Automatic orientation issues detection and fix, experimental

copienator/commands/gemini_for_labels.py

@@ -17,6 +17,7 @@ from pydantic import BaseModel, Field, model_validator
 from copienator import configuration as config
 from copienator.gemini_config import fresh_seed, thinking_config
 from copienator.copy_errors import marked_copy_paths
+from copienator.orientation import record_detection, reports as orientation_reports
 from copienator import (
     CliError,
     EvaluationWorkspace,
@@ -149,6 +150,10 @@ class BoxItem(BaseModel):
     label: str = Field(description="The label associated with the specific box")
 
 class AnnotationData(BaseModel):
+    upside_down_pages: typing.List[typing.Annotated[int, Field(strict=True, ge=1)]] = Field(
+        default_factory=list,
+        description='1-based column numbers in this image that appear upside down (180 degrees)',
+    )
     error: typing.Literal["insufficient_crop"] | None = Field(
         default=None, description="Report insufficient_crop when the crop hides information needed to identify labels"
     )
@@ -160,7 +165,7 @@ class AnnotationData(BaseModel):
 
     @model_validator(mode="after")
     def require_success_payload(self):
-        if self.error is None and not {"name", "list"} <= self.model_fields_set:
+        if self.error is None and not self.upside_down_pages and not {"name", "list"} <= self.model_fields_set:
             raise ValueError("Successful detection must include name and list")
         return self
 
@@ -286,6 +291,12 @@ students may skip questions. On success, return error=null.
         text = text.replace("image of the left columns", "image of the full pages")
         text += "\nThis image now contains full pages, in the same reading order. Identify the labels using this expanded view."
 
+    text += ('\nReport upside-down handwriting in upside_down_pages, using 1-based '
+             'column numbers in THIS image, left to right. Only report clear 180-degree '
+             'orientation errors; blank pages are not evidence. If any are reported, '
+             'you may return name="Unknown", list=[] and error=null. Orientation '
+             'reporting takes priority over insufficient_crop.')
+
     contents = [
         types.Content(
             role="user",
@@ -514,6 +525,10 @@ def process_copy_group(
                     config=request_config,
                 )
                 annotation = AnnotationData.model_validate_json(response.text)
+                if record_detection(workspace, image_file, annotation.upside_down_pages):
+                    output_json.unlink(missing_ok=True)
+                    print(f'[{group_key}] Orientation à vérifier avant de valider les labels.')
+                    break
                 if annotation.error == "insufficient_crop":
                     print(f"[{group_key}] {image_file.name}: insufficient crop: "
                           f"{annotation.error_reason or 'labels require a wider view'}")
@@ -573,7 +588,7 @@ def process_copy_group(
                 annotation.list = sort_boxes_for_image(
                     workspace, image_file, annotation.list
                 )
-                atomic_write_json(output_json, annotation.model_dump(exclude={"error", "error_reason"}))
+                atomic_write_json(output_json, annotation.model_dump(exclude={"error", "error_reason", "upside_down_pages"}))
                 accumulated_labels.extend(box.label for box in annotation.list)
                 generated += 1
                 print(f"[{group_key}] Saved {image_file.name} after {time.monotonic() - started:.0f}s.")
@@ -696,7 +711,13 @@ def run(
         print("Incomplete images (rerun label detection to resume):")
         for path in sorted(incomplete):
             print(f"  {path.name}")
-    return ExitCode.PARTIAL if warnings or incomplete else ExitCode.SUCCESS
+    orientation = {name: data for name, data in orientation_reports(workspace).items()
+                   if Path(name).stem in groups}
+    for name, data in orientation.items():
+        pages = sorted({p for values in data.get('images', {}).values() for p in values})
+        if pages:
+            print(f'[Orientation] {name}: pages {pages}. Signalez la copie ou utilisez la correction automatique.')
+    return ExitCode.PARTIAL if warnings or incomplete or orientation else ExitCode.SUCCESS
 
 
 def build_parser() -> argparse.ArgumentParser: