Files
dev/scripts
James Peter 32561af3aa fix(core/mcp): honor per-server startup_timeout_ms and make tools/list failures non-fatal; add test MCP server + smoke harness to validate slow/fast scenarios
- Add  to  and parse/write in config
- Apply per-server timeout to  and initial
- Treat per-server  errors as non-fatal; record and skip those servers
- Keep manager creation successful even if some servers time out
- Export  so local smoke tool can exercise it
- Add  (stdio JSON-RPC) and  binary for manual validation
- Update TUI  to set  by default

This resolves GitHub issue #91 where a slow MCP server caused manager creation to time out and fail entirely.
2025-09-12 00:10:56 +10:00
..