Merge pull request #4 from xmindlab-heicode/fix/ci-all-suites

CI：7 套测试全部纳入 gate + 修复 e2e 退出竞态（非验收）

.github/workflows/ci.yml

@@ -54,3 +54,19 @@ jobs:
       - name: End-to-end workflow test
         env: { REDIS_FAKE: "1" }
         run: python scripts/test-workflow-e2e.py
+
+      - name: Manager event-contract test
+        env: { REDIS_FAKE: "1" }
+        run: python scripts/test-contract-events.py
+
+      - name: Benchmark metric formulas (v2.1)
+        env: { REDIS_FAKE: "1" }
+        run: python scripts/test-benchmark-metrics.py
+
+      - name: Benchmark collector
+        env: { REDIS_FAKE: "1" }
+        run: python scripts/test-benchmark-collector.py
+
+      - name: Baseline comparison
+        env: { REDIS_FAKE: "1" }
+        run: python scripts/test-baseline-comparison.py

scripts/test-workflow-e2e.py

@@ -68,7 +68,8 @@ async def main():
     config = uvicorn.Config(orch.app, host="127.0.0.1", port=PORT, log_level="warning")
     server = uvicorn.Server(config)
     server.install_signal_handlers = lambda: None  # required when not on the main thread
-    threading.Thread(target=server.run, daemon=True).start()
+    server_thread = threading.Thread(target=server.run, daemon=True)
+    server_thread.start()
 
     agent = StubAgent(WS, "stub-1", [
         "python", "code_generation", "testing", "pytest", "technical-writing", "general",
@@ -78,7 +79,7 @@ async def main():
         async with httpx.AsyncClient(timeout=10) as client:
             if not await wait_health(client):
                 check("orchestrator started", False)
-                return
+                return 1
 
             agent_task = asyncio.create_task(agent.run())
             await asyncio.sleep(0.5)  # let the agent register
@@ -120,13 +121,20 @@ async def main():
         if agent_task:
             agent_task.cancel()
         server.should_exit = True
+        server_thread.join(timeout=5)  # let uvicorn stop so no daemon thread lingers at exit
 
     print()
     if failures:
         print(f"{len(failures)} workflow check(s) FAILED: {failures}")
-        sys.exit(1)
+        return 1
     print("workflow follows the expected sequence: decompose -> dispatch -> execute -> review/iterate -> synthesize")
+    return 0
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    # os._exit after flushing avoids a Fatal Python error if the uvicorn daemon thread is still
+    # finalizing (writing to stderr) at interpreter shutdown — guarantees a deterministic exit code.
+    _code = asyncio.run(main())
+    sys.stdout.flush()
+    sys.stderr.flush()
+    os._exit(_code or 0)