feat(langchain): add ChatAnthropic support to langchain instrumentation by bhumikadangayach · Pull Request #188 · open-telemetry/opentelemetry-python-genai

bhumikadangayach · 2026-06-30T19:26:13Z

Fixes #139

Summary

Adds ChatAnthropic to the list of supported chat models in the LangChain callback handler. Previously only ChatOpenAI and ChatBedrock were instrumented; Anthropic users received no spans at all.

Changes

Add ChatAnthropic to the allowlist in on_chat_model_start
Add "model" param key for model name extraction (Anthropic uses model, not model_name or model_id)
Add "stop_sequences" fallback for stop param (Anthropic's native param name)
Add "max_tokens" fallback for max tokens param
Add langchain-anthropic to test requirements
Add ChatAnthropic fixture and VCR cassette test

Notes

The implementation approach follows the existing pattern for ChatBedrock — provider-specific param key fallbacks in on_chat_model_start. The original fix was prototyped in opentelemetry-python-contrib#4496 by @salaboy before the repo migration; this ports and updates it to the current codebase structure.

Copilot

Pull request overview

Adds ChatAnthropic coverage to the LangChain GenAI instrumentation so Anthropic chat invocations emit spans and model/request parameters are captured consistently with existing OpenAI/Bedrock handling.

Changes:

Extend the on_chat_model_start allowlist and parameter key extraction to support ChatAnthropic (model/stop/max_tokens fallbacks).
Add a ChatAnthropic test fixture, dependency, and a VCR-backed test/cassette to validate span creation and model attribution.

Reviewed changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 3 comments.

Show a summary per file

File	Description
instrumentation/opentelemetry-instrumentation-genai-langchain/src/opentelemetry/instrumentation/genai/langchain/callback_handler.py	Adds `ChatAnthropic` to supported chat models and introduces Anthropic-specific request param fallbacks.
instrumentation/opentelemetry-instrumentation-genai-langchain/tests/test_llm_call.py	Adds a VCR-backed test asserting Anthropic invocation produces a span and captures the request model.
instrumentation/opentelemetry-instrumentation-genai-langchain/tests/conftest.py	Adds a `ChatAnthropic` fixture for use in tests.
instrumentation/opentelemetry-instrumentation-genai-langchain/tests/requirements.txt	Adds `langchain-anthropic` to the test dependencies.
instrumentation/opentelemetry-instrumentation-genai-langchain/tests/cassettes/test_chat_anthropic_claude_sonnet_llm_call.yaml	Adds the recorded cassette for the new Anthropic test.

bhumikadangayach · 2026-07-03T07:28:05Z

            frequency_penalty = params.get("frequency_penalty")
            presence_penalty = params.get("presence_penalty")
-            stop_sequences = params.get("stop")
+            stop_sequences = params.get("stop") or params.get("stop_sequences")


Applied in 242dc03.

bhumikadangayach · 2026-07-03T07:28:27Z

            seed = params.get("seed")
            temperature = params.get("temperature")
-            max_tokens = params.get("max_completion_tokens")
+            max_tokens = params.get("max_completion_tokens") or params.get("max_tokens")


Applied in 242dc03.

bhumikadangayach · 2026-07-03T07:28:20Z

+    spans = span_exporter.get_finished_spans()
+    assert len(spans) == 1
+    span = spans[0]
+    assert span.attributes.get("gen_ai.request.model") == "claude-sonnet-4-5"


Applied in 242dc03.

opentelemetry-pr-dashboard · 2026-06-30T19:29:43Z

This PR has review comments. Review suggestions, whether from maintainers or automated reviewers, aren't always correct or required. Please evaluate each comment on its merits, then make sure each thread has a clear outcome.

For example, link to the commit if you applied a suggestion, explain why it wasn't applied, or ask a follow-up question.

Automation flags a PR for human review once every review thread has a reply or is marked as resolved.

Status across open PRs is visible on the pull request dashboard.

eternalcuriouslearner · 2026-07-02T01:01:41Z

question(non-blocking): Can you please check if we need to add tool support for anthropic?

bhumikadangayach · 2026-07-02T06:01:30Z

@eternalcuriouslearner Good question — the existing on_llm_end handler already captures tool calls via chat_generation.message.tool_calls, which reads from LangChain's unified message format and is provider-agnostic. So tool calls through ChatAnthropic should flow through that path without additional changes. That said, I haven't tested a tool-calling scenario with ChatAnthropic specifically — happy to add a test for it if you'd like that coverage before merging.

eternalcuriouslearner · 2026-07-05T20:31:35Z

@eternalcuriouslearner Good question — the existing on_llm_end handler already captures tool calls via chat_generation.message.tool_calls, which reads from LangChain's unified message format and is provider-agnostic. So tool calls through ChatAnthropic should flow through that path without additional changes. That said, I haven't tested a tool-calling scenario with ChatAnthropic specifically — happy to add a test for it if you'd like that coverage before merging.

That would be great. Please add a test with vcr cassettes if possible. I just want to ensure we are supporting the current workflows this instrumentation supports for bedrock and openai.

bhumikadangayach · 2026-07-07T07:06:19Z

@eternalcuriouslearner Added the VCR tool-calling test for ChatAnthropic. While validating it, found a real bug: the finish_reason extraction was looking for Bedrock's camelCase stopReason key, but ChatAnthropic's response_metadata uses snake_case stop_reason — so tool-call responses were falling through to unknown instead of the correct reason. Fixed the key lookup and confirmed the fix with the new test. All checks are green now.

rads-1996 · 2026-07-08T22:34:55Z

@bhumikadangayach Some of these changes have been addressed in PR - #129. Do you mind rebasing, I believe the tests still do apply and probably the changes for stop sequences. Thanks.

eternalcuriouslearner · 2026-07-08T23:05:41Z

@bhumikadangayach Some of these changes have been addressed in PR - #129. Do you mind rebasing, I believe the tests still do apply and probably the changes for stop sequences. Thanks.

@rads-1996, @wrisa can you please take a look into this pr when you have sometime. Thanks a lot in advance.

bhumikadangayach · 2026-07-09T09:51:46Z

Rebased onto main — thanks for the heads up on #129. The allowlist change was fully superseded by the generic model key lookup there, so I dropped it. Kept the stop_sequences/max_tokens None-check fixes and the Anthropic tool-calling test/fixture, since those weren't covered by #129. All local tests pass (156/156) against the rebased code.

eternalcuriouslearner · 2026-07-10T01:16:19Z

howdy @bhumikadangayach I am looking into this sorry for the delay. Will be getting back on this.

rads-1996

LGTM. Nit: Perhaps the changelog can be rephrased, since the callback handler mostly handles None conditions.

salaboy · 2026-07-10T18:57:07Z

🙌🙌🙌🙌🙌🙌🙌 - Blog: http://salaboy.com <http://salaboy.wordpress.com> - Github user: http://github.com/salaboy - Twitter: http://twitter.com/salaboy - Mauricio "Salaboy" Salatino -

…

On Fri, 10 Jul 2026 at 16:35, Radhika Gupta ***@***.***> wrote: ***@***.**** approved this pull request. LGTM. Nit: Perhaps the changelog can be rephrased, since the callback handler mostly handles None conditions. — Reply to this email directly, view it on GitHub <#188?email_source=notifications&email_token=AACCMXQYMGKR2ZS6KJ22PJ35EEELPA5CNFSNUABKM5UWIORPF5TWS5BNNB2WEL2QOVWGYUTFOF2WK43UKJSXM2LFO4XTINRXGI4DIMBYG4Y2M4TFMFZW63VHNVSW45DJN5XKKZLWMVXHJLDGN5XXIZLSL5RWY2LDNM#pullrequestreview-4672840871>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AACCMXSXYKO4L3WQPSQPYXT5EEELPAVCNFSNUABGKJSXA33TNF2G64TZHMYTEMZXGAYDENJVHE5US43TOVSTWNBXG44TQMRVGQZDNILWAI> . You are receiving this because you were mentioned.Message ID: <open-telemetry/opentelemetry-python-genai/pull/188/review/4672840871@ github.com>

Adds ChatAnthropic to the list of supported chat models in the LangChain callback handler. Previously only ChatOpenAI and ChatBedrock were instrumented; Anthropic users received no spans. Changes: - Add ChatAnthropic to the allowlist in on_chat_model_start - Add 'model' param key for model name extraction (Anthropic uses 'model', not 'model_name' or 'model_id') - Add 'stop_sequences' fallback for stop param (Anthropic's param name) - Add 'max_tokens' fallback for max tokens param - Add langchain-anthropic to test requirements - Add ChatAnthropic fixture and VCR cassette test Fixes open-telemetry#139

…eason

…with tool_use convention

bhumikadangayach · 2026-07-11T15:10:58Z

Thanks for the review, @rads-1996! Good point on the changelog — will tighten the wording to reflect that this is mostly correcting existing None-handling rather than adding new behavior. And @salaboy — glad this finally landed properly, appreciate you flagging the original gap back in the contrib repo!

bhumikadangayach requested a review from a team as a code owner June 30, 2026 19:26

Copilot AI review requested due to automatic review settings June 30, 2026 19:26

github-project-automation Bot added this to GenAI Semantic Conventions and Instrumentation libraries Jun 30, 2026

Copilot started reviewing on behalf of bhumikadangayach June 30, 2026 19:26 View session

opentelemetry-pr-dashboard Bot mentioned this pull request Jun 30, 2026

Pull Request Dashboard #171

Open

Copilot AI reviewed Jun 30, 2026

View reviewed changes

bhumikadangayach force-pushed the feat/chat-anthropic-langchain-support branch from 7544771 to bc6b94c Compare July 9, 2026 09:50

rads-1996 approved these changes Jul 10, 2026

View reviewed changes

bhumikadangayach force-pushed the feat/chat-anthropic-langchain-support branch from a5a5ed3 to 03e78f5 Compare July 11, 2026 14:55

bhumikadangayach added 11 commits July 11, 2026 20:28

changelog: add entry for ChatAnthropic langchain support

580f009

fix: address Copilot review comments

f8b1fd2

fix: rename changelog fragment to match PR number

1774cb7

fix: apply ruff formatting

c1c73d5

fix: apply ruff formatting to test_llm_call.py

a5ffe8f

test(langchain): add VCR tool-calling test for ChatAnthropic

3a48d73

fix: move tool import to top-level

f4c89ae

fix(langchain): correct stop_reason key lookup for Anthropic finish r…

3687ee9

…eason

fix(langchain): apply ruff formatting, align finish_reason assertion …

6d2f2a8

…with tool_use convention

style(langchain): remove blank line per ruff 0.14.1 formatting

32bee0b

style: remove leftover blank lines from conflict resolution

3961919

bhumikadangayach force-pushed the feat/chat-anthropic-langchain-support branch from 03e78f5 to 3961919 Compare July 11, 2026 15:01

docs: clarify changelog entry per rads-1996's review

9f39975

Uh oh!

Conversation

bhumikadangayach commented Jun 30, 2026

Summary

Changes

Notes

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

bhumikadangayach Jul 3, 2026

Choose a reason for hiding this comment

Uh oh!

bhumikadangayach Jul 3, 2026

Choose a reason for hiding this comment

Uh oh!

bhumikadangayach Jul 3, 2026

Choose a reason for hiding this comment

Uh oh!

opentelemetry-pr-dashboard Bot commented Jun 30, 2026

Uh oh!

eternalcuriouslearner commented Jul 2, 2026

Uh oh!

bhumikadangayach commented Jul 2, 2026

Uh oh!

eternalcuriouslearner commented Jul 5, 2026

Uh oh!

bhumikadangayach commented Jul 7, 2026

Uh oh!

rads-1996 commented Jul 8, 2026

Uh oh!

eternalcuriouslearner commented Jul 8, 2026

Uh oh!

bhumikadangayach commented Jul 9, 2026

Uh oh!

eternalcuriouslearner commented Jul 10, 2026

Uh oh!

rads-1996 left a comment

Choose a reason for hiding this comment

Uh oh!

salaboy commented Jul 10, 2026 via email

Uh oh!

bhumikadangayach commented Jul 11, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

5 participants