Add in LLM Observability Prompt Tracking API

[sabrenner]

What Does This Do

Adds a manual prompt track API for the LLM Observability SDK. This works by exposing a prompt object builder to pass in to a new annotatePrompt method. This method only applies the prompt annotation on LLM spans.

Motivation

Further support parity with Node.js and Python SDKs.

Additional Notes

We'll need to follow up with allowing these to be annotated on auto-instrumented LLM spans (ie OpenAI)

Contributor Checklist

• Format the title according to the contribution guidelines
• Assign the type: and (comp: or inst:) labels in addition to any other useful labels
• Avoid using close, fix, or any linking keywords when referencing an issue
  Use solves instead, and assign the PR milestone to the issue
• Update the CODEOWNERS file on source file addition, migration, or deletion
• Update public documentation with any new configuration flags or behaviors
• Once approved, use merge queue to merge the PR

Jira ticket: MLOB-7901

[sabrenner]

@codex review

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 21b2f2e0ba

ℹ️ About Codex in GitHub

Codex has been enabled to automatically 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 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

[sabrenner]

@codex review

[chatgpt-codex-connector]

Codex Review: Didn't find any major issues. More of your lovely PRs please.

Reviewed commit: 866782e2d6

ℹ️ About Codex in GitHub

Codex has been enabled to automatically 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 👍.

When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".

[datadog-datadog-us1-prod]

🎯 Code Coverage (details)
• Patch Coverage: 87.31%
• Overall Coverage: 57.53% (-0.41%)

_{This comment will be updated automatically if new data arrives.
🔗 Commit SHA: dbe9f51 | Docs | Datadog PR Page | Give us feedback!}

[dd-octo-sts]

🟢 Java Benchmark SLOs — All performance SLOs passed

Suite	Status
Startup	🟢 pass

SLO thresholds are defined here based on automatically generated metrics. A warning is raised when results are within 5% of the threshold.

PR vs. master results

Scenario	Candidate	master	Δ (95% CI of mean)
startup:insecure-bank:iast:Agent	14.82 s	14.73 s	[-0.3%; +1.5%] (no difference)
startup:insecure-bank:tracing:Agent	13.70 s	13.73 s	[-1.0%; +0.5%] (no difference)
startup:petclinic:appsec:Agent	17.43 s	17.35 s	[-0.5%; +1.4%] (no difference)
startup:petclinic:iast:Agent	16.88 s	17.48 s	[-8.9%; +2.1%] (unstable)
startup:petclinic:profiling:Agent	16.55 s	17.50 s	[-9.7%; -1.1%] (significantly better)
startup:petclinic:sca:Agent	17.22 s	17.16 s	[-0.7%; +1.4%] (no difference)
startup:petclinic:tracing:Agent	16.45 s	16.73 s	[-2.8%; -0.5%] (maybe better)

Commit: dbe9f517 · CI Pipeline · Benchmarking Platform UI

---

Load and DaCapo benchmarks can be triggered manually in the GitLab pipeline. Results will appear in the Benchmarking Platform UI after completion.

[datadog-datadog-us1-prod]

A later prompt annotation that only adds version or tags silently resets custom RAG context and query variable keys to defaults, corrupting tracking classification for applications that enrich a prompt across multiple calls.

_{📊 Validated against 7 scenarios · Open Bits AI session}

_{🤖 Datadog Autotest · Commit b387155 · What is Autotest? · @DataDog review to ask questions · Any feedback? Reach out in #autotest}