Harden RC7 API response contracts

backend/app/schemas/qa.py

@@ -1,10 +1,13 @@
 from __future__ import annotations
 
 from datetime import datetime
+from typing import Any
 from uuid import UUID
 
 from pydantic import BaseModel, Field
 
+from app.schemas.common import GeoJsonFeatureCollection
+
 
 class QaProviderComparisonRequest(BaseModel):
     candidate_dataset_id: UUID
@@ -72,3 +75,40 @@ class QualityCheckList(BaseModel):
     total: int
     limit: int
     offset: int
+
+
+class QualityEvidenceResponse(BaseModel):
+    quality_check_id: UUID
+    project_id: UUID
+    candidate_dataset_id: UUID | None = None
+    reference_dataset_id: UUID
+    analysis_run_id: UUID | None = None
+    feature_count: int
+    warnings: list[str] = Field(default_factory=list)
+    geojson: GeoJsonFeatureCollection
+
+
+class AnalysisQaResponse(BaseModel):
+    status: str
+    quality_check_id: UUID
+    analysis_run_id: UUID
+    reference_dataset_id: UUID
+    candidate_feature_count: int
+    reference_feature_count: int
+    candidate_feature_count_raw: int | None = None
+    reference_feature_count_raw: int | None = None
+    matches: int
+    false_positives: int
+    false_negatives: int
+    precision: float | None = None
+    recall: float | None = None
+    f1_score: float | None = None
+    mean_iou: float | None = None
+    iou_threshold: float
+    warnings: list[str] = Field(default_factory=list)
+    coverage: dict[str, Any] | None = None
+    temporal_compatibility: dict[str, Any] | None = None
+    box_to_footprint_diagnostics: dict[str, Any] | None = None
+    match_evidence: list[dict[str, Any]] = Field(default_factory=list)
+    false_positive_evidence: list[dict[str, Any]] = Field(default_factory=list)
+    false_negative_evidence: list[dict[str, Any]] = Field(default_factory=list)