fix: strip reasoningContent blocks in filter_restored_tool_context

[gingeekrishna]

Summary

• _filter_restored_tool_context() stripped toolUse/toolResult blocks from restored session history but left reasoningContent (extended thinking) blocks intact.
• Bedrock rejects an assistant message where reasoningContent blocks are present without their companion toolUse blocks, raising a ValidationException.
• Fix: add "reasoningContent" not in content to the filter predicate so thinking blocks are stripped together with the tool calls they preceded.

Root cause

When extended thinking is enabled, an assistant turn produces a message like:

{
  "role": "assistant",
  "content": [
    {"reasoningContent": {"reasoningText": {"text": "…"}}},
    {"toolUse": {"toolUseId": "t1", "name": "my_tool", "input": {}}}
  ]
}

reasoningContent and toolUse are semantically coupled — the Bedrock API requires them to appear together. filter_restored_tool_context was removing toolUse while keeping reasoningContent, producing a partial message that the API refuses.

Test plan

• test_strips_reasoning_content_alongside_tool_use — assistant message with reasoningContent+toolUse → both stripped, only plain-text assistant message survives
• test_message_with_only_reasoning_and_tool_use_is_dropped_entirely — message becomes empty after stripping → excluded from output
• test_text_alongside_reasoning_and_tool_use_is_preserved — text content survives after stripping reasoning+toolUse
• test_messages_without_tool_context_are_unchanged — plain text messages pass through unchanged (no regression)
• test_existing_tool_use_filtering_still_works — original toolUse/toolResult behaviour preserved

5 passed in 0.XXs

Fixes #621

[Copilot]

Pull request overview

This PR fixes restored-session filtering for Bedrock extended thinking by ensuring reasoningContent blocks are removed alongside toolUse/toolResult blocks, preventing invalid assistant messages from being sent to Bedrock.

Changes:

• Update _filter_restored_tool_context() to also strip reasoningContent blocks when filtering restored history.
• Expand the session manager integration test suite with regression cases covering reasoning+tool interactions and preservation of plain text.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File	Description
tests/bedrock_agentcore/memory/integrations/strands/test_agentcore_memory_session_manager.py	Adds regression tests validating restored-history filtering when reasoningContent is present.
src/bedrock_agentcore/memory/integrations/strands/session_manager.py	Extends restored tool-context filtering to remove reasoningContent blocks and documents the rationale.

---

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

[gingeekrishna]

Done - addressed Copilot review: updated the filter_restored_tool_context docstring in AgentCoreMemoryConfig (commit d4f9b5d) to clarify that it strips toolUse, toolResult, and reasoningContent (extended thinking) blocks, with a note explaining that reasoning blocks must always be removed alongside the tool calls that followed them.