feat(openai): Add `gen_ai.request.reasoning.level` to OpenAI spans by pabloDeputter · Pull Request #6892 · getsentry/sentry-python · GitHub

Description

Add gen_ai.request.reasoning.level to OpenAI spans for:

Responses API via reasoning.effort
Chat Completions API via reasoning_effort

Issues

Refs: #6877 & #6878; PY-2620 & PY-2621

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

…s Api Read `effort` field from the `reasoning`request parameter from `responses.create()` and set it on the gen_ai span as `gen_ai.request.reasoning_level`. `reasoning`may be passed as a dict or as the SDK's `Reasoning`object. Refs #6878 Refs PY-2621

…ons Api Read `reasoning_effort` request parameter from `chat.completions.create()` and set it on the gen_ai span as `gen_ai.request.reasoning_level`. Refs #6877 Refs PY-2620

Codecov Results 📊

✅ 98651 passed | ⏭️ 6806 skipped | Total: 105457 | Pass Rate: 93.55% | Execution Time: 360m 11s

📊 Comparison with Base Branch

Metric	Change
Total Tests	📈 +564
Passed Tests	📈 +373
Failed Tests	📉 -1
Skipped Tests	📈 +192

➖ Removed Tests (1)

View removed tests

test_circular_references_span_streaming
- File: tests.tracing.test_misc

All tests are passing successfully.

✅ Patch coverage is 100.00%. Project has 2508 uncovered lines.
✅ Project coverage is 89.72%. Comparing base (base) to head (head).

Coverage diff

@@            Coverage Diff             @@
##          main       #PR       +/-##
==========================================
+ Coverage    89.69%    89.72%    +0.03%
==========================================
  Files          193       193         —
  Lines        24437     24402       -35
  Branches      8660      8648       -12
==========================================
+ Hits         21919     21894       -25
- Misses        2518      2508       -10
- Partials      1398      1400        +2

Generated by Codecov Action

Can you also co-locate assertions with assertions on other request configuration such asgen_ai.request.top_p, gen_ai.request.temperature, etc ...

That way, we ensure that the attribute is set in all scenarios we test against, such as streaming and non-streaming, sync and async, etc ...

Only extract `effort` from dict `reasoning` in the Responses API. Refs #6878

Cursor Bugbot has reviewed your changes and found 2 potential issues.

❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.

Reviewed by Cursor Bugbot for commit a509b01. Configure here.

Nice, LGTM!

As discussed in person, adding the assertions to existing tests is ugly because it's not available on old openai versions. Feel free to go with your original approach with adding a few new tests @pabloDeputter!

…rom Completions API

You can merge whenever you've passed CI since I've approved the PR already.
We trust each other to make the relevant changes and merge when we approve with a comment

…etsentry#6892) ### Description Add `gen_ai.request.reasoning.level` to OpenAI spans for: - Responses API via `reasoning.effort` - Chat Completions API via `reasoning_effort` #### Issues Refs: getsentry#6877 & getsentry#6878; PY-2620 & PY-2621

pabloDeputter added 2 commits July 24, 2026 16:32

feat(openai): Add gen_ai.request.reasoning.level to OpenAI Completi…

ff2be99

…ons Api Read `reasoning_effort` request parameter from `chat.completions.create()` and set it on the gen_ai span as `gen_ai.request.reasoning_level`. Refs #6877 Refs PY-2620

pabloDeputter marked this pull request as ready for review July 27, 2026 11:56

pabloDeputter requested a review from a team as a code owner July 27, 2026 11:56

cursor Bot reviewed Jul 27, 2026

View reviewed changes

Comment thread sentry_sdk/consts.py Outdated

fix(openai): Correct typo in GEN_AI_REQUEST_REASONING_LEVEL

ec38233

alexander-alderman-webb reviewed Jul 27, 2026

View reviewed changes

Comment thread sentry_sdk/integrations/openai.py Outdated

pabloDeputter added 2 commits July 27, 2026 14:37

fix(openai): Simplify reasoning effort extraction in Responses API

9156169

Only extract `effort` from dict `reasoning` in the Responses API. Refs #6878

test(openai): Add assertions to non-streaming and streaming tests

a509b01

cursor Bot reviewed Jul 27, 2026

View reviewed changes

Comment thread tests/integrations/openai/test_openai.py Outdated

Comment thread sentry_sdk/integrations/openai.py

alexander-alderman-webb approved these changes Jul 27, 2026

View reviewed changes

sentry-warden Bot reviewed Jul 27, 2026

View reviewed changes

Comment thread sentry_sdk/integrations/openai.py

test(openai): Remove breakingreasoning_effort args and assertions f…

b623ce7

…rom Completions API

pabloDeputter merged commit 54f77b9 into master Jul 27, 2026
523 of 529 checks passed

pabloDeputter deleted the pablo/genai-request-reasoning-level branch July 27, 2026 14:14

sentry-release-bot Bot mentioned this pull request Aug 10, 2026

publish: getsentry/sentry-python@2.67.0 getsentry/publish#9190

Closed

6 tasks

feat(openai): Add `gen_ai.request.reasoning.level` to OpenAI spans by pabloDeputter · Pull Request #6892 · getsentry/sentry-python · GitHub

Uh oh!

feat(openai): Add gen_ai.request.reasoning.level to OpenAI spans - #6892

feat(openai): Add gen_ai.request.reasoning.level to OpenAI spans#6892
pabloDeputter merged 6 commits into
masterfrom
pablo/genai-request-reasoning-level

pabloDeputter commented Jul 27, 2026 •
edited
Loading

Uh oh!

Uh oh!

github-actions Bot commented Jul 27, 2026 •
edited
Loading

Uh oh!

Uh oh!

Uh oh!

alexander-alderman-webb left a comment

Uh oh!

Uh oh!

cursor Bot left a comment

Uh oh!

Uh oh!

Uh oh!

alexander-alderman-webb left a comment •
edited
Loading

Uh oh!

Uh oh!

Uh oh!

alexander-alderman-webb commented Jul 27, 2026

Uh oh!

alexander-alderman-webb commented Jul 27, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

feat(openai): Add `gen_ai.request.reasoning.level` to OpenAI spans by pabloDeputter · Pull Request #6892 · getsentry/sentry-python · GitHub

Uh oh!

feat(openai): Add gen_ai.request.reasoning.level to OpenAI spans - #6892

feat(openai): Add gen_ai.request.reasoning.level to OpenAI spans#6892pabloDeputter merged 6 commits intomastergetsentry/sentry-python:masterfrom pablo/genai-request-reasoning-levelgetsentry/sentry-python:pablo/genai-request-reasoning-levelCopy head branch name to clipboard

Conversation

pabloDeputter commented Jul 27, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Issues

Reminders

Uh oh!

github-actions Bot commented Jul 27, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Results 📊

📊 Comparison with Base Branch

➖ Removed Tests (1)

Uh oh!

Uh oh!

alexander-alderman-webb left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

cursor Bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

alexander-alderman-webb left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Uh oh!

alexander-alderman-webb commented Jul 27, 2026

Uh oh!

alexander-alderman-webb commented Jul 27, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

feat(openai): Add gen_ai.request.reasoning.level to OpenAI spans#6892
pabloDeputter merged 6 commits into
masterfrom
pablo/genai-request-reasoning-level

pabloDeputter commented Jul 27, 2026 •
edited
Loading

github-actions Bot commented Jul 27, 2026 •
edited
Loading

alexander-alderman-webb left a comment •
edited
Loading