dd-trace-py chore(llmobs): dac strip io from OpenAI

Remove potentially sensitive i/o data from apm spans. This way, prompt and completion data will only appear on the llm obs spans, which are/will be subject to data access controls.

Mostly, this just removes io tag sets. A few things (mostly metrics) have llmobs tags dependent on span tags, so there is a bit more refactoring there.

Let me know if I removed anything that should really stay, or if I missed something that should be restricted.

This one does a lot that the others don't. I've left things like audio transcript and image/file retrieval that we don't duplicate.

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

Jun 26 '25 18:06 jsimpher

CODEOWNERS have been resolved as:

releasenotes/notes/remove-io-data-from-apm-span-openai-integration-81f3ae914a5d2faf.yaml  @DataDog/apm-python
ddtrace/contrib/internal/openai/_endpoint_hooks.py                      @DataDog/ml-observability
ddtrace/contrib/internal/openai/patch.py                                @DataDog/ml-observability
ddtrace/contrib/internal/openai/utils.py                                @DataDog/ml-observability
ddtrace/llmobs/_integrations/openai.py                                  @DataDog/ml-observability
ddtrace/llmobs/_integrations/utils.py                                   @DataDog/ml-observability
ddtrace/llmobs/_utils.py                                                @DataDog/ml-observability
tests/contrib/openai/test_openai_llmobs.py                              @DataDog/ml-observability
tests/contrib/openai/test_openai_v1.py                                  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_acompletion.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_azure_openai_chat_completion.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_azure_openai_completion.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_azure_openai_embedding.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_chat_completion.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_chat_completion_function_calling.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_chat_completion_image_input.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_chat_completion_stream.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_completion.json   @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_completion_stream.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_create_moderation.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_embedding.json    @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_embedding_array_of_token_arrays.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_embedding_string_array.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_embedding_token_array.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_file_create.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_file_delete.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_file_download.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_file_list.json    @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_file_retrieve.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_image_b64_json_response.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_image_create.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_misuse.json       @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_model_delete.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_model_list.json   @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_model_retrieve.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_response.json     @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_response_error.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_response_stream.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_response_tools.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_response_tools_stream.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai.test_span_finish_on_stream_error.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai_v1.test_completion_stream_est_tokens.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai_v1.test_empty_streamed_chat_completion_resp_returns.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai_v1.test_empty_streamed_completion_resp_returns.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai_v1.test_empty_streamed_response_resp_returns.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai_v1.test_integration_async.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai_v1.test_integration_service_name[None-None].json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai_v1.test_integration_service_name[None-v0].json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai_v1.test_integration_service_name[None-v1].json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai_v1.test_integration_service_name[mysvc-None].json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai_v1.test_integration_service_name[mysvc-v0].json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai_v1.test_integration_service_name[mysvc-v1].json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai.test_openai_v1.test_integration_sync.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai_agents.test_openai_agents.test_openai_agents.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai_agents.test_openai_agents.test_openai_agents_streaming.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai_agents.test_openai_agents.test_openai_agents_sync.json  @DataDog/ml-observability
tests/snapshots/tests.contrib.openai_agents.test_openai_agents.test_openai_agents_with_tool_error.json  @DataDog/ml-observability

Jun 26 '25 18:06 github-actions[bot]

Bootstrap import analysis

Comparison of import times between this PR and base.

Summary

The average import time from this PR is: 278 ± 3 ms.

The average import time from base is: 283 ± 7 ms.

The import time difference between this PR and base is: -4.8 ± 0.2 ms.

Import time breakdown

The following import paths have shrunk:

ddtrace.auto 2.205 ms (0.79%)

ddtrace.bootstrap.sitecustomize 1.520 ms (0.55%)

ddtrace.bootstrap.preload 1.520 ms (0.55%)

ddtrace.internal.remoteconfig.client 0.703 ms (0.25%)

ddtrace 0.685 ms (0.25%)

ddtrace.internal._unpatched 0.034 ms (0.01%)

json 0.034 ms (0.01%)

json.decoder 0.034 ms (0.01%)

re 0.034 ms (0.01%)

enum 0.034 ms (0.01%)

types 0.034 ms (0.01%)

Jun 26 '25 18:06 github-actions[bot]

Benchmarks

Benchmark execution time: 2025-07-15 19:37:22

Comparing candidate commit 94ab642ef45f55065fb35ee8338f0670d9ea3d90 in PR branch jsimpher/dac-strip-io-from-openai with baseline commit c81e59493b4d3d505795985ab898c01de9d03595 in branch main.

Found 0 performance improvements and 0 performance regressions! Performance is the same for 508 metrics, 2 unstable metrics.

Jun 26 '25 19:06 pr-commenter[bot]

/merge

Jul 17 '25 13:07 jsimpher

View all feedbacks in Devflow UI.

2025-07-17 13:14:55 UTC :information_source: Start processing command /merge

2025-07-17 13:15:15 UTC :information_source: MergeQueue: waiting for PR to be ready

This merge request is not mergeable yet, because of pending checks/missing approvals. It will be added to the queue as soon as checks pass and/or get approvals. Note: if you pushed new commits since the last approval, you may need additional approval. You can remove it from the waiting list with /remove command.

2025-07-17 13:17:25 UTC :information_source: MergeQueue: merge request added to the queue

The expected merge time in main is approximately 2h (p90).

2025-07-17 15:03:46 UTC :information_source: MergeQueue: This merge request was merged

Jul 17 '25 13:07 dd-devflow-routing-codex[bot]