG9rZW5zIjowLCJpbmZlcmVuY2VfZ2VvIjoiZ2xvYmFsIiwiaW5wdXRfdG9rZW5zIjoyODQ1LCJvdXRwdXRfdG9rZW5zIjo3Mywib3V0cHV0X3Rva2Vuc19kZXRhaWxzIjp7InRoaW5raW5nX3Rva2VucyI6MH0sInNlcnZlcl90b29sX3VzZSI6bnVsbCwic2VydmljZV90aWVyIjoic3RhbmRhcmQifSwibW9kZWxfbmFtZSI6ImNsYXVkZS1zb25uZXQiLCJtb2RlbF9wcm92aWRlciI6ImFudGhyb3BpYyJ9LCJ0eXBlIjoiYWkiLCJuYW1lIjoicmVzZWFyY2hlciIsImlkIjoibGNfcnVuLS0wMWEwZmUwMy0yMWEzLTcwMDAtYTM4MS0yODRhNmEwYzAzZjctMCIsInRvb2xfY2FsbHMiOlt7Im5hbWUiOiJ3ZWJfc2VhcmNoIiwiYXJncyI6eyJxdWVyeSI6ImRvY3MucHl0aG9uLm9yZyB0dXBsZXMgaW1tdXRhYmxlIHNlcXVlbmNlcyBsaXN0cyBtdXRhYmxlIGRhdGEgc3RydWN0dXJlcyB0dXRvcmlhbCJ9LCJpZCI6InRvb2x1XzAxQjJMZkhHRGpZU0ZKaG1pWE5qNEN1USIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6Mjg0NSwib3V0cHV0X3Rva2VucyI6NzMsInRvdGFsX3Rva2VucyI6MjkxOCwiaW5wdXRfdG9rZW5fZGV0YWlscyI6eyJjYWNoZV9yZWFkIjowLCJjYWNoZV9jcmVhdGlvbiI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MH0sIm91dHB1dF90b2tlbl9kZXRhaWxzIjp7InJlYXNvbmluZyI6MH19fSx7ImNvbnRlbnQiOiJbe1widGl0bGVcIjogXCI1LiBEYXRhIFN0cnVjdHVyZXMgXFx1MjAxNCBQeXRob24gMy4xNC41IGRvY3VtZW50YXRpb25cIiwgXCJ1cmxcIjogXCJodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL3R1dG9yaWFsL2RhdGFzdHJ1Y3R1cmVzLmh0bWxcIiwgXCJoaWdobGlnaHRzXCI6IFtcIllvdSBtaWdodCBoYXZlIG5vdGljZWQgdGhhdCBtZXRob2RzIGxpa2VgaW5zZXJ0YCxgcmVtb3ZlYCBvcmBzb3J0YCB0aGF0IG9ubHkgbW9kaWZ5IHRoZSBsaXN0IGhhdmUgbm8gcmV0dXJuIHZhbHVlIHByaW50ZWQgXFx1MjAxMyB0aGV5IHJldHVybiB0aGUgZGVmYXVsdGBOb25lYC4gWzFdIFRoaXMgaXMgYSBkZXNpZ24gcHJpbmNpcGxlIGZvciBhbGwgbXV0YWJsZSBkYXRhIHN0cnVjdHVyZXMgaW4gUHl0aG9uLlxcbi4uLlxcbiMjIDUuMy4gVHVwbGVzIGFuZCBTZXF1ZW5jZXNcXHUwMGI2XFxuXFxuV2Ugc2F3IHRoYXQgbGlzdHMgYW5kIHN0cmluZ3MgaGF2ZSBtYW55IGNvbW1vbiBwcm9wZXJ0aWVzLCBzdWNoIGFzIGluZGV4aW5nIGFuZCBzbGljaW5nIG9wZXJhdGlvbnMuIFRoZXkgYXJlIHR3byBleGFtcGxlcyBvZiBzZXF1ZW5jZSBkYXRhIHR5cGVzIChzZWUgU2VxdWVuY2UgVHlwZXMgXFx1MjAxNCBsaXN0LCB0dXBsZSwgcmFuZ2UpLiBTaW5jZSBQeXRob24gaXMgYW4gZXZvbHZpbmcgbGFuZ3VhZ2UsIG90aGVyIHNlcXVlbmNlIGRhdGEgdHlwZXMgbWF5IGJlIGFkZGVkLiBUaGVyZSBpcyBhbHNvIGFub3RoZXIgc3RhbmRhcmQgc2VxdWVuY2UgZGF0YSB0eXBlOiB0aGUgdHVwbGUuXFxuXFxuQSB0dXBsZSBjb25zaXN0cyBvZiBhIG51bWJlciBvZiB2YWx1ZXMgc2VwYXJhdGVkIGJ5IGNvbW1hcywgZm9yIGluc3RhbmNlOlxcbi4uLlxcbj4+PiAjIFR1cGxlcyBhcmUgaW1tdXRhYmxlOlxcbj4+PiB0WzBdID0gODg4ODhcXG5UcmFjZWJhY2sgKG1vc3QgcmVjZW50IGNhbGwgbGFzdCk6XFxuICBGaWxlIFxcXCI8c3RkaW4+XFxcIiwgbGluZSAxLCBpbiA8bW9kdWxlPlxcblR5cGVFcnJvcjogJ3R1cGxlJyBvYmplY3QgZG9lcyBub3Qgc3VwcG9ydCBpdGVtIGFzc2lnbm1lbnRcXG4+Pj4gIyBidXQgdGhleSBjYW4gY29udGFpbiBtdXRhYmxlIG9iamVjdHM6XFxuPj4+IHYgPSAoWzEsIDIsIDNdLCBbMywgMiwgMV0pXFxuPj4+IHZcXG4oWzEsIDIsIDNdLCBbMywgMiwgMV0pXFxuLi4uXFxuQXMgeW91IHNlZSwgb24gb3V0cHV0IHR1cGxlcyBhcmUgYWx3YXlzIGVuY2xvc2VkIGluIHBhcmVudGhlc2VzLCBzbyB0aGF0IG5lc3RlZCB0dXBsZXMgYXJlIGludGVycHJldGVkIGNvcnJlY3RseTsgdGhleSBtYXkgYmUgaW5wdXQgd2l0aCBvciB3aXRob3V0IHN1cnJvdW5kaW5nIHBhcmVudGhlc2VzLCBhbHRob3VnaCBvZnRlbiBwYXJlbnRoZXNlcyBhcmUgbmVjZXNzYXJ5IGFueXdheSAoaWYgdGhlIHR1cGxlIGlzIHBhcnQgb2YgYSBsYXJnZXIgZXhwcmVzc2lvbikuIEl0IGlzIG5vdCBwb3NzaWJsZSB0byBhc3NpZ24gdG8gdGhlIGluZGl2aWR1YWwgaXRlbXMgb2YgYSB0dXBsZSwgaG93ZXZlciBpdCBpcyBwb3NzaWJsZSB0byBjcmVhdGUgdHVwbGVzIHdoaWNoIGNvbnRhaW4gbXV0YWJsZSBvYmplY3RzLCBzdWNoIGFzIGxpc3RzLlxcblxcblRob3VnaCB0dXBsZXMgbWF5IHNlZW0gc2ltaWxhciB0byBsaXN0cywgdGhleSBhcmUgb2Z0ZW4gdXNlZCBpbiBkaWZmZXJlbnQgc2l0dWF0aW9ucyBhbmQgZm9yIGRpZmZlcmVudCBwdXJwb3Nlcy4gVHVwbGVzIGFyZSBpbW11dGFibGUsIGFuZCB1c3VhbGx5IGNvbnRhaW4gYSBoZXRlcm9nZW5lb3VzIHNlcXVlbmNlIG9mIGVsZW1lbnRzIHRoYXQgYXJlIGFjY2Vzc2VkIHZpYSB1bnBhY2tpbmcgKHNlZSBsYXRlciBpbiB0aGlzIHNlY3Rpb24pIG9yIGluZGV4aW5nIChvciBldmVuIGJ5IGF0dHJpYnV0ZSBpbiB0aGUgY2FzZSBvZiBuYW1lZHR1cGxlcykuIExpc3RzIGFyZSBtdXRhYmxlLCBhbmQgdGhlaXIgZWxlbWVudHMgYXJlIHVzdWFsbHkgaG9tb2dlbmVvdXMgYW5kIGFyZSBhY2Nlc3NlZCBieSBpdGVyYXRpbmcgb3ZlciB0aGUgbGlzdC5cXG4uLi5cXG5Bbm90aGVyIHVzZWZ1bCBkYXRhIHR5cGUgYnVpbHQgaW50byBQeXRob24gaXMgdGhlIGRpY3Rpb25hcnkgKHNlZSBNYXBwaW5nIFR5cGVzIFxcdTIwMTQgZGljdCkuIERpY3Rpb25hcmllcyBhcmUgc29tZXRpbWVzIGZvdW5kIGluIG90aGVyIGxhbmd1YWdlcyBhcyBcXHUyMDFjYXNzb2NpYXRpdmUgbWVtb3JpZXNcXHUyMDFkIG9yIFxcdTIwMWNhc3NvY2lhdGl2ZSBhcnJheXNcXHUyMDFkLiBVbmxpa2Ugc2VxdWVuY2VzLCB3aGljaCBhcmUgaW5kZXhlZCBieSBhIHJhbmdlIG9mIG51bWJlcnMsIGRpY3Rpb25hcmllcyBhcmUgaW5kZXhlZCBieSBrZXlzLCB3aGljaCBjYW4gYmUgYW55IGltbXV0YWJsZSB0eXBlOyBzdHJpbmdzIGFuZCBudW1iZXJzIGNhbiBhbHdheXMgYmUga2V5cy4gVHVwbGVzIGNhbiBiZSB1c2VkIGFzIGtleXMgaWYgdGhleSBjb250YWluIG9ubHkgc3RyaW5ncywgbnVtYmVycywgb3IgdHVwbGVzOyBpZiBhIHR1cGxlIGNvbnRhaW5zIGFueSBtdXRhYmxlIG9iamVjdCBlaXRoZXIgZGlyZWN0bHkgb3IgaW5kaXJlY3RseSwgaXQgY2Fubm90IGJlIHVzZWQgYXMgYSBrZXkuIFlvdSBjYW5cXHUyMDE5dCB1c2UgbGlzdHMgYXMga2V5cywgc2luY2UgbGlzdHMgY2FuIGJlIG1vZGlmaWVkIGluIHBsYWNlIHVzaW5nIGluZGV4IGFzc2lnbm1lbnRzLCBzbGljZSBhc3NpZ25tZW50cywgb3IgbWV0aG9kcyBsaWtlIGFwcGVuZCgpIGFuZCBleHRlbmQoKS5cIl19LCB7XCJ0aXRsZVwiOiBcIjMuIERhdGEgbW9kZWwgXFx1MjAxNCBQeXRob24gMy4xNC41IGRvY3VtZW50YXRpb25cIiwgXCJ1cmxcIjogXCJodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL3JlZmVyZW5jZS9kYXRhbW9kZWwuaHRtbFwiLCBcImhpZ2hsaWdodHNcIjogW1wiVGhlIHZhbHVlIG9mIHNvbWUgb2JqZWN0cyBjYW4gY2hhbmdlLiBPYmplY3RzIHdob3NlIHZhbHVlIGNhbiBjaGFuZ2UgYXJlIHNhaWQgdG8gYmUgbXV0YWJsZTsgb2JqZWN0cyB3aG9zZSB2YWx1ZSBpcyB1bmNoYW5nZWFibGUgb25jZSB0aGV5IGFyZSBjcmVhdGVkIGFyZSBjYWxsZWQgaW1tdXRhYmxlLiAoVGhlIHZhbHVlIG9mIGFuIGltbXV0YWJsZSBjb250YWluZXIgb2JqZWN0IHRoYXQgY29udGFpbnMgYSByZWZlcmVuY2UgdG8gYSBtdXRhYmxlIG9iamVjdCBjYW4gY2hhbmdlIHdoZW4gdGhlIGxhdHRlclxcdTIwMTlzIHZhbHVlIGlzIGNoYW5nZWQ7IGhvd2V2ZXIgdGhlIGNvbnRhaW5lciBpcyBzdGlsbCBjb25zaWRlcmVkIGltbXV0YWJsZSwgYmVjYXVzZSB0aGUgY29sbGVjdGlvbiBvZiBvYmplY3RzIGl0IGNvbnRhaW5zIGNhbm5vdCBiZSBjaGFuZ2VkLiBTbywgaW1tdXRhYmlsaXR5IGlzIG5vdCBzdHJpY3RseSB0aGUgc2FtZSBhcyBoYXZpbmcgYW4gdW5jaGFuZ2VhYmxlIHZhbHVlLCBpdCBpcyBtb3JlIHN1YnRsZS4pIEFuIG9iamVjdFxcdTIwMTlzIG11dGFiaWxpdHkgaXMgZGV0ZXJtaW5lZCBieSBpdHMgdHlwZTsgZm9yIGluc3RhbmNlLCBudW1iZXJzLCBzdHJpbmdzIGFuZCB0dXBsZXMgYXJlIGltbXV0YWJsZSwgd2hpbGUgZGljdGlvbmFyaWVzIGFuZCBsaXN0cyBhcmUgbXV0YWJsZS5cXG4uLi5cXG5Tb21lIG9iamVjdHMgY29udGFpbiByZWZlcmVuY2VzIHRvIG90aGVyIG9iamVjdHM7IHRoZXNlIGFyZSBjYWxsZWQgY29udGFpbmVycy4gRXhhbXBsZXMgb2YgY29udGFpbmVycyBhcmUgdHVwbGVzLCBsaXN0cyBhbmQgZGljdGlvbmFyaWVzLiBUaGUgcmVmZXJlbmNlcyBhcmUgcGFydCBvZiBhIGNvbnRhaW5lclxcdTIwMTlzIHZhbHVlLiBJbiBtb3N0IGNhc2VzLCB3aGVuIHdlIHRhbGsgYWJvdXQgdGhlIHZhbHVlIG9mIGEgY29udGFpbmVyLCB3ZSBpbXBseSB0aGUgdmFsdWVzLCBub3QgdGhlIGlkZW50aXRpZXMgb2YgdGhlIGNvbnRhaW5lZCBvYmplY3RzOyBob3dldmVyLCB3aGVuIHdlIHRhbGsgYWJvdXQgdGhlIG11dGFiaWxpdHkgb2YgYSBjb250YWluZXIsIG9ubHkgdGhlIGlkZW50aXRpZXMgb2YgdGhlIGltbWVkaWF0ZWx5IGNvbnRhaW5lZCBvYmplY3RzIGFyZSBpbXBsaWVkLiBTbywgaWYgYW4gaW1tdXRhYmxlIGNvbnRhaW5lciAobGlrZSBhIHR1cGxlKSBjb250YWlucyBhIHJlZmVyZW5jZSB0byBhIG11dGFibGUgb2JqZWN0LCBpdHMgdmFsdWUgY2hhbmdlcyBpZiB0aGF0IG11dGFibGUgb2JqZWN0IGlzIGNoYW5nZWQuXFxuLi4uXFxuIyMjIDMuMi41LiBTZXF1ZW5jZXNcXHUwMGI2XFxuLi4uXFxuIyMjIyAzLjIuNS4xLiBJbW11dGFibGUgc2VxdWVuY2VzXFx1MDBiNlxcblxcbkFuIG9iamVjdCBvZiBhbiBpbW11dGFibGUgc2VxdWVuY2UgdHlwZSBjYW5ub3QgY2hhbmdlIG9uY2UgaXQgaXMgY3JlYXRlZC4gKElmIHRoZSBvYmplY3QgY29udGFpbnMgcmVmZXJlbmNlcyB0byBvdGhlciBvYmplY3RzLCB0aGVzZSBvdGhlciBvYmplY3RzIG1heSBiZSBtdXRhYmxlIGFuZCBtYXkgYmUgY2hhbmdlZDsgaG93ZXZlciwgdGhlIGNvbGxlY3Rpb24gb2Ygb2JqZWN0cyBkaXJlY3RseSByZWZlcmVuY2VkIGJ5IGFuIGltbXV0YWJsZSBvYmplY3QgY2Fubm90IGNoYW5nZS4pXFxuXFxuVGhlIGZvbGxvd2luZyB0eXBlcyBhcmUgaW1tdXRhYmxlIHNlcXVlbmNlczpcXG4uLi5cXG5UdXBsZXNcXG46IFRoZSBpdGVtcyBvZiBhIGB0dXBsZWAgYXJlIGFyYml0cmFyeSBQeXRob24gb2JqZWN0cy4gVHVwbGVzIG9mIHR3byBvciBtb3JlIGl0ZW1zIGFyZSBmb3JtZWQgYnkgY29tbWEtc2VwYXJhdGVkIGxpc3RzIG9mIGV4cHJlc3Npb25zLiBBIHR1cGxlIG9mIG9uZSBpdGVtIChhIFxcdTIwMThzaW5nbGV0b25cXHUyMDE5KSBjYW4gYmUgZm9ybWVkIGJ5IGFmZml4aW5nIGEgY29tbWEgdG8gYW4gZXhwcmVzc2lvbiAoYW4gZXhwcmVzc2lvbiBieSBpdHNlbGYgZG9lcyBub3QgY3JlYXRlIGEgdHVwbGUsIHNpbmNlIHBhcmVudGhlc2VzIG11c3QgYmUgdXNhYmxlIGZvciBncm91cGluZyBvZiBleHByZXNzaW9ucykuIEFuIGVtcHR5IHR1cGxlIGNhbiBiZSBmb3JtZWQgYnkgYW4gZW1wdHkgcGFpciBvZiBwYXJlbnRoZXNlcy5cXG4uLi5cXG4jIyMjIDMuMi41LjIuIE11dGFibGUgc2VxdWVuY2VzXFx1MDBiNlxcblxcbk11dGFibGUgc2VxdWVuY2VzIGNhbiBiZSBjaGFuZ2VkIGFmdGVyIHRoZXkgYXJlIGNyZWF0ZWQuIFRoZSBzdWJzY3JpcHRpb24gYW5kIHNsaWNpbmcgbm90YXRpb25zIGNhbiBiZSB1c2VkIGFzIHRoZSB0YXJnZXQgb2YgYXNzaWdubWVudCBhbmQgYGRlbGAgKGRlbGV0ZSkgc3RhdGVtZW50cy5cXG4uLi5cXG5UaGVyZSBhcmUgY3VycmVudGx5IHR3byBpbnRyaW5zaWMgbXV0YWJsZSBzZXF1ZW5jZSB0eXBlczpcXG5cXG5MaXN0c1xcbjogVGhlIGl0ZW1zIG9mIGEgbGlzdCBhcmUgYXJiaXRyYXJ5IFB5dGhvbiBvYmplY3RzLiBMaXN0cyBhcmUgZm9ybWVkIGJ5IHBsYWNpbmcgYSBjb21tYS1zZXBhcmF0ZWQgbGlzdCBvZiBleHByZXNzaW9ucyBpbiBzcXVhcmUgYnJhY2tldHMuIChOb3RlIHRoYXQgdGhlcmUgYXJlIG5vIHNwZWNpYWwgY2FzZXMgbmVlZGVkIHRvIGZvcm0gbGlzdHMgb2YgbGVuZ3RoIDAgb3IgMS4pXCJdfSwge1widGl0bGVcIjogXCJCdWlsdC1pbiBUeXBlcyBcXHUyMDE0IFB5dGhvbiAzLjE0LjcgZG9jdW1lbnRhdGlvblwiLCBcInVybFwiOiBcImh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvYnVpbHRpbnMvc3RkdHlwZXMuaHRtbFwiLCBcImhpZ2hsaWdodHNcIjogW1wiY29sbGVjdGlvbiBjbGFzc2VzIGFyZSBtdXRhYmxlLiBUaGUgbWV0aG9kcyB0aGF0IGFkZCwgc3VidHJhY3QsIG9yIHJlYXJyYW5nZSB0aGVpciAuLi4gaW4gcGxhY2UsIGFuZCBkb25cXHUyMDE5dCByZXR1cm4gYSAuLi4gLCBuZXZlciByZXR1cm4gdGhlIGNvbGxlY3Rpb24gaW5zdGFuY2UgaXRzZWxmIGJ1dCBgTm9uZWAuXFxuLi4uXFxuIyMgU2VxdWVuY2UgVHlwZXMgXFx1MjAxNCBgbGlzdGAsIGB0dXBsZWAsIGByYW5nZWBcXHUwMGI2XFxuXFxuVGhlcmUgYXJlIHRocmVlIGJhc2ljIHNlcXVlbmNlIHR5cGVzOiBsaXN0cywgdHVwbGVzLCBhbmQgcmFuZ2Ugb2JqZWN0cy4gQWRkaXRpb25hbCBzZXF1ZW5jZSB0eXBlcyB0YWlsb3JlZCBmb3IgcHJvY2Vzc2luZyBvZiBiaW5hcnkgZGF0YSBhbmQgdGV4dCBzdHJpbmdzIGFyZSBkZXNjcmliZWQgaW4gZGVkaWNhdGVkIHNlY3Rpb25zLlxcbi4uLlxcblRoZSBvcGVyYXRpb25zIGluIHRoZSBmb2xsb3dpbmcgdGFibGUgLi4uIG11dGFibGUgYW5kIGltbXV0YWJsZS4gVGhlIGBjb2xsZWN0aW9ucy4gLi4uIGlzIHByb3ZpZGVkIHRvIG1ha2UgLi4uIGVhc2llciB0byBjb3JyZWN0bHkgaW1wbGVtZW50IHRoZXNlIG9wZXJhdGlvbnMgb24gY3VzdG9tIHNlcXVlbmNlIHR5cGVzXFxuLi4uXFxuIyMjIEltbXV0YWJsZSBTZXF1ZW5jZSBUeXBlc1xcdTAwYjZcXG4uLi5cXG5tdXRhYmxlIHNlcXVlbmNlIHR5cGVzIGlzXFxuLi4uXFxuc3VwcG9ydCBhbGxvd3MgaW1tdXRhYmxlIHNlcXVlbmNlcywgLi4uICwgdG8gYmUgdXNlZCBhcyBgZGljdGAga2V5cyBhbmQgc3RvcmVkIGluIC4uLiBlbnNldGAgaW5zdGFuY2VzXFxuLi4uXFxuIyMjIE11dGFibGUgU2VxdWVuY2UgVHlwZXNcXHUwMGI2XFxuLi4uXFxuIyMjIExpc3RzXFx1MDBiNlxcblxcbkxpc3RzIGFyZSBtdXRhYmxlIHNlcXVlbmNlcywgdHlwaWNhbGx5IHVzZWQgdG8gc3RvcmUgY29sbGVjdGlvbnMgb2YgaG9tb2dlbmVvdXMgaXRlbXMgKHdoZXJlIHRoZSBwcmVjaXNlIGRlZ3JlZSBvZiBzaW1pbGFyaXR5IHdpbGwgdmFyeSBieSBhcHBsaWNhdGlvbikuXFxuLi4uXFxuIyMjIFR1cGxlc1xcdTAwYjZcXG5cXG5UdXBsZXMgYXJlIGltbXV0YWJsZSBzZXF1ZW5jZXMsIHR5cGljYWxseSB1c2VkIHRvIHN0b3JlIGNvbGxlY3Rpb25zIG9mIGhldGVyb2dlbmVvdXMgZGF0YSAoc3VjaCBhcyB0aGUgMi10dXBsZXMgcHJvZHVjZWQgYnkgdGhlIGBlbnVtZXJhdGUoKWAgYnVpbHQtaW4pLiBUdXBsZXMgYXJlIGFsc28gdXNlZCBmb3IgY2FzZXMgd2hlcmUgYW4gaW1tdXRhYmxlIHNlcXVlbmNlIG9mIGhvbW9nZW5lb3VzIGRhdGEgaXMgbmVlZGVkIChzdWNoIGFzIGFsbG93aW5nIHN0b3JhZ2UgaW4gYSBgc2V0YCBvciBgZGljdGAgaW5zdGFuY2UpLlxcbi4uLlxcbnR1cGxlKGl0ZXJhYmxlPVxcbi4uLlxcblRoZSBjb25zdHJ1Y3RvciBidWlsZHMgYSB0dXBsZSB3aG9zZSBpdGVtcyBhcmUgdGhlIHNhbWUgYW5kIGluIHRoZSBzYW1lIG9yZGVyIGFzIGl0ZXJhYmxlXFx1MjAxOXMgaXRlbXMuIGl0ZXJhYmxlIG1heSBiZSBlaXRoZXIgYSBzZXF1ZW5jZSwgYSBjb250YWluZXIgdGhhdCBzdXBwb3J0cyBpdGVyYXRpb24sIG9yIGFuIGl0ZXJhdG9yIG9iamVjdC4gSWYgaXRlcmFibGUgaXMgYWxyZWFkeSBhIHR1cGxlLCBpdCBpcyByZXR1cm5lZCB1bmNoYW5nZWQuIEZvciBleGFtcGxlLCBgdHVwbGUoJ2FiYycpYCByZXR1cm5zIGAoJ2EnLCAnYicsICdjJylgIGFuZCBgdHVwbGUoIFsxLCAyLCAzXSApYCByZXR1cm5zIGAoMSwgMiwgMylgLiBJZiBubyBhcmd1bWVudCBpcyBnaXZlbiwgdGhlIGNvbnN0cnVjdG9yIGNyZWF0ZXMgYSBuZXcgZW1wdHkgdHVwbGUsIGAoKWAuXFxuLi4uXFxuVHVwbGVzIGltcGxlbWVudCBhbGwgb2YgdGhlIGNvbW1vbiBzZXF1ZW5jZSBvcGVyYXRpb25zLlxcbi4uLlxcbkZvciBoZXRlcm9nZW5lb3VzIGNvbGxlY3Rpb25zIG9mIGRhdGEgd2hlcmUgYWNjZXNzIGJ5IG5hbWUgaXMgY2xlYXJlciB0aGFuIGFjY2VzcyBieSBpbmRleCwgYGNvbGxlY3Rpb25zLm5hbWVkdHVwbGUoKWAgbWF5IGJlIGEgbW9yZSBhcHByb3ByaWF0ZSBjaG9pY2UgdGhhbiBhIHNpbXBsZSB0dXBsZSBvYmplY3QuXCJdfSwge1widGl0bGVcIjogXCJCdWlsdC1pbiBUeXBlcyBcXHUyMDE0IFB5dGhvbiAzLjE0LjUgZG9jdW1lbnRhdGlvblwiLCBcInVybFwiOiBcImh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvbGlicmFyeS9zdGR0eXBlcy5odG1sXCIsIFwiaGlnaGxpZ2h0c1wiOiBbXCJTb21lIGNvbGxlY3Rpb24gY2xhc3NlcyBhcmUgbXV0YWJsZS4gVGhlIG1ldGhvZHMgdGhhdCBhZGQsIHN1YnRyYWN0LCBvciByZWFycmFuZ2UgdGhlaXIgLi4uIGluIHBsYWNlLCBhbmQgZG9uXFx1MjAxOXQgcmV0dXJuIGEgLi4uICwgbmV2ZXIgcmV0dXJuIHRoZSBjb2xsZWN0aW9uIGluc3RhbmNlIGl0c2VsZiBidXQgYE5vbmVgLlxcbi4uLlxcbiMjIFNlcXVlbmNlIFR5cGVzIFxcdTIwMTQgYGxpc3RgLCBgdHVwbGVgLCBgcmFuZ2VgXFx1MDBiNlxcblxcblRoZXJlIGFyZSB0aHJlZSBiYXNpYyBzZXF1ZW5jZSB0eXBlczogbGlzdHMsIHR1cGxlcywgYW5kIC4uLiBvYmplY3RzLiBBZGRpdGlvbmFsIHNlcXVlbmNlIHR5cGVzIHRhaWxvcmVkIGZvciBwcm9jZXNzaW5nIG9mIGJpbmFyeSBkYXRhIGFuZCB0ZXh0IHN0cmluZ3MgYXJlIGRlc2NyaWJlZCBpbiBkZWRpY2F0ZWQgc2VjdGlvbnMuXFxuLi4uXFxuVGhlIG9wZXJhdGlvbnMgaW4gdGhlIGZvbGxvd2luZyB0YWJsZSAuLi4gaW1tdXRhYmxlLiBUaGUgYCAuLi4gaXMgcHJvdmlkZWQgdG8gbWFrZSAuLi4gZWFzaWVyIHRvIGNvcnJlY3RseSBpbXBsZW1lbnQgdGhlc2Ugb3BlcmF0aW9ucyBvbiBjdXN0b20gc2VxdWVuY2UgdHlwZXNcXG4uLi5cXG4jIyMgSW1tdXRhYmxlIFNlcXVlbmNlIFR5cGVzXFx1MDBiNlxcbi4uLlxcbm9wZXJhdGlvbiB0aGF0IGltbXV0YWJsZSBzZXF1ZW5jZSAuLi4gYnkgbXV0YWJsZSBzZXF1ZW5jZSB0eXBlcyBpcyAuLi4gYGhhc2goKWBcXG4uLi5cXG5UaGlzIHN1cHBvcnQgYWxsb3dzIGltbXV0YWJsZSBzZXF1ZW5jZXMsIHN1Y2ggYXMgYHR1cGxlYCBpbnN0YW5jZXMsIHRvIGJlIHVzZWQgYXMgYGRpY3RgIGtleXMgYW5kIHN0b3JlZCBpbiBgc2V0YCBhbmQgYGZyb3plbnNldGAgaW5zdGFuY2VzLlxcbi4uLlxcbiMjIyBNdXRhYmxlIFNlcXVlbmNlIFR5cGVzXFx1MDBiNlxcbi4uLlxcbiMjIyBMaXN0c1xcdTAwYjZcXG5cXG5MaXN0cyBhcmUgbXV0YWJsZSBzZXF1ZW5jZXMsIHR5cGljYWxseSB1c2VkIHRvIHN0b3JlIGNvbGxlY3Rpb25zIG9mIGhvbW9nZW5lb3VzIGl0ZW1zICh3aGVyZSB0aGUgcHJlY2lzZSBkZWdyZWUgb2Ygc2ltaWxhcml0eSB3aWxsIHZhcnkgYnkgYXBwbGljYXRpb24pLlxcbi4uLlxcbiMjIyBUdXBsZXNcXHUwMGI2XFxuXFxuVHVwbGVzIGFyZSBpbW11dGFibGUgc2VxdWVuY2VzLCB0eXBpY2FsbHkgdXNlZCB0byBzdG9yZSBjb2xsZWN0aW9ucyBvZiBoZXRlcm9nZW5lb3VzIGRhdGEgKHN1Y2ggYXMgdGhlIDItdHVwbGVzIHByb2R1Y2VkIGJ5IHRoZSBgZW51bWVyYXRlKClgIGJ1aWx0LWluKS4gVHVwbGVzIGFyZSBhbHNvIHVzZWQgZm9yIGNhc2VzIHdoZXJlIGFuIGltbXV0YWJsZSBzZXF1ZW5jZSBvZiBob21vZ2VuZW91cyBkYXRhIGlzIG5lZWRlZCAoc3VjaCBhcyBhbGxvd2luZyBzdG9yYWdlIGluIGEgYHNldGAgb3IgYGRpY3RgIGluc3RhbmNlKS5cXG4uLi5cXG5UaGUgY29uc3RydWN0b3IgYnVpbGRzIGEgdHVwbGUgd2hvc2UgaXRlbXMgYXJlIHRoZSBzYW1lIGFuZCBpbiB0aGUgc2FtZSBvcmRlciBhcyBpdGVyYWJsZVxcdTIwMTlzIGl0ZW1zLiBpdGVyYWJsZSBtYXkgYmUgZWl0aGVyIGEgc2VxdWVuY2UsIGEgY29udGFpbmVyIHRoYXQgc3VwcG9ydHMgaXRlcmF0aW9uLCBvciBhbiBpdGVyYXRvciBvYmplY3QuIElmIGl0ZXJhYmxlIGlzIGFscmVhZHkgYSB0dXBsZSwgaXQgaXMgcmV0dXJuZWQgdW5jaGFuZ2VkLiBGb3IgZXhhbXBsZSwgYHR1cGxlKCdhYmMnKWAgcmV0dXJucyBgKCdhJywgJ2InLCAnYycpYCBhbmQgYHR1cGxlKCBbMSwgMiwgM10gKWAgcmV0dXJucyBgKDEsIDIsIDMpYC4gSWYgbm8gYXJndW1lbnQgaXMgZ2l2ZW4sIHRoZSBjb25zdHJ1Y3RvciBjcmVhdGVzIGEgbmV3IGVtcHR5IHR1cGxlLCBgKClgLlxcbi4uLlxcblR1cGxlcyBpbXBsZW1lbnQgYWxsIG9mIHRoZSBjb21tb24gc2VxdWVuY2Ugb3BlcmF0aW9ucy5cXG4uLi5cXG5Gb3IgaGV0ZXJvZ2VuZW91cyBjb2xsZWN0aW9ucyBvZiBkYXRhIHdoZXJlIGFjY2VzcyBieSBuYW1lIGlzIGNsZWFyZXIgdGhhbiBhY2Nlc3MgYnkgaW5kZXgsIGBjb2xsZWN0aW9ucy5uYW1lZHR1cGxlKClgIG1heSBiZSBhIG1vcmUgYXBwcm9wcmlhdGUgY2hvaWNlIHRoYW4gYSBzaW1wbGUgdHVwbGUgb2JqZWN0LlwiXX0sIHtcInRpdGxlXCI6IFwiNS4gRGF0YSBTdHJ1Y3R1cmVzIFxcdTIwMTQgUHl0aG9uIDMuMTAuMjAgZG9jdW1lbnRhdGlvblwiLCBcInVybFwiOiBcImh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMuMTAvdHV0b3JpYWwvZGF0YXN0cnVjdHVyZXMuaHRtbFwiLCBcImhpZ2hsaWdodHNcIjogW1wiWW91IG1pZ2h0IGhhdmUgbm90aWNlZCB0aGF0IG1ldGhvZHMgbGlrZSBgaW5zZXJ0YCwgYHJlbW92ZWAgb3IgYHNvcnRgIHRoYXQgb25seSBtb2RpZnkgdGhlIGxpc3QgaGF2ZSBubyByZXR1cm4gdmFsdWUgcHJpbnRlZCBcXHUyMDEzIHRoZXkgcmV0dXJuIHRoZSBkZWZhdWx0IGBOb25lYC4gMSBUaGlzIGlzIGEgZGVzaWduIHByaW5jaXBsZSBmb3IgYWxsIG11dGFibGUgZGF0YSBzdHJ1Y3R1cmVzIGluIFB5dGhvbi5cXG4uLi5cXG4jIyA1LjMuIFR1cGxlcyBhbmQgU2VxdWVuY2VzXFx1MDBiNlxcblxcbldlIHNhdyB0aGF0IGxpc3RzIGFuZCBzdHJpbmdzIGhhdmUgbWFueSBjb21tb24gcHJvcGVydGllcywgc3VjaCBhcyBpbmRleGluZyBhbmQgc2xpY2luZyBvcGVyYXRpb25zLiBUaGV5IGFyZSB0d28gZXhhbXBsZXMgb2Ygc2VxdWVuY2UgZGF0YSB0eXBlcyAoc2VlIFNlcXVlbmNlIFR5cGVzIFxcdTIwMTQgbGlzdCwgdHVwbGUsIHJhbmdlKS4gU2luY2UgUHl0aG9uIGlzIGFuIGV2b2x2aW5nIGxhbmd1YWdlLCBvdGhlciBzZXF1ZW5jZSBkYXRhIHR5cGVzIG1heSBiZSBhZGRlZC4gVGhlcmUgaXMgYWxzbyBhbm90aGVyIHN0YW5kYXJkIHNlcXVlbmNlIGRhdGEgdHlwZTogdGhlIHR1cGxlLlxcblxcbkEgdHVwbGUgY29uc2lzdHMgb2YgYSBudW1iZXIgb2YgdmFsdWVzIHNlcGFyYXRlZCBieSBjb21tYXMsIGZvciBpbnN0YW5jZTpcXG4uLi5cXG4+Pj4gIyBUdXBsZXMgYXJlIGltbXV0YWJsZTpcXG4uLi4gdFswXSA9IDg4ODg4XFxuVHJhY2ViYWNrIChtb3N0IHJlY2VudCBjYWxsIGxhc3QpOlxcbiAgRmlsZSBcXFwiPHN0ZGluPlxcXCIsIGxpbmUgMSwgaW4gPG1vZHVsZT5cXG5UeXBlRXJyb3I6ICd0dXBsZScgb2JqZWN0IGRvZXMgbm90IHN1cHBvcnQgaXRlbSBhc3NpZ25tZW50XFxuPj4+ICMgYnV0IHRoZXkgY2FuIGNvbnRhaW4gbXV0YWJsZSBvYmplY3RzOlxcbi4uLiB2ID0gKFsxLCAyLCAzXSwgWzMsIDIsIDFdKVxcbj4+PiB2XFxuKFsxLCAyLCAzXSwgWzMsIDIsIDFdKVxcbi4uLlxcbkFzIHlvdSBzZWUsIG9uIG91dHB1dCB0dXBsZXMgYXJlIGFsd2F5cyBlbmNsb3NlZCBpbiBwYXJlbnRoZXNlcywgc28gdGhhdCBuZXN0ZWQgdHVwbGVzIGFyZSBpbnRlcnByZXRlZCBjb3JyZWN0bHk7IHRoZXkgbWF5IGJlIGlucHV0IHdpdGggb3Igd2l0aG91dCBzdXJyb3VuZGluZyBwYXJlbnRoZXNlcywgYWx0aG91Z2ggb2Z0ZW4gcGFyZW50aGVzZXMgYXJlIG5lY2Vzc2FyeSBhbnl3YXkgKGlmIHRoZSB0dXBsZSBpcyBwYXJ0IG9mIGEgbGFyZ2VyIGV4cHJlc3Npb24pLiBJdCBpcyBub3QgcG9zc2libGUgdG8gYXNzaWduIHRvIHRoZSBpbmRpdmlkdWFsIGl0ZW1zIG9mIGEgdHVwbGUsIGhvd2V2ZXIgaXQgaXMgcG9zc2libGUgdG8gY3JlYXRlIHR1cGxlcyB3aGljaCBjb250YWluIG11dGFibGUgb2JqZWN0cywgc3VjaCBhcyBsaXN0cy5cXG5cXG5UaG91Z2ggdHVwbGVzIG1heSBzZWVtIHNpbWlsYXIgdG8gbGlzdHMsIHRoZXkgYXJlIG9mdGVuIHVzZWQgaW4gZGlmZmVyZW50IHNpdHVhdGlvbnMgYW5kIGZvciBkaWZmZXJlbnQgcHVycG9zZXMuIFR1cGxlcyBhcmUgaW1tdXRhYmxlLCBhbmQgdXN1YWxseSBjb250YWluIGEgaGV0ZXJvZ2VuZW91cyBzZXF1ZW5jZSBvZiBlbGVtZW50cyB0aGF0IGFyZSBhY2Nlc3NlZCB2aWEgdW5wYWNraW5nIChzZWUgbGF0ZXIgaW4gdGhpcyBzZWN0aW9uKSBvciBpbmRleGluZyAob3IgZXZlbiBieSBhdHRyaWJ1dGUgaW4gdGhlIGNhc2Ugb2YgYG5hbWVkdHVwbGVzYCkuIExpc3RzIGFyZSBtdXRhYmxlLCBhbmQgdGhlaXIgZWxlbWVudHMgYXJlIHVzdWFsbHkgaG9tb2dlbmVvdXMgYW5kIGFyZSBhY2Nlc3NlZCBieSBpdGVyYXRpbmcgb3ZlciB0aGUgbGlzdC5cXG4uLi5cXG4jIyA1LjQuXFxuLi4uXFxuLiBTZXQgb2JqZWN0c1xcbi4uLlxcbiMjIDUuNS4gRGljdGlvbmFyaWVzXFx1MDBiNlxcblxcbkFub3RoZXIgdXNlZnVsIGRhdGEgdHlwZSBidWlsdCBpbnRvIFB5dGhvbiBpcyB0aGUgZGljdGlvbmFyeSAoc2VlIE1hcHBpbmcgVHlwZXMgXFx1MjAxNCBkaWN0KS4gRGljdGlvbmFyaWVzIGFyZSBzb21ldGltZXMgZm91bmQgaW4gb3RoZXIgbGFuZ3VhZ2VzIGFzIFxcdTIwMWNhc3NvY2lhdGl2ZSBtZW1vcmllc1xcdTIwMWQgb3IgXFx1MjAxY2Fzc29jaWF0aXZlIGFycmF5c1xcdTIwMWQuIFVubGlrZSBzZXF1ZW5jZXMsIHdoaWNoIGFyZSBpbmRleGVkIGJ5IGEgcmFuZ2Ugb2YgbnVtYmVycywgZGljdGlvbmFyaWVzIGFyZSBpbmRleGVkIGJ5IGtleXMsIHdoaWNoIGNhbiBiZSBhbnkgaW1tdXRhYmxlIHR5cGU7IHN0cmluZ3MgYW5kIG51bWJlcnMgY2FuIGFsd2F5cyBiZSBrZXlzLiBUdXBsZXMgY2FuIGJlIHVzZWQgYXMga2V5cyBpZiB0aGV5IGNvbnRhaW4gb25seSBzdHJpbmdzLCBudW1iZXJzLCBvciB0dXBsZXM7IGlmIGEgdHVwbGUgY29udGFpbnMgYW55IG11dGFibGUgb2JqZWN0IGVpdGhlciBkaXJlY3RseSBvciBpbmRpcmVjdGx5LCBpdCBjYW5ub3QgYmUgdXNlZCBhcyBhIGtleS4gWW91IGNhblxcdTIwMTl0IHVzZSBsaXN0cyBhcyBrZXlzLCBzaW5jZSBsaXN0cyBjYW4gYmUgbW9kaWZpZWQgaW4gcGxhY2UgdXNpbmcgaW5kZXggYXNzaWdubWVudHMsIHNsaWNlIGFzc2lnbm1lbnRzLCBvciBtZXRob2RzIGxpa2UgYGFwcGVuZCgpYCBhbmQgYGV4dGVuZCgpYC5cIl19XSIsImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnt9LCJ0eXBlIjoidG9vbCIsIm5hbWUiOiJ3ZWJfc2VhcmNoIiwiaWQiOiI2ZTUxMjVhYy0zMTY0LTRhNzYtOWM1Mi1hYzM0NjBjZTM2ZTQiLCJ0b29sX2NhbGxfaWQiOiJ0b29sdV8wMUIyTGZIR0RqWVNGSmhtaVhOajRDdVEiLCJzdGF0dXMiOiJzdWNjZXNzIn0seyJjb250ZW50IjpbeyJpZCI6InRvb2x1XzAxWGpqM2FSZFd5aEJKZlBtVEpCeFFhOSIsImNhbGxlciI6eyJ0eXBlIjoiZGlyZWN0In0sImlucHV0Ijp7fSwibmFtZSI6InRyYW5zZmVyX3RvX3NrZXB0aWMiLCJ0eXBlIjoidG9vbF91c2UiLCJ0b29sc2V0X25hbWUiOm51bGx9XSwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6eyJpZCI6Im1zZ18wMTFDZmR3QTZGNGNDTjV5aEQ0Q3JzOU0iLCJjb250YWluZXIiOm51bGwsImRpYWdub3N0aWNzIjpudWxsLCJtb2RlbCI6ImNsYXVkZS1zb25uZXQiLCJzdG9wX2RldGFpbHMiOm51bGwsInN0b3BfcmVhc29uIjoidG9vbF91c2UiLCJzdG9wX3NlcXVlbmNlIjpudWxsLCJ1c2FnZSI6eyJjYWNoZV9jcmVhdGlvbiI6eyJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowfSwiY2FjaGVfY3JlYXRpb25faW5wdXRfdG9rZW5zIjowLCJjYWNoZV9yZWFkX2lucHV0X3Rva2VucyI6MCwiaW5mZXJlbmNlX2dlbyI6Imdsb2JhbCIsImlucHV0X3Rva2VucyI6NzM3OCwib3V0cHV0X3Rva2VucyI6MzMsIm91dHB1dF90b2tlbnNfZGV0YWlscyI6eyJ0aGlua2luZ190b2tlbnMiOjB9LCJzZXJ2ZXJfdG9vbF91c2UiOm51bGwsInNlcnZpY2VfdGllciI6InN0YW5kYXJkIn0sIm1vZGVsX25hbWUiOiJjbGF1ZGUtc29ubmV0IiwibW9kZWxfcHJvdmlkZXIiOiJhbnRocm9waWMifSwidHlwZSI6ImFpIiwibmFtZSI6InJlc2VhcmNoZXIiLCJpZCI6ImxjX3J1bi0tMDFhMGZlMDMtM2NkOC03OWYxLTg4YTEtY2U2Y2VlMjk0ZTc5LTAiLCJ0b29sX2NhbGxzIjpbeyJuYW1lIjoidHJhbnNmZXJfdG9fc2tlcHRpYyIsImFyZ3MiOnt9LCJpZCI6InRvb2x1XzAxWGpqM2FSZFd5aEJKZlBtVEpCeFFhOSIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6NzM3OCwib3V0cHV0X3Rva2VucyI6MzMsInRvdGFsX3Rva2VucyI6NzQxMSwiaW5wdXRfdG9rZW5fZGV0YWlscyI6eyJjYWNoZV9yZWFkIjowLCJjYWNoZV9jcmVhdGlvbiI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MH0sIm91dHB1dF90b2tlbl9kZXRhaWxzIjp7InJlYXNvbmluZyI6MH19fSx7ImNvbnRlbnQiOiJTdWNjZXNzZnVsbHkgdHJhbnNmZXJyZWQgdG8gc2tlcHRpYyIsImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnt9LCJ0eXBlIjoidG9vbCIsIm5hbWUiOiJ0cmFuc2Zlcl90b19za2VwdGljIiwiaWQiOiIzODkwNThkMS0wODNmLTQ2MzItYmJjNS0wOWJmZDNhMGZmZDIiLCJ0b29sX2NhbGxfaWQiOiJ0b29sdV8wMVhqajNhUmRXeWhCSmZQbVRKQnhRYTkiLCJzdGF0dXMiOiJzdWNjZXNzIn0seyJjb250ZW50IjpbeyJzaWduYXR1cmUiOiJDQVFTMVFnS0VBZ1NHQUk0QVVJSWRHaHBibXRwYm1jU0RONlRmVTZORE05NzFsRWJ6eG9NdlJVQTFKOW94M2ZKUVlUOUlqQXJDUVFHSEJQNHBSSFBhdlh6UmxiTWJhWUhDNTdZaitHYnhncjBoZWx2ZDJPSUwvbzZSYnQ0UEZBM0ZhSUZVbGdxOGdjN0tRSTlGdEdudlNBa0xCUnpJc1VwLzJkNVJkMnpnRXNma0ZWZVhzbjhXWVlaa2luQVFWVnk2QTdCM0xhRUpXMHhiL3g4OERpNjdmZWR3eDBRK0ZsWnR3Y21UM0RjYWExMUp2ZXlIUnIzZG0rekdTWlA2Q1hlWE5KOG5yVFo3VzFZUlR5c0Q2dzdvN0xwOGgxUndxNGY0bzhqK1FVZlkwdmplK3pKWnN4SFBtUU50M3lrZUtoOTloZ242ZGJpejYvRUhxbWJIalNBdTFNNFNxRURmcUlLVGhIWWVuYW1BWm1jUTRYQU9vNm1kUTYrNzdWZ3BWMWxDMS9rNTJJaVVvSmprR2xRcm5MQ3Z1dGlJN0tOK3NnSzhjMisyS0NKclBSQ3ZWVitCa1N0dlA1aldXcXp5dHBLUStuSHpoTDQ0OE9ySUE5Z2RKQzM5QzhlRHJYZVJuSTd0NEZxbGtYR29NbFpBVjlVTWNyUUhSeE9NaTh0T3lUemk5b3lCRkRUU3NRK0xKcWVyMHR6MUZ0OWdlazZ2emc1MFNwVkFGUWRMRVJ2OFIxWXFNYWVJK3hzdlRBRVc5TVJndlJNa3pMdXpSVDJndXczakQrRmppcDM3eGdLNVFJMFIrQ3NPQW1RUG9UWml6emNJeUFVQXVDSkZDZ3EvZ0QvQ2liTHhveW1pVlVJMWFuOVNudDNLcE5Sb1dkdldJbmUzM1YwcHY4UEhnOXlXMkp1TE9xUUdpbExDc0svUTNvUXIzdXBFTVh4WEdqQ0w3V1VpenZSWkdGRUVWK1ZwbFl0N3Y0dEtaTWo1cGszdmRlTTBNSjVYWmc3UHZVc1J6eWN4Y25yVDNLbm9jM3FNK3R0cVpmVHNiOGQ2VS9wUWlmcTdHdWFoRk9IcnZyb3FnSkxqKy84MVl5MXBaRmtqZkpnWTBYa2x6QW5BNkNGcS9ZVDBneGJWK1RINUlTK1dhWU9VekszNlM4czVxcU13aG5ndjRJekUzY3RYWHFuaElaWE56bnlWQnFiWWEvR3gyYkNqY0VqMm41UnlHWVJTLytNY3VsZ0xCem5ROU1rRzJEN1FQM01xL253SFhLTUlhTFM4Vks4aEczZDByQWpsdm5hdVhTaE5ySnh0a2o0cWt3bnhENExyRWprMXVlK1BMY2JMcVlXd0FyOG4wcys0MWpyc0lQVnl5Szl2RmFFWnJBOUthQnhrSnlpcXg1MEdaTm43Y2t4K21rSTE4Z0g1Mml5VlB0VThGS01YanVnQ2w2bVBMaUhZaURRZCtHNjNMdWRtT0t5czlpdFZuQkRCTk1QMmIvSTcrYklWUmxoZUdhWldyNk1BVEtsODZCM3krMGt1T3JMUk15V2NkaWJjMmlRa1ptKzhmN2RUVXdiS2JCSnNLT0ZZNzMvOG5sTC9KaVlwano2blVJaytJcVNqYUZ5SzZYRmxDY3VrV3BXSHBESm5TdmJFemV5N3FIeUNxSitJK29uOGlQOEdPdGVtcFFhUzAvNGtaR1N3bHJFNnhPajZFd0dwZmpiRFpLSGtQLzJSQWROWVBRcTN6N2JkVkpNSk5uRk16NmUzN216TXBDQmlod1BkU0ZUUkUzU0NZNjZ3dlRnSnpHQ1V5aEhiU2k1aTFhenpPWGQ4dUhDU3BULzZMMW82VlUwcGpvUjhLYWE0d0NXSEdmN1AvV0VkK2F2eXAwMkpudTFjbXBXMCtHcSt2SzloMHRkYjJJQ2xNL2VOZmRvdVFQK2VwOE1KVWpyYURSSUNtQUpRWTVvYlM3MXZuaU9vK3JlYUZ5MHpSZ0IiLCJ0aGlua2luZyI6IiIsInR5cGUiOiJ0aGlua2luZyJ9LHsic2lnbmF0dXJlIjoiQ0FRUy9SRUtFUWdTR0FJNEFVSUpibUZ5Y21GMGFXOXVFZ3dGaDNBVkpaUDNzOHkxSHEwYURHNzZ1aEhPTmFTY1hBR1NoaUl3R2dqTFhIVXgxeVpya0xQbGpqelRPUXljcExKaUtWd1hjeG0vRXpLSm0xczhNNVd4dVJFV0VsZFhjb2FOMC9tc0twa1JNVCtlTGI1aWg5ckFIVUxUb21VTnNVd0pldTBqckplNEdMYXp5N3NQNUt0akVPRUJLUXNYVWZvUTdmRGtaT1FVSFppOXp6UU40aEZObVlKVWYzT1ZxZjlUUU5kQzErbS8vSEFaUGZXbUF5Nkh0RHZtN2tnQkprQ0VvaUZubTd0bi9QWDFoWEdQUmdXYzZCVFhVTXIyV0E4YUt5cWdnUlViTUgyK0pZdjVpV1pkZENjMXVwMU5icjNzRjdXUGNvdDlaQmh5SFFYcjY5MnplSms2U0pneWdJVnJBU2JNbHkyYkJ4VFdKQjYyM2dWZ3pwQ21WU0xaRnBrS1hnUGNwOGhHeURLT3ZGNlNpUVNIcUdSeFFvZnI3VnMxYVBoZlppeFJPSkdEK01scmtnZ1ZBbkdNeVlJRFVacGF2dENlaVUxSm1CU3owMDg0YlhQdFQvdG5wc0tPblNQWVpRbzNCMEJYS2JxQS9Xc0tuZzgvVjNaOFV1YWpvNklWWjJoZ0ExV0RkdXFRT1FrRXhHVTZwRnVMaGViSWp1V3hTTkkvRGZmdlIvL0xOcUNmdmRuZjBodm9QdER4ZngvU2F3SXg0L3NwcTl4YndGekh0TGdvSGcxRjJ3Rnc3Y2xQRGxnMVB5RC92MnlKRzNWOVQ4R0w2akdQRTZyaGZpbC91NEhOdmY3QlcwZFF6Q1RUWGNxWnk0bkJ5eTArcCtTN1p4Zk1sNEtweGEyZ09oaFNOamZwZnVYMFFwTDRrTUU4SjFubGlGTjFkOEtxRVB1REkxOEJRSFVoRC9VZlkyOW9BMHg1MTBGak0vQnNMWjRuNXNwcGtvSWk3Q0ZvUXEyYUFLVk5mQzFLaWxoSXBSRCsxZHlEdFpRa2xOOGdacE9FU0h3Nk1MMVR0VTB5ZkFjYm1xb3hKNmhoanp3SDZDTXNUUUVFeThNYlJCTStRS0trSVJkUkNQSEdGVzJMa3VSNTArSjBwRi90cjZwcVZ2SmVvemZpTW5yRWlsQjI3VFpQNG5LVEpHOHJkLy92Q1dlbjB5N0NBLzhkQko5Z2RwNXR4N05WQTQ1azFnZGN4RVIxZ1lvdU5YM24xdkczL0IxRjQrOTN3WFc5TXFvNlVzNTlUUW1yYjlOcWE3cFNRTlNySDA2dzFHeHlCQWxrRmZxQWxhZmsxNmFNcHE0MTZUSllwR3k0M1dDVWlDY0xXbGhpV2d6MnNnT0xBWFA5YTV3ZVdBS1JDOEo2amtjVWtEZVhuVytIRlNpUE02KzlCbzZrVmhMVWhONXJjNG1IWk9acEY3cHRQcHNRTjRYQ3FMUHNxcFJILzhvNVhweUM2Wm5lVGVGMkV4dGpod1pWalhEd01iSXpWWUlidzF5MlBQR3c4ZEM3cGM0c0lWU25JNG9RQUgwdjY1MGdoZmhtTWV2V1c0aDRQeWxidy9ERzRmZGVUMys4ejBmOE1PU1R0ZmlweDA1L1F0dEhsQXZPRFJ4YTV5REN2T3o2bjNmMUJPME4vNE1iR3lPTTI3cVc0eDhtQlZvcnlVWldmc21oZmkwL0dmTnZCOCt5bFRHYllOWDI3T2NFRjVXWnROcWJXRXk3VjVHYm1aVVN4c3BjZzdGQlozajMvM0w3bXV2WlhvWmkxZjVlcnE0eTNsU0grb0Y3cVBGbnZpZXlMT0N3dWJjUXkrb3lvd2o0Y0QwaWRSZWNucCtzKzUyRDcrbXpGMWdwVytmK2NKYXNveGlnYnhrT2xvUzR5ZWlLdmdNNG5XU3BHRWoxMlJQeDVvODBFbXppWE45dDR6SnpXMWh0QTVoWEpKZUZ5bXBNWXR5Q1VDZXZSV1ZtclJZa3RRN1VuQ2E2dEwvQVZQaTFuaTVYQ1hIZkxPdXFmSzVLTFl4andWdGRoaGZtQ0x2cGFLVk5DRU9DZjRuTkdIcUQ5OHdVYjBlaldOd0RZQm5KR2tCUnc5UlZzcGZ3TmRvV29WY24ycXY4eXdHVXA3eWMvc2syTHBJNlZ6aVJ5dldxYkdORzFaSnFWVnV0UmM0NitzT0U0VlNlUzIvQ1ROS05hNk5NQ2YvaHh4YVVWc1lmS2RQK1MxTGM0aWFuS3Awc1V1Z1BwbXRveWRDMENQMlJ3am5ITGNuenhDbnZxeGxMUVdYTU5QVHN1MnlCY0hsV0pMdGNtZGcvTWNMYWd5N2w1a0c2c043WnhKTEQva0F4OEU2dXFvaFArSy9qTVNyWXVRSm5ocjR0ZjRiaVdGWTNKemYvS3BBWXlWU3ErcGJmRktYTWJMOW5IRW9aUVQxNVd5YWJkNkRNQXEzUVpPdGhNNXBVemROcVVYa2NySTFQd2pBU0FnNGRWVS8ybys5OG1UWG55aFA3VmxFa1RuZGRwd3lKRitZQ0NjMDFwcWE2Wlg5OXBuUitZT3BJcmI1RHRQY0txMHQ1Y0ZDRHlReE4xbFV1cVpjWXVqdlgvR0M3KzZJcFJUei9Oa0VZLzVjbnRPZlpKeWQ2U2tVeC9KUjVBSklSUENOZWliMHJjV25uRm4wWEs4czIyeDQwd0xqRXR1ZlhETzkreXJhZjRrSHhsQkkzU0IwbWVNamVwWDUwQ0poQXg3TmVra1JGbndvZWNMZnFJeXJqWHJnQVpzVE1QaVg5NHNuamRyemlzQVh0QkthbnVsaWxTeE9mVzJIU21mbmswTDJHWEhKSjNTK3ZDYmdSRW1sOWRla2ZtSGhtd0VZdHYza2ZodGg3RVJJd1ZUOGo2OU90SUJDbWVUSUp1QTdvNzNQWGMxTEoyd2h1Wks3RlplNk5UT3M2MU1QN0pWbEljNnRiaHRPQmszTlhVOHBCUE9DWTZRNTVkNjNGdHBVVS9LQ2JRMEsyV1E5bzVqTkd3Tk5KNkN3NUZEQ3QreDVZSmVQMWQyUXpEU2lxK2NTWnF3cUNaVmNOb0FmdEdHemdyUlo0dmtwYlAweFFaSEN0V3NVd0hWVGpyWTROZlJEakhkVlBSbjhKOVh0b29jL2hJV2txekZhY3pZVGxhcHUyUkNKcWU4YUVvM2p6V1pDRUo3QWlCekJZcmFZRGdPZmVpUXllSlVzYmJYSGRHS2lpdzIyQmRwNE0rWXo2NzFNWjBpZTlFV1JrczBRMkRIR1VUbmU5UzR0QUFKUEdiVWY0eHRDTW9KNDBRNFFXMDVRTFNaeTN3TkZBVUZZbVhFNEVDREZCOCtJRWVORkZGL3RnQW5maDhHdkZoLzF4WStMRStvek1taW5qU1J3aHEwOXpRQUVrTkZ5dTBJS2d2RGt5T0kraWNjRjdkb1dMVFVhc1B4TEgxeEdQQlNLa2VXQ25Tb1gvNEMyYzlkdTY2QmJSWGFtSHFhZStWQ2lTNkJOOTUzaVlLT3U4ck1rbmVXK1RGalYwQ3pBZjhQTkc5TEJheVVnWTVVdzl4MFNhcDZ6STRQcGFaS0g0ZDlrdGtGVSs5MXlCYk41U1J0ZGQ4L0VRYXRKWG1CTmZ3N2tScmxsK0xqd1p3ZVdMRWIwalQxUnBHdURxSExkTFRNTWdvd1NjenJwMnpDc0pkUUgvc2VhWXJwd2tDRlI4ZFJqTTdKUlVrVmExQTBTdmRaQVg3NXZ1QnZ2TEJ6TjJjK1JidDVvcXk5M2xxSUJJaktiN3cyVWtSVGI0cEJXY05LTlBVZ3QzYXovUHhReEVhc2FsdGRtdXl2c1hZYnVyM1ZQTm44SnpOLzZKNU4rUUNuejU3MVRjY2FwQ21rUHZGRStnYXlYVStVRjFWS1l5RmNVdmxldjdsc1FsbWpxeksyUUE4WDdRM1R6RmFwcWh2SktsdDdkekJIcmFxWkJnUGdiOU40b0tOYXlpOEZaVDcxK2thWWhJaEZyRVNLWVJIZkhrajVuM2tmaGdMeSt4K2pMRGJLeE1nZ2tnSG5KejlSdUVIWlhCV3RrWUFRPT0iLCJ0aGlua2luZyI6IiIsInR5cGUiOiJ0aGlua2luZyJ9LHsiaWQiOiJ0b29sdV8wMUg2ZlY4SnZSSk52WHk0N2VSbmQzakgiLCJjYWxsZXIiOnsidHlwZSI6ImRpcmVjdCJ9LCJpbnB1dCI6e30sIm5hbWUiOiJ0cmFuc2Zlcl90b192ZXJpZmllciIsInR5cGUiOiJ0b29sX3VzZSIsInRvb2xzZXRfbmFtZSI6bnVsbH1dLCJhZGRpdGlvbmFsX2t3YXJncyI6e30sInJlc3BvbnNlX21ldGFkYXRhIjp7ImlkIjoibXNnXzAxMUNmZHdBTVJkUzIxRmVKZnpRaE0zcyIsImNvbnRhaW5lciI6bnVsbCwiZGlhZ25vc3RpY3MiOm51bGwsIm1vZGVsIjoiY2xhdWRlLXNvbm5ldCIsInN0b3BfZGV0YWlscyI6bnVsbCwic3RvcF9yZWFzb24iOiJ0b29sX3VzZSIsInN0b3Bfc2VxdWVuY2UiOm51bGwsInVzYWdlIjp7ImNhY2hlX2NyZWF0aW9uIjp7ImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjB9LCJjYWNoZV9jcmVhdGlvbl9pbnB1dF90b2tlbnMiOjAsImNhY2hlX3JlYWRfaW5wdXRfdG9rZW5zIjowLCJpbmZlcmVuY2VfZ2VvIjoiZ2xvYmFsIiwiaW5wdXRfdG9rZW5zIjo3Mzk2LCJvdXRwdXRfdG9rZW5zIjo3NzAsIm91dHB1dF90b2tlbnNfZGV0YWlscyI6eyJ0aGlua2luZ190b2tlbnMiOjczOX0sInNlcnZlcl90b29sX3VzZSI6bnVsbCwic2VydmljZV90aWVyIjoic3RhbmRhcmQifSwibW9kZWxfbmFtZSI6ImNsYXVkZS1zb25uZXQiLCJtb2RlbF9wcm92aWRlciI6ImFudGhyb3BpYyJ9LCJ0eXBlIjoiYWkiLCJuYW1lIjoic2tlcHRpYyIsImlkIjoibGNfcnVuLS0wMWEwZmUwMy00YWU5LTc2YzAtODlhNi00ZjBiMTE0ZTMwMzAtMCIsInRvb2xfY2FsbHMiOlt7Im5hbWUiOiJ0cmFuc2Zlcl90b192ZXJpZmllciIsImFyZ3MiOnt9LCJpZCI6InRvb2x1XzAxSDZmVjhKdlJKTnZYeTQ3ZVJuZDNqSCIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6NzM5Niwib3V0cHV0X3Rva2VucyI6NzcwLCJ0b3RhbF90b2tlbnMiOjgxNjYsImlucHV0X3Rva2VuX2RldGFpbHMiOnsiY2FjaGVfcmVhZCI6MCwiY2FjaGVfY3JlYXRpb24iOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjB9LCJvdXRwdXRfdG9rZW5fZGV0YWlscyI6eyJyZWFzb25pbmciOjczOX19fSx7ImNvbnRlbnQiOiJTdWNjZXNzZnVsbHkgdHJhbnNmZXJyZWQgdG8gdmVyaWZpZXIiLCJhZGRpdGlvbmFsX2t3YXJncyI6e30sInJlc3BvbnNlX21ldGFkYXRhIjp7fSwidHlwZSI6InRvb2wiLCJuYW1lIjoidHJhbnNmZXJfdG9fdmVyaWZpZXIiLCJpZCI6ImMwNjQ1NjNhLTk3NGYtNGYwZi1hYjRhLTA4MGU2M2MwMWNmNSIsInRvb2xfY2FsbF9pZCI6InRvb2x1XzAxSDZmVjhKdlJKTnZYeTQ3ZVJuZDNqSCIsInN0YXR1cyI6InN1Y2Nlc3MifSx7ImNvbnRlbnQiOlt7InNpZ25hdHVyZSI6IkNBUVM5Z1VLRUFnU0dBSTRBVUlJZEdocGJtdHBibWNTREdGeUoxTVhvWStBaTZOa2J4b01SZDJUclVmVVU3V3JQcEEySWpEZ3k4ZFVwbGNaS2M3RG5Kd05MVEJmSDVVTlIrbkduYWtTUFFpYThVVkl6cmprT25KMmZMcldVc0Eyb0VPOHlSc3Frd1hra0RDc3loQjk3ZHdqNTdSTXQ5MVh6Z1doTDlsdU5FR085MnlXMHJORkdvTVNVVk94UElyRmM1Ump5cmhLRWMzKzFSbnB4Q2t5bHErTE5sUTVORnhMbjZ2MmNGNUR6cXB2QkhOUjdYQWlnK3VySklVM2dYeWRDa2FHWlpEZXRKdFFPVU9YZ1ppOXo5MTAwTnBkQUVrWERvMklDSENHVEdwVmMwSi9wYlh4V1JCeGI2QjEvR2wwWWpuNjhWNkhsZXNIN0lvQzdHUi8zSHdSdTlOU0RCRzR0dGZRakVXY2crUGVBZWE0Um43anp4K1RtOUg3TDFqb1RLVmdEYlFnNWlLTUxmanZQcWxua3NDTHRYT3Q4alNJUzVPWUxON2EvN1RYNi93NWQzNHZudzh2UERtVTFVWWkwUTcycVVXaFVhMnZ3OE9YTnBjS0w3QnAwbE5mQlM4cnZIWSt2Qlk4L2hhQW9UTDN3dkxGVTFmVCs0ei92QTNCY3NpZ1pEWWxmSmVEWWN4WG1SdXF4enhFR3BYQ1JlOXMxSFd0SUQrNDFwSHU2bHBaSGtYYWdocGM2VFpITHhOd2NWaFRiNmZNUTdRbysyTDZQdmtsaDFtMzJwZW9keGVnMllpUGhkcGwzdy94a09FdTUvSkVGN1pCeHBkVUwrdTN3a081cFVsc3FmZ1g3dWh6djdIQzJXcFNXVmltcndpUXdRT1V4MCtKUHJMdHcrbFlmcTdJM2pydW8wR1cwZ3VXdm51ZjdKTTNZTGo4NHErSmdIb21uU1Nabm5abXJMMFVhUnZyVnlMbzg3N0YzOWNjTFM3WG9abm51aThKNFA1OFpUbWlMa0VKZUdjeDFJdWFnMmUzMzMzOU83WWV3LzU5dExiUXRJR2g5VldNd0hCbkZ4MzlTOC80TEVGcks1SGxkUFFoT3Jsb3lUdGtSczY2aVFSS3R4TUtTMFZJNlFUS1pEQWJzN2E3SDF5QnYrbUppOVhnNHVLbXlVNnFubjd6RUtqalkyYklsQ3dleng0TExHUDVIRDNacjZmWnNtZEcxVUh6RHNCdllHMm9DSTBvcUVLTSt2YWxzVDZoVThNUmpiUUJEL0pKOEpKTi9pQkdsaEJBVUhvMFVtaGh0UjJldVRWcFpXbE1uaG1wWEFkS0RYU2ZQZGFQb2hnQiIsInRoaW5raW5nIjoiIiwidHlwZSI6InRoaW5raW5nIn0seyJpZCI6InRvb2x1XzAxWEVBdWhRSENCZHlDd3R5bVp3RmZEaSIsImNhbGxlciI6eyJ0eXBlIjoiZGlyZWN0In0sImlucHV0Ijp7fSwibmFtZSI6InRyYW5zZmVyX3RvX3JlZF90ZWFtIiwidHlwZSI6InRvb2xfdXNlIiwidG9vbHNldF9uYW1lIjpudWxsfV0sImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnsiaWQiOiJtc2dfMDExQ2Zkd0FzYWJEcXVlZ0hpNllVcENuIiwiY29udGFpbmVyIjpudWxsLCJkaWFnbm9zdGljcyI6bnVsbCwibW9kZWwiOiJjbGF1ZGUtc29ubmV0Iiwic3RvcF9kZXRhaWxzIjpudWxsLCJzdG9wX3JlYXNvbiI6InRvb2xfdXNlIiwic3RvcF9zZXF1ZW5jZSI6bnVsbCwidXNhZ2UiOnsiY2FjaGVfY3JlYXRpb24iOnsiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MH0sImNhY2hlX2NyZWF0aW9uX2lucHV0X3Rva2VucyI6MCwiY2FjaGVfcmVhZF9pbnB1dF90b2tlbnMiOjAsImluZmVyZW5jZV9nZW8iOiJnbG9iYWwiLCJpbnB1dF90b2tlbnMiOjc1MDksIm91dHB1dF90b2tlbnMiOjg4LCJvdXRwdXRfdG9rZW5zX2RldGFpbHMiOnsidGhpbmtpbmdfdG9rZW5zIjo1NX0sInNlcnZlcl90b29sX3VzZSI6bnVsbCwic2VydmljZV90aWVyIjoic3RhbmRhcmQifSwibW9kZWxfbmFtZSI6ImNsYXVkZS1zb25uZXQiLCJtb2RlbF9wcm92aWRlciI6ImFudGhyb3BpYyJ9LCJ0eXBlIjoiYWkiLCJuYW1lIjoidmVyaWZpZXIiLCJpZCI6ImxjX3J1bi0tMDFhMGZlMDMtNjY4Mi03ZDIxLThjMTUtZmZiY2U5NDIyYzlmLTAiLCJ0b29sX2NhbGxzIjpbeyJuYW1lIjoidHJhbnNmZXJfdG9fcmVkX3RlYW0iLCJhcmdzIjp7fSwiaWQiOiJ0b29sdV8wMVhFQXVoUUhDQmR5Q3d0eW1ad0ZmRGkiLCJ0eXBlIjoidG9vbF9jYWxsIn1dLCJpbnZhbGlkX3Rvb2xfY2FsbHMiOltdLCJ1c2FnZV9tZXRhZGF0YSI6eyJpbnB1dF90b2tlbnMiOjc1MDksIm91dHB1dF90b2tlbnMiOjg4LCJ0b3RhbF90b2tlbnMiOjc1OTcsImlucHV0X3Rva2VuX2RldGFpbHMiOnsiY2FjaGVfcmVhZCI6MCwiY2FjaGVfY3JlYXRpb24iOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjB9LCJvdXRwdXRfdG9rZW5fZGV0YWlscyI6eyJyZWFzb25pbmciOjU1fX19LHsiY29udGVudCI6IlN1Y2Nlc3NmdWxseSB0cmFuc2ZlcnJlZCB0byByZWRfdGVhbSIsImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnt9LCJ0eXBlIjoidG9vbCIsIm5hbWUiOiJ0cmFuc2Zlcl90b19yZWRfdGVhbSIsImlkIjoiOTgyYzAxMjYtZTZhYi00NThhLTkyMmUtN2IyNjZlODNjMmIyIiwidG9vbF9jYWxsX2lkIjoidG9vbHVfMDFYRUF1aFFIQ0JkeUN3dHltWndGZkRpIiwic3RhdHVzIjoic3VjY2VzcyJ9LHsiY29udGVudCI6W3sic2lnbmF0dXJlIjoiQ0FRU3dnY0tFQWdTR0FJNEFVSUlkR2hwYm10cGJtY1NET1JYZ2U5dUwxODMyUk1Rd0JvTWpRd0F3QUhiOWlQMW9qUEdJakREU2NhbDQ4NmJlQ0pidEc4L0QyWTlnOVM1eElQZmpvSGcvZHh3WDVIeXBTUUVCYmpGaVRTYlBFQ1hTRnpWNllJcTN3YkxjbXlQYnZ1c0duRGV4Rmd4KzNzSVh6dnF5RlYvNjl4aGloTW5TcGZUQ0h5MCswelN1MVdwWVUvV1VwSWZvYVNYVGNUYTFxa004eDhFay95LzFqa0tNWlVmREZhOTN1aFVKeE9DNCtRZ1BXQmwvK1h5MnQ4MkwyeC9lYnE3UUxRVHF0UjBqWGVhVVJRbTNDbzZKdk9nV21Edk1wRWRUZVRXRTNmRGgxdHp6VktzZmx1bTRkODliNkNhS3RuOG5sUWQ3UmhOOTl2TlFNUUhHNVY0T3VWTmRySFBaWnBGT3VoZGVqc01GV1h5Qis1NXNsR0FkOHdFWGdGS2JJL2tuT1hWR3pML05ERjhHdHkxdE5abHUyZmRTQ0FzWVdNc0ZRUDFjYndMZVFHc3p5WHpKTVZaSjJJOXhCUGt5ejFIT1hDUHloNUYrajJnUlRQaWtWQjNBUkM2dGZCL2xEU1VlS0JWWlBRUzhwWS9CNGVDcytJamphQk5XcnVMemZxQ3NjNnhMMEN1UVBTWXlRWGFZRmpZclNSTmNDNzBXUUJXVDVWVmhwMG1BOXlaREdZYlJadDlJNU9LOVFrUW11SjV6REZhTUVPWHpTcnNDNGx0ZVA2TWRpbWlNaWp2c0gzaXErYzZXVVlvbFJqM25lSTg4RWFISXpMQUdScTY0Qk5DTHpkQVlMMnBFVTJzYjV1Rzc4UEtWb1VVQ2JWSkw1anBET2hMT1RPMWJRc1R1b1VwblJSckxRRC9rSXpWK2xqcFZCd3dmSmN5cTc1VEpBL0N0UHIveHIyU1o5QjFiMnNiakc2akQwbGh0b0NkZGVEZ2NxZ2wvTFNTa2N1YVlZOHhQV0N5K0x0TmhjcVRoZm1mdm5ITEpJcEw2Z2pialcvT1FwUmZWVXdmdzFqT2I5YldWd2NnSGhOWWZLWUdQdE04b3RoNXh3TFlSUlZnenFNS092czdmYWxYUmhWeloyU1A2SXcwQk1tQUFaNkhqZkNsOUwrdFBxSk5sblFRT0hwb1dqdW00QitYc1lsZEZFS0dRV1Fxc2Q1OWlOUHZhbzlwL3NDT3Q3ckdxQ296Y21naUVtNHc2NmV6L1FJRHliNDZuMCt0Y05KUFVjb0JLdlEvakR3RTZWd21rUS9uRUNqRnAzVWREVCtrV1lRU05kOGo4VkJaT3BHOExscVVZckVaQ3YwcTdCczF2Y05yZFlpYUZvUzMyb3NheW5XaytIdDNPSHVGV2JFRjhKbHNGVFFBTzA1VnZZa2VjZjBWL29USHNHNWh5T09zN1VFYURGcTd1YUp1eldWaGg1cEFvaklhQmNSOGZWbG4yUExSVFg3aXMybnNBK1FyZGlkZVBjWnRGdGd4QWlLWWUxaTJzU0ZpNHZtOEVPa0NiUTYzd2RRZVk0VXJyNVB1b01Fd3hVVUxqZ0thZ2lBbXNKRHE0UnJWbTdzTzQrNll1QTlqNmwydXlsa09FYzY3dmYvNWZrWHVDc2lBcE5MNmtlYjhjK3ZMMG40RlhHZHpqK2FwU0RmRkdCZ0IiLCJ0aGlua2luZyI6IiIsInR5cGUiOiJ0aGlua2luZyJ9LHsiaWQiOiJ0b29sdV8wMVZCcldkV0VXWWdpdDRrTlllaEJNVTUiLCJjYWxsZXIiOnsidHlwZSI6ImRpcmVjdCJ9LCJpbnB1dCI6e30sIm5hbWUiOiJ0cmFuc2Zlcl90b19lZGl0b3IiLCJ0eXBlIjoidG9vbF91c2UiLCJ0b29sc2V0X25hbWUiOm51bGx9XSwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6eyJpZCI6Im1zZ18wMTFDZmR3QXpmanFVb3BvRW1aTGFxbTEiLCJjb250YWluZXIiOm51bGwsImRpYWdub3N0aWNzIjpudWxsLCJtb2RlbCI6ImNsYXVkZS1zb25uZXQiLCJzdG9wX2RldGFpbHMiOm51bGwsInN0b3BfcmVhc29uIjoidG9vbF91c2UiLCJzdG9wX3NlcXVlbmNlIjpudWxsLCJ1c2FnZSI6eyJjYWNoZV9jcmVhdGlvbiI6eyJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowfSwiY2FjaGVfY3JlYXRpb25faW5wdXRfdG9rZW5zIjowLCJjYWNoZV9yZWFkX2lucHV0X3Rva2VucyI6MCwiaW5mZXJlbmNlX2dlbyI6Imdsb2JhbCIsImlucHV0X3Rva2VucyI6NzQxNiwib3V0cHV0X3Rva2VucyI6MTUxLCJvdXRwdXRfdG9rZW5zX2RldGFpbHMiOnsidGhpbmtpbmdfdG9rZW5zIjoxMTl9LCJzZXJ2ZXJfdG9vbF91c2UiOm51bGwsInNlcnZpY2VfdGllciI6InN0YW5kYXJkIn0sIm1vZGVsX25hbWUiOiJjbGF1ZGUtc29ubmV0IiwibW9kZWxfcHJvdmlkZXIiOiJhbnRocm9waWMifSwidHlwZSI6ImFpIiwibmFtZSI6InJlZF90ZWFtIiwiaWQiOiJsY19ydW4tLTAxYTBmZTAzLTZjZTYtNzI1MS1iNzk2LTRmNjQzMzNmNjdjNi0wIiwidG9vbF9jYWxscyI6W3sibmFtZSI6InRyYW5zZmVyX3RvX2VkaXRvciIsImFyZ3MiOnt9LCJpZCI6InRvb2x1XzAxVkJyV2RXRVdZZ2l0NGtOWWVoQk1VNSIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6NzQxNiwib3V0cHV0X3Rva2VucyI6MTUxLCJ0b3RhbF90b2tlbnMiOjc1NjcsImlucHV0X3Rva2VuX2RldGFpbHMiOnsiY2FjaGVfcmVhZCI6MCwiY2FjaGVfY3JlYXRpb24iOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjB9LCJvdXRwdXRfdG9rZW5fZGV0YWlscyI6eyJyZWFzb25pbmciOjExOX19fSx7ImNvbnRlbnQiOiJTdWNjZXNzZnVsbHkgdHJhbnNmZXJyZWQgdG8gZWRpdG9yIiwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6e30sInR5cGUiOiJ0b29sIiwibmFtZSI6InRyYW5zZmVyX3RvX2VkaXRvciIsImlkIjoiNWQzOWUzNmItYzViNS00NDI2LWE5YWEtYmUyZjdkMzgxNmQ2IiwidG9vbF9jYWxsX2lkIjoidG9vbHVfMDFWQnJXZFdFV1lnaXQ0a05ZZWhCTVU1Iiwic3RhdHVzIjoic3VjY2VzcyJ9LHsiY29udGVudCI6W3sic2lnbmF0dXJlIjoiQ0FRUzVnWUtFQWdTR0FJNEFVSUlkR2hwYm10cGJtY1NESTRRSWI3TDJ3NWFXM2NNL1JvTUxpMndFeERrcWh1eEpEaVlJakFxR3hNNFdVd2lxNHVaSHJpQ2J1QzRrVndhN2lnZFVMb29jWmJpNWZldktiZndxSFNickxOVDUxTkdYNFhzTHRzcWd3WS90YWJIamxsenF1N25SV3Y4K0Z6NFI2bjlqYTdDcGoyNFp1eEZ1S2trUU9CbUE0VGYxYXBrM1JQcWNFUStqK3dlZHUwbE8rcmRFQ3lkM2xYaGZnRVJGRnFjTTZhdWN4ZWw0UmJ3NW9BSFh1OStYZVR0emwrTjh0QWVaOWlHWjJYVHRVNU9iOGFQVDFLdVgrdXA4a1E0VlVYa0JUZmQyZjVKUDlSeFpFcTl3U1lhWnN5SGR2MG4rMVU0NkFPc3ZLWm1wOVFYQndvMmY0TzkwalA4ZWdpcmVtOUViWmJtYVlPSjhXSzdDdEtSVmJZMnk0Kzl4UlVKMDRuc2RJejVGNUZGS0V4eE5PckI0bWMvTkU4M2FiM1o2NGlXek93cW9VR0FHUVNrYUgwZDVjRXVtWm80ZlpaQWhQeXVKZVFEeHVsTUNld243RUdDbnBKdy9uemkwd295RWFRTDRZN2g5OVA3YVh4RnIyOHA1S0N5SkVKVERlZmVJcFZsQXdNQ0Fqeit4QzY5QUFMbXd5VFErY0ZFTStLQWdlSVNwaExWeThBUHIyRlNoYXhCTnJYUWd6MXM5czJkaExaUU9CaXd6aHhtRWdkSzcrOEphcWhCMGVFRWQvMVJWQXVJWWRlekE1SEJyd0U5RHlRaUNsM1VPc2JTbk5FVmUrZ3JIcDVwM3RtTUJxNjhnTFY4Mm9BekZZWmwrQ2V3eDcxdjVkUEZPdktQRUhVenBRWU9WTHJuQjFFWlJZclp6NzJuMndmU1Z4Qk96cFRjbkJ4VjZIZWRDUHlJektYWk05K3lFZVRKaThRdHZWZ1oxdyt2MGhtQ0ZHcG5tWk43bVhsZ3FMMXM2TVhWeWRwUE9LUGxNM05hN0NkSG5QRllpd3Iyekx2a2tjSU03Q3NrL0MzK1pNQVdUSytDOUIxdmJHeFBsdEUzT3Y4a085OFBnU1htMUFKdUViWHkrcjNhM0QzUWxaSjNkRUtlMkxOZEFCeXJQTWhTY0tVOEdsZkgvOU50Z3JodGFrZ2xsRC9NZkFsVHNiTndORHJVdFdSeG1EdUovMForaGtrL1lOd0VEWUFaYThUbXdWb1dPZEJIcFJQSHZaOUU5dXNldWx0bWErSmsxZ1JMRHR2RVprcVhVRVNrTWNxVXRWd1lNNWFqSkE1TjUyY05pWjE1QlRmOFhqR2hLV2RPVjQwKzhIMFBPU3hNMkppZndDTzBDNXhGVzVCbzNJaUlOdjBVT3RZNWY4a3ZQZE0zUGpraGFPcksxeVRBOGVFRTQ0dnVuTDlQa29HZWNiWW0rWEU1S3pMM1FzRW4yWTFJSndPOXcweEhYUVpFZWlQNSswdTNZbkRjOHE5ZEJMaEdXM0Z5MzBnWUFRPT0iLCJ0aGlua2luZyI6IiIsInR5cGUiOiJ0aGlua2luZyJ9LHsiaWQiOiJ0b29sdV8wMUJtOEFVOUVzUVV3cW9WTFlweEtBNzciLCJjYWxsZXIiOnsidHlwZSI6ImRpcmVjdCJ9LCJpbnB1dCI6eyJmaWxlX3BhdGgiOiIvYW5zd2VyLm1kIiwiY29udGVudCI6IioqVHVwbGUgdnMuIGxpc3QgaW1tdXRhYmlsaXR5IChQeXRob24pKipcblxuQSB0dXBsZSBpcyBpbW11dGFibGU6IG9uY2UgY3JlYXRlZCwgeW91IGNhbid0IGFzc2lnbiB0byBpdHMgaXRlbXMsIGFuZCB0aGUgY29sbGVjdGlvbiBvZiBvYmplY3RzIGl0IHJlZmVyZW5jZXMgY2FuJ3QgY2hhbmdlLiBgdFswXSA9IDFgIHJhaXNlcyBgVHlwZUVycm9yYC4gQSBsaXN0IGlzIG11dGFibGU6IHlvdSBjYW4gY2hhbmdlIGl0IGluIHBsYWNlIHdpdGggaW5kZXggb3Igc2xpY2UgYXNzaWdubWVudCwgYGFwcGVuZCgpYCwgYGV4dGVuZCgpYCwgYHNvcnQoKWAgYW5kIHNpbWlsYXIgbWV0aG9kcy5cblxuVHVwbGUgaW1tdXRhYmlsaXR5IGlzIHNoYWxsb3cuIElmIGEgdHVwbGUgaG9sZHMgYSBtdXRhYmxlIG9iamVjdCwgc3VjaCBhcyBhIGxpc3QsIHRoYXQgaW5uZXIgb2JqZWN0IGNhbiBzdGlsbCBjaGFuZ2UsIGFuZCBzbyB0aGUgdHVwbGUncyB2YWx1ZSBjaGFuZ2VzLiBCZWNhdXNlIG9mIHRoaXMsIGEgdHVwbGUgY2FuIGJlIGEgYGRpY3RgIGtleSBvciBgc2V0YCBtZW1iZXIgb25seSBpZiBldmVyeXRoaW5nIGluc2lkZSBpdCBpcyBoYXNoYWJsZS4gQSBsaXN0IGNhbiBuZXZlciBiZSBhIGtleS5cblxuU291cmNlczpcbi0gaHR0cHM6Ly9kb2NzLnB5dGhvbi5vcmcvMy90dXRvcmlhbC9kYXRhc3RydWN0dXJlcy5odG1sXG4tIGh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvcmVmZXJlbmNlL2RhdGFtb2RlbC5odG1sXG4tIGh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvbGlicmFyeS9zdGR0eXBlcy5odG1sXG4ifSwibmFtZSI6IndyaXRlX2ZpbGUiLCJ0eXBlIjoidG9vbF91c2UiLCJ0b29sc2V0X25hbWUiOm51bGx9XSwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6eyJpZCI6Im1zZ18wMTFDZmR3QkJhYTlnak1DY2UxNlRVZW4iLCJjb250YWluZXIiOm51bGwsImRpYWdub3N0aWNzIjpudWxsLCJtb2RlbCI6ImNsYXVkZS1zb25uZXQiLCJzdG9wX2RldGFpbHMiOm51bGwsInN0b3BfcmVhc29uIjoidG9vbF91c2UiLCJzdG9wX3NlcXVlbmNlIjpudWxsLCJ1c2FnZSI6eyJjYWNoZV9jcmVhdGlvbiI6eyJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowfSwiY2FjaGVfY3JlYXRpb25faW5wdXRfdG9rZW5zIjowLCJjYWNoZV9yZWFkX2lucHV0X3Rva2VucyI6MCwiaW5mZXJlbmNlX2dlbyI6Imdsb2JhbCIsImlucHV0X3Rva2VucyI6ODEyNywib3V0cHV0X3Rva2VucyI6NDMzLCJvdXRwdXRfdG9rZW5zX2RldGFpbHMiOnsidGhpbmtpbmdfdG9rZW5zIjo3OX0sInNlcnZlcl90b29sX3VzZSI6bnVsbCwic2VydmljZV90aWVyIjoic3RhbmRhcmQifSwibW9kZWxfbmFtZSI6ImNsYXVkZS1zb25uZXQiLCJtb2RlbF9wcm92aWRlciI6ImFudGhyb3BpYyJ9LCJ0eXBlIjoiYWkiLCJuYW1lIjoiZWRpdG9yIiwiaWQiOiJsY19ydW4tLTAxYTBmZTAzLTc2ZTktN2NhMy1hNWZmLTYzZGU2NmRkOGRkMS0wIiwidG9vbF9jYWxscyI6W3sibmFtZSI6IndyaXRlX2ZpbGUiLCJhcmdzIjp7ImZpbGVfcGF0aCI6Ii9hbnN3ZXIubWQiLCJjb250ZW50IjoiKipUdXBsZSB2cy4gbGlzdCBpbW11dGFiaWxpdHkgKFB5dGhvbikqKlxuXG5BIHR1cGxlIGlzIGltbXV0YWJsZTogb25jZSBjcmVhdGVkLCB5b3UgY2FuJ3QgYXNzaWduIHRvIGl0cyBpdGVtcywgYW5kIHRoZSBjb2xsZWN0aW9uIG9mIG9iamVjdHMgaXQgcmVmZXJlbmNlcyBjYW4ndCBjaGFuZ2UuIGB0WzBdID0gMWAgcmFpc2VzIGBUeXBlRXJyb3JgLiBBIGxpc3QgaXMgbXV0YWJsZTogeW91IGNhbiBjaGFuZ2UgaXQgaW4gcGxhY2Ugd2l0aCBpbmRleCBvciBzbGljZSBhc3NpZ25tZW50LCBgYXBwZW5kKClgLCBgZXh0ZW5kKClgLCBgc29ydCgpYCBhbmQgc2ltaWxhciBtZXRob2RzLlxuXG5UdXBsZSBpbW11dGFiaWxpdHkgaXMgc2hhbGxvdy4gSWYgYSB0dXBsZSBob2xkcyBhIG11dGFibGUgb2JqZWN0LCBzdWNoIGFzIGEgbGlzdCwgdGhhdCBpbm5lciBvYmplY3QgY2FuIHN0aWxsIGNoYW5nZSwgYW5kIHNvIHRoZSB0dXBsZSdzIHZhbHVlIGNoYW5nZXMuIEJlY2F1c2Ugb2YgdGhpcywgYSB0dXBsZSBjYW4gYmUgYSBgZGljdGAga2V5IG9yIGBzZXRgIG1lbWJlciBvbmx5IGlmIGV2ZXJ5dGhpbmcgaW5zaWRlIGl0IGlzIGhhc2hhYmxlLiBBIGxpc3QgY2FuIG5ldmVyIGJlIGEga2V5LlxuXG5Tb3VyY2VzOlxuLSBodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL3R1dG9yaWFsL2RhdGFzdHJ1Y3R1cmVzLmh0bWxcbi0gaHR0cHM6Ly9kb2NzLnB5dGhvbi5vcmcvMy9yZWZlcmVuY2UvZGF0YW1vZGVsLmh0bWxcbi0gaHR0cHM6Ly9kb2NzLnB5dGhvbi5vcmcvMy9saWJyYXJ5L3N0ZHR5cGVzLmh0bWxcbiJ9LCJpZCI6InRvb2x1XzAxQm04QVU5RXNRVXdxb1ZMWXB4S0E3NyIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6ODEyNywib3V0cHV0X3Rva2VucyI6NDMzLCJ0b3RhbF90b2tlbnMiOjg1NjAsImlucHV0X3Rva2VuX2RldGFpbHMiOnsiY2FjaGVfcmVhZCI6MCwiY2FjaGVfY3JlYXRpb24iOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjB9LCJvdXRwdXRfdG9rZW5fZGV0YWlscyI6eyJyZWFzb25pbmciOjc5fX19LHsiY29udGVudCI6IlVwZGF0ZWQgZmlsZSAvYW5zd2VyLm1kIiwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6e30sInR5cGUiOiJ0b29sIiwibmFtZSI6IndyaXRlX2ZpbGUiLCJpZCI6ImUzNDkyZTA4LWM4NjktNDdlYy1hNWY3LWNjNTdlYTVmNjQwMyIsInRvb2xfY2FsbF9pZCI6InRvb2x1XzAxQm04QVU5RXNRVXdxb1ZMWXB4S0E3NyIsInN0YXR1cyI6InN1Y2Nlc3MifSx7ImNvbnRlbnQiOiJJIHdyb3RlIHRoZSBhbnN3ZXIgdG8gYC9hbnN3ZXIubWRgLiBJdCBpcyBhYm91dCAxMDAgd29yZHMsIHVuZGVyIHRoZSAxMjAtd29yZCBsaW1pdC5cblxuSSBkaWQgbm90IGdldCBhIHNrZXB0aWMgb3IgdmVyaWZpZXIgY2hlY2suIEkgaGFuZGVkIG9mZiB0byBib3RoLCBidXQgbmVpdGhlciByZXR1cm5lZCBhbnkgZmVlZGJhY2suIEkgYWxzbyB0cmllZCB0byBoYW5kIG9mZiB0byBhIGByZWRfdGVhbWAgYWdlbnQsIGFuZCB0aGF0IHRyYW5zZmVyIGlzbid0IG9uZSBvZiB0aGUgdG9vbHMgSSB3YXMgZ2l2ZW4uIEkgdGhlbiB3cm90ZSB0aGUgYW5zd2VyIG15c2VsZiBmcm9tIHRoZSBvZmZpY2lhbCBQeXRob24gZG9jdW1lbnRhdGlvbiBzZWFyY2ggcmVzdWx0cy4gSSBkaWRuJ3Qgb3BlbiB0aGUgcGFnZXMgZGlyZWN0bHkuXG5cbioqVHVwbGUgdnMuIGxpc3QgaW1tdXRhYmlsaXR5IChQeXRob24pKipcblxuQSB0dXBsZSBpcyBpbW11dGFibGU6IG9uY2UgY3JlYXRlZCwgeW91IGNhbid0IGFzc2lnbiB0byBpdHMgaXRlbXMsIGFuZCB0aGUgY29sbGVjdGlvbiBvZiBvYmplY3RzIGl0IHJlZmVyZW5jZXMgY2FuJ3QgY2hhbmdlLiBgdFswXSA9IDFgIHJhaXNlcyBgVHlwZUVycm9yYC4gQSBsaXN0IGlzIG11dGFibGU6IHlvdSBjYW4gY2hhbmdlIGl0IGluIHBsYWNlIHdpdGggaW5kZXggb3Igc2xpY2UgYXNzaWdubWVudCwgYGFwcGVuZCgpYCwgYGV4dGVuZCgpYCwgYHNvcnQoKWAgYW5kIHNpbWlsYXIgbWV0aG9kcy5cblxuVHVwbGUgaW1tdXRhYmlsaXR5IGlzIHNoYWxsb3cuIElmIGEgdHVwbGUgaG9sZHMgYSBtdXRhYmxlIG9iamVjdCwgc3VjaCBhcyBhIGxpc3QsIHRoYXQgaW5uZXIgb2JqZWN0IGNhbiBzdGlsbCBjaGFuZ2UsIGFuZCBzbyB0aGUgdHVwbGUncyB2YWx1ZSBjaGFuZ2VzLiBCZWNhdXNlIG9mIHRoaXMsIGEgdHVwbGUgY2FuIGJlIGEgYGRpY3RgIGtleSBvciBgc2V0YCBtZW1iZXIgb25seSBpZiBldmVyeXRoaW5nIGluc2lkZSBpdCBpcyBoYXNoYWJsZS4gQSBsaXN0IGNhbiBuZXZlciBiZSBhIGtleS5cblxuU291cmNlczpcbi0gaHR0cHM6Ly9kb2NzLnB5dGhvbi5vcmcvMy90dXRvcmlhbC9kYXRhc3RydWN0dXJlcy5odG1sXG4tIGh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvcmVmZXJlbmNlL2RhdGFtb2RlbC5odG1sXG4tIGh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvbGlicmFyeS9zdGR0eXBlcy5odG1sIiwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6eyJpZCI6Im1zZ18wMTFDZmR3QlVzTmhyMTlnUU5WY0ZzVWUiLCJjb250YWluZXIiOm51bGwsImRpYWdub3N0aWNzIjpudWxsLCJtb2RlbCI6ImNsYXVkZS1zb25uZXQiLCJzdG9wX2RldGFpbHMiOm51bGwsInN0b3BfcmVhc29uIjoiZW5kX3R1cm4iLCJzdG9wX3NlcXVlbmNlIjpudWxsLCJ1c2FnZSI6eyJjYWNoZV9jcmVhdGlvbiI6eyJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowfSwiY2FjaGVfY3JlYXRpb25faW5wdXRfdG9rZW5zIjowLCJjYWNoZV9yZWFkX2lucHV0X3Rva2VucyI6MCwiaW5mZXJlbmNlX2dlbyI6Imdsb2JhbCIsImlucHV0X3Rva2VucyI6ODQ5NCwib3V0cHV0X3Rva2VucyI6NDE1LCJvdXRwdXRfdG9rZW5zX2RldGFpbHMiOnsidGhpbmtpbmdfdG9rZW5zIjowfSwic2VydmVyX3Rvb2xfdXNlIjpudWxsLCJzZXJ2aWNlX3RpZXIiOiJzdGFuZGFyZCJ9LCJtb2RlbF9uYW1lIjoiY2xhdWRlLXNvbm5ldCIsIm1vZGVsX3Byb3ZpZGVyIjoiYW50aHJvcGljIn0sInR5cGUiOiJhaSIsIm5hbWUiOiJlZGl0b3IiLCJpZCI6ImxjX3J1bi0tMDFhMGZlMDMtODZiYi03NjYxLWE1OWYtYTM5ZDZiNGU2Yjc0LTAiLCJ0b29sX2NhbGxzIjpbXSwiaW52YWxpZF90b29sX2NhbGxzIjpbXSwidXNhZ2VfbWV0YWRhdGEiOnsiaW5wdXRfdG9rZW5zIjo4NDk0LCJvdXRwdXRfdG9rZW5zIjo0MTUsInRvdGFsX3Rva2VucyI6ODkwOSwiaW5wdXRfdG9rZW5fZGV0YWlscyI6eyJjYWNoZV9yZWFkIjowLCJjYWNoZV9jcmVhdGlvbiI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MH0sIm91dHB1dF90b2tlbl9kZXRhaWxzIjp7InJlYXNvbmluZyI6MH19fV19" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "4809a44f637a7046", + "parentSpanId": "41a84418436b8795", + "name": "editor", + "kind": 1, + "startTimeUnixNano": "1790968035043306240", + "endTimeUnixNano": "1790968042918324992", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "editor" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "5" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "editor" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:editor\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"editor\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "editor" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "seq:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "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" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "5eb6729648b8a8b0", + "parentSpanId": "4809a44f637a7046", + "name": "model", + "kind": 1, + "startTimeUnixNano": "1790968039096445952", + "endTimeUnixNano": "1790968042917764864", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "3" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|model:d639a607-1d3b-b4dc-823b-564098184f56" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "editor" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "graph:step:3" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "eyJtZXNzYWdlcyI6W3siY29udGVudCI6IkZvciBhIHN5bnRoZXRpYyB0cmFjaW5nIGZpeHR1cmUsIGV4cGxhaW4gUHl0aG9uIHR1cGxlIHZlcnN1cyBsaXN0IGltbXV0YWJpbGl0eSBpbiBhdCBtb3N0IDEyMCB3b3Jkcy4gVXNlIG9ubHkgb2ZmaWNpYWwgUHl0aG9uIGRvY3VtZW50YXRpb24gaWYgeW91IHNlYXJjaC4gSGF2ZSB0aGUgc2tlcHRpYyBhbmQgdmVyaWZpZXIgY2hlY2sgaXQsIHRoZW4gaGF2ZSB0aGUgZWRpdG9yIHdyaXRlIC9hbnN3ZXIubWQuIEtlZXAgdGhlIHJ1biBzaG9ydCBhbmQgZG8gbm90IGFzayBmb2xsb3ctdXAgcXVlc3Rpb25zLiIsImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnt9LCJ0eXBlIjoiaHVtYW4iLCJpZCI6IjQ2MjA0MzA1LWY4ZWUtNDM4NC05Y2U4LWZjZDgwYmZjZGY3NSJ9LHsiY29udGVudCI6W3siaWQiOiJ0b29sdV8wMUIyTGZIR0RqWVNGSmhtaVhOajRDdVEiLCJjYWxsZXIiOnsidHlwZSI6ImRpcmVjdCJ9LCJpbnB1dCI6eyJxdWVyeSI6ImRvY3MucHl0aG9uLm9yZyB0dXBsZXMgaW1tdXRhYmxlIHNlcXVlbmNlcyBsaXN0cyBtdXRhYmxlIGRhdGEgc3RydWN0dXJlcyB0dXRvcmlhbCJ9LCJuYW1lIjoid2ViX3NlYXJjaCIsInR5cGUiOiJ0b29sX3VzZSIsInRvb2xzZXRfbmFtZSI6bnVsbH1dLCJhZGRpdGlvbmFsX2t3YXJncyI6e30sInJlc3BvbnNlX21ldGFkYXRhIjp7ImlkIjoibXNnXzAxMUNmZHc5YVc5YnJlblBxZ3liZk53UCIsImNvbnRhaW5lciI6bnVsbCwiZGlhZ25vc3RpY3MiOm51bGwsIm1vZGVsIjoiY2xhdWRlLXNvbm5ldCIsInN0b3BfZGV0YWlscyI6bnVsbCwic3RvcF9yZWFzb24iOiJ0b29sX3VzZSIsInN0b3Bfc2VxdWVuY2UiOm51bGwsInVzYWdlIjp7ImNhY2hlX2NyZWF0aW9uIjp7ImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjB9LCJjYWNoZV9jcmVhdGlvbl9pbnB1dF90b2tlbnMiOjAsImNhY2hlX3JlYWRfaW5wdXRfdG9rZW5zIjowLCJpbmZlcmVuY2VfZ2VvIjoiZ2xvYmFsIiwiaW5wdXRfdG9rZW5zIjoyODQ1LCJvdXRwdXRfdG9rZW5zIjo3Mywib3V0cHV0X3Rva2Vuc19kZXRhaWxzIjp7InRoaW5raW5nX3Rva2VucyI6MH0sInNlcnZlcl90b29sX3VzZSI6bnVsbCwic2VydmljZV90aWVyIjoic3RhbmRhcmQifSwibW9kZWxfbmFtZSI6ImNsYXVkZS1zb25uZXQiLCJtb2RlbF9wcm92aWRlciI6ImFudGhyb3BpYyJ9LCJ0eXBlIjoiYWkiLCJuYW1lIjoicmVzZWFyY2hlciIsImlkIjoibGNfcnVuLS0wMWEwZmUwMy0yMWEzLTcwMDAtYTM4MS0yODRhNmEwYzAzZjctMCIsInRvb2xfY2FsbHMiOlt7Im5hbWUiOiJ3ZWJfc2VhcmNoIiwiYXJncyI6eyJxdWVyeSI6ImRvY3MucHl0aG9uLm9yZyB0dXBsZXMgaW1tdXRhYmxlIHNlcXVlbmNlcyBsaXN0cyBtdXRhYmxlIGRhdGEgc3RydWN0dXJlcyB0dXRvcmlhbCJ9LCJpZCI6InRvb2x1XzAxQjJMZkhHRGpZU0ZKaG1pWE5qNEN1USIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6Mjg0NSwib3V0cHV0X3Rva2VucyI6NzMsInRvdGFsX3Rva2VucyI6MjkxOCwiaW5wdXRfdG9rZW5fZGV0YWlscyI6eyJjYWNoZV9yZWFkIjowLCJjYWNoZV9jcmVhdGlvbiI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MH0sIm91dHB1dF90b2tlbl9kZXRhaWxzIjp7InJlYXNvbmluZyI6MH19fSx7ImNvbnRlbnQiOiJbe1widGl0bGVcIjogXCI1LiBEYXRhIFN0cnVjdHVyZXMgXFx1MjAxNCBQeXRob24gMy4xNC41IGRvY3VtZW50YXRpb25cIiwgXCJ1cmxcIjogXCJodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL3R1dG9yaWFsL2RhdGFzdHJ1Y3R1cmVzLmh0bWxcIiwgXCJoaWdobGlnaHRzXCI6IFtcIllvdSBtaWdodCBoYXZlIG5vdGljZWQgdGhhdCBtZXRob2RzIGxpa2VgaW5zZXJ0YCxgcmVtb3ZlYCBvcmBzb3J0YCB0aGF0IG9ubHkgbW9kaWZ5IHRoZSBsaXN0IGhhdmUgbm8gcmV0dXJuIHZhbHVlIHByaW50ZWQgXFx1MjAxMyB0aGV5IHJldHVybiB0aGUgZGVmYXVsdGBOb25lYC4gWzFdIFRoaXMgaXMgYSBkZXNpZ24gcHJpbmNpcGxlIGZvciBhbGwgbXV0YWJsZSBkYXRhIHN0cnVjdHVyZXMgaW4gUHl0aG9uLlxcbi4uLlxcbiMjIDUuMy4gVHVwbGVzIGFuZCBTZXF1ZW5jZXNcXHUwMGI2XFxuXFxuV2Ugc2F3IHRoYXQgbGlzdHMgYW5kIHN0cmluZ3MgaGF2ZSBtYW55IGNvbW1vbiBwcm9wZXJ0aWVzLCBzdWNoIGFzIGluZGV4aW5nIGFuZCBzbGljaW5nIG9wZXJhdGlvbnMuIFRoZXkgYXJlIHR3byBleGFtcGxlcyBvZiBzZXF1ZW5jZSBkYXRhIHR5cGVzIChzZWUgU2VxdWVuY2UgVHlwZXMgXFx1MjAxNCBsaXN0LCB0dXBsZSwgcmFuZ2UpLiBTaW5jZSBQeXRob24gaXMgYW4gZXZvbHZpbmcgbGFuZ3VhZ2UsIG90aGVyIHNlcXVlbmNlIGRhdGEgdHlwZXMgbWF5IGJlIGFkZGVkLiBUaGVyZSBpcyBhbHNvIGFub3RoZXIgc3RhbmRhcmQgc2VxdWVuY2UgZGF0YSB0eXBlOiB0aGUgdHVwbGUuXFxuXFxuQSB0dXBsZSBjb25zaXN0cyBvZiBhIG51bWJlciBvZiB2YWx1ZXMgc2VwYXJhdGVkIGJ5IGNvbW1hcywgZm9yIGluc3RhbmNlOlxcbi4uLlxcbj4+PiAjIFR1cGxlcyBhcmUgaW1tdXRhYmxlOlxcbj4+PiB0WzBdID0gODg4ODhcXG5UcmFjZWJhY2sgKG1vc3QgcmVjZW50IGNhbGwgbGFzdCk6XFxuICBGaWxlIFxcXCI8c3RkaW4+XFxcIiwgbGluZSAxLCBpbiA8bW9kdWxlPlxcblR5cGVFcnJvcjogJ3R1cGxlJyBvYmplY3QgZG9lcyBub3Qgc3VwcG9ydCBpdGVtIGFzc2lnbm1lbnRcXG4+Pj4gIyBidXQgdGhleSBjYW4gY29udGFpbiBtdXRhYmxlIG9iamVjdHM6XFxuPj4+IHYgPSAoWzEsIDIsIDNdLCBbMywgMiwgMV0pXFxuPj4+IHZcXG4oWzEsIDIsIDNdLCBbMywgMiwgMV0pXFxuLi4uXFxuQXMgeW91IHNlZSwgb24gb3V0cHV0IHR1cGxlcyBhcmUgYWx3YXlzIGVuY2xvc2VkIGluIHBhcmVudGhlc2VzLCBzbyB0aGF0IG5lc3RlZCB0dXBsZXMgYXJlIGludGVycHJldGVkIGNvcnJlY3RseTsgdGhleSBtYXkgYmUgaW5wdXQgd2l0aCBvciB3aXRob3V0IHN1cnJvdW5kaW5nIHBhcmVudGhlc2VzLCBhbHRob3VnaCBvZnRlbiBwYXJlbnRoZXNlcyBhcmUgbmVjZXNzYXJ5IGFueXdheSAoaWYgdGhlIHR1cGxlIGlzIHBhcnQgb2YgYSBsYXJnZXIgZXhwcmVzc2lvbikuIEl0IGlzIG5vdCBwb3NzaWJsZSB0byBhc3NpZ24gdG8gdGhlIGluZGl2aWR1YWwgaXRlbXMgb2YgYSB0dXBsZSwgaG93ZXZlciBpdCBpcyBwb3NzaWJsZSB0byBjcmVhdGUgdHVwbGVzIHdoaWNoIGNvbnRhaW4gbXV0YWJsZSBvYmplY3RzLCBzdWNoIGFzIGxpc3RzLlxcblxcblRob3VnaCB0dXBsZXMgbWF5IHNlZW0gc2ltaWxhciB0byBsaXN0cywgdGhleSBhcmUgb2Z0ZW4gdXNlZCBpbiBkaWZmZXJlbnQgc2l0dWF0aW9ucyBhbmQgZm9yIGRpZmZlcmVudCBwdXJwb3Nlcy4gVHVwbGVzIGFyZSBpbW11dGFibGUsIGFuZCB1c3VhbGx5IGNvbnRhaW4gYSBoZXRlcm9nZW5lb3VzIHNlcXVlbmNlIG9mIGVsZW1lbnRzIHRoYXQgYXJlIGFjY2Vzc2VkIHZpYSB1bnBhY2tpbmcgKHNlZSBsYXRlciBpbiB0aGlzIHNlY3Rpb24pIG9yIGluZGV4aW5nIChvciBldmVuIGJ5IGF0dHJpYnV0ZSBpbiB0aGUgY2FzZSBvZiBuYW1lZHR1cGxlcykuIExpc3RzIGFyZSBtdXRhYmxlLCBhbmQgdGhlaXIgZWxlbWVudHMgYXJlIHVzdWFsbHkgaG9tb2dlbmVvdXMgYW5kIGFyZSBhY2Nlc3NlZCBieSBpdGVyYXRpbmcgb3ZlciB0aGUgbGlzdC5cXG4uLi5cXG5Bbm90aGVyIHVzZWZ1bCBkYXRhIHR5cGUgYnVpbHQgaW50byBQeXRob24gaXMgdGhlIGRpY3Rpb25hcnkgKHNlZSBNYXBwaW5nIFR5cGVzIFxcdTIwMTQgZGljdCkuIERpY3Rpb25hcmllcyBhcmUgc29tZXRpbWVzIGZvdW5kIGluIG90aGVyIGxhbmd1YWdlcyBhcyBcXHUyMDFjYXNzb2NpYXRpdmUgbWVtb3JpZXNcXHUyMDFkIG9yIFxcdTIwMWNhc3NvY2lhdGl2ZSBhcnJheXNcXHUyMDFkLiBVbmxpa2Ugc2VxdWVuY2VzLCB3aGljaCBhcmUgaW5kZXhlZCBieSBhIHJhbmdlIG9mIG51bWJlcnMsIGRpY3Rpb25hcmllcyBhcmUgaW5kZXhlZCBieSBrZXlzLCB3aGljaCBjYW4gYmUgYW55IGltbXV0YWJsZSB0eXBlOyBzdHJpbmdzIGFuZCBudW1iZXJzIGNhbiBhbHdheXMgYmUga2V5cy4gVHVwbGVzIGNhbiBiZSB1c2VkIGFzIGtleXMgaWYgdGhleSBjb250YWluIG9ubHkgc3RyaW5ncywgbnVtYmVycywgb3IgdHVwbGVzOyBpZiBhIHR1cGxlIGNvbnRhaW5zIGFueSBtdXRhYmxlIG9iamVjdCBlaXRoZXIgZGlyZWN0bHkgb3IgaW5kaXJlY3RseSwgaXQgY2Fubm90IGJlIHVzZWQgYXMgYSBrZXkuIFlvdSBjYW5cXHUyMDE5dCB1c2UgbGlzdHMgYXMga2V5cywgc2luY2UgbGlzdHMgY2FuIGJlIG1vZGlmaWVkIGluIHBsYWNlIHVzaW5nIGluZGV4IGFzc2lnbm1lbnRzLCBzbGljZSBhc3NpZ25tZW50cywgb3IgbWV0aG9kcyBsaWtlIGFwcGVuZCgpIGFuZCBleHRlbmQoKS5cIl19LCB7XCJ0aXRsZVwiOiBcIjMuIERhdGEgbW9kZWwgXFx1MjAxNCBQeXRob24gMy4xNC41IGRvY3VtZW50YXRpb25cIiwgXCJ1cmxcIjogXCJodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL3JlZmVyZW5jZS9kYXRhbW9kZWwuaHRtbFwiLCBcImhpZ2hsaWdodHNcIjogW1wiVGhlIHZhbHVlIG9mIHNvbWUgb2JqZWN0cyBjYW4gY2hhbmdlLiBPYmplY3RzIHdob3NlIHZhbHVlIGNhbiBjaGFuZ2UgYXJlIHNhaWQgdG8gYmUgbXV0YWJsZTsgb2JqZWN0cyB3aG9zZSB2YWx1ZSBpcyB1bmNoYW5nZWFibGUgb25jZSB0aGV5IGFyZSBjcmVhdGVkIGFyZSBjYWxsZWQgaW1tdXRhYmxlLiAoVGhlIHZhbHVlIG9mIGFuIGltbXV0YWJsZSBjb250YWluZXIgb2JqZWN0IHRoYXQgY29udGFpbnMgYSByZWZlcmVuY2UgdG8gYSBtdXRhYmxlIG9iamVjdCBjYW4gY2hhbmdlIHdoZW4gdGhlIGxhdHRlclxcdTIwMTlzIHZhbHVlIGlzIGNoYW5nZWQ7IGhvd2V2ZXIgdGhlIGNvbnRhaW5lciBpcyBzdGlsbCBjb25zaWRlcmVkIGltbXV0YWJsZSwgYmVjYXVzZSB0aGUgY29sbGVjdGlvbiBvZiBvYmplY3RzIGl0IGNvbnRhaW5zIGNhbm5vdCBiZSBjaGFuZ2VkLiBTbywgaW1tdXRhYmlsaXR5IGlzIG5vdCBzdHJpY3RseSB0aGUgc2FtZSBhcyBoYXZpbmcgYW4gdW5jaGFuZ2VhYmxlIHZhbHVlLCBpdCBpcyBtb3JlIHN1YnRsZS4pIEFuIG9iamVjdFxcdTIwMTlzIG11dGFiaWxpdHkgaXMgZGV0ZXJtaW5lZCBieSBpdHMgdHlwZTsgZm9yIGluc3RhbmNlLCBudW1iZXJzLCBzdHJpbmdzIGFuZCB0dXBsZXMgYXJlIGltbXV0YWJsZSwgd2hpbGUgZGljdGlvbmFyaWVzIGFuZCBsaXN0cyBhcmUgbXV0YWJsZS5cXG4uLi5cXG5Tb21lIG9iamVjdHMgY29udGFpbiByZWZlcmVuY2VzIHRvIG90aGVyIG9iamVjdHM7IHRoZXNlIGFyZSBjYWxsZWQgY29udGFpbmVycy4gRXhhbXBsZXMgb2YgY29udGFpbmVycyBhcmUgdHVwbGVzLCBsaXN0cyBhbmQgZGljdGlvbmFyaWVzLiBUaGUgcmVmZXJlbmNlcyBhcmUgcGFydCBvZiBhIGNvbnRhaW5lclxcdTIwMTlzIHZhbHVlLiBJbiBtb3N0IGNhc2VzLCB3aGVuIHdlIHRhbGsgYWJvdXQgdGhlIHZhbHVlIG9mIGEgY29udGFpbmVyLCB3ZSBpbXBseSB0aGUgdmFsdWVzLCBub3QgdGhlIGlkZW50aXRpZXMgb2YgdGhlIGNvbnRhaW5lZCBvYmplY3RzOyBob3dldmVyLCB3aGVuIHdlIHRhbGsgYWJvdXQgdGhlIG11dGFiaWxpdHkgb2YgYSBjb250YWluZXIsIG9ubHkgdGhlIGlkZW50aXRpZXMgb2YgdGhlIGltbWVkaWF0ZWx5IGNvbnRhaW5lZCBvYmplY3RzIGFyZSBpbXBsaWVkLiBTbywgaWYgYW4gaW1tdXRhYmxlIGNvbnRhaW5lciAobGlrZSBhIHR1cGxlKSBjb250YWlucyBhIHJlZmVyZW5jZSB0byBhIG11dGFibGUgb2JqZWN0LCBpdHMgdmFsdWUgY2hhbmdlcyBpZiB0aGF0IG11dGFibGUgb2JqZWN0IGlzIGNoYW5nZWQuXFxuLi4uXFxuIyMjIDMuMi41LiBTZXF1ZW5jZXNcXHUwMGI2XFxuLi4uXFxuIyMjIyAzLjIuNS4xLiBJbW11dGFibGUgc2VxdWVuY2VzXFx1MDBiNlxcblxcbkFuIG9iamVjdCBvZiBhbiBpbW11dGFibGUgc2VxdWVuY2UgdHlwZSBjYW5ub3QgY2hhbmdlIG9uY2UgaXQgaXMgY3JlYXRlZC4gKElmIHRoZSBvYmplY3QgY29udGFpbnMgcmVmZXJlbmNlcyB0byBvdGhlciBvYmplY3RzLCB0aGVzZSBvdGhlciBvYmplY3RzIG1heSBiZSBtdXRhYmxlIGFuZCBtYXkgYmUgY2hhbmdlZDsgaG93ZXZlciwgdGhlIGNvbGxlY3Rpb24gb2Ygb2JqZWN0cyBkaXJlY3RseSByZWZlcmVuY2VkIGJ5IGFuIGltbXV0YWJsZSBvYmplY3QgY2Fubm90IGNoYW5nZS4pXFxuXFxuVGhlIGZvbGxvd2luZyB0eXBlcyBhcmUgaW1tdXRhYmxlIHNlcXVlbmNlczpcXG4uLi5cXG5UdXBsZXNcXG46IFRoZSBpdGVtcyBvZiBhIGB0dXBsZWAgYXJlIGFyYml0cmFyeSBQeXRob24gb2JqZWN0cy4gVHVwbGVzIG9mIHR3byBvciBtb3JlIGl0ZW1zIGFyZSBmb3JtZWQgYnkgY29tbWEtc2VwYXJhdGVkIGxpc3RzIG9mIGV4cHJlc3Npb25zLiBBIHR1cGxlIG9mIG9uZSBpdGVtIChhIFxcdTIwMThzaW5nbGV0b25cXHUyMDE5KSBjYW4gYmUgZm9ybWVkIGJ5IGFmZml4aW5nIGEgY29tbWEgdG8gYW4gZXhwcmVzc2lvbiAoYW4gZXhwcmVzc2lvbiBieSBpdHNlbGYgZG9lcyBub3QgY3JlYXRlIGEgdHVwbGUsIHNpbmNlIHBhcmVudGhlc2VzIG11c3QgYmUgdXNhYmxlIGZvciBncm91cGluZyBvZiBleHByZXNzaW9ucykuIEFuIGVtcHR5IHR1cGxlIGNhbiBiZSBmb3JtZWQgYnkgYW4gZW1wdHkgcGFpciBvZiBwYXJlbnRoZXNlcy5cXG4uLi5cXG4jIyMjIDMuMi41LjIuIE11dGFibGUgc2VxdWVuY2VzXFx1MDBiNlxcblxcbk11dGFibGUgc2VxdWVuY2VzIGNhbiBiZSBjaGFuZ2VkIGFmdGVyIHRoZXkgYXJlIGNyZWF0ZWQuIFRoZSBzdWJzY3JpcHRpb24gYW5kIHNsaWNpbmcgbm90YXRpb25zIGNhbiBiZSB1c2VkIGFzIHRoZSB0YXJnZXQgb2YgYXNzaWdubWVudCBhbmQgYGRlbGAgKGRlbGV0ZSkgc3RhdGVtZW50cy5cXG4uLi5cXG5UaGVyZSBhcmUgY3VycmVudGx5IHR3byBpbnRyaW5zaWMgbXV0YWJsZSBzZXF1ZW5jZSB0eXBlczpcXG5cXG5MaXN0c1xcbjogVGhlIGl0ZW1zIG9mIGEgbGlzdCBhcmUgYXJiaXRyYXJ5IFB5dGhvbiBvYmplY3RzLiBMaXN0cyBhcmUgZm9ybWVkIGJ5IHBsYWNpbmcgYSBjb21tYS1zZXBhcmF0ZWQgbGlzdCBvZiBleHByZXNzaW9ucyBpbiBzcXVhcmUgYnJhY2tldHMuIChOb3RlIHRoYXQgdGhlcmUgYXJlIG5vIHNwZWNpYWwgY2FzZXMgbmVlZGVkIHRvIGZvcm0gbGlzdHMgb2YgbGVuZ3RoIDAgb3IgMS4pXCJdfSwge1widGl0bGVcIjogXCJCdWlsdC1pbiBUeXBlcyBcXHUyMDE0IFB5dGhvbiAzLjE0LjcgZG9jdW1lbnRhdGlvblwiLCBcInVybFwiOiBcImh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvYnVpbHRpbnMvc3RkdHlwZXMuaHRtbFwiLCBcImhpZ2hsaWdodHNcIjogW1wiY29sbGVjdGlvbiBjbGFzc2VzIGFyZSBtdXRhYmxlLiBUaGUgbWV0aG9kcyB0aGF0IGFkZCwgc3VidHJhY3QsIG9yIHJlYXJyYW5nZSB0aGVpciAuLi4gaW4gcGxhY2UsIGFuZCBkb25cXHUyMDE5dCByZXR1cm4gYSAuLi4gLCBuZXZlciByZXR1cm4gdGhlIGNvbGxlY3Rpb24gaW5zdGFuY2UgaXRzZWxmIGJ1dCBgTm9uZWAuXFxuLi4uXFxuIyMgU2VxdWVuY2UgVHlwZXMgXFx1MjAxNCBgbGlzdGAsIGB0dXBsZWAsIGByYW5nZWBcXHUwMGI2XFxuXFxuVGhlcmUgYXJlIHRocmVlIGJhc2ljIHNlcXVlbmNlIHR5cGVzOiBsaXN0cywgdHVwbGVzLCBhbmQgcmFuZ2Ugb2JqZWN0cy4gQWRkaXRpb25hbCBzZXF1ZW5jZSB0eXBlcyB0YWlsb3JlZCBmb3IgcHJvY2Vzc2luZyBvZiBiaW5hcnkgZGF0YSBhbmQgdGV4dCBzdHJpbmdzIGFyZSBkZXNjcmliZWQgaW4gZGVkaWNhdGVkIHNlY3Rpb25zLlxcbi4uLlxcblRoZSBvcGVyYXRpb25zIGluIHRoZSBmb2xsb3dpbmcgdGFibGUgLi4uIG11dGFibGUgYW5kIGltbXV0YWJsZS4gVGhlIGBjb2xsZWN0aW9ucy4gLi4uIGlzIHByb3ZpZGVkIHRvIG1ha2UgLi4uIGVhc2llciB0byBjb3JyZWN0bHkgaW1wbGVtZW50IHRoZXNlIG9wZXJhdGlvbnMgb24gY3VzdG9tIHNlcXVlbmNlIHR5cGVzXFxuLi4uXFxuIyMjIEltbXV0YWJsZSBTZXF1ZW5jZSBUeXBlc1xcdTAwYjZcXG4uLi5cXG5tdXRhYmxlIHNlcXVlbmNlIHR5cGVzIGlzXFxuLi4uXFxuc3VwcG9ydCBhbGxvd3MgaW1tdXRhYmxlIHNlcXVlbmNlcywgLi4uICwgdG8gYmUgdXNlZCBhcyBgZGljdGAga2V5cyBhbmQgc3RvcmVkIGluIC4uLiBlbnNldGAgaW5zdGFuY2VzXFxuLi4uXFxuIyMjIE11dGFibGUgU2VxdWVuY2UgVHlwZXNcXHUwMGI2XFxuLi4uXFxuIyMjIExpc3RzXFx1MDBiNlxcblxcbkxpc3RzIGFyZSBtdXRhYmxlIHNlcXVlbmNlcywgdHlwaWNhbGx5IHVzZWQgdG8gc3RvcmUgY29sbGVjdGlvbnMgb2YgaG9tb2dlbmVvdXMgaXRlbXMgKHdoZXJlIHRoZSBwcmVjaXNlIGRlZ3JlZSBvZiBzaW1pbGFyaXR5IHdpbGwgdmFyeSBieSBhcHBsaWNhdGlvbikuXFxuLi4uXFxuIyMjIFR1cGxlc1xcdTAwYjZcXG5cXG5UdXBsZXMgYXJlIGltbXV0YWJsZSBzZXF1ZW5jZXMsIHR5cGljYWxseSB1c2VkIHRvIHN0b3JlIGNvbGxlY3Rpb25zIG9mIGhldGVyb2dlbmVvdXMgZGF0YSAoc3VjaCBhcyB0aGUgMi10dXBsZXMgcHJvZHVjZWQgYnkgdGhlIGBlbnVtZXJhdGUoKWAgYnVpbHQtaW4pLiBUdXBsZXMgYXJlIGFsc28gdXNlZCBmb3IgY2FzZXMgd2hlcmUgYW4gaW1tdXRhYmxlIHNlcXVlbmNlIG9mIGhvbW9nZW5lb3VzIGRhdGEgaXMgbmVlZGVkIChzdWNoIGFzIGFsbG93aW5nIHN0b3JhZ2UgaW4gYSBgc2V0YCBvciBgZGljdGAgaW5zdGFuY2UpLlxcbi4uLlxcbnR1cGxlKGl0ZXJhYmxlPVxcbi4uLlxcblRoZSBjb25zdHJ1Y3RvciBidWlsZHMgYSB0dXBsZSB3aG9zZSBpdGVtcyBhcmUgdGhlIHNhbWUgYW5kIGluIHRoZSBzYW1lIG9yZGVyIGFzIGl0ZXJhYmxlXFx1MjAxOXMgaXRlbXMuIGl0ZXJhYmxlIG1heSBiZSBlaXRoZXIgYSBzZXF1ZW5jZSwgYSBjb250YWluZXIgdGhhdCBzdXBwb3J0cyBpdGVyYXRpb24sIG9yIGFuIGl0ZXJhdG9yIG9iamVjdC4gSWYgaXRlcmFibGUgaXMgYWxyZWFkeSBhIHR1cGxlLCBpdCBpcyByZXR1cm5lZCB1bmNoYW5nZWQuIEZvciBleGFtcGxlLCBgdHVwbGUoJ2FiYycpYCByZXR1cm5zIGAoJ2EnLCAnYicsICdjJylgIGFuZCBgdHVwbGUoIFsxLCAyLCAzXSApYCByZXR1cm5zIGAoMSwgMiwgMylgLiBJZiBubyBhcmd1bWVudCBpcyBnaXZlbiwgdGhlIGNvbnN0cnVjdG9yIGNyZWF0ZXMgYSBuZXcgZW1wdHkgdHVwbGUsIGAoKWAuXFxuLi4uXFxuVHVwbGVzIGltcGxlbWVudCBhbGwgb2YgdGhlIGNvbW1vbiBzZXF1ZW5jZSBvcGVyYXRpb25zLlxcbi4uLlxcbkZvciBoZXRlcm9nZW5lb3VzIGNvbGxlY3Rpb25zIG9mIGRhdGEgd2hlcmUgYWNjZXNzIGJ5IG5hbWUgaXMgY2xlYXJlciB0aGFuIGFjY2VzcyBieSBpbmRleCwgYGNvbGxlY3Rpb25zLm5hbWVkdHVwbGUoKWAgbWF5IGJlIGEgbW9yZSBhcHByb3ByaWF0ZSBjaG9pY2UgdGhhbiBhIHNpbXBsZSB0dXBsZSBvYmplY3QuXCJdfSwge1widGl0bGVcIjogXCJCdWlsdC1pbiBUeXBlcyBcXHUyMDE0IFB5dGhvbiAzLjE0LjUgZG9jdW1lbnRhdGlvblwiLCBcInVybFwiOiBcImh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvbGlicmFyeS9zdGR0eXBlcy5odG1sXCIsIFwiaGlnaGxpZ2h0c1wiOiBbXCJTb21lIGNvbGxlY3Rpb24gY2xhc3NlcyBhcmUgbXV0YWJsZS4gVGhlIG1ldGhvZHMgdGhhdCBhZGQsIHN1YnRyYWN0LCBvciByZWFycmFuZ2UgdGhlaXIgLi4uIGluIHBsYWNlLCBhbmQgZG9uXFx1MjAxOXQgcmV0dXJuIGEgLi4uICwgbmV2ZXIgcmV0dXJuIHRoZSBjb2xsZWN0aW9uIGluc3RhbmNlIGl0c2VsZiBidXQgYE5vbmVgLlxcbi4uLlxcbiMjIFNlcXVlbmNlIFR5cGVzIFxcdTIwMTQgYGxpc3RgLCBgdHVwbGVgLCBgcmFuZ2VgXFx1MDBiNlxcblxcblRoZXJlIGFyZSB0aHJlZSBiYXNpYyBzZXF1ZW5jZSB0eXBlczogbGlzdHMsIHR1cGxlcywgYW5kIC4uLiBvYmplY3RzLiBBZGRpdGlvbmFsIHNlcXVlbmNlIHR5cGVzIHRhaWxvcmVkIGZvciBwcm9jZXNzaW5nIG9mIGJpbmFyeSBkYXRhIGFuZCB0ZXh0IHN0cmluZ3MgYXJlIGRlc2NyaWJlZCBpbiBkZWRpY2F0ZWQgc2VjdGlvbnMuXFxuLi4uXFxuVGhlIG9wZXJhdGlvbnMgaW4gdGhlIGZvbGxvd2luZyB0YWJsZSAuLi4gaW1tdXRhYmxlLiBUaGUgYCAuLi4gaXMgcHJvdmlkZWQgdG8gbWFrZSAuLi4gZWFzaWVyIHRvIGNvcnJlY3RseSBpbXBsZW1lbnQgdGhlc2Ugb3BlcmF0aW9ucyBvbiBjdXN0b20gc2VxdWVuY2UgdHlwZXNcXG4uLi5cXG4jIyMgSW1tdXRhYmxlIFNlcXVlbmNlIFR5cGVzXFx1MDBiNlxcbi4uLlxcbm9wZXJhdGlvbiB0aGF0IGltbXV0YWJsZSBzZXF1ZW5jZSAuLi4gYnkgbXV0YWJsZSBzZXF1ZW5jZSB0eXBlcyBpcyAuLi4gYGhhc2goKWBcXG4uLi5cXG5UaGlzIHN1cHBvcnQgYWxsb3dzIGltbXV0YWJsZSBzZXF1ZW5jZXMsIHN1Y2ggYXMgYHR1cGxlYCBpbnN0YW5jZXMsIHRvIGJlIHVzZWQgYXMgYGRpY3RgIGtleXMgYW5kIHN0b3JlZCBpbiBgc2V0YCBhbmQgYGZyb3plbnNldGAgaW5zdGFuY2VzLlxcbi4uLlxcbiMjIyBNdXRhYmxlIFNlcXVlbmNlIFR5cGVzXFx1MDBiNlxcbi4uLlxcbiMjIyBMaXN0c1xcdTAwYjZcXG5cXG5MaXN0cyBhcmUgbXV0YWJsZSBzZXF1ZW5jZXMsIHR5cGljYWxseSB1c2VkIHRvIHN0b3JlIGNvbGxlY3Rpb25zIG9mIGhvbW9nZW5lb3VzIGl0ZW1zICh3aGVyZSB0aGUgcHJlY2lzZSBkZWdyZWUgb2Ygc2ltaWxhcml0eSB3aWxsIHZhcnkgYnkgYXBwbGljYXRpb24pLlxcbi4uLlxcbiMjIyBUdXBsZXNcXHUwMGI2XFxuXFxuVHVwbGVzIGFyZSBpbW11dGFibGUgc2VxdWVuY2VzLCB0eXBpY2FsbHkgdXNlZCB0byBzdG9yZSBjb2xsZWN0aW9ucyBvZiBoZXRlcm9nZW5lb3VzIGRhdGEgKHN1Y2ggYXMgdGhlIDItdHVwbGVzIHByb2R1Y2VkIGJ5IHRoZSBgZW51bWVyYXRlKClgIGJ1aWx0LWluKS4gVHVwbGVzIGFyZSBhbHNvIHVzZWQgZm9yIGNhc2VzIHdoZXJlIGFuIGltbXV0YWJsZSBzZXF1ZW5jZSBvZiBob21vZ2VuZW91cyBkYXRhIGlzIG5lZWRlZCAoc3VjaCBhcyBhbGxvd2luZyBzdG9yYWdlIGluIGEgYHNldGAgb3IgYGRpY3RgIGluc3RhbmNlKS5cXG4uLi5cXG5UaGUgY29uc3RydWN0b3IgYnVpbGRzIGEgdHVwbGUgd2hvc2UgaXRlbXMgYXJlIHRoZSBzYW1lIGFuZCBpbiB0aGUgc2FtZSBvcmRlciBhcyBpdGVyYWJsZVxcdTIwMTlzIGl0ZW1zLiBpdGVyYWJsZSBtYXkgYmUgZWl0aGVyIGEgc2VxdWVuY2UsIGEgY29udGFpbmVyIHRoYXQgc3VwcG9ydHMgaXRlcmF0aW9uLCBvciBhbiBpdGVyYXRvciBvYmplY3QuIElmIGl0ZXJhYmxlIGlzIGFscmVhZHkgYSB0dXBsZSwgaXQgaXMgcmV0dXJuZWQgdW5jaGFuZ2VkLiBGb3IgZXhhbXBsZSwgYHR1cGxlKCdhYmMnKWAgcmV0dXJucyBgKCdhJywgJ2InLCAnYycpYCBhbmQgYHR1cGxlKCBbMSwgMiwgM10gKWAgcmV0dXJucyBgKDEsIDIsIDMpYC4gSWYgbm8gYXJndW1lbnQgaXMgZ2l2ZW4sIHRoZSBjb25zdHJ1Y3RvciBjcmVhdGVzIGEgbmV3IGVtcHR5IHR1cGxlLCBgKClgLlxcbi4uLlxcblR1cGxlcyBpbXBsZW1lbnQgYWxsIG9mIHRoZSBjb21tb24gc2VxdWVuY2Ugb3BlcmF0aW9ucy5cXG4uLi5cXG5Gb3IgaGV0ZXJvZ2VuZW91cyBjb2xsZWN0aW9ucyBvZiBkYXRhIHdoZXJlIGFjY2VzcyBieSBuYW1lIGlzIGNsZWFyZXIgdGhhbiBhY2Nlc3MgYnkgaW5kZXgsIGBjb2xsZWN0aW9ucy5uYW1lZHR1cGxlKClgIG1heSBiZSBhIG1vcmUgYXBwcm9wcmlhdGUgY2hvaWNlIHRoYW4gYSBzaW1wbGUgdHVwbGUgb2JqZWN0LlwiXX0sIHtcInRpdGxlXCI6IFwiNS4gRGF0YSBTdHJ1Y3R1cmVzIFxcdTIwMTQgUHl0aG9uIDMuMTAuMjAgZG9jdW1lbnRhdGlvblwiLCBcInVybFwiOiBcImh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMuMTAvdHV0b3JpYWwvZGF0YXN0cnVjdHVyZXMuaHRtbFwiLCBcImhpZ2hsaWdodHNcIjogW1wiWW91IG1pZ2h0IGhhdmUgbm90aWNlZCB0aGF0IG1ldGhvZHMgbGlrZSBgaW5zZXJ0YCwgYHJlbW92ZWAgb3IgYHNvcnRgIHRoYXQgb25seSBtb2RpZnkgdGhlIGxpc3QgaGF2ZSBubyByZXR1cm4gdmFsdWUgcHJpbnRlZCBcXHUyMDEzIHRoZXkgcmV0dXJuIHRoZSBkZWZhdWx0IGBOb25lYC4gMSBUaGlzIGlzIGEgZGVzaWduIHByaW5jaXBsZSBmb3IgYWxsIG11dGFibGUgZGF0YSBzdHJ1Y3R1cmVzIGluIFB5dGhvbi5cXG4uLi5cXG4jIyA1LjMuIFR1cGxlcyBhbmQgU2VxdWVuY2VzXFx1MDBiNlxcblxcbldlIHNhdyB0aGF0IGxpc3RzIGFuZCBzdHJpbmdzIGhhdmUgbWFueSBjb21tb24gcHJvcGVydGllcywgc3VjaCBhcyBpbmRleGluZyBhbmQgc2xpY2luZyBvcGVyYXRpb25zLiBUaGV5IGFyZSB0d28gZXhhbXBsZXMgb2Ygc2VxdWVuY2UgZGF0YSB0eXBlcyAoc2VlIFNlcXVlbmNlIFR5cGVzIFxcdTIwMTQgbGlzdCwgdHVwbGUsIHJhbmdlKS4gU2luY2UgUHl0aG9uIGlzIGFuIGV2b2x2aW5nIGxhbmd1YWdlLCBvdGhlciBzZXF1ZW5jZSBkYXRhIHR5cGVzIG1heSBiZSBhZGRlZC4gVGhlcmUgaXMgYWxzbyBhbm90aGVyIHN0YW5kYXJkIHNlcXVlbmNlIGRhdGEgdHlwZTogdGhlIHR1cGxlLlxcblxcbkEgdHVwbGUgY29uc2lzdHMgb2YgYSBudW1iZXIgb2YgdmFsdWVzIHNlcGFyYXRlZCBieSBjb21tYXMsIGZvciBpbnN0YW5jZTpcXG4uLi5cXG4+Pj4gIyBUdXBsZXMgYXJlIGltbXV0YWJsZTpcXG4uLi4gdFswXSA9IDg4ODg4XFxuVHJhY2ViYWNrIChtb3N0IHJlY2VudCBjYWxsIGxhc3QpOlxcbiAgRmlsZSBcXFwiPHN0ZGluPlxcXCIsIGxpbmUgMSwgaW4gPG1vZHVsZT5cXG5UeXBlRXJyb3I6ICd0dXBsZScgb2JqZWN0IGRvZXMgbm90IHN1cHBvcnQgaXRlbSBhc3NpZ25tZW50XFxuPj4+ICMgYnV0IHRoZXkgY2FuIGNvbnRhaW4gbXV0YWJsZSBvYmplY3RzOlxcbi4uLiB2ID0gKFsxLCAyLCAzXSwgWzMsIDIsIDFdKVxcbj4+PiB2XFxuKFsxLCAyLCAzXSwgWzMsIDIsIDFdKVxcbi4uLlxcbkFzIHlvdSBzZWUsIG9uIG91dHB1dCB0dXBsZXMgYXJlIGFsd2F5cyBlbmNsb3NlZCBpbiBwYXJlbnRoZXNlcywgc28gdGhhdCBuZXN0ZWQgdHVwbGVzIGFyZSBpbnRlcnByZXRlZCBjb3JyZWN0bHk7IHRoZXkgbWF5IGJlIGlucHV0IHdpdGggb3Igd2l0aG91dCBzdXJyb3VuZGluZyBwYXJlbnRoZXNlcywgYWx0aG91Z2ggb2Z0ZW4gcGFyZW50aGVzZXMgYXJlIG5lY2Vzc2FyeSBhbnl3YXkgKGlmIHRoZSB0dXBsZSBpcyBwYXJ0IG9mIGEgbGFyZ2VyIGV4cHJlc3Npb24pLiBJdCBpcyBub3QgcG9zc2libGUgdG8gYXNzaWduIHRvIHRoZSBpbmRpdmlkdWFsIGl0ZW1zIG9mIGEgdHVwbGUsIGhvd2V2ZXIgaXQgaXMgcG9zc2libGUgdG8gY3JlYXRlIHR1cGxlcyB3aGljaCBjb250YWluIG11dGFibGUgb2JqZWN0cywgc3VjaCBhcyBsaXN0cy5cXG5cXG5UaG91Z2ggdHVwbGVzIG1heSBzZWVtIHNpbWlsYXIgdG8gbGlzdHMsIHRoZXkgYXJlIG9mdGVuIHVzZWQgaW4gZGlmZmVyZW50IHNpdHVhdGlvbnMgYW5kIGZvciBkaWZmZXJlbnQgcHVycG9zZXMuIFR1cGxlcyBhcmUgaW1tdXRhYmxlLCBhbmQgdXN1YWxseSBjb250YWluIGEgaGV0ZXJvZ2VuZW91cyBzZXF1ZW5jZSBvZiBlbGVtZW50cyB0aGF0IGFyZSBhY2Nlc3NlZCB2aWEgdW5wYWNraW5nIChzZWUgbGF0ZXIgaW4gdGhpcyBzZWN0aW9uKSBvciBpbmRleGluZyAob3IgZXZlbiBieSBhdHRyaWJ1dGUgaW4gdGhlIGNhc2Ugb2YgYG5hbWVkdHVwbGVzYCkuIExpc3RzIGFyZSBtdXRhYmxlLCBhbmQgdGhlaXIgZWxlbWVudHMgYXJlIHVzdWFsbHkgaG9tb2dlbmVvdXMgYW5kIGFyZSBhY2Nlc3NlZCBieSBpdGVyYXRpbmcgb3ZlciB0aGUgbGlzdC5cXG4uLi5cXG4jIyA1LjQuXFxuLi4uXFxuLiBTZXQgb2JqZWN0c1xcbi4uLlxcbiMjIDUuNS4gRGljdGlvbmFyaWVzXFx1MDBiNlxcblxcbkFub3RoZXIgdXNlZnVsIGRhdGEgdHlwZSBidWlsdCBpbnRvIFB5dGhvbiBpcyB0aGUgZGljdGlvbmFyeSAoc2VlIE1hcHBpbmcgVHlwZXMgXFx1MjAxNCBkaWN0KS4gRGljdGlvbmFyaWVzIGFyZSBzb21ldGltZXMgZm91bmQgaW4gb3RoZXIgbGFuZ3VhZ2VzIGFzIFxcdTIwMWNhc3NvY2lhdGl2ZSBtZW1vcmllc1xcdTIwMWQgb3IgXFx1MjAxY2Fzc29jaWF0aXZlIGFycmF5c1xcdTIwMWQuIFVubGlrZSBzZXF1ZW5jZXMsIHdoaWNoIGFyZSBpbmRleGVkIGJ5IGEgcmFuZ2Ugb2YgbnVtYmVycywgZGljdGlvbmFyaWVzIGFyZSBpbmRleGVkIGJ5IGtleXMsIHdoaWNoIGNhbiBiZSBhbnkgaW1tdXRhYmxlIHR5cGU7IHN0cmluZ3MgYW5kIG51bWJlcnMgY2FuIGFsd2F5cyBiZSBrZXlzLiBUdXBsZXMgY2FuIGJlIHVzZWQgYXMga2V5cyBpZiB0aGV5IGNvbnRhaW4gb25seSBzdHJpbmdzLCBudW1iZXJzLCBvciB0dXBsZXM7IGlmIGEgdHVwbGUgY29udGFpbnMgYW55IG11dGFibGUgb2JqZWN0IGVpdGhlciBkaXJlY3RseSBvciBpbmRpcmVjdGx5LCBpdCBjYW5ub3QgYmUgdXNlZCBhcyBhIGtleS4gWW91IGNhblxcdTIwMTl0IHVzZSBsaXN0cyBhcyBrZXlzLCBzaW5jZSBsaXN0cyBjYW4gYmUgbW9kaWZpZWQgaW4gcGxhY2UgdXNpbmcgaW5kZXggYXNzaWdubWVudHMsIHNsaWNlIGFzc2lnbm1lbnRzLCBvciBtZXRob2RzIGxpa2UgYGFwcGVuZCgpYCBhbmQgYGV4dGVuZCgpYC5cIl19XSIsImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnt9LCJ0eXBlIjoidG9vbCIsIm5hbWUiOiJ3ZWJfc2VhcmNoIiwiaWQiOiI2ZTUxMjVhYy0zMTY0LTRhNzYtOWM1Mi1hYzM0NjBjZTM2ZTQiLCJ0b29sX2NhbGxfaWQiOiJ0b29sdV8wMUIyTGZIR0RqWVNGSmhtaVhOajRDdVEiLCJzdGF0dXMiOiJzdWNjZXNzIn0seyJjb250ZW50IjpbeyJpZCI6InRvb2x1XzAxWGpqM2FSZFd5aEJKZlBtVEpCeFFhOSIsImNhbGxlciI6eyJ0eXBlIjoiZGlyZWN0In0sImlucHV0Ijp7fSwibmFtZSI6InRyYW5zZmVyX3RvX3NrZXB0aWMiLCJ0eXBlIjoidG9vbF91c2UiLCJ0b29sc2V0X25hbWUiOm51bGx9XSwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6eyJpZCI6Im1zZ18wMTFDZmR3QTZGNGNDTjV5aEQ0Q3JzOU0iLCJjb250YWluZXIiOm51bGwsImRpYWdub3N0aWNzIjpudWxsLCJtb2RlbCI6ImNsYXVkZS1zb25uZXQiLCJzdG9wX2RldGFpbHMiOm51bGwsInN0b3BfcmVhc29uIjoidG9vbF91c2UiLCJzdG9wX3NlcXVlbmNlIjpudWxsLCJ1c2FnZSI6eyJjYWNoZV9jcmVhdGlvbiI6eyJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowfSwiY2FjaGVfY3JlYXRpb25faW5wdXRfdG9rZW5zIjowLCJjYWNoZV9yZWFkX2lucHV0X3Rva2VucyI6MCwiaW5mZXJlbmNlX2dlbyI6Imdsb2JhbCIsImlucHV0X3Rva2VucyI6NzM3OCwib3V0cHV0X3Rva2VucyI6MzMsIm91dHB1dF90b2tlbnNfZGV0YWlscyI6eyJ0aGlua2luZ190b2tlbnMiOjB9LCJzZXJ2ZXJfdG9vbF91c2UiOm51bGwsInNlcnZpY2VfdGllciI6InN0YW5kYXJkIn0sIm1vZGVsX25hbWUiOiJjbGF1ZGUtc29ubmV0IiwibW9kZWxfcHJvdmlkZXIiOiJhbnRocm9waWMifSwidHlwZSI6ImFpIiwibmFtZSI6InJlc2VhcmNoZXIiLCJpZCI6ImxjX3J1bi0tMDFhMGZlMDMtM2NkOC03OWYxLTg4YTEtY2U2Y2VlMjk0ZTc5LTAiLCJ0b29sX2NhbGxzIjpbeyJuYW1lIjoidHJhbnNmZXJfdG9fc2tlcHRpYyIsImFyZ3MiOnt9LCJpZCI6InRvb2x1XzAxWGpqM2FSZFd5aEJKZlBtVEpCeFFhOSIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6NzM3OCwib3V0cHV0X3Rva2VucyI6MzMsInRvdGFsX3Rva2VucyI6NzQxMSwiaW5wdXRfdG9rZW5fZGV0YWlscyI6eyJjYWNoZV9yZWFkIjowLCJjYWNoZV9jcmVhdGlvbiI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MH0sIm91dHB1dF90b2tlbl9kZXRhaWxzIjp7InJlYXNvbmluZyI6MH19fSx7ImNvbnRlbnQiOiJTdWNjZXNzZnVsbHkgdHJhbnNmZXJyZWQgdG8gc2tlcHRpYyIsImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnt9LCJ0eXBlIjoidG9vbCIsIm5hbWUiOiJ0cmFuc2Zlcl90b19za2VwdGljIiwiaWQiOiIzODkwNThkMS0wODNmLTQ2MzItYmJjNS0wOWJmZDNhMGZmZDIiLCJ0b29sX2NhbGxfaWQiOiJ0b29sdV8wMVhqajNhUmRXeWhCSmZQbVRKQnhRYTkiLCJzdGF0dXMiOiJzdWNjZXNzIn0seyJjb250ZW50IjpbeyJzaWduYXR1cmUiOiJDQVFTMVFnS0VBZ1NHQUk0QVVJSWRHaHBibXRwYm1jU0RONlRmVTZORE05NzFsRWJ6eG9NdlJVQTFKOW94M2ZKUVlUOUlqQXJDUVFHSEJQNHBSSFBhdlh6UmxiTWJhWUhDNTdZaitHYnhncjBoZWx2ZDJPSUwvbzZSYnQ0UEZBM0ZhSUZVbGdxOGdjN0tRSTlGdEdudlNBa0xCUnpJc1VwLzJkNVJkMnpnRXNma0ZWZVhzbjhXWVlaa2luQVFWVnk2QTdCM0xhRUpXMHhiL3g4OERpNjdmZWR3eDBRK0ZsWnR3Y21UM0RjYWExMUp2ZXlIUnIzZG0rekdTWlA2Q1hlWE5KOG5yVFo3VzFZUlR5c0Q2dzdvN0xwOGgxUndxNGY0bzhqK1FVZlkwdmplK3pKWnN4SFBtUU50M3lrZUtoOTloZ242ZGJpejYvRUhxbWJIalNBdTFNNFNxRURmcUlLVGhIWWVuYW1BWm1jUTRYQU9vNm1kUTYrNzdWZ3BWMWxDMS9rNTJJaVVvSmprR2xRcm5MQ3Z1dGlJN0tOK3NnSzhjMisyS0NKclBSQ3ZWVitCa1N0dlA1aldXcXp5dHBLUStuSHpoTDQ0OE9ySUE5Z2RKQzM5QzhlRHJYZVJuSTd0NEZxbGtYR29NbFpBVjlVTWNyUUhSeE9NaTh0T3lUemk5b3lCRkRUU3NRK0xKcWVyMHR6MUZ0OWdlazZ2emc1MFNwVkFGUWRMRVJ2OFIxWXFNYWVJK3hzdlRBRVc5TVJndlJNa3pMdXpSVDJndXczakQrRmppcDM3eGdLNVFJMFIrQ3NPQW1RUG9UWml6emNJeUFVQXVDSkZDZ3EvZ0QvQ2liTHhveW1pVlVJMWFuOVNudDNLcE5Sb1dkdldJbmUzM1YwcHY4UEhnOXlXMkp1TE9xUUdpbExDc0svUTNvUXIzdXBFTVh4WEdqQ0w3V1VpenZSWkdGRUVWK1ZwbFl0N3Y0dEtaTWo1cGszdmRlTTBNSjVYWmc3UHZVc1J6eWN4Y25yVDNLbm9jM3FNK3R0cVpmVHNiOGQ2VS9wUWlmcTdHdWFoRk9IcnZyb3FnSkxqKy84MVl5MXBaRmtqZkpnWTBYa2x6QW5BNkNGcS9ZVDBneGJWK1RINUlTK1dhWU9VekszNlM4czVxcU13aG5ndjRJekUzY3RYWHFuaElaWE56bnlWQnFiWWEvR3gyYkNqY0VqMm41UnlHWVJTLytNY3VsZ0xCem5ROU1rRzJEN1FQM01xL253SFhLTUlhTFM4Vks4aEczZDByQWpsdm5hdVhTaE5ySnh0a2o0cWt3bnhENExyRWprMXVlK1BMY2JMcVlXd0FyOG4wcys0MWpyc0lQVnl5Szl2RmFFWnJBOUthQnhrSnlpcXg1MEdaTm43Y2t4K21rSTE4Z0g1Mml5VlB0VThGS01YanVnQ2w2bVBMaUhZaURRZCtHNjNMdWRtT0t5czlpdFZuQkRCTk1QMmIvSTcrYklWUmxoZUdhWldyNk1BVEtsODZCM3krMGt1T3JMUk15V2NkaWJjMmlRa1ptKzhmN2RUVXdiS2JCSnNLT0ZZNzMvOG5sTC9KaVlwano2blVJaytJcVNqYUZ5SzZYRmxDY3VrV3BXSHBESm5TdmJFemV5N3FIeUNxSitJK29uOGlQOEdPdGVtcFFhUzAvNGtaR1N3bHJFNnhPajZFd0dwZmpiRFpLSGtQLzJSQWROWVBRcTN6N2JkVkpNSk5uRk16NmUzN216TXBDQmlod1BkU0ZUUkUzU0NZNjZ3dlRnSnpHQ1V5aEhiU2k1aTFhenpPWGQ4dUhDU3BULzZMMW82VlUwcGpvUjhLYWE0d0NXSEdmN1AvV0VkK2F2eXAwMkpudTFjbXBXMCtHcSt2SzloMHRkYjJJQ2xNL2VOZmRvdVFQK2VwOE1KVWpyYURSSUNtQUpRWTVvYlM3MXZuaU9vK3JlYUZ5MHpSZ0IiLCJ0aGlua2luZyI6IiIsInR5cGUiOiJ0aGlua2luZyJ9LHsic2lnbmF0dXJlIjoiQ0FRUy9SRUtFUWdTR0FJNEFVSUpibUZ5Y21GMGFXOXVFZ3dGaDNBVkpaUDNzOHkxSHEwYURHNzZ1aEhPTmFTY1hBR1NoaUl3R2dqTFhIVXgxeVpya0xQbGpqelRPUXljcExKaUtWd1hjeG0vRXpLSm0xczhNNVd4dVJFV0VsZFhjb2FOMC9tc0twa1JNVCtlTGI1aWg5ckFIVUxUb21VTnNVd0pldTBqckplNEdMYXp5N3NQNUt0akVPRUJLUXNYVWZvUTdmRGtaT1FVSFppOXp6UU40aEZObVlKVWYzT1ZxZjlUUU5kQzErbS8vSEFaUGZXbUF5Nkh0RHZtN2tnQkprQ0VvaUZubTd0bi9QWDFoWEdQUmdXYzZCVFhVTXIyV0E4YUt5cWdnUlViTUgyK0pZdjVpV1pkZENjMXVwMU5icjNzRjdXUGNvdDlaQmh5SFFYcjY5MnplSms2U0pneWdJVnJBU2JNbHkyYkJ4VFdKQjYyM2dWZ3pwQ21WU0xaRnBrS1hnUGNwOGhHeURLT3ZGNlNpUVNIcUdSeFFvZnI3VnMxYVBoZlppeFJPSkdEK01scmtnZ1ZBbkdNeVlJRFVacGF2dENlaVUxSm1CU3owMDg0YlhQdFQvdG5wc0tPblNQWVpRbzNCMEJYS2JxQS9Xc0tuZzgvVjNaOFV1YWpvNklWWjJoZ0ExV0RkdXFRT1FrRXhHVTZwRnVMaGViSWp1V3hTTkkvRGZmdlIvL0xOcUNmdmRuZjBodm9QdER4ZngvU2F3SXg0L3NwcTl4YndGekh0TGdvSGcxRjJ3Rnc3Y2xQRGxnMVB5RC92MnlKRzNWOVQ4R0w2akdQRTZyaGZpbC91NEhOdmY3QlcwZFF6Q1RUWGNxWnk0bkJ5eTArcCtTN1p4Zk1sNEtweGEyZ09oaFNOamZwZnVYMFFwTDRrTUU4SjFubGlGTjFkOEtxRVB1REkxOEJRSFVoRC9VZlkyOW9BMHg1MTBGak0vQnNMWjRuNXNwcGtvSWk3Q0ZvUXEyYUFLVk5mQzFLaWxoSXBSRCsxZHlEdFpRa2xOOGdacE9FU0h3Nk1MMVR0VTB5ZkFjYm1xb3hKNmhoanp3SDZDTXNUUUVFeThNYlJCTStRS0trSVJkUkNQSEdGVzJMa3VSNTArSjBwRi90cjZwcVZ2SmVvemZpTW5yRWlsQjI3VFpQNG5LVEpHOHJkLy92Q1dlbjB5N0NBLzhkQko5Z2RwNXR4N05WQTQ1azFnZGN4RVIxZ1lvdU5YM24xdkczL0IxRjQrOTN3WFc5TXFvNlVzNTlUUW1yYjlOcWE3cFNRTlNySDA2dzFHeHlCQWxrRmZxQWxhZmsxNmFNcHE0MTZUSllwR3k0M1dDVWlDY0xXbGhpV2d6MnNnT0xBWFA5YTV3ZVdBS1JDOEo2amtjVWtEZVhuVytIRlNpUE02KzlCbzZrVmhMVWhONXJjNG1IWk9acEY3cHRQcHNRTjRYQ3FMUHNxcFJILzhvNVhweUM2Wm5lVGVGMkV4dGpod1pWalhEd01iSXpWWUlidzF5MlBQR3c4ZEM3cGM0c0lWU25JNG9RQUgwdjY1MGdoZmhtTWV2V1c0aDRQeWxidy9ERzRmZGVUMys4ejBmOE1PU1R0ZmlweDA1L1F0dEhsQXZPRFJ4YTV5REN2T3o2bjNmMUJPME4vNE1iR3lPTTI3cVc0eDhtQlZvcnlVWldmc21oZmkwL0dmTnZCOCt5bFRHYllOWDI3T2NFRjVXWnROcWJXRXk3VjVHYm1aVVN4c3BjZzdGQlozajMvM0w3bXV2WlhvWmkxZjVlcnE0eTNsU0grb0Y3cVBGbnZpZXlMT0N3dWJjUXkrb3lvd2o0Y0QwaWRSZWNucCtzKzUyRDcrbXpGMWdwVytmK2NKYXNveGlnYnhrT2xvUzR5ZWlLdmdNNG5XU3BHRWoxMlJQeDVvODBFbXppWE45dDR6SnpXMWh0QTVoWEpKZUZ5bXBNWXR5Q1VDZXZSV1ZtclJZa3RRN1VuQ2E2dEwvQVZQaTFuaTVYQ1hIZkxPdXFmSzVLTFl4andWdGRoaGZtQ0x2cGFLVk5DRU9DZjRuTkdIcUQ5OHdVYjBlaldOd0RZQm5KR2tCUnc5UlZzcGZ3TmRvV29WY24ycXY4eXdHVXA3eWMvc2syTHBJNlZ6aVJ5dldxYkdORzFaSnFWVnV0UmM0NitzT0U0VlNlUzIvQ1ROS05hNk5NQ2YvaHh4YVVWc1lmS2RQK1MxTGM0aWFuS3Awc1V1Z1BwbXRveWRDMENQMlJ3am5ITGNuenhDbnZxeGxMUVdYTU5QVHN1MnlCY0hsV0pMdGNtZGcvTWNMYWd5N2w1a0c2c043WnhKTEQva0F4OEU2dXFvaFArSy9qTVNyWXVRSm5ocjR0ZjRiaVdGWTNKemYvS3BBWXlWU3ErcGJmRktYTWJMOW5IRW9aUVQxNVd5YWJkNkRNQXEzUVpPdGhNNXBVemROcVVYa2NySTFQd2pBU0FnNGRWVS8ybys5OG1UWG55aFA3VmxFa1RuZGRwd3lKRitZQ0NjMDFwcWE2Wlg5OXBuUitZT3BJcmI1RHRQY0txMHQ1Y0ZDRHlReE4xbFV1cVpjWXVqdlgvR0M3KzZJcFJUei9Oa0VZLzVjbnRPZlpKeWQ2U2tVeC9KUjVBSklSUENOZWliMHJjV25uRm4wWEs4czIyeDQwd0xqRXR1ZlhETzkreXJhZjRrSHhsQkkzU0IwbWVNamVwWDUwQ0poQXg3TmVra1JGbndvZWNMZnFJeXJqWHJnQVpzVE1QaVg5NHNuamRyemlzQVh0QkthbnVsaWxTeE9mVzJIU21mbmswTDJHWEhKSjNTK3ZDYmdSRW1sOWRla2ZtSGhtd0VZdHYza2ZodGg3RVJJd1ZUOGo2OU90SUJDbWVUSUp1QTdvNzNQWGMxTEoyd2h1Wks3RlplNk5UT3M2MU1QN0pWbEljNnRiaHRPQmszTlhVOHBCUE9DWTZRNTVkNjNGdHBVVS9LQ2JRMEsyV1E5bzVqTkd3Tk5KNkN3NUZEQ3QreDVZSmVQMWQyUXpEU2lxK2NTWnF3cUNaVmNOb0FmdEdHemdyUlo0dmtwYlAweFFaSEN0V3NVd0hWVGpyWTROZlJEakhkVlBSbjhKOVh0b29jL2hJV2txekZhY3pZVGxhcHUyUkNKcWU4YUVvM2p6V1pDRUo3QWlCekJZcmFZRGdPZmVpUXllSlVzYmJYSGRHS2lpdzIyQmRwNE0rWXo2NzFNWjBpZTlFV1JrczBRMkRIR1VUbmU5UzR0QUFKUEdiVWY0eHRDTW9KNDBRNFFXMDVRTFNaeTN3TkZBVUZZbVhFNEVDREZCOCtJRWVORkZGL3RnQW5maDhHdkZoLzF4WStMRStvek1taW5qU1J3aHEwOXpRQUVrTkZ5dTBJS2d2RGt5T0kraWNjRjdkb1dMVFVhc1B4TEgxeEdQQlNLa2VXQ25Tb1gvNEMyYzlkdTY2QmJSWGFtSHFhZStWQ2lTNkJOOTUzaVlLT3U4ck1rbmVXK1RGalYwQ3pBZjhQTkc5TEJheVVnWTVVdzl4MFNhcDZ6STRQcGFaS0g0ZDlrdGtGVSs5MXlCYk41U1J0ZGQ4L0VRYXRKWG1CTmZ3N2tScmxsK0xqd1p3ZVdMRWIwalQxUnBHdURxSExkTFRNTWdvd1NjenJwMnpDc0pkUUgvc2VhWXJwd2tDRlI4ZFJqTTdKUlVrVmExQTBTdmRaQVg3NXZ1QnZ2TEJ6TjJjK1JidDVvcXk5M2xxSUJJaktiN3cyVWtSVGI0cEJXY05LTlBVZ3QzYXovUHhReEVhc2FsdGRtdXl2c1hZYnVyM1ZQTm44SnpOLzZKNU4rUUNuejU3MVRjY2FwQ21rUHZGRStnYXlYVStVRjFWS1l5RmNVdmxldjdsc1FsbWpxeksyUUE4WDdRM1R6RmFwcWh2SktsdDdkekJIcmFxWkJnUGdiOU40b0tOYXlpOEZaVDcxK2thWWhJaEZyRVNLWVJIZkhrajVuM2tmaGdMeSt4K2pMRGJLeE1nZ2tnSG5KejlSdUVIWlhCV3RrWUFRPT0iLCJ0aGlua2luZyI6IiIsInR5cGUiOiJ0aGlua2luZyJ9LHsiaWQiOiJ0b29sdV8wMUg2ZlY4SnZSSk52WHk0N2VSbmQzakgiLCJjYWxsZXIiOnsidHlwZSI6ImRpcmVjdCJ9LCJpbnB1dCI6e30sIm5hbWUiOiJ0cmFuc2Zlcl90b192ZXJpZmllciIsInR5cGUiOiJ0b29sX3VzZSIsInRvb2xzZXRfbmFtZSI6bnVsbH1dLCJhZGRpdGlvbmFsX2t3YXJncyI6e30sInJlc3BvbnNlX21ldGFkYXRhIjp7ImlkIjoibXNnXzAxMUNmZHdBTVJkUzIxRmVKZnpRaE0zcyIsImNvbnRhaW5lciI6bnVsbCwiZGlhZ25vc3RpY3MiOm51bGwsIm1vZGVsIjoiY2xhdWRlLXNvbm5ldCIsInN0b3BfZGV0YWlscyI6bnVsbCwic3RvcF9yZWFzb24iOiJ0b29sX3VzZSIsInN0b3Bfc2VxdWVuY2UiOm51bGwsInVzYWdlIjp7ImNhY2hlX2NyZWF0aW9uIjp7ImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjB9LCJjYWNoZV9jcmVhdGlvbl9pbnB1dF90b2tlbnMiOjAsImNhY2hlX3JlYWRfaW5wdXRfdG9rZW5zIjowLCJpbmZlcmVuY2VfZ2VvIjoiZ2xvYmFsIiwiaW5wdXRfdG9rZW5zIjo3Mzk2LCJvdXRwdXRfdG9rZW5zIjo3NzAsIm91dHB1dF90b2tlbnNfZGV0YWlscyI6eyJ0aGlua2luZ190b2tlbnMiOjczOX0sInNlcnZlcl90b29sX3VzZSI6bnVsbCwic2VydmljZV90aWVyIjoic3RhbmRhcmQifSwibW9kZWxfbmFtZSI6ImNsYXVkZS1zb25uZXQiLCJtb2RlbF9wcm92aWRlciI6ImFudGhyb3BpYyJ9LCJ0eXBlIjoiYWkiLCJuYW1lIjoic2tlcHRpYyIsImlkIjoibGNfcnVuLS0wMWEwZmUwMy00YWU5LTc2YzAtODlhNi00ZjBiMTE0ZTMwMzAtMCIsInRvb2xfY2FsbHMiOlt7Im5hbWUiOiJ0cmFuc2Zlcl90b192ZXJpZmllciIsImFyZ3MiOnt9LCJpZCI6InRvb2x1XzAxSDZmVjhKdlJKTnZYeTQ3ZVJuZDNqSCIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6NzM5Niwib3V0cHV0X3Rva2VucyI6NzcwLCJ0b3RhbF90b2tlbnMiOjgxNjYsImlucHV0X3Rva2VuX2RldGFpbHMiOnsiY2FjaGVfcmVhZCI6MCwiY2FjaGVfY3JlYXRpb24iOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjB9LCJvdXRwdXRfdG9rZW5fZGV0YWlscyI6eyJyZWFzb25pbmciOjczOX19fSx7ImNvbnRlbnQiOiJTdWNjZXNzZnVsbHkgdHJhbnNmZXJyZWQgdG8gdmVyaWZpZXIiLCJhZGRpdGlvbmFsX2t3YXJncyI6e30sInJlc3BvbnNlX21ldGFkYXRhIjp7fSwidHlwZSI6InRvb2wiLCJuYW1lIjoidHJhbnNmZXJfdG9fdmVyaWZpZXIiLCJpZCI6ImMwNjQ1NjNhLTk3NGYtNGYwZi1hYjRhLTA4MGU2M2MwMWNmNSIsInRvb2xfY2FsbF9pZCI6InRvb2x1XzAxSDZmVjhKdlJKTnZYeTQ3ZVJuZDNqSCIsInN0YXR1cyI6InN1Y2Nlc3MifSx7ImNvbnRlbnQiOlt7InNpZ25hdHVyZSI6IkNBUVM5Z1VLRUFnU0dBSTRBVUlJZEdocGJtdHBibWNTREdGeUoxTVhvWStBaTZOa2J4b01SZDJUclVmVVU3V3JQcEEySWpEZ3k4ZFVwbGNaS2M3RG5Kd05MVEJmSDVVTlIrbkduYWtTUFFpYThVVkl6cmprT25KMmZMcldVc0Eyb0VPOHlSc3Frd1hra0RDc3loQjk3ZHdqNTdSTXQ5MVh6Z1doTDlsdU5FR085MnlXMHJORkdvTVNVVk94UElyRmM1Ump5cmhLRWMzKzFSbnB4Q2t5bHErTE5sUTVORnhMbjZ2MmNGNUR6cXB2QkhOUjdYQWlnK3VySklVM2dYeWRDa2FHWlpEZXRKdFFPVU9YZ1ppOXo5MTAwTnBkQUVrWERvMklDSENHVEdwVmMwSi9wYlh4V1JCeGI2QjEvR2wwWWpuNjhWNkhsZXNIN0lvQzdHUi8zSHdSdTlOU0RCRzR0dGZRakVXY2crUGVBZWE0Um43anp4K1RtOUg3TDFqb1RLVmdEYlFnNWlLTUxmanZQcWxua3NDTHRYT3Q4alNJUzVPWUxON2EvN1RYNi93NWQzNHZudzh2UERtVTFVWWkwUTcycVVXaFVhMnZ3OE9YTnBjS0w3QnAwbE5mQlM4cnZIWSt2Qlk4L2hhQW9UTDN3dkxGVTFmVCs0ei92QTNCY3NpZ1pEWWxmSmVEWWN4WG1SdXF4enhFR3BYQ1JlOXMxSFd0SUQrNDFwSHU2bHBaSGtYYWdocGM2VFpITHhOd2NWaFRiNmZNUTdRbysyTDZQdmtsaDFtMzJwZW9keGVnMllpUGhkcGwzdy94a09FdTUvSkVGN1pCeHBkVUwrdTN3a081cFVsc3FmZ1g3dWh6djdIQzJXcFNXVmltcndpUXdRT1V4MCtKUHJMdHcrbFlmcTdJM2pydW8wR1cwZ3VXdm51ZjdKTTNZTGo4NHErSmdIb21uU1Nabm5abXJMMFVhUnZyVnlMbzg3N0YzOWNjTFM3WG9abm51aThKNFA1OFpUbWlMa0VKZUdjeDFJdWFnMmUzMzMzOU83WWV3LzU5dExiUXRJR2g5VldNd0hCbkZ4MzlTOC80TEVGcks1SGxkUFFoT3Jsb3lUdGtSczY2aVFSS3R4TUtTMFZJNlFUS1pEQWJzN2E3SDF5QnYrbUppOVhnNHVLbXlVNnFubjd6RUtqalkyYklsQ3dleng0TExHUDVIRDNacjZmWnNtZEcxVUh6RHNCdllHMm9DSTBvcUVLTSt2YWxzVDZoVThNUmpiUUJEL0pKOEpKTi9pQkdsaEJBVUhvMFVtaGh0UjJldVRWcFpXbE1uaG1wWEFkS0RYU2ZQZGFQb2hnQiIsInRoaW5raW5nIjoiIiwidHlwZSI6InRoaW5raW5nIn0seyJpZCI6InRvb2x1XzAxWEVBdWhRSENCZHlDd3R5bVp3RmZEaSIsImNhbGxlciI6eyJ0eXBlIjoiZGlyZWN0In0sImlucHV0Ijp7fSwibmFtZSI6InRyYW5zZmVyX3RvX3JlZF90ZWFtIiwidHlwZSI6InRvb2xfdXNlIiwidG9vbHNldF9uYW1lIjpudWxsfV0sImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnsiaWQiOiJtc2dfMDExQ2Zkd0FzYWJEcXVlZ0hpNllVcENuIiwiY29udGFpbmVyIjpudWxsLCJkaWFnbm9zdGljcyI6bnVsbCwibW9kZWwiOiJjbGF1ZGUtc29ubmV0Iiwic3RvcF9kZXRhaWxzIjpudWxsLCJzdG9wX3JlYXNvbiI6InRvb2xfdXNlIiwic3RvcF9zZXF1ZW5jZSI6bnVsbCwidXNhZ2UiOnsiY2FjaGVfY3JlYXRpb24iOnsiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MH0sImNhY2hlX2NyZWF0aW9uX2lucHV0X3Rva2VucyI6MCwiY2FjaGVfcmVhZF9pbnB1dF90b2tlbnMiOjAsImluZmVyZW5jZV9nZW8iOiJnbG9iYWwiLCJpbnB1dF90b2tlbnMiOjc1MDksIm91dHB1dF90b2tlbnMiOjg4LCJvdXRwdXRfdG9rZW5zX2RldGFpbHMiOnsidGhpbmtpbmdfdG9rZW5zIjo1NX0sInNlcnZlcl90b29sX3VzZSI6bnVsbCwic2VydmljZV90aWVyIjoic3RhbmRhcmQifSwibW9kZWxfbmFtZSI6ImNsYXVkZS1zb25uZXQiLCJtb2RlbF9wcm92aWRlciI6ImFudGhyb3BpYyJ9LCJ0eXBlIjoiYWkiLCJuYW1lIjoidmVyaWZpZXIiLCJpZCI6ImxjX3J1bi0tMDFhMGZlMDMtNjY4Mi03ZDIxLThjMTUtZmZiY2U5NDIyYzlmLTAiLCJ0b29sX2NhbGxzIjpbeyJuYW1lIjoidHJhbnNmZXJfdG9fcmVkX3RlYW0iLCJhcmdzIjp7fSwiaWQiOiJ0b29sdV8wMVhFQXVoUUhDQmR5Q3d0eW1ad0ZmRGkiLCJ0eXBlIjoidG9vbF9jYWxsIn1dLCJpbnZhbGlkX3Rvb2xfY2FsbHMiOltdLCJ1c2FnZV9tZXRhZGF0YSI6eyJpbnB1dF90b2tlbnMiOjc1MDksIm91dHB1dF90b2tlbnMiOjg4LCJ0b3RhbF90b2tlbnMiOjc1OTcsImlucHV0X3Rva2VuX2RldGFpbHMiOnsiY2FjaGVfcmVhZCI6MCwiY2FjaGVfY3JlYXRpb24iOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjB9LCJvdXRwdXRfdG9rZW5fZGV0YWlscyI6eyJyZWFzb25pbmciOjU1fX19LHsiY29udGVudCI6IlN1Y2Nlc3NmdWxseSB0cmFuc2ZlcnJlZCB0byByZWRfdGVhbSIsImFkZGl0aW9uYWxfa3dhcmdzIjp7fSwicmVzcG9uc2VfbWV0YWRhdGEiOnt9LCJ0eXBlIjoidG9vbCIsIm5hbWUiOiJ0cmFuc2Zlcl90b19yZWRfdGVhbSIsImlkIjoiOTgyYzAxMjYtZTZhYi00NThhLTkyMmUtN2IyNjZlODNjMmIyIiwidG9vbF9jYWxsX2lkIjoidG9vbHVfMDFYRUF1aFFIQ0JkeUN3dHltWndGZkRpIiwic3RhdHVzIjoic3VjY2VzcyJ9LHsiY29udGVudCI6W3sic2lnbmF0dXJlIjoiQ0FRU3dnY0tFQWdTR0FJNEFVSUlkR2hwYm10cGJtY1NET1JYZ2U5dUwxODMyUk1Rd0JvTWpRd0F3QUhiOWlQMW9qUEdJakREU2NhbDQ4NmJlQ0pidEc4L0QyWTlnOVM1eElQZmpvSGcvZHh3WDVIeXBTUUVCYmpGaVRTYlBFQ1hTRnpWNllJcTN3YkxjbXlQYnZ1c0duRGV4Rmd4KzNzSVh6dnF5RlYvNjl4aGloTW5TcGZUQ0h5MCswelN1MVdwWVUvV1VwSWZvYVNYVGNUYTFxa004eDhFay95LzFqa0tNWlVmREZhOTN1aFVKeE9DNCtRZ1BXQmwvK1h5MnQ4MkwyeC9lYnE3UUxRVHF0UjBqWGVhVVJRbTNDbzZKdk9nV21Edk1wRWRUZVRXRTNmRGgxdHp6VktzZmx1bTRkODliNkNhS3RuOG5sUWQ3UmhOOTl2TlFNUUhHNVY0T3VWTmRySFBaWnBGT3VoZGVqc01GV1h5Qis1NXNsR0FkOHdFWGdGS2JJL2tuT1hWR3pML05ERjhHdHkxdE5abHUyZmRTQ0FzWVdNc0ZRUDFjYndMZVFHc3p5WHpKTVZaSjJJOXhCUGt5ejFIT1hDUHloNUYrajJnUlRQaWtWQjNBUkM2dGZCL2xEU1VlS0JWWlBRUzhwWS9CNGVDcytJamphQk5XcnVMemZxQ3NjNnhMMEN1UVBTWXlRWGFZRmpZclNSTmNDNzBXUUJXVDVWVmhwMG1BOXlaREdZYlJadDlJNU9LOVFrUW11SjV6REZhTUVPWHpTcnNDNGx0ZVA2TWRpbWlNaWp2c0gzaXErYzZXVVlvbFJqM25lSTg4RWFISXpMQUdScTY0Qk5DTHpkQVlMMnBFVTJzYjV1Rzc4UEtWb1VVQ2JWSkw1anBET2hMT1RPMWJRc1R1b1VwblJSckxRRC9rSXpWK2xqcFZCd3dmSmN5cTc1VEpBL0N0UHIveHIyU1o5QjFiMnNiakc2akQwbGh0b0NkZGVEZ2NxZ2wvTFNTa2N1YVlZOHhQV0N5K0x0TmhjcVRoZm1mdm5ITEpJcEw2Z2pialcvT1FwUmZWVXdmdzFqT2I5YldWd2NnSGhOWWZLWUdQdE04b3RoNXh3TFlSUlZnenFNS092czdmYWxYUmhWeloyU1A2SXcwQk1tQUFaNkhqZkNsOUwrdFBxSk5sblFRT0hwb1dqdW00QitYc1lsZEZFS0dRV1Fxc2Q1OWlOUHZhbzlwL3NDT3Q3ckdxQ296Y21naUVtNHc2NmV6L1FJRHliNDZuMCt0Y05KUFVjb0JLdlEvakR3RTZWd21rUS9uRUNqRnAzVWREVCtrV1lRU05kOGo4VkJaT3BHOExscVVZckVaQ3YwcTdCczF2Y05yZFlpYUZvUzMyb3NheW5XaytIdDNPSHVGV2JFRjhKbHNGVFFBTzA1VnZZa2VjZjBWL29USHNHNWh5T09zN1VFYURGcTd1YUp1eldWaGg1cEFvaklhQmNSOGZWbG4yUExSVFg3aXMybnNBK1FyZGlkZVBjWnRGdGd4QWlLWWUxaTJzU0ZpNHZtOEVPa0NiUTYzd2RRZVk0VXJyNVB1b01Fd3hVVUxqZ0thZ2lBbXNKRHE0UnJWbTdzTzQrNll1QTlqNmwydXlsa09FYzY3dmYvNWZrWHVDc2lBcE5MNmtlYjhjK3ZMMG40RlhHZHpqK2FwU0RmRkdCZ0IiLCJ0aGlua2luZyI6IiIsInR5cGUiOiJ0aGlua2luZyJ9LHsiaWQiOiJ0b29sdV8wMVZCcldkV0VXWWdpdDRrTlllaEJNVTUiLCJjYWxsZXIiOnsidHlwZSI6ImRpcmVjdCJ9LCJpbnB1dCI6e30sIm5hbWUiOiJ0cmFuc2Zlcl90b19lZGl0b3IiLCJ0eXBlIjoidG9vbF91c2UiLCJ0b29sc2V0X25hbWUiOm51bGx9XSwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6eyJpZCI6Im1zZ18wMTFDZmR3QXpmanFVb3BvRW1aTGFxbTEiLCJjb250YWluZXIiOm51bGwsImRpYWdub3N0aWNzIjpudWxsLCJtb2RlbCI6ImNsYXVkZS1zb25uZXQiLCJzdG9wX2RldGFpbHMiOm51bGwsInN0b3BfcmVhc29uIjoidG9vbF91c2UiLCJzdG9wX3NlcXVlbmNlIjpudWxsLCJ1c2FnZSI6eyJjYWNoZV9jcmVhdGlvbiI6eyJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowfSwiY2FjaGVfY3JlYXRpb25faW5wdXRfdG9rZW5zIjowLCJjYWNoZV9yZWFkX2lucHV0X3Rva2VucyI6MCwiaW5mZXJlbmNlX2dlbyI6Imdsb2JhbCIsImlucHV0X3Rva2VucyI6NzQxNiwib3V0cHV0X3Rva2VucyI6MTUxLCJvdXRwdXRfdG9rZW5zX2RldGFpbHMiOnsidGhpbmtpbmdfdG9rZW5zIjoxMTl9LCJzZXJ2ZXJfdG9vbF91c2UiOm51bGwsInNlcnZpY2VfdGllciI6InN0YW5kYXJkIn0sIm1vZGVsX25hbWUiOiJjbGF1ZGUtc29ubmV0IiwibW9kZWxfcHJvdmlkZXIiOiJhbnRocm9waWMifSwidHlwZSI6ImFpIiwibmFtZSI6InJlZF90ZWFtIiwiaWQiOiJsY19ydW4tLTAxYTBmZTAzLTZjZTYtNzI1MS1iNzk2LTRmNjQzMzNmNjdjNi0wIiwidG9vbF9jYWxscyI6W3sibmFtZSI6InRyYW5zZmVyX3RvX2VkaXRvciIsImFyZ3MiOnt9LCJpZCI6InRvb2x1XzAxVkJyV2RXRVdZZ2l0NGtOWWVoQk1VNSIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6NzQxNiwib3V0cHV0X3Rva2VucyI6MTUxLCJ0b3RhbF90b2tlbnMiOjc1NjcsImlucHV0X3Rva2VuX2RldGFpbHMiOnsiY2FjaGVfcmVhZCI6MCwiY2FjaGVfY3JlYXRpb24iOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjB9LCJvdXRwdXRfdG9rZW5fZGV0YWlscyI6eyJyZWFzb25pbmciOjExOX19fSx7ImNvbnRlbnQiOiJTdWNjZXNzZnVsbHkgdHJhbnNmZXJyZWQgdG8gZWRpdG9yIiwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6e30sInR5cGUiOiJ0b29sIiwibmFtZSI6InRyYW5zZmVyX3RvX2VkaXRvciIsImlkIjoiNWQzOWUzNmItYzViNS00NDI2LWE5YWEtYmUyZjdkMzgxNmQ2IiwidG9vbF9jYWxsX2lkIjoidG9vbHVfMDFWQnJXZFdFV1lnaXQ0a05ZZWhCTVU1Iiwic3RhdHVzIjoic3VjY2VzcyJ9LHsiY29udGVudCI6W3sic2lnbmF0dXJlIjoiQ0FRUzVnWUtFQWdTR0FJNEFVSUlkR2hwYm10cGJtY1NESTRRSWI3TDJ3NWFXM2NNL1JvTUxpMndFeERrcWh1eEpEaVlJakFxR3hNNFdVd2lxNHVaSHJpQ2J1QzRrVndhN2lnZFVMb29jWmJpNWZldktiZndxSFNickxOVDUxTkdYNFhzTHRzcWd3WS90YWJIamxsenF1N25SV3Y4K0Z6NFI2bjlqYTdDcGoyNFp1eEZ1S2trUU9CbUE0VGYxYXBrM1JQcWNFUStqK3dlZHUwbE8rcmRFQ3lkM2xYaGZnRVJGRnFjTTZhdWN4ZWw0UmJ3NW9BSFh1OStYZVR0emwrTjh0QWVaOWlHWjJYVHRVNU9iOGFQVDFLdVgrdXA4a1E0VlVYa0JUZmQyZjVKUDlSeFpFcTl3U1lhWnN5SGR2MG4rMVU0NkFPc3ZLWm1wOVFYQndvMmY0TzkwalA4ZWdpcmVtOUViWmJtYVlPSjhXSzdDdEtSVmJZMnk0Kzl4UlVKMDRuc2RJejVGNUZGS0V4eE5PckI0bWMvTkU4M2FiM1o2NGlXek93cW9VR0FHUVNrYUgwZDVjRXVtWm80ZlpaQWhQeXVKZVFEeHVsTUNld243RUdDbnBKdy9uemkwd295RWFRTDRZN2g5OVA3YVh4RnIyOHA1S0N5SkVKVERlZmVJcFZsQXdNQ0Fqeit4QzY5QUFMbXd5VFErY0ZFTStLQWdlSVNwaExWeThBUHIyRlNoYXhCTnJYUWd6MXM5czJkaExaUU9CaXd6aHhtRWdkSzcrOEphcWhCMGVFRWQvMVJWQXVJWWRlekE1SEJyd0U5RHlRaUNsM1VPc2JTbk5FVmUrZ3JIcDVwM3RtTUJxNjhnTFY4Mm9BekZZWmwrQ2V3eDcxdjVkUEZPdktQRUhVenBRWU9WTHJuQjFFWlJZclp6NzJuMndmU1Z4Qk96cFRjbkJ4VjZIZWRDUHlJektYWk05K3lFZVRKaThRdHZWZ1oxdyt2MGhtQ0ZHcG5tWk43bVhsZ3FMMXM2TVhWeWRwUE9LUGxNM05hN0NkSG5QRllpd3Iyekx2a2tjSU03Q3NrL0MzK1pNQVdUSytDOUIxdmJHeFBsdEUzT3Y4a085OFBnU1htMUFKdUViWHkrcjNhM0QzUWxaSjNkRUtlMkxOZEFCeXJQTWhTY0tVOEdsZkgvOU50Z3JodGFrZ2xsRC9NZkFsVHNiTndORHJVdFdSeG1EdUovMForaGtrL1lOd0VEWUFaYThUbXdWb1dPZEJIcFJQSHZaOUU5dXNldWx0bWErSmsxZ1JMRHR2RVprcVhVRVNrTWNxVXRWd1lNNWFqSkE1TjUyY05pWjE1QlRmOFhqR2hLV2RPVjQwKzhIMFBPU3hNMkppZndDTzBDNXhGVzVCbzNJaUlOdjBVT3RZNWY4a3ZQZE0zUGpraGFPcksxeVRBOGVFRTQ0dnVuTDlQa29HZWNiWW0rWEU1S3pMM1FzRW4yWTFJSndPOXcweEhYUVpFZWlQNSswdTNZbkRjOHE5ZEJMaEdXM0Z5MzBnWUFRPT0iLCJ0aGlua2luZyI6IiIsInR5cGUiOiJ0aGlua2luZyJ9LHsiaWQiOiJ0b29sdV8wMUJtOEFVOUVzUVV3cW9WTFlweEtBNzciLCJjYWxsZXIiOnsidHlwZSI6ImRpcmVjdCJ9LCJpbnB1dCI6eyJmaWxlX3BhdGgiOiIvYW5zd2VyLm1kIiwiY29udGVudCI6IioqVHVwbGUgdnMuIGxpc3QgaW1tdXRhYmlsaXR5IChQeXRob24pKipcblxuQSB0dXBsZSBpcyBpbW11dGFibGU6IG9uY2UgY3JlYXRlZCwgeW91IGNhbid0IGFzc2lnbiB0byBpdHMgaXRlbXMsIGFuZCB0aGUgY29sbGVjdGlvbiBvZiBvYmplY3RzIGl0IHJlZmVyZW5jZXMgY2FuJ3QgY2hhbmdlLiBgdFswXSA9IDFgIHJhaXNlcyBgVHlwZUVycm9yYC4gQSBsaXN0IGlzIG11dGFibGU6IHlvdSBjYW4gY2hhbmdlIGl0IGluIHBsYWNlIHdpdGggaW5kZXggb3Igc2xpY2UgYXNzaWdubWVudCwgYGFwcGVuZCgpYCwgYGV4dGVuZCgpYCwgYHNvcnQoKWAgYW5kIHNpbWlsYXIgbWV0aG9kcy5cblxuVHVwbGUgaW1tdXRhYmlsaXR5IGlzIHNoYWxsb3cuIElmIGEgdHVwbGUgaG9sZHMgYSBtdXRhYmxlIG9iamVjdCwgc3VjaCBhcyBhIGxpc3QsIHRoYXQgaW5uZXIgb2JqZWN0IGNhbiBzdGlsbCBjaGFuZ2UsIGFuZCBzbyB0aGUgdHVwbGUncyB2YWx1ZSBjaGFuZ2VzLiBCZWNhdXNlIG9mIHRoaXMsIGEgdHVwbGUgY2FuIGJlIGEgYGRpY3RgIGtleSBvciBgc2V0YCBtZW1iZXIgb25seSBpZiBldmVyeXRoaW5nIGluc2lkZSBpdCBpcyBoYXNoYWJsZS4gQSBsaXN0IGNhbiBuZXZlciBiZSBhIGtleS5cblxuU291cmNlczpcbi0gaHR0cHM6Ly9kb2NzLnB5dGhvbi5vcmcvMy90dXRvcmlhbC9kYXRhc3RydWN0dXJlcy5odG1sXG4tIGh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvcmVmZXJlbmNlL2RhdGFtb2RlbC5odG1sXG4tIGh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvbGlicmFyeS9zdGR0eXBlcy5odG1sXG4ifSwibmFtZSI6IndyaXRlX2ZpbGUiLCJ0eXBlIjoidG9vbF91c2UiLCJ0b29sc2V0X25hbWUiOm51bGx9XSwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6eyJpZCI6Im1zZ18wMTFDZmR3QkJhYTlnak1DY2UxNlRVZW4iLCJjb250YWluZXIiOm51bGwsImRpYWdub3N0aWNzIjpudWxsLCJtb2RlbCI6ImNsYXVkZS1zb25uZXQiLCJzdG9wX2RldGFpbHMiOm51bGwsInN0b3BfcmVhc29uIjoidG9vbF91c2UiLCJzdG9wX3NlcXVlbmNlIjpudWxsLCJ1c2FnZSI6eyJjYWNoZV9jcmVhdGlvbiI6eyJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowfSwiY2FjaGVfY3JlYXRpb25faW5wdXRfdG9rZW5zIjowLCJjYWNoZV9yZWFkX2lucHV0X3Rva2VucyI6MCwiaW5mZXJlbmNlX2dlbyI6Imdsb2JhbCIsImlucHV0X3Rva2VucyI6ODEyNywib3V0cHV0X3Rva2VucyI6NDMzLCJvdXRwdXRfdG9rZW5zX2RldGFpbHMiOnsidGhpbmtpbmdfdG9rZW5zIjo3OX0sInNlcnZlcl90b29sX3VzZSI6bnVsbCwic2VydmljZV90aWVyIjoic3RhbmRhcmQifSwibW9kZWxfbmFtZSI6ImNsYXVkZS1zb25uZXQiLCJtb2RlbF9wcm92aWRlciI6ImFudGhyb3BpYyJ9LCJ0eXBlIjoiYWkiLCJuYW1lIjoiZWRpdG9yIiwiaWQiOiJsY19ydW4tLTAxYTBmZTAzLTc2ZTktN2NhMy1hNWZmLTYzZGU2NmRkOGRkMS0wIiwidG9vbF9jYWxscyI6W3sibmFtZSI6IndyaXRlX2ZpbGUiLCJhcmdzIjp7ImZpbGVfcGF0aCI6Ii9hbnN3ZXIubWQiLCJjb250ZW50IjoiKipUdXBsZSB2cy4gbGlzdCBpbW11dGFiaWxpdHkgKFB5dGhvbikqKlxuXG5BIHR1cGxlIGlzIGltbXV0YWJsZTogb25jZSBjcmVhdGVkLCB5b3UgY2FuJ3QgYXNzaWduIHRvIGl0cyBpdGVtcywgYW5kIHRoZSBjb2xsZWN0aW9uIG9mIG9iamVjdHMgaXQgcmVmZXJlbmNlcyBjYW4ndCBjaGFuZ2UuIGB0WzBdID0gMWAgcmFpc2VzIGBUeXBlRXJyb3JgLiBBIGxpc3QgaXMgbXV0YWJsZTogeW91IGNhbiBjaGFuZ2UgaXQgaW4gcGxhY2Ugd2l0aCBpbmRleCBvciBzbGljZSBhc3NpZ25tZW50LCBgYXBwZW5kKClgLCBgZXh0ZW5kKClgLCBgc29ydCgpYCBhbmQgc2ltaWxhciBtZXRob2RzLlxuXG5UdXBsZSBpbW11dGFiaWxpdHkgaXMgc2hhbGxvdy4gSWYgYSB0dXBsZSBob2xkcyBhIG11dGFibGUgb2JqZWN0LCBzdWNoIGFzIGEgbGlzdCwgdGhhdCBpbm5lciBvYmplY3QgY2FuIHN0aWxsIGNoYW5nZSwgYW5kIHNvIHRoZSB0dXBsZSdzIHZhbHVlIGNoYW5nZXMuIEJlY2F1c2Ugb2YgdGhpcywgYSB0dXBsZSBjYW4gYmUgYSBgZGljdGAga2V5IG9yIGBzZXRgIG1lbWJlciBvbmx5IGlmIGV2ZXJ5dGhpbmcgaW5zaWRlIGl0IGlzIGhhc2hhYmxlLiBBIGxpc3QgY2FuIG5ldmVyIGJlIGEga2V5LlxuXG5Tb3VyY2VzOlxuLSBodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL3R1dG9yaWFsL2RhdGFzdHJ1Y3R1cmVzLmh0bWxcbi0gaHR0cHM6Ly9kb2NzLnB5dGhvbi5vcmcvMy9yZWZlcmVuY2UvZGF0YW1vZGVsLmh0bWxcbi0gaHR0cHM6Ly9kb2NzLnB5dGhvbi5vcmcvMy9saWJyYXJ5L3N0ZHR5cGVzLmh0bWxcbiJ9LCJpZCI6InRvb2x1XzAxQm04QVU5RXNRVXdxb1ZMWXB4S0E3NyIsInR5cGUiOiJ0b29sX2NhbGwifV0sImludmFsaWRfdG9vbF9jYWxscyI6W10sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6ODEyNywib3V0cHV0X3Rva2VucyI6NDMzLCJ0b3RhbF90b2tlbnMiOjg1NjAsImlucHV0X3Rva2VuX2RldGFpbHMiOnsiY2FjaGVfcmVhZCI6MCwiY2FjaGVfY3JlYXRpb24iOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjB9LCJvdXRwdXRfdG9rZW5fZGV0YWlscyI6eyJyZWFzb25pbmciOjc5fX19LHsiY29udGVudCI6IlVwZGF0ZWQgZmlsZSAvYW5zd2VyLm1kIiwiYWRkaXRpb25hbF9rd2FyZ3MiOnt9LCJyZXNwb25zZV9tZXRhZGF0YSI6e30sInR5cGUiOiJ0b29sIiwibmFtZSI6IndyaXRlX2ZpbGUiLCJpZCI6ImUzNDkyZTA4LWM4NjktNDdlYy1hNWY3LWNjNTdlYTVmNjQwMyIsInRvb2xfY2FsbF9pZCI6InRvb2x1XzAxQm04QVU5RXNRVXdxb1ZMWXB4S0E3NyIsInN0YXR1cyI6InN1Y2Nlc3MifV19" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "17535b52f19759b3", + "parentSpanId": "5eb6729648b8a8b0", + "name": "FilesystemMiddleware.wrap_model_call", + "kind": 1, + "startTimeUnixNano": "1790968039097378048", + "endTimeUnixNano": "1790968042917388032", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "FilesystemMiddleware.wrap_model_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "3" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|model:d639a607-1d3b-b4dc-823b-564098184f56" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "editor" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "6ad99925c2a25881", + "parentSpanId": "17535b52f19759b3", + "name": "UnsupportedContentMiddleware.wrap_model_call", + "kind": 1, + "startTimeUnixNano": "1790968039097809152", + "endTimeUnixNano": "1790968042917225984", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chain" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "e30=" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "UnsupportedContentMiddleware.wrap_model_call" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "langchain" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_create_agent" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "3" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|model:d639a607-1d3b-b4dc-823b-564098184f56" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "editor" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + }, + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "73aee64af021a907", + "parentSpanId": "6ad99925c2a25881", + "name": "ChatAnthropic", + "kind": 1, + "startTimeUnixNano": "1790968039099990016", + "endTimeUnixNano": "1790968042916750848", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chat" + } + }, + { + "key": "gen_ai.serialized.name", + "value": { + "stringValue": "ChatAnthropic" + } + }, + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "llm" + } + }, + { + "key": "langsmith.trace.name", + "value": { + "stringValue": "ChatAnthropic" + } + }, + { + "key": "langsmith.trace.session_name", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "gen_ai.system", + "value": { + "stringValue": "anthropic" + } + }, + { + "key": "gen_ai.request.model", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "gen_ai.tool.definitions", + "value": { + "stringValue": "[{\"name\":\"ls\",\"input_schema\":{\"properties\":{\"path\":{\"description\":\"Absolute path to the directory to list. Must be absolute, not relative.\",\"type\":\"string\"}},\"required\":[\"path\"],\"type\":\"object\"},\"description\":\"Lists all files in a directory.\\n\\nThis is useful for exploring the filesystem and finding the right file to read or edit.\\nYou should almost ALWAYS use this tool before using the read_file or edit_file tools.\"},{\"name\":\"read_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path to the file to read. Must be absolute, not relative.\",\"type\":\"string\"},\"offset\":{\"default\":0,\"description\":\"Line number to start reading from (0-indexed). Use for pagination of large files.\",\"type\":\"integer\"},\"limit\":{\"default\":100,\"description\":\"Maximum number of lines to read. Use for pagination of large files.\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"},\"description\":\"Reads a file from the filesystem. Assume any path the user provides is valid; reading a missing file returns an error.\\n\\nUsage:\\n- By default, it reads up to 100 lines starting from the beginning of the file. Use `offset`/`limit` to page through large files instead of reading them whole.\\n- A status header, `@@ field | field | ... @@`, sits above the file content, and every line after it is verbatim file content. When content is truncated, there may be an explanation before the header. Never include the header when editing.\\n- Speculatively batch multiple `read_file` calls in one response when several files may be useful.\\n- An empty file returns a system-reminder warning in place of contents.\\n- Large tool results may be offloaded to a file; the tool message gives the path. Read that path here, paging with `offset`/`limit`.\\n- Images (`.png`, `.jpg`, etc.), audio, video, and PDFs return multimodal content blocks (https://docs.langchain.com/oss/python/langchain/messages#multimodal).\\n- For images and PDFs, pagination via `offset`/`limit` is text-only - supply `file_path` only\\n- Always read a file before editing it.\"},{\"name\":\"write_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path where the file should be written. Must be absolute, not relative.\",\"type\":\"string\"},\"content\":{\"description\":\"The text content to write to the file. This parameter is required.\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"},\"description\":\"Writes content to a file. Creates the file if it does not exist; replaces it entirely if it does.\\n\\nUsage:\\n- Use this tool when you intend to create a new file or replace the whole file. You do not need to read the file first.\\n- Prefer to edit existing files (with the edit_file tool) over creating new ones when possible.\"},{\"name\":\"edit_file\",\"input_schema\":{\"properties\":{\"file_path\":{\"description\":\"Absolute path to the file to edit. Must be absolute, not relative.\",\"type\":\"string\"},\"old_string\":{\"description\":\"The exact text to find and replace. Must be unique in the file unless replace_all is True.\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace old_string with. Must be different from old_string.\",\"type\":\"string\"},\"replace_all\":{\"default\":false,\"description\":\"If True, replace all occurrences of old_string. If False (default), old_string must be unique.\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"},\"description\":\"Performs exact string replacements in files.\\n\\nUsage:\\n- You must read the file before editing; this tool errors otherwise.\\n- Preserve the exact source indentation from the read output, and never include the read status header in old_string or new_string.\\n- Prefer editing an existing file over creating a new one.\\n- Only use emojis if the user explicitly requests it.\"},{\"name\":\"glob\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Glob pattern to match files (e.g., '*.py', '**/*.py', '/subdir/**/*.md'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path; a leading '/' anchors to the search root ('/*.py' matches only top-level files). Leading-dot names are excluded unless the pattern segment starts with '.', so prefer the bare form '*.py' over '**/*.py' -- '**' will not descend into dot-directories like '.github'.\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Base directory to search from. Defaults to the backend's default root.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Find files matching a glob pattern, returning absolute paths.\\n\\nSupports `*` (any characters within a path segment), `**` (any directories), `?` (single character), `[abc]` (one character from a set), and `{a,b}` (alternatives), e.g. `*.py`, `src/**/*.py`, `*.{yml,yaml}`.\\n\\nA pattern without `/` matches the file name at any depth under the search root (`*.py` matches `src/app/main.py`). A pattern containing `/` matches the search-root-relative path (`src/**/*.py`). A leading `/` anchors to the search root (`/*.py` matches only top-level Python files).\\n\\nLeading-dot names are only matched when the pattern segment itself starts with `.` (use `.env`, or `.github/**/*.yml`). Because `**` will not descend into dot-directories, the bare form `*.yml` is *broader* than `**/*.yml` and is usually what you want.\"},{\"name\":\"grep\",\"input_schema\":{\"properties\":{\"pattern\":{\"description\":\"Text pattern to search for (literal string, not regex).\",\"type\":\"string\"},\"path\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Directory to search in. Defaults to current working directory.\"},\"glob\":{\"anyOf\":[{\"type\":\"string\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Glob pattern (NOT regex) limiting which files are searched (e.g. '*.py', '*.ts'). A pattern without '/' matches the file name at any depth; a pattern containing '/' matches the search-root-relative path (e.g. 'src/**/*.py'). This is an in-tool file filter, not a call to the separate glob tool. Brace expansion (e.g. '*.{ts,tsx}') is not supported on all backends; run a separate search per extension for reliable results.\"},\"output_mode\":{\"default\":\"files_with_matches\",\"description\":\"Shape of the returned text. 'files_with_matches' (default): newline-separated matching file paths. 'content': matching lines grouped by file under a ':' header, each line indented and formatted ': ' (only the matched line, no surrounding context). 'count': one ': ' line per file.\",\"enum\":[\"files_with_matches\",\"content\",\"count\"],\"type\":\"string\"},\"max_count\":{\"anyOf\":[{\"exclusiveMinimum\":0,\"type\":\"integer\"},{\"type\":\"null\"}],\"default\":null,\"description\":\"Optional cap on the total number of matches returned across all files. Leave unset to use the configured default. When the cap is hit, results are truncated and a note says so; narrow the pattern or path to see the rest.\"}},\"required\":[\"pattern\"],\"type\":\"object\"},\"description\":\"Search for a LITERAL text pattern across files (NOT regex).\\n\\nThe pattern is matched verbatim: regex metacharacters are ordinary characters, not operators. To match any of several strings, run a separate grep for each; `grep(pattern=\\\"foo|bar\\\")` searches for the literal text \\\"foo|bar\\\", and `.*` or `\\\\.` match those characters literally.\\n\\nReturns matching files or content per `output_mode`. Offloaded large tool results live under the artifacts root (`/large_tool_results/` by default); grep that directory to search them when you do not know the exact path.\"},{\"name\":\"transfer_to_researcher\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Request missing evidence from the researcher\"},{\"name\":\"transfer_to_skeptic\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Request another critique from the skeptic\"},{\"name\":\"transfer_to_verifier\",\"input_schema\":{\"properties\":{},\"type\":\"object\"},\"description\":\"Request another source check from the verifier\"}]" + } + }, + { + "key": "langsmith.metadata.ls_integration", + "value": { + "stringValue": "langchain_chat_model" + } + }, + { + "key": "langsmith.metadata.langgraph_step", + "value": { + "intValue": "3" + } + }, + { + "key": "langsmith.metadata.langgraph_node", + "value": { + "stringValue": "model" + } + }, + { + "key": "langsmith.metadata.langgraph_triggers", + "value": { + "stringValue": "[\"branch:to:model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_path", + "value": { + "stringValue": "[\"__pregel_pull\",\"model\"]" + } + }, + { + "key": "langsmith.metadata.langgraph_checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134|model:d639a607-1d3b-b4dc-823b-564098184f56" + } + }, + { + "key": "langsmith.metadata.lc_agent_name", + "value": { + "stringValue": "editor" + } + }, + { + "key": "langsmith.metadata.checkpoint_ns", + "value": { + "stringValue": "editor:42b8f95e-d208-6d0d-c59e-cc043f552134" + } + }, + { + "key": "langsmith.metadata.ls_provider", + "value": { + "stringValue": "anthropic" + } + }, + { + "key": "langsmith.metadata.ls_model_name", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "langsmith.metadata.ls_model_type", + "value": { + "stringValue": "chat" + } + }, + { + "key": "langsmith.metadata.ls_max_tokens", + "value": { + "intValue": "4096" + } + }, + { + "key": "langsmith.metadata.lc_versions", + "value": { + "stringValue": "{\"langchain-core\":\"1.6.6\",\"langchain\":\"1.4.3\",\"langchain-anthropic\":\"1.7.5\"}" + } + }, + { + "key": "langsmith.metadata.ls_method", + "value": { + "stringValue": "traceable" + } + }, + { + "key": "langsmith.metadata.model", + "value": { + "stringValue": "claude-sonnet" + } + }, + { + "key": "langsmith.metadata.max_tokens", + "value": { + "intValue": "4096" + } + }, + { + "key": "langsmith.metadata.model_kwargs", + "value": { + "stringValue": "{\"extra_body\":{\"extra_headers\":{\"anthropic-workspace-id\":\"[redacted workspace]\"}}}" + } + }, + { + "key": "langsmith.metadata.streaming", + "value": { + "boolValue": false + } + }, + { + "key": "langsmith.metadata.max_retries", + "value": { + "intValue": "2" + } + }, + { + "key": "langsmith.metadata._type", + "value": { + "stringValue": "anthropic-chat" + } + }, + { + "key": "langsmith.metadata.usage_metadata", + "value": { + "stringValue": "{\"input_tokens\":8494,\"output_tokens\":415,\"total_tokens\":8909,\"input_token_details\":{\"cache_read\":0,\"cache_creation\":0,\"ephemeral_5m_input_tokens\":0,\"ephemeral_1h_input_tokens\":0},\"output_token_details\":{\"reasoning\":0}}" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_OTLP_TRACES_ENDPOINT", + "value": { + "stringValue": "http://127.0.0.1:58108/langsmith/v1/traces" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_PROJECT", + "value": { + "stringValue": "litellm-fixture" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING", + "value": { + "stringValue": "true" + } + }, + { + "key": "langsmith.metadata.LANGSMITH_TRACING_MODE", + "value": { + "stringValue": "otel" + } + }, + { + "key": "langsmith.metadata.revision_id", + "value": { + "stringValue": "abd4db9" + } + }, + { + "key": "langsmith.span.tags", + "value": { + "stringValue": "seq:step:1" + } + }, + { + "key": "gen_ai.prompt", + "value": { + "bytesValue": "eyJtZXNzYWdlcyI6W1t7ImxjIjoxLCJ0eXBlIjoiY29uc3RydWN0b3IiLCJpZCI6WyJsYW5nY2hhaW4iLCJzY2hlbWEiLCJtZXNzYWdlcyIsIlN5c3RlbU1lc3NhZ2UiXSwia3dhcmdzIjp7ImNvbnRlbnQiOiJZb3UgYXJlIHRoZSBlZGl0b3IuIFVzZSB0aGUgc2hhcmVkIGNvbnZlcnNhdGlvbiB0byB3cml0ZSBvbmUgY29uY2lzZSBhbnN3ZXIgd2l0aCBzb3VyY2UgVVJMcy4gV3JpdGUgdGhlIGZpbmFsIGFuc3dlciB0byAvYW5zd2VyLm1kIGluIHRoZSBzaGFyZWQgdmlydHVhbCBmaWxlc3lzdGVtIGJlZm9yZSByZXBseWluZy4gSWYgaW1wb3J0YW50IGlzc3VlcyByZW1haW4sIGhhbmQgb2ZmIHRvIHRoZSByaWdodCBhZ2VudCBiZWZvcmUgYW5zd2VyaW5nLiIsInR5cGUiOiJzeXN0ZW0ifX0seyJsYyI6MSwidHlwZSI6ImNvbnN0cnVjdG9yIiwiaWQiOlsibGFuZ2NoYWluIiwic2NoZW1hIiwibWVzc2FnZXMiLCJIdW1hbk1lc3NhZ2UiXSwia3dhcmdzIjp7ImNvbnRlbnQiOiJGb3IgYSBzeW50aGV0aWMgdHJhY2luZyBmaXh0dXJlLCBleHBsYWluIFB5dGhvbiB0dXBsZSB2ZXJzdXMgbGlzdCBpbW11dGFiaWxpdHkgaW4gYXQgbW9zdCAxMjAgd29yZHMuIFVzZSBvbmx5IG9mZmljaWFsIFB5dGhvbiBkb2N1bWVudGF0aW9uIGlmIHlvdSBzZWFyY2guIEhhdmUgdGhlIHNrZXB0aWMgYW5kIHZlcmlmaWVyIGNoZWNrIGl0LCB0aGVuIGhhdmUgdGhlIGVkaXRvciB3cml0ZSAvYW5zd2VyLm1kLiBLZWVwIHRoZSBydW4gc2hvcnQgYW5kIGRvIG5vdCBhc2sgZm9sbG93LXVwIHF1ZXN0aW9ucy4iLCJ0eXBlIjoiaHVtYW4iLCJpZCI6IjQ2MjA0MzA1LWY4ZWUtNDM4NC05Y2U4LWZjZDgwYmZjZGY3NSJ9fSx7ImxjIjoxLCJ0eXBlIjoiY29uc3RydWN0b3IiLCJpZCI6WyJsYW5nY2hhaW4iLCJzY2hlbWEiLCJtZXNzYWdlcyIsIkFJTWVzc2FnZSJdLCJrd2FyZ3MiOnsiY29udGVudCI6W3siaWQiOiJ0b29sdV8wMUIyTGZIR0RqWVNGSmhtaVhOajRDdVEiLCJjYWxsZXIiOnsidHlwZSI6ImRpcmVjdCJ9LCJpbnB1dCI6eyJxdWVyeSI6ImRvY3MucHl0aG9uLm9yZyB0dXBsZXMgaW1tdXRhYmxlIHNlcXVlbmNlcyBsaXN0cyBtdXRhYmxlIGRhdGEgc3RydWN0dXJlcyB0dXRvcmlhbCJ9LCJuYW1lIjoid2ViX3NlYXJjaCIsInR5cGUiOiJ0b29sX3VzZSIsInRvb2xzZXRfbmFtZSI6bnVsbH1dLCJyZXNwb25zZV9tZXRhZGF0YSI6eyJpZCI6Im1zZ18wMTFDZmR3OWFXOWJyZW5QcWd5YmZOd1AiLCJjb250YWluZXIiOm51bGwsImRpYWdub3N0aWNzIjpudWxsLCJtb2RlbCI6ImNsYXVkZS1zb25uZXQiLCJzdG9wX2RldGFpbHMiOm51bGwsInN0b3BfcmVhc29uIjoidG9vbF91c2UiLCJzdG9wX3NlcXVlbmNlIjpudWxsLCJ1c2FnZSI6eyJjYWNoZV9jcmVhdGlvbiI6eyJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowfSwiY2FjaGVfY3JlYXRpb25faW5wdXRfdG9rZW5zIjowLCJjYWNoZV9yZWFkX2lucHV0X3Rva2VucyI6MCwiaW5mZXJlbmNlX2dlbyI6Imdsb2JhbCIsImlucHV0X3Rva2VucyI6Mjg0NSwib3V0cHV0X3Rva2VucyI6NzMsIm91dHB1dF90b2tlbnNfZGV0YWlscyI6eyJ0aGlua2luZ190b2tlbnMiOjB9LCJzZXJ2ZXJfdG9vbF91c2UiOm51bGwsInNlcnZpY2VfdGllciI6InN0YW5kYXJkIn0sIm1vZGVsX25hbWUiOiJjbGF1ZGUtc29ubmV0IiwibW9kZWxfcHJvdmlkZXIiOiJhbnRocm9waWMifSwidHlwZSI6ImFpIiwibmFtZSI6InJlc2VhcmNoZXIiLCJpZCI6ImxjX3J1bi0tMDFhMGZlMDMtMjFhMy03MDAwLWEzODEtMjg0YTZhMGMwM2Y3LTAiLCJ0b29sX2NhbGxzIjpbeyJuYW1lIjoid2ViX3NlYXJjaCIsImFyZ3MiOnsicXVlcnkiOiJkb2NzLnB5dGhvbi5vcmcgdHVwbGVzIGltbXV0YWJsZSBzZXF1ZW5jZXMgbGlzdHMgbXV0YWJsZSBkYXRhIHN0cnVjdHVyZXMgdHV0b3JpYWwifSwiaWQiOiJ0b29sdV8wMUIyTGZIR0RqWVNGSmhtaVhOajRDdVEiLCJ0eXBlIjoidG9vbF9jYWxsIn1dLCJ1c2FnZV9tZXRhZGF0YSI6eyJpbnB1dF90b2tlbnMiOjI4NDUsIm91dHB1dF90b2tlbnMiOjczLCJ0b3RhbF90b2tlbnMiOjI5MTgsImlucHV0X3Rva2VuX2RldGFpbHMiOnsiY2FjaGVfcmVhZCI6MCwiY2FjaGVfY3JlYXRpb24iOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjB9LCJvdXRwdXRfdG9rZW5fZGV0YWlscyI6eyJyZWFzb25pbmciOjB9fSwiaW52YWxpZF90b29sX2NhbGxzIjpbXX19LHsibGMiOjEsInR5cGUiOiJjb25zdHJ1Y3RvciIsImlkIjpbImxhbmdjaGFpbiIsInNjaGVtYSIsIm1lc3NhZ2VzIiwiVG9vbE1lc3NhZ2UiXSwia3dhcmdzIjp7ImNvbnRlbnQiOiJbe1widGl0bGVcIjogXCI1LiBEYXRhIFN0cnVjdHVyZXMgXFx1MjAxNCBQeXRob24gMy4xNC41IGRvY3VtZW50YXRpb25cIiwgXCJ1cmxcIjogXCJodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL3R1dG9yaWFsL2RhdGFzdHJ1Y3R1cmVzLmh0bWxcIiwgXCJoaWdobGlnaHRzXCI6IFtcIllvdSBtaWdodCBoYXZlIG5vdGljZWQgdGhhdCBtZXRob2RzIGxpa2VgaW5zZXJ0YCxgcmVtb3ZlYCBvcmBzb3J0YCB0aGF0IG9ubHkgbW9kaWZ5IHRoZSBsaXN0IGhhdmUgbm8gcmV0dXJuIHZhbHVlIHByaW50ZWQgXFx1MjAxMyB0aGV5IHJldHVybiB0aGUgZGVmYXVsdGBOb25lYC4gWzFdIFRoaXMgaXMgYSBkZXNpZ24gcHJpbmNpcGxlIGZvciBhbGwgbXV0YWJsZSBkYXRhIHN0cnVjdHVyZXMgaW4gUHl0aG9uLlxcbi4uLlxcbiMjIDUuMy4gVHVwbGVzIGFuZCBTZXF1ZW5jZXNcXHUwMGI2XFxuXFxuV2Ugc2F3IHRoYXQgbGlzdHMgYW5kIHN0cmluZ3MgaGF2ZSBtYW55IGNvbW1vbiBwcm9wZXJ0aWVzLCBzdWNoIGFzIGluZGV4aW5nIGFuZCBzbGljaW5nIG9wZXJhdGlvbnMuIFRoZXkgYXJlIHR3byBleGFtcGxlcyBvZiBzZXF1ZW5jZSBkYXRhIHR5cGVzIChzZWUgU2VxdWVuY2UgVHlwZXMgXFx1MjAxNCBsaXN0LCB0dXBsZSwgcmFuZ2UpLiBTaW5jZSBQeXRob24gaXMgYW4gZXZvbHZpbmcgbGFuZ3VhZ2UsIG90aGVyIHNlcXVlbmNlIGRhdGEgdHlwZXMgbWF5IGJlIGFkZGVkLiBUaGVyZSBpcyBhbHNvIGFub3RoZXIgc3RhbmRhcmQgc2VxdWVuY2UgZGF0YSB0eXBlOiB0aGUgdHVwbGUuXFxuXFxuQSB0dXBsZSBjb25zaXN0cyBvZiBhIG51bWJlciBvZiB2YWx1ZXMgc2VwYXJhdGVkIGJ5IGNvbW1hcywgZm9yIGluc3RhbmNlOlxcbi4uLlxcbj4+PiAjIFR1cGxlcyBhcmUgaW1tdXRhYmxlOlxcbj4+PiB0WzBdID0gODg4ODhcXG5UcmFjZWJhY2sgKG1vc3QgcmVjZW50IGNhbGwgbGFzdCk6XFxuICBGaWxlIFxcXCI8c3RkaW4+XFxcIiwgbGluZSAxLCBpbiA8bW9kdWxlPlxcblR5cGVFcnJvcjogJ3R1cGxlJyBvYmplY3QgZG9lcyBub3Qgc3VwcG9ydCBpdGVtIGFzc2lnbm1lbnRcXG4+Pj4gIyBidXQgdGhleSBjYW4gY29udGFpbiBtdXRhYmxlIG9iamVjdHM6XFxuPj4+IHYgPSAoWzEsIDIsIDNdLCBbMywgMiwgMV0pXFxuPj4+IHZcXG4oWzEsIDIsIDNdLCBbMywgMiwgMV0pXFxuLi4uXFxuQXMgeW91IHNlZSwgb24gb3V0cHV0IHR1cGxlcyBhcmUgYWx3YXlzIGVuY2xvc2VkIGluIHBhcmVudGhlc2VzLCBzbyB0aGF0IG5lc3RlZCB0dXBsZXMgYXJlIGludGVycHJldGVkIGNvcnJlY3RseTsgdGhleSBtYXkgYmUgaW5wdXQgd2l0aCBvciB3aXRob3V0IHN1cnJvdW5kaW5nIHBhcmVudGhlc2VzLCBhbHRob3VnaCBvZnRlbiBwYXJlbnRoZXNlcyBhcmUgbmVjZXNzYXJ5IGFueXdheSAoaWYgdGhlIHR1cGxlIGlzIHBhcnQgb2YgYSBsYXJnZXIgZXhwcmVzc2lvbikuIEl0IGlzIG5vdCBwb3NzaWJsZSB0byBhc3NpZ24gdG8gdGhlIGluZGl2aWR1YWwgaXRlbXMgb2YgYSB0dXBsZSwgaG93ZXZlciBpdCBpcyBwb3NzaWJsZSB0byBjcmVhdGUgdHVwbGVzIHdoaWNoIGNvbnRhaW4gbXV0YWJsZSBvYmplY3RzLCBzdWNoIGFzIGxpc3RzLlxcblxcblRob3VnaCB0dXBsZXMgbWF5IHNlZW0gc2ltaWxhciB0byBsaXN0cywgdGhleSBhcmUgb2Z0ZW4gdXNlZCBpbiBkaWZmZXJlbnQgc2l0dWF0aW9ucyBhbmQgZm9yIGRpZmZlcmVudCBwdXJwb3Nlcy4gVHVwbGVzIGFyZSBpbW11dGFibGUsIGFuZCB1c3VhbGx5IGNvbnRhaW4gYSBoZXRlcm9nZW5lb3VzIHNlcXVlbmNlIG9mIGVsZW1lbnRzIHRoYXQgYXJlIGFjY2Vzc2VkIHZpYSB1bnBhY2tpbmcgKHNlZSBsYXRlciBpbiB0aGlzIHNlY3Rpb24pIG9yIGluZGV4aW5nIChvciBldmVuIGJ5IGF0dHJpYnV0ZSBpbiB0aGUgY2FzZSBvZiBuYW1lZHR1cGxlcykuIExpc3RzIGFyZSBtdXRhYmxlLCBhbmQgdGhlaXIgZWxlbWVudHMgYXJlIHVzdWFsbHkgaG9tb2dlbmVvdXMgYW5kIGFyZSBhY2Nlc3NlZCBieSBpdGVyYXRpbmcgb3ZlciB0aGUgbGlzdC5cXG4uLi5cXG5Bbm90aGVyIHVzZWZ1bCBkYXRhIHR5cGUgYnVpbHQgaW50byBQeXRob24gaXMgdGhlIGRpY3Rpb25hcnkgKHNlZSBNYXBwaW5nIFR5cGVzIFxcdTIwMTQgZGljdCkuIERpY3Rpb25hcmllcyBhcmUgc29tZXRpbWVzIGZvdW5kIGluIG90aGVyIGxhbmd1YWdlcyBhcyBcXHUyMDFjYXNzb2NpYXRpdmUgbWVtb3JpZXNcXHUyMDFkIG9yIFxcdTIwMWNhc3NvY2lhdGl2ZSBhcnJheXNcXHUyMDFkLiBVbmxpa2Ugc2VxdWVuY2VzLCB3aGljaCBhcmUgaW5kZXhlZCBieSBhIHJhbmdlIG9mIG51bWJlcnMsIGRpY3Rpb25hcmllcyBhcmUgaW5kZXhlZCBieSBrZXlzLCB3aGljaCBjYW4gYmUgYW55IGltbXV0YWJsZSB0eXBlOyBzdHJpbmdzIGFuZCBudW1iZXJzIGNhbiBhbHdheXMgYmUga2V5cy4gVHVwbGVzIGNhbiBiZSB1c2VkIGFzIGtleXMgaWYgdGhleSBjb250YWluIG9ubHkgc3RyaW5ncywgbnVtYmVycywgb3IgdHVwbGVzOyBpZiBhIHR1cGxlIGNvbnRhaW5zIGFueSBtdXRhYmxlIG9iamVjdCBlaXRoZXIgZGlyZWN0bHkgb3IgaW5kaXJlY3RseSwgaXQgY2Fubm90IGJlIHVzZWQgYXMgYSBrZXkuIFlvdSBjYW5cXHUyMDE5dCB1c2UgbGlzdHMgYXMga2V5cywgc2luY2UgbGlzdHMgY2FuIGJlIG1vZGlmaWVkIGluIHBsYWNlIHVzaW5nIGluZGV4IGFzc2lnbm1lbnRzLCBzbGljZSBhc3NpZ25tZW50cywgb3IgbWV0aG9kcyBsaWtlIGFwcGVuZCgpIGFuZCBleHRlbmQoKS5cIl19LCB7XCJ0aXRsZVwiOiBcIjMuIERhdGEgbW9kZWwgXFx1MjAxNCBQeXRob24gMy4xNC41IGRvY3VtZW50YXRpb25cIiwgXCJ1cmxcIjogXCJodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL3JlZmVyZW5jZS9kYXRhbW9kZWwuaHRtbFwiLCBcImhpZ2hsaWdodHNcIjogW1wiVGhlIHZhbHVlIG9mIHNvbWUgb2JqZWN0cyBjYW4gY2hhbmdlLiBPYmplY3RzIHdob3NlIHZhbHVlIGNhbiBjaGFuZ2UgYXJlIHNhaWQgdG8gYmUgbXV0YWJsZTsgb2JqZWN0cyB3aG9zZSB2YWx1ZSBpcyB1bmNoYW5nZWFibGUgb25jZSB0aGV5IGFyZSBjcmVhdGVkIGFyZSBjYWxsZWQgaW1tdXRhYmxlLiAoVGhlIHZhbHVlIG9mIGFuIGltbXV0YWJsZSBjb250YWluZXIgb2JqZWN0IHRoYXQgY29udGFpbnMgYSByZWZlcmVuY2UgdG8gYSBtdXRhYmxlIG9iamVjdCBjYW4gY2hhbmdlIHdoZW4gdGhlIGxhdHRlclxcdTIwMTlzIHZhbHVlIGlzIGNoYW5nZWQ7IGhvd2V2ZXIgdGhlIGNvbnRhaW5lciBpcyBzdGlsbCBjb25zaWRlcmVkIGltbXV0YWJsZSwgYmVjYXVzZSB0aGUgY29sbGVjdGlvbiBvZiBvYmplY3RzIGl0IGNvbnRhaW5zIGNhbm5vdCBiZSBjaGFuZ2VkLiBTbywgaW1tdXRhYmlsaXR5IGlzIG5vdCBzdHJpY3RseSB0aGUgc2FtZSBhcyBoYXZpbmcgYW4gdW5jaGFuZ2VhYmxlIHZhbHVlLCBpdCBpcyBtb3JlIHN1YnRsZS4pIEFuIG9iamVjdFxcdTIwMTlzIG11dGFiaWxpdHkgaXMgZGV0ZXJtaW5lZCBieSBpdHMgdHlwZTsgZm9yIGluc3RhbmNlLCBudW1iZXJzLCBzdHJpbmdzIGFuZCB0dXBsZXMgYXJlIGltbXV0YWJsZSwgd2hpbGUgZGljdGlvbmFyaWVzIGFuZCBsaXN0cyBhcmUgbXV0YWJsZS5cXG4uLi5cXG5Tb21lIG9iamVjdHMgY29udGFpbiByZWZlcmVuY2VzIHRvIG90aGVyIG9iamVjdHM7IHRoZXNlIGFyZSBjYWxsZWQgY29udGFpbmVycy4gRXhhbXBsZXMgb2YgY29udGFpbmVycyBhcmUgdHVwbGVzLCBsaXN0cyBhbmQgZGljdGlvbmFyaWVzLiBUaGUgcmVmZXJlbmNlcyBhcmUgcGFydCBvZiBhIGNvbnRhaW5lclxcdTIwMTlzIHZhbHVlLiBJbiBtb3N0IGNhc2VzLCB3aGVuIHdlIHRhbGsgYWJvdXQgdGhlIHZhbHVlIG9mIGEgY29udGFpbmVyLCB3ZSBpbXBseSB0aGUgdmFsdWVzLCBub3QgdGhlIGlkZW50aXRpZXMgb2YgdGhlIGNvbnRhaW5lZCBvYmplY3RzOyBob3dldmVyLCB3aGVuIHdlIHRhbGsgYWJvdXQgdGhlIG11dGFiaWxpdHkgb2YgYSBjb250YWluZXIsIG9ubHkgdGhlIGlkZW50aXRpZXMgb2YgdGhlIGltbWVkaWF0ZWx5IGNvbnRhaW5lZCBvYmplY3RzIGFyZSBpbXBsaWVkLiBTbywgaWYgYW4gaW1tdXRhYmxlIGNvbnRhaW5lciAobGlrZSBhIHR1cGxlKSBjb250YWlucyBhIHJlZmVyZW5jZSB0byBhIG11dGFibGUgb2JqZWN0LCBpdHMgdmFsdWUgY2hhbmdlcyBpZiB0aGF0IG11dGFibGUgb2JqZWN0IGlzIGNoYW5nZWQuXFxuLi4uXFxuIyMjIDMuMi41LiBTZXF1ZW5jZXNcXHUwMGI2XFxuLi4uXFxuIyMjIyAzLjIuNS4xLiBJbW11dGFibGUgc2VxdWVuY2VzXFx1MDBiNlxcblxcbkFuIG9iamVjdCBvZiBhbiBpbW11dGFibGUgc2VxdWVuY2UgdHlwZSBjYW5ub3QgY2hhbmdlIG9uY2UgaXQgaXMgY3JlYXRlZC4gKElmIHRoZSBvYmplY3QgY29udGFpbnMgcmVmZXJlbmNlcyB0byBvdGhlciBvYmplY3RzLCB0aGVzZSBvdGhlciBvYmplY3RzIG1heSBiZSBtdXRhYmxlIGFuZCBtYXkgYmUgY2hhbmdlZDsgaG93ZXZlciwgdGhlIGNvbGxlY3Rpb24gb2Ygb2JqZWN0cyBkaXJlY3RseSByZWZlcmVuY2VkIGJ5IGFuIGltbXV0YWJsZSBvYmplY3QgY2Fubm90IGNoYW5nZS4pXFxuXFxuVGhlIGZvbGxvd2luZyB0eXBlcyBhcmUgaW1tdXRhYmxlIHNlcXVlbmNlczpcXG4uLi5cXG5UdXBsZXNcXG46IFRoZSBpdGVtcyBvZiBhIGB0dXBsZWAgYXJlIGFyYml0cmFyeSBQeXRob24gb2JqZWN0cy4gVHVwbGVzIG9mIHR3byBvciBtb3JlIGl0ZW1zIGFyZSBmb3JtZWQgYnkgY29tbWEtc2VwYXJhdGVkIGxpc3RzIG9mIGV4cHJlc3Npb25zLiBBIHR1cGxlIG9mIG9uZSBpdGVtIChhIFxcdTIwMThzaW5nbGV0b25cXHUyMDE5KSBjYW4gYmUgZm9ybWVkIGJ5IGFmZml4aW5nIGEgY29tbWEgdG8gYW4gZXhwcmVzc2lvbiAoYW4gZXhwcmVzc2lvbiBieSBpdHNlbGYgZG9lcyBub3QgY3JlYXRlIGEgdHVwbGUsIHNpbmNlIHBhcmVudGhlc2VzIG11c3QgYmUgdXNhYmxlIGZvciBncm91cGluZyBvZiBleHByZXNzaW9ucykuIEFuIGVtcHR5IHR1cGxlIGNhbiBiZSBmb3JtZWQgYnkgYW4gZW1wdHkgcGFpciBvZiBwYXJlbnRoZXNlcy5cXG4uLi5cXG4jIyMjIDMuMi41LjIuIE11dGFibGUgc2VxdWVuY2VzXFx1MDBiNlxcblxcbk11dGFibGUgc2VxdWVuY2VzIGNhbiBiZSBjaGFuZ2VkIGFmdGVyIHRoZXkgYXJlIGNyZWF0ZWQuIFRoZSBzdWJzY3JpcHRpb24gYW5kIHNsaWNpbmcgbm90YXRpb25zIGNhbiBiZSB1c2VkIGFzIHRoZSB0YXJnZXQgb2YgYXNzaWdubWVudCBhbmQgYGRlbGAgKGRlbGV0ZSkgc3RhdGVtZW50cy5cXG4uLi5cXG5UaGVyZSBhcmUgY3VycmVudGx5IHR3byBpbnRyaW5zaWMgbXV0YWJsZSBzZXF1ZW5jZSB0eXBlczpcXG5cXG5MaXN0c1xcbjogVGhlIGl0ZW1zIG9mIGEgbGlzdCBhcmUgYXJiaXRyYXJ5IFB5dGhvbiBvYmplY3RzLiBMaXN0cyBhcmUgZm9ybWVkIGJ5IHBsYWNpbmcgYSBjb21tYS1zZXBhcmF0ZWQgbGlzdCBvZiBleHByZXNzaW9ucyBpbiBzcXVhcmUgYnJhY2tldHMuIChOb3RlIHRoYXQgdGhlcmUgYXJlIG5vIHNwZWNpYWwgY2FzZXMgbmVlZGVkIHRvIGZvcm0gbGlzdHMgb2YgbGVuZ3RoIDAgb3IgMS4pXCJdfSwge1widGl0bGVcIjogXCJCdWlsdC1pbiBUeXBlcyBcXHUyMDE0IFB5dGhvbiAzLjE0LjcgZG9jdW1lbnRhdGlvblwiLCBcInVybFwiOiBcImh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvYnVpbHRpbnMvc3RkdHlwZXMuaHRtbFwiLCBcImhpZ2hsaWdodHNcIjogW1wiY29sbGVjdGlvbiBjbGFzc2VzIGFyZSBtdXRhYmxlLiBUaGUgbWV0aG9kcyB0aGF0IGFkZCwgc3VidHJhY3QsIG9yIHJlYXJyYW5nZSB0aGVpciAuLi4gaW4gcGxhY2UsIGFuZCBkb25cXHUyMDE5dCByZXR1cm4gYSAuLi4gLCBuZXZlciByZXR1cm4gdGhlIGNvbGxlY3Rpb24gaW5zdGFuY2UgaXRzZWxmIGJ1dCBgTm9uZWAuXFxuLi4uXFxuIyMgU2VxdWVuY2UgVHlwZXMgXFx1MjAxNCBgbGlzdGAsIGB0dXBsZWAsIGByYW5nZWBcXHUwMGI2XFxuXFxuVGhlcmUgYXJlIHRocmVlIGJhc2ljIHNlcXVlbmNlIHR5cGVzOiBsaXN0cywgdHVwbGVzLCBhbmQgcmFuZ2Ugb2JqZWN0cy4gQWRkaXRpb25hbCBzZXF1ZW5jZSB0eXBlcyB0YWlsb3JlZCBmb3IgcHJvY2Vzc2luZyBvZiBiaW5hcnkgZGF0YSBhbmQgdGV4dCBzdHJpbmdzIGFyZSBkZXNjcmliZWQgaW4gZGVkaWNhdGVkIHNlY3Rpb25zLlxcbi4uLlxcblRoZSBvcGVyYXRpb25zIGluIHRoZSBmb2xsb3dpbmcgdGFibGUgLi4uIG11dGFibGUgYW5kIGltbXV0YWJsZS4gVGhlIGBjb2xsZWN0aW9ucy4gLi4uIGlzIHByb3ZpZGVkIHRvIG1ha2UgLi4uIGVhc2llciB0byBjb3JyZWN0bHkgaW1wbGVtZW50IHRoZXNlIG9wZXJhdGlvbnMgb24gY3VzdG9tIHNlcXVlbmNlIHR5cGVzXFxuLi4uXFxuIyMjIEltbXV0YWJsZSBTZXF1ZW5jZSBUeXBlc1xcdTAwYjZcXG4uLi5cXG5tdXRhYmxlIHNlcXVlbmNlIHR5cGVzIGlzXFxuLi4uXFxuc3VwcG9ydCBhbGxvd3MgaW1tdXRhYmxlIHNlcXVlbmNlcywgLi4uICwgdG8gYmUgdXNlZCBhcyBgZGljdGAga2V5cyBhbmQgc3RvcmVkIGluIC4uLiBlbnNldGAgaW5zdGFuY2VzXFxuLi4uXFxuIyMjIE11dGFibGUgU2VxdWVuY2UgVHlwZXNcXHUwMGI2XFxuLi4uXFxuIyMjIExpc3RzXFx1MDBiNlxcblxcbkxpc3RzIGFyZSBtdXRhYmxlIHNlcXVlbmNlcywgdHlwaWNhbGx5IHVzZWQgdG8gc3RvcmUgY29sbGVjdGlvbnMgb2YgaG9tb2dlbmVvdXMgaXRlbXMgKHdoZXJlIHRoZSBwcmVjaXNlIGRlZ3JlZSBvZiBzaW1pbGFyaXR5IHdpbGwgdmFyeSBieSBhcHBsaWNhdGlvbikuXFxuLi4uXFxuIyMjIFR1cGxlc1xcdTAwYjZcXG5cXG5UdXBsZXMgYXJlIGltbXV0YWJsZSBzZXF1ZW5jZXMsIHR5cGljYWxseSB1c2VkIHRvIHN0b3JlIGNvbGxlY3Rpb25zIG9mIGhldGVyb2dlbmVvdXMgZGF0YSAoc3VjaCBhcyB0aGUgMi10dXBsZXMgcHJvZHVjZWQgYnkgdGhlIGBlbnVtZXJhdGUoKWAgYnVpbHQtaW4pLiBUdXBsZXMgYXJlIGFsc28gdXNlZCBmb3IgY2FzZXMgd2hlcmUgYW4gaW1tdXRhYmxlIHNlcXVlbmNlIG9mIGhvbW9nZW5lb3VzIGRhdGEgaXMgbmVlZGVkIChzdWNoIGFzIGFsbG93aW5nIHN0b3JhZ2UgaW4gYSBgc2V0YCBvciBgZGljdGAgaW5zdGFuY2UpLlxcbi4uLlxcbnR1cGxlKGl0ZXJhYmxlPVxcbi4uLlxcblRoZSBjb25zdHJ1Y3RvciBidWlsZHMgYSB0dXBsZSB3aG9zZSBpdGVtcyBhcmUgdGhlIHNhbWUgYW5kIGluIHRoZSBzYW1lIG9yZGVyIGFzIGl0ZXJhYmxlXFx1MjAxOXMgaXRlbXMuIGl0ZXJhYmxlIG1heSBiZSBlaXRoZXIgYSBzZXF1ZW5jZSwgYSBjb250YWluZXIgdGhhdCBzdXBwb3J0cyBpdGVyYXRpb24sIG9yIGFuIGl0ZXJhdG9yIG9iamVjdC4gSWYgaXRlcmFibGUgaXMgYWxyZWFkeSBhIHR1cGxlLCBpdCBpcyByZXR1cm5lZCB1bmNoYW5nZWQuIEZvciBleGFtcGxlLCBgdHVwbGUoJ2FiYycpYCByZXR1cm5zIGAoJ2EnLCAnYicsICdjJylgIGFuZCBgdHVwbGUoIFsxLCAyLCAzXSApYCByZXR1cm5zIGAoMSwgMiwgMylgLiBJZiBubyBhcmd1bWVudCBpcyBnaXZlbiwgdGhlIGNvbnN0cnVjdG9yIGNyZWF0ZXMgYSBuZXcgZW1wdHkgdHVwbGUsIGAoKWAuXFxuLi4uXFxuVHVwbGVzIGltcGxlbWVudCBhbGwgb2YgdGhlIGNvbW1vbiBzZXF1ZW5jZSBvcGVyYXRpb25zLlxcbi4uLlxcbkZvciBoZXRlcm9nZW5lb3VzIGNvbGxlY3Rpb25zIG9mIGRhdGEgd2hlcmUgYWNjZXNzIGJ5IG5hbWUgaXMgY2xlYXJlciB0aGFuIGFjY2VzcyBieSBpbmRleCwgYGNvbGxlY3Rpb25zLm5hbWVkdHVwbGUoKWAgbWF5IGJlIGEgbW9yZSBhcHByb3ByaWF0ZSBjaG9pY2UgdGhhbiBhIHNpbXBsZSB0dXBsZSBvYmplY3QuXCJdfSwge1widGl0bGVcIjogXCJCdWlsdC1pbiBUeXBlcyBcXHUyMDE0IFB5dGhvbiAzLjE0LjUgZG9jdW1lbnRhdGlvblwiLCBcInVybFwiOiBcImh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvbGlicmFyeS9zdGR0eXBlcy5odG1sXCIsIFwiaGlnaGxpZ2h0c1wiOiBbXCJTb21lIGNvbGxlY3Rpb24gY2xhc3NlcyBhcmUgbXV0YWJsZS4gVGhlIG1ldGhvZHMgdGhhdCBhZGQsIHN1YnRyYWN0LCBvciByZWFycmFuZ2UgdGhlaXIgLi4uIGluIHBsYWNlLCBhbmQgZG9uXFx1MjAxOXQgcmV0dXJuIGEgLi4uICwgbmV2ZXIgcmV0dXJuIHRoZSBjb2xsZWN0aW9uIGluc3RhbmNlIGl0c2VsZiBidXQgYE5vbmVgLlxcbi4uLlxcbiMjIFNlcXVlbmNlIFR5cGVzIFxcdTIwMTQgYGxpc3RgLCBgdHVwbGVgLCBgcmFuZ2VgXFx1MDBiNlxcblxcblRoZXJlIGFyZSB0aHJlZSBiYXNpYyBzZXF1ZW5jZSB0eXBlczogbGlzdHMsIHR1cGxlcywgYW5kIC4uLiBvYmplY3RzLiBBZGRpdGlvbmFsIHNlcXVlbmNlIHR5cGVzIHRhaWxvcmVkIGZvciBwcm9jZXNzaW5nIG9mIGJpbmFyeSBkYXRhIGFuZCB0ZXh0IHN0cmluZ3MgYXJlIGRlc2NyaWJlZCBpbiBkZWRpY2F0ZWQgc2VjdGlvbnMuXFxuLi4uXFxuVGhlIG9wZXJhdGlvbnMgaW4gdGhlIGZvbGxvd2luZyB0YWJsZSAuLi4gaW1tdXRhYmxlLiBUaGUgYCAuLi4gaXMgcHJvdmlkZWQgdG8gbWFrZSAuLi4gZWFzaWVyIHRvIGNvcnJlY3RseSBpbXBsZW1lbnQgdGhlc2Ugb3BlcmF0aW9ucyBvbiBjdXN0b20gc2VxdWVuY2UgdHlwZXNcXG4uLi5cXG4jIyMgSW1tdXRhYmxlIFNlcXVlbmNlIFR5cGVzXFx1MDBiNlxcbi4uLlxcbm9wZXJhdGlvbiB0aGF0IGltbXV0YWJsZSBzZXF1ZW5jZSAuLi4gYnkgbXV0YWJsZSBzZXF1ZW5jZSB0eXBlcyBpcyAuLi4gYGhhc2goKWBcXG4uLi5cXG5UaGlzIHN1cHBvcnQgYWxsb3dzIGltbXV0YWJsZSBzZXF1ZW5jZXMsIHN1Y2ggYXMgYHR1cGxlYCBpbnN0YW5jZXMsIHRvIGJlIHVzZWQgYXMgYGRpY3RgIGtleXMgYW5kIHN0b3JlZCBpbiBgc2V0YCBhbmQgYGZyb3plbnNldGAgaW5zdGFuY2VzLlxcbi4uLlxcbiMjIyBNdXRhYmxlIFNlcXVlbmNlIFR5cGVzXFx1MDBiNlxcbi4uLlxcbiMjIyBMaXN0c1xcdTAwYjZcXG5cXG5MaXN0cyBhcmUgbXV0YWJsZSBzZXF1ZW5jZXMsIHR5cGljYWxseSB1c2VkIHRvIHN0b3JlIGNvbGxlY3Rpb25zIG9mIGhvbW9nZW5lb3VzIGl0ZW1zICh3aGVyZSB0aGUgcHJlY2lzZSBkZWdyZWUgb2Ygc2ltaWxhcml0eSB3aWxsIHZhcnkgYnkgYXBwbGljYXRpb24pLlxcbi4uLlxcbiMjIyBUdXBsZXNcXHUwMGI2XFxuXFxuVHVwbGVzIGFyZSBpbW11dGFibGUgc2VxdWVuY2VzLCB0eXBpY2FsbHkgdXNlZCB0byBzdG9yZSBjb2xsZWN0aW9ucyBvZiBoZXRlcm9nZW5lb3VzIGRhdGEgKHN1Y2ggYXMgdGhlIDItdHVwbGVzIHByb2R1Y2VkIGJ5IHRoZSBgZW51bWVyYXRlKClgIGJ1aWx0LWluKS4gVHVwbGVzIGFyZSBhbHNvIHVzZWQgZm9yIGNhc2VzIHdoZXJlIGFuIGltbXV0YWJsZSBzZXF1ZW5jZSBvZiBob21vZ2VuZW91cyBkYXRhIGlzIG5lZWRlZCAoc3VjaCBhcyBhbGxvd2luZyBzdG9yYWdlIGluIGEgYHNldGAgb3IgYGRpY3RgIGluc3RhbmNlKS5cXG4uLi5cXG5UaGUgY29uc3RydWN0b3IgYnVpbGRzIGEgdHVwbGUgd2hvc2UgaXRlbXMgYXJlIHRoZSBzYW1lIGFuZCBpbiB0aGUgc2FtZSBvcmRlciBhcyBpdGVyYWJsZVxcdTIwMTlzIGl0ZW1zLiBpdGVyYWJsZSBtYXkgYmUgZWl0aGVyIGEgc2VxdWVuY2UsIGEgY29udGFpbmVyIHRoYXQgc3VwcG9ydHMgaXRlcmF0aW9uLCBvciBhbiBpdGVyYXRvciBvYmplY3QuIElmIGl0ZXJhYmxlIGlzIGFscmVhZHkgYSB0dXBsZSwgaXQgaXMgcmV0dXJuZWQgdW5jaGFuZ2VkLiBGb3IgZXhhbXBsZSwgYHR1cGxlKCdhYmMnKWAgcmV0dXJucyBgKCdhJywgJ2InLCAnYycpYCBhbmQgYHR1cGxlKCBbMSwgMiwgM10gKWAgcmV0dXJucyBgKDEsIDIsIDMpYC4gSWYgbm8gYXJndW1lbnQgaXMgZ2l2ZW4sIHRoZSBjb25zdHJ1Y3RvciBjcmVhdGVzIGEgbmV3IGVtcHR5IHR1cGxlLCBgKClgLlxcbi4uLlxcblR1cGxlcyBpbXBsZW1lbnQgYWxsIG9mIHRoZSBjb21tb24gc2VxdWVuY2Ugb3BlcmF0aW9ucy5cXG4uLi5cXG5Gb3IgaGV0ZXJvZ2VuZW91cyBjb2xsZWN0aW9ucyBvZiBkYXRhIHdoZXJlIGFjY2VzcyBieSBuYW1lIGlzIGNsZWFyZXIgdGhhbiBhY2Nlc3MgYnkgaW5kZXgsIGBjb2xsZWN0aW9ucy5uYW1lZHR1cGxlKClgIG1heSBiZSBhIG1vcmUgYXBwcm9wcmlhdGUgY2hvaWNlIHRoYW4gYSBzaW1wbGUgdHVwbGUgb2JqZWN0LlwiXX0sIHtcInRpdGxlXCI6IFwiNS4gRGF0YSBTdHJ1Y3R1cmVzIFxcdTIwMTQgUHl0aG9uIDMuMTAuMjAgZG9jdW1lbnRhdGlvblwiLCBcInVybFwiOiBcImh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMuMTAvdHV0b3JpYWwvZGF0YXN0cnVjdHVyZXMuaHRtbFwiLCBcImhpZ2hsaWdodHNcIjogW1wiWW91IG1pZ2h0IGhhdmUgbm90aWNlZCB0aGF0IG1ldGhvZHMgbGlrZSBgaW5zZXJ0YCwgYHJlbW92ZWAgb3IgYHNvcnRgIHRoYXQgb25seSBtb2RpZnkgdGhlIGxpc3QgaGF2ZSBubyByZXR1cm4gdmFsdWUgcHJpbnRlZCBcXHUyMDEzIHRoZXkgcmV0dXJuIHRoZSBkZWZhdWx0IGBOb25lYC4gMSBUaGlzIGlzIGEgZGVzaWduIHByaW5jaXBsZSBmb3IgYWxsIG11dGFibGUgZGF0YSBzdHJ1Y3R1cmVzIGluIFB5dGhvbi5cXG4uLi5cXG4jIyA1LjMuIFR1cGxlcyBhbmQgU2VxdWVuY2VzXFx1MDBiNlxcblxcbldlIHNhdyB0aGF0IGxpc3RzIGFuZCBzdHJpbmdzIGhhdmUgbWFueSBjb21tb24gcHJvcGVydGllcywgc3VjaCBhcyBpbmRleGluZyBhbmQgc2xpY2luZyBvcGVyYXRpb25zLiBUaGV5IGFyZSB0d28gZXhhbXBsZXMgb2Ygc2VxdWVuY2UgZGF0YSB0eXBlcyAoc2VlIFNlcXVlbmNlIFR5cGVzIFxcdTIwMTQgbGlzdCwgdHVwbGUsIHJhbmdlKS4gU2luY2UgUHl0aG9uIGlzIGFuIGV2b2x2aW5nIGxhbmd1YWdlLCBvdGhlciBzZXF1ZW5jZSBkYXRhIHR5cGVzIG1heSBiZSBhZGRlZC4gVGhlcmUgaXMgYWxzbyBhbm90aGVyIHN0YW5kYXJkIHNlcXVlbmNlIGRhdGEgdHlwZTogdGhlIHR1cGxlLlxcblxcbkEgdHVwbGUgY29uc2lzdHMgb2YgYSBudW1iZXIgb2YgdmFsdWVzIHNlcGFyYXRlZCBieSBjb21tYXMsIGZvciBpbnN0YW5jZTpcXG4uLi5cXG4+Pj4gIyBUdXBsZXMgYXJlIGltbXV0YWJsZTpcXG4uLi4gdFswXSA9IDg4ODg4XFxuVHJhY2ViYWNrIChtb3N0IHJlY2VudCBjYWxsIGxhc3QpOlxcbiAgRmlsZSBcXFwiPHN0ZGluPlxcXCIsIGxpbmUgMSwgaW4gPG1vZHVsZT5cXG5UeXBlRXJyb3I6ICd0dXBsZScgb2JqZWN0IGRvZXMgbm90IHN1cHBvcnQgaXRlbSBhc3NpZ25tZW50XFxuPj4+ICMgYnV0IHRoZXkgY2FuIGNvbnRhaW4gbXV0YWJsZSBvYmplY3RzOlxcbi4uLiB2ID0gKFsxLCAyLCAzXSwgWzMsIDIsIDFdKVxcbj4+PiB2XFxuKFsxLCAyLCAzXSwgWzMsIDIsIDFdKVxcbi4uLlxcbkFzIHlvdSBzZWUsIG9uIG91dHB1dCB0dXBsZXMgYXJlIGFsd2F5cyBlbmNsb3NlZCBpbiBwYXJlbnRoZXNlcywgc28gdGhhdCBuZXN0ZWQgdHVwbGVzIGFyZSBpbnRlcnByZXRlZCBjb3JyZWN0bHk7IHRoZXkgbWF5IGJlIGlucHV0IHdpdGggb3Igd2l0aG91dCBzdXJyb3VuZGluZyBwYXJlbnRoZXNlcywgYWx0aG91Z2ggb2Z0ZW4gcGFyZW50aGVzZXMgYXJlIG5lY2Vzc2FyeSBhbnl3YXkgKGlmIHRoZSB0dXBsZSBpcyBwYXJ0IG9mIGEgbGFyZ2VyIGV4cHJlc3Npb24pLiBJdCBpcyBub3QgcG9zc2libGUgdG8gYXNzaWduIHRvIHRoZSBpbmRpdmlkdWFsIGl0ZW1zIG9mIGEgdHVwbGUsIGhvd2V2ZXIgaXQgaXMgcG9zc2libGUgdG8gY3JlYXRlIHR1cGxlcyB3aGljaCBjb250YWluIG11dGFibGUgb2JqZWN0cywgc3VjaCBhcyBsaXN0cy5cXG5cXG5UaG91Z2ggdHVwbGVzIG1heSBzZWVtIHNpbWlsYXIgdG8gbGlzdHMsIHRoZXkgYXJlIG9mdGVuIHVzZWQgaW4gZGlmZmVyZW50IHNpdHVhdGlvbnMgYW5kIGZvciBkaWZmZXJlbnQgcHVycG9zZXMuIFR1cGxlcyBhcmUgaW1tdXRhYmxlLCBhbmQgdXN1YWxseSBjb250YWluIGEgaGV0ZXJvZ2VuZW91cyBzZXF1ZW5jZSBvZiBlbGVtZW50cyB0aGF0IGFyZSBhY2Nlc3NlZCB2aWEgdW5wYWNraW5nIChzZWUgbGF0ZXIgaW4gdGhpcyBzZWN0aW9uKSBvciBpbmRleGluZyAob3IgZXZlbiBieSBhdHRyaWJ1dGUgaW4gdGhlIGNhc2Ugb2YgYG5hbWVkdHVwbGVzYCkuIExpc3RzIGFyZSBtdXRhYmxlLCBhbmQgdGhlaXIgZWxlbWVudHMgYXJlIHVzdWFsbHkgaG9tb2dlbmVvdXMgYW5kIGFyZSBhY2Nlc3NlZCBieSBpdGVyYXRpbmcgb3ZlciB0aGUgbGlzdC5cXG4uLi5cXG4jIyA1LjQuXFxuLi4uXFxuLiBTZXQgb2JqZWN0c1xcbi4uLlxcbiMjIDUuNS4gRGljdGlvbmFyaWVzXFx1MDBiNlxcblxcbkFub3RoZXIgdXNlZnVsIGRhdGEgdHlwZSBidWlsdCBpbnRvIFB5dGhvbiBpcyB0aGUgZGljdGlvbmFyeSAoc2VlIE1hcHBpbmcgVHlwZXMgXFx1MjAxNCBkaWN0KS4gRGljdGlvbmFyaWVzIGFyZSBzb21ldGltZXMgZm91bmQgaW4gb3RoZXIgbGFuZ3VhZ2VzIGFzIFxcdTIwMWNhc3NvY2lhdGl2ZSBtZW1vcmllc1xcdTIwMWQgb3IgXFx1MjAxY2Fzc29jaWF0aXZlIGFycmF5c1xcdTIwMWQuIFVubGlrZSBzZXF1ZW5jZXMsIHdoaWNoIGFyZSBpbmRleGVkIGJ5IGEgcmFuZ2Ugb2YgbnVtYmVycywgZGljdGlvbmFyaWVzIGFyZSBpbmRleGVkIGJ5IGtleXMsIHdoaWNoIGNhbiBiZSBhbnkgaW1tdXRhYmxlIHR5cGU7IHN0cmluZ3MgYW5kIG51bWJlcnMgY2FuIGFsd2F5cyBiZSBrZXlzLiBUdXBsZXMgY2FuIGJlIHVzZWQgYXMga2V5cyBpZiB0aGV5IGNvbnRhaW4gb25seSBzdHJpbmdzLCBudW1iZXJzLCBvciB0dXBsZXM7IGlmIGEgdHVwbGUgY29udGFpbnMgYW55IG11dGFibGUgb2JqZWN0IGVpdGhlciBkaXJlY3RseSBvciBpbmRpcmVjdGx5LCBpdCBjYW5ub3QgYmUgdXNlZCBhcyBhIGtleS4gWW91IGNhblxcdTIwMTl0IHVzZSBsaXN0cyBhcyBrZXlzLCBzaW5jZSBsaXN0cyBjYW4gYmUgbW9kaWZpZWQgaW4gcGxhY2UgdXNpbmcgaW5kZXggYXNzaWdubWVudHMsIHNsaWNlIGFzc2lnbm1lbnRzLCBvciBtZXRob2RzIGxpa2UgYGFwcGVuZCgpYCBhbmQgYGV4dGVuZCgpYC5cIl19XSIsInR5cGUiOiJ0b29sIiwibmFtZSI6IndlYl9zZWFyY2giLCJpZCI6IjZlNTEyNWFjLTMxNjQtNGE3Ni05YzUyLWFjMzQ2MGNlMzZlNCIsInRvb2xfY2FsbF9pZCI6InRvb2x1XzAxQjJMZkhHRGpZU0ZKaG1pWE5qNEN1USIsInN0YXR1cyI6InN1Y2Nlc3MifX0seyJsYyI6MSwidHlwZSI6ImNvbnN0cnVjdG9yIiwiaWQiOlsibGFuZ2NoYWluIiwic2NoZW1hIiwibWVzc2FnZXMiLCJBSU1lc3NhZ2UiXSwia3dhcmdzIjp7ImNvbnRlbnQiOlt7ImlkIjoidG9vbHVfMDFYamozYVJkV3loQkpmUG1USkJ4UWE5IiwiY2FsbGVyIjp7InR5cGUiOiJkaXJlY3QifSwiaW5wdXQiOnt9LCJuYW1lIjoidHJhbnNmZXJfdG9fc2tlcHRpYyIsInR5cGUiOiJ0b29sX3VzZSIsInRvb2xzZXRfbmFtZSI6bnVsbH1dLCJyZXNwb25zZV9tZXRhZGF0YSI6eyJpZCI6Im1zZ18wMTFDZmR3QTZGNGNDTjV5aEQ0Q3JzOU0iLCJjb250YWluZXIiOm51bGwsImRpYWdub3N0aWNzIjpudWxsLCJtb2RlbCI6ImNsYXVkZS1zb25uZXQiLCJzdG9wX2RldGFpbHMiOm51bGwsInN0b3BfcmVhc29uIjoidG9vbF91c2UiLCJzdG9wX3NlcXVlbmNlIjpudWxsLCJ1c2FnZSI6eyJjYWNoZV9jcmVhdGlvbiI6eyJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowfSwiY2FjaGVfY3JlYXRpb25faW5wdXRfdG9rZW5zIjowLCJjYWNoZV9yZWFkX2lucHV0X3Rva2VucyI6MCwiaW5mZXJlbmNlX2dlbyI6Imdsb2JhbCIsImlucHV0X3Rva2VucyI6NzM3OCwib3V0cHV0X3Rva2VucyI6MzMsIm91dHB1dF90b2tlbnNfZGV0YWlscyI6eyJ0aGlua2luZ190b2tlbnMiOjB9LCJzZXJ2ZXJfdG9vbF91c2UiOm51bGwsInNlcnZpY2VfdGllciI6InN0YW5kYXJkIn0sIm1vZGVsX25hbWUiOiJjbGF1ZGUtc29ubmV0IiwibW9kZWxfcHJvdmlkZXIiOiJhbnRocm9waWMifSwidHlwZSI6ImFpIiwibmFtZSI6InJlc2VhcmNoZXIiLCJpZCI6ImxjX3J1bi0tMDFhMGZlMDMtM2NkOC03OWYxLTg4YTEtY2U2Y2VlMjk0ZTc5LTAiLCJ0b29sX2NhbGxzIjpbeyJuYW1lIjoidHJhbnNmZXJfdG9fc2tlcHRpYyIsImFyZ3MiOnt9LCJpZCI6InRvb2x1XzAxWGpqM2FSZFd5aEJKZlBtVEpCeFFhOSIsInR5cGUiOiJ0b29sX2NhbGwifV0sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6NzM3OCwib3V0cHV0X3Rva2VucyI6MzMsInRvdGFsX3Rva2VucyI6NzQxMSwiaW5wdXRfdG9rZW5fZGV0YWlscyI6eyJjYWNoZV9yZWFkIjowLCJjYWNoZV9jcmVhdGlvbiI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MH0sIm91dHB1dF90b2tlbl9kZXRhaWxzIjp7InJlYXNvbmluZyI6MH19LCJpbnZhbGlkX3Rvb2xfY2FsbHMiOltdfX0seyJsYyI6MSwidHlwZSI6ImNvbnN0cnVjdG9yIiwiaWQiOlsibGFuZ2NoYWluIiwic2NoZW1hIiwibWVzc2FnZXMiLCJUb29sTWVzc2FnZSJdLCJrd2FyZ3MiOnsiY29udGVudCI6IlN1Y2Nlc3NmdWxseSB0cmFuc2ZlcnJlZCB0byBza2VwdGljIiwidHlwZSI6InRvb2wiLCJuYW1lIjoidHJhbnNmZXJfdG9fc2tlcHRpYyIsImlkIjoiMzg5MDU4ZDEtMDgzZi00NjMyLWJiYzUtMDliZmQzYTBmZmQyIiwidG9vbF9jYWxsX2lkIjoidG9vbHVfMDFYamozYVJkV3loQkpmUG1USkJ4UWE5Iiwic3RhdHVzIjoic3VjY2VzcyJ9fSx7ImxjIjoxLCJ0eXBlIjoiY29uc3RydWN0b3IiLCJpZCI6WyJsYW5nY2hhaW4iLCJzY2hlbWEiLCJtZXNzYWdlcyIsIkFJTWVzc2FnZSJdLCJrd2FyZ3MiOnsiY29udGVudCI6W3sic2lnbmF0dXJlIjoiQ0FRUzFRZ0tFQWdTR0FJNEFVSUlkR2hwYm10cGJtY1NETjZUZlU2TkRNOTcxbEVienhvTXZSVUExSjlveDNmSlFZVDlJakFyQ1FRR0hCUDRwUkhQYXZYelJsYk1iYVlIQzU3WWorR2J4Z3IwaGVsdmQyT0lML282UmJ0NFBGQTNGYUlGVWxncThnYzdLUUk5RnRHbnZTQWtMQlJ6SXNVcC8yZDVSZDJ6Z0VzZmtGVmVYc244V1lZWmtpbkFRVlZ5NkE3QjNMYUVKVzB4Yi94ODhEaTY3ZmVkd3gwUStGbFp0d2NtVDNEY2FhMTFKdmV5SFJyM2RtK3pHU1pQNkNYZVhOSjhuclRaN1cxWVJUeXNENnc3bzdMcDhoMVJ3cTRmNG84aitRVWZZMHZqZSt6SlpzeEhQbVFOdDN5a2VLaDk5aGduNmRiaXo2L0VIcW1iSGpTQXUxTTRTcUVEZnFJS1RoSFllbmFtQVptY1E0WEFPbzZtZFE2Kzc3VmdwVjFsQzEvazUySWlVb0pqa0dsUXJuTEN2dXRpSTdLTitzZ0s4YzIrMktDSnJQUkN2VlYrQmtTdHZQNWpXV3F6eXRwS1Erbkh6aEw0NDhPcklBOWdkSkMzOUM4ZURyWGVSbkk3dDRGcWxrWEdvTWxaQVY5VU1jclFIUnhPTWk4dE95VHppOW95QkZEVFNzUStMSnFlcjB0ejFGdDlnZWs2dnpnNTBTcFZBRlFkTEVSdjhSMVlxTWFlSSt4c3ZUQUVXOU1SZ3ZSTWt6THV6UlQyZ3V3M2pEK0ZqaXAzN3hnSzVRSTBSK0NzT0FtUVBvVFppenpjSXlBVUF1Q0pGQ2dxL2dEL0NpYkx4b3ltaVZVSTFhbjlTbnQzS3BOUm9XZHZXSW5lMzNWMHB2OFBIZzl5VzJKdUxPcVFHaWxMQ3NLL1Ezb1FyM3VwRU1YeFhHakNMN1dVaXp2UlpHRkVFVitWcGxZdDd2NHRLWk1qNXBrM3ZkZU0wTUo1WFpnN1B2VXNSenljeGNuclQzS25vYzNxTSt0dHFaZlRzYjhkNlUvcFFpZnE3R3VhaEZPSHJ2cm9xZ0pMaisvODFZeTFwWkZramZKZ1kwWGtsekFuQTZDRnEvWVQwZ3hiVitUSDVJUytXYVlPVXpLMzZTOHM1cXFNd2huZ3Y0SXpFM2N0WFhxbmhJWlhOem55VkJxYllhL0d4MmJDamNFajJuNVJ5R1lSUy8rTWN1bGdMQnpuUTlNa0cyRDdRUDNNcS9ud0hYS01JYUxTOFZLOGhHM2QwckFqbHZuYXVYU2hOckp4dGtqNHFrd254RDRMckVqazF1ZStQTGNiTHFZV3dBcjhuMHMrNDFqcnNJUFZ5eUs5dkZhRVpyQTlLYUJ4a0p5aXF4NTBHWk5uN2NreCtta0kxOGdINTJpeVZQdFU4RktNWGp1Z0NsNm1QTGlIWWlEUWQrRzYzTHVkbU9LeXM5aXRWbkJEQk5NUDJiL0k3K2JJVlJsaGVHYVpXcjZNQVRLbDg2QjN5KzBrdU9yTFJNeVdjZGliYzJpUWtabSs4ZjdkVFV3YktiQkpzS09GWTczLzhubEwvSmlZcGp6Nm5VSWsrSXFTamFGeUs2WEZsQ2N1a1dwV0hwREpuU3ZiRXpleTdxSHlDcUorSStvbjhpUDhHT3RlbXBRYVMwLzRrWkdTd2xyRTZ4T2o2RXdHcGZqYkRaS0hrUC8yUkFkTllQUXEzejdiZFZKTUpObkZNejZlMzdtek1wQ0JpaHdQZFNGVFJFM1NDWTY2d3ZUZ0p6R0NVeWhIYlNpNWkxYXp6T1hkOHVIQ1NwVC82TDFvNlZVMHBqb1I4S2FhNHdDV0hHZjdQL1dFZCthdnlwMDJKbnUxY21wVzArR3Erdks5aDB0ZGIySUNsTS9lTmZkb3VRUCtlcDhNSlVqcmFEUklDbUFKUVk1b2JTNzF2bmlPbytyZWFGeTB6UmdCIiwidGhpbmtpbmciOiIiLCJ0eXBlIjoidGhpbmtpbmcifSx7InNpZ25hdHVyZSI6IkNBUVMvUkVLRVFnU0dBSTRBVUlKYm1GeWNtRjBhVzl1RWd3RmgzQVZKWlAzczh5MUhxMGFERzc2dWhIT05hU2NYQUdTaGlJd0dnakxYSFV4MXlacmtMUGxqanpUT1F5Y3BMSmlLVndYY3htL0V6S0ptMXM4TTVXeHVSRVdFbGRYY29hTjAvbXNLcGtSTVQrZUxiNWloOXJBSFVMVG9tVU5zVXdKZXUwanJKZTRHTGF6eTdzUDVLdGpFT0VCS1FzWFVmb1E3ZkRrWk9RVUhaaTl6elFONGhGTm1ZSlVmM09WcWY5VFFOZEMxK20vL0hBWlBmV21BeTZIdER2bTdrZ0JKa0NFb2lGbm03dG4vUFgxaFhHUFJnV2M2QlRYVU1yMldBOGFLeXFnZ1JVYk1IMitKWXY1aVdaZGRDYzF1cDFOYnIzc0Y3V1Bjb3Q5WkJoeUhRWHI2OTJ6ZUprNlNKZ3lnSVZyQVNiTWx5MmJCeFRXSkI2MjNnVmd6cENtVlNMWkZwa0tYZ1BjcDhoR3lES092RjZTaVFTSHFHUnhRb2ZyN1ZzMWFQaGZaaXhST0pHRCtNbHJrZ2dWQW5HTXlZSURVWnBhdnRDZWlVMUptQlN6MDA4NGJYUHRUL3RucHNLT25TUFlaUW8zQjBCWEticUEvV3NLbmc4L1YzWjhVdWFqbzZJVloyaGdBMVdEZHVxUU9Ra0V4R1U2cEZ1TGhlYklqdVd4U05JL0RmZnZSLy9MTnFDZnZkbmYwaHZvUHREeGZ4L1Nhd0l4NC9zcHE5eGJ3RnpIdExnb0hnMUYyd0Z3N2NsUERsZzFQeUQvdjJ5SkczVjlUOEdMNmpHUEU2cmhmaWwvdTRITnZmN0JXMGRRekNUVFhjcVp5NG5CeXkwK3ArUzdaeGZNbDRLcHhhMmdPaGhTTmpmcGZ1WDBRcEw0a01FOEoxbmxpRk4xZDhLcUVQdURJMThCUUhVaEQvVWZZMjlvQTB4NTEwRmpNL0JzTFo0bjVzcHBrb0lpN0NGb1FxMmFBS1ZOZkMxS2lsaElwUkQrMWR5RHRaUWtsTjhnWnBPRVNIdzZNTDFUdFUweWZBY2JtcW94SjZoaGp6d0g2Q01zVFFFRXk4TWJSQk0rUUtLa0lSZFJDUEhHRlcyTGt1UjUwK0owcEYvdHI2cHFWdkplb3pmaU1uckVpbEIyN1RaUDRuS1RKRzhyZC8vdkNXZW4weTdDQS84ZEJKOWdkcDV0eDdOVkE0NWsxZ2RjeEVSMWdZb3VOWDNuMXZHMy9CMUY0Kzkzd1hXOU1xbzZVczU5VFFtcmI5TnFhN3BTUU5TckgwNncxR3h5QkFsa0ZmcUFsYWZrMTZhTXBxNDE2VEpZcEd5NDNXQ1VpQ2NMV2xoaVdnejJzZ09MQVhQOWE1d2VXQUtSQzhKNmprY1VrRGVYblcrSEZTaVBNNis5Qm82a1ZoTFVoTjVyYzRtSFpPWnBGN3B0UHBzUU40WENxTFBzcXBSSC84bzVYcHlDNlpuZVRlRjJFeHRqaHdaVmpYRHdNYkl6VllJYncxeTJQUEd3OGRDN3BjNHNJVlNuSTRvUUFIMHY2NTBnaGZobU1ldldXNGg0UHlsYncvREc0ZmRlVDMrOHowZjhNT1NUdGZpcHgwNS9RdHRIbEF2T0RSeGE1eURDdk96Nm4zZjFCTzBOLzRNYkd5T00yN3FXNHg4bUJWb3J5VVpXZnNtaGZpMC9HZk52QjgreWxUR2JZTlgyN09jRUY1V1p0TnFiV0V5N1Y1R2JtWlVTeHNwY2c3RkJaM2ozLzNMN211dlpYb1ppMWY1ZXJxNHkzbFNIK29GN3FQRm52aWV5TE9Dd3ViY1F5K295b3dqNGNEMGlkUmVjbnArcys1MkQ3K216RjFncFcrZitjSmFzb3hpZ2J4a09sb1M0eWVpS3ZnTTRuV1NwR0VqMTJSUHg1bzgwRW16aVhOOXQ0ekp6VzFodEE1aFhKSmVGeW1wTVl0eUNVQ2V2UldWbXJSWWt0UTdVbkNhNnRML0FWUGkxbmk1WENYSGZMT3VxZks1S0xZeGp3VnRkaGhmbUNMdnBhS1ZOQ0VPQ2Y0bk5HSHFEOTh3VWIwZWpXTndEWUJuSkdrQlJ3OVJWc3Bmd05kb1dvVmNuMnF2OHl3R1VwN3ljL3NrMkxwSTZWemlSeXZXcWJHTkcxWkpxVlZ1dFJjNDYrc09FNFZTZVMyL0NUTktOYTZOTUNmL2h4eGFVVnNZZktkUCtTMUxjNGlhbktwMHNVdWdQcG10b3lkQzBDUDJSd2puSExjbnp4Q252cXhsTFFXWE1OUFRzdTJ5QmNIbFdKTHRjbWRnL01jTGFneTdsNWtHNnNON1p4SkxEL2tBeDhFNnVxb2hQK0svak1Tcll1UUpuaHI0dGY0YmlXRlkzSnpmL0twQVl5VlNxK3BiZkZLWE1iTDluSEVvWlFUMTVXeWFiZDZETUFxM1FaT3RoTTVwVXpkTnFVWGtjckkxUHdqQVNBZzRkVlUvMm8rOThtVFhueWhQN1ZsRWtUbmRkcHd5SkYrWUNDYzAxcHFhNlpYOTlwblIrWU9wSXJiNUR0UGNLcTB0NWNGQ0R5UXhOMWxVdXFaY1l1anZYL0dDNys2SXBSVHovTmtFWS81Y250T2ZaSnlkNlNrVXgvSlI1QUpJUlBDTmVpYjByY1dubkZuMFhLOHMyMng0MHdMakV0dWZYRE85K3lyYWY0a0h4bEJJM1NCMG1lTWplcFg1MENKaEF4N05la2tSRm53b2VjTGZxSXlyalhyZ0Fac1RNUGlYOTRzbmpkcnppc0FYdEJLYW51bGlsU3hPZlcySFNtZm5rMEwyR1hISkozUyt2Q2JnUkVtbDlkZWtmbUhobXdFWXR2M2tmaHRoN0VSSXdWVDhqNjlPdElCQ21lVElKdUE3bzczUFhjMUxKMndodVpLN0ZaZTZOVE9zNjFNUDdKVmxJYzZ0Ymh0T0JrM05YVThwQlBPQ1k2UTU1ZDYzRnRwVVUvS0NiUTBLMldROW81ak5Hd05OSjZDdzVGREN0K3g1WUplUDFkMlF6RFNpcStjU1pxd3FDWlZjTm9BZnRHR3pnclJaNHZrcGJQMHhRWkhDdFdzVXdIVlRqclk0TmZSRGpIZFZQUm44SjlYdG9vYy9oSVdrcXpGYWN6WVRsYXB1MlJDSnFlOGFFbzNqeldaQ0VKN0FpQnpCWXJhWURnT2ZlaVF5ZUpVc2JiWEhkR0tpaXcyMkJkcDRNK1l6NjcxTVowaWU5RVdSa3MwUTJESEdVVG5lOVM0dEFBSlBHYlVmNHh0Q01vSjQwUTRRVzA1UUxTWnkzd05GQVVGWW1YRTRFQ0RGQjgrSUVlTkZGRi90Z0FuZmg4R3ZGaC8xeFkrTEUrb3pNbWlualNSd2hxMDl6UUFFa05GeXUwSUtndkRreU9JK2ljY0Y3ZG9XTFRVYXNQeExIMXhHUEJTS2tlV0NuU29YLzRDMmM5ZHU2NkJiUlhhbUhxYWUrVkNpUzZCTjk1M2lZS091OHJNa25lVytURmpWMEN6QWY4UE5HOUxCYXlVZ1k1VXc5eDBTYXA2ekk0UHBhWktINGQ5a3RrRlUrOTF5QmJONVNSdGRkOC9FUWF0SlhtQk5mdzdrUnJsbCtMandad2VXTEViMGpUMVJwR3VEcUhMZExUTU1nb3dTY3pycDJ6Q3NKZFFIL3NlYVlycHdrQ0ZSOGRSak03SlJVa1ZhMUEwU3ZkWkFYNzV2dUJ2dkxCek4yYytSYnQ1b3F5OTNscUlCSWpLYjd3MlVrUlRiNHBCV2NOS05QVWd0M2F6L1B4UXhFYXNhbHRkbXV5dnNYWWJ1cjNWUE5uOEp6Ti82SjVOK1FDbno1NzFUY2NhcENta1B2RkUrZ2F5WFUrVUYxVktZeUZjVXZsZXY3bHNRbG1qcXpLMlFBOFg3UTNUekZhcHFodkpLbHQ3ZHpCSHJhcVpCZ1BnYjlONG9LTmF5aThGWlQ3MStrYVloSWhGckVTS1lSSGZIa2o1bjNrZmhnTHkreCtqTERiS3hNZ2drZ0huSno5UnVFSFpYQld0a1lBUT09IiwidGhpbmtpbmciOiIiLCJ0eXBlIjoidGhpbmtpbmcifSx7ImlkIjoidG9vbHVfMDFINmZWOEp2UkpOdlh5NDdlUm5kM2pIIiwiY2FsbGVyIjp7InR5cGUiOiJkaXJlY3QifSwiaW5wdXQiOnt9LCJuYW1lIjoidHJhbnNmZXJfdG9fdmVyaWZpZXIiLCJ0eXBlIjoidG9vbF91c2UiLCJ0b29sc2V0X25hbWUiOm51bGx9XSwicmVzcG9uc2VfbWV0YWRhdGEiOnsiaWQiOiJtc2dfMDExQ2Zkd0FNUmRTMjFGZUpmelFoTTNzIiwiY29udGFpbmVyIjpudWxsLCJkaWFnbm9zdGljcyI6bnVsbCwibW9kZWwiOiJjbGF1ZGUtc29ubmV0Iiwic3RvcF9kZXRhaWxzIjpudWxsLCJzdG9wX3JlYXNvbiI6InRvb2xfdXNlIiwic3RvcF9zZXF1ZW5jZSI6bnVsbCwidXNhZ2UiOnsiY2FjaGVfY3JlYXRpb24iOnsiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MH0sImNhY2hlX2NyZWF0aW9uX2lucHV0X3Rva2VucyI6MCwiY2FjaGVfcmVhZF9pbnB1dF90b2tlbnMiOjAsImluZmVyZW5jZV9nZW8iOiJnbG9iYWwiLCJpbnB1dF90b2tlbnMiOjczOTYsIm91dHB1dF90b2tlbnMiOjc3MCwib3V0cHV0X3Rva2Vuc19kZXRhaWxzIjp7InRoaW5raW5nX3Rva2VucyI6NzM5fSwic2VydmVyX3Rvb2xfdXNlIjpudWxsLCJzZXJ2aWNlX3RpZXIiOiJzdGFuZGFyZCJ9LCJtb2RlbF9uYW1lIjoiY2xhdWRlLXNvbm5ldCIsIm1vZGVsX3Byb3ZpZGVyIjoiYW50aHJvcGljIn0sInR5cGUiOiJhaSIsIm5hbWUiOiJza2VwdGljIiwiaWQiOiJsY19ydW4tLTAxYTBmZTAzLTRhZTktNzZjMC04OWE2LTRmMGIxMTRlMzAzMC0wIiwidG9vbF9jYWxscyI6W3sibmFtZSI6InRyYW5zZmVyX3RvX3ZlcmlmaWVyIiwiYXJncyI6e30sImlkIjoidG9vbHVfMDFINmZWOEp2UkpOdlh5NDdlUm5kM2pIIiwidHlwZSI6InRvb2xfY2FsbCJ9XSwidXNhZ2VfbWV0YWRhdGEiOnsiaW5wdXRfdG9rZW5zIjo3Mzk2LCJvdXRwdXRfdG9rZW5zIjo3NzAsInRvdGFsX3Rva2VucyI6ODE2NiwiaW5wdXRfdG9rZW5fZGV0YWlscyI6eyJjYWNoZV9yZWFkIjowLCJjYWNoZV9jcmVhdGlvbiI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MH0sIm91dHB1dF90b2tlbl9kZXRhaWxzIjp7InJlYXNvbmluZyI6NzM5fX0sImludmFsaWRfdG9vbF9jYWxscyI6W119fSx7ImxjIjoxLCJ0eXBlIjoiY29uc3RydWN0b3IiLCJpZCI6WyJsYW5nY2hhaW4iLCJzY2hlbWEiLCJtZXNzYWdlcyIsIlRvb2xNZXNzYWdlIl0sImt3YXJncyI6eyJjb250ZW50IjoiU3VjY2Vzc2Z1bGx5IHRyYW5zZmVycmVkIHRvIHZlcmlmaWVyIiwidHlwZSI6InRvb2wiLCJuYW1lIjoidHJhbnNmZXJfdG9fdmVyaWZpZXIiLCJpZCI6ImMwNjQ1NjNhLTk3NGYtNGYwZi1hYjRhLTA4MGU2M2MwMWNmNSIsInRvb2xfY2FsbF9pZCI6InRvb2x1XzAxSDZmVjhKdlJKTnZYeTQ3ZVJuZDNqSCIsInN0YXR1cyI6InN1Y2Nlc3MifX0seyJsYyI6MSwidHlwZSI6ImNvbnN0cnVjdG9yIiwiaWQiOlsibGFuZ2NoYWluIiwic2NoZW1hIiwibWVzc2FnZXMiLCJBSU1lc3NhZ2UiXSwia3dhcmdzIjp7ImNvbnRlbnQiOlt7InNpZ25hdHVyZSI6IkNBUVM5Z1VLRUFnU0dBSTRBVUlJZEdocGJtdHBibWNTREdGeUoxTVhvWStBaTZOa2J4b01SZDJUclVmVVU3V3JQcEEySWpEZ3k4ZFVwbGNaS2M3RG5Kd05MVEJmSDVVTlIrbkduYWtTUFFpYThVVkl6cmprT25KMmZMcldVc0Eyb0VPOHlSc3Frd1hra0RDc3loQjk3ZHdqNTdSTXQ5MVh6Z1doTDlsdU5FR085MnlXMHJORkdvTVNVVk94UElyRmM1Ump5cmhLRWMzKzFSbnB4Q2t5bHErTE5sUTVORnhMbjZ2MmNGNUR6cXB2QkhOUjdYQWlnK3VySklVM2dYeWRDa2FHWlpEZXRKdFFPVU9YZ1ppOXo5MTAwTnBkQUVrWERvMklDSENHVEdwVmMwSi9wYlh4V1JCeGI2QjEvR2wwWWpuNjhWNkhsZXNIN0lvQzdHUi8zSHdSdTlOU0RCRzR0dGZRakVXY2crUGVBZWE0Um43anp4K1RtOUg3TDFqb1RLVmdEYlFnNWlLTUxmanZQcWxua3NDTHRYT3Q4alNJUzVPWUxON2EvN1RYNi93NWQzNHZudzh2UERtVTFVWWkwUTcycVVXaFVhMnZ3OE9YTnBjS0w3QnAwbE5mQlM4cnZIWSt2Qlk4L2hhQW9UTDN3dkxGVTFmVCs0ei92QTNCY3NpZ1pEWWxmSmVEWWN4WG1SdXF4enhFR3BYQ1JlOXMxSFd0SUQrNDFwSHU2bHBaSGtYYWdocGM2VFpITHhOd2NWaFRiNmZNUTdRbysyTDZQdmtsaDFtMzJwZW9keGVnMllpUGhkcGwzdy94a09FdTUvSkVGN1pCeHBkVUwrdTN3a081cFVsc3FmZ1g3dWh6djdIQzJXcFNXVmltcndpUXdRT1V4MCtKUHJMdHcrbFlmcTdJM2pydW8wR1cwZ3VXdm51ZjdKTTNZTGo4NHErSmdIb21uU1Nabm5abXJMMFVhUnZyVnlMbzg3N0YzOWNjTFM3WG9abm51aThKNFA1OFpUbWlMa0VKZUdjeDFJdWFnMmUzMzMzOU83WWV3LzU5dExiUXRJR2g5VldNd0hCbkZ4MzlTOC80TEVGcks1SGxkUFFoT3Jsb3lUdGtSczY2aVFSS3R4TUtTMFZJNlFUS1pEQWJzN2E3SDF5QnYrbUppOVhnNHVLbXlVNnFubjd6RUtqalkyYklsQ3dleng0TExHUDVIRDNacjZmWnNtZEcxVUh6RHNCdllHMm9DSTBvcUVLTSt2YWxzVDZoVThNUmpiUUJEL0pKOEpKTi9pQkdsaEJBVUhvMFVtaGh0UjJldVRWcFpXbE1uaG1wWEFkS0RYU2ZQZGFQb2hnQiIsInRoaW5raW5nIjoiIiwidHlwZSI6InRoaW5raW5nIn0seyJpZCI6InRvb2x1XzAxWEVBdWhRSENCZHlDd3R5bVp3RmZEaSIsImNhbGxlciI6eyJ0eXBlIjoiZGlyZWN0In0sImlucHV0Ijp7fSwibmFtZSI6InRyYW5zZmVyX3RvX3JlZF90ZWFtIiwidHlwZSI6InRvb2xfdXNlIiwidG9vbHNldF9uYW1lIjpudWxsfV0sInJlc3BvbnNlX21ldGFkYXRhIjp7ImlkIjoibXNnXzAxMUNmZHdBc2FiRHF1ZWdIaTZZVXBDbiIsImNvbnRhaW5lciI6bnVsbCwiZGlhZ25vc3RpY3MiOm51bGwsIm1vZGVsIjoiY2xhdWRlLXNvbm5ldCIsInN0b3BfZGV0YWlscyI6bnVsbCwic3RvcF9yZWFzb24iOiJ0b29sX3VzZSIsInN0b3Bfc2VxdWVuY2UiOm51bGwsInVzYWdlIjp7ImNhY2hlX2NyZWF0aW9uIjp7ImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjB9LCJjYWNoZV9jcmVhdGlvbl9pbnB1dF90b2tlbnMiOjAsImNhY2hlX3JlYWRfaW5wdXRfdG9rZW5zIjowLCJpbmZlcmVuY2VfZ2VvIjoiZ2xvYmFsIiwiaW5wdXRfdG9rZW5zIjo3NTA5LCJvdXRwdXRfdG9rZW5zIjo4OCwib3V0cHV0X3Rva2Vuc19kZXRhaWxzIjp7InRoaW5raW5nX3Rva2VucyI6NTV9LCJzZXJ2ZXJfdG9vbF91c2UiOm51bGwsInNlcnZpY2VfdGllciI6InN0YW5kYXJkIn0sIm1vZGVsX25hbWUiOiJjbGF1ZGUtc29ubmV0IiwibW9kZWxfcHJvdmlkZXIiOiJhbnRocm9waWMifSwidHlwZSI6ImFpIiwibmFtZSI6InZlcmlmaWVyIiwiaWQiOiJsY19ydW4tLTAxYTBmZTAzLTY2ODItN2QyMS04YzE1LWZmYmNlOTQyMmM5Zi0wIiwidG9vbF9jYWxscyI6W3sibmFtZSI6InRyYW5zZmVyX3RvX3JlZF90ZWFtIiwiYXJncyI6e30sImlkIjoidG9vbHVfMDFYRUF1aFFIQ0JkeUN3dHltWndGZkRpIiwidHlwZSI6InRvb2xfY2FsbCJ9XSwidXNhZ2VfbWV0YWRhdGEiOnsiaW5wdXRfdG9rZW5zIjo3NTA5LCJvdXRwdXRfdG9rZW5zIjo4OCwidG90YWxfdG9rZW5zIjo3NTk3LCJpbnB1dF90b2tlbl9kZXRhaWxzIjp7ImNhY2hlX3JlYWQiOjAsImNhY2hlX2NyZWF0aW9uIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowfSwib3V0cHV0X3Rva2VuX2RldGFpbHMiOnsicmVhc29uaW5nIjo1NX19LCJpbnZhbGlkX3Rvb2xfY2FsbHMiOltdfX0seyJsYyI6MSwidHlwZSI6ImNvbnN0cnVjdG9yIiwiaWQiOlsibGFuZ2NoYWluIiwic2NoZW1hIiwibWVzc2FnZXMiLCJUb29sTWVzc2FnZSJdLCJrd2FyZ3MiOnsiY29udGVudCI6IlN1Y2Nlc3NmdWxseSB0cmFuc2ZlcnJlZCB0byByZWRfdGVhbSIsInR5cGUiOiJ0b29sIiwibmFtZSI6InRyYW5zZmVyX3RvX3JlZF90ZWFtIiwiaWQiOiI5ODJjMDEyNi1lNmFiLTQ1OGEtOTIyZS03YjI2NmU4M2MyYjIiLCJ0b29sX2NhbGxfaWQiOiJ0b29sdV8wMVhFQXVoUUhDQmR5Q3d0eW1ad0ZmRGkiLCJzdGF0dXMiOiJzdWNjZXNzIn19LHsibGMiOjEsInR5cGUiOiJjb25zdHJ1Y3RvciIsImlkIjpbImxhbmdjaGFpbiIsInNjaGVtYSIsIm1lc3NhZ2VzIiwiQUlNZXNzYWdlIl0sImt3YXJncyI6eyJjb250ZW50IjpbeyJzaWduYXR1cmUiOiJDQVFTd2djS0VBZ1NHQUk0QVVJSWRHaHBibXRwYm1jU0RPUlhnZTl1TDE4MzJSTVF3Qm9NalF3QXdBSGI5aVAxb2pQR0lqRERTY2FsNDg2YmVDSmJ0RzgvRDJZOWc5UzV4SVBmam9IZy9keHdYNUh5cFNRRUJiakZpVFNiUEVDWFNGelY2WUlxM3diTGNteVBidnVzR25EZXhGZ3grM3NJWHp2cXlGVi82OXhoaWhNblNwZlRDSHkwKzB6U3UxV3BZVS9XVXBJZm9hU1hUY1RhMXFrTTh4OEVrL3kvMWprS01aVWZERmE5M3VoVUp4T0M0K1FnUFdCbC8rWHkydDgyTDJ4L2VicTdRTFFUcXRSMGpYZWFVUlFtM0NvNkp2T2dXbUR2TXBFZFRlVFdFM2ZEaDF0enpWS3NmbHVtNGQ4OWI2Q2FLdG44bmxRZDdSaE45OXZOUU1RSEc1VjRPdVZOZHJIUFpacEZPdWhkZWpzTUZXWHlCKzU1c2xHQWQ4d0VYZ0ZLYkkva25PWFZHekwvTkRGOEd0eTF0TlpsdTJmZFNDQXNZV01zRlFQMWNid0xlUUdzenlYekpNVlpKMkk5eEJQa3l6MUhPWENQeWg1RitqMmdSVFBpa1ZCM0FSQzZ0ZkIvbERTVWVLQlZaUFFTOHBZL0I0ZUNzK0lqamFCTldydUx6ZnFDc2M2eEwwQ3VRUFNZeVFYYVlGallyU1JOY0M3MFdRQldUNVZWaHAwbUE5eVpER1liUlp0OUk1T0s5UWtRbXVKNXpERmFNRU9YelNyc0M0bHRlUDZNZGltaU1panZzSDNpcStjNldVWW9sUmozbmVJODhFYUhJekxBR1JxNjRCTkNMemRBWUwycEVVMnNiNXVHNzhQS1ZvVVVDYlZKTDVqcERPaExPVE8xYlFzVHVvVXBuUlJyTFFEL2tJelYrbGpwVkJ3d2ZKY3lxNzVUSkEvQ3RQci94cjJTWjlCMWIyc2JqRzZqRDBsaHRvQ2RkZURnY3FnbC9MU1NrY3VhWVk4eFBXQ3krTHROaGNxVGhmbWZ2bkhMSklwTDZnamJqVy9PUXBSZlZVd2Z3MWpPYjliV1Z3Y2dIaE5ZZktZR1B0TThvdGg1eHdMWVJSVmd6cU1LT3ZzN2ZhbFhSaFZ6WjJTUDZJdzBCTW1BQVo2SGpmQ2w5TCt0UHFKTmxuUVFPSHBvV2p1bTRCK1hzWWxkRkVLR1FXUXFzZDU5aU5QdmFvOXAvc0NPdDdyR3FDb3pjbWdpRW00dzY2ZXovUUlEeWI0Nm4wK3RjTkpQVWNvQkt2US9qRHdFNlZ3bWtRL25FQ2pGcDNVZERUK2tXWVFTTmQ4ajhWQlpPcEc4TGxxVVlyRVpDdjBxN0JzMXZjTnJkWWlhRm9TMzJvc2F5bldrK0h0M09IdUZXYkVGOEpsc0ZUUUFPMDVWdllrZWNmMFYvb1RIc0c1aHlPT3M3VUVhREZxN3VhSnV6V1ZoaDVwQW9qSWFCY1I4ZlZsbjJQTFJUWDdpczJuc0ErUXJkaWRlUGNadEZ0Z3hBaUtZZTFpMnNTRmk0dm04RU9rQ2JRNjN3ZFFlWTRVcnI1UHVvTUV3eFVVTGpnS2FnaUFtc0pEcTRSclZtN3NPNCs2WXVBOWo2bDJ1eWxrT0VjNjd2Zi81ZmtYdUNzaUFwTkw2a2ViOGMrdkwwbjRGWEdkemorYXBTRGZGR0JnQiIsInRoaW5raW5nIjoiIiwidHlwZSI6InRoaW5raW5nIn0seyJpZCI6InRvb2x1XzAxVkJyV2RXRVdZZ2l0NGtOWWVoQk1VNSIsImNhbGxlciI6eyJ0eXBlIjoiZGlyZWN0In0sImlucHV0Ijp7fSwibmFtZSI6InRyYW5zZmVyX3RvX2VkaXRvciIsInR5cGUiOiJ0b29sX3VzZSIsInRvb2xzZXRfbmFtZSI6bnVsbH1dLCJyZXNwb25zZV9tZXRhZGF0YSI6eyJpZCI6Im1zZ18wMTFDZmR3QXpmanFVb3BvRW1aTGFxbTEiLCJjb250YWluZXIiOm51bGwsImRpYWdub3N0aWNzIjpudWxsLCJtb2RlbCI6ImNsYXVkZS1zb25uZXQiLCJzdG9wX2RldGFpbHMiOm51bGwsInN0b3BfcmVhc29uIjoidG9vbF91c2UiLCJzdG9wX3NlcXVlbmNlIjpudWxsLCJ1c2FnZSI6eyJjYWNoZV9jcmVhdGlvbiI6eyJlcGhlbWVyYWxfMWhfaW5wdXRfdG9rZW5zIjowLCJlcGhlbWVyYWxfNW1faW5wdXRfdG9rZW5zIjowfSwiY2FjaGVfY3JlYXRpb25faW5wdXRfdG9rZW5zIjowLCJjYWNoZV9yZWFkX2lucHV0X3Rva2VucyI6MCwiaW5mZXJlbmNlX2dlbyI6Imdsb2JhbCIsImlucHV0X3Rva2VucyI6NzQxNiwib3V0cHV0X3Rva2VucyI6MTUxLCJvdXRwdXRfdG9rZW5zX2RldGFpbHMiOnsidGhpbmtpbmdfdG9rZW5zIjoxMTl9LCJzZXJ2ZXJfdG9vbF91c2UiOm51bGwsInNlcnZpY2VfdGllciI6InN0YW5kYXJkIn0sIm1vZGVsX25hbWUiOiJjbGF1ZGUtc29ubmV0IiwibW9kZWxfcHJvdmlkZXIiOiJhbnRocm9waWMifSwidHlwZSI6ImFpIiwibmFtZSI6InJlZF90ZWFtIiwiaWQiOiJsY19ydW4tLTAxYTBmZTAzLTZjZTYtNzI1MS1iNzk2LTRmNjQzMzNmNjdjNi0wIiwidG9vbF9jYWxscyI6W3sibmFtZSI6InRyYW5zZmVyX3RvX2VkaXRvciIsImFyZ3MiOnt9LCJpZCI6InRvb2x1XzAxVkJyV2RXRVdZZ2l0NGtOWWVoQk1VNSIsInR5cGUiOiJ0b29sX2NhbGwifV0sInVzYWdlX21ldGFkYXRhIjp7ImlucHV0X3Rva2VucyI6NzQxNiwib3V0cHV0X3Rva2VucyI6MTUxLCJ0b3RhbF90b2tlbnMiOjc1NjcsImlucHV0X3Rva2VuX2RldGFpbHMiOnsiY2FjaGVfcmVhZCI6MCwiY2FjaGVfY3JlYXRpb24iOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjB9LCJvdXRwdXRfdG9rZW5fZGV0YWlscyI6eyJyZWFzb25pbmciOjExOX19LCJpbnZhbGlkX3Rvb2xfY2FsbHMiOltdfX0seyJsYyI6MSwidHlwZSI6ImNvbnN0cnVjdG9yIiwiaWQiOlsibGFuZ2NoYWluIiwic2NoZW1hIiwibWVzc2FnZXMiLCJUb29sTWVzc2FnZSJdLCJrd2FyZ3MiOnsiY29udGVudCI6IlN1Y2Nlc3NmdWxseSB0cmFuc2ZlcnJlZCB0byBlZGl0b3IiLCJ0eXBlIjoidG9vbCIsIm5hbWUiOiJ0cmFuc2Zlcl90b19lZGl0b3IiLCJpZCI6IjVkMzllMzZiLWM1YjUtNDQyNi1hOWFhLWJlMmY3ZDM4MTZkNiIsInRvb2xfY2FsbF9pZCI6InRvb2x1XzAxVkJyV2RXRVdZZ2l0NGtOWWVoQk1VNSIsInN0YXR1cyI6InN1Y2Nlc3MifX0seyJsYyI6MSwidHlwZSI6ImNvbnN0cnVjdG9yIiwiaWQiOlsibGFuZ2NoYWluIiwic2NoZW1hIiwibWVzc2FnZXMiLCJBSU1lc3NhZ2UiXSwia3dhcmdzIjp7ImNvbnRlbnQiOlt7InNpZ25hdHVyZSI6IkNBUVM1Z1lLRUFnU0dBSTRBVUlJZEdocGJtdHBibWNTREk0UUliN0wydzVhVzNjTS9Sb01MaTJ3RXhEa3FodXhKRGlZSWpBcUd4TTRXVXdpcTR1WkhyaUNidUM0a1Z3YTdpZ2RVTG9vY1piaTVmZXZLYmZ3cUhTYnJMTlQ1MU5HWDRYc0x0c3Fnd1kvdGFiSGpsbHpxdTduUld2OCtGejRSNm45amE3Q3BqMjRadXhGdUtra1FPQm1BNFRmMWFwazNSUHFjRVErait3ZWR1MGxPK3JkRUN5ZDNsWGhmZ0VSRkZxY002YXVjeGVsNFJidzVvQUhYdTkrWGVUdHpsK044dEFlWjlpR1oyWFR0VTVPYjhhUFQxS3VYK3VwOGtRNFZVWGtCVGZkMmY1SlA5UnhaRXE5d1NZYVpzeUhkdjBuKzFVNDZBT3N2S1ptcDlRWEJ3bzJmNE85MGpQOGVnaXJlbTlFYlpibWFZT0o4V0s3Q3RLUlZiWTJ5NCs5eFJVSjA0bnNkSXo1RjVGRktFeHhOT3JCNG1jL05FODNhYjNaNjRpV3pPd3FvVUdBR1FTa2FIMGQ1Y0V1bVpvNGZaWkFoUHl1SmVRRHh1bE1DZXduN0VHQ25wSncvbnppMHdveUVhUUw0WTdoOTlQN2FYeEZyMjhwNUtDeUpFSlREZWZlSXBWbEF3TUNBanoreEM2OUFBTG13eVRRK2NGRU0rS0FnZUlTcGhMVnk4QVByMkZTaGF4Qk5yWFFnejFzOXMyZGhMWlFPQml3emh4bUVnZEs3KzhKYXFoQjBlRUVkLzFSVkF1SVlkZXpBNUhCcndFOUR5UWlDbDNVT3NiU25ORVZlK2dySHA1cDN0bU1CcTY4Z0xWODJvQXpGWVpsK0Nld3g3MXY1ZFBGT3ZLUEVIVXpwUVlPVkxybkIxRVpSWXJaejcybjJ3ZlNWeEJPenBUY25CeFY2SGVkQ1B5SXpLWFpNOSt5RWVUSmk4UXR2VmdaMXcrdjBobUNGR3BubVpON21YbGdxTDFzNk1YVnlkcFBPS1BsTTNOYTdDZEhuUEZZaXdyMnpMdmtrY0lNN0Nzay9DMytaTUFXVEsrQzlCMXZiR3hQbHRFM092OGtPOThQZ1NYbTFBSnVFYlh5K3IzYTNEM1FsWkozZEVLZTJMTmRBQnlyUE1oU2NLVThHbGZILzlOdGdyaHRha2dsbEQvTWZBbFRzYk53TkRyVXRXUnhtRHVKLzBaK2hray9ZTndFRFlBWmE4VG13Vm9XT2RCSHBSUEh2WjlFOXVzZXVsdG1hK0prMWdSTER0dkVaa3FYVUVTa01jcVV0VndZTTVhakpBNU41MmNOaVoxNUJUZjhYakdoS1dkT1Y0MCs4SDBQT1N4TTJKaWZ3Q08wQzV4Rlc1Qm8zSWlJTnYwVU90WTVmOGt2UGRNM1Bqa2hhT3JLMXlUQThlRUU0NHZ1bkw5UGtvR2VjYlltK1hFNUt6TDNRc0VuMlkxSUp3Tzl3MHhIWFFaRWVpUDUrMHUzWW5EYzhxOWRCTGhHVzNGeTMwZ1lBUT09IiwidGhpbmtpbmciOiIiLCJ0eXBlIjoidGhpbmtpbmcifSx7ImlkIjoidG9vbHVfMDFCbThBVTlFc1FVd3FvVkxZcHhLQTc3IiwiY2FsbGVyIjp7InR5cGUiOiJkaXJlY3QifSwiaW5wdXQiOnsiZmlsZV9wYXRoIjoiL2Fuc3dlci5tZCIsImNvbnRlbnQiOiIqKlR1cGxlIHZzLiBsaXN0IGltbXV0YWJpbGl0eSAoUHl0aG9uKSoqXG5cbkEgdHVwbGUgaXMgaW1tdXRhYmxlOiBvbmNlIGNyZWF0ZWQsIHlvdSBjYW4ndCBhc3NpZ24gdG8gaXRzIGl0ZW1zLCBhbmQgdGhlIGNvbGxlY3Rpb24gb2Ygb2JqZWN0cyBpdCByZWZlcmVuY2VzIGNhbid0IGNoYW5nZS4gYHRbMF0gPSAxYCByYWlzZXMgYFR5cGVFcnJvcmAuIEEgbGlzdCBpcyBtdXRhYmxlOiB5b3UgY2FuIGNoYW5nZSBpdCBpbiBwbGFjZSB3aXRoIGluZGV4IG9yIHNsaWNlIGFzc2lnbm1lbnQsIGBhcHBlbmQoKWAsIGBleHRlbmQoKWAsIGBzb3J0KClgIGFuZCBzaW1pbGFyIG1ldGhvZHMuXG5cblR1cGxlIGltbXV0YWJpbGl0eSBpcyBzaGFsbG93LiBJZiBhIHR1cGxlIGhvbGRzIGEgbXV0YWJsZSBvYmplY3QsIHN1Y2ggYXMgYSBsaXN0LCB0aGF0IGlubmVyIG9iamVjdCBjYW4gc3RpbGwgY2hhbmdlLCBhbmQgc28gdGhlIHR1cGxlJ3MgdmFsdWUgY2hhbmdlcy4gQmVjYXVzZSBvZiB0aGlzLCBhIHR1cGxlIGNhbiBiZSBhIGBkaWN0YCBrZXkgb3IgYHNldGAgbWVtYmVyIG9ubHkgaWYgZXZlcnl0aGluZyBpbnNpZGUgaXQgaXMgaGFzaGFibGUuIEEgbGlzdCBjYW4gbmV2ZXIgYmUgYSBrZXkuXG5cblNvdXJjZXM6XG4tIGh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvdHV0b3JpYWwvZGF0YXN0cnVjdHVyZXMuaHRtbFxuLSBodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL3JlZmVyZW5jZS9kYXRhbW9kZWwuaHRtbFxuLSBodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL2xpYnJhcnkvc3RkdHlwZXMuaHRtbFxuIn0sIm5hbWUiOiJ3cml0ZV9maWxlIiwidHlwZSI6InRvb2xfdXNlIiwidG9vbHNldF9uYW1lIjpudWxsfV0sInJlc3BvbnNlX21ldGFkYXRhIjp7ImlkIjoibXNnXzAxMUNmZHdCQmFhOWdqTUNjZTE2VFVlbiIsImNvbnRhaW5lciI6bnVsbCwiZGlhZ25vc3RpY3MiOm51bGwsIm1vZGVsIjoiY2xhdWRlLXNvbm5ldCIsInN0b3BfZGV0YWlscyI6bnVsbCwic3RvcF9yZWFzb24iOiJ0b29sX3VzZSIsInN0b3Bfc2VxdWVuY2UiOm51bGwsInVzYWdlIjp7ImNhY2hlX2NyZWF0aW9uIjp7ImVwaGVtZXJhbF8xaF9pbnB1dF90b2tlbnMiOjAsImVwaGVtZXJhbF81bV9pbnB1dF90b2tlbnMiOjB9LCJjYWNoZV9jcmVhdGlvbl9pbnB1dF90b2tlbnMiOjAsImNhY2hlX3JlYWRfaW5wdXRfdG9rZW5zIjowLCJpbmZlcmVuY2VfZ2VvIjoiZ2xvYmFsIiwiaW5wdXRfdG9rZW5zIjo4MTI3LCJvdXRwdXRfdG9rZW5zIjo0MzMsIm91dHB1dF90b2tlbnNfZGV0YWlscyI6eyJ0aGlua2luZ190b2tlbnMiOjc5fSwic2VydmVyX3Rvb2xfdXNlIjpudWxsLCJzZXJ2aWNlX3RpZXIiOiJzdGFuZGFyZCJ9LCJtb2RlbF9uYW1lIjoiY2xhdWRlLXNvbm5ldCIsIm1vZGVsX3Byb3ZpZGVyIjoiYW50aHJvcGljIn0sInR5cGUiOiJhaSIsIm5hbWUiOiJlZGl0b3IiLCJpZCI6ImxjX3J1bi0tMDFhMGZlMDMtNzZlOS03Y2EzLWE1ZmYtNjNkZTY2ZGQ4ZGQxLTAiLCJ0b29sX2NhbGxzIjpbeyJuYW1lIjoid3JpdGVfZmlsZSIsImFyZ3MiOnsiZmlsZV9wYXRoIjoiL2Fuc3dlci5tZCIsImNvbnRlbnQiOiIqKlR1cGxlIHZzLiBsaXN0IGltbXV0YWJpbGl0eSAoUHl0aG9uKSoqXG5cbkEgdHVwbGUgaXMgaW1tdXRhYmxlOiBvbmNlIGNyZWF0ZWQsIHlvdSBjYW4ndCBhc3NpZ24gdG8gaXRzIGl0ZW1zLCBhbmQgdGhlIGNvbGxlY3Rpb24gb2Ygb2JqZWN0cyBpdCByZWZlcmVuY2VzIGNhbid0IGNoYW5nZS4gYHRbMF0gPSAxYCByYWlzZXMgYFR5cGVFcnJvcmAuIEEgbGlzdCBpcyBtdXRhYmxlOiB5b3UgY2FuIGNoYW5nZSBpdCBpbiBwbGFjZSB3aXRoIGluZGV4IG9yIHNsaWNlIGFzc2lnbm1lbnQsIGBhcHBlbmQoKWAsIGBleHRlbmQoKWAsIGBzb3J0KClgIGFuZCBzaW1pbGFyIG1ldGhvZHMuXG5cblR1cGxlIGltbXV0YWJpbGl0eSBpcyBzaGFsbG93LiBJZiBhIHR1cGxlIGhvbGRzIGEgbXV0YWJsZSBvYmplY3QsIHN1Y2ggYXMgYSBsaXN0LCB0aGF0IGlubmVyIG9iamVjdCBjYW4gc3RpbGwgY2hhbmdlLCBhbmQgc28gdGhlIHR1cGxlJ3MgdmFsdWUgY2hhbmdlcy4gQmVjYXVzZSBvZiB0aGlzLCBhIHR1cGxlIGNhbiBiZSBhIGBkaWN0YCBrZXkgb3IgYHNldGAgbWVtYmVyIG9ubHkgaWYgZXZlcnl0aGluZyBpbnNpZGUgaXQgaXMgaGFzaGFibGUuIEEgbGlzdCBjYW4gbmV2ZXIgYmUgYSBrZXkuXG5cblNvdXJjZXM6XG4tIGh0dHBzOi8vZG9jcy5weXRob24ub3JnLzMvdHV0b3JpYWwvZGF0YXN0cnVjdHVyZXMuaHRtbFxuLSBodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL3JlZmVyZW5jZS9kYXRhbW9kZWwuaHRtbFxuLSBodHRwczovL2RvY3MucHl0aG9uLm9yZy8zL2xpYnJhcnkvc3RkdHlwZXMuaHRtbFxuIn0sImlkIjoidG9vbHVfMDFCbThBVTlFc1FVd3FvVkxZcHhLQTc3IiwidHlwZSI6InRvb2xfY2FsbCJ9XSwidXNhZ2VfbWV0YWRhdGEiOnsiaW5wdXRfdG9rZW5zIjo4MTI3LCJvdXRwdXRfdG9rZW5zIjo0MzMsInRvdGFsX3Rva2VucyI6ODU2MCwiaW5wdXRfdG9rZW5fZGV0YWlscyI6eyJjYWNoZV9yZWFkIjowLCJjYWNoZV9jcmVhdGlvbiI6MCwiZXBoZW1lcmFsXzVtX2lucHV0X3Rva2VucyI6MCwiZXBoZW1lcmFsXzFoX2lucHV0X3Rva2VucyI6MH0sIm91dHB1dF90b2tlbl9kZXRhaWxzIjp7InJlYXNvbmluZyI6Nzl9fSwiaW52YWxpZF90b29sX2NhbGxzIjpbXX19LHsibGMiOjEsInR5cGUiOiJjb25zdHJ1Y3RvciIsImlkIjpbImxhbmdjaGFpbiIsInNjaGVtYSIsIm1lc3NhZ2VzIiwiVG9vbE1lc3NhZ2UiXSwia3dhcmdzIjp7ImNvbnRlbnQiOiJVcGRhdGVkIGZpbGUgL2Fuc3dlci5tZCIsInR5cGUiOiJ0b29sIiwibmFtZSI6IndyaXRlX2ZpbGUiLCJpZCI6ImUzNDkyZTA4LWM4NjktNDdlYy1hNWY3LWNjNTdlYTVmNjQwMyIsInRvb2xfY2FsbF9pZCI6InRvb2x1XzAxQm04QVU5RXNRVXdxb1ZMWXB4S0E3NyIsInN0YXR1cyI6InN1Y2Nlc3MifX1dXX0=" + } + }, + { + "key": "gen_ai.usage.input_tokens", + "value": { + "intValue": "8494" + } + }, + { + "key": "gen_ai.usage.output_tokens", + "value": { + "intValue": "415" + } + }, + { + "key": "gen_ai.usage.total_tokens", + "value": { + "intValue": "8909" + } + }, + { + "key": "gen_ai.completion", + "value": { + "bytesValue": "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" + } + } + ], + "status": { + "code": 1 + }, + "flags": 256 + } + ] + }, + { + "scope": { + "name": "deeplite" + }, + "spans": [ + { + "traceId": "b2952a96b863250c304cef3376fe4c82", + "spanId": "e8da3a18a9815276", + "name": "deeplite.run", + "kind": 1, + "startTimeUnixNano": "1790968013175004000", + "endTimeUnixNano": "1790968042976537000", + "attributes": [ + { + "key": "langsmith.span.kind", + "value": { + "stringValue": "chain" + } + }, + { + "key": "input.value", + "value": { + "stringValue": "For a synthetic tracing fixture, explain Python tuple versus list immutability in at most 120 words. Use only official Python documentation if you search. Have the skeptic and verifier check it, then have the editor write /answer.md. Keep the run short and do not ask follow-up questions." + } + }, + { + "key": "output.value", + "value": { + "stringValue": "I wrote the answer to `/answer.md`. It is about 100 words, under the 120-word limit.\n\nI did not get a skeptic or verifier check. I handed off to both, but neither returned any feedback. I also tried to hand off to a `red_team` agent, and that transfer isn't one of the tools I was given. I then wrote the answer myself from the official Python documentation search results. I didn't open the pages directly.\n\n**Tuple vs. list immutability (Python)**\n\nA tuple is immutable: once created, you can't assign to its items, and the collection of objects it references can't change. `t[0] = 1` raises `TypeError`. A list is mutable: you can change it in place with index or slice assignment, `append()`, `extend()`, `sort()` and similar methods.\n\nTuple immutability is shallow. If a tuple holds a mutable object, such as a list, that inner object can still change, and so the tuple's value changes. Because of this, a tuple can be a `dict` key or `set` member only if everything inside it is hashable. A list can never be a key.\n\nSources:\n- https://docs.python.org/3/tutorial/datastructures.html\n- https://docs.python.org/3/reference/datamodel.html\n- https://docs.python.org/3/library/stdtypes.html" + } + } + ], + "status": {}, + "flags": 256 + } + ] + } + ] + } + ] +} diff --git a/litellm-rust/crates/traces/tests/fixtures/query_alternate.json b/litellm-rust/crates/traces/tests/fixtures/query_alternate.json new file mode 100644 index 00000000000..5445613ea79 --- /dev/null +++ b/litellm-rust/crates/traces/tests/fixtures/query_alternate.json @@ -0,0 +1,39 @@ +{ + "resourceSpans": [ + { + "resource": { + "attributes": [ + { + "key": "service.name", + "value": { + "stringValue": "fixture" + } + } + ] + }, + "scopeSpans": [ + { + "scope": { + "name": "fixture" + }, + "spans": [ + { + "traceId": "01010101010101010101010101010101", + "spanId": "0404040404040404", + "parentSpanId": "", + "name": "alternate", + "kind": 1, + "startTimeUnixNano": "1735689601000000000", + "endTimeUnixNano": "1735689602000000000", + "attributes": [], + "status": { + "code": 1, + "message": "" + } + } + ] + } + ] + } + ] +} diff --git a/litellm-rust/crates/traces/tests/fixtures/query_children.json b/litellm-rust/crates/traces/tests/fixtures/query_children.json new file mode 100644 index 00000000000..66e9d975003 --- /dev/null +++ b/litellm-rust/crates/traces/tests/fixtures/query_children.json @@ -0,0 +1,85 @@ +{ + "resourceSpans": [ + { + "resource": { + "attributes": [ + { + "key": "service.name", + "value": { + "stringValue": "fixture" + } + } + ] + }, + "scopeSpans": [ + { + "scope": { + "name": "fixture" + }, + "spans": [ + { + "traceId": "01010101010101010101010101010101", + "spanId": "0202020202020202", + "parentSpanId": "0101010101010101", + "name": "completion", + "kind": 1, + "startTimeUnixNano": "1735689600100000000", + "endTimeUnixNano": "1735689600600000000", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "chat" + } + }, + { + "key": "gen_ai.response.id", + "value": { + "stringValue": "response-shared" + } + }, + { + "key": "gen_ai.usage.input_tokens", + "value": { + "stringValue": "12" + } + }, + { + "key": "gen_ai.usage.output_tokens", + "value": { + "stringValue": "6" + } + } + ], + "status": { + "code": 1, + "message": "" + } + }, + { + "traceId": "01010101010101010101010101010101", + "spanId": "0303030303030303", + "parentSpanId": "0101010101010101", + "name": "lookup", + "kind": 1, + "startTimeUnixNano": "1735689600700000000", + "endTimeUnixNano": "1735689600800000000", + "attributes": [ + { + "key": "gen_ai.operation.name", + "value": { + "stringValue": "execute_tool" + } + } + ], + "status": { + "code": 2, + "message": "lookup timed out" + } + } + ] + } + ] + } + ] +} diff --git a/litellm-rust/crates/traces/tests/fixtures/query_other_team.json b/litellm-rust/crates/traces/tests/fixtures/query_other_team.json new file mode 100644 index 00000000000..c3dff4b969b --- /dev/null +++ b/litellm-rust/crates/traces/tests/fixtures/query_other_team.json @@ -0,0 +1,46 @@ +{ + "resourceSpans": [ + { + "resource": { + "attributes": [ + { + "key": "service.name", + "value": { + "stringValue": "fixture" + } + } + ] + }, + "scopeSpans": [ + { + "scope": { + "name": "fixture" + }, + "spans": [ + { + "traceId": "01010101010101010101010101010101", + "spanId": "0505050505050505", + "parentSpanId": "", + "name": "other-team", + "kind": 1, + "startTimeUnixNano": "1735689602000000000", + "endTimeUnixNano": "1735689603000000000", + "attributes": [ + { + "key": "gen_ai.response.id", + "value": { + "stringValue": "response-shared" + } + } + ], + "status": { + "code": 1, + "message": "" + } + } + ] + } + ] + } + ] +} diff --git a/litellm-rust/crates/traces/tests/fixtures/query_root.json b/litellm-rust/crates/traces/tests/fixtures/query_root.json new file mode 100644 index 00000000000..83b7b7c77e1 --- /dev/null +++ b/litellm-rust/crates/traces/tests/fixtures/query_root.json @@ -0,0 +1,46 @@ +{ + "resourceSpans": [ + { + "resource": { + "attributes": [ + { + "key": "service.name", + "value": { + "stringValue": "fixture" + } + } + ] + }, + "scopeSpans": [ + { + "scope": { + "name": "fixture" + }, + "spans": [ + { + "traceId": "01010101010101010101010101010101", + "spanId": "0101010101010101", + "parentSpanId": "", + "name": "review", + "kind": 1, + "startTimeUnixNano": "1735689600000000000", + "endTimeUnixNano": "1735689602000000000", + "attributes": [ + { + "key": "gen_ai.input.messages", + "value": { + "stringValue": "Review the change" + } + } + ], + "status": { + "code": 1, + "message": "" + } + } + ] + } + ] + } + ] +} diff --git a/litellm-rust/crates/traces/tests/otlp.rs b/litellm-rust/crates/traces/tests/otlp.rs index 5df13cb1596..e5705354533 100644 --- a/litellm-rust/crates/traces/tests/otlp.rs +++ b/litellm-rust/crates/traces/tests/otlp.rs @@ -1,11 +1,35 @@ use litellm_traces::decode_otlp; use litellm_traces::{ObservationType, Shared}; +use opentelemetry_proto::tonic::trace::v1::Span; use rstest::rstest; const FIXTURE: &[u8] = include_bytes!( "../../../../tests/test_litellm/tracing/fixtures/langsmith_deep_agent_export.json" ); +#[rstest] +#[case::root(include_bytes!("fixtures/query_root.json"), ObservationType::Agent, 0, 0)] +#[case::children(include_bytes!("fixtures/query_children.json"), ObservationType::Llm, 12, 6)] +#[case::alternate(include_bytes!("fixtures/query_alternate.json"), ObservationType::Agent, 0, 0)] +#[case::other_team(include_bytes!("fixtures/query_other_team.json"), ObservationType::Agent, 0, 0)] +fn query_fixtures_decode_and_normalize( + #[case] body: &[u8], + #[case] observation_type: ObservationType, + #[case] input_tokens: u32, + #[case] output_tokens: u32, +) { + let spans = decode_otlp(body, Some("application/json")).unwrap(); + let first = &spans[0]; + assert_eq!(first.normalized.observation_type, observation_type); + assert_eq!(first.normalized.input_tokens, input_tokens); + assert_eq!(first.normalized.output_tokens, output_tokens); + assert!( + spans + .iter() + .all(|span| span.resource_attributes["service.name"] == "fixture") + ); +} + #[rstest] #[case::json(FIXTURE, Some("application/json"))] fn decodes_neutral_spans(#[case] body: &[u8], #[case] content_type: Option<&str>) { @@ -133,7 +157,7 @@ fn rejects_ids_and_timestamps_that_cannot_be_stored( }; assert!(matches!( decode_otlp(&request_with(span).encode_to_vec(), None), - Err(litellm_traces::DecodeError::InvalidPayload) + Err(litellm_traces::Error::InvalidPayload) )); } @@ -216,7 +240,7 @@ fn nested_values_are_serialized_once(span: opentelemetry_proto::tonic::trace::v1 fn rejects_json_structure_before_building_a_tree(#[case] body: Vec) { assert!(matches!( decode_otlp(&body, Some("application/json")), - Err(litellm_traces::DecodeError::TooLarge) + Err(litellm_traces::Error::TooLarge) )); } @@ -252,7 +276,7 @@ fn protobuf_preflight_rejects_expansion_before_prost_allocates( let body = request.encode_to_vec(); assert!(matches!( decode_otlp(&body, None), - Err(litellm_traces::DecodeError::TooLarge) + Err(litellm_traces::Error::TooLarge) )); } @@ -310,7 +334,7 @@ fn unique_attribute_expansion_still_respects_decoded_budget( assert!(body.len() < 16 * 1024 * 1024); assert!(matches!( decode_otlp(&body, None), - Err(litellm_traces::DecodeError::TooLarge) + Err(litellm_traces::Error::TooLarge) )); } @@ -338,7 +362,7 @@ fn escaped_attribute_expansion_is_bounded_below_four_mib( assert!(body.len() < 4 * 1024 * 1024); assert!(matches!( decode_otlp(&body, None), - Err(litellm_traces::DecodeError::TooLarge) + Err(litellm_traces::Error::TooLarge) )); } @@ -387,6 +411,279 @@ fn normalizes_langsmith_fixture() { assert!(tool.normalized.output.starts_with("Based on my research")); } +fn decode_normalization( + span: Span, + scope: &str, + attributes: &[(&str, &str)], +) -> Result { + use opentelemetry_proto::tonic::{ + collector::trace::v1::ExportTraceServiceRequest, + common::v1::{AnyValue, InstrumentationScope, KeyValue, any_value::Value}, + trace::v1::{ResourceSpans, ScopeSpans}, + }; + use prost::Message; + + let request = ExportTraceServiceRequest { + resource_spans: vec![ResourceSpans { + scope_spans: vec![ScopeSpans { + scope: Some(InstrumentationScope { + name: scope.to_owned(), + ..Default::default() + }), + spans: vec![Span { + attributes: attributes + .iter() + .map(|(key, value)| KeyValue { + key: (*key).to_owned(), + value: Some(AnyValue { + value: Some(Value::StringValue((*value).to_owned())), + }), + ..Default::default() + }) + .collect(), + ..span + }], + ..Default::default() + }], + ..Default::default() + }], + }; + decode_otlp(&request.encode_to_vec(), None) + .map(|spans| spans.into_iter().next().expect("one synthetic span")) +} + +#[rstest] +#[case::agent("invoke_agent", false, ObservationType::Agent)] +#[case::chat("chat", false, ObservationType::Llm)] +#[case::completion("text_completion", false, ObservationType::Llm)] +#[case::content("generate_content", false, ObservationType::Llm)] +#[case::tool("execute_tool", false, ObservationType::Tool)] +#[case::unknown_root("unknown", true, ObservationType::Agent)] +#[case::unknown_child("unknown", false, ObservationType::Chain)] +#[case::missing_root("", true, ObservationType::Agent)] +#[case::missing_child("", false, ObservationType::Chain)] +fn genai_operations_and_parentage_classify_spans( + span: Span, + #[case] operation: &str, + #[case] root: bool, + #[case] expected: ObservationType, +) { + let decoded = decode_normalization( + Span { + parent_span_id: if root { vec![] } else { vec![3; 8] }, + ..span + }, + "", + &[("gen_ai.operation.name", operation)], + ) + .unwrap(); + assert_eq!(decoded.normalized.observation_type, expected); +} + +#[rstest] +#[case::primary("request-model", "messages-in", "messages-out", ["request-model", "messages-in", "messages-out"])] +#[case::fallback("", "", "", ["response-model", "tool-in", "tool-out"])] +#[case::independent_fallback("request-model", "", "messages-out", ["request-model", "tool-in", "messages-out"])] +fn genai_fields_and_consumed_attributes_follow_the_same_fallback( + span: Span, + #[case] model: &str, + #[case] input: &str, + #[case] output: &str, + #[case] expected: [&str; 3], +) { + let decoded = decode_normalization( + span, + "", + &[ + ("gen_ai.request.model", model), + ("gen_ai.response.model", "response-model"), + ("gen_ai.input.messages", input), + ("gen_ai.output.messages", output), + ("gen_ai.tool.call.arguments", "tool-in"), + ("gen_ai.tool.call.result", "tool-out"), + ("gen_ai.agent.name", "test-agent"), + ("gen_ai.response.id", "response-1"), + ], + ) + .unwrap(); + let fields = &decoded.normalized; + assert_eq!( + [ + fields.model.as_str(), + fields.input.as_str(), + fields.output.as_str() + ], + expected + ); + assert_eq!(fields.agent_name, "test-agent"); + assert_eq!(fields.litellm_request_id, "response-1"); + assert_eq!( + fields.input, + decoded.attributes[decoded.consumed_attributes[0]] + ); + assert_eq!( + fields.output, + decoded.attributes[decoded.consumed_attributes[1]] + ); +} + +#[rstest] +#[case::specific(&[("llm.token_count.prompt", "5"), ("llm.token_count.completion", "9")], 5, 9)] +#[case::fallback(&[], 17, 23)] +#[case::mixed(&[("llm.token_count.prompt", "5")], 5, 23)] +#[case::empty_specific(&[("llm.token_count.prompt", "")], 0, 23)] +fn openinference_fields_override_genai_and_usage_falls_back_per_field( + span: Span, + #[case] token_attributes: &[(&str, &str)], + #[case] input_tokens: u32, + #[case] output_tokens: u32, +) { + let attributes = [ + ("openinference.span.kind", "lLm"), + ("gen_ai.operation.name", "execute_tool"), + ("llm.model_name", "inference-model"), + ("gen_ai.request.model", "other-model"), + ("agent.name", "inference-agent"), + ("input.value", "inference-input"), + ("output.value", "inference-output"), + ("gen_ai.input.messages", "other-input"), + ("gen_ai.output.messages", "other-output"), + ("gen_ai.usage.input_tokens", "17"), + ("gen_ai.usage.output_tokens", "23"), + ]; + let combined = attributes + .iter() + .chain(token_attributes) + .copied() + .collect::>(); + let decoded = decode_normalization(span, "", &combined).unwrap(); + let fields = &decoded.normalized; + assert_eq!(fields.observation_type, ObservationType::Llm); + assert_eq!(fields.model, "inference-model"); + assert_eq!(fields.agent_name, "inference-agent"); + assert_eq!(fields.input, "inference-input"); + assert_eq!(fields.output, "inference-output"); + assert_eq!( + (fields.input_tokens, fields.output_tokens), + (input_tokens, output_tokens) + ); + assert_eq!(decoded.consumed_attributes, ["input.value", "output.value"]); +} + +#[rstest] +#[case::scope("langsmith", &[], ObservationType::Agent)] +#[case::attribute("other", &[("langsmith.span.kind", "llm")], ObservationType::Llm)] +fn langsmith_dispatch_overrides_other_conventions( + span: Span, + #[case] scope: &str, + #[case] convention_attributes: &[(&str, &str)], + #[case] observation_type: ObservationType, +) { + let attributes = [ + ("openinference.span.kind", "TOOL"), + ("gen_ai.operation.name", "execute_tool"), + ("langsmith.metadata.lc_agent_name", "test-agent"), + ( + "gen_ai.prompt", + r#"{"messages":[{"type":"human","content":"hello"}]}"#, + ), + ("gen_ai.completion", "{}"), + ("input.value", "other-input"), + ]; + let combined = attributes + .iter() + .chain(convention_attributes) + .copied() + .collect::>(); + let decoded = decode_normalization(span, scope, &combined).unwrap(); + assert_eq!(decoded.normalized.observation_type, observation_type); + assert_eq!(decoded.normalized.agent_name, "test-agent"); + assert_eq!( + serde_json::from_str::(&decoded.normalized.input).unwrap(), + serde_json::json!([{"role": "user", "content": "hello"}]), + ); + assert_eq!( + decoded.consumed_attributes, + ["gen_ai.prompt", "gen_ai.completion"] + ); +} + +#[rstest] +#[case::flat(r#"{"messages":[{"type":"human","content":"hello"}]}"#)] +#[case::nested(r#"{"messages":[[{"kwargs":{"type":"human","content":"hello"}}],[{"type":"human","content":"ignored batch"}]]}"#)] +fn langsmith_llm_messages_preserve_visible_content_and_tool_calls( + span: Span, + #[case] prompt: &str, +) { + let completion = r#"{ + "generations": [[{"message": {"kwargs": { + "type": "ai", + "content": [ + {"type": "text", "text": "first"}, + {"type": "thinking", "thinking": "hidden"}, + {"type": "tool_use", "id": "call-1"}, + {"type": "text", "text": "second"} + ], + "tool_calls": [{"name": "search", "args": {"query": "hello"}, "id": "call-1"}], + "response_metadata": {"id": "response-1"} + }}}]] + }"#; + let decoded = decode_normalization( + span, + "langsmith", + &[ + ("langsmith.span.kind", "llm"), + ("gen_ai.prompt", prompt), + ("gen_ai.completion", completion), + ], + ) + .unwrap(); + let input: serde_json::Value = serde_json::from_str(&decoded.normalized.input).unwrap(); + let output: serde_json::Value = serde_json::from_str(&decoded.normalized.output).unwrap(); + assert_eq!( + input, + serde_json::json!([{"role": "user", "content": "hello"}]) + ); + assert_eq!( + output, + serde_json::json!({ + "role": "assistant", + "content": "first\n\nsecond", + "tool_calls": [{"name": "search", "args": {"query": "hello"}, "id": "call-1"}], + }) + ); + assert_eq!(decoded.normalized.litellm_request_id, "response-1"); +} + +#[rstest] +#[case::string(r#""result""#, "result")] +#[case::wrapped(r#"{"output":{"content":"result"}}"#, "result")] +#[case::command( + r#"{"output":{"update":{"messages":[{"content":"ignored"},{"content":"result"}]}}}"#, + "result" +)] +#[case::object(r#"{"output":{"count":2}}"#, r#"{"count": 2}"#)] +#[case::null(r#"{"output":null}"#, "null")] +fn langsmith_tool_output_unwraps_supported_shapes( + span: Span, + #[case] completion: &str, + #[case] expected: &str, +) { + let decoded = decode_normalization( + span, + "langsmith", + &[ + ("langsmith.span.kind", "tool"), + ("gen_ai.prompt", "raw-tool-input"), + ("gen_ai.completion", completion), + ], + ) + .unwrap(); + assert_eq!(decoded.normalized.observation_type, ObservationType::Tool); + assert_eq!(decoded.normalized.input, "raw-tool-input"); + assert_eq!(decoded.normalized.output, expected); +} + const CLAUDE_AGENT_SDK_FIXTURE: &[u8] = include_bytes!("../../../../tests/test_litellm/tracing/fixtures/claude_agent_sdk_export.json"); const CLAUDE_AGENT_SDK_DETAILED_FIXTURE: &[u8] = include_bytes!( diff --git a/litellm-rust/crates/traces/tests/query.rs b/litellm-rust/crates/traces/tests/query.rs new file mode 100644 index 00000000000..79f9886dae6 --- /dev/null +++ b/litellm-rust/crates/traces/tests/query.rs @@ -0,0 +1,34 @@ +use litellm_traces::{InvalidQuery, ReadQuery}; +use rstest::rstest; + +#[rstest] +#[case::list_traces("list_traces", ReadQuery::ListTraces)] +#[case::trace_spans("trace_spans", ReadQuery::TraceSpans)] +#[case::span_detail("span_detail", ReadQuery::SpanDetail)] +#[case::span_error("span_error", ReadQuery::SpanError)] +#[case::identity("trace_identity", ReadQuery::TraceIdentity)] +#[case::spend("spend_by_response_ids", ReadQuery::SpendByResponseIds)] +#[case::availability("availability", ReadQuery::Availability)] +#[case::agents("agents", ReadQuery::Agents)] +#[case::sample("sample", ReadQuery::Sample)] +#[case::content("content", ReadQuery::Content)] +#[case::evidence("evidence", ReadQuery::Evidence)] +fn names_select_the_public_query(#[case] name: &str, #[case] query: ReadQuery) { + assert_eq!(ReadQuery::parse(name).unwrap(), query); + assert_eq!(query.as_ref(), name); + assert_eq!(query.to_string(), name); +} + +#[rstest] +#[case::unknown("unknown")] +#[case::case_sensitive("List_Traces")] +#[case::whitespace(" list_traces")] +#[case::empty("")] +fn invalid_names_preserve_the_public_error(#[case] name: &str) { + let error = ReadQuery::parse(name).unwrap_err(); + assert!(matches!(error, InvalidQuery)); + assert_eq!(error.to_string(), "unknown ClickHouse read query"); +} + +#[path = "query/named.rs"] +mod named; diff --git a/litellm-rust/crates/traces/tests/query/named.rs b/litellm-rust/crates/traces/tests/query/named.rs new file mode 100644 index 00000000000..b20da7bd800 --- /dev/null +++ b/litellm-rust/crates/traces/tests/query/named.rs @@ -0,0 +1,63 @@ +use litellm_traces::query::named::*; +use rstest::rstest; +use serde::{Serialize, de::DeserializeOwned}; +use serde_json::{Value, json}; + +fn round_trip(wire: Value) { + let contract: T = serde_json::from_value(wire.clone()).unwrap(); + assert_eq!(serde_json::to_value(contract).unwrap(), wire); +} + +#[rstest] +#[case::admin(vec![], "")] +#[case::multiple_teams(vec!["team-a", "team-b"], "")] +#[case::key(vec!["team-a"], "key")] +#[case::teamless_key(vec![], "key")] +fn named_requests_preserve_all_access_cases(#[case] teams: Vec<&str>, #[case] key: &str) { + let access = json!({"all_teams": u8::from(teams.is_empty() && key.is_empty()), "user_id": "", "team_ids": teams, "api_key_hash": key}); + round_trip::(access.clone()); + let request = |specific: Value| { + Value::Object( + access + .as_object() + .unwrap() + .iter() + .chain(specific.as_object().unwrap()) + .map(|(key, value)| (key.clone(), value.clone())) + .collect(), + ) + }; + round_trip::(request( + json!({"start_ms": -1, "end_ms": 10, "cursor_ms": 0, "cursor_trace_id": "", "limit": 100}), + )); + round_trip::(request(json!({"trace_id": "trace"}))); + round_trip::(request(json!({"trace_id": "trace", "trace_ref": "ref"}))); + round_trip::(request( + json!({"trace_id": "trace", "trace_ref": "ref", "span_id": "span"}), + )); + round_trip::(request( + json!({"trace_id": "trace", "trace_ref": "ref", "span_id": "span", "error_offset": u64::MAX, "error_version": "version"}), + )); + round_trip::(request( + json!({"response_ids": ["response"], "start_ms": -1, "end_ms": 10}), + )); +} + +#[rstest] +fn result_contracts_preserve_public_field_names() { + round_trip::( + json!({"trace_id": "trace", "trace_ref": "ref", "team_id": "team", "api_key_hash": "key", "user_id": "user", "name": "agent", "service": "service", "input_preview": "input", "status": "ok", "start_ms": -1, "duration_ms": 20, "span_count": u64::MAX, "agent_count": 1, "agent_invocations": 2, "llm_calls": 3, "tool_calls": 4, "input_tokens": 5, "output_tokens": 6, "models": ["model"], "error_count": 0, "request_ids": ["request"]}), + ); + round_trip::( + json!({"span_id": "span", "parent_span_id": "parent", "name": "agent", "type": "agent", "agent": "agent", "status": "error", "status_message": "error", "error_truncated": 1, "start_ns": -1, "duration_ns": u64::MAX, "service": "service", "input_preview": "input", "model": "model", "input_tokens": u32::MAX, "output_tokens": 6, "litellm_request_id": "request", "team_id": "team", "api_key_hash": "key", "user_id": "user"}), + ); + round_trip::( + json!({"span_id": "span", "input": "input", "output": "output", "attributes": {"count": "42"}}), + ); + round_trip::( + json!({"span_id": "span", "message": "error", "total_chars": u64::MAX, "version": "version"}), + ); + round_trip::( + json!({"request_id": "request", "response_id": "response", "team_id": "team", "api_key": "key", "user": "user", "spend": 0.125, "start_ms": -1}), + ); +} diff --git a/litellm-rust/crates/traces/tests/query_access.rs b/litellm-rust/crates/traces/tests/query_access.rs index b71bcce614e..e21abc6f427 100644 --- a/litellm-rust/crates/traces/tests/query_access.rs +++ b/litellm-rust/crates/traces/tests/query_access.rs @@ -1,268 +1,49 @@ -use std::collections::BTreeMap; - -use litellm_http::Client; -use litellm_traces::{ - Connection, Error, QueryReaders, QueryScope, ensure_schema, query_help, query_sql, -}; -use rstest::{fixture, rstest}; +use litellm_traces::{InvalidScope, QueryScope}; +use rstest::rstest; use serde_json::{Value, json}; -use testcontainers_modules::{ - clickhouse::ClickHouse, - testcontainers::{ContainerAsync, ImageExt, runners::AsyncRunner}, -}; -struct Database { - _container: ContainerAsync, - client: Client, - writer: Connection, - readers: QueryReaders, -} - -#[fixture] -async fn database() -> Result> { - let container = ClickHouse::default() - .with_tag( - "26.9.6.6@sha256:eb4870e7ca7ed70c259eebfcfbee6cf797017f6b5436c2926bbbfe3d4d28486e", - ) - .with_env_var("CLICKHOUSE_SKIP_USER_SETUP", "1") - .start() - .await?; - let writer = Connection::parse(&format!( - "http://{}:{}", - container.get_host().await?, - container.get_host_port_ipv4(8123).await? - ))?; - let client = Client::no_redirect_for_test(); - ensure_schema(&client, &writer, "trace_test", 7).await?; - for sql in [ - "INSERT INTO trace_test.otel_traces (TeamId, ApiKeyHash, TraceId, SpanId, Timestamp, SpanAttributes) VALUES ('team-a', 'key-a1', 'shared-trace', 'a1', now(), map('visible', 'a')), ('team-a', 'key-a2', 'shared-trace', 'a2', now(), map('visible', 'a')), ('team-b', 'key-b', 'shared-trace', 'b', now(), map('secret-b', 'b'))", - "INSERT INTO trace_test.spend_logs (team_id, api_key, request_id, start_time, end_time, metadata) VALUES ('team-a', 'key-a1', 'a1', now(), now(), '{\"visible\":1}'), ('team-a', 'key-a2', 'a2', now(), now(), '{\"visible\":1}'), ('team-b', 'key-b', 'b', now(), now(), '{\"secret_b\":1}')", - "CREATE TABLE trace_test.private_data (secret String) ENGINE = Memory", - "INSERT INTO trace_test.private_data VALUES ('hidden')", - ] { - let response = client.post(writer.url().clone()).body(sql).send().await?; - assert!(response.status().is_success(), "{}", response.text().await?); +#[rstest] +#[case::admin(json!({"kind": "admin"}), true)] +#[case::team(json!({"kind": "team", "team_id": "team"}), true)] +#[case::empty_team(json!({"kind": "team", "team_id": ""}), false)] +#[case::key(json!({"kind": "key", "team_id": "team", "api_key_hash": "key"}), true)] +#[case::teamless_key(json!({"kind": "key", "team_id": "", "api_key_hash": "key"}), true)] +#[case::empty_key(json!({"kind": "key", "team_id": "team", "api_key_hash": ""}), false)] +#[case::user_logs(json!({"kind": "logs", "user_id": "user", "team_ids": [], "api_key_hash": ""}), true)] +#[case::permitted_teams(json!({"kind": "logs", "user_id": "", "team_ids": ["team"], "api_key_hash": ""}), true)] +#[case::key_logs(json!({"kind": "logs", "user_id": "", "team_ids": [], "api_key_hash": "key"}), true)] +#[case::anonymous_logs(json!({"kind": "logs", "user_id": "", "team_ids": [], "api_key_hash": ""}), false)] +#[case::empty_permitted_team(json!({"kind": "logs", "user_id": "user", "team_ids": [""], "api_key_hash": ""}), false)] +#[case::empty_teamless_key(json!({"kind": "key", "team_id": "", "api_key_hash": ""}), false)] +fn scope_validation_preserves_authorization_and_wire_shape( + #[case] wire: Value, + #[case] valid: bool, +) { + let scope: QueryScope = serde_json::from_value(wire.clone()).unwrap(); + assert_eq!(serde_json::to_value(&scope).unwrap(), wire); + match (scope.validate(), valid) { + (Ok(()), true) | (Err(InvalidScope), false) => (), + (result, _) => panic!("unexpected validation: {result:?}"), } - let readers = QueryReaders::new(writer.clone(), "trace_test".to_owned()); - Ok(Database { - _container: container, - client, - writer, - readers, - }) } #[rstest] -#[case::team(QueryScope::Team { team_id: "team-a".to_owned() }, vec!["a1", "a2"])] -#[case::project_key(QueryScope::Key { team_id: "team-a".to_owned(), api_key_hash: "key-a1".to_owned() }, vec!["a1"])] -#[case::admin(QueryScope::Admin, vec!["a1", "a2", "b"])] -#[case::quoted_team(QueryScope::Team { team_id: "team-a' OR 1=1 --\\".to_owned() }, vec![])] -#[tokio::test] -async fn queries_and_help_are_scoped_by_the_database( - #[future(awt)] database: Result>, - #[case] scope: QueryScope, - #[case] expected: Vec<&str>, -) -> Result<(), Box> { - let database = database?; - let reader = database - .readers - .connection(&database.client, &scope, "test-master-secret") - .await?; - let queries = [ - "SELECT SpanId AS id FROM otel_traces ORDER BY id", - "SELECT SpanId AS id FROM trace_test.otel_traces WHERE 1 = 1 ORDER BY id", - "SELECT SpanId AS id FROM merge('trace_test', '^otel_traces$') ORDER BY id", - "WITH source AS (SELECT * FROM trace_test.otel_traces) SELECT SpanId AS id FROM source ORDER BY id", - "SELECT SpanId AS id FROM otel_traces UNION DISTINCT SELECT SpanId AS id FROM trace_test.otel_traces ORDER BY id", - "SELECT t.SpanId AS id FROM otel_traces t INNER JOIN spend_logs s ON t.SpanId = s.request_id ORDER BY id", - "SELECT request_id AS id FROM spend_logs FINAL ORDER BY id", - ]; - for sql in queries { - let body: Value = serde_json::from_str(&query_sql(&database.client, &reader, sql).await?)?; - assert_eq!( - body["data"], - json!( - expected - .iter() - .map(|id| json!({"id": id})) - .collect::>() - ), - "{sql}" - ); - } - let summary: Value = serde_json::from_str( - &query_sql( - &database.client, - &reader, - "SELECT sum(SpanCount) AS count FROM agent_traces_by_key", - ) - .await?, - )?; - assert_eq!(summary["data"][0]["count"], json!(expected.len())); - let help = query_help(&database.client, &reader).await?; - assert_eq!(help.contains("secret_b"), expected.contains(&"b")); - assert_eq!(help.contains("secret-b"), expected.contains(&"b")); - let recreated = QueryReaders::new(database.writer.clone(), "trace_test".to_owned()); - let repeated = recreated - .connection(&database.client, &scope, "test-master-secret") - .await?; - assert_eq!(reader.url(), repeated.url()); - Ok(()) +#[case::unknown_kind(json!({"kind": "all"}))] +#[case::unknown_field(json!({"kind": "team", "team_id": "team", "extra": true}))] +#[case::missing_team(json!({"kind": "key", "api_key_hash": "key"}))] +#[case::missing_key(json!({"kind": "key", "team_id": "team"}))] +fn scope_rejects_invalid_wire_shape(#[case] wire: Value) { + assert!(serde_json::from_value::(wire).is_err()); } #[rstest] -#[tokio::test] -async fn rotating_master_secret_revokes_previous_reader_credentials( - #[future(awt)] database: Result>, -) -> Result<(), Box> { - let database = database?; - let scope = QueryScope::Team { - team_id: "team-a".to_owned(), - }; - let old_reader = database - .readers - .connection(&database.client, &scope, "old-master-secret") - .await?; - let old_result = query_sql( - &database.client, - &old_reader, - "SELECT SpanId AS id FROM otel_traces ORDER BY id", - ) - .await?; - let old_rows: Value = serde_json::from_str(&old_result)?; - assert_eq!(old_rows["data"], json!([{ "id": "a1" }, { "id": "a2" }])); - - let rotated_readers = QueryReaders::new(database.writer.clone(), "trace_test".into()); - let new_reader = rotated_readers - .connection(&database.client, &scope, "new-master-secret") - .await?; - assert!( - query_sql( - &database.client, - &old_reader, - "SELECT SpanId AS id FROM otel_traces ORDER BY id", - ) - .await - .is_err() +fn admin_preserves_existing_extra_field_handling() { + let scope: QueryScope = + serde_json::from_value(json!({"kind": "admin", "team_id": "ignored"})).unwrap(); + assert!(matches!(scope, QueryScope::Admin)); + assert!(scope.validate().is_ok()); + assert_eq!( + serde_json::to_value(scope).unwrap(), + json!({"kind": "admin"}) ); - let new_result = query_sql( - &database.client, - &new_reader, - "SELECT SpanId AS id FROM otel_traces ORDER BY id", - ) - .await?; - let new_rows: Value = serde_json::from_str(&new_result)?; - assert_eq!(new_rows["data"], json!([{ "id": "a1" }, { "id": "a2" }])); - assert_eq!(old_reader.url().username(), new_reader.url().username()); - assert_ne!(old_reader.url().password(), new_reader.url().password()); - Ok(()) -} - -#[rstest] -#[tokio::test] -async fn managed_reader_rejects_privilege_and_scope_bypasses( - #[future(awt)] database: Result>, -) -> Result<(), Box> { - let database = database?; - let scope = QueryScope::Team { - team_id: "team-a".to_owned(), - }; - let reader = database - .readers - .connection(&database.client, &scope, "test-master-secret") - .await?; - for sql in [ - "INSERT INTO otel_traces (TraceId) VALUES ('injected')", - "DROP TABLE otel_traces", - "SELECT * FROM private_data", - "SELECT * FROM otel_traces SETTINGS readonly = 0", - "SELECT * FROM otel_traces SETTINGS max_memory_usage = 0", - "SELECT * FROM otel_traces SETTINGS max_execution_time = 0", - "CREATE USER scope_bypass", - "CREATE NAMED COLLECTION scope_bypass AS host = 'localhost'", - "BACKUP TABLE otel_traces TO Disk('default', 'scope-bypass')", - "SELECT * FROM url('http://127.0.0.1:1/', 'LineAsString', 'line String')", - "SELECT * FROM remote('127.0.0.1', 'trace_test', 'otel_traces')", - ] { - assert!( - matches!( - query_sql(&database.client, &reader, sql).await, - Err(Error::QueryFailed(_)) - ), - "{sql}" - ); - } - let roles: Value = serde_json::from_str( - &query_sql(&database.client, &reader, "SELECT enabledRoles() AS roles").await?, - )?; - assert_eq!(roles["data"], json!([{ "roles": [] }])); - let rows: Value = serde_json::from_str( - &query_sql( - &database.client, - &reader, - "SELECT DISTINCT TeamId FROM otel_traces", - ) - .await?, - )?; - assert_eq!(rows["data"], json!([{ "TeamId": "team-a" }])); - Ok(()) -} - -#[rstest] -#[tokio::test] -async fn provisioning_failure_never_returns_a_writer_connection( - #[future(awt)] database: Result>, -) -> Result<(), Box> { - let database = database?; - let reader = database - .readers - .connection(&database.client, &QueryScope::Admin, "test-master-secret") - .await?; - let no_provision_privileges = QueryReaders::new(reader, "trace_test".to_owned()); - let result = no_provision_privileges - .connection( - &database.client, - &QueryScope::Team { - team_id: "team-a".to_owned(), - }, - "other-secret", - ) - .await; - assert!(result.is_err()); - assert!( - database - .readers - .connection(&database.client, &QueryScope::Admin, "") - .await - .is_err() - ); - assert!( - database - .readers - .connection( - &database.client, - &QueryScope::Team { - team_id: String::new() - }, - "test-master-secret" - ) - .await - .is_err() - ); - let permits = (0..8) - .map(|_| database.readers.acquire()) - .collect::, _>>()?; - assert!(database.readers.acquire().is_err()); - drop(permits); - assert!(database.readers.acquire().is_ok()); - let rows = litellm_traces::execute_read( - &database.client, - &database.writer, - "SELECT count() AS count FROM trace_test.otel_traces", - &BTreeMap::new(), - ) - .await?; - let rows: Value = serde_json::from_str(&rows)?; - assert_eq!(rows["data"][0]["count"], 3); - Ok(()) } diff --git a/litellm/proxy/_types.py b/litellm/proxy/_types.py index cabb04cc52b..da69b77286e 100644 --- a/litellm/proxy/_types.py +++ b/litellm/proxy/_types.py @@ -543,6 +543,7 @@ class LiteLLMRoutes(enum.Enum): "/v1/traces/query/help", "/v1/traces/{trace_id}", "/v1/traces/{trace_id}/spans/{span_id}", + "/v1/traces/{trace_id}/spans/{span_id}/error", ] anthropic_routes = [ diff --git a/litellm/proxy/auth/route_checks.py b/litellm/proxy/auth/route_checks.py index 2ab76a7a101..6445f0d7b05 100644 --- a/litellm/proxy/auth/route_checks.py +++ b/litellm/proxy/auth/route_checks.py @@ -410,7 +410,7 @@ class RouteChecks: if RouteChecks.check_route_access(route=route, allowed_routes=LiteLLMRoutes.agent_inference_routes.value): return True - if route in LiteLLMRoutes.litellm_native_routes.value: + if RouteChecks.check_route_access(route=route, allowed_routes=LiteLLMRoutes.litellm_native_routes.value): return True # fuzzy match routes like "/v1/threads/thread_49EIN5QF32s4mH20M7GFKdlZ" diff --git a/litellm/proxy/lens/sources.py b/litellm/proxy/lens/sources.py index 17550cc4aab..3313cd2ded2 100644 --- a/litellm/proxy/lens/sources.py +++ b/litellm/proxy/lens/sources.py @@ -1,10 +1,9 @@ import base64 import json -from collections.abc import Awaitable, Mapping -from types import MappingProxyType -from typing import Final, Literal, Protocol +from collections.abc import Awaitable, Sequence +from typing import Final, Protocol, TypeAlias -from pydantic import BaseModel, TypeAdapter +from pydantic import TypeAdapter from litellm.proxy.lens.models import ( Evidence, @@ -16,59 +15,29 @@ from litellm.proxy.lens.models import ( Scope, TracePart, ) - - -class ActivityAvailability(BaseModel): - traces: bool = False - requests: bool = False +from litellm.rust_bridge.trace_queries import ( + ActivityAvailability, + AgentRow, + CountRow, + ExecutionRow, + LensAccessParams, + LensContentParams, + LensEvidenceParams, + LensSampleParams, + PartRow, +) class Storage(Protocol): - def lens_availability(self, parameters: Mapping[str, object]) -> Awaitable[object]: ... - def lens_agents(self, parameters: Mapping[str, object]) -> Awaitable[object]: ... - def lens_sample(self, parameters: Mapping[str, object]) -> Awaitable[object]: ... - def lens_content(self, parameters: Mapping[str, object]) -> Awaitable[object]: ... - def lens_evidence(self, parameters: Mapping[str, object]) -> Awaitable[object]: ... + def lens_availability(self, parameters: LensAccessParams) -> Awaitable[Sequence[ActivityAvailability]]: ... + def lens_agents(self, parameters: LensAccessParams) -> Awaitable[Sequence[AgentRow]]: ... + def lens_sample(self, parameters: LensSampleParams) -> Awaitable[Sequence[ExecutionRow]]: ... + def lens_content(self, parameters: LensContentParams) -> Awaitable[Sequence[PartRow]]: ... + def lens_evidence(self, parameters: LensEvidenceParams) -> Awaitable[Sequence[CountRow]]: ... -class ExecutionRow(BaseModel): - selection_key: str = "" - source: Literal["traces", "requests"] - trace_id: str - trace_ref: str = "" - team_id: str - name: str - start_time: str - span_count: int - root_seen: int - eligible: int - selected: int = 0 - service: str = "" - attributes: tuple[tuple[str, str], ...] = () - - -class PartRow(BaseModel): - span_id: str - parent_span_id: str - name: str - kind: str - content: str - truncated: int - - -class CountRow(BaseModel): - count: int - - -class AgentRow(BaseModel): - agent_name: str - - -_AVAILABILITY: Final = TypeAdapter(tuple[ActivityAvailability, ...]) -_AGENTS: Final = TypeAdapter(tuple[AgentRow, ...]) -_ROWS: Final = TypeAdapter(tuple[ExecutionRow, ...]) -_PARTS: Final = TypeAdapter(tuple[PartRow, ...]) -_COUNTS: Final = TypeAdapter(tuple[CountRow, ...]) +ExecutionIdParts: TypeAlias = tuple[str, str, str] | tuple[str, str, str, str] +_EXECUTION_ID: Final[TypeAdapter[ExecutionIdParts]] = TypeAdapter(ExecutionIdParts) def execution_id(source: str, team_id: str, trace_id: str, trace_ref: str = "") -> str: @@ -76,22 +45,12 @@ def execution_id(source: str, team_id: str, trace_id: str, trace_ref: str = "") def parse_execution(value: str) -> tuple[str, str, str, str]: - parts: Final = TypeAdapter(tuple[str, str, str] | tuple[str, str, str, str]).validate_json( - base64.urlsafe_b64decode(value) - ) + parts: Final = _EXECUTION_ID.validate_json(base64.urlsafe_b64decode(value)) return (parts[0], parts[1], parts[2], parts[3] if len(parts) == 4 else "") -def parameters(scope: Scope, filters: tuple[MetadataFilter, ...]) -> Mapping[str, object]: - return MappingProxyType( - { - "all_teams": int(scope.all_teams), - "team": scope.team_id, - "key_hash": scope.api_key_hash, - "filter_keys": tuple(f.key for f in filters), - "filter_values": tuple(f.value for f in filters), - } - ) +def access_parameters(scope: Scope) -> LensAccessParams: + return LensAccessParams(all_teams=1 if scope.all_teams else 0, team=scope.team_id, key_hash=scope.api_key_hash) def selection_id(value: str) -> str: @@ -104,11 +63,11 @@ class SourceReader: self.storage: Final = storage async def availability(self, scope: Scope) -> ActivityAvailability: - rows: Final = _AVAILABILITY.validate_python(await self.storage.lens_availability(parameters(scope, ()))) + rows: Final = await self.storage.lens_availability(access_parameters(scope)) return rows[0] if rows else ActivityAvailability() async def agents(self, scope: Scope) -> tuple[str, ...]: - rows: Final = _AGENTS.validate_python(await self.storage.lens_agents(parameters(scope, ()))) + rows: Final = await self.storage.lens_agents(access_parameters(scope)) return tuple(row.agent_name for row in rows) async def sample( @@ -122,25 +81,27 @@ class SourceReader: preview: bool = False, cursor: str = "", ) -> Sample: - params: Final = MappingProxyType( - { - **parameters(scope, settings.filters), - "source": settings.source, - "start": start, - "end": end, - "service": settings.service, - "agent_name": settings.agent_name, - "limit": page_size, - "offset": offset, - "after": cursor, - "sample_percent": str(settings.sample_percent), - "sample_cap": settings.sample_size or 0, - "preview": int(preview), - "selected_team": settings.team_id, - "execution_ids": tuple(selection_id(value) for value in settings.execution_ids), - } + params: Final = LensSampleParams( + all_teams=1 if scope.all_teams else 0, + team=scope.team_id, + key_hash=scope.api_key_hash, + source=settings.source, + start=start, + end=end, + service=settings.service, + agent_name=settings.agent_name, + filter_keys=tuple(f.key for f in settings.filters), + filter_values=tuple(f.value for f in settings.filters), + limit=page_size, + offset=offset, + after=cursor, + sample_percent=settings.sample_percent, + sample_cap=settings.sample_size or 0, + preview=1 if preview else 0, + selected_team=settings.team_id, + execution_ids=tuple(selection_id(value) for value in settings.execution_ids), ) - rows: Final = _ROWS.validate_python(await self.storage.lens_sample(params)) + rows: Final = await self.storage.lens_sample(params) return Sample( eligible=rows[0].eligible if rows else 0, selected=rows[0].selected if rows else 0, @@ -173,18 +134,18 @@ class SourceReader: ) async def content(self, scope: Scope, execution: Execution, cursor: str = "", offset: int = 0) -> ExecutionContent: - params: Final = MappingProxyType( - { - **parameters(scope, ()), - "source": execution.source, - "id": execution.trace_id, - "trace_ref": execution.trace_ref, - "record_team": execution.team_id, - "cursor": cursor, - "offset": offset + 1, - } + params: Final = LensContentParams( + all_teams=1 if scope.all_teams else 0, + team=scope.team_id, + key_hash=scope.api_key_hash, + source=execution.source, + id=execution.trace_id, + trace_ref=execution.trace_ref, + record_team=execution.team_id, + cursor=cursor, + offset=offset + 1, ) - rows: Final = _PARTS.validate_python(await self.storage.lens_content(params)) + rows: Final = await self.storage.lens_content(params) return ExecutionContent( execution=execution, parts=tuple( @@ -204,16 +165,16 @@ class SourceReader: ) async def verify_evidence(self, scope: Scope, execution: Execution, evidence: Evidence) -> bool: - params: Final = MappingProxyType( - { - **parameters(scope, ()), - "source": execution.source, - "id": execution.trace_id, - "trace_ref": execution.trace_ref, - "record_team": execution.team_id, - "span": evidence.span_id, - "quote": evidence.quote, - } + params: Final = LensEvidenceParams( + all_teams=1 if scope.all_teams else 0, + team=scope.team_id, + key_hash=scope.api_key_hash, + source=execution.source, + id=execution.trace_id, + trace_ref=execution.trace_ref, + record_team=execution.team_id, + span=evidence.span_id, + quote=evidence.quote, ) - rows: Final = _COUNTS.validate_python(await self.storage.lens_evidence(params)) + rows: Final = await self.storage.lens_evidence(params) return bool(rows and rows[0].count) diff --git a/litellm/proxy/spend_tracking/log_visibility.py b/litellm/proxy/spend_tracking/log_visibility.py new file mode 100644 index 00000000000..83f236d3028 --- /dev/null +++ b/litellm/proxy/spend_tracking/log_visibility.py @@ -0,0 +1,44 @@ +from collections.abc import Awaitable, Callable +from dataclasses import dataclass +from typing import Final + +from fastapi import HTTPException + +from litellm.proxy._types import UserAPIKeyAuth + + +@dataclass(frozen=True, slots=True) +class LogVisibility: + all_teams: bool = False + user_id: str = "" + team_ids: tuple[str, ...] = () + api_key_hash: str = "" + + +async def permitted_log_teams(auth: UserAPIKeyAuth) -> tuple[str, ...]: + from litellm.proxy.proxy_server import prisma_client + from litellm.proxy.spend_tracking.spend_management_endpoints import ( + _get_permitted_team_ids_for_spend_logs_or_empty, # pyright: ignore[reportPrivateUsage] # Reuse request-log policy + ) + + if prisma_client is None: + return () + return await _get_permitted_team_ids_for_spend_logs_or_empty(prisma_client=prisma_client, user_api_key_dict=auth) + + +async def log_visibility( + auth: UserAPIKeyAuth, + team_lookup: Callable[[UserAPIKeyAuth], Awaitable[tuple[str, ...]]] = permitted_log_teams, +) -> LogVisibility: + from litellm.proxy.spend_tracking.spend_management_endpoints import ( + _is_admin_view_safe, # pyright: ignore[reportPrivateUsage] # Reuse request-log policy + ) + + if _is_admin_view_safe(user_api_key_dict=auth): + return LogVisibility(all_teams=True) + if auth.user_id: + team_ids: Final = await team_lookup(auth) + return LogVisibility(user_id=auth.user_id, team_ids=team_ids, api_key_hash=auth.token or "") + if auth.token: + return LogVisibility(api_key_hash=auth.token) + raise HTTPException(status_code=403, detail="Not allowed to view logs") diff --git a/litellm/proxy/tracing_endpoints.py b/litellm/proxy/tracing_endpoints.py index e4d46560f08..d741e0b29b4 100644 --- a/litellm/proxy/tracing_endpoints.py +++ b/litellm/proxy/tracing_endpoints.py @@ -22,7 +22,9 @@ from litellm.constants import OTLP_RETRY_AFTER_SECONDS from litellm.proxy._types import LitellmUserRoles, UserAPIKeyAuth from litellm.proxy.auth.user_api_key_auth import user_api_key_auth from litellm.proxy.common_utils.http_parsing_utils import is_otlp_trace_request +from litellm.proxy.spend_tracking.log_visibility import log_visibility from litellm.proxy.tracing_runtime import provide_receiver, require_receiver +from litellm.rust_bridge.trace_query_responses import TraceQueryHelp, TraceSQLResponse from litellm.rust_bridge.traces import ClickHouseStorage, QueryScope from litellm.tracing import ( Tenant, @@ -30,6 +32,7 @@ from litellm.tracing import ( TracingPayloadTooLargeError, ) from litellm.tracing.decode import InvalidOTLPPayloadError, encode_otlp_response +from litellm.tracing.store import AmbiguousTraceError from litellm.tracing.types import SpanDetail, SpanErrorPage, Trace, TracePage, TraceScope router = APIRouter(tags=["agent tracing"]) @@ -59,18 +62,27 @@ async def provide_trace_access( auth: Annotated[UserAPIKeyAuth, Depends(user_api_key_auth)], tracing: Annotated[TraceReceiver | None, Depends(provide_receiver)], ) -> TraceAccessContext: - tenant: Final = Tenant(team_id=auth.team_id or "", api_key_hash=auth.token or "", org_id=auth.org_id or "") - match auth.user_role: - case LitellmUserRoles.PROXY_ADMIN: - return TraceAccessContext(tracing, TraceScope(team_ids=(), api_key_hash=""), tenant) - case LitellmUserRoles.PROXY_ADMIN_VIEW_ONLY: - return TraceAccessContext(tracing, TraceScope(team_ids=(), api_key_hash=""), None) - case _ if auth.team_id: - return TraceAccessContext(tracing, TraceScope(team_ids=(auth.team_id,), api_key_hash=""), tenant) - case _ if auth.token: - return TraceAccessContext(tracing, TraceScope(team_ids=("",), api_key_hash=auth.token), tenant) - case _: - return TraceAccessContext(tracing, None, tenant) + tenant: Final = Tenant( + team_id=auth.team_id or "", api_key_hash=auth.token or "", org_id=auth.org_id or "", user_id=auth.user_id or "" + ) + write_tenant: Final = None if auth.user_role == LitellmUserRoles.PROXY_ADMIN_VIEW_ONLY else tenant + if ( + not auth.user_id + and not auth.token + and auth.user_role not in (LitellmUserRoles.PROXY_ADMIN, LitellmUserRoles.PROXY_ADMIN_VIEW_ONLY) + ): + return TraceAccessContext(tracing, None, write_tenant) + visibility: Final = await log_visibility(auth) + return TraceAccessContext( + tracing, + TraceScope( + all_teams=1 if visibility.all_teams else 0, + user_id=visibility.user_id, + team_ids=visibility.team_ids, + api_key_hash=visibility.api_key_hash, + ), + write_tenant, + ) def otlp_error_response( @@ -160,18 +172,16 @@ def provide_trace_query_secret() -> str: return master_key -def trace_query_scope(auth: UserAPIKeyAuth) -> QueryScope: - if auth.user_role in (LitellmUserRoles.PROXY_ADMIN, LitellmUserRoles.PROXY_ADMIN_VIEW_ONLY): +async def trace_query_scope(auth: UserAPIKeyAuth) -> QueryScope: + visibility: Final = await log_visibility(auth) + if visibility.all_teams: return {"kind": "admin"} - if auth.project_id and auth.token: - return {"kind": "key", "team_id": auth.team_id or "", "api_key_hash": auth.token} - if auth.project_id: - raise HTTPException(status_code=403, detail="Project trace SQL queries require a project key") - if auth.team_id: - return {"kind": "team", "team_id": auth.team_id} - if auth.token: - return {"kind": "key", "team_id": "", "api_key_hash": auth.token} - raise HTTPException(status_code=403, detail="Trace SQL queries require an authenticated trace scope") + return { + "kind": "logs", + "user_id": visibility.user_id, + "team_ids": visibility.team_ids, + "api_key_hash": visibility.api_key_hash, + } async def provide_trace_query_access( @@ -179,18 +189,16 @@ async def provide_trace_query_access( tracing: Annotated[TraceReceiver | None, Depends(provide_receiver)], secret: Annotated[str, Depends(provide_trace_query_secret)], ) -> TraceQueryAccess: - return TraceQueryAccess(require_receiver(tracing).store.storage, trace_query_scope(auth), secret) + return TraceQueryAccess(require_receiver(tracing).store.storage, await trace_query_scope(auth), secret) -@router.post("/v1/traces/query") +@router.post("/v1/traces/query", response_model=TraceSQLResponse, response_model_exclude_unset=True) async def query_agent_traces( body: TraceQueryRequest, access: Annotated[TraceQueryAccess, Depends(provide_trace_query_access)], -) -> Response: +) -> TraceSQLResponse: try: - return Response( - content=await access.storage.query_sql(body.sql, access.scope, access.secret), media_type="application/json" - ) + return await access.storage.query_sql(body.sql, access.scope, access.secret) except ValueError as error: raise HTTPException(status_code=400, detail=str(error)) from error except RuntimeError as error: @@ -198,14 +206,12 @@ async def query_agent_traces( raise HTTPException(status_code=503, detail="Trace SQL query failed or exceeded reader limits") from error -@router.get("/v1/traces/query/help") +@router.get("/v1/traces/query/help", response_model=TraceQueryHelp, response_model_exclude_unset=True) async def help_agent_trace_queries( access: Annotated[TraceQueryAccess, Depends(provide_trace_query_access)], -) -> Response: +) -> TraceQueryHelp: try: - return Response( - content=await access.storage.query_help(access.scope, access.secret), media_type="application/json" - ) + return await access.storage.query_help(access.scope, access.secret) except RuntimeError as error: verbose_proxy_logger.warning("Trace query help unavailable: %s", error) raise HTTPException(status_code=503, detail="Trace query help is temporarily unavailable") from error @@ -218,7 +224,10 @@ async def get_agent_trace( trace_ref: Annotated[str, Query()] = "", ) -> Trace: tracing, scope = context.reader() - trace: Final = await tracing.get_trace(trace_id, scope, trace_ref) + try: + trace: Final = await tracing.get_trace(trace_id, scope, trace_ref) + except AmbiguousTraceError as error: + raise HTTPException(status_code=400, detail=str(error)) from error if trace is None: raise HTTPException(status_code=404, detail=f"Trace {trace_id} not found") return trace @@ -232,7 +241,10 @@ async def get_agent_trace_span( trace_ref: Annotated[str, Query()] = "", ) -> SpanDetail: tracing, scope = context.reader() - span: Final = await tracing.get_span(trace_id, span_id, scope, trace_ref) + try: + span: Final = await tracing.get_span(trace_id, span_id, scope, trace_ref) + except AmbiguousTraceError as error: + raise HTTPException(status_code=400, detail=str(error)) from error if span is None: raise HTTPException(status_code=404, detail=f"Span {span_id} not found") return span diff --git a/litellm/rust_bridge/_native.pyi b/litellm/rust_bridge/_native.pyi index 0f70c559840..a86daaa35ad 100644 --- a/litellm/rust_bridge/_native.pyi +++ b/litellm/rust_bridge/_native.pyi @@ -11,6 +11,7 @@ from litellm.rust_bridge.embeddings.entrypoints import LiteLLMEmbeddingRequest from litellm.rust_bridge.messages.entrypoints import LiteLLMMessagesRequest from litellm.rust_bridge.ocr.entrypoints import LiteLLMOcrRequest from litellm.rust_bridge.responses.entrypoints import LiteLLMResponsesRequest +from litellm.rust_bridge.trace_queries import ReadQueryName from litellm.rust_bridge.traces import DecodedSpan, QueryScope from litellm.types.llms.anthropic_messages.anthropic_response import AnthropicMessagesResponse from litellm.types.llms.openai import ResponsesAPIResponse @@ -41,8 +42,7 @@ class NativeTraceStorage: def insert_rows(self, table: str, rows: Sequence[Mapping[str, object]]) -> Future[None]: ... def query_sql(self, sql: str, scope: QueryScope, secret: str) -> Future[str]: ... def query_help(self, scope: QueryScope, secret: str) -> Future[str]: ... - def lens_query(self, name: str, parameters: Mapping[str, str | int | Sequence[str]]) -> Future[str]: ... - def query(self, query: str, parameters: Mapping[str, str | int | Sequence[str]]) -> Future[str]: ... + def query(self, query: ReadQueryName, parameters: Mapping[str, str | int | float | Sequence[str]]) -> Future[str]: ... @final class NativeDiagnosticProcessor: diff --git a/litellm/rust_bridge/trace_queries.py b/litellm/rust_bridge/trace_queries.py new file mode 100644 index 00000000000..0a9fe186646 --- /dev/null +++ b/litellm/rust_bridge/trace_queries.py @@ -0,0 +1,320 @@ +from collections.abc import Mapping +from dataclasses import dataclass +from typing import Annotated, Final, Generic, Literal, TypeAlias, TypeVar + +from pydantic import BaseModel, ConfigDict, Field, TypeAdapter +from typing_extensions import NotRequired, ReadOnly, TypedDict + +ReadQueryName: TypeAlias = Literal[ + "list_traces", + "trace_spans", + "trace_identity", + "span_detail", + "span_error", + "spend_by_response_ids", + "availability", + "agents", + "sample", + "content", + "evidence", +] + +Int64: TypeAlias = Annotated[int, Field(ge=-(2**63), le=2**63 - 1)] +UInt64: TypeAlias = Annotated[int, Field(ge=0, le=2**64 - 1)] +UInt32: TypeAlias = Annotated[int, Field(ge=0, le=2**32 - 1)] +_PARAMETERS_CONFIG: Final = ConfigDict(frozen=True, extra="forbid") + + +class ListTracesParams(BaseModel): + model_config = _PARAMETERS_CONFIG + all_teams: Literal[0, 1] + user_id: str + team_ids: tuple[str, ...] + api_key_hash: str + start_ms: Int64 + end_ms: Int64 + cursor_ms: Int64 + cursor_trace_id: str + limit: UInt32 + + +class TraceSpansParams(BaseModel): + model_config = _PARAMETERS_CONFIG + all_teams: Literal[0, 1] + user_id: str + team_ids: tuple[str, ...] + api_key_hash: str + trace_id: str + trace_ref: str + + +class SpanDetailParams(BaseModel): + model_config = _PARAMETERS_CONFIG + all_teams: Literal[0, 1] + user_id: str + team_ids: tuple[str, ...] + api_key_hash: str + trace_id: str + trace_ref: str + span_id: str + + +class SpanErrorParams(BaseModel): + model_config = _PARAMETERS_CONFIG + all_teams: Literal[0, 1] + user_id: str + team_ids: tuple[str, ...] + api_key_hash: str + trace_id: str + trace_ref: str + span_id: str + error_offset: UInt64 + error_version: str + + +class SpendByResponseIdsParams(BaseModel): + model_config = _PARAMETERS_CONFIG + all_teams: Literal[0, 1] + user_id: str + team_ids: tuple[str, ...] + api_key_hash: str + response_ids: tuple[str, ...] + start_ms: Int64 + end_ms: Int64 + + +class LensAccessParams(BaseModel): + model_config = _PARAMETERS_CONFIG + all_teams: Literal[0, 1] + team: str + key_hash: str + + +class LensSampleParams(BaseModel): + model_config = _PARAMETERS_CONFIG + all_teams: Literal[0, 1] + team: str + key_hash: str + source: Literal["traces", "requests", "both"] + start: UInt64 + end: UInt64 + agent_name: str + service: str + filter_keys: tuple[str, ...] + filter_values: tuple[str, ...] + selected_team: str + execution_ids: tuple[str, ...] + sample_cap: UInt64 + sample_percent: Annotated[float, Field(ge=0, le=100, allow_inf_nan=False)] + preview: Literal[0, 1] + after: str + limit: UInt32 + offset: UInt64 + + +class LensContentParams(BaseModel): + model_config = _PARAMETERS_CONFIG + all_teams: Literal[0, 1] + team: str + key_hash: str + source: Literal["traces", "requests"] + id: str + record_team: str + trace_ref: str + cursor: str + offset: UInt32 + + +class LensEvidenceParams(BaseModel): + model_config = _PARAMETERS_CONFIG + all_teams: Literal[0, 1] + team: str + key_hash: str + source: Literal["traces", "requests"] + id: str + record_team: str + trace_ref: str + span: str + quote: str + + +class TraceIdentityParams(BaseModel): + model_config = _PARAMETERS_CONFIG + all_teams: Literal[0, 1] + user_id: str + team_ids: tuple[str, ...] + api_key_hash: str + trace_id: str + + +class TraceIdentityRow(BaseModel): + model_config = ConfigDict(frozen=True) + trace_ref: str + + +class ListTracesRow(TypedDict): + trace_id: ReadOnly[str] + trace_ref: ReadOnly[str] + team_id: ReadOnly[str] + api_key_hash: ReadOnly[str] + user_id: ReadOnly[str] + name: ReadOnly[str] + service: ReadOnly[str] + input_preview: ReadOnly[str] + status: ReadOnly[str] + start_ms: ReadOnly[int] + duration_ms: ReadOnly[int] + span_count: ReadOnly[int] + agent_count: ReadOnly[int] + agent_invocations: ReadOnly[int] + agent_names: NotRequired[ReadOnly[tuple[str, ...]]] + frameworks: NotRequired[ReadOnly[tuple[str, ...]]] + llm_calls: ReadOnly[int] + tool_calls: ReadOnly[int] + input_tokens: ReadOnly[int] + output_tokens: ReadOnly[int] + models: ReadOnly[tuple[str, ...]] + error_count: ReadOnly[int] + request_ids: ReadOnly[tuple[str, ...]] + + +class TraceSpansRow(TypedDict): + span_id: ReadOnly[str] + parent_span_id: ReadOnly[str] + name: ReadOnly[str] + type: ReadOnly[Literal["agent", "llm", "tool", "chain", "framework"]] + agent: ReadOnly[str] + framework: NotRequired[ReadOnly[str]] + status: ReadOnly[str] + status_message: ReadOnly[str] + error_truncated: ReadOnly[bool] + start_ns: ReadOnly[int] + duration_ns: ReadOnly[int] + service: ReadOnly[str] + input_preview: ReadOnly[str] + model: ReadOnly[str] + input_tokens: ReadOnly[int] + output_tokens: ReadOnly[int] + litellm_request_id: ReadOnly[str] + team_id: ReadOnly[str] + api_key_hash: ReadOnly[str] + user_id: ReadOnly[str] + + +class SpanDetailRow(TypedDict): + span_id: ReadOnly[str] + input: ReadOnly[str] + output: ReadOnly[str] + attributes: ReadOnly[Mapping[str, str]] + + +class SpanErrorRow(BaseModel): + model_config = ConfigDict(frozen=True) + span_id: str + message: str + total_chars: int + version: str + + +class SpendRow(BaseModel): + model_config = ConfigDict(frozen=True) + request_id: str + response_id: str + team_id: str + api_key: str + user: str + spend: float + start_ms: int + + +class ActivityAvailability(BaseModel): + model_config = ConfigDict(frozen=True) + traces: bool = False + requests: bool = False + + +class ExecutionRow(BaseModel): + model_config = ConfigDict(frozen=True) + selection_key: str = "" + source: Literal["traces", "requests"] + trace_id: str + trace_ref: str = "" + team_id: str + name: str + start_time: str + span_count: int + root_seen: int + eligible: int + selected: int = 0 + service: str = "" + attributes: tuple[tuple[str, str], ...] = () + + +class PartRow(BaseModel): + model_config = ConfigDict(frozen=True) + span_id: str + parent_span_id: str + name: str + kind: str + content: str + truncated: int + + +class CountRow(BaseModel): + model_config = ConfigDict(frozen=True) + count: int + + +class AgentRow(BaseModel): + model_config = ConfigDict(frozen=True) + agent_name: str + + +ParamsT: Final = TypeVar("ParamsT", bound=BaseModel) +RowT: Final = TypeVar("RowT") + + +class QueryResponse(BaseModel, Generic[RowT]): + model_config = ConfigDict(frozen=True) + data: tuple[RowT, ...] + + +@dataclass(frozen=True, slots=True) +class ReadQuery(Generic[ParamsT, RowT]): + name: ReadQueryName + parameters: type[ParamsT] + response: TypeAdapter[QueryResponse[RowT]] + + +LIST_TRACES: Final[ReadQuery[ListTracesParams, ListTracesRow]] = ReadQuery( + "list_traces", ListTracesParams, TypeAdapter(QueryResponse[ListTracesRow]) +) +TRACE_SPANS: Final[ReadQuery[TraceSpansParams, TraceSpansRow]] = ReadQuery( + "trace_spans", TraceSpansParams, TypeAdapter(QueryResponse[TraceSpansRow]) +) +SPAN_DETAIL: Final[ReadQuery[SpanDetailParams, SpanDetailRow]] = ReadQuery( + "span_detail", SpanDetailParams, TypeAdapter(QueryResponse[SpanDetailRow]) +) +SPAN_ERROR: Final[ReadQuery[SpanErrorParams, SpanErrorRow]] = ReadQuery( + "span_error", SpanErrorParams, TypeAdapter(QueryResponse[SpanErrorRow]) +) +SPEND_BY_RESPONSE_IDS: Final[ReadQuery[SpendByResponseIdsParams, SpendRow]] = ReadQuery( + "spend_by_response_ids", SpendByResponseIdsParams, TypeAdapter(QueryResponse[SpendRow]) +) +LENS_AVAILABILITY: Final[ReadQuery[LensAccessParams, ActivityAvailability]] = ReadQuery( + "availability", LensAccessParams, TypeAdapter(QueryResponse[ActivityAvailability]) +) +LENS_AGENTS: Final[ReadQuery[LensAccessParams, AgentRow]] = ReadQuery( + "agents", LensAccessParams, TypeAdapter(QueryResponse[AgentRow]) +) +LENS_SAMPLE: Final[ReadQuery[LensSampleParams, ExecutionRow]] = ReadQuery( + "sample", LensSampleParams, TypeAdapter(QueryResponse[ExecutionRow]) +) +LENS_CONTENT: Final[ReadQuery[LensContentParams, PartRow]] = ReadQuery( + "content", LensContentParams, TypeAdapter(QueryResponse[PartRow]) +) +LENS_EVIDENCE: Final[ReadQuery[LensEvidenceParams, CountRow]] = ReadQuery( + "evidence", LensEvidenceParams, TypeAdapter(QueryResponse[CountRow]) +) + +TRACE_IDENTITY: Final = ReadQuery("trace_identity", TraceIdentityParams, TypeAdapter(QueryResponse[TraceIdentityRow])) diff --git a/litellm/rust_bridge/trace_query_responses.py b/litellm/rust_bridge/trace_query_responses.py new file mode 100644 index 00000000000..914d9b6c8d4 --- /dev/null +++ b/litellm/rust_bridge/trace_query_responses.py @@ -0,0 +1,109 @@ +from collections.abc import Mapping +from typing import Final + +from pydantic import BaseModel, ConfigDict, JsonValue + +_RESPONSE_CONFIG: Final = ConfigDict(frozen=True, extra="allow") + + +class TraceQueryColumn(BaseModel): + model_config = _RESPONSE_CONFIG + name: str + type: str + + +class TraceQueryStatistics(BaseModel): + model_config = _RESPONSE_CONFIG + elapsed: float + rows_read: int | str + bytes_read: int | str + + +class TraceSQLResponse(BaseModel): + model_config = _RESPONSE_CONFIG + meta: tuple[TraceQueryColumn, ...] + data: tuple[Mapping[str, JsonValue], ...] + rows: int | str + statistics: TraceQueryStatistics + + +class TraceQueryTable(BaseModel): + model_config = ConfigDict(frozen=True) + name: str + columns: tuple[TraceQueryColumn, ...] + + +class TraceQueryNormalizedField(BaseModel): + model_config = ConfigDict(frozen=True) + table: str + name: str + column: str + type: str + meaning: str + + +class TraceQueryMetadataField(BaseModel): + model_config = ConfigDict(frozen=True) + path: tuple[str | int, ...] + types: tuple[str, ...] + expression: str + + +class TraceQueryMetadata(BaseModel): + model_config = ConfigDict(frozen=True) + table: str + column: str + fields: tuple[TraceQueryMetadataField, ...] + sampled_rows: int + invalid_json_rows: int + truncated: bool + sample_sql: str + scope: str + error: str | None = None + + +class TraceQueryAttributeField(BaseModel): + model_config = ConfigDict(frozen=True) + key: str + type: str + expression: str + + +class TraceQueryAttributes(BaseModel): + model_config = ConfigDict(frozen=True) + table: str + column: str + fields: tuple[TraceQueryAttributeField, ...] + truncated: bool + discovery_sql: str + scope: str + error: str | None = None + + +class TraceQueryRelationship(BaseModel): + model_config = ConfigDict(frozen=True) + left: str + right: str + additional_predicates: str + meaning: str + + +class TraceQueryExample(BaseModel): + model_config = ConfigDict(frozen=True) + name: str + sql: str + + +class TraceQueryHelp(BaseModel): + model_config = ConfigDict(frozen=True) + dialect: str + access: str + response: str + tables: tuple[TraceQueryTable, ...] + normalized_fields: tuple[TraceQueryNormalizedField, ...] + metadata: TraceQueryMetadata + attributes: tuple[TraceQueryAttributes, ...] + relationships: tuple[TraceQueryRelationship, ...] + examples: tuple[TraceQueryExample, ...] + gotchas: tuple[str, ...] + guide: str diff --git a/litellm/rust_bridge/traces.py b/litellm/rust_bridge/traces.py index 8599d4cb6b8..2ed2df4e55e 100644 --- a/litellm/rust_bridge/traces.py +++ b/litellm/rust_bridge/traces.py @@ -1,12 +1,32 @@ from collections.abc import Awaitable, Mapping, Sequence from dataclasses import dataclass -from types import MappingProxyType -from typing import Final, Literal, Protocol, TypedDict, cast +from typing import Final, Literal, Protocol, TypedDict, TypeVar, runtime_checkable -from pydantic import BaseModel, ConfigDict, Field, JsonValue, TypeAdapter +from pydantic import BaseModel, ConfigDict, Field, TypeAdapter, ValidationError from typing_extensions import ReadOnly from litellm.rust_bridge.loader import get_native_bridge +from litellm.rust_bridge.trace_queries import ( + LENS_AGENTS, + LENS_AVAILABILITY, + LENS_CONTENT, + LENS_EVIDENCE, + LENS_SAMPLE, + ActivityAvailability, + AgentRow, + CountRow, + ExecutionRow, + LensAccessParams, + LensContentParams, + LensEvidenceParams, + LensSampleParams, + ParamsT, + PartRow, + ReadQuery, + ReadQueryName, + RowT, +) +from litellm.rust_bridge.trace_query_responses import TraceQueryHelp, TraceSQLResponse class DecodedEvent(TypedDict): @@ -57,9 +77,6 @@ class DecodedSpan(TypedDict): consumed_attributes: ReadOnly[tuple[str, str]] -ReadQueryName = Literal["list_traces", "trace_spans", "span_detail", "span_error", "spend_by_response_ids"] - - class AdminQueryScope(TypedDict): kind: ReadOnly[Literal["admin"]] @@ -75,7 +92,14 @@ class KeyQueryScope(TypedDict): api_key_hash: ReadOnly[str] -QueryScope = AdminQueryScope | TeamQueryScope | KeyQueryScope +class LogQueryScope(TypedDict): + kind: ReadOnly[Literal["logs"]] + user_id: ReadOnly[str] + team_ids: ReadOnly[tuple[str, ...]] + api_key_hash: ReadOnly[str] + + +QueryScope = AdminQueryScope | TeamQueryScope | KeyQueryScope | LogQueryScope class NativeStore(Protocol): @@ -89,11 +113,12 @@ class NativeStore(Protocol): def query_help(self, scope: QueryScope, secret: str) -> Awaitable[str]: ... - def lens_query(self, name: str, parameters: Mapping[str, str | int | Sequence[str]]) -> Awaitable[str]: ... - - def query(self, name: ReadQueryName, parameters: Mapping[str, str | int | Sequence[str]]) -> Awaitable[str]: ... + def query( + self, name: ReadQueryName, parameters: Mapping[str, str | int | float | Sequence[str]] + ) -> Awaitable[str]: ... +@runtime_checkable class NativeTraces(Protocol): NativeTraceConfig: type["NativeConfig"] NativeTraceStorage: type[NativeStore] @@ -109,13 +134,14 @@ class NativeTraces(Protocol): def trace_normalized_field_definitions(self) -> list[dict[str, str]]: ... -class QueryResponse(BaseModel): - model_config = ConfigDict(frozen=True) - data: list[dict[str, JsonValue]] - - -QUERY_PARAMETERS: Final = TypeAdapter(dict[str, str | int | list[str]]) +QUERY_PARAMETERS: Final = TypeAdapter(dict[str, str | int | float | list[str]]) _FIELD_DEFINITIONS_ADAPTER: Final = TypeAdapter(tuple[NormalizedFieldDefinition, ...]) +_SQL_RESPONSE: Final = TypeAdapter(TraceSQLResponse) +_HELP_RESPONSE: Final = TypeAdapter(TraceQueryHelp) +_ResponseT: Final = TypeVar("_ResponseT") +_NATIVE_ADAPTER: Final[TypeAdapter[NativeTraces]] = TypeAdapter( + NativeTraces, config=ConfigDict(arbitrary_types_allowed=True) +) class NativeConfig(Protocol): @@ -133,7 +159,7 @@ def _native() -> NativeTraces: native: Final = get_native_bridge() if native is None: raise RuntimeError("Agent tracing requires the Rust extension") - return cast(NativeTraces, native) # cast-ok: the native extension is validated against this protocol at call sites + return _NATIVE_ADAPTER.validate_python(native) def decode_otlp(body: bytes, content_type: str | None) -> list[DecodedSpan]: @@ -156,6 +182,13 @@ def encode_error(message: str) -> bytes: return _native().trace_encode_error(message) +def _decode_query_response(adapter: TypeAdapter[_ResponseT], body: str) -> _ResponseT: + try: + return adapter.validate_json(body) + except ValidationError as error: + raise RuntimeError("Native trace query returned an invalid response") from error + + class ClickHouseStorage: def __init__(self, config: TraceStorageConfig) -> None: native: Final = _native() @@ -172,35 +205,30 @@ class ClickHouseStorage: async def insert_rows(self, table: str, rows: Sequence[Mapping[str, object]]) -> None: await self._native.insert_rows(table, rows) - async def query( - self, name: ReadQueryName, parameters: Mapping[str, object] | None = None - ) -> list[dict[str, JsonValue]]: - result: Final = await self._native.query( - name, QUERY_PARAMETERS.validate_python(parameters or MappingProxyType({})) - ) - return QueryResponse.model_validate_json(result).data + async def query(self, query: ReadQuery[ParamsT, RowT], parameters: ParamsT) -> tuple[RowT, ...]: + validated: Final = query.parameters.model_validate(parameters) + result: Final = await self._native.query(query.name, QUERY_PARAMETERS.validate_python(validated.model_dump())) + return _decode_query_response(query.response, result).data - async def query_sql(self, sql: str, scope: QueryScope, secret: str) -> str: - return await self._native.query_sql(sql, scope, secret) + async def query_sql(self, sql: str, scope: QueryScope, secret: str) -> TraceSQLResponse: + result: Final = await self._native.query_sql(sql, scope, secret) + return _decode_query_response(_SQL_RESPONSE, result) - async def query_help(self, scope: QueryScope, secret: str) -> str: - return await self._native.query_help(scope, secret) + async def query_help(self, scope: QueryScope, secret: str) -> TraceQueryHelp: + result: Final = await self._native.query_help(scope, secret) + return _decode_query_response(_HELP_RESPONSE, result) - async def _lens_query(self, name: str, parameters: Mapping[str, object]) -> list[dict[str, JsonValue]]: - result: Final = await self._native.lens_query(name, QUERY_PARAMETERS.validate_python(parameters)) - return QueryResponse.model_validate_json(result).data + async def lens_sample(self, parameters: LensSampleParams) -> tuple[ExecutionRow, ...]: + return await self.query(LENS_SAMPLE, parameters) - async def lens_sample(self, parameters: Mapping[str, object]) -> list[dict[str, JsonValue]]: - return await self._lens_query("sample", parameters) + async def lens_availability(self, parameters: LensAccessParams) -> tuple[ActivityAvailability, ...]: + return await self.query(LENS_AVAILABILITY, parameters) - async def lens_availability(self, parameters: Mapping[str, object]) -> list[dict[str, JsonValue]]: - return await self._lens_query("availability", parameters) + async def lens_agents(self, parameters: LensAccessParams) -> tuple[AgentRow, ...]: + return await self.query(LENS_AGENTS, parameters) - async def lens_agents(self, parameters: Mapping[str, object]) -> list[dict[str, JsonValue]]: - return await self._lens_query("agents", parameters) + async def lens_content(self, parameters: LensContentParams) -> tuple[PartRow, ...]: + return await self.query(LENS_CONTENT, parameters) - async def lens_content(self, parameters: Mapping[str, object]) -> list[dict[str, JsonValue]]: - return await self._lens_query("content", parameters) - - async def lens_evidence(self, parameters: Mapping[str, object]) -> list[dict[str, JsonValue]]: - return await self._lens_query("evidence", parameters) + async def lens_evidence(self, parameters: LensEvidenceParams) -> tuple[CountRow, ...]: + return await self.query(LENS_EVIDENCE, parameters) diff --git a/litellm/tracing/decode.py b/litellm/tracing/decode.py index 246a7cd3337..f7aa54e47cd 100644 --- a/litellm/tracing/decode.py +++ b/litellm/tracing/decode.py @@ -177,6 +177,7 @@ def _span_row(span: DecodedSpan) -> SpanRow: StatusMessage=span["status_message"] or _exception_message(span), TeamId="", ApiKeyHash="", + UserId="", ObservationType=normalized.observation_type, AgentName=normalized.agent_name, Framework=normalized.framework, diff --git a/litellm/tracing/receiver.py b/litellm/tracing/receiver.py index 9164e0722a3..c6f256d59ff 100644 --- a/litellm/tracing/receiver.py +++ b/litellm/tracing/receiver.py @@ -45,10 +45,11 @@ class TracingOverloadedError(RuntimeError): class Tenant: """Who sent the spans. Always taken from auth, never from span attributes.""" - def __init__(self, team_id: str, api_key_hash: str, org_id: str = "") -> None: + def __init__(self, team_id: str, api_key_hash: str, org_id: str = "", user_id: str = "") -> None: self.team_id = team_id self.api_key_hash = api_key_hash self.org_id = org_id + self.user_id = user_id def stamp(self, row: SpanRow) -> SpanRow: return self.stamp_rows((row,))[0] @@ -63,6 +64,7 @@ class Tenant: "litellm.team_id": self.team_id, "litellm.api_key_hash": self.api_key_hash, "litellm.org_id": self.org_id, + "litellm.user_id": self.user_id, } ) for identity, attributes in resources.items() @@ -75,6 +77,7 @@ class Tenant: **row, "TeamId": self.team_id, "ApiKeyHash": self.api_key_hash, + "UserId": self.user_id, "ResourceAttributes": resource, } return stamped diff --git a/litellm/tracing/store.py b/litellm/tracing/store.py index e45a18477c2..623e25849da 100644 --- a/litellm/tracing/store.py +++ b/litellm/tracing/store.py @@ -7,7 +7,7 @@ from collections.abc import Mapping, Sequence from datetime import datetime, timezone from itertools import chain from types import MappingProxyType -from typing import Any, Final +from typing import Annotated, Final, TypeAlias from pydantic import BaseModel, ConfigDict, Field, TypeAdapter @@ -16,6 +16,23 @@ from litellm.constants import AGENT_TRACING_LIST_PAGE_SIZE from litellm.integrations.clickhouse.schema import ( OTEL_TRACES_TABLE, ) +from litellm.rust_bridge.trace_queries import ( + LIST_TRACES, + SPAN_DETAIL, + SPAN_ERROR, + SPEND_BY_RESPONSE_IDS, + TRACE_IDENTITY, + TRACE_SPANS, + ListTracesParams, + ListTracesRow, + SpanDetailParams, + SpanErrorParams, + SpendByResponseIdsParams, + SpendRow, + TraceIdentityParams, + TraceSpansParams, + TraceSpansRow, +) from litellm.rust_bridge.traces import ClickHouseStorage from litellm.tracing.types import ( AgentNode, @@ -33,7 +50,11 @@ from litellm.tracing.ui_format import to_ui_content NANOS_PER_MS: Final = 1_000_000 SPEND_WINDOW_MS: Final = 30 * 60 * 1000 -_STATUS: Final = MappingProxyType({"STATUS_CODE_OK": "ok", "STATUS_CODE_ERROR": "error"}) +_STATUS: Final[Mapping[str, SpanStatus]] = MappingProxyType({"STATUS_CODE_OK": "ok", "STATUS_CODE_ERROR": "error"}) + + +TraceCursorParts: TypeAlias = tuple[Annotated[int, Field(gt=0)], Annotated[str, Field(min_length=1)]] +_TRACE_CURSOR: Final[TypeAdapter[TraceCursorParts]] = TypeAdapter(TraceCursorParts) class _ErrorCursor(BaseModel): @@ -42,43 +63,33 @@ class _ErrorCursor(BaseModel): version: str = Field(pattern=r"^[A-F0-9]{64}$") -class _ErrorRow(BaseModel): - model_config = ConfigDict(frozen=True) - span_id: str - message: str - total_chars: int - version: str +class AmbiguousTraceError(ValueError): + pass -class _SpendRow(BaseModel): - model_config = ConfigDict(frozen=True) - - request_id: str - response_id: str - team_id: str - api_key: str - spend: float - start_ms: int - - -_SPEND_ROWS: Final = TypeAdapter(tuple[_SpendRow, ...]) - - -def _spend_for(request_id: str, team_id: str, api_key_hash: str, rows: Sequence[_SpendRow]) -> float | None: +def _spend_for( + request_id: str, team_id: str, api_key_hash: str, user_id: str, rows: Sequence[SpendRow] +) -> float | None: + if not request_id: + return None matches: Final = tuple( - row for row in rows if row.response_id == request_id and row.team_id == team_id and row.api_key == api_key_hash + row + for row in rows + if row.response_id == request_id + and row.team_id == team_id + and (bool(user_id and row.user == user_id) or bool(api_key_hash and row.api_key == api_key_hash)) ) return matches[0].spend if len(matches) == 1 else None def _trace_spend( - request_ids: Sequence[str], team_id: str, api_key_hash: str, rows: Sequence[_SpendRow] + request_ids: Sequence[str], team_id: str, api_key_hash: str, user_id: str, rows: Sequence[SpendRow] ) -> float | None: - ids: Final = frozenset(request_id for request_id in request_ids if request_id) - costs: Final = tuple(_spend_for(request_id, team_id, api_key_hash, rows) for request_id in ids) - return ( - sum(cost for cost in costs if cost is not None) if costs and all(cost is not None for cost in costs) else None - ) + if not request_ids or any(not request_id for request_id in request_ids): + return None + ids: Final = frozenset(request_ids) + costs: Final = tuple(_spend_for(request_id, team_id, api_key_hash, user_id, rows) for request_id in ids) + return sum(cost for cost in costs if cost is not None) if all(cost is not None for cost in costs) else None def encode_cursor(start_ms: int, trace_id: str) -> str: @@ -89,18 +100,7 @@ def decode_cursor(cursor: str | None) -> tuple[int, str]: if not cursor: return 0, "" try: - value: Final = json.loads(base64.b64decode(cursor, altchars=b"-_", validate=True)) - if ( - not isinstance(value, list) - or len(value) != 2 - or not isinstance(value[0], int) - or isinstance(value[0], bool) - or value[0] <= 0 - or not isinstance(value[1], str) - or not value[1] - ): - raise ValueError("Invalid trace cursor") - return value[0], value[1] + return _TRACE_CURSOR.validate_json(base64.b64decode(cursor, altchars=b"-_", validate=True), strict=True) except (ValueError, UnicodeError, binascii.Error) as error: raise ValueError("Invalid trace cursor") from error @@ -113,7 +113,7 @@ def _status(code: str) -> SpanStatus: return _STATUS.get(code, "unset") -def trace_summary_from_row(row: dict[str, Any], spend_rows: Sequence[_SpendRow] = ()) -> TraceSummary: +def trace_summary_from_row(row: ListTracesRow, spend_rows: Sequence[SpendRow] = ()) -> TraceSummary: return TraceSummary( trace_id=row["trace_id"], trace_ref=row.get("trace_ref", ""), @@ -135,12 +135,16 @@ def trace_summary_from_row(row: dict[str, Any], spend_rows: Sequence[_SpendRow] output_tokens=int(row["output_tokens"]), models=tuple(row["models"]), spend=_trace_spend( - row.get("request_ids") or (), row.get("team_id") or "", row.get("api_key_hash") or "", spend_rows + row.get("request_ids") or (), + row.get("team_id") or "", + row.get("api_key_hash") or "", + row.get("user_id") or "", + spend_rows, ), ) -def span_from_row(row: dict[str, Any], trace_start_ns: int, spend_rows: Sequence[_SpendRow] = ()) -> Span: +def span_from_row(row: TraceSpansRow, trace_start_ns: int, spend_rows: Sequence[SpendRow] = ()) -> Span: return Span( span_id=row["span_id"], parent_span_id=row["parent_span_id"] or None, @@ -159,7 +163,13 @@ def span_from_row(row: dict[str, Any], trace_start_ns: int, spend_rows: Sequence output_tokens=int(row["output_tokens"]), litellm_request_id=row["litellm_request_id"] or None, spend=( - _spend_for(row["litellm_request_id"], row.get("team_id") or "", row.get("api_key_hash") or "", spend_rows) + _spend_for( + row["litellm_request_id"], + row.get("team_id") or "", + row.get("api_key_hash") or "", + row.get("user_id") or "", + spend_rows, + ) if row["litellm_request_id"] else None ), @@ -222,22 +232,15 @@ def agent_nodes(spans: Sequence[Span]) -> tuple[AgentNode, ...]: def _agent_spend(spans: Sequence[Span], agent_name: str) -> float | None: - by_request: Final = MappingProxyType( - { - span["litellm_request_id"]: span["spend"] - for span in spans - if span["type"] == "llm" and span["agent"] == agent_name and span["litellm_request_id"] - } - ) - return ( - sum(cost for cost in by_request.values() if cost is not None) - if by_request and all(cost is not None for cost in by_request.values()) - else None - ) + llm_spans: Final = tuple(span for span in spans if span["type"] == "llm" and span["agent"] == agent_name) + if any(not span["litellm_request_id"] or span["spend"] is None for span in llm_spans): + return None + by_request: Final = MappingProxyType({span["litellm_request_id"]: span["spend"] for span in llm_spans}) + return sum(cost for cost in by_request.values() if cost is not None) if by_request else None def trace_from_rows( - trace_id: str, rows: list[dict[str, Any]], trace_ref: str = "", spend_rows: Sequence[_SpendRow] = () + trace_id: str, rows: Sequence[TraceSpansRow], trace_ref: str = "", spend_rows: Sequence[SpendRow] = () ) -> Trace | None: if not rows: return None @@ -269,9 +272,10 @@ def trace_from_rows( output_tokens=sum(s["output_tokens"] for s in spans), models=tuple(sorted(frozenset(s["model"] for s in llm_spans if s["model"]))), spend=_trace_spend( - tuple(row["litellm_request_id"] for row in rows), + tuple(row["litellm_request_id"] for row in rows if row["type"] == "llm" or row["litellm_request_id"]), rows[0].get("team_id") or "", rows[0].get("api_key_hash") or "", + rows[0].get("user_id") or "", spend_rows, ), ), @@ -289,28 +293,34 @@ class TraceStore: async def insert_spans(self, rows: Sequence[SpanRow]) -> None: await self.storage.insert_rows(OTEL_TRACES_TABLE, tuple(rows)) + async def _reference(self, trace_id: str, scope: TraceScope, trace_ref: str) -> str | None: + if trace_ref: + return trace_ref + identities: Final = await self.storage.query(TRACE_IDENTITY, TraceIdentityParams(**scope, trace_id=trace_id)) + if len(identities) > 1: + raise AmbiguousTraceError("Multiple traces have this ID; provide trace_ref") + return identities[0].trace_ref if identities else None + async def _spend_rows( self, scope: TraceScope, request_ids: Sequence[str], start_ms: int, end_ms: int - ) -> tuple[_SpendRow, ...]: + ) -> tuple[SpendRow, ...]: ids: Final = tuple(sorted(frozenset(request_id for request_id in request_ids if request_id))) if not ids: return () try: rows: Final = await self.storage.query( - "spend_by_response_ids", - MappingProxyType( - { - **scope, - "response_ids": ids, - "start_ms": start_ms - SPEND_WINDOW_MS, - "end_ms": end_ms + SPEND_WINDOW_MS, - } + SPEND_BY_RESPONSE_IDS, + SpendByResponseIdsParams( + **scope, + response_ids=ids, + start_ms=start_ms - SPEND_WINDOW_MS, + end_ms=end_ms + SPEND_WINDOW_MS, ), ) except RuntimeError as error: verbose_logger.warning("Trace spend lookup unavailable: %s", error) return () - return _SPEND_ROWS.validate_python(rows) + return tuple(rows) async def list_traces( self, @@ -321,17 +331,15 @@ class TraceStore: limit: int = AGENT_TRACING_LIST_PAGE_SIZE, ) -> TracePage: cursor_ms, cursor_trace_id = decode_cursor(cursor) - rows = await self.storage.query( - "list_traces", - MappingProxyType( - { - **scope, - "start_ms": start_ms, - "end_ms": end_ms, - "cursor_ms": cursor_ms, - "cursor_trace_id": cursor_trace_id, - "limit": limit, - } + rows: Final = await self.storage.query( + LIST_TRACES, + ListTracesParams( + **scope, + start_ms=start_ms, + end_ms=end_ms, + cursor_ms=cursor_ms, + cursor_trace_id=cursor_trace_id, + limit=limit, ), ) spend_rows: Final = await self._spend_rows( @@ -340,12 +348,17 @@ class TraceStore: min((int(row["start_ms"]) for row in rows), default=start_ms), max((int(row["start_ms"]) + int(row["duration_ms"]) for row in rows), default=end_ms), ) - next_cursor = encode_cursor(int(rows[-1]["start_ms"]), rows[-1]["trace_ref"]) if len(rows) == limit else None + next_cursor: Final = ( + encode_cursor(int(rows[-1]["start_ms"]), rows[-1]["trace_ref"]) if len(rows) == limit else None + ) return TracePage(data=tuple(trace_summary_from_row(r, spend_rows) for r in rows), next_cursor=next_cursor) async def get_trace(self, trace_id: str, scope: TraceScope, trace_ref: str = "") -> Trace | None: - rows = await self.storage.query( - "trace_spans", MappingProxyType({**scope, "trace_id": trace_id, "trace_ref": trace_ref}) + reference: Final = await self._reference(trace_id, scope, trace_ref) + if reference is None: + return None + rows: Final = await self.storage.query( + TRACE_SPANS, TraceSpansParams(**scope, trace_id=trace_id, trace_ref=reference) ) spend_rows: Final = await self._spend_rows( scope, @@ -353,12 +366,15 @@ class TraceStore: min((int(row["start_ns"]) // NANOS_PER_MS for row in rows), default=0), max(((int(row["start_ns"]) + int(row["duration_ns"])) // NANOS_PER_MS for row in rows), default=0), ) - return trace_from_rows(trace_id, rows, trace_ref, spend_rows) + return trace_from_rows(trace_id, rows, reference, spend_rows) async def get_span(self, trace_id: str, span_id: str, scope: TraceScope, trace_ref: str = "") -> SpanDetail | None: - rows = await self.storage.query( - "span_detail", - MappingProxyType({**scope, "trace_id": trace_id, "span_id": span_id, "trace_ref": trace_ref}), + reference: Final = await self._reference(trace_id, scope, trace_ref) + if reference is None: + return None + rows: Final = await self.storage.query( + SPAN_DETAIL, + SpanDetailParams(**scope, trace_id=trace_id, span_id=span_id, trace_ref=reference), ) if not rows: return None @@ -368,7 +384,7 @@ class TraceStore: output=rows[0]["output"], input_ui=to_ui_content(rows[0]["input"]), output_ui=to_ui_content(rows[0]["output"]), - attributes=rows[0]["attributes"], + attributes=dict(rows[0]["attributes"]), ) async def get_span_error( @@ -382,22 +398,23 @@ class TraceStore: ) except (ValueError, binascii.Error) as error: raise ValueError("Invalid diagnostic cursor") from error + reference: Final = await self._reference(trace_id, scope, trace_ref) + if reference is None: + return None rows: Final = await self.storage.query( - "span_error", - MappingProxyType( - { - **scope, - "trace_id": trace_id, - "span_id": span_id, - "trace_ref": trace_ref, - "error_offset": position.offset if position else 0, - "error_version": position.version if position else "", - } + SPAN_ERROR, + SpanErrorParams( + **scope, + trace_id=trace_id, + span_id=span_id, + trace_ref=reference, + error_offset=position.offset if position else 0, + error_version=position.version if position else "", ), ) if not rows: return None - row: Final = _ErrorRow.model_validate(rows[0]) + row: Final = rows[0] offset: Final = (position.offset if position else 0) + len(row.message) continuation: Final = _ErrorCursor(offset=offset, version=row.version) if offset < row.total_chars else None return SpanErrorPage( diff --git a/litellm/tracing/types.py b/litellm/tracing/types.py index 28830ec5225..15b28293590 100644 --- a/litellm/tracing/types.py +++ b/litellm/tracing/types.py @@ -103,8 +103,10 @@ class SpanErrorPage(TypedDict): class TraceScope(TypedDict): - """Who is asking. Empty team_ids = all teams (admins only).""" + """Authenticated request-log visibility.""" + all_teams: ReadOnly[Literal[0, 1]] + user_id: ReadOnly[str] team_ids: ReadOnly[tuple[str, ...]] api_key_hash: ReadOnly[str] @@ -129,6 +131,7 @@ class SpanRow(TypedDict): StatusMessage: ReadOnly[str] TeamId: ReadOnly[str] ApiKeyHash: ReadOnly[str] + UserId: ReadOnly[str] ObservationType: SpanType AgentName: str Framework: ReadOnly[str] diff --git a/tests/test_litellm/tracing/test_receiver.py b/tests/test_litellm/tracing/test_receiver.py index 0d9aa8d034d..b8a92606417 100644 --- a/tests/test_litellm/tracing/test_receiver.py +++ b/tests/test_litellm/tracing/test_receiver.py @@ -20,7 +20,7 @@ from litellm.tracing.types import TraceScope pytestmark = pytest.mark.requires_rust_extension FIXTURE = Path(__file__).parent / "fixtures" / "langsmith_deep_agent_export.json" -TENANT = Tenant(team_id="team-research", api_key_hash="hashed-key", org_id="org-1") +TENANT = Tenant(team_id="team-research", api_key_hash="hashed-key", org_id="org-1", user_id="user-1") def _fake_store() -> MagicMock: @@ -38,6 +38,7 @@ def _spoofed_export() -> bytes: KeyValue(key="service.name", value=AnyValue(string_value="svc")), KeyValue(key="litellm.team_id", value=AnyValue(string_value="someone-elses-team")), KeyValue(key="litellm.api_key_hash", value=AnyValue(string_value="someone-elses-key")), + KeyValue(key="litellm.user_id", value=AnyValue(string_value="someone-elses-user")), ] ) return ExportTraceServiceRequest(resource_spans=[resource_spans]).SerializeToString() @@ -64,6 +65,8 @@ async def test_ingest_overwrites_client_supplied_tenant_attributes(): assert row["TeamId"] == "team-research" assert row["ResourceAttributes"]["litellm.team_id"] == "team-research" assert row["ResourceAttributes"]["litellm.api_key_hash"] == "hashed-key" + assert row["UserId"] == TENANT.user_id + assert row["ResourceAttributes"]["litellm.user_id"] == TENANT.user_id @pytest.mark.asyncio diff --git a/tests/test_litellm/tracing/test_store.py b/tests/test_litellm/tracing/test_store.py index 997a34c0e68..0c1820d7c5f 100644 --- a/tests/test_litellm/tracing/test_store.py +++ b/tests/test_litellm/tracing/test_store.py @@ -2,11 +2,19 @@ Tests for the pure read-side helpers in litellm/tracing/store.py (no ClickHouse needed). """ -from typing import Any +from typing import Any, Final from unittest.mock import AsyncMock, MagicMock import pytest +from litellm.rust_bridge.trace_queries import ( + LIST_TRACES, + TRACE_SPANS, + SPAN_ERROR, + SpanErrorParams, + SpanErrorRow, + SpendRow, +) from litellm.tracing.store import ( TraceStore, agent_nodes, @@ -48,6 +56,11 @@ def _row( "input_tokens": 0, "output_tokens": 0, "litellm_request_id": "", + "team_id": "", + "api_key_hash": "", + "user_id": "", + "status_message": "", + "error_truncated": False, **extra, } @@ -245,7 +258,8 @@ def test_trace_frameworks_are_the_sorted_distinct_span_frameworks(): _row("tool", "root", "Bash", "tool", "claude-code", framework="claude-code"), _row("other", "root", "step", "chain", "claude-code", framework=""), ] - trace = trace_from_rows("t1", rows) + validated_rows: Final = TRACE_SPANS.response.validate_python({"data": rows}).data + trace = trace_from_rows("t1", validated_rows) assert trace is not None assert trace["summary"]["frameworks"] == ("claude-agent-sdk", "claude-code") spans = {span["span_id"]: span for span in trace["spans"]} @@ -278,26 +292,39 @@ def test_invalid_cursor_is_rejected(cursor): def test_trace_summary_from_row(): - summary = trace_summary_from_row( + rows: Final = LIST_TRACES.response.validate_python( { - "trace_id": "t1", - "name": "deep_research_agent", - "service": "agent-demo", - "input_preview": "hi", - "start_ms": 1790742989377, - "duration_ms": 51385, - "status": "STATUS_CODE_OK", - "span_count": "126", - "agent_count": "2", - "llm_calls": "7", - "tool_calls": "26", - "error_count": "1", - "input_tokens": "30175", - "output_tokens": "2620", - "models": ["claude-sonnet-4-5"], - "frameworks": ["claude-agent-sdk", "claude-code"], + "data": [ + { + "trace_id": "t1", + "trace_ref": "ref", + "team_id": "team", + "api_key_hash": "key", + "user_id": "owner", + "agent_invocations": 2, + "agent_names": ["deep_research_agent"], + "request_ids": [], + "name": "deep_research_agent", + "service": "agent-demo", + "input_preview": "hi", + "start_ms": 1790742989377, + "duration_ms": 51385, + "status": "STATUS_CODE_OK", + "span_count": "126", + "agent_count": "2", + "llm_calls": "7", + "tool_calls": "26", + "error_count": "1", + "input_tokens": "30175", + "output_tokens": "2620", + "models": ["claude-sonnet-4-5"], + "frameworks": ["claude-agent-sdk", "claude-code"], + } + ] } - ) + ).data + summary: Final = trace_summary_from_row(rows[0]) + assert summary["agent_names"] == ("deep_research_agent",) assert summary["frameworks"] == ("claude-agent-sdk", "claude-code") assert summary["status"] == "ok" assert (summary["span_count"], summary["error_count"]) == (126, 1) @@ -327,18 +354,18 @@ async def test_list_traces_sets_next_cursor_on_full_page(): } client.query = AsyncMock(return_value=[row, {**row, "trace_id": "t1", "trace_ref": "ref1", "start_ms": 900}]) store = TraceStore(client) - scope: TraceScope = {"team_ids": ("team-a",), "api_key_hash": ""} + scope: TraceScope = {"all_teams": 0, "user_id": "", "team_ids": ("team-a",), "api_key_hash": ""} page = await store.list_traces(scope, 0, 2000, limit=2) assert [t["trace_id"] for t in page["data"]] == ["t2", "t1"] assert page["next_cursor"] is not None assert decode_cursor(page["next_cursor"]) == (900, "ref1") params = client.query.call_args.args[1] - assert params["team_ids"] == ("team-a",) and params["limit"] == 2 and params["cursor_ms"] == 0 + assert params.team_ids == ("team-a",) and params.limit == 2 and params.cursor_ms == 0 page = await store.list_traces(scope, 0, 2000, cursor=page["next_cursor"], limit=3) assert page["next_cursor"] is None - assert client.query.call_args.args[1]["cursor_trace_id"] == "ref1" + assert client.query.call_args.args[1].cursor_trace_id == "ref1" @pytest.mark.asyncio @@ -346,13 +373,13 @@ async def test_get_span_not_found_and_found(): client = MagicMock() client.query = AsyncMock(return_value=[]) store = TraceStore(client) - scope: TraceScope = {"team_ids": (), "api_key_hash": ""} - assert await store.get_span("t", "s", scope) is None + scope: TraceScope = {"all_teams": 1, "user_id": "", "team_ids": (), "api_key_hash": ""} + assert await store.get_span("t", "s", scope, "ref") is None stored_input = '[{"role": "user", "content": "hi"}]' client.query = AsyncMock( return_value=[{"span_id": "s", "input": stored_input, "output": '{"ok": true}', "attributes": {"k": "v"}}] ) - assert await store.get_span("t", "s", scope) == { + assert await store.get_span("t", "s", scope, "ref") == { "span_id": "s", "input": stored_input, "output": '{"ok": true}', @@ -389,24 +416,24 @@ async def test_trace_cost_is_scoped_and_counts_repeated_request_once(): }, { "request_id": "request-other-key", - "response_id": "response-1", + "response_id": "unrelated-response", "team_id": "team-a", "api_key": "key-c", "spend": 50.0, "start_ms": T0 // MS, }, ] - client.query = AsyncMock(side_effect=[spans, spend]) + client.query = AsyncMock(side_effect=[spans, tuple(SpendRow.model_validate({**row, "user": ""}) for row in spend)]) store = TraceStore(client) - scope: TraceScope = {"team_ids": ("team-a",), "api_key_hash": ""} + scope: TraceScope = {"all_teams": 0, "user_id": "", "team_ids": ("team-a",), "api_key_hash": ""} - trace = await store.get_trace("trace-1", scope) + trace = await store.get_trace("trace-1", scope, "ref") assert trace is not None assert trace["summary"]["spend"] == 0.25 assert trace["agents"][0]["spend"] == 0.25 assert [span["spend"] for span in trace["spans"]] == [None, 0.25, 0.25] - assert [call.args[0] for call in client.query.await_args_list] == ["trace_spans", "spend_by_response_ids"] + assert [call.args[0].name for call in client.query.await_args_list] == ["trace_spans", "spend_by_response_ids"] @pytest.mark.asyncio @@ -445,13 +472,13 @@ async def test_run_list_uses_matching_spend_and_leaves_missing_cost_unavailable( "start_ms": 1000, } ] - client.query = AsyncMock(side_effect=[rows, spend]) - scope: TraceScope = {"team_ids": ("team-a",), "api_key_hash": ""} + client.query = AsyncMock(side_effect=[rows, tuple(SpendRow.model_validate({**row, "user": ""}) for row in spend)]) + scope: TraceScope = {"all_teams": 0, "user_id": "", "team_ids": ("team-a",), "api_key_hash": ""} page = await TraceStore(client).list_traces(scope, 0, 2000) assert [run["spend"] for run in page["data"]] == [0.25, None] - assert [call.args[0] for call in client.query.await_args_list] == ["list_traces", "spend_by_response_ids"] + assert [call.args[0].name for call in client.query.await_args_list] == ["list_traces", "spend_by_response_ids"] @pytest.mark.asyncio @@ -469,11 +496,11 @@ async def test_ambiguous_cache_response_id_keeps_cost_unavailable(): } for request_id, cost in (("response-1", 0.25), ("response-1_cache_hit123", 0.0)) ] - client.query = AsyncMock(side_effect=[[span], spend]) + client.query = AsyncMock(side_effect=[[span], tuple(SpendRow.model_validate({**row, "user": ""}) for row in spend)]) store = TraceStore(client) - scope: TraceScope = {"team_ids": ("",), "api_key_hash": "key-a"} + scope: TraceScope = {"all_teams": 0, "user_id": "", "team_ids": (), "api_key_hash": "key-a"} - trace = await store.get_trace("trace-1", scope) + trace = await store.get_trace("trace-1", scope, "ref") assert trace is not None assert trace["summary"]["spend"] is None @@ -489,12 +516,12 @@ async def test_diagnostic_continuation_preserves_content_version_scope_and_unico client = MagicMock() client.query = AsyncMock( side_effect=[ - [{"span_id": "span-1", "message": "first 🧪", "total_chars": len(message), "version": version}], - [{"span_id": "span-1", "message": "\nlast", "total_chars": len(message), "version": version}], + [SpanErrorRow(span_id="span-1", message="first 🧪", total_chars=len(message), version=version)], + [SpanErrorRow(span_id="span-1", message="\nlast", total_chars=len(message), version=version)], ] ) store = TraceStore(client) - scope = {"team_ids": ("team-a",), "api_key_hash": "key-a"} + scope = {"all_teams": 0, "user_id": "", "team_ids": ("team-a",), "api_key_hash": "key-a"} first = await store.get_span_error("trace-1", "span-1", scope, "scoped-run") assert first is not None and first["next_cursor"] is not None last = await store.get_span_error("trace-1", "span-1", scope, "scoped-run", first["next_cursor"]) @@ -502,15 +529,15 @@ async def test_diagnostic_continuation_preserves_content_version_scope_and_unico assert first["message"] + last["message"] == message assert last["next_cursor"] is None client.query.assert_awaited_with( - "span_error", - { + SPAN_ERROR, + SpanErrorParams( **scope, - "trace_id": "trace-1", - "span_id": "span-1", - "trace_ref": "scoped-run", - "error_offset": len(first["message"]), - "error_version": version, - }, + trace_id="trace-1", + span_id="span-1", + trace_ref="scoped-run", + error_offset=len(first["message"]), + error_version=version, + ), ) @@ -520,5 +547,123 @@ async def test_malformed_diagnostic_cursor_never_reaches_storage(cursor): client = MagicMock() client.query = AsyncMock() with pytest.raises(ValueError, match="Invalid diagnostic cursor"): - await TraceStore(client).get_span_error("trace", "span", {"team_ids": (), "api_key_hash": ""}, cursor=cursor) + await TraceStore(client).get_span_error( + "trace", "span", {"all_teams": 1, "user_id": "", "team_ids": (), "api_key_hash": ""}, cursor=cursor + ) client.query.assert_not_awaited() + + +@pytest.mark.parametrize( + ("trace_team", "trace_user", "trace_key", "spend_team", "spend_user", "spend_key", "known"), + ( + ("team", "", "export", "team", "", "request", False), + ("team", "", "export", "team", "", "export", True), + ("", "user", "export", "", "user", "request", True), + ("", "", "key", "", "", "key", True), + ("team", "user", "key", "other-team", "user", "key", False), + ("", "user", "export", "", "other-user", "request", False), + ("", "", "export", "", "", "request", False), + ("", "", "", "", "", "", False), + ("", "", "master", "", "", "", False), + ), +) +def test_cost_attribution_requires_shared_ownership_after_visibility( + trace_team: str, + trace_user: str, + trace_key: str, + spend_team: str, + spend_user: str, + spend_key: str, + known: bool, +) -> None: + rows: Final = ( + _row("agent", "", "agent", "agent", "agent", team_id=trace_team, user_id=trace_user, api_key_hash=trace_key), + _llm_row("llm", "agent", "agent", "response", team_id=trace_team, user_id=trace_user, api_key_hash=trace_key), + ) + spend: Final = SpendRow( + request_id="request", + response_id="response", + team_id=spend_team, + user=spend_user, + api_key=spend_key, + spend=0.25, + start_ms=T0 // MS, + ) + trace: Final = trace_from_rows("trace", rows, "visible-reference", (spend,)) + assert trace is not None + expected: Final = spend.spend if known else None + assert trace["summary"]["spend"] == expected + assert trace["agents"][0]["spend"] == expected + assert trace["spans"][1]["spend"] == expected + summary: Final = trace_summary_from_row( + { + "trace_id": "trace", + "team_id": trace_team, + "user_id": trace_user, + "api_key_hash": trace_key, + "request_ids": ("response",), + "name": "agent", + "service": "service", + "input_preview": "", + "start_ms": T0 // MS, + "duration_ms": 10, + "status": "STATUS_CODE_OK", + "span_count": 2, + "agent_count": 1, + "llm_calls": 1, + "tool_calls": 0, + "input_tokens": 0, + "output_tokens": 0, + "models": (), + }, + (spend,), + ) + assert summary["spend"] == expected + + +@pytest.mark.parametrize("failure", ("missing_id", "missing_spend", "duplicate_spend")) +def test_incomplete_llm_cost_never_becomes_a_partial_trace_or_agent_total(failure: str) -> None: + second_id: Final = "" if failure == "missing_id" else "second" + rows: Final = ( + _row("agent", "", "agent", "agent", "agent", team_id="team", api_key_hash="export"), + _llm_row("first", "agent", "agent", "first", team_id="team", api_key_hash="export"), + _llm_row("second", "agent", "agent", second_id, team_id="team", api_key_hash="export"), + ) + first: Final = SpendRow( + request_id="first", + response_id="first", + team_id="team", + user="", + api_key="export", + spend=0.25, + start_ms=0, + ) + second: Final = first.model_copy(update={"request_id": "second", "response_id": "second"}) + spend: Final = ( + (first, second, second.model_copy(update={"request_id": "duplicate"})) + if failure == "duplicate_spend" + else (first,) + ) + trace: Final = trace_from_rows("trace", rows, "ref", spend) + assert trace is not None + assert trace["spans"][1]["spend"] == first.spend + assert trace["spans"][2]["spend"] is None + assert trace["summary"]["spend"] is None + assert trace["agents"][0]["spend"] is None + + +@pytest.mark.asyncio +async def test_trace_id_collision_requires_a_visible_reference_before_reading_content() -> None: + from litellm.rust_bridge.trace_queries import TraceIdentityRow + from litellm.tracing.store import AmbiguousTraceError + + storage: Final = MagicMock() + storage.query = AsyncMock(return_value=(TraceIdentityRow(trace_ref="first"), TraceIdentityRow(trace_ref="second"))) + store: Final = TraceStore(storage) + scope: Final[TraceScope] = {"all_teams": 1, "user_id": "", "team_ids": (), "api_key_hash": ""} + with pytest.raises(AmbiguousTraceError, match="provide trace_ref"): + await store.get_trace("shared-id", scope) + with pytest.raises(AmbiguousTraceError, match="provide trace_ref"): + await store.get_span("shared-id", "span", scope) + with pytest.raises(AmbiguousTraceError, match="provide trace_ref"): + await store.get_span_error("shared-id", "span", scope) diff --git a/tests/test_litellm_rust/test_traces.py b/tests/test_litellm_rust/test_traces.py index efc0a44f311..264f489520d 100644 --- a/tests/test_litellm_rust/test_traces.py +++ b/tests/test_litellm_rust/test_traces.py @@ -7,8 +7,15 @@ from typing import Final from urllib.parse import parse_qs, urlsplit import pytest +from pydantic import JsonValue from litellm.rust_bridge._native import NativeTraceConfig, NativeTraceStorage, trace_decode_otlp +from litellm.rust_bridge.trace_queries import ( + TRACE_SPANS, + ActivityAvailability, + LensAccessParams, + TraceSpansParams, +) from litellm.rust_bridge.traces import ( ClickHouseStorage, NormalizedSpan, @@ -28,15 +35,47 @@ def _native_storage(database: str, url: str, retention_days: int = 14) -> Native return NativeTraceStorage(NativeTraceConfig(database, url, retention_days)) +@pytest.fixture +def span_row() -> dict[str, JsonValue]: + return { + "span_id": "span-1", + "parent_span_id": "", + "name": "root", + "type": "agent", + "agent": "", + "status": "STATUS_CODE_OK", + "status_message": "", + "error_truncated": 0, + "start_ns": "1000000000", + "duration_ns": "1000", + "service": "test", + "input_preview": "hello", + "model": "", + "input_tokens": 0, + "output_tokens": 0, + "litellm_request_id": "", + "team_id": "", + "api_key_hash": "", + "user_id": "", + } + + +@pytest.fixture +def span_params() -> dict[str, str | int | list[str]]: + return {"trace_id": "trace-1", "trace_ref": "", "all_teams": 1, "user_id": "", "team_ids": [], "api_key_hash": ""} + + @pytest.mark.asyncio -async def test_trace_reader_projects_connection_and_parameters(recording_server: RecordingServer) -> None: - recording_server.enqueue(ResponseSpec(body={"data": [{"trace_id": "trace-1"}]})) +async def test_trace_reader_projects_connection_and_parameters( + recording_server: RecordingServer, span_row: dict[str, JsonValue], span_params: dict[str, str | int | list[str]] +) -> None: + recording_server.enqueue(ResponseSpec(body={"data": [span_row]})) url: Final = recording_server.base_url.replace("http://", "http://reader:p%40ss%2Fword%25@") storage: Final = _native_storage("trace_test", url + "?database=wrong") - rows: Final = json.loads(await storage.query("trace_spans", {"trace_id": "trace-1"})) + rows: Final = json.loads(await storage.query("trace_spans", span_params)) request: Final = recording_server.requests[0] parameters: Final = parse_qs(urlsplit(request.path).query) - assert rows == {"data": [{"trace_id": "trace-1"}]} + assert rows == {"data": [span_row]} assert b"o.TraceId = {trace_id:String}" in request.raw_body assert parameters["database"] == ["trace_test"] assert parameters["param_trace_id"] == ["trace-1"] @@ -47,11 +86,13 @@ async def test_trace_reader_projects_connection_and_parameters(recording_server: @pytest.mark.asyncio -async def test_trace_reader_rejects_success_status_with_embedded_error(recording_server: RecordingServer) -> None: +async def test_trace_reader_rejects_success_status_with_embedded_error( + recording_server: RecordingServer, span_params: dict[str, str | int | list[str]] +) -> None: recording_server.enqueue(ResponseSpec(body={"data": [], "exception": "query failed"})) storage: Final = _native_storage("trace_test", recording_server.base_url) with pytest.raises(RuntimeError, match="invalid or failed JSON"): - await storage.query("trace_spans", {}) + await storage.query("trace_spans", span_params) @pytest.mark.asyncio @@ -87,7 +128,7 @@ async def test_from_env_reads_with_clickhouse_url( recording_server.enqueue(ResponseSpec(body={"data": []})) monkeypatch.setenv("CLICKHOUSE_URL", recording_server.base_url) monkeypatch.delenv("CLICKHOUSE_READER_URL", raising=False) - scope: Final[TraceScope] = {"team_ids": (), "api_key_hash": ""} + scope: Final[TraceScope] = {"all_teams": 1, "user_id": "", "team_ids": (), "api_key_hash": ""} page: Final = await TraceReceiver.from_env().list_traces(scope, 0, 1) assert page == {"data": (), "next_cursor": None} assert len(recording_server.requests) == 1 @@ -95,7 +136,7 @@ async def test_from_env_reads_with_clickhouse_url( @pytest.mark.asyncio async def test_schema_setup_uses_configured_retention(recording_server: RecordingServer) -> None: - recording_server.expected_requests = 8 + recording_server.expected_requests = None storage: Final = _native_storage("trace_test", recording_server.base_url, 7) await storage.ensure_schema() ttl_statements: Final = tuple( @@ -192,6 +233,7 @@ def test_decode_and_tenant_stamping_share_resources_without_crossing_groups() -> "litellm.team_id": "team-a", "litellm.api_key_hash": "key-a", "litellm.org_id": "org-a", + "litellm.user_id": "", } assert second[0]["ResourceAttributes"]["litellm.team_id"] == "team-b" assert rows[0]["ResourceAttributes"] == {"shared": "x" * 128, "litellm.team_id": "spoofed"} @@ -264,7 +306,12 @@ def test_trace_sql_endpoint_executes_for_admin_and_preserves_clickhouse_envelope from litellm.proxy.auth.user_api_key_auth import user_api_key_auth from litellm.proxy.tracing_endpoints import provide_receiver, provide_trace_query_secret, router - envelope: Final = {"meta": [{"name": "answer", "type": "UInt8"}], "data": [{"answer": 42}], "rows": 1} + envelope: Final = { + "meta": [{"name": "answer", "type": "UInt8"}], + "data": [{"answer": 42}], + "rows": 1, + "statistics": {"elapsed": 0.01, "rows_read": 1, "bytes_read": 1}, + } recording_server.expected_requests = 12 for _ in range(11): recording_server.enqueue(ResponseSpec(body="")) @@ -326,9 +373,18 @@ def test_trace_help_endpoint_runs_native_schema_and_metadata_discovery(recording assert body["attributes"][1]["fields"][0]["expression"] == "ResourceAttributes['custom.resource']" -@pytest.mark.parametrize("clickhouse_status, expected_status", [(400, 400), (404, 400), (500, 503), (503, 503)]) +@pytest.mark.parametrize( + ("clickhouse_status", "body", "expected_status"), + ( + (400, b"ClickHouse rejected the query", 400), + (404, b"ClickHouse rejected the query", 400), + (500, b"ClickHouse rejected the query", 503), + (503, b"ClickHouse rejected the query", 503), + (200, b'{"data":[]}', 503), + ), +) def test_trace_sql_endpoint_distinguishes_query_errors_from_reader_failures( - recording_server: RecordingServer, clickhouse_status: int, expected_status: int + recording_server: RecordingServer, clickhouse_status: int, body: bytes, expected_status: int ) -> None: from fastapi import FastAPI from fastapi.testclient import TestClient @@ -340,8 +396,13 @@ def test_trace_sql_endpoint_distinguishes_query_errors_from_reader_failures( recording_server.expected_requests = 13 for _ in range(11): recording_server.enqueue(ResponseSpec(body="")) - recording_server.enqueue(ResponseSpec(status=clickhouse_status, body=b"ClickHouse rejected the query")) - envelope: Final = {"meta": [{"name": "answer", "type": "UInt8"}], "data": [{"answer": 42}], "rows": 1} + recording_server.enqueue(ResponseSpec(status=clickhouse_status, body=body)) + envelope: Final = { + "meta": [{"name": "answer", "type": "UInt8"}], + "data": [{"answer": 42}], + "rows": 1, + "statistics": {"elapsed": 0.01, "rows_read": 1, "bytes_read": 1}, + } recording_server.enqueue(ResponseSpec(body=envelope)) storage: Final = ClickHouseStorage(TraceStorageConfig(recording_server.base_url, "trace_test")) app: Final = FastAPI() @@ -360,15 +421,39 @@ def test_trace_sql_endpoint_distinguishes_query_errors_from_reader_failures( @pytest.mark.asyncio async def test_trace_receiver_reads_with_only_one_clickhouse_url( - recording_server: RecordingServer, monkeypatch: pytest.MonkeyPatch + recording_server: RecordingServer, + monkeypatch: pytest.MonkeyPatch, + span_row: dict[str, JsonValue], + span_params: dict[str, str | int | list[str]], ) -> None: monkeypatch.setenv("CLICKHOUSE_URL", recording_server.base_url) monkeypatch.setenv("CLICKHOUSE_DATABASE", "trace_test") monkeypatch.delenv("CLICKHOUSE_READER_URL", raising=False) - recording_server.enqueue(ResponseSpec(body={"data": [{"trace_id": "trace-1"}]})) + recording_server.enqueue(ResponseSpec(body={"data": [span_row]})) receiver: Final = TraceReceiver.from_env() - rows: Final = await receiver.store.storage.query("trace_spans", {"trace_id": "trace-1"}) - assert rows == [{"trace_id": "trace-1"}] + rows: Final = await receiver.store.storage.query(TRACE_SPANS, TraceSpansParams.model_validate(span_params)) + assert rows == ( + { + **span_row, + "start_ns": int(str(span_row["start_ns"])), + "duration_ns": int(str(span_row["duration_ns"])), + "error_truncated": False, + }, + ) parameters: Final = parse_qs(urlsplit(recording_server.requests[0].path).query) assert parameters["database"] == ["trace_test"] assert parameters["readonly"] == ["1"] + + +@pytest.mark.asyncio +async def test_lens_read_uses_the_shared_native_query_and_returns_typed_rows( + recording_server: RecordingServer, +) -> None: + recording_server.enqueue(ResponseSpec(body={"data": [{"traces": 0, "requests": 1}]})) + storage: Final = ClickHouseStorage(TraceStorageConfig(recording_server.base_url, "trace_test")) + rows: Final = await storage.lens_availability(LensAccessParams(all_teams=0, team="team-a", key_hash="key-a")) + assert rows == (ActivityAvailability(traces=False, requests=True),) + parameters: Final = parse_qs(urlsplit(recording_server.requests[0].path).query) + assert parameters["param_all_teams"] == ["0"] + assert parameters["param_team"] == ["team-a"] + assert parameters["param_key_hash"] == ["key-a"] diff --git a/tests/unit/proxy/auth/test_route_checks.py b/tests/unit/proxy/auth/test_route_checks.py index 6503e5bf50e..6b1d8bc3a2c 100644 --- a/tests/unit/proxy/auth/test_route_checks.py +++ b/tests/unit/proxy/auth/test_route_checks.py @@ -4425,3 +4425,19 @@ def test_legacy_sse_respects_virtual_key_route_permissions(route: str, route_gro request_data={}, ) assert RouteChecks.is_virtual_key_allowed_to_call_route(route=route, valid_token=token, request=request) + + +@pytest.mark.parametrize( + "route", + ("/v1/traces", "/v1/traces/trace-id", "/v1/traces/trace-id/spans/span-id", + "/v1/traces/trace-id/spans/span-id/error"), +) +def test_non_admin_trace_reads_reach_endpoint_visibility_checks(route: str) -> None: + user_role: Final = LitellmUserRoles.INTERNAL_USER + user: Final = LiteLLM_UserTable(user_id="reader", user_role=user_role.value) + auth: Final = UserAPIKeyAuth(user_id="reader", user_role=user_role) + request: Final = Request({"type": "http", "method": "GET", "query_string": b""}) + assert RouteChecks.is_llm_api_route(route) + RouteChecks.non_proxy_admin_allowed_routes_check( + user_obj=user, _user_role=user_role.value, route=route, request=request, valid_token=auth, request_data={} + ) diff --git a/tests/unit/proxy/lens/test_sources.py b/tests/unit/proxy/lens/test_sources.py index f063f496314..38af8477cf9 100644 --- a/tests/unit/proxy/lens/test_sources.py +++ b/tests/unit/proxy/lens/test_sources.py @@ -4,12 +4,11 @@ from typing import Final import pytest -from litellm.proxy.lens.models import Scope, MetadataFilter -from litellm.proxy.lens.sources import SourceReader +from litellm.proxy.lens.models import MetadataFilter, Scope +from litellm.proxy.lens.sources import SourceReader, execution_id, parse_execution +from litellm.rust_bridge.trace_queries import ActivityAvailability, AgentRow, ExecutionRow from tests.unit.proxy.lens.test_state import lens -from litellm.proxy.lens.sources import execution_id, parse_execution - def test_same_trace_id_from_different_keys_is_a_distinct_execution() -> None: assert execution_id("traces", "team", "trace", "key-one-ref") != execution_id( @@ -36,24 +35,24 @@ def test_previous_saved_findings_keep_their_execution_links() -> None: async def test_sample_never_returns_authentication_attributes() -> None: class StorageResponse: async def lens_sample(self, parameters): - assert parameters["team"] == "alpha" + assert parameters.team == "alpha" return [ - { - "source": "traces", - "trace_id": "trace", - "team_id": "alpha", - "name": "run", - "start_time": "", - "span_count": 1, - "root_seen": 1, - "eligible": 1, - "attributes": [ - ["litellm.api_key_hash", "opaque-oauth-bearer"], - ["environment", "production"], - ["", "invalid"], - ["oversized", "x" * 501], - ], - } + ExecutionRow( + source="traces", + trace_id="trace", + team_id="alpha", + name="run", + start_time="", + span_count=1, + root_seen=1, + eligible=1, + attributes=( + ("litellm.api_key_hash", "opaque-oauth-bearer"), + ("environment", "production"), + ("", "invalid"), + ("oversized", "x" * 501), + ), + ) ] reader: Final = SourceReader(StorageResponse()) @@ -67,10 +66,10 @@ async def test_sample_never_returns_authentication_attributes() -> None: async def test_agents_use_the_same_team_and_key_scope_as_samples() -> None: class AgentStorage: async def lens_agents(self, parameters): - assert parameters["all_teams"] == 0 - assert parameters["team"] == "alpha" - assert parameters["key_hash"] == "key-hash" - return [{"agent_name": "research_agent"}, {"agent_name": "support_agent"}] + assert parameters.all_teams == 0 + assert parameters.team == "alpha" + assert parameters.key_hash == "key-hash" + return (AgentRow(agent_name="research_agent"), AgentRow(agent_name="support_agent")) names: Final = await SourceReader(AgentStorage()).agents(Scope(team_id="alpha", api_key_hash="key-hash")) assert names == ("research_agent", "support_agent") @@ -80,8 +79,8 @@ async def test_agents_use_the_same_team_and_key_scope_as_samples() -> None: async def test_request_only_storage_is_available_for_investigation() -> None: class RequestStorage: async def lens_availability(self, parameters): - assert parameters["team"] == "alpha" - return [{"traces": 0, "requests": 1}] + assert parameters.team == "alpha" + return (ActivityAvailability(traces=False, requests=True),) available: Final = await SourceReader(RequestStorage()).availability(Scope(team_id="alpha")) assert available.requests @@ -92,10 +91,10 @@ async def test_request_only_storage_is_available_for_investigation() -> None: async def test_agent_filter_is_independent_of_service_and_metadata() -> None: class SampleStorage: async def lens_sample(self, parameters): - assert parameters["agent_name"] == "research_agent" - assert parameters["service"] == "shared-app" - assert parameters["filter_keys"] == ("enduser.id",) - assert parameters["filter_values"] == ("user-42",) + assert parameters.agent_name == "research_agent" + assert parameters.service == "shared-app" + assert parameters.filter_keys == ("enduser.id",) + assert parameters.filter_values == ("user-42",) return [] settings: Final = lens().settings.model_copy( diff --git a/tests/unit/proxy/spend_tracking/test_log_visibility.py b/tests/unit/proxy/spend_tracking/test_log_visibility.py new file mode 100644 index 00000000000..140225d2000 --- /dev/null +++ b/tests/unit/proxy/spend_tracking/test_log_visibility.py @@ -0,0 +1,47 @@ +from typing import Final + +import pytest +from fastapi import HTTPException + +from litellm.proxy._types import LitellmUserRoles, UserAPIKeyAuth +from litellm.proxy.spend_tracking.log_visibility import LogVisibility, log_visibility + + +@pytest.mark.asyncio +@pytest.mark.parametrize( + ("auth", "expected"), + ( + (UserAPIKeyAuth(user_role=LitellmUserRoles.PROXY_ADMIN), LogVisibility(all_teams=True)), + (UserAPIKeyAuth(user_role=LitellmUserRoles.PROXY_ADMIN_VIEW_ONLY), LogVisibility(all_teams=True)), + ( + UserAPIKeyAuth(user_id="user", token="key", team_id="unpermitted"), + LogVisibility(user_id="user", team_ids=("permitted",), api_key_hash="key"), + ), + (UserAPIKeyAuth(token="key", team_id="unpermitted"), LogVisibility(api_key_hash="key")), + ), +) +async def test_log_visibility_uses_user_and_permitted_teams_instead_of_key_team_membership( + auth: UserAPIKeyAuth, + expected: LogVisibility, +) -> None: + async def permitted_teams(caller: UserAPIKeyAuth) -> tuple[str, ...]: + assert caller is auth + return ("permitted",) + + assert await log_visibility(auth, permitted_teams) == expected + + +@pytest.mark.asyncio +async def test_missing_team_permissions_preserve_authenticated_user_and_key_visibility() -> None: + async def no_teams(auth: UserAPIKeyAuth) -> tuple[str, ...]: + return () + + auth: Final = UserAPIKeyAuth(user_id="user", token="key", team_id="team") + assert await log_visibility(auth, no_teams) == LogVisibility(user_id=auth.user_id, api_key_hash="key") + + +@pytest.mark.asyncio +async def test_team_membership_without_authenticated_identity_does_not_grant_log_access() -> None: + with pytest.raises(HTTPException) as error: + await log_visibility(UserAPIKeyAuth(team_id="team")) + assert error.value.status_code == 403 diff --git a/tests/unit/proxy/test_tracing_endpoints.py b/tests/unit/proxy/test_tracing_endpoints.py index 2c587897938..7c69796ddfa 100644 --- a/tests/unit/proxy/test_tracing_endpoints.py +++ b/tests/unit/proxy/test_tracing_endpoints.py @@ -15,11 +15,45 @@ from litellm.proxy import tracing_endpoints from litellm.proxy._types import LitellmUserRoles, ProxyLifespanState, UserAPIKeyAuth from litellm.proxy.auth.user_api_key_auth import user_api_key_auth from litellm.proxy.tracing_runtime import manage_tracing, provide_storage +from litellm.rust_bridge.trace_queries import SPAN_DETAIL, SpanDetailParams +from litellm.rust_bridge.trace_query_responses import TraceQueryHelp, TraceSQLResponse from litellm.rust_bridge.traces import ClickHouseStorage from litellm.tracing import TraceReceiver, TracingPayloadTooLargeError from litellm.tracing.store import TraceStore from litellm.tracing.types import TraceScope +SQL_ENVELOPE: Final = { + "meta": [{"name": "value", "type": "UInt64"}], + "data": [{"value": "9007199254740993"}], + "rows": 1, + "statistics": {"elapsed": 0.01, "rows_read": 1, "bytes_read": 8}, + "rows_before_limit_at_least": 1, +} +QUERY_HELP: Final = { + "dialect": "test SQL", + "access": "authenticated scope", + "response": "JSON envelope", + "tables": [{"name": "traces", "columns": [{"name": "value", "type": "String", "comment": "label"}]}], + "normalized_fields": [], + "metadata": { + "table": "traces", + "column": "metadata", + "fields": [], + "sampled_rows": 0, + "invalid_json_rows": 0, + "truncated": True, + "sample_sql": "SELECT metadata FROM traces", + "scope": "bounded sample", + "error": "discovery unavailable", + }, + "attributes": [], + "relationships": [], + "examples": [{"name": "recent", "sql": "SELECT * FROM traces LIMIT 1"}], + "gotchas": ["Keep queries bounded"], + "guide": "scoped", +} + + TEAM_KEY = UserAPIKeyAuth( token="hashed-key", team_id="team-research", org_id="org-1", user_role=LitellmUserRoles.INTERNAL_USER ) @@ -61,25 +95,25 @@ SPAN_DETAIL_RESPONSE: Final = { ( pytest.param( UserAPIKeyAuth(token="admin-key", team_id="team-a", user_role=LitellmUserRoles.PROXY_ADMIN), - TraceScope(team_ids=(), api_key_hash=""), + TraceScope(all_teams=1, user_id="", team_ids=(), api_key_hash=""), True, id="admin", ), pytest.param( UserAPIKeyAuth(token="view-key", team_id="team-a", user_role=LitellmUserRoles.PROXY_ADMIN_VIEW_ONLY), - TraceScope(team_ids=(), api_key_hash=""), + TraceScope(all_teams=1, user_id="", team_ids=(), api_key_hash=""), False, id="view-only-admin", ), pytest.param( TEAM_KEY, - TraceScope(team_ids=("team-research",), api_key_hash=""), + TraceScope(all_teams=0, user_id="", team_ids=(), api_key_hash="hashed-key"), True, id="team-key", ), pytest.param( UserAPIKeyAuth(token="hashed-key", user_role=LitellmUserRoles.INTERNAL_USER), - TraceScope(team_ids=("",), api_key_hash="hashed-key"), + TraceScope(all_teams=0, user_id="", team_ids=(), api_key_hash="hashed-key"), True, id="teamless-key", ), @@ -191,7 +225,10 @@ def test_list_traces_passes_scope_window_and_cursor(client, receiver): assert response.status_code == 200 assert response.json() == {"data": [], "next_cursor": None} receiver.list_traces.assert_awaited_once_with( - scope={"team_ids": ("team-research",), "api_key_hash": ""}, start_ms=1, end_ms=2, cursor="abc" + scope={"all_teams": 0, "user_id": "", "team_ids": (), "api_key_hash": "hashed-key"}, + start_ms=1, + end_ms=2, + cursor="abc", ) @@ -208,7 +245,9 @@ def test_get_trace_404_and_200(client, receiver): response = client.get("/v1/traces/t1") assert response.status_code == 200 assert response.json() == TRACE_RESPONSE - receiver.get_trace.assert_awaited_with("t1", {"team_ids": ("team-research",), "api_key_hash": ""}, "") + receiver.get_trace.assert_awaited_with( + "t1", {"all_teams": 0, "user_id": "", "team_ids": (), "api_key_hash": "hashed-key"}, "" + ) def test_get_span_404_and_200(client, receiver): @@ -217,7 +256,9 @@ def test_get_span_404_and_200(client, receiver): response = client.get("/v1/traces/t1/spans/s1") assert response.status_code == 200 assert response.json()["span_id"] == "s1" - receiver.get_span.assert_awaited_with("t1", "s1", {"team_ids": ("team-research",), "api_key_hash": ""}, "") + receiver.get_span.assert_awaited_with( + "t1", "s1", {"all_teams": 0, "user_id": "", "team_ids": (), "api_key_hash": "hashed-key"}, "" + ) def test_get_span_serves_ui_content_from_stored_payloads(client): @@ -227,7 +268,7 @@ def test_get_span_serves_ui_content_from_stored_payloads(client): return_value=[{"span_id": "s1", "input": '{"city": "Paris"}', "output": stored_output, "attributes": {}}] ) client.app.dependency_overrides[tracing_endpoints.provide_receiver] = lambda: TraceReceiver(TraceStore(storage)) - body = client.get("/v1/traces/t1/spans/s1").json() + body = client.get("/v1/traces/t1/spans/s1?trace_ref=run-one").json() assert body["output"] == stored_output assert body["input_ui"] == {"kind": "fields", "fields": [{"key": "city", "value": "Paris"}]} assert body["output_ui"] == { @@ -241,7 +282,9 @@ def test_get_span_serves_ui_content_from_stored_payloads(client): def test_trace_detail_passes_scoped_reference(client, receiver): receiver.get_trace.return_value = TRACE_RESPONSE assert client.get("/v1/traces/t1?trace_ref=run-one").status_code == 200 - receiver.get_trace.assert_awaited_with("t1", {"team_ids": ("team-research",), "api_key_hash": ""}, "run-one") + receiver.get_trace.assert_awaited_with( + "t1", {"all_teams": 0, "user_id": "", "team_ids": (), "api_key_hash": "hashed-key"}, "run-one" + ) def test_invalid_export_and_cursor_are_client_errors(client, receiver): @@ -350,6 +393,7 @@ def test_injected_receiver_persists_authenticated_tenant(client: TestClient) -> "litellm.team_id": TEAM_KEY.team_id, "litellm.api_key_hash": TEAM_KEY.token, "litellm.org_id": TEAM_KEY.org_id, + "litellm.user_id": TEAM_KEY.user_id or "", } @@ -428,24 +472,28 @@ def test_lifespan_receivers_are_app_local() -> None: } assert first_storage.query.await_count == 2 first_storage.query.assert_awaited_with( - "span_detail", - { - "team_ids": (TEAM_KEY.team_id,), - "api_key_hash": "", - "trace_id": "t1", - "span_id": "first-span", - "trace_ref": "first-run", - }, + SPAN_DETAIL, + SpanDetailParams( + all_teams=0, + user_id="", + team_ids=(), + api_key_hash=TEAM_KEY.token, + trace_id="t1", + span_id="first-span", + trace_ref="first-run", + ), ) second_storage.query.assert_awaited_once_with( - "span_detail", - { - "team_ids": (TEAM_KEY.team_id,), - "api_key_hash": "", - "trace_id": "t1", - "span_id": "second-span", - "trace_ref": "second-run", - }, + SPAN_DETAIL, + SpanDetailParams( + all_teams=0, + user_id="", + team_ids=(), + api_key_hash=TEAM_KEY.token, + trace_id="t1", + span_id="second-span", + trace_ref="second-run", + ), ) @@ -504,7 +552,7 @@ def test_lens_reads_from_the_lifespan_storage() -> None: assert response.status_code == 200, response.text assert response.json()["executions"] == [] storage.lens_sample.assert_awaited_once() - assert storage.lens_sample.await_args.args[0]["all_teams"] == 1 + assert storage.lens_sample.await_args.args[0].all_teams == 1 def test_lens_reads_from_injected_storage_without_receiver() -> None: @@ -534,12 +582,12 @@ def test_lens_reads_from_injected_storage_without_receiver() -> None: ( (UserAPIKeyAuth(user_role=LitellmUserRoles.PROXY_ADMIN), {"kind": "admin"}), (UserAPIKeyAuth(user_role=LitellmUserRoles.PROXY_ADMIN_VIEW_ONLY), {"kind": "admin"}), - (TEAM_KEY, {"kind": "team", "team_id": "team-research"}), + (TEAM_KEY, {"kind": "logs", "user_id": "", "team_ids": (), "api_key_hash": "hashed-key"}), ( UserAPIKeyAuth(token="project-key", team_id="team-a", project_id="project-a"), - {"kind": "key", "team_id": "team-a", "api_key_hash": "project-key"}, + {"kind": "logs", "user_id": "", "team_ids": (), "api_key_hash": "project-key"}, ), - (UserAPIKeyAuth(token="solo-key"), {"kind": "key", "team_id": "", "api_key_hash": "solo-key"}), + (UserAPIKeyAuth(token="solo-key"), {"kind": "logs", "user_id": "", "team_ids": (), "api_key_hash": "solo-key"}), ), ) def test_sql_and_help_use_authenticated_scope( @@ -547,17 +595,17 @@ def test_sql_and_help_use_authenticated_scope( ) -> None: client.app.dependency_overrides[user_api_key_auth] = lambda: auth client.app.dependency_overrides[tracing_endpoints.provide_trace_query_secret] = lambda: "test-secret" - receiver.store.storage.query_sql = AsyncMock(return_value='{"data":[{"value":1}]}') - receiver.store.storage.query_help = AsyncMock(return_value='{"guide":"scoped"}') + receiver.store.storage.query_sql = AsyncMock(return_value=TraceSQLResponse.model_validate(SQL_ENVELOPE)) + receiver.store.storage.query_help = AsyncMock(return_value=TraceQueryHelp.model_validate(QUERY_HELP)) result: Final = client.post("/v1/traces/query", json={"sql": "SELECT * FROM otel_traces"}) assert result.status_code == 200, result.text - assert result.json() == {"data": [{"value": 1}]} + assert result.json() == SQL_ENVELOPE receiver.store.storage.query_sql.assert_awaited_once_with( "SELECT * FROM otel_traces", expected_scope, "test-secret" ) help_result: Final = client.get("/v1/traces/query/help") assert help_result.status_code == 200, help_result.text - assert help_result.json() == {"guide": "scoped"} + assert help_result.json() == QUERY_HELP receiver.store.storage.query_help.assert_awaited_once_with(expected_scope, "test-secret") forged: Final = client.post("/v1/traces/query", json={"sql": "SELECT 1", "scope": {"kind": "admin"}}) assert forged.status_code == 422, forged.text @@ -588,7 +636,7 @@ def test_sql_reports_rejected_queries_and_unavailable_readers( result: Final = client.post("/v1/traces/query", json={"sql": "SELECT 1"}) assert result.status_code == status, result.text receiver.store.storage.query_sql.assert_awaited_once_with( - "SELECT 1", {"kind": "team", "team_id": "team-research"}, "test-secret" + "SELECT 1", {"kind": "logs", "user_id": "", "team_ids": (), "api_key_hash": "hashed-key"}, "test-secret" ) @@ -598,7 +646,7 @@ def test_query_help_does_not_fall_back_when_reader_provisioning_fails(client: Te result: Final = client.get("/v1/traces/query/help") assert result.status_code == 503, result.text receiver.store.storage.query_help.assert_awaited_once_with( - {"kind": "team", "team_id": "team-research"}, "test-secret" + {"kind": "logs", "user_id": "", "team_ids": (), "api_key_hash": "hashed-key"}, "test-secret" ) @@ -609,7 +657,7 @@ def test_queries_require_a_proxy_secret( from litellm.proxy import proxy_server monkeypatch.setattr(proxy_server, "master_key", secret) - receiver.store.storage.query_sql = AsyncMock(return_value='{"data":[]}') + receiver.store.storage.query_sql = AsyncMock(return_value=TraceSQLResponse.model_validate(SQL_ENVELOPE)) result: Final = client.post("/v1/traces/query", json={"sql": "SELECT 1"}) if secret is None: assert result.status_code == 503, result.text @@ -618,5 +666,5 @@ def test_queries_require_a_proxy_secret( return assert result.status_code == 200, result.text receiver.store.storage.query_sql.assert_awaited_once_with( - "SELECT 1", {"kind": "team", "team_id": "team-research"}, secret + "SELECT 1", {"kind": "logs", "user_id": "", "team_ids": (), "api_key_hash": "hashed-key"}, secret ) diff --git a/tests/unit/rust_bridge/test_trace_queries.py b/tests/unit/rust_bridge/test_trace_queries.py new file mode 100644 index 00000000000..5ffe9ea0404 --- /dev/null +++ b/tests/unit/rust_bridge/test_trace_queries.py @@ -0,0 +1,59 @@ +from typing import Final + +import pytest +from pydantic import JsonValue, ValidationError + +from litellm.rust_bridge.trace_queries import SPAN_DETAIL, SPAN_ERROR, SpanDetailParams +from litellm.rust_bridge.trace_query_responses import TraceSQLResponse + + +@pytest.mark.parametrize("offset", (-1, 2**64)) +def test_named_query_rejects_offsets_outside_the_native_integer_range(offset: int) -> None: + with pytest.raises(ValidationError) as error: + SPAN_ERROR.parameters.model_validate( + { + "all_teams": 0, + "user_id": "", + "team_ids": ["team"], + "api_key_hash": "key", + "trace_id": "trace", + "trace_ref": "ref", + "span_id": "span", + "error_offset": offset, + "error_version": "", + } + ) + assert error.value.error_count() == 1 + + +def test_named_query_rejects_parameters_for_a_different_query() -> None: + detail: Final = SpanDetailParams( + all_teams=0, + user_id="", + team_ids=("team",), + api_key_hash="key", + trace_id="trace", + trace_ref="ref", + span_id="span", + ) + with pytest.raises(ValidationError) as error: + SPAN_ERROR.parameters.model_validate(detail) + assert error.value.error_count() == 1 + + +def test_named_query_rejects_rows_missing_required_result_fields() -> None: + with pytest.raises(ValidationError) as error: + SPAN_DETAIL.response.validate_json('{"data":[{"span_id":"span","input":"input","output":"output"}]}') + assert error.value.error_count() == 1 + + +def test_sql_envelope_preserves_nested_data_large_integer_strings_and_extra_fields() -> None: + envelope: Final[dict[str, JsonValue]] = { + "meta": [{"name": "count", "type": "UInt64", "comment": "label"}], + "data": [{"count": "9007199254740993", "nested": [True, None, {"value": 2}]}], + "rows": "1", + "statistics": {"elapsed": 0.01, "rows_read": "1", "bytes_read": "8", "extra_stat": 4}, + "totals": {"count": "9007199254740993"}, + } + result: Final = TraceSQLResponse.model_validate(envelope) + assert result.model_dump(mode="json", exclude_unset=True) == envelope diff --git a/ui/litellm-dashboard/src/lib/http/schema.d.ts b/ui/litellm-dashboard/src/lib/http/schema.d.ts index cc0b081b670..df968e0bc9f 100644 --- a/ui/litellm-dashboard/src/lib/http/schema.d.ts +++ b/ui/litellm-dashboard/src/lib/http/schema.d.ts @@ -46895,11 +46895,163 @@ export interface components { */ truncated: boolean; }; + /** TraceQueryAttributeField */ + TraceQueryAttributeField: { + /** Expression */ + expression: string; + /** Key */ + key: string; + /** Type */ + type: string; + }; + /** TraceQueryAttributes */ + TraceQueryAttributes: { + /** Column */ + column: string; + /** Discovery Sql */ + discovery_sql: string; + /** Error */ + error?: string | null; + /** Fields */ + fields: components["schemas"]["TraceQueryAttributeField"][]; + /** Scope */ + scope: string; + /** Table */ + table: string; + /** Truncated */ + truncated: boolean; + }; + /** TraceQueryColumn */ + TraceQueryColumn: { + /** Name */ + name: string; + /** Type */ + type: string; + } & { + [key: string]: unknown; + }; + /** TraceQueryExample */ + TraceQueryExample: { + /** Name */ + name: string; + /** Sql */ + sql: string; + }; + /** TraceQueryHelp */ + TraceQueryHelp: { + /** Access */ + access: string; + /** Attributes */ + attributes: components["schemas"]["TraceQueryAttributes"][]; + /** Dialect */ + dialect: string; + /** Examples */ + examples: components["schemas"]["TraceQueryExample"][]; + /** Gotchas */ + gotchas: string[]; + /** Guide */ + guide: string; + metadata: components["schemas"]["TraceQueryMetadata"]; + /** Normalized Fields */ + normalized_fields: components["schemas"]["TraceQueryNormalizedField"][]; + /** Relationships */ + relationships: components["schemas"]["TraceQueryRelationship"][]; + /** Response */ + response: string; + /** Tables */ + tables: components["schemas"]["TraceQueryTable"][]; + }; + /** TraceQueryMetadata */ + TraceQueryMetadata: { + /** Column */ + column: string; + /** Error */ + error?: string | null; + /** Fields */ + fields: components["schemas"]["TraceQueryMetadataField"][]; + /** Invalid Json Rows */ + invalid_json_rows: number; + /** Sample Sql */ + sample_sql: string; + /** Sampled Rows */ + sampled_rows: number; + /** Scope */ + scope: string; + /** Table */ + table: string; + /** Truncated */ + truncated: boolean; + }; + /** TraceQueryMetadataField */ + TraceQueryMetadataField: { + /** Expression */ + expression: string; + /** Path */ + path: (string | number)[]; + /** Types */ + types: string[]; + }; + /** TraceQueryNormalizedField */ + TraceQueryNormalizedField: { + /** Column */ + column: string; + /** Meaning */ + meaning: string; + /** Name */ + name: string; + /** Table */ + table: string; + /** Type */ + type: string; + }; + /** TraceQueryRelationship */ + TraceQueryRelationship: { + /** Additional Predicates */ + additional_predicates: string; + /** Left */ + left: string; + /** Meaning */ + meaning: string; + /** Right */ + right: string; + }; /** TraceQueryRequest */ TraceQueryRequest: { /** Sql */ sql: string; }; + /** TraceQueryStatistics */ + TraceQueryStatistics: { + /** Bytes Read */ + bytes_read: number | string; + /** Elapsed */ + elapsed: number; + /** Rows Read */ + rows_read: number | string; + } & { + [key: string]: unknown; + }; + /** TraceQueryTable */ + TraceQueryTable: { + /** Columns */ + columns: components["schemas"]["TraceQueryColumn"][]; + /** Name */ + name: string; + }; + /** TraceSQLResponse */ + TraceSQLResponse: { + /** Data */ + data: { + [key: string]: components["schemas"]["JsonValue"]; + }[]; + /** Meta */ + meta: components["schemas"]["TraceQueryColumn"][]; + /** Rows */ + rows: number | string; + statistics: components["schemas"]["TraceQueryStatistics"]; + } & { + [key: string]: unknown; + }; /** TraceSummary */ TraceSummary: { /** Agent Count */ @@ -79783,7 +79935,7 @@ export interface operations { [name: string]: unknown; }; content: { - "application/json": unknown; + "application/json": components["schemas"]["TraceSQLResponse"]; }; }; /** @description Validation Error */ @@ -79812,7 +79964,7 @@ export interface operations { [name: string]: unknown; }; content: { - "application/json": unknown; + "application/json": components["schemas"]["TraceQueryHelp"]; }; }; }; diff --git a/ui/litellm-dashboard/src/lib/http/traceQueryTypes.test-d.ts b/ui/litellm-dashboard/src/lib/http/traceQueryTypes.test-d.ts new file mode 100644 index 00000000000..d977a628012 --- /dev/null +++ b/ui/litellm-dashboard/src/lib/http/traceQueryTypes.test-d.ts @@ -0,0 +1,20 @@ +import { expectTypeOf, test } from "vitest"; + +import type { components, paths } from "@/lib/http/schema"; + +type SQLResponse = paths["/v1/traces/query"]["post"]["responses"][200]["content"]["application/json"]; +type QueryHelp = paths["/v1/traces/query/help"]["get"]["responses"][200]["content"]["application/json"]; + +test("SQL results expose column metadata, JSON values and row counts", () => { + expectTypeOf().toEqualTypeOf(); + expectTypeOf().toEqualTypeOf(); + expectTypeOf().toEqualTypeOf(); + expectTypeOf().toEqualTypeOf(); +}); + +test("query help exposes schema discovery, examples and discovery failures", () => { + expectTypeOf().toEqualTypeOf(); + expectTypeOf().toEqualTypeOf(); + expectTypeOf().toEqualTypeOf(); + expectTypeOf().toEqualTypeOf(); +});