orchestrator/main.py

@@ -678,7 +678,13 @@ async def refresh_swarm_run_status(run):
                 await swarm_runtime.save_run(run)
             return
 
-    next_status = "failed" if any(task.status == TaskStatus.FAILED for task in tasks) else "completed"
+    # Failure isolation (SC-12): a single failed task must NOT sink the whole run (e.g. one task
+    # tripped a transient LLM-gateway 404). Declare the run failed ONLY when there is no completed
+    # work to deliver; otherwise take the completed path and let the Queen / convergence judge
+    # acceptability (the failure is still surfaced in convergence termination_reason).
+    failed_tasks = [t for t in tasks if t.status == TaskStatus.FAILED]
+    completed_tasks = [t for t in tasks if t.status == TaskStatus.COMPLETED]
+    next_status = "failed" if (failed_tasks and not completed_tasks) else "completed"
 
     # Master review-and-iterate gate: before declaring success, optionally run the critic and
     # send rejected work back to the specialists. Off unless ENABLE_REVIEW_LOOP is set, so the