litellm/tests/integration/observability
devin-ai-integration[bot] 85a3869dfd
feat(guardrails): per-mode stream_scope with bedrock stream and pass-through fixes (#43801)
* feat(guardrails): run each mode only on streaming, non-streaming, or both

Add stream_scope so a rail can target streaming inference, non-streaming inference, or both per pre, during, and post mode

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(guardrails): honor stream_scope in pipelines and dashboard types

Pipeline steps skipped the stream_scope filter, direct construction ignored mixed-case maps, and schema.d.ts was stale.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(guardrails): skip unmatched stream_scope steps instead of allowing

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(ui): keep stored stream_scope keys for modes not on screen

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(ci): format stream_scope helpers and update fork MCP unit tests

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(mcp): keep hang cancellation tests from timing out during setup

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(guardrails): honor path-defined streaming for stream_scope

Passthrough routes like Gemini streamGenerateContent decide streaming from the URL, so stamp that onto hook data before guardrails run.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(rust): copy AnthropicModelCapabilities instead of cloning

Clippy treats clone-on-Copy as an error, which failed rust-lint on the messages request tests.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(guardrails): trust only server stream classification

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(guardrails): keep streaming marker through deepcopy

scan_raw_request snapshots copy each field, so a plain object() marker would lose identity and skip streaming-only rails.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(cost-map): drop duplicate perceptron-mk1.5 row

Two main cost-map PRs both added the OpenRouter model, so the merge left a second key that CI rejects.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(rust): expect native transcription 429 as RustUpstreamError

HTTP status errors from native routes map through route_error_to_pyerr, so the wheel SIGINT child was dying on an outdated RuntimeError check and never reached the hang probe.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(tests): follow Google Interactions OpenAPI without hardcoded names

The live spec dropped CreateModelInteractionParams and renamed the item path to {interactionsId}. Misc CI failed because the compliance tests still looked those names up as literals.

* test(guardrails): reproduce stream_scope bedrock and passthrough field gaps

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(guardrails): cover invalid stored stream_scope reads

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(guardrails): classify bedrock stream actions and keep caller is_streaming_request

Co-authored-by: Shivi Jain <mobile.350017@gmail.com>
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* refactor(guardrails): make stream_scope_allows public and drop mutable builds

Co-authored-by: Shivi Jain <mobile.350017@gmail.com>
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(guardrails): classify pass-through and Bedrock stream scopes

Co-authored-by: Shivi Jain <mobile.350017@gmail.com>
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(guardrails): harden stream classification and validation

Co-authored-by: Shivi Jain <mobile.350017@gmail.com>
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(guardrails): add stream scope integration audit

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(proxy): avoid mutating passthrough custom body

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(guardrails): run stream scope audit without enterprise license

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(guardrails): keep stored scope restart cell on one worker

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(guardrails): scope stream scope audit sink assertions to the rail under test

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(guardrails): assert logging_only scope absence behind an ordered barrier rail

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(guardrails): assert one logging_only scan per phase after the barrier rail

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(guardrails): set request scope on pass-through stream fixtures

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(guardrails): tolerate invalid YAML stream_scope in v1 guardrails list

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* chore: merge main into litellm_guardrail_stream_scope_fixes

Update pass-through pre-call test callbacks for main's endpoint_type argument

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(guardrails): add request paths to pass-through fixtures

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(guardrails): cover websocket pass-through stream scope and LIT-9050 outage spend rows

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* chore(lint): remove unused type discipline suppressions

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(guardrails): script the vertex live upstream in the websocket stream scope test

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(guardrails): keep stream marker json-serializable and restore pass-through helper names

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(lint): allow required Bedrock action re-export

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(guardrails): strip the stream marker from pass-through payloads

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(guardrails): drop stream marker by value in scans and snapshots, plain-tuple stream scope state

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* fix(ui): render tag-scoped guardrail modes read-only in the custom code editor

A guardrail whose litellm_params.mode is the tag-scoped dict {tags, default}
crashed the Custom Code editor on open: normalizeMode wrapped the dict into
the mode array and StreamScopeFields rendered it as a React child (error #31,
whole dashboard unmounted). Treat a non-string non-array mode as no editable
modes, show formatGuardrailMode(mode) in a disabled input (read-only, matching
the guardrail info view), and keep mode/stream_scope out of the update payload
for such guardrails.

* fix(ui): resolve merge fallout in guardrails components

Deduplicate toModeArray import after the merge, and move the read-only
guardrail details block back into GuardrailReadOnlyDetails (now rendering
the shared mode/logging-only rows plus the stream-scope detail) so
guardrail_info.tsx stays under the 800-line lint budget. Guardrails UI
suite: 298 passed.

* fix(ui): drop duplicate toModeArray import reintroduced by merge

* chore(pass-through): document the deliberate in-place marker strip as mutable-ok

The clear/update on _parsed_body is load-bearing: rebinding to a fresh
mapping instead breaks 75 pass-through tests because the marker-free body
must propagate through the caller's request dict so downstream guardrail
scans and snapshots never observe the server streaming marker.

* fix(guardrails): move stream_scope after timeout in CustomGuardrail init

Inserting stream_scope before the existing timeout parameter shifted the
positional slot of timeout, so positional callers constructed with their
timeout bound to stream_scope (ValueError) and timeout silently None.
Restores the base parameter order; keyword callers are unaffected.

* fix(guardrails): typing pass for the lint gates

stream_scope leaves the declared constructor parameters (restoring the
base positional surface; keyword construction unchanged), unknown config
values crossing the new stream-scope code paths get typed locals or
cast-ok boundaries, and the passthrough payload literals are annotated.
All three lint gates pass against current main; the guardrail suites are
unchanged (236+5019 passing; one known anyio-driver failure pre-existing
on base).

* style: sort cast imports for the ruff gate

* chore(pass-through): drop unused BEDROCK_STREAMING_ACTIONS re-export

The streaming check now uses is_bedrock_streaming_endpoint; nothing in
the repo imports the name from this module.

---------

Co-authored-by: Shivi Jain <mobile.350017@gmail.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: yucheng <yucheng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: gabriele <gabriele@berri.ai>
2026-10-08 13:46:53 -07:00
..
_azure_storage_support.py fix(azure_storage): name Data Lake objects without base64 padding or slashes (#43914) 2026-09-30 18:17:13 -07:00
_logging_only_scope_support.py feat(guardrails): add logging_only_scope to observe input, output, or both (#43695) 2026-10-07 14:03:33 -07:00
_s3_v2_support.py fix(s3_v2): upload fresh events first, drop terminal failures and hour-old retries by default, opt-in adaptive concurrency (#43022) 2026-09-26 14:58:28 -07:00
azure_dispatch_support.py fix(guardrails): restore Azure guardrail get_user_prompt dispatch and allow logging (#44067) 2026-10-01 23:30:32 -07:00
conftest.py test(observability): wait for warm-up spend rows in capped and count only the post-wipe half in X4 (#45006) 2026-10-07 11:29:05 -07:00
test_azure_content_safety_audit.py fix(guardrails): scan Responses API input in Azure Text Moderation (#43965) 2026-09-30 22:58:03 -07:00
test_azure_content_safety_dispatch.py fix(guardrails): restore Azure guardrail get_user_prompt dispatch and allow logging (#44067) 2026-10-01 23:30:32 -07:00
test_azure_content_safety_dispatch_resilience.py fix(guardrails): restore Azure guardrail get_user_prompt dispatch and allow logging (#44067) 2026-10-01 23:30:32 -07:00
test_azure_content_safety_endpoints.py fix(guardrails): scan Responses API input in Azure Prompt Shield (#43786) 2026-09-30 22:48:20 -07:00
test_azure_storage_chaos.py fix(azure_storage): keep the DataLakeServiceClient alive until its TTL elapses (#43082) 2026-09-30 18:50:15 -07:00
test_azure_storage_client_ttl.py fix(azure_storage): keep the DataLakeServiceClient alive until its TTL elapses (#43082) 2026-09-30 18:50:15 -07:00
test_azure_storage_file_names.py fix(azure_storage): keep client call ids from sharing one Data Lake file (#44099) 2026-10-01 23:23:37 -07:00
test_bedrock_error_request_id.py test(integration): cover customer reported cache key, cache_control, bedrock request id, responses schema, scim and tag budget contracts (#42785) 2026-09-23 13:19:38 -07:00
test_cache_hit_guardrail_metrics.py fix(proxy): keep deployment labels on cache-hit post_call guardrail rejections (#42780) 2026-09-23 22:48:04 -07:00
test_cache_hit_guardrail_metrics_chaos.py test(observability): wait for warm-up spend rows in capped and count only the post-wipe half in X4 (#45006) 2026-10-07 11:29:05 -07:00
test_callback_delivery.py test(integration): regression tests for August cost tracking and budgeting bugs (#42622) 2026-09-23 04:13:03 +00:00
test_file_usage_counter_span.py feat(proxy): cap batch file records, daily batch uploads, and per-file downloads (#43632) 2026-10-06 03:06:36 +00:00
test_grayswan_wire.py fix(grayswan): send request conversation and tool calls to post-call monitor (#43770) 2026-09-30 17:52:53 -07:00
test_grayswan_wire_chaos.py fix(grayswan): send request conversation and tool calls to post-call monitor (#43770) 2026-09-30 17:52:53 -07:00
test_guardrail_effects.py feat(guardrails): add logging_only_scope to observe input, output, or both (#43695) 2026-10-07 14:03:33 -07:00
test_guardrail_stream_scope.py feat(guardrails): per-mode stream_scope with bedrock stream and pass-through fixes (#43801) 2026-10-08 13:46:53 -07:00
test_guardrail_stream_scope_chaos.py feat(guardrails): per-mode stream_scope with bedrock stream and pass-through fixes (#43801) 2026-10-08 13:46:53 -07:00
test_guardrail_stream_scope_matrix.py feat(guardrails): per-mode stream_scope with bedrock stream and pass-through fixes (#43801) 2026-10-08 13:46:53 -07:00
test_guardrail_timeout_all_providers.py feat(guardrails): honor litellm_params.timeout in every HTTP guardrail (#43134) 2026-09-30 21:18:47 -07:00
test_langfuse_delivery.py fix(proxy): traceparent/baggage fallback must not override caller metadata (#43688) 2026-10-07 19:24:50 -07:00
test_langtrace_delivery.py test(integration): turn the model-info refresh off in every integration proxy config (#45104) 2026-10-07 11:46:34 -07:00
test_logging_only_scope_chaos.py feat(guardrails): add logging_only_scope to observe input, output, or both (#43695) 2026-10-07 14:03:33 -07:00
test_logging_only_scope_config.py feat(guardrails): add logging_only_scope to observe input, output, or both (#43695) 2026-10-07 14:03:33 -07:00
test_logging_only_scope_runtime.py feat(guardrails): add logging_only_scope to observe input, output, or both (#43695) 2026-10-07 14:03:33 -07:00
test_otel_conversation_id.py test(integration): turn the model-info refresh off in every integration proxy config (#45104) 2026-10-07 11:46:34 -07:00
test_otel_excluded_services.py fix(caching): key response cache by router model group in litellm_metadata (#44542) 2026-10-05 17:06:21 +00:00
test_otel_excluded_services_matrix.py fix(otel): tolerate non-dict callback_settings.otel and ignore bare EXCLUDED_SERVICES env (#44086) 2026-10-02 12:36:46 -07:00
test_otel_text_completion_choices.py fix(otel): keep text completion choice fields beside the synthesized message (#42537) 2026-09-22 14:24:32 -07:00
test_otel_v1_request_trace.py fix(caching): key response cache by router model group in litellm_metadata (#44542) 2026-10-05 17:06:21 +00:00
test_passthrough_upstream_error_chaos.py fix(ci): stop stale CI reds, keep unit tests off the host env, retry CyberArk policy conflicts (#43294) 2026-09-26 09:25:13 -07:00
test_passthrough_upstream_error_visibility.py test(integration): opt the config pass-through spend-log case into auth (#44265) 2026-10-02 23:12:15 +00:00
test_presidio_entity_masking.py test(integration): move legacy proxy, router and Redis tests into tests/integration (#44128) 2026-10-01 23:00:54 -07:00
test_presidio_streaming_output.py fix(presidio): mask streamed /v1/messages output when the first upstream read is a keepalive, a data-less ping, or a split utf8 character (#43023) 2026-09-25 00:48:42 -07:00
test_prometheus_series_cap.py feat(prometheus): cap series per metric for every labeled metric (#44420) 2026-10-06 01:28:44 +00:00
test_prometheus_series_cap_chaos.py feat(prometheus): cap series per metric for every labeled metric (#44420) 2026-10-06 01:28:44 +00:00
test_s3_v2_flush_surfaces.py fix(s3_v2): upload fresh events first, drop terminal failures and hour-old retries by default, opt-in adaptive concurrency (#43022) 2026-09-26 14:58:28 -07:00
test_s3_v2_partition_granularity.py feat(s3_v2): add s3_partition_granularity option for hourly S3 folders (#43748) 2026-10-01 11:00:21 -07:00
test_s3_v2_streaming_failure_dedupe.py fix(responses): stop SDK retries nesting under router retries, and unbreak CircleCI integration tests (#44791) 2026-10-06 15:57:33 +00:00
test_s3_v2_upload_fanout.py chore(lint): remove the LIT002 mutable-construction rule (#43971) 2026-10-01 12:24:02 -07:00
test_signoz_delivery.py test(integration): turn the model-info refresh off in every integration proxy config (#45104) 2026-10-07 11:46:34 -07:00
test_straiker_v3_platform.py test(straiker): assert a saved api_version v1 with an sk_agt_ key routes to v3 (#44153) 2026-10-02 01:31:02 -07:00
test_xecguard_wire.py refactor(types): replace Any with proven types in 7 files (#43704) 2026-09-29 06:12:58 -07:00