Refactor digitador bot and add runtime monitoring

services/extraction/worker/tasks.py

@@ -24,6 +24,8 @@ from domain.profiles import get_profile
 from domain.prompts import PromptBuilder
 from domain.normalizer import normalize_to_schema
 from domain.rate_limiter import get_rate_limiter
+from domain.config import settings
+from domain.usage_tracking import record_api_usage
 
 logger = logging.getLogger(__name__)
 
@@ -131,8 +133,8 @@ async def process_document(
         await rate_limiter.acquire(estimated_tokens=estimated_tokens)
 
         # Extracción + normalización (CPU + IO bound, en thread pool)
-        def _extract_and_normalize() -> tuple[dict, dict]:
-            data, _usage = service.extract_full_from_pdf(
+        def _extract_and_normalize() -> tuple[dict, dict, dict | None, dict | None]:
+            data, extraction_usage = service.extract_full_from_pdf(
                 queue_path,
                 instruction=prompt,
                 tiff_page_range=tiff_range,
@@ -149,11 +151,13 @@ async def process_document(
                 profile_name=prof.get("name", "invoice"),
             )
             normalized_obj = data
+            normalizer_usage = None
             if isinstance(norm, dict):
                 normalized_obj = norm.get("normalized") or data
-            return raw_data, normalized_obj
+                normalizer_usage = norm.get("_usage")
+            return raw_data, normalized_obj, extraction_usage, normalizer_usage
 
-        _raw, normalized_obj = await asyncio.to_thread(_extract_and_normalize)
+        _raw, normalized_obj, extraction_usage, normalizer_usage = await asyncio.to_thread(_extract_and_normalize)
 
         # Persistir resultado en BD
         def _persist() -> dict[str, Any]:
@@ -164,6 +168,15 @@ async def process_document(
                     return {"skipped": True, "reason": "task_not_found"}
 
                 result = dict(task.result or {})
+                result = record_api_usage(
+                    result, phase="extract", model=str(effective_model), usage=extraction_usage,
+                    radicado=radicado, filename=filename,
+                )
+                result = record_api_usage(
+                    result, phase="normalize", model=str(settings.api.normalizer_model), usage=normalizer_usage,
+                    radicado=radicado, filename=filename,
+                )
+                task.result = result
 
                 if structure_mode == "radicados" and doc_types and doc_type:
                     partials = dict(result.get("partials") or {})