full ingestion -> OCR -> extraction flow is now working correctly.

apps/svc_extract/main.py

@@ -64,28 +64,6 @@ Return a JSON object with the extracted fields and confidence scores.
 """
 
 
-# Create app and settings
-app, settings = create_app(
-    service_name="svc-extract",
-    title="Tax Agent Extraction Service",
-    description="LLM-based field extraction service",
-    settings_class=ExtractionSettings,
-)
-
-# Add middleware
-middleware_factory = create_trusted_proxy_middleware(settings.internal_cidrs)
-app.add_middleware(middleware_factory)
-
-# Global clients
-storage_client: StorageClient | None = None
-document_storage: DocumentStorage | None = None
-event_bus: EventBus | None = None
-confidence_calibrator: ConfidenceCalibrator | None = None
-tracer = get_tracer("svc-extract")
-metrics = get_metrics()
-
-
-@app.on_event("startup")
 async def startup_event() -> None:
     """Initialize service dependencies"""
     global storage_client, document_storage, event_bus, confidence_calibrator
@@ -116,7 +94,6 @@ async def startup_event() -> None:
     logger.info("Extraction service started successfully")
 
 
-@app.on_event("shutdown")
 async def shutdown_event() -> None:
     """Cleanup service dependencies"""
     global event_bus
@@ -129,6 +106,29 @@ async def shutdown_event() -> None:
     logger.info("Extraction service shutdown complete")
 
 
+# Create app and settings
+app, settings = create_app(
+    service_name="svc-extract",
+    title="Tax Agent Extraction Service",
+    description="LLM-based field extraction service",
+    settings_class=ExtractionSettings,
+    startup_hooks=[startup_event],
+    shutdown_hooks=[shutdown_event],
+)
+
+# Add middleware
+middleware_factory = create_trusted_proxy_middleware(settings.internal_cidrs)
+app.add_middleware(middleware_factory)
+
+# Global clients
+storage_client: StorageClient | None = None
+document_storage: DocumentStorage | None = None
+event_bus: EventBus | None = None
+confidence_calibrator: ConfidenceCalibrator | None = None
+tracer = get_tracer("svc-extract")
+metrics = get_metrics()
+
+
 @app.post("/extract/{doc_id}", response_model=ExtractionResponse)
 async def extract_fields(
     doc_id: str,
@@ -334,13 +334,14 @@ async def _extract_fields_async(
                 )
 
             # Update metrics
-            metrics.counter("extractions_completed_total").labels(
-                tenant_id=tenant_id, strategy=strategy
-            ).inc()
+            metrics.counter(
+                "extract_extractions_completed_total",
+                labelnames=["tenant_id", "strategy"],
+            ).labels(tenant_id=tenant_id, strategy=strategy).inc()
 
-            metrics.histogram("extraction_confidence").labels(
-                strategy=strategy
-            ).observe(calibrated_confidence)
+            metrics.histogram(
+                "extract_extraction_confidence", labelnames=["strategy"]
+            ).labels(strategy=strategy).observe(calibrated_confidence)
 
             # Publish completion event
             event_payload = EventPayload(
@@ -371,7 +372,10 @@ async def _extract_fields_async(
             logger.error("Field extraction failed", doc_id=doc_id, error=str(e))
 
             # Update error metrics
-            metrics.counter("extraction_errors_total").labels(
+            metrics.counter(
+                "extract_extraction_errors_total",
+                labelnames=["tenant_id", "strategy", "error_type"],
+            ).labels(
                 tenant_id=tenant_id, strategy=strategy, error_type=type(e).__name__
             ).inc()