[opentelemetry-instrumentation-genai-anthropic] Capture reasoning token counts on messages

[rads-1996]

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?

Please describe the tests that you ran to verify your changes. Provide
instructions so we can reproduce. List any relevant details for your test
configuration.

• uv run tox -e py312-test-instrumentation-genai-anthropic-- -q
• uv run tox -e py312-test-instrumentation-genai-anthropic-conformance -- -q
• uv run --python 3.12 tox -e lint-instrumentation-genai-anthropic

Checklist

See CONTRIBUTING.md
for the style guide, changelog guidance, and more.

• Followed the style guidelines of this project
• Changelog updated if the change requires an entry
• Unit tests added
• Documentation updated

[opentelemetry-pr-dashboard]

Pull request dashboard status

Merged · refreshed 2026-10-01 17:09 UTC

Status above doesn't look right?

• Anything look wrong? Report it with what you expected; it helps us improve the dashboard.

[Copilot]

Copilot review overview

🟡 Changes recommended

One or more issues must be addressed before approval.

Get a fresh assessment by requesting another Copilot review.

Review effort: Lite
Findings: 1

Open (1)

• Add streaming coverage for reasoning-token extraction · New

What changed in this PR

Adds Anthropic reasoning-token telemetry using gen_ai.usage.reasoning.output_tokens.

Changes:

• Extracts thinking_tokens from response usage.
• Adds sync/async assertions and updated VCR fixtures.
• Adds a changelog entry.

File	Description
instrumentation/​opentelemetry-instrumentation-genai-anthropic/​tests/​test_sync_messages.py	Updated as part of this pull request.
instrumentation/​opentelemetry-instrumentation-genai-anthropic/​tests/​test_messages_extractors.py	Updated as part of this pull request.
instrumentation/​opentelemetry-instrumentation-genai-anthropic/​tests/​test_async_messages.py	Updated as part of this pull request.
instrumentation/​opentelemetry-instrumentation-genai-anthropic/​tests/​cassettes/​test_sync_messages_create_captures_thinking_content.yaml	Updated as part of this pull request.
instrumentation/​opentelemetry-instrumentation-genai-anthropic/​tests/​cassettes/​test_async_messages_create_captures_thinking_content.yaml	Updated as part of this pull request.
instrumentation/​opentelemetry-instrumentation-genai-anthropic/​src/​opentelemetry/​instrumentation/​genai/​anthropic/​messages_extractors.py	Updated as part of this pull request.
instrumentation/​opentelemetry-instrumentation-genai-anthropic/​.changelog/​779.added	Updated as part of this pull request.

---

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

[Copilot]

Copilot review overview

🟢 Approval recommended

No unresolved issues were identified that would block approval.

Review effort: Lite
Findings: None

Resolved since last review (1)

• Add streaming coverage for reasoning-token extraction

[eternalcuriouslearner]

LGTM!! Should we add the attributes to conformance test suite?

[rads-1996]

LGTM!! Should we add the attributes to conformance test suite?

So, this PR already verifies that the attribute is correctly emitted in the test_async_wrappers and test_sync_wrappers proving that the integration tests work correctly, I don't see an additional value in adding the attribute to the conformace test suite, moreover other instrumentations like openai and langchain also do not add this attribute in their conformance test suite. WDYT?