Add comprehensive tests to increase code coverage from 89.81% to 90.28%:
writeSkillOutput.ts (63.88% → 100%):
- Add test for techStack file writing
- Add tests for EPERM/EACCES error handling
- Add test for generic error handling
- Add test for non-Error object handling
fileSystemReadFileTool.ts (62.5% → 100%):
- Add test for directory path error
- Add test for successful file reading
- Add test for security check failure
- Add test for general errors during file reading
- Add test for non-Error object handling
Add comment explaining why structuredContent is omitted from error responses
to prevent schema validation issues. Remove commented-out code from tests
for better maintainability as suggested in PR review.
- Update all 7 MCP tool files from tool() to registerTool() API
- Add structured outputSchema with Zod schemas for type safety
- Reorganize tool configuration with inputSchema and annotations
- Update test mocks to use registerTool instead of deprecated tool()
- Maintain backward compatibility with result field in pack tools
- Add comprehensive output schemas for better LLM integration
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Change buildMcpToolSuccessResponse: message → description
- Change buildMcpToolErrorResponse: message → errorMessage
- Update convertErrorToJson to return errorMessage field
- Update all tool implementations to use new field names
- Update all test expectations to match new response format
This provides better semantic clarity:
- description: explanatory text for successful operations
- errorMessage: specific error information for failures
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Upgrade @modelcontextprotocol/sdk from 1.11.0 to 1.15.0
- Add structured content support to all MCP tool responses
- Update error handling to use convertErrorToJson utility
- Rename formatToolResponse to formatPackToolResponse for clarity
- Fix property naming consistency (contents → content)
- Update all tests to expect new JSON response format
- Replace 'any' types with proper TypeScript types for better type safety
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Kazuki Yamada
Tran Quoc Huy
Kazuki Yamada
Devin AI