feat: Update docker-compose configuration to use environment variables for sensitive data, enhance testing documentation with new LaTeX files for capacity planning, and refine README for clarity on compilation and testing processes.

services/extraction/api/main.py

@@ -1107,12 +1107,16 @@ class CountJobFileCreate(BaseModel):
   services: list[dict[str, Any]] = Field(default_factory=list)
   status: str = "ok"
   error: str | None = None
+  nit: str | None = None
+  object_key: str | None = None
 
 
 class CreateCountJobRequest(BaseModel):
   title: str | None = None
   job_id: str | None = None  # si se pasa, se usa el job existente
   results: list[CountJobFileCreate]
+  download_job_id: str | None = None
+  source: str | None = None
 
 
 class CountJobFileRead(BaseModel):
@@ -1128,6 +1132,8 @@ class CountJobFileRead(BaseModel):
   is_valid: bool | None
   error: str | None
   created_at: str
+  nit: str | None = None
+  object_key: str | None = None
 
 
 class UpdateCountJobFileRequest(BaseModel):
@@ -1163,6 +1169,8 @@ def serialize_count_file(f: CountJobFile) -> dict[str, Any]:
     "is_valid": f.is_valid,
     "error": f.error,
     "created_at": f.created_at.isoformat(),
+    "nit": getattr(f, "nit", None),
+    "object_key": getattr(f, "object_key", None),
   }
 
 
@@ -1193,12 +1201,16 @@ def create_count_job(request: CreateCountJobRequest) -> dict[str, Any]:
       type="counting",
       status="completed",
       title=default_title,
-      request={},
+      request={
+        "source": request.source or ("from-download" if request.download_job_id else "desktop"),
+        "download_job_id": request.download_job_id,
+      },
       result={
         "total": total,
         "processed": total,
         "ok": sum(1 for r in request.results if r.status == "ok"),
         "failed": sum(1 for r in request.results if r.status != "ok"),
+        "nits": sorted({r.nit for r in request.results if r.nit}),
       },
       started_at=utcnow(),
       finished_at=utcnow(),
@@ -1215,6 +1227,8 @@ def create_count_job(request: CreateCountJobRequest) -> dict[str, Any]:
           filename=r.filename,
           file_path=r.file_path,
           doc_type=r.doc_type,
+          nit=r.nit,
+          object_key=r.object_key,
           service_count=r.service_count,
           services=r.services,
           status=r.status,

services/extraction/infrastructure/database.py

@@ -111,6 +111,8 @@ class CountJobFile(Base):
   filename: Mapped[str] = mapped_column(String(512))
   file_path: Mapped[str | None] = mapped_column(Text, nullable=True)
   doc_type: Mapped[str | None] = mapped_column(String(128), nullable=True)
+  nit: Mapped[str | None] = mapped_column(String(255), nullable=True, index=True)
+  object_key: Mapped[str | None] = mapped_column(Text, nullable=True)
   service_count: Mapped[int | None] = mapped_column(Integer, nullable=True)
   services: Mapped[list[Any]] = mapped_column(JSON, default=list)
   status: Mapped[str] = mapped_column(String(32), default="ok", index=True)

services/extraction/worker/tasks.py

@@ -11,6 +11,7 @@ import logging
 import os
 from typing import Any
 
+from sqlalchemy.orm.attributes import flag_modified
 from infrastructure.database import ExtractionRow, Task, session_scope, utcnow
 from infrastructure.serialization import flatten_extraction_result
 from api.desktop_ingest import (
@@ -128,7 +129,8 @@ async def process_document(
         # Persistir resultado en BD
         def _persist() -> dict[str, Any]:
             with session_scope() as session:
-                task = session.get(Task, task_id)
+                # Lock evita lost-update en result.processed con N workers concurrentes.
+                task = session.get(Task, task_id, with_for_update=True)
                 if task is None:
                     return {"skipped": True, "reason": "task_not_found"}
 
@@ -185,6 +187,7 @@ async def process_document(
                 result["row_count"] = row_index
                 result["processed"] = int(result.get("processed") or 0) + 1
                 task.result = result
+                flag_modified(task, "result")
                 task.updated_at = utcnow()
                 session.flush()
                 mark_task_completed_if_done(session, task, batch_id)
@@ -206,7 +209,7 @@ async def process_document(
         def _record_error() -> None:
             try:
                 with session_scope() as session:
-                    task = session.get(Task, task_id)
+                    task = session.get(Task, task_id, with_for_update=True)
                     if task is None:
                         return
                     result = dict(task.result or {})
@@ -219,6 +222,7 @@ async def process_document(
                     result["errors"] = errors
                     result["processed"] = int(result.get("processed") or 0) + 1
                     task.result = result
+                    flag_modified(task, "result")
                     task.updated_at = utcnow()
                     mark_task_completed_if_done(session, task, batch_id)
             except Exception as inner: