mirror of
https://github.com/coder/coder.git
synced 2026-06-03 04:58:23 +00:00
Michael Suchacz
60779ad2ec
Fixes [CODAGT-367](https://linear.app/codercom/issue/CODAGT-367). `TestResolveExploreToolSnapshot/*` flaked on CI (Linux and Windows) with `context deadline exceeded` on the `GetMCPServerConfigsByIDs` call inside `resolveExploreToolSnapshot`. Each test setup called `server.CreateChat` twice with `MCPServerIDs` set to fake `.example.com` URLs. `CreateChat` marks the chat pending and calls `signalWake`, which causes the chatd background `acquireLoop` to pick the chat up. That goroutine then dialed the fake MCP URLs (NXDOMAIN, slower on Windows) and made an OpenAI request with the dbgen default test key (401). Under CI load, that activity racing the 4 parallel subtests' `GetMCPServerConfigsByIDs` calls was enough to exceed the 25s test context deadline. The failure logs in the issue showed both side effects firing in the same job. `resolveExploreToolSnapshot` only reads `ID`, `MCPServerIDs`, `PlanMode`, `ParentChatID`, and `Mode` off the parent argument, so the chats do not need to be persisted. Build them as in-memory `database.Chat` values instead. The MCP server configs remain in the DB because the function still queries them via `GetMCPServerConfigsByIDs`. Verified locally with `go test ./coderd/x/chatd -run TestResolveExploreToolSnapshot -count=100 -race` (passes, ~5s total) and the surrounding `TestResolve*` / `TestCreateChildSubagentChat*` / `TestSpawnAgent_Explore*` tests. --- _Made by Coder Agents on behalf of @ibetitsmike. [Linear session](https://linear.app/codercom/issue/CODAGT-367/flake-testresolveexploretoolsnapshot#agent-session-0730f3fe)._