feat: add prompt-first batches and pausable task guidance

apps/admin_console/services/task_queue_service.py

@@ -302,7 +302,7 @@ class TaskQueueService:
         normalized = current_status.lower().strip() if isinstance(current_status, str) else None
         if normalized == "success":
             return "completed", True
-        if normalized in {"completed", "failed", "cancelled"}:
+        if normalized in {"completed", "failed", "cancelled", "interrupted"}:
             return normalized, False
         return ("completed" if returncode == 0 else "failed"), True
 
@@ -388,10 +388,9 @@ class TaskQueueService:
     @classmethod
     def _dispatch_pending_tasks(cls) -> None:
         """Launch every pending task admissible under the current concurrency limit."""
+        cls._sync_control_states()
         limit = cls._concurrency_limit()
         state.prune_finished_runs()
-        if limit == 1 and state.is_running:
-            return
 
         # Dispatched-but-not-yet-spawned runs are only visible as queue items in
         # "running" state, so admission must count those too -- active_runs alone
@@ -410,7 +409,9 @@ class TaskQueueService:
                 and item.get("pid") not in active_pids
                 for item in in_flight
             )
-            capacity = limit - len(state.active_runs) - starting
+            capacity = (
+                limit - sum(not r.get("parked") for r in state.active_runs.values()) - starting
+            )
             if capacity <= 0:
                 return
         busy_devices = state.busy_device_ids | {
@@ -432,11 +433,15 @@ class TaskQueueService:
                 # A task without a resolved device may bind to any serial, so it
                 # only launches on an otherwise idle scheduler; the device lock
                 # then allocates freely without contending against active runs.
-                if device is None and (state.active_runs or in_flight or dispatched_any):
+                if device is None and (
+                    any(not r.get("parked") for r in state.active_runs.values())
+                    or in_flight
+                    or dispatched_any
+                ):
                     continue
                 if device is not None and target.lock_key in busy_devices:
                     continue
-            elif limit > 1 and device is not None and target.lock_key in busy_devices:
+            elif limit >= 1 and device is not None and target.lock_key in busy_devices:
                 # A second worker for this device would wait on its lock.
                 continue
 
@@ -454,6 +459,42 @@ class TaskQueueService:
                 if capacity <= 0:
                     break
 
+    @classmethod
+    def _sync_control_states(cls) -> None:
+        from artemis.runtime.task_control import read_state
+        from apps.admin_console.services.automation_store import store
+
+        for item in state.queue_items:
+            if not isinstance(item, dict):
+                continue
+            sid = str(item.get("session_id") or "")
+            run = state.active_runs.get(sid)
+            if not run:
+                continue
+            status = read_state(sid).get("status")
+            if status not in {"running", "task_paused", "resuming"}:
+                continue
+            old = item.get("status")
+            if status == old:
+                continue
+            parked = status in {"task_paused", "resuming"}
+            now = time.time()
+            if parked and not run.get("parked"):
+                run["non_execution_started_at"] = now
+            elif not parked and run.get("parked"):
+                run["non_execution_seconds"] = (
+                    float(run.get("non_execution_seconds") or 0)
+                    + now
+                    - float(run.pop("non_execution_started_at", now))
+                )
+            run["parked"] = parked
+            item["status"] = status
+            job = store.job(sid)
+            if job and job.get("status") != "finalizing":
+                job["status"] = status
+                store.save_job(job)
+            cls._broadcast_event("task_status", {"session_id": sid, "status": status})
+
     @classmethod
     def _begin_task_run(
         cls,
@@ -531,6 +572,22 @@ class TaskQueueService:
             env["ARTEMIS_SESSION_ID"] = str(sess_id)
         env["ARTEMIS_TASK_INGRESS"] = str(task_item.get("ingress", "frontend"))
         env["ARTEMIS_TASK_WORKER"] = "1"
+        overrides = task_item.get("runtime_overrides") or {}
+        for option, variable in {
+            "model": "OPENAI_MODEL",
+            "reasoning_effort": "OPENAI_REASONING_EFFORT",
+            "request_timeout_seconds": "OPENAI_TIMEOUT_SECONDS",
+            "max_retries": "OPENAI_MAX_RETRIES",
+            "retry_interval_seconds": "OPENAI_RETRY_INTERVAL_SECONDS",
+            "record_video": "ARTEMIS_RECORDING_ENABLED",
+            "analyze_video": "ARTEMIS_VIDEO_ENABLED",
+        }.items():
+            if overrides.get(option) is not None:
+                env[variable] = (
+                    str(overrides[option]).lower()
+                    if isinstance(overrides[option], bool)
+                    else str(overrides[option])
+                )
         target.endpoint.apply_to_environment(env)
         env[DeviceExecutionLock.LOCK_SCOPE_ENV] = target.lock_scope
         queue_ticket = task_item.get("queue_ticket")
@@ -664,6 +721,12 @@ class TaskQueueService:
             returncode,
             manual_stop,
         )
+        if (
+            state.is_shutting_down
+            and not manual_stop
+            and current_status not in {"completed", "success", "failed", "interrupted"}
+        ):
+            new_status, should_persist = "interrupted", True
         if should_persist:
             if session_repo.update_session_status(sess_id, new_status, time.time()):
                 print(f"[QueueWorker] Updated session {sess_id} status to '{new_status}'")
@@ -1069,6 +1132,7 @@ class TaskQueueService:
         conversation_id: str | None = None,
         verification_level: str | None = None,
         explorer_mode: str | None = None,
+        runtime_overrides: dict[str, Any] | None = None,
     ) -> dict[str, Any]:
         """Enqueues one or more goals and wakes up the background worker.
 
@@ -1123,6 +1187,8 @@ class TaskQueueService:
                 verification_level=verification_level,
                 explorer_mode=explorer_mode,
             )
+            if runtime_overrides:
+                task_item["runtime_overrides"] = runtime_overrides
             state.queue_items.append(task_item)
             enqueued_tasks.append(task_item)
             cls._broadcast_startup_progress(