feat(llmobs): [MLOB-2680] add apm span for openai responses endpoint

[XG-xin]

Checklist

• PR author has checked that all the criteria below are met
• The PR description includes an overview of the change
• The PR description articulates the motivation for the change
• The change includes tests OR the PR description describes a testing strategy
• The PR description notes risks associated with the change, if any
• Newly-added code is easy to change
• The change follows the library release note guidelines
• The change includes or references documentation updates if necessary
• Backport labels are set (if applicable)

Reviewer Checklist

• Reviewer has checked that all the criteria below are met
• Title is accurate
• All changes are related to the pull request's stated goal
• Avoids breaking API changes
• Testing strategy adequately addresses listed risks
• Newly-added code is easy to change
• Release note makes sense to a user of the library
• If necessary, author has acknowledged and discussed the performance implications of this PR as reported in the benchmarks PR comment
• Backport labels are set in a manner that is consistent with the release branch maintenance policy

[datadog-datadog-prod-us1]

🟠 Code Quality Violation

variable name is the same as a function parameter (...read more)

A function parameter should only be read and not be modified. If your intent is to modify the value of the parameter, return the value in the function and handle the new value in the caller of the function.

    

[github-actions]

CODEOWNERS have been resolved as:

tests/contrib/openai/cassettes/v1/response_create.yaml                  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai_llmobs.test_response_completion.json  @DataDog/apm-python
ddtrace/contrib/internal/openai/_endpoint_hooks.py                      @DataDog/ml-observability
ddtrace/contrib/internal/openai/patch.py                                @DataDog/ml-observability
tests/contrib/openai/test_openai_llmobs.py                              @DataDog/ml-observability

[github-actions]

Bootstrap import analysis

Comparison of import times between this PR and base.

Summary

The average import time from this PR is: 229 ± 2 ms.

The average import time from base is: 233 ± 2 ms.

The import time difference between this PR and base is: -3.8 ± 0.09 ms.

Import time breakdown

The following import paths have shrunk:

ddtrace.auto 2.173 ms (0.95%)

ddtrace.bootstrap.sitecustomize 1.419 ms (0.62%)

ddtrace.bootstrap.preload 1.419 ms (0.62%)

ddtrace.internal.products 1.419 ms (0.62%)

ddtrace.internal.remoteconfig.client 0.656 ms (0.29%)

ddtrace 0.754 ms (0.33%)

ddtrace._logger 0.081 ms (0.04%)

logging 0.045 ms (0.02%)

traceback 0.045 ms (0.02%)

contextlib 0.045 ms (0.02%)

ddtrace.internal.telemetry 0.036 ms (0.02%)

ddtrace.internal.telemetry.writer 0.036 ms (0.02%)

ddtrace.internal.periodic 0.036 ms (0.02%)

ddtrace.internal._threads 0.036 ms (0.02%)

[pr-commenter]

Benchmarks

Benchmark execution time: 2025-04-30 14:41:26

Comparing candidate commit f928b0f in PR branch xinyuan/openai-responses with baseline commit 6bbb551 in branch main.

Found 14 performance improvements and 1 performance regressions! Performance is the same for 482 metrics, 3 unstable metrics.

scenario:iast_aspects-lower_aspect

• 🟥 execution_time [+207.505ns; +255.262ns] or [+9.154%; +11.260%]

scenario:packagesupdateimporteddependencies-import_many

• 🟩 execution_time [-27.254ms; -27.153ms] or [-99.618%; -99.251%]

scenario:packagesupdateimporteddependencies-import_many_cached

• 🟩 execution_time [-27.932µs; -26.344µs] or [-18.867%; -17.794%]

scenario:packagesupdateimporteddependencies-import_many_stdlib

• 🟩 execution_time [-731.857ms; -728.222ms] or [-100.148%; -99.651%]

scenario:packagesupdateimporteddependencies-import_many_stdlib_cached

• 🟩 execution_time [-730.359ms; -726.657ms] or [-100.231%; -99.723%]

scenario:packagesupdateimporteddependencies-import_many_unknown

• 🟩 execution_time [-30.034ms; -29.921ms] or [-97.491%; -97.125%]

scenario:packagesupdateimporteddependencies-import_many_unknown_cached

• 🟩 execution_time [-251.324µs; -234.297µs] or [-24.311%; -22.664%]

scenario:packagesupdateimporteddependencies-import_one

• 🟩 execution_time [-11.298ms; -11.227ms] or [-100.139%; -99.511%]

scenario:packagesupdateimporteddependencies-import_one_cache

• 🟩 execution_time [-787.277ns; -718.496ns] or [-11.207%; -10.228%]

scenario:packagesupdateimporteddependencies-import_one_stdlib

• 🟩 execution_time [-10.345ms; -10.302ms] or [-100.028%; -99.610%]

scenario:packagesupdateimporteddependencies-import_one_stdlib_cache

• 🟩 execution_time [-646.281ns; -578.189ns] or [-9.374%; -8.386%]

scenario:packagesupdateimporteddependencies-import_one_unknown

• 🟩 execution_time [-19.721ms; -19.639ms] or [-99.978%; -99.561%]

scenario:packagesupdateimporteddependencies-import_one_unknown_cache

• 🟩 execution_time [-846.313ns; -755.410ns] or [-11.998%; -10.709%]

scenario:samplingrules-average_match

• 🟩 execution_time [-187.801µs; -183.599µs] or [-36.167%; -35.358%]

scenario:samplingrules-low_match

• 🟩 execution_time [-347.516µs; -344.182µs] or [-67.487%; -66.840%]

[XG-xin]

Closing this because because I'm working on #13304