fix: prevent event loop saturation from trajectory flush

卧龙 · 卧龙 · commit 5dad918f652c · 2026-05-04T13:47:54.000+08:00
Three changes to prevent the trajectory flush from blocking the event loop for 25+ minutes under heavy session load: 1. queued-file-writer: yield event loop via setImmediate between each queued write to prevent the promise chain from consuming 100% of the event loop. Without this yield, 700+ queued writes (50MB trajectory) block the event loop continuously. 2. trajectory paths: reduce TRAJECTORY_RUNTIME_FILE_MAX_BYTES from 50MB to 10MB to prevent any single trajectory file from growing large enough to cause multi-second flush delays. 3. run-cleanup-timeout: increase AGENT_CLEANUP_STEP_TIMEOUT_MS from 10s to 30s to give large trajectories more time to flush before the timeout warning fires. Closes #75839
diff --git a/src/agents/queued-file-writer.ts b/src/agents/queued-file-writer.ts
@@ -130,6 +130,7 @@ export function getQueuedFileWriter(
     write: (line: string) => {
       queue = queue
         .then(() => ready)
+        .then(() => new Promise<void>((resolve) => setImmediate(resolve)))
         .then(() => safeAppendFile(filePath, line, options))
         .catch(() => undefined);
     },
diff --git a/src/agents/run-cleanup-timeout.ts b/src/agents/run-cleanup-timeout.ts
@@ -1,6 +1,6 @@
 import { formatErrorMessage } from "../infra/errors.js";
 
-export const AGENT_CLEANUP_STEP_TIMEOUT_MS = 10_000;
+export const AGENT_CLEANUP_STEP_TIMEOUT_MS = 30_000;
 
 type AgentCleanupLogger = {
   warn: (message: string) => void;
diff --git a/src/trajectory/paths.ts b/src/trajectory/paths.ts
@@ -2,7 +2,7 @@ import fs from "node:fs";
 import path from "node:path";
 import { resolveHomeRelativePath } from "../infra/home-dir.js";
 
-export const TRAJECTORY_RUNTIME_FILE_MAX_BYTES = 50 * 1024 * 1024;
+export const TRAJECTORY_RUNTIME_FILE_MAX_BYTES = 10 * 1024 * 1024;
 export const TRAJECTORY_RUNTIME_EVENT_MAX_BYTES = 256 * 1024;
 
 type TrajectoryPointerOpenFlagConstants = Pick<
