litellm/scripts
devin-ai-integration[bot] 461a58c40a
refactor(lens): storage-independent trace reads, shared keyset pager, typed read failures (#44422)
* feat(lens): own trace reads behind a cached TraceStore port

Move storage-independent trace reads into litellm-traces-cache behind a
TraceStore port that ClickHouse implements. One keyset pager drives the
span, list span and spend reads, and a run list batch reads spend once.

Trace opens, pages and list summaries share one resolved read per trace
in an in-process cache with single-flight loading. Live traces and reads
with unknown spend expire after 5s, quiet traces after 10 minutes, failed
reads are never cached, and the accepted list page size is remembered per
scope.

Trace read failures map to their own status and code (400, 409, 413, 503
with Retry-After), and the trace drawer retries temporary failures while
offering only a refresh for changed or oversized traces.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* perf(lens): seed large profiles with server-side copies and long sessions

Replay one copy through the proxy, then copy it inside ClickHouse and
PostgreSQL with INSERT ... SELECT, rewriting trace, span and call IDs so
every copy keeps its own spend. Add three long single-trace sessions for
drawer paging and the oversized read path

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* chores

* style(lens): float the investigation setup badge on the tab edge

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* refactor(lens): restructure the trace drawer and polish its layout

Split the 547-line TraceDrawer into run/, tree/, span/, content/ and
conversation/ modules. Step rows now sit on one line with colored span
family tiles, and the per-row timing bar moved into an optional Waterfall
layout with a time axis. The steps and details panes are separated by the
shadcn Resizable handle, with the split remembered per orientation.

Span payloads go through one pure classifier (payloadView) that picks
messages, a tool result, a nested field tree or text. JSON-encoded field
values unfold into a tree, prose renders as markdown, repr and tracebacks
stay monospace, and every section offers a Raw view. LangChain's
serialized messages now render as conversation cards.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* typesafety

* wip

* fmt

---------

Co-authored-by: Yujong Lee <yujong@berri.ai>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-04 12:39:47 -07:00
..
adaptive_router_demo docs: stop advertising sk-1234 as the master key in shipped configs and examples 2026-09-19 12:59:48 -07:00
health_check feat(rate-limiter): allow opting out of v3 TPM reservation and Redis circuit breaker (#30211) 2026-06-11 10:34:26 -07:00
trace_codegen fix(lens): paginate trace reads within ClickHouse limits (#44384) 2026-10-03 10:38:40 -07:00
auto-close-duplicates.test.ts fix(ci): keep earlier objections when the duplicate notice is re-posted 2026-08-29 17:30:39 -04:00
auto-close-duplicates.ts ci: classify new issues into domain, provider, kind, priority and lift labels 2026-09-18 11:37:55 -07:00
benchmark_anthropic_messages_perf.py chore: remove the dead telemetry flag from the SDK, proxy CLI and configs 2026-09-20 01:44:10 +00:00
benchmark_chat_completions_perf.py chore: remove the dead telemetry flag from the SDK, proxy CLI and configs 2026-09-20 01:44:10 +00:00
benchmark_mock.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
benchmark_model_response_creator.py fix: improve bedrock streaming hot path perf (#28720) 2026-05-28 11:31:37 -07:00
benchmark_ocr_callbacks.py refactor(ocr): complete native lifecycle and preserve Azure auth (#40734) 2026-09-12 11:56:49 -07:00
benchmark_proxy_vs_provider.py style: run black formatter on files from main merge 2026-04-17 13:02:59 -07:00
benchmark_streaming_chunk_overhead.py feat: litellm oss 110626 (#30202) 2026-06-11 22:30:26 -07:00
budget_ratchet_check.py test(ci): prove RULE_CODES by running every checker rule 2026-09-20 08:27:02 +00:00
check_mcp_operation_boundary.py refactor(mcp): extract explicit operation context and dispatch 2026-09-21 12:24:15 -07:00
check_mcp_sdk_install.py fix(mcp): preserve legacy behavior on SDK2 and streamline verification 2026-09-18 22:28:31 -07:00
check_test_quality.py fix(ci): excuse retired test-quality rules in the budget ratchet 2026-09-20 08:12:39 +00:00
check_type_discipline.py chore(lint): remove the LIT002 mutable-construction rule (#43971) 2026-10-01 12:24:02 -07:00
classify-issue.test.ts fix(issue-classifier): queue runs per issue and judge edits by live labels 2026-09-18 11:37:55 -07:00
classify-issue.ts fix(issue-classifier): queue runs per issue and judge edits by live labels 2026-09-18 11:37:55 -07:00
comment-fixed-issue.test.ts chore(ci): drop litellm_internal_staging and litellm_oss_staging references, main is the only trunk (#42745) 2026-09-23 08:14:11 -07:00
comment-fixed-issue.ts feat(ci): close open pull requests superseded by a merged fix on their linked issue (#42609) 2026-09-22 18:24:35 -07:00
create_litellm_branch.ps1 feat: add script to create branches with litellm_ prefix (#17606) 2025-12-06 10:41:39 -08:00
create_litellm_branch.sh enhance: create_litellm_branch tool to be more robust (#17874) 2025-12-12 05:35:50 -08:00
create_team_key_and_submit_guardrail.sh feat(guardrails): team-based guardrail registration and approval workflow (#22459) 2026-03-02 22:06:49 -08:00
default_branch.py ci: follow the default branch in development tooling 2026-09-07 14:34:45 -07:00
eval_compression.py Prompt Compression - add it to the proxy (#25729) 2026-04-20 15:08:00 -07:00
flag-duplicate-issue.test.ts ci(duplicate-check): drop the unused considered field from the verdict schema 2026-09-13 15:41:30 -07:00
flag-duplicate-issue.ts ci(duplicate-check): only warn about the auto close the sweep will actually do 2026-09-12 20:27:37 -07:00
gate_slot_lock.py refactor(make): stop queueing bootstrap for a machine-wide gate slot 2026-08-15 21:53:28 +00:00
generate_trace_types.py feat(traces): tracing development seed (#44363) 2026-10-03 09:59:51 +00:00
install-cli.sh fix(install): pass an explicit Python version request to uv tool install 2026-07-26 21:02:35 -07:00
install.sh fix(install): pass an explicit Python version request to uv tool install 2026-07-26 21:02:35 -07:00
install_git_hooks.sh build(lint): rename make pre-commit to make check with a working-tree fallback 2026-08-08 03:25:35 -07:00
issue-labels.ts ci(issue-classifier): name every workflow, script and job after the issue it works on 2026-09-18 11:37:55 -07:00
label-issue.test.ts ci(issue-classifier): parse only form headings and keep the claude code label 2026-09-18 11:37:55 -07:00
label-issue.ts ci(issue-classifier): name every workflow, script and job after the issue it works on 2026-09-18 11:37:55 -07:00
lens_dev.sh refactor(lens): storage-independent trace reads, shared keyset pager, typed read failures (#44422) 2026-10-04 12:39:47 -07:00
mock_bedrock_passthrough_target.py Refactor Bedrock response stream shape handling (#27257) 2026-05-06 17:39:38 -07:00
mock_grayswan_timeout_server.py implement failopen option default to True on grayswan guardrail (#18266) 2026-01-06 15:17:05 +05:30
mutation_report.py fix: address cross-version CI failures 2026-09-02 14:17:19 -07:00
pre_commit_lint.sh refactor(mcp): extract explicit operation context and dispatch 2026-09-21 12:24:15 -07:00
prisma_generate_if_needed.py fix(lint): generate the prisma client into the gate-owned venv 2026-08-06 01:54:26 -07:00
quickstart.ps1 feat(docker): add a Windows quickstart in PowerShell, and a styled terminal for both quickstarts (#44310) 2026-10-03 13:35:32 -07:00
quickstart.sh feat(docker): add a Windows quickstart in PowerShell, and a styled terminal for both quickstarts (#44310) 2026-10-03 13:35:32 -07:00
ruff_strict_gate.py ci: follow the default branch in development tooling 2026-09-07 14:34:45 -07:00
run_tracing_proxy_local.sh feat: improve Lens dev seeding and live UI (#44468) 2026-10-04 01:03:11 +00:00
seed_request_logs.py refactor(lens): storage-independent trace reads, shared keyset pager, typed read failures (#44422) 2026-10-04 12:39:47 -07:00
seed_tracing_fixtures.py refactor(lens): storage-independent trace reads, shared keyset pager, typed read failures (#44422) 2026-10-04 12:39:47 -07:00
sync-issue-labels.test.ts ci(issue-classifier): name every workflow, script and job after the issue it works on 2026-09-18 11:37:55 -07:00
sync-issue-labels.ts ci(issue-classifier): name every workflow, script and job after the issue it works on 2026-09-18 11:37:55 -07:00
sync_together_ai_models.py fix(together_ai): stop writing context_length as max_output_tokens in the serverless sync 2026-08-29 15:26:44 -07:00
test_agent_mcp_endpoints.sh Agents - assign tools (#22064) 2026-02-25 11:44:30 -08:00
test_guardrails_register_endpoints.sh feat(guardrails): team-based guardrail registration and approval workflow (#22459) 2026-03-02 22:06:49 -08:00
test_quality_gate.py ci: follow the default branch in development tooling 2026-09-07 14:34:45 -07:00
test_tool_allowlist_script.py test(proxy): move middleware, spend_tracking, pass_through, common_utils and root proxy tests into tests/unit/proxy (#44015) 2026-10-01 18:23:31 +00:00
tpm_headline_test.sh fix: atomic TPM rate limit (#27001) 2026-05-05 16:58:07 -07:00
type_check_gate.py chore(ci): drop litellm_internal_staging and litellm_oss_staging references, main is the only trunk (#42745) 2026-09-23 08:14:11 -07:00
type_discipline_gate.py chore(lint): remove the LIT002 mutable-construction rule (#43971) 2026-10-01 12:24:02 -07:00
verify_adaptive_router.py feat: add adaptive routing to litellm 2026-04-18 16:35:17 -07:00
with_dashboard_node.sh fix(bootstrap): fail fast when nvm cannot activate the pinned node 2026-08-04 21:18:58 -07:00