[Lucas Kim (kimnamu)]

Thanks to the SK maintainers for the Bedrock connector and the consistent connector design — this change just fills a gap the sibling Anthropic connector already handles.

Motivation and Context

Fixes #14073. Python analogue of #13647 (.NET).

When a model calls multiple tools in one turn, SK emits one ChatMessageContent per tool call/result. _prepare_chat_history_for_request mapped each 1:1 to a Converse message, so parallel toolResults landed in separate user messages → Converse rejects: Expected toolResult blocks at messages.X.content ....

Description

Merge consecutive messages that map to the same Bedrock role, so all toolUse blocks land in one assistant message and all toolResult blocks in one user message. Mirrors the existing Anthropic connector (formatted_messages[-1][content_key] += ...).

Item	Before	After
2 parallel tool calls → assistant msgs	❌ 2 separate toolUse messages	✅ 1 assistant msg, 2 toolUse blocks
2 parallel tool results → user msgs	❌ 2 separate toolResult messages (Converse rejects)	✅ 1 user msg, 2 toolResult blocks
Total Converse messages (this case)	❌ 5	✅ 3
Single tool call / no-tool histories	✅ unchanged	✅ unchanged
Streaming path, _format_* converters, public API/args	✅ unchanged	✅ unchanged

Contribution Checklist

• Added test_prepare_chat_history_for_request_merges_parallel_tool_results. Reverting only the source makes it fail with assert 5 == 3 (proving it catches the bug); with the fix the full bedrock unit suite passes (114 passed). ruff format/ruff check/mypy clean.

---

This contribution was prepared with the help of an AI agent (Claude Code); a human reviewed the change, reasoning, and test results before submission.

[Copilot]

Pull request overview

Note

Copilot was unable to run its full agentic suite in this review.

Adds Bedrock Converse compatibility by coalescing consecutive same-role messages (notably parallel tool calls/results) into single messages to avoid Bedrock request validation errors.

Changes:

• Update Bedrock chat history preparation to merge consecutive messages that map to the same Bedrock role.
• Add a unit test verifying parallel tool call + tool result messages are merged into the required Bedrock structure.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

File	Description
python/semantic_kernel/connectors/ai/bedrock/services/bedrock_chat_completion.py	Merge consecutive same-role Bedrock messages by concatenating content blocks.
python/tests/unit/connectors/ai/bedrock/services/test_bedrock_chat_completion.py	Add test coverage for merging parallel tool calls/results into single assistant/user messages.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[github-actions]

Automated Code Review

Reviewers: 5 | Confidence: 93% | Result: All clear

Reviewed: Correctness, Security Reliability, Test Coverage, Failure Modes, Design Approach

---

Automated review by kimnamu's agents

[Lucas Kim (kimnamu)]

Thanks for the review! Addressed both points in the latest commit:

1. Explicit list merge — replaced the in-place content += ... with building a new combined list ([*prev, *new]). Clearer type intent and avoids mutating the previously-appended message.
2. Non-tool merge coverage — added test_prepare_chat_history_for_request_merges_consecutive_same_role_messages, which verifies two consecutive plain user text messages collapse into a single user message with both text blocks preserved in order.

Full bedrock connector suite passes (40 tests); ruff check/format clean.

[Lucas Kim (kimnamu)]

@microsoft-github-policy-service agree

[Lucas Kim (kimnamu)]

Evan Mattson (@moonbox3) Thank you for keeping the Python Bedrock connector moving (I saw #14363 land earlier this month) and for the time you give to community PRs in this area.

This PR is still applicable on current main: without it, parallel toolResults are still emitted as separate Converse user messages, which Bedrock rejects (#14073). The change is 13 lines in _prepare_chat_history_for_request plus two unit tests, mirroring what the Anthropic connector already does.

Status	OPEN, mergeable, no conflicts (branch is behind main, merges cleanly locally)
CI	pull_request workflows (Python Unit Tests / Lint) have not run on this PR yet; only the pull_request_target label + CLA checks have
Base	main@ca40aa7 · PR tests against main source: 2 failed · PR merged with main: 115 passed, ruff check/format clean

# main@ca40aa7 source + the PR's tests
FAILED ...::test_prepare_chat_history_for_request_merges_parallel_tool_results  - assert 5 == 3
FAILED ...::test_prepare_chat_history_for_request_merges_consecutive_same_role_messages  - assert 2 == 1

# PR merged with main@ca40aa7
uv run pytest tests/unit/connectors/ai/bedrock -q   -> 115 passed

When it fits your schedule, would you be willing to take a look (or approve the workflow run so CI can confirm the above)?

If this isn't a priority right now, tell me and I'll close it to keep your queue clean.