phase cv 0

core/schema/models/detect_jobs.py

@@ -93,13 +93,12 @@ class StageCheckpoint:
     frames_meta: List[Dict[str, Any]] = field(default_factory=list)  # sequence, chunk_id, timestamp, hash
     filtered_frame_sequences: List[int] = field(default_factory=list)
 
-    # Detection state (full structured data, not just summaries)
-    boxes_by_frame: Dict[str, List[Dict[str, Any]]] = field(default_factory=dict)
-    text_candidates: List[Dict[str, Any]] = field(default_factory=list)
-    unresolved_candidates: List[Dict[str, Any]] = field(default_factory=list)
-    detections: List[Dict[str, Any]] = field(default_factory=list)
+    # Stage output — stored as blob in MinIO: checkpoints/{job_id}/stages/{stage}.bson
+    # Each stage's serialize_fn/deserialize_fn owns the format.
+    # Postgres only stores the S3 key, not the data itself.
+    stage_output_key: str = ""  # s3 key to the serialized stage output
 
-    # Pipeline state
+    # Pipeline state (small, stays in Postgres)
     stats: Dict[str, Any] = field(default_factory=dict)
     config_snapshot: Dict[str, Any] = field(default_factory=dict)
     config_overrides: Dict[str, Any] = field(default_factory=dict)
@@ -108,6 +107,13 @@ class StageCheckpoint:
     video_path: str = ""
     profile_name: str = ""
 
+    # Scenario — a checkpoint bookmarked for the editor workflow.
+    # Created by seeders (manual scripts that populate state from real footage)
+    # or captured from a running pipeline. Loaded via URL:
+    #   /detection/?job=<job_id>&stage=<stage>&editor=true
+    is_scenario: bool = False
+    scenario_label: str = ""  # human-readable name, e.g. "chelsea_edges_lowcanny"
+
     # Timestamps
     created_at: Optional[datetime] = None