scorevision: push artifact

miner.py

@@ -35,9 +35,40 @@ from pathlib import Path
 
 import numpy as np
 import onnxruntime as ort
+from pydantic import BaseModel
 
 MANIFEST_OBJECTS = ["fire", "smoke", "fire extinguisher"]
 
+
+# predict_batch MUST return objects exposing .model_dump(), not plain dicts.
+# The live chute does `fr = frame_result.model_dump()` unconditionally
+# (chute_template/turbovision_chute.py.j2), while the compliance runner does
+# `model_dump() if hasattr(...) else dict(frame_result)`. Returning dicts
+# therefore PASSES compliance and fails every real challenge with
+# "'dict' object has no attribute 'model_dump'" - a successful HTTP 200 whose
+# body is {"success": false}, scored as zero. Mirror the reference contract in
+# scorevision/miner/open_source/example_miner/miner.py exactly.
+class BoundingBox(BaseModel):
+    x1: int
+    y1: int
+    x2: int
+    y2: int
+    cls_id: int
+    conf: float
+
+
+class Polygon(BaseModel):
+    cls_id: int
+    conf: float
+    points: list[tuple[int, int]]
+
+
+class TVFrameResult(BaseModel):
+    frame_id: int
+    boxes: list[BoundingBox] | None = None
+    polygons: list[Polygon] | None = None
+    keypoints: list[tuple[int, int]] | None = None
+
 MODEL_FILE = "model.onnx"
 # 640/672/768 all fit the CPU budget; the incumbent runs 672 at 43.7 ms p95
 # on a 4-thread box against a 110 ms ceiling, so 768 is affordable and buys
@@ -308,8 +339,8 @@ class Miner:
             x1, y1, x2, y2 = boxes[i]
             if x2 <= x1 or y2 <= y1:
                 continue
-            out.append({"x1": int(x1), "y1": int(y1), "x2": int(x2), "y2": int(y2),
-                        "cls_id": int(mapped[i]), "conf": float(conf[i])})
+            out.append(BoundingBox(x1=int(x1), y1=int(y1), x2=int(x2), y2=int(y2),
+                                   cls_id=int(mapped[i]), conf=float(conf[i])))
             if len(out) >= MAX_DET:
                 break
         return out
@@ -335,6 +366,6 @@ class Miner:
                 # "crashed" - silent except made those indistinguishable.
                 self.last_error = f"{type(e).__name__}: {e}"
                 dets = []
-            results.append({"frame_id": frame_id, "boxes": dets,
-                            "polygons": [], "keypoints": []})
+            results.append(TVFrameResult(frame_id=frame_id, boxes=dets,
+                                         polygons=[], keypoints=[]))
         return results