[waleedlatif1]

Summary

• When a search MCP call's arguments fail the schema with unrecognized_keys, the rejection log now names the unknown fields (at most 5, each cut to 64 characters), not just the path and code
• When a batched read_document returns an error entry for a document (a stale or altered ID, a scope change, a provider failure), the server now logs the caller-facing reason; before, only unexpected failures were logged, so a call that returned errors for every document looked like a success
• Lets us tell a repeated client mistake apart from a new one and decide whether the existing argument repair should cover it; values are still never logged

Type of Change

• Improvement

Testing

• server.test.ts and server.protocol.test.ts pass
• New tool-arguments.test.ts: fails on the old code (no keys), passes on the new
• route-handler.test.ts passes; biome clean

Checklist

• Code follows project style guidelines
• Self-reviewed my changes
• Tests added/updated and passing (new tests pass the test-audit authoring gate)
• No new warnings introduced
• I confirm that I have read and agree to the terms outlined in the Contributor License Agreement (CLA)

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

1 Skipped Deployment

Project	Deployment	Actions	Updated
docs	Skipped		Nov 13, 2026 6:14pm UTC

[greptile-apps]

Confidence Score: 5/5

[Low impact] The PR appears safe to merge; no actionable issues were found.

Summary

Adds unknown field names to rejected MCP tool-call diagnostics.

• Rejected search calls now name unknown fields in logs.

_{Reviews (3) · Last reviewed commit: "improvement(search-mcp): say the logged-..." · Reviewed by Greptile}

[cubic-dev-ai]

All reported issues were addressed across 2 files

<sub>Reply with feedback, questions, or to request a fix.

Turn on auto-fix | Re-trigger cubic</sub>

[waleedlatif1]

@greptile

[waleedlatif1]

@cubic-dev-ai review this PR

[cubic-dev-ai]

@cubic-dev-ai review this PR

@waleedlatif1 I have started the AI code review. It will take a few minutes to complete.

[cubic-dev-ai]

No issues found across 2 files

Confidence score: 5/5

• Automated review surfaced no issues in the provided summaries.
• No files require special attention.

_{Turn on auto-fix | Re-trigger cubic}

[waleedlatif1]

@greptile

[waleedlatif1]

@cubic-dev-ai review this PR

[cubic-dev-ai]

@cubic-dev-ai review this PR

@waleedlatif1 I have started the AI code review. It will take a few minutes to complete.

[cubic-dev-ai]

No issues found across 2 files

Confidence score: 5/5

• Automated review surfaced no issues in the provided summaries.
• No files require special attention.

_{Re-trigger cubic}