chore(llmobs): add support for creating experiment

[Yun-Kim]

MLOB-3275

Adds support for creating Experiments to Datadog. This isn't a user-facing change, but allows the LLMObs service/writer to send a POST request to LLMObs experiments to create a new experiment object.

Also includes minor type hints, as well as changing the LLMObs service instance to be stored on each Experiment object instead of the LLMObs class. Lastly adds tags as an Experiment attribute.

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/llmobs/llmobs_cassettes/datadog/datadog_api_unstable_llm-obs_v1_datasets_delete_post_15d029c8.yaml  @DataDog/ml-observability
tests/llmobs/llmobs_cassettes/datadog/datadog_api_unstable_llm-obs_v1_datasets_post_05168258.yaml  @DataDog/ml-observability
tests/llmobs/llmobs_cassettes/datadog/datadog_api_unstable_llm-obs_v1_experiments_post_a0c42048.yaml  @DataDog/ml-observability
tests/llmobs/llmobs_cassettes/datadog/datadog_api_unstable_llm-obs_v1_experiments_post_fad24359.yaml  @DataDog/ml-observability
ddtrace/llmobs/_experiment.py                                           @DataDog/ml-observability
ddtrace/llmobs/_llmobs.py                                               @DataDog/ml-observability
ddtrace/llmobs/_writer.py                                               @DataDog/ml-observability
tests/llmobs/test_experiments.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: 274 ± 2 ms.

The average import time from base is: 276 ± 2 ms.

The import time difference between this PR and base is: -1.86 ± 0.08 ms.

Import time breakdown

The following import paths have shrunk:

ddtrace.auto 1.979 ms (0.72%)

ddtrace.bootstrap.sitecustomize 1.304 ms (0.48%)

ddtrace.bootstrap.preload 1.304 ms (0.48%)

ddtrace.internal.remoteconfig.client 0.654 ms (0.24%)

ddtrace 0.675 ms (0.25%)

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: 2025-07-14 22:52:57

Comparing candidate commit 6741cf7 in PR branch yunkim/llmobs-create-experiment with baseline commit 904966d in branch main.

Found 0 performance improvements and 2 performance regressions! Performance is the same for 546 metrics, 2 unstable metrics.

scenario:iastaspectsospath-ospathbasename_aspect

• 🟥 execution_time [+717.996ns; +827.492ns] or [+16.730%; +19.282%]

scenario:iastaspectsospath-ospathsplitext_aspect

• 🟥 execution_time [+585.270ns; +714.603ns] or [+12.684%; +15.487%]