fix: Pipeline-Skalierung — 6 Optimierungen für 80k+ Controls

1. control_generator: GeneratorResult.status Default "completed" → "running" (Bug)
2. control_generator: Anthropic API mit Phase-Timeouts + Retry bei Disconnect
3. control_generator: regulation_exclude Filter + Harmonization via Qdrant statt In-Memory
4. decomposition_pass: Enrich Pass Batch-UPDATEs (400k → ~400 DB-Calls)
5. decomposition_pass: Merge Pass single Query statt N+1
6. batch_dedup_runner: Cross-Group Dedup parallelisiert (asyncio.gather)
7. canonical_control_routes: Framework Controls API Pagination (limit/offset)
8. DB-Indizes: idx_oc_parent_release, idx_oc_trigger_null, idx_cc_framework

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

control-pipeline/api/canonical_control_routes.py

@@ -274,6 +274,8 @@ async def list_framework_controls(
     verification_method: Optional[str] = Query(None),
     category: Optional[str] = Query(None),
     target_audience: Optional[str] = Query(None),
+    limit: Optional[int] = Query(None, ge=1, le=5000),
+    offset: Optional[int] = Query(None, ge=0),
 ):
     """List controls belonging to a framework."""
     with SessionLocal() as db:
@@ -309,6 +311,12 @@ async def list_framework_controls(
             params["ta"] = json.dumps([target_audience])
 
         query += " ORDER BY control_id"
+        if limit is not None:
+            query += " LIMIT :lim"
+            params["lim"] = limit
+        if offset is not None:
+            query += " OFFSET :off"
+            params["off"] = offset
         rows = db.execute(text(query), params).fetchall()
 
     return [_control_row(r) for r in rows]

control-pipeline/api/control_generator_routes.py

@@ -55,6 +55,7 @@ class GenerateRequest(BaseModel):
     skip_web_search: bool = False
     dry_run: bool = False
     regulation_filter: Optional[List[str]] = None  # Only process these regulation_code prefixes
+    regulation_exclude: Optional[List[str]] = None  # Skip these regulation_code prefixes
     skip_prefilter: bool = False  # Skip local LLM pre-filter, send all chunks to API
 
 
@@ -148,6 +149,7 @@ async def start_generation(req: GenerateRequest):
         skip_web_search=req.skip_web_search,
         dry_run=req.dry_run,
         regulation_filter=req.regulation_filter,
+        regulation_exclude=req.regulation_exclude,
         skip_prefilter=req.skip_prefilter,
     )