From 6d5d0a367314d6b997111619dbcca9dac62fce97 Mon Sep 17 00:00:00 2001
From: SnapOtter <snapotter.hq@gmail.com>
Date: Thu, 30 Apr 2026 18:45:55 +0800
Subject: [PATCH] fix: do not count normal dispatcher exits as crashes

The close handler called recordCrash() unconditionally, even for exit
code 0 (normal MAX_REQUESTS restart). After 5 normal cycles within 60s
the dispatcher was permanently disabled. Now only non-zero exits count.
---
 packages/ai/src/bridge.ts    |  6 ++--
 tests/unit/ai/bridge.test.ts | 53 ++++++++++++++++++++++++++++++++++++
 2 files changed, 57 insertions(+), 2 deletions(-)

diff --git a/packages/ai/src/bridge.ts b/packages/ai/src/bridge.ts
index 398ef3e7..c54ab084 100644
--- a/packages/ai/src/bridge.ts
+++ b/packages/ai/src/bridge.ts
@@ -216,12 +216,14 @@ function startDispatcher(): ChildProcess | null {
       dispatcherReady = false;
     });
 
-    child.on("close", () => {
+    child.on("close", (code) => {
       for (const [id, req] of pendingRequests.entries()) {
         req.reject(new Error("Python dispatcher exited unexpectedly"));
         pendingRequests.delete(id);
       }
-      recordCrash();
+      if (code !== 0) {
+        recordCrash();
+      }
       dispatcher = null;
       dispatcherReady = false;
     });
diff --git a/tests/unit/ai/bridge.test.ts b/tests/unit/ai/bridge.test.ts
index 72b84240..df56142b 100644
--- a/tests/unit/ai/bridge.test.ts
+++ b/tests/unit/ai/bridge.test.ts
@@ -1035,6 +1035,59 @@ describe("bridge - dispatcher lifecycle via runPythonWithProgress", () => {
     // The important thing is no crash -- the line is collected for pending requests
   });
 
+  it("does not count exit code 0 as a crash (normal MAX_REQUESTS restart)", async () => {
+    const mockDispatcher = createMockProcess();
+    const mockPerReq = createMockProcess();
+    let callCount = 0;
+
+    vi.mocked(spawn).mockImplementation(() => {
+      callCount++;
+      if (callCount === 1) return mockDispatcher.process;
+      return mockPerReq.process;
+    });
+
+    const promise = runPythonWithProgress("test.py", []);
+
+    // Dispatcher exits with code 0 (normal MAX_REQUESTS shutdown)
+    mockDispatcher.emitEvent("close", 0, null);
+
+    await new Promise((r) => setTimeout(r, 10));
+
+    mockPerReq.stdout.emit("data", Buffer.from('{"ok": true}\n'));
+    mockPerReq.emitEvent("close", 0, null);
+    await promise;
+
+    const status = getDispatcherStatus();
+    expect(status.consecutiveCrashes).toBe(0);
+    expect(status.failed).toBe(false);
+  });
+
+  it("still counts non-zero exit codes as crashes", async () => {
+    const mockDispatcher = createMockProcess();
+    const mockPerReq = createMockProcess();
+    let callCount = 0;
+
+    vi.mocked(spawn).mockImplementation(() => {
+      callCount++;
+      if (callCount === 1) return mockDispatcher.process;
+      return mockPerReq.process;
+    });
+
+    const promise = runPythonWithProgress("test.py", []);
+
+    // Dispatcher exits with code 1 (real crash)
+    mockDispatcher.emitEvent("close", 1, null);
+
+    await new Promise((r) => setTimeout(r, 10));
+
+    mockPerReq.stdout.emit("data", Buffer.from('{"ok": true}\n'));
+    mockPerReq.emitEvent("close", 0, null);
+    await promise;
+
+    const status = getDispatcherStatus();
+    expect(status.consecutiveCrashes).toBeGreaterThanOrEqual(1);
+  });
+
   it("per-request fallback retries with python3 when venv python fails with ENOENT", async () => {
     const mockDispatcher = createMockProcess();
     const mockVenvPython = createMockProcess();