fix: forward _meta to MCP tool calls and fix model_dump alias seriali…

[mananpatel320]

Description

MCPClient doesn't forward the _meta field to ClientSession.call_tool(), so custom metadata per the MCP
spec never reaches the
server. Separately, the OpenTelemetry instrumentation in mcp_instrumentation.py uses model_dump()
instead of model_dump(by_alias=True), which serializes the Pydantic field as "meta" (Python name)
rather than "_meta" (wire name). This causes setdefault("_meta", {}) to create a new empty dict instead
of reusing the existing one, corrupting the outgoing payload.

This PR adds a meta parameter to call_tool_sync, call_tool_async, and _create_call_tool_coroutine that
gets forwarded to ClientSession.call_tool(meta=...), and fixes the instrumentation to use
model_dump(by_alias=True).

Resolves: #1916

Public API Changes

call_tool_sync and call_tool_async now accept an optional meta keyword argument:

python

Before: no way to pass _meta

result = mcp_client.call_tool_sync(
tool_use_id="id", name="my_tool", arguments={"key": "value"}
)

After: meta forwarded to the MCP server

result = mcp_client.call_tool_sync(
tool_use_id="id", name="my_tool", arguments={"key": "value"},
meta={"com.example/request_id": "abc-123"}
)

The meta parameter defaults to None, so this is fully backward compatible.

Related Issues

#1916

Type of Change

Bug fix

Testing

• Updated existing unit test assertions to match the new meta=None kwarg in call_tool calls

• Updated mock model_dump signatures to accept by_alias kwarg

• Added unit tests for meta forwarding in both sync and async paths

• Added unit test verifying instrumentation preserves existing _meta values

• Added integration tests for call_tool_sync/call_tool_async with meta

• Added integration test verifying instrumentation correctly sets _meta on outgoing requests

• I ran hatch run prepare

Checklist

• I have read the CONTRIBUTING document
• I have added any necessary tests that prove my fix is effective or my feature works
• I have updated the documentation accordingly
• I have added an appropriate example to the documentation to outline the feature, or no new docs
  are needed
• My changes generate no new warnings
• Any dependent changes have been merged and published

[github-actions]

Review Summary

Assessment: Approve

This PR correctly addresses both issues described in #1916: forwarding the meta parameter to MCP tool calls and fixing the model_dump(by_alias=True) serialization issue in instrumentation.

Review Notes

• Implementation Quality: Changes are clean, well-documented with Google-style docstrings, and follow existing codebase patterns
• Testing: Comprehensive unit tests and integration tests cover both sync and async paths, including meta preservation
• Backward Compatibility: The meta=None default ensures existing code continues to work without modification
• Minor Gap: The task-augmented execution path (experimental) does not forward meta - flagged as inline comment

Nice work on a thorough fix with good test coverage! 🎉

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

[mkmeral]

/strands review

[github-actions]

Re-Review Summary

Assessment: Approve ✅

I've reviewed the new commit (3fb6359 - "fix: address review feedback on PR #1918").

Changes in Latest Commit

The instrumentation code was improved to properly handle None values:

# Before (setdefault doesn't handle explicit None)
meta = params_dict.setdefault("_meta", {})

# After (properly handles None values)
meta = params_dict.get("_meta") if params_dict.get("_meta") is not None else {}
params_dict["_meta"] = meta

This is an improvement because setdefault only uses the default when the key is missing, but the new code also handles the case where _meta exists but is explicitly None.

Verification Summary

Component	Status
mcp_client.py	✅ meta parameter added and forwarded
mcp_instrumentation.py	✅ by_alias=True + None handling
Unit tests	✅ Comprehensive coverage
Integration tests	✅ echo_meta verifies end-to-end
Codecov	✅ 100% coverage on modified lines

The PR is ready to merge.