fix(llmobs): mark artificially added gen_ai tags on APM spans

[mz1119]

Summary

• When set_gen_ai_apm_tags writes gen_ai.* attributes onto an APM span, it now also sets an internal _dd.llmobs.artificial_gen_ai_tags tag.
• This lets our backend processor distinguish gen_ai tags that ddtrace added artificially from tags a user set directly on the span. Uses the existing _dd. prefix convention for internal, non-user-searchable tags (see _dd.llmobs.* shadow tags in ddtrace/llmobs/_constants.py).

Follow-up to #20083 / #20375.

Testing plan

• Extended tests/llmobs/test_llmobs_gen_ai_apm_tags.py to assert the new tag is set alongside the existing gen_ai.* tags.

🤖 Generated with Claude Code

[chatgpt-codex-connector]

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review	Status	Commit	Review trigger
📝 Code Review	✅ Completed 2026-09-17T21:30:05.246456Z	121091b	PR opened
🔒 Security Review	✅ Completed 2026-09-17T21:29:49.889913Z	121091b	PR opened

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

[datadog-datadog-prod-us1-2]

 

❌ Errors

Your PR has failed checks. Please review the issues below and take necessary action before merging.

🚦 1 Pipeline job failed

Changelog | Validate changelog

View more details · View in GitHub Actions

ℹ️ Info

No other issues found (see more)

🧪 All tests passed
❄️ No new flaky tests detected

Useful? React with 👍 / 👎

_{This comment will be updated automatically if new data arrives.
🔗 Commit SHA: d9638f9 | Docs | View more details | Give us feedback!}

[cit-pr-commenter-54b7da]

Codeowners resolved as

Resolved from the full PR diff against main using the target branch CODEOWNERS file.
CODEOWNERS team requests not listed below are not required by the current file set.

No remaining files require a CODEOWNERS review.

[cit-pr-commenter-54b7da]

Circular import analysis

⚠️ Existing circular imports

There are 1 circular imports that already exist on the base branch and have not been changed by this PR.

ddtrace.errortracking._handled_exceptions.bytecode_injector -> ddtrace.errortracking._handled_exceptions.callbacks -> ddtrace.errortracking._handled_exceptions.collector -> ddtrace.errortracking._handled_exceptions.bytecode_reporting -> ddtrace.errortracking._handled_exceptions.bytecode_injector

[cit-pr-commenter-54b7da]

Dependency direction analysis

⚠️ Existing dependency direction violations

There are 210 dependency direction violations that already exist on the base branch and have not been changed by this PR.

Show existing violations (showing 5 of 210 highest severity)

ddtrace.internal.tracemethods -×-> ddtrace.trace  (internal-core -> product:tracing, score=133)
ddtrace.llmobs._integrations.openai -×-> ddtrace.trace  (product:llmobs -> product:tracing, score=131)
ddtrace.internal.openfeature._span_enrichment -×-> ddtrace.trace  (product:openfeature -> product:tracing, score=131)
ddtrace.llmobs._integrations.crewai -×-> ddtrace.trace  (product:llmobs -> product:tracing, score=131)
ddtrace.llmobs._integrations.langchain -×-> ddtrace.trace  (product:llmobs -> product:tracing, score=131)

To see all violations, download the layers-base.json and layers-pr.json artifacts from this CI job and run:

uv run --script scripts/import-analysis/layers.py compare layers-base.json layers-pr.json

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 121091bce6

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[pr-commenter]

Benchmarks

Benchmark execution time: 2026-09-18 18:52:58

Comparing candidate commit d9638f9 in PR branch max.zhang/mark-artificial-gen-ai-tags with baseline commit 7c1421e in branch main.

📊 Benchmarking dashboard

Found 0 performance improvements and 1 performance regressions! Performance is the same for 590 metrics, 10 unstable metrics, 7 known flaky benchmarks, 17 flaky benchmarks without significant changes.

Explanation

This is an A/B test comparing a candidate commit's performance against that of a baseline commit. Performance changes are noted in the tables below as:

• 🟩 = significantly better candidate vs. baseline
• 🟥 = significantly worse candidate vs. baseline

We compute a confidence interval (CI) over the relative difference of means between metrics from the candidate and baseline commits, considering the baseline as the reference.

If the CI is entirely outside the configured SIGNIFICANT_IMPACT_THRESHOLD (or the deprecated UNCONFIDENCE_THRESHOLD), the change is considered significant.

Feel free to reach out to #apm-benchmarking-platform on Slack if you have any questions.

More details about the CI and significant changes

You can imagine this CI as a range of values that is likely to contain the true difference of means between the candidate and baseline commits.

CIs of the difference of means are often centered around 0%, because often changes are not that big:

---------------------------------(------|---^--------)-------------------------------->
                              -0.6%    0%  0.3%     +1.2%
                                 |          |        |
         lower bound of the CI --'          |        |
sample mean (center of the CI) -------------'        |
         upper bound of the CI ----------------------'

As described above, a change is considered significant if the CI is entirely outside the configured SIGNIFICANT_IMPACT_THRESHOLD (or the deprecated UNCONFIDENCE_THRESHOLD).

For instance, for an execution time metric, this confidence interval indicates a significantly worse performance:

----------------------------------------|---------|---(---------^---------)---------->
                                       0%        1%  1.3%      2.2%      3.1%
                                                  |   |         |         |
       significant impact threshold --------------'   |         |         |
                      lower bound of CI --------------'         |         |
       sample mean (center of the CI) --------------------------'         |
                      upper bound of CI ----------------------------------'

scenario:otelspan-start

• 🟥 execution_time [+2.191ms; +3.262ms] or [+7.007%; +10.431%]

Unstable benchmarks

These benchmarks have a confidence interval too wide to call a change; treat them as noise rather than signal.

scenario:coreapiscenario-context_with_data_listeners

• unstable execution_time [-709.137ns; +784.966ns] or [-6.346%; +7.025%]

scenario:coreapiscenario-core_dispatch_1_listener

• unstable execution_time [-41.708ns; +24.047ns] or [-6.758%; +3.896%]

scenario:coreapiscenario-core_dispatch_50_listeners

• unstable execution_time [-2071.848ns; +1196.599ns] or [-12.080%; +6.977%]

scenario:coreapiscenario-core_dispatch_exception_listeners

• unstable execution_time [-1173.089ns; +1288.097ns] or [-8.922%; +9.797%]

scenario:coreapiscenario-core_dispatch_listeners

• unstable execution_time [-330.430ns; +313.825ns] or [-8.968%; +8.517%]

scenario:coreapiscenario-core_dispatch_no_args_listeners

• unstable execution_time [-316.403ns; +190.302ns] or [-10.721%; +6.448%]

scenario:coreapiscenario-core_dispatch_with_results_1_listener

• unstable execution_time [-68.094ns; +87.942ns] or [-5.864%; +7.574%]

scenario:coreapiscenario-core_dispatch_with_results_50_listeners

• unstable execution_time [-3879.906ns; +4010.523ns] or [-9.530%; +9.850%]

scenario:coreapiscenario-core_dispatch_with_results_listeners

• unstable execution_time [-722.715ns; +839.458ns] or [-8.872%; +10.305%]

scenario:packagesupdateimporteddependencies-import_many_stdlib_cached

• unstable execution_time [-56066.132ns; +56602.819ns] or [-9.547%; +9.639%]

Known flaky benchmarks

These benchmarks are marked as flaky and will not trigger a failure. Modify FLAKY_BENCHMARKS_REGEX to control which benchmarks are marked as flaky.

scenario:httppropagationinject-ids_only

• 🟥 execution_time [+2.729µs; +2.865µs] or [+16.206%; +17.013%]

scenario:iastaspects-casefold_noaspect

• 🟥 execution_time [+38.375µs; +44.704µs] or [+15.898%; +18.520%]

scenario:iastaspects-swapcase_aspect

• 🟥 execution_time [+40.141µs; +45.676µs] or [+14.087%; +16.029%]

scenario:iastaspectsospath-ospathbasename_aspect

• 🟥 execution_time [+118.566µs; +124.853µs] or [+29.314%; +30.868%]

scenario:span-start

• 🟥 execution_time [+1.772ms; +1.954ms] or [+12.273%; +13.533%]

scenario:telemetryaddmetric-1-count-metric-1-times

• 🟥 execution_time [+621.279ns; +671.184ns] or [+22.553%; +24.365%]

scenario:tracer-small

• 🟥 execution_time [+36.759µs; +39.789µs] or [+11.418%; +12.359%]

Known flaky benchmarks without significant changes:

• scenario:errortrackingflasksqli-baseline
• scenario:flasksimple-iast-get
• scenario:iastaspects-casefold_aspect
• scenario:iastaspects-index_aspect
• scenario:iastaspects-ljust_noaspect
• scenario:iastaspects-lower_aspect
• scenario:iastaspects-replace_aspect
• scenario:iastaspects-rstrip_aspect
• scenario:iastaspects-title_noaspect
• scenario:iastaspects-translate_aspect
• scenario:iastaspects-translate_noaspect
• scenario:iastaspects-upper_noaspect
• scenario:iastaspectssplit-rsplit_aspect
• scenario:packagespackageforrootmodulemapping-cache_off
• scenario:packagespackageforrootmodulemapping-cache_on
• scenario:sethttpmeta-all-enabled
• scenario:telemetryaddmetric-record-100-metrics

[ncybul]

LGTM besides a couple minor comments. Before we merge this, let's test this in conjunction with your backend PR.