Enhance LangChain GenAI semconv tracing by nagkumar91 · Pull Request #4389 · open-telemetry/opentelemetry-python-contrib

nagkumar91 · 2026-04-02T16:41:36Z

Description

This PR expands the LangChain instrumentor toward semconv-first GenAI coverage and folds in the review/test follow-up fixes needed to make the package consistent with contrib expectations.

The main changes are:

semconv-aligned model, agent, workflow, tool, and retriever tracing
richer message/tool/retriever event emission and improved LangGraph/W3C parent propagation
review follow-up fixes for callback/span handling plus VCR compatibility with current pytest-recording
final changelog, typecheck, and spellcheck cleanup for the package

Type of change

Bug fix (non-breaking change which fixes an issue)
New feature (non-breaking change which adds functionality)
Breaking change (fix or feature that would cause existing functionality to not work as expected)
This change requires a documentation update

How Has This Been Tested?

python3 -m pytest instrumentation-genai/opentelemetry-instrumentation-langchain/tests
uv tool run ruff check src tests (from instrumentation-genai/opentelemetry-instrumentation-langchain)
tox -e typecheck
tox -e spellcheck

Does This PR Require a Core Repo Change?

Yes. - Link to PR:
No.

Checklist:

Followed the style guidelines of this project
Changelogs have been updated
Unit tests have been added
Documentation has been updated

Notes

Package changelog updated at instrumentation-genai/opentelemetry-instrumentation-langchain/CHANGELOG.md.
test_gemini is skipped when tests/cassettes/test_gemini.yaml is absent and no real Google API key is available for recording.
Bedrock cassette replay now ignores path drift caused by newer inference-profile/model request shapes while keeping the recorded response assertions intact.

Add on_llm_new_token callback method to track streaming chunk timing: - Records time_to_first_chunk (TTFC) on first token arrival - Records time_per_output_chunk (TPOC) between subsequent tokens - Uses timeit.default_timer() consistent with TelemetryHandler timing - Builds metric attributes matching InvocationMetricsRecorder pattern - Cleans up streaming state in on_llm_end and on_llm_error Creates two new histograms using semconv metric names: - gen_ai.client.operation.time_to_first_chunk - gen_ai.client.operation.time_per_output_chunk Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Major enhancement to the LangChain instrumentor bringing it to parity with the GenAI semantic conventions for spans, metrics, and events. New callback handlers: - on_chain_start/end/error: invoke_agent and invoke_workflow spans - on_tool_start/end/error: execute_tool spans with tool attributes - on_retriever_start/end/error: execute_tool spans with retriever semantics - on_llm_start: text_completion spans for non-chat models - on_llm_new_token: streaming timing metrics (TTFC, TPOC) - on_agent_action/finish: agent lifecycle support New infrastructure: - operation_mapping.py: safe callback-to-semconv classification - semconv_attributes.py: per-operation attribute matrix - span_manager.py: full span lifecycle with hierarchy tracking - utils.py: provider detection, server address, W3C propagation - message_formatting.py: structured message serialization with redaction - content_recording.py: content capture policy integration - event_emitter.py: semconv-aligned events for non-LLM spans Key capabilities: - Removed ChatOpenAI/ChatBedrock restriction, supports any LLM - Full request/response attribute extraction per semconv - Parent-child hierarchy with LangGraph support (filtering, goto, stacks) - Token usage accumulation from LLM to agent spans - W3C trace context propagation (incoming traceparent/tracestate) - Cache token attributes (cache_read, cache_creation) - Streaming metrics (time_to_first_chunk, time_per_output_chunk) - 276 unit and e2e tests Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Apply the follow-up LangChain review fixes, wire non-LLM event emission, correct experimental content capture behavior, clean ignored-run state, and repair the package's VCR-based integration tests under the current pytest-recording setup. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

MikeGoldsmith · 2026-04-07T14:50:20Z

Thanks for the PR @nagkumar91. At over 7k lines of code, this is nearly impossible to approve with confidence.

Could you break this up in to smaller chunks? For example, your PR desc breaks down the changes into 4 distint areas, I'd suggest trying to use those as areas to focus on per PR.

MikeGoldsmith

Forgot to add a review yesterday. I'd really like to see this PR broken down into smaller parts.

…nt recording modules Add foundation modules for enhanced LangChain GenAI semantic convention tracing: - semconv_attributes.py: Per-operation attribute matrix based on OTel GenAI semantic conventions. Single source of truth for which attributes apply to which operations (chat, text_completion, invoke_agent, execute_tool, invoke_workflow, retrieval). - operation_mapping.py: Callback-to-semconv operation mapping. Maps each LangChain callback to the correct GenAI semantic convention operation name. Includes heuristic classification for on_chain_start callbacks (agents vs workflows vs internal plumbing) and LangGraph marker recognition. - content_recording.py: Thin integration layer over the shared genai content capture utilities. Provides clear APIs for the callback handler to decide what content should be recorded on spans and events. Part 1 of a series breaking down open-telemetry#4389 into smaller reviewable PRs. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

…propagation utilities Add utility modules for the LangChain instrumentor: - utils.py: Provider name inference from LangChain callback data (ls_provider, base_url, class name, endpoint fields), server address/port extraction, and W3C trace context header extraction and propagation support. - message_formatting.py: Message, tool, and document serialization with content-redaction support. Converts LangChain message objects into the compact JSON format expected by OpenTelemetry GenAI semantic conventions. Part 2 of a series breaking down open-telemetry#4389 into smaller reviewable PRs. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Enhance the span lifecycle manager and add event emission for non-LLM GenAI operations: - span_manager.py: Enhanced with ignored-run walkthrough (re-parenting children of skipped internal runs), per-thread agent stacks for hierarchy tracking, token usage accumulation and propagation to parent agent spans, and LangGraph Command(goto=...) transition support. - event_emitter.py: Emits semantic-convention-aligned log-record events for tool, agent, and retriever spans. All event emission is gated behind the content policy. Uses LogRecord instances linked to the active span context. Part 3 of a series breaking down open-telemetry#4389 into smaller reviewable PRs. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

…h wiring Wire all foundation modules into the callback handler and add comprehensive callback implementations: - callback_handler.py: Enhanced with model start/end/error (improved provider and server inference), chain start/end/error (with operation classification), agent action/finish, LLM new token (streaming chunk timing metrics), tool start/end/error, and retriever start/end/error callbacks. - __init__.py: Wire SpanManager, EventEmitter, and tracer into the instrumentor's _instrument method. - conftest.py: Updated test infrastructure for enhanced callback testing. Part 4 of a series breaking down open-telemetry#4389 into smaller reviewable PRs. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Add remaining test coverage for the LangChain enhanced tracing: - test_tool_callbacks.py: Tool start/end/error callbacks, content redaction, tool definitions formatting, event emission - test_retriever_callbacks.py: Retriever start/end/error callbacks, document serialization, query capture, content redaction - test_e2e_scenarios.py: End-to-end scenarios covering multi-step agent workflows, nested chains, concurrent execution, error propagation Update CHANGELOG.md with the enhancement entry. Part 5 (final) of a series breaking down open-telemetry#4389 into smaller reviewable PRs. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

nagkumar91 · 2026-04-16T22:04:01Z

PR Split into Smaller Reviews

This PR has been broken down into 5 smaller, independently reviewable PRs to make the review process more manageable:

#	PR	Focus	Lines
1	#4450	Foundation: semconv attributes, operation mapping, content recording	~1,280
2	#4451	Utils: provider inference, message formatting, W3C propagation	~1,420
3	#4452	Infrastructure: span manager enhancements + event emitter	~1,250
4	#4453	Integration: callback handler (all callbacks) + wiring	~1,990
5	#4454	Tests: tool/retriever/E2E tests + changelog	~1,500

Merge order: 1 → 2 → 3 → 4 → 5 (each PR includes changes from previous PRs)

Once the series is merged, this PR can be closed.

nagkumar91 and others added 3 commits April 1, 2026 20:46

nagkumar91 requested a review from a team as a code owner April 2, 2026 16:41

github-project-automation Bot added this to Python PR digest Apr 2, 2026

fix(langchain): clear PR checks

05e1357

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

tammy-baylis-swi moved this to Ready for review in Python PR digest Apr 2, 2026

MikeGoldsmith requested changes Apr 8, 2026

View reviewed changes

github-project-automation Bot moved this from Ready for review to Reviewed PRs that need fixes in Python PR digest Apr 8, 2026

nagkumar91 mentioned this pull request Apr 16, 2026

feat(langchain): add semconv attributes, operation mapping, and content recording modules [1/5] #4450

Open

3 tasks

nagkumar91 mentioned this pull request Apr 16, 2026

feat(langchain): add provider inference, message formatting, and W3C propagation utilities [2/5] #4451

Open

3 tasks

nagkumar91 mentioned this pull request Apr 16, 2026

feat(langchain): enhance span manager and add event emitter [3/5] #4452

Open

3 tasks

nagkumar91 mentioned this pull request Apr 16, 2026

feat(langchain): add model, chain, agent, and streaming callback handlers [4/5] #4453

Open

3 tasks

nagkumar91 mentioned this pull request Apr 16, 2026

feat(langchain): add tool, retriever E2E tests and changelog [5/5] #4454

Open

4 tasks

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Enhance LangChain GenAI semconv tracing#4389

Enhance LangChain GenAI semconv tracing#4389
nagkumar91 wants to merge 4 commits intoopen-telemetry:mainfrom
nagkumar91:feature/langchain-instrumentor-enhanced-tracing

nagkumar91 commented Apr 2, 2026 •

edited

Loading

Uh oh!

MikeGoldsmith commented Apr 7, 2026 •

edited

Loading

Uh oh!

MikeGoldsmith left a comment

Uh oh!

nagkumar91 commented Apr 16, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

nagkumar91 commented Apr 2, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Type of change

How Has This Been Tested?

Does This PR Require a Core Repo Change?

Checklist:

Notes

Uh oh!

MikeGoldsmith commented Apr 7, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

MikeGoldsmith left a comment

Choose a reason for hiding this comment

Uh oh!

nagkumar91 commented Apr 16, 2026

PR Split into Smaller Reviews

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

nagkumar91 commented Apr 2, 2026 •

edited

Loading

MikeGoldsmith commented Apr 7, 2026 •

edited

Loading