feat(llmobs): [MLOB-2662] [MLOB-3100] add agent manifest

[ncybul]

This PR adds instrumentation for the agent manifest for our LLM Obs agentic integrations (minus LangGraph which will be covered in @sabrenner's PR). I have been using this doc to track what information is available in the Agent Manifest for each integration, but a summary is below:

Agent Manifest Schema

Crew AI

• Framework
• Name
• Goal
• Backstory
• Model
• Model Settings
• Tools
• Handoffs
• Code Execution Permissions
• Max Iterations

Open AI Agents

• Framework
• Name
• Instructions
• Handoff Description
• Model
• Model Settings
• Tools
• Handoffs
• Guardrails

PydanticAI

• Framework
• Name
• Instructions
• System Prompts
• Model
• Model Settings
• Tools
• Dependencies

Next Steps

• Make the current Agent Manifest UI work for the new fields that have been added

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:

releasenotes/notes/tag-agent-manifest-fa6c399b5ec46e18.yaml             @DataDog/apm-python
tests/contrib/openai_agents/cassettes/test_single_agent_with_ootb_tools.yaml  @DataDog/ml-observability
ddtrace/contrib/internal/openai_agents/patch.py                         @DataDog/ml-observability
ddtrace/llmobs/_constants.py                                            @DataDog/ml-observability
ddtrace/llmobs/_integrations/crewai.py                                  @DataDog/ml-observability
ddtrace/llmobs/_integrations/openai_agents.py                           @DataDog/ml-observability
ddtrace/llmobs/_integrations/pydantic_ai.py                             @DataDog/ml-observability
ddtrace/llmobs/_integrations/utils.py                                   @DataDog/ml-observability
ddtrace/llmobs/_llmobs.py                                               @DataDog/ml-observability
ddtrace/llmobs/_utils.py                                                @DataDog/ml-observability
tests/contrib/crewai/test_crewai_llmobs.py                              @DataDog/ml-observability
tests/contrib/openai_agents/conftest.py                                 @DataDog/ml-observability
tests/contrib/openai_agents/test_openai_agents_llmobs.py                @DataDog/ml-observability
tests/contrib/pydantic_ai/test_pydantic_ai_llmobs.py                    @DataDog/ml-observability
tests/contrib/pydantic_ai/utils.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: 283 ± 4 ms.

The average import time from base is: 286 ± 4 ms.

The import time difference between this PR and base is: -2.3 ± 0.2 ms.

Import time breakdown

The following import paths have shrunk:

ddtrace.auto 2.063 ms (0.73%)

ddtrace.bootstrap.sitecustomize 1.385 ms (0.49%)

ddtrace.bootstrap.preload 1.385 ms (0.49%)

ddtrace.internal.remoteconfig.client 0.682 ms (0.24%)

ddtrace 0.678 ms (0.24%)

ddtrace.internal._unpatched 0.030 ms (0.01%)

json 0.030 ms (0.01%)

json.decoder 0.030 ms (0.01%)

re 0.030 ms (0.01%)

enum 0.030 ms (0.01%)

types 0.030 ms (0.01%)

[pr-commenter]

Benchmarks

Benchmark execution time: 2025-07-16 20:53:43

Comparing candidate commit dc1036c in PR branch nicole-cybul/agent-manifest-instrumentation with baseline commit ff294ae in branch main.

Found 0 performance improvements and 1 performance regressions! Performance is the same for 546 metrics, 3 unstable metrics.

scenario:telemetryaddmetric-flush-1-metric

• 🟥 execution_time [+381.238ns; +458.769ns] or [+9.285%; +11.173%]

[github-actions]

This pull request has been automatically closed after a period of inactivity.
After this much time, it will likely be easier to open a new pull request with the
same changes than to update this one from the base branch. Please comment or reopen
if you think this pull request was closed in error.

[sabrenner]

nice, super cool!! did a first pass and mostly just some cleanup stuff, most of the actual implementation lgtm

[sabrenner]

nice! lgtm - just a couple small comments