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/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: