feat: Add sync streaming support for Anthropic instrumentation by vasantteja · Pull Request #4155 · open-telemetry/opentelemetry-python-contrib

vasantteja · 2026-02-01T16:30:36Z

Description

This PR adds sync streaming support for the Anthropic instrumentation. It enables telemetry capture for:

Messages.create(stream=True) - Streaming responses via the create method with stream parameter
Messages.stream() - The dedicated streaming method that returns a MessageStreamManager

Key changes:

Added StreamWrapper class to wrap Stream[RawMessageStreamEvent] and extract telemetry from streaming chunks
Added MessageStreamManagerWrapper to wrap MessageStreamManager context manager
Added MessageWrapper for non-streaming response telemetry extraction
Renamed MessageCreateParams to MessageRequestParams to reflect broader API coverage
Modified messages_create to use manual lifecycle management (start_llm/stop_llm) instead of context manager to support both streaming and non-streaming

Fixes #3949 partially.

Type of change

Please delete options that are not relevant.

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?

Added comprehensive tests for sync streaming functionality:

test_sync_messages_create_streaming - Tests streaming with context manager
test_sync_messages_create_streaming_iteration - Tests direct iteration without context manager
test_sync_messages_create_streaming_connection_error - Tests error handling for streaming
test_sync_messages_stream_basic - Tests Messages.stream() method
test_sync_messages_stream_with_params - Tests stream with additional parameters (temperature, top_p, top_k)
test_sync_messages_stream_token_usage - Tests token usage capture in streaming
test_sync_messages_stream_connection_error - Tests error handling for stream method

All tests use VCR cassettes for reproducible HTTP interaction replay.

Does This PR Require a Core Repo Change?

Yes. - Link to PR:
No.

Checklist:

See contributing.md for styleguide, changelog guidelines, and more.

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

- Add support for Messages.create(stream=True) with StreamWrapper - Add support for Messages.stream() with MessageStreamManagerWrapper - Add MessageWrapper for non-streaming response telemetry - Rename MessageCreateParams to MessageRequestParams - Add comprehensive tests for sync streaming functionality

- Add type: ignore[arg-type] for Union type narrowing in messages_create - Add type: ignore[return-value] for wrapper return types - Add type: ignore[return-value] for __exit__ returning None

...opentelemetry-instrumentation-anthropic/src/opentelemetry/instrumentation/anthropic/patch.py

...opentelemetry-instrumentation-anthropic/src/opentelemetry/instrumentation/anthropic/utils.py

lmolkova · 2026-02-08T18:40:13Z

tagging @anirudha who was interested to review the PR :)

anirudha · 2026-02-08T18:57:11Z

Thanks. Taking a look today

…r handling - Introduce constants for provider name and cache token attributes. - Normalize stop reasons and aggregate cache token fields in MessageWrapper and StreamWrapper. - Enhance tests to validate input token aggregation and stop reason normalization. - Update cassettes for new request and response structures in streaming scenarios.

…d consistency - Simplify constant definitions and normalize function calls in utils.py. - Enhance test cases by removing unnecessary line breaks and improving formatting. - Ensure consistent usage of type hints and comments in test functions.

- Update the pylint directive to disable too-many-arguments warning for better clarity. - Maintain consistency in function signature and improve code readability.

anirudha

Tests all pass locally. Nice work overall — the wrapper separation is clean. One bug to fix (double finalize), rest are suggestions.

Note: conftest.py isn't in this diff so I can't leave a line comment, but scrub_response_headers is a no-op and all new cassettes leak anthropic-organization-id: 455ea6be-bd92-4199-83ec-0c6b39c5c169. Worth scrubbing that or adding it to filter_headers.

Also, the PR description says Fixes #3949 but async streaming isn't covered. Totally fine to scope this to sync only, but Fixes will auto-close the issue on merge. Maybe Partially addresses #3949 instead?

...opentelemetry-instrumentation-anthropic/src/opentelemetry/instrumentation/anthropic/utils.py

...opentelemetry-instrumentation-anthropic/src/opentelemetry/instrumentation/anthropic/patch.py

…tion - Update test cases to validate streaming behavior with various parameters, including token usage and stop reasons. - Introduce new cassettes for different scenarios, ensuring comprehensive coverage of streaming interactions. - Refactor existing tests for clarity and consistency in structure and assertions.

…ocals in test_stream_wrapper_finalize_idempotent function

…eja/opentelemetry-python-contrib into anthropic-sync-streaming

instrumentation-genai/opentelemetry-instrumentation-anthropic/tests/conftest.py

- Introduced a new fixture to instrument Anthropic with EVENT_ONLY content capture mode. - Added tests to verify that content is not captured in span attributes while ensuring log events are emitted correctly. - Updated cassettes to reflect new request and response structures for EVENT_ONLY scenarios. - Enhanced existing tests to cover various content capture scenarios, including streaming and tool usage.

- Simplified the assertion statement in the test_sync_messages_create_event_only_no_content_in_span function to improve readability.

lmolkova

Looks great, left a few minor comments

...opentelemetry-instrumentation-anthropic/src/opentelemetry/instrumentation/anthropic/patch.py

...opentelemetry-instrumentation-anthropic/src/opentelemetry/instrumentation/anthropic/utils.py

instrumentation-genai/opentelemetry-instrumentation-anthropic/tests/test_sync_messages.py

…pic instrumentation.

…e. Introduced MessageWrapper and StreamWrapper classes for telemetry handling. Updated tests to reflect changes in instrumentation behavior.

…ty functions, and update wrapper classes for better clarity and maintainability. Removed unused code and improved type safety in utility functions. Updated tests to reflect changes in the instrumentation behavior.

…imports and streamline finish reason normalization for improved clarity and maintainability.

aabmass · 2026-02-17T18:08:29Z

instrumentation-genai/opentelemetry-instrumentation-anthropic/tests/test_sync_messages.py

+def _skip_if_cassette_missing_and_no_real_key(request):
+    cassette_path = (
+        Path(__file__).parent / "cassettes" / f"{request.node.name}.yaml"
+    )
+    api_key = os.getenv("ANTHROPIC_API_KEY")
+    if not cassette_path.exists() and api_key == "test_anthropic_api_key":
+        pytest.skip(
+            f"Cassette {cassette_path.name} is missing. "
+            "Set a real ANTHROPIC_API_KEY to record it."
+        )


Why would the cassette be missing?

The _skip_if_cassette_missing_and_no_real_key guard is called only by the tool_use and thinking tests — whose cassettes may not exist if the SDK version is too old to record them. It prevents a confusing failure (dummy key hitting the real API) by cleanly skipping the test with a message to set a real key. Lmk if you want to remove this.

aabmass · 2026-02-17T18:13:54Z

...lemetry-instrumentation-anthropic/tests/cassettes/test_sync_messages_create_stop_reason.yaml

Why are there several new requests in here? It doesn't look like test_sync_messages_create_stop_reason was changed to make more request

In case you haven't seen it, you can pass VCR record mode with --vcr-record=<mode>

Honeslty thanks for this. I was using this pytest instrumentation-genai/opentelemetry-instrumentation-anthropic/tests --vcr-record=all and it was appending my requests. I was rerunning this everytime I make a change just to ensure everything is good. This bulked up the cassettes. I deleted the cassettes and recreated them.

…st and response structures, enhance error handling scenarios, and ensure consistency in message formats across various test cases. Removed outdated data and improved clarity in test interactions.

MikeGoldsmith

Looking good, thanks @vasantteja.

I've left some suggestions and things we need to figure out if we want to remove or update.

...ntelemetry-instrumentation-anthropic/src/opentelemetry/instrumentation/anthropic/wrappers.py

...opentelemetry-instrumentation-anthropic/src/opentelemetry/instrumentation/anthropic/patch.py

instrumentation-genai/opentelemetry-instrumentation-anthropic/tests/conftest.py

MikeGoldsmith · 2026-02-18T16:32:10Z

...ntelemetry-instrumentation-anthropic/src/opentelemetry/instrumentation/anthropic/wrappers.py

+_logger = logging.getLogger(__name__)
+
+
+class MessageWrapper:


Could this be a function instead of a class?

It could be a function but I redesigned it as a class as I wanted to maintain code parity with all other wrappers.

...ntelemetry-instrumentation-anthropic/src/opentelemetry/instrumentation/anthropic/wrappers.py

...opentelemetry-instrumentation-anthropic/src/opentelemetry/instrumentation/anthropic/patch.py

...ntelemetry-instrumentation-anthropic/src/opentelemetry/instrumentation/anthropic/wrappers.py

…apper to include content capture logic, improve type safety with explicit casting, and streamline test cases for better clarity. Added new test for streaming response attributes and refined existing tests to ensure consistency in message handling.

…Ds, timestamps, and token usage across various test cases. Refine content capture logic and ensure consistency in message formats, including adjustments to event data and headers for improved clarity and accuracy.

vasantteja requested a review from a team as a code owner February 1, 2026 16:30

github-actions bot assigned codefromthecrypt, karthikscale3, lmolkova, lzchen, nirga and vasantteja Feb 1, 2026

vasantteja removed their assignment Feb 1, 2026

Add changelog entry for sync streaming support

ea0bd94

github-actions bot assigned vasantteja Feb 1, 2026

Fix type checking errors with type: ignore comments

504d0df

- Add type: ignore[arg-type] for Union type narrowing in messages_create - Add type: ignore[return-value] for wrapper return types - Add type: ignore[return-value] for __exit__ returning None

vasantteja force-pushed the anthropic-sync-streaming branch from 99a2596 to 504d0df Compare February 1, 2026 16:57

vasantteja removed their assignment Feb 5, 2026

lmolkova reviewed Feb 8, 2026

View reviewed changes

github-actions bot assigned vasantteja Feb 9, 2026

vasantteja removed their assignment Feb 9, 2026

github-actions bot assigned vasantteja Feb 9, 2026

vasantteja removed their assignment Feb 9, 2026

Refactor argument handling in assert_span_attributes function

e6c83ac

- Update the pylint directive to disable too-many-arguments warning for better clarity. - Maintain consistency in function signature and improve code readability.

github-actions bot assigned vasantteja Feb 9, 2026

anirudha reviewed Feb 9, 2026

View reviewed changes

vasantteja added 4 commits February 8, 2026 23:18

Merge branch 'main' into anthropic-sync-streaming

a011520

Update test_sync_messages.py to disable pylint warning for too-many-l…

2851e4a

…ocals in test_stream_wrapper_finalize_idempotent function

Merge branch 'anthropic-sync-streaming' of https://github.com/vasantt…

3e5cbda

…eja/opentelemetry-python-contrib into anthropic-sync-streaming

Cirilla-zmh reviewed Feb 12, 2026

View reviewed changes

instrumentation-genai/opentelemetry-instrumentation-anthropic/tests/conftest.py Show resolved Hide resolved

vasantteja added 2 commits February 11, 2026 21:49

Refactor assertion in sync messages test for clarity

d1af778

- Simplified the assertion statement in the test_sync_messages_create_event_only_no_content_in_span function to improve readability.

lmolkova reviewed Feb 12, 2026

View reviewed changes

vasantteja added 2 commits February 13, 2026 10:08

Merge branch 'main' into anthropic-sync-streaming

5093cbe

Refactor content capture logic and enhance streaming tests for Anthro…

401e1b1

…pic instrumentation.

github-actions bot assigned DylanRussell Feb 13, 2026

unsetting the model.

15d1b05

vasantteja removed their assignment Feb 14, 2026

lmolkova approved these changes Feb 15, 2026

View reviewed changes

vasantteja mentioned this pull request Feb 15, 2026

Implement OpenAI Responses API instrumentation and examples #4166

Open

11 tasks

Merge branch 'main' into anthropic-sync-streaming

44b97a8

github-actions bot assigned vasantteja Feb 16, 2026

vasantteja removed their assignment Feb 16, 2026

Remove instrumentation for Messages.stream() and refactor related cod…

7800a0e

…e. Introduced MessageWrapper and StreamWrapper classes for telemetry handling. Updated tests to reflect changes in instrumentation behavior.

github-actions bot assigned vasantteja Feb 16, 2026

vasantteja added 3 commits February 16, 2026 20:20

Add message extractors for Anthropic instrumentation.

2590274

Refactor message extractors in Anthropic instrumentation: reorganize …

b4adeec

…imports and streamline finish reason normalization for improved clarity and maintainability.

xrmx requested review from Cirilla-zmh and anirudha February 17, 2026 08:21

aabmass reviewed Feb 17, 2026

View reviewed changes

vasantteja removed their assignment Feb 17, 2026

Update test cassettes for Anthropic instrumentation: streamline reque…

e9c235a

…st and response structures, enhance error handling scenarios, and ensure consistency in message formats across various test cases. Removed outdated data and improved clarity in test interactions.

github-actions bot assigned vasantteja Feb 18, 2026

vasantteja removed their assignment Feb 18, 2026

MikeGoldsmith reviewed Feb 18, 2026

View reviewed changes

github-actions bot assigned vasantteja Feb 19, 2026

Conversation

vasantteja commented Feb 1, 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:

Uh oh!

Uh oh!

Uh oh!

Uh oh!

lmolkova commented Feb 8, 2026

Uh oh!

anirudha commented Feb 8, 2026

Uh oh!

anirudha left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

lmolkova left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

aabmass Feb 17, 2026

Choose a reason for hiding this comment

Uh oh!

vasantteja Feb 18, 2026

Choose a reason for hiding this comment

Uh oh!

aabmass Feb 17, 2026

Choose a reason for hiding this comment

Uh oh!

vasantteja Feb 18, 2026

Choose a reason for hiding this comment

Uh oh!

MikeGoldsmith left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

MikeGoldsmith Feb 18, 2026

Choose a reason for hiding this comment

Uh oh!

vasantteja Feb 19, 2026

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

11 participants

Comments

vasantteja commented Feb 1, 2026 •

edited

Loading