feat(llmobs): support tracing bedrock converse stream

[lievan]

Supports tracing converse_stream method from the bedrock converse API

Since output messages, token information, and stop reason are all in the stream chunks returned by the API, we leave the responsibility to parse these out solely in _extract_output_message_for_converse_stream. This contains the bulk of the logic in the PR.

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/converse-stream-c0ac59a206aa16ad.yaml                @DataDog/apm-python
tests/snapshots/tests.contrib.botocore.test_bedrock.test_converse_stream.json  @DataDog/apm-python
ddtrace/contrib/internal/botocore/patch.py                              @DataDog/apm-core-python @DataDog/apm-idm-python
ddtrace/contrib/internal/botocore/services/bedrock.py                   @DataDog/ml-observability
ddtrace/llmobs/_integrations/bedrock.py                                 @DataDog/ml-observability
ddtrace/llmobs/_integrations/utils.py                                   @DataDog/ml-observability
tests/contrib/botocore/bedrock_cassettes/bedrock_converse_stream.yaml   @DataDog/ml-observability
tests/contrib/botocore/bedrock_utils.py                                 @DataDog/ml-observability
tests/contrib/botocore/test_bedrock.py                                  @DataDog/ml-observability
tests/contrib/botocore/test_bedrock_llmobs.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: 231 ± 3 ms.

The average import time from base is: 233 ± 4 ms.

The import time difference between this PR and base is: -2.0 ± 0.2 ms.

Import time breakdown

The following import paths have shrunk:

ddtrace.auto 1.998 ms (0.87%)

ddtrace.bootstrap.sitecustomize 1.333 ms (0.58%)

ddtrace.bootstrap.preload 1.333 ms (0.58%)

ddtrace.internal.products 1.333 ms (0.58%)

ddtrace.internal.remoteconfig.client 0.636 ms (0.28%)

ddtrace 0.665 ms (0.29%)

[pr-commenter]

Benchmarks

Benchmark execution time: 2025-04-03 16:20:42

Comparing candidate commit 6df1cb2 in PR branch evan.li/bedrock-converse-streaming with baseline commit 9159b81 in branch main.

Found 2 performance improvements and 0 performance regressions! Performance is the same for 496 metrics, 2 unstable metrics.

scenario:iast_aspects-format_map_aspect

• 🟩 execution_time [-1.185µs; -1.149µs] or [-23.370%; -22.644%]

scenario:iast_aspects-replace_aspect

• 🟩 execution_time [-1.358µs; -1.316µs] or [-20.547%; -19.918%]

[Kyle-Verhoog]

just one suggestion, otherwise lgtm

[Kyle-Verhoog]

just a nit but good from me