fix(langchain): Stop double-counting usage in multi-candidate responses

[alexander-alderman-webb]

Description

Take token usage from the first candidate object in each generation, instead of summing token usage from each candidate.

The inner list in LLMResult.generations contains candidate generations (multiple output choices). Candidates do not have independent token usage, but langchain hooks duplicate the token usage on each candidate.

Add a test using a google-genai response, as ChatOpenAI models do not enter the else: branch below:

sentry-python/sentry_sdk/integrations/langchain.py

Lines 769 to 774 in f670a1b

	def _record_token_usage(span: "Union[Span, StreamedSpan]", response: "Any") -> None:
	token_usage = _get_token_usage(response)
	if token_usage:
	input_tokens, output_tokens, total_tokens = _extract_tokens(token_usage)
	else:
	input_tokens, output_tokens, total_tokens = _extract_tokens_from_generations(

Issues

Reminders

• Please add tests to validate your changes, and lint your code using uv run ruff.
• Add GH Issue ID & Linear ID (if applicable)
• PR title should use conventional commit style (feat:, fix:, ref:, meta:)
• For external contributors: CONTRIBUTING.md, Sentry SDK development docs, Discord community

[github-actions]

Codecov Results 📊

✅ 99182 passed | ⏭️ 6527 skipped | Total: 105709 | Pass Rate: 93.83% | Execution Time: 357m 15s

📊 Comparison with Base Branch

Metric	Change
Total Tests	📈 +72
Passed Tests	📈 +25
Failed Tests	📉 -1
Skipped Tests	📈 +48

➖ Removed Tests (1)

View removed tests

• test_continuous_profiler_auto_start_and_stop_sampled_span_streaming[non-experiment-thread]
  • File: tests.profiler.test_continuous_profiler

All tests are passing successfully.

✅ Patch coverage is 88.89%. Project has 2496 uncovered lines.
✅ Project coverage is 89.99%. Comparing base (base) to head (head).

Files with missing lines (1)

File	Patch %	Lines
sentry_sdk/integrations/langchain.py	88.89%	⚠️ 1 Missing and 1 partials

Coverage diff

@@            Coverage Diff             @@
##          main       #PR       +/-##
==========================================
+ Coverage    89.99%    89.99%        —%
==========================================
  Files          193       193         —
  Lines        24946     24947        +1
  Branches      9000      9000         —
==========================================
+ Hits         22451     22451         —
- Misses        2495      2496        +1
- Partials      1435      1435         —

---

Generated by Codecov Action