phase 3

detect/profiles/base.py

@@ -1,17 +1,20 @@
 """
 ContentTypeProfile protocol and config dataclasses.
 
-The pipeline graph is fixed — what varies per content type is configuration
-and hooks. Each profile provides stage configs, a brand dictionary,
-VLM prompt templates, and an aggregation strategy.
+Each profile defines the pipeline topology (as a JSONB blob), stage configs,
+brand dictionary, VLM prompt templates, and aggregation strategy.
+
+When profiles are persisted, the pipeline field is a JSONB column.
+For now, profiles are code-only and pipeline_config() returns a hardcoded value.
 """
 
 from __future__ import annotations
 
 from dataclasses import dataclass, field
-from typing import Protocol
+from typing import Any, Dict, Protocol
 
 from detect.models import BrandDetection, DetectionReport
+from core.schema.models.pipeline_config import PipelineConfig, StageRef, Edge
 
 
 @dataclass
@@ -64,9 +67,24 @@ class CropContext:
     position_hint: str = ""
 
 
+def pipeline_config_from_dict(data: Dict[str, Any]) -> PipelineConfig:
+    """Deserialize a PipelineConfig from a JSONB dict."""
+    stages = [StageRef(**s) for s in data.get("stages", [])]
+    edges = [Edge(**e) for e in data.get("edges", [])]
+    return PipelineConfig(
+        name=data.get("name", ""),
+        profile_name=data.get("profile_name", ""),
+        stages=stages,
+        edges=edges,
+        routing_rules=data.get("routing_rules", {}),
+    )
+
+
 class ContentTypeProfile(Protocol):
     name: str
+    pipeline: Dict[str, Any]  # JSONB blob — PipelineConfig shape
 
+    def pipeline_config(self) -> PipelineConfig: ...
     def frame_extraction_config(self) -> FrameExtractionConfig: ...
     def scene_filter_config(self) -> SceneFilterConfig: ...
     def region_analysis_config(self) -> RegionAnalysisConfig: ...

detect/profiles/soccer.py

@@ -2,6 +2,7 @@
 
 from __future__ import annotations
 
+from core.schema.models.pipeline_config import PipelineConfig
 from detect.models import BrandDetection, BrandStats, DetectionReport, PipelineStats
 
 from .base import (
@@ -12,12 +13,46 @@ from .base import (
     RegionAnalysisConfig,
     ResolverConfig,
     SceneFilterConfig,
+    pipeline_config_from_dict,
 )
 
 
 class SoccerBroadcastProfile:
     name = "soccer_broadcast"
 
+    # Pipeline topology as JSONB — will be a DB field when profiles are persisted
+    pipeline = {
+        "name": "soccer_broadcast",
+        "profile_name": "soccer_broadcast",
+        "stages": [
+            {"name": "extract_frames", "branch": "trunk"},
+            {"name": "filter_scenes", "branch": "trunk"},
+            {"name": "detect_edges", "branch": "hoarding"},
+            {"name": "detect_objects", "branch": "objects"},
+            {"name": "preprocess"},
+            {"name": "run_ocr"},
+            {"name": "match_brands"},
+            {"name": "escalate_vlm"},
+            {"name": "escalate_cloud"},
+            {"name": "compile_report"},
+        ],
+        "edges": [
+            {"source": "extract_frames", "target": "filter_scenes"},
+            {"source": "filter_scenes", "target": "detect_edges"},
+            {"source": "filter_scenes", "target": "detect_objects"},
+            {"source": "detect_edges", "target": "preprocess"},
+            {"source": "detect_objects", "target": "preprocess"},
+            {"source": "preprocess", "target": "run_ocr"},
+            {"source": "run_ocr", "target": "match_brands"},
+            {"source": "match_brands", "target": "escalate_vlm"},
+            {"source": "escalate_vlm", "target": "escalate_cloud"},
+            {"source": "escalate_cloud", "target": "compile_report"},
+        ],
+    }
+
+    def pipeline_config(self) -> PipelineConfig:
+        return pipeline_config_from_dict(self.pipeline)
+
     def frame_extraction_config(self) -> FrameExtractionConfig:
         return FrameExtractionConfig(fps=2.0, max_frames=500)