- Add structured logger utility with Cloud Run trace context support
- Uses AsyncLocalStorage for request context propagation
- Replace all console.log/error/warn statements with structured logger
- Add logging middleware to capture request/response metadata
- Support Google Cloud Logging severity levels and trace correlation
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add Accept header to mock requests per MCP spec requirement
- Fix TypeScript build errors in integration tests
- Add shutdownSession calls to properly clean up MCP server intervals
- Update afterEach to ensure proper test cleanup
- Add debug configurations for Jest in VS Code launch.json
All tests now pass without hanging processes.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Update tests to handle async session initialization
- Fix session ID retrieval from SSE/JSON responses
- Update DELETE request tests to match new behavior
- Remove references to deprecated startServerListeningToRedis
- Add proper waits for async operations
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add explicit DELETE request handling in handleStreamableHTTP
- Validate session existence before termination
- Send shutdown control messages to clean up Redis resources
- Return proper HTTP status codes (200 for success, 404 for not found)
- Fix TypeScript issue with JSONRPCMessage id access in redisTransport
- Add missing semicolon in startServerListeningToRedis call
Follows MCP specification for explicit session termination.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Fix timing issue by awaiting startServerListeningToRedis
- Add request-id based response channel routing
- Implement control message system for proper server shutdown
- Add comprehensive integration tests
- Ensure response subscription is established before message sending
- Fix MCP server cleanup integration to prevent async hanging
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Implement new ServerRedisTransport for server->client messages using request-specific channels
- Add redisRelayToMcpServer function for dynamic request-id based subscriptions
- Update shttp handler to use new transport return types with cleanup functions
- Remove old relayTransports and helper functions in favor of new architecture
- Add comprehensive test suites for Redis transport and shttp handler components
- Fix linting issues and ensure all tests pass
The new system routes server responses to channels like:
- mcp:shttp:toclient:${sessionId}:${requestId} for request responses
- mcp:shttp:toclient:${sessionId}:__GET_stream for notifications
This enables efficient scaling across multiple shttp instances as each client
only subscribes to channels relevant to their specific requests.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Add detailed logging to Redis transport lifecycle
- Log session validation and message flow
- Track MCP server request handling
- Add diagnostics for streamable HTTP transport connections
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
