chore(llmobs): try to fix oom ci errors for openai agents

[lievan]

Make sure we clean up all the references we have to raw openai sdk spans

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

[github-actions]

CODEOWNERS have been resolved as:

tests/contrib/openai_agents/requirements.txt                            @DataDog/apm-core-python @DataDog/apm-idm-python
ddtrace/contrib/internal/openai_agents/patch.py                         @DataDog/apm-core-python @DataDog/apm-idm-python
ddtrace/contrib/internal/openai_agents/processor.py                     @DataDog/apm-core-python @DataDog/apm-idm-python
ddtrace/llmobs/_integrations/openai_agents.py                           @DataDog/ml-observability
tests/contrib/openai_agents/test_openai_agents_patch.py                 @DataDog/apm-core-python @DataDog/apm-idm-python
tests/contrib/patch.py                                                  @DataDog/apm-core-python @DataDog/apm-idm-python

[github-actions]

Bootstrap import analysis

Comparison of import times between this PR and base.

Summary

The average import time from this PR is: 234 ± 3 ms.

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

The import time difference between this PR and base is: 0.7 ± 0.1 ms.

Import time breakdown

The following import paths have grown:

ddtrace.auto 0.377 ms (0.16%)

ddtrace.bootstrap.sitecustomize 0.377 ms (0.16%)

ddtrace.bootstrap.preload 0.377 ms (0.16%)

ddtrace.internal.products 0.188 ms (0.08%)

ddtrace.internal.remoteconfig.worker 0.097 ms (0.04%)

ddtrace.internal.symbol_db.remoteconfig 0.091 ms (0.04%)

ddtrace.internal.symbol_db.symbols 0.091 ms (0.04%)

ddtrace.settings.symbol_db 0.091 ms (0.04%)

ddtrace.internal.runtime.runtime_metrics 0.108 ms (0.05%)

ddtrace.settings.profiling 0.081 ms (0.03%)

ddtrace.internal.datadog.profiling.stack_v2 0.081 ms (0.03%)

ddtrace.internal.datadog.profiling.stack_v2._stack_v2 0.081 ms (0.03%)

The following import paths have shrunk:

ddtrace.auto 2.088 ms (0.89%)

ddtrace.bootstrap.sitecustomize 1.430 ms (0.61%)

ddtrace.bootstrap.preload 1.430 ms (0.61%)

ddtrace.internal.products 1.274 ms (0.55%)

ddtrace.internal.remoteconfig.client 0.586 ms (0.25%)

ddtrace.internal.symbol_db.remoteconfig 0.128 ms (0.05%)

ddtrace.internal.symbol_db.symbols 0.128 ms (0.05%)

ddtrace.settings.dynamic_instrumentation 0.061 ms (0.03%)

ddtrace.settings.crashtracker 0.094 ms (0.04%)

ddtrace.settings.profiling 0.063 ms (0.03%)

ddtrace 0.658 ms (0.28%)

[pr-commenter]

Benchmarks

Benchmark execution time: 2025-04-04 20:07:22

Comparing candidate commit 89db686 in PR branch evan.li/fix-test-oai with baseline commit 9a5fd14 in branch main.

Found 0 performance improvements and 0 performance regressions! Performance is the same for 498 metrics, 2 unstable metrics.