fix(llmobs): fix parsing errors for bedrock converse stream

[lievan]

Fixing a noop test discovered a couple bugs for parsing out the response from converse stream

1. We were adding a [{"role": "assistant"}] message that didn't contain any content blocks to be parsed out - the fix is to only try to extract a message if it contains associated content block indices
2. toolName -> name

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-parsing-cd9ebb9506f8bbe1.yaml               @DataDog/apm-python
ddtrace/llmobs/_integrations/bedrock.py                                 @DataDog/ml-observability
ddtrace/llmobs/_integrations/utils.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: 236 ± 4 ms.

The average import time from base is: 244 ± 5 ms.

The import time difference between this PR and base is: -7.4 ± 0.2 ms.

Import time breakdown

The following import paths have shrunk:

ddtrace.auto 2.535 ms (1.07%)

ddtrace.bootstrap.sitecustomize 1.687 ms (0.71%)

ddtrace.bootstrap.preload 1.687 ms (0.71%)

ddtrace.internal.products 1.687 ms (0.71%)

ddtrace.internal.remoteconfig.client 0.744 ms (0.31%)

ddtrace.internal.symbol_db.remoteconfig 0.036 ms (0.02%)

ddtrace.internal.symbol_db.symbols 0.036 ms (0.02%)

gzip 0.036 ms (0.02%)

ddtrace 0.848 ms (0.36%)

ddtrace._logger 0.158 ms (0.07%)

logging 0.118 ms (0.05%)

traceback 0.118 ms (0.05%)

contextlib 0.118 ms (0.05%)

ddtrace.internal.telemetry 0.040 ms (0.02%)

ddtrace.internal.telemetry.writer 0.040 ms (0.02%)

ddtrace.internal.telemetry.metrics_namespaces 0.040 ms (0.02%)

[pr-commenter]

Benchmarks

Benchmark execution time: 2025-04-22 12:36:51

Comparing candidate commit 21d3ed8 in PR branch evan.li/fix-parsing-stream with baseline commit 1e1626a in branch main.

Found 0 performance improvements and 2 performance regressions! Performance is the same for 498 metrics, 8 unstable metrics.

scenario:iast_aspects-ospathsplit_aspect

• 🟥 execution_time [+385.352ns; +635.775ns] or [+8.153%; +13.451%]

scenario:iast_aspects-ospathsplitext_aspect

• 🟥 execution_time [+369.503ns; +538.846ns] or [+8.110%; +11.826%]

[lievan]

rename context -> content to be consistent with what we are actually parsing from bedrock