🔌 fix: Reuse Undici Agents Per Transport and Close on Disconnect (danny-avila#11935)

* fix: error handling for transient HTTP request failures in MCP connection

- Added specific handling for the "fetch failed" TypeError, indicating that the request was aborted likely due to a timeout, while the connection remains usable.
- Updated the error message to provide clearer context for users regarding the transient nature of the error.

* refactor: MCPConnection with Agent Lifecycle Management

- Introduced an array to manage undici Agents, ensuring they are reused across requests and properly closed during disconnection.
- Updated the custom fetch and SSE connection methods to utilize the new Agent management system.
- Implemented error handling for SSE 404 responses based on session presence, improving connection stability.
- Added integration tests to validate the Agent lifecycle, ensuring agents are reused and closed correctly.

* fix: enhance error handling and connection management in MCPConnection

- Updated SSE connection timeout handling to use nullish coalescing for better defaulting.
- Improved the connection closure process by ensuring agents are properly closed and errors are logged non-fatally.
- Added tests to validate handling of "fetch failed" errors, marking them as transient and providing clearer messaging for users.

* fix: update timeout handling in MCPConnection for improved defaulting

- Changed timeout handling in MCPConnection to use logical OR instead of nullish coalescing for better default value assignment.
- Ensured consistent timeout behavior for both standard and SSE connections, enhancing reliability in connection management.

Author: danny-avila

packages/api/src/mcp/__tests__/MCPConnection.test.ts

@@ -290,6 +290,16 @@ describe('extractSSEErrorMessage', () => {
       };
     }
 
+    if (rawMessage === 'fetch failed') {
+      return {
+        message:
+          'fetch failed (request aborted, likely after a timeout — connection may still be usable)',
+        code,
+        isProxyHint: false,
+        isTransient: true,
+      };
+    }
+
     return {
       message: rawMessage,
       code,
@@ -528,4 +538,24 @@ describe('extractSSEErrorMessage', () => {
       expect(result.isTransient).toBe(false);
     });
   });
+
+  describe('fetch failed errors', () => {
+    it('should detect "fetch failed" as transient', () => {
+      const error = { message: 'fetch failed' };
+      const result = extractSSEErrorMessage(error);
+
+      expect(result.message).toContain('fetch failed');
+      expect(result.message).toContain('request aborted');
+      expect(result.isProxyHint).toBe(false);
+      expect(result.isTransient).toBe(true);
+    });
+
+    it('should not match "fetch failed" as a substring in a longer message', () => {
+      const error = { message: 'Something fetch failed to do' };
+      const result = extractSSEErrorMessage(error);
+
+      expect(result.message).toBe('Something fetch failed to do');
+      expect(result.isTransient).toBe(false);
+    });
+  });
 });