feat: Introduce bot-descarga service for PDF downloads and remote bot control. Add Docker configuration, environment variables, and a GUI for agent management. Enhance README with bot details and installation instructions.

2026-07-12 21:20:29 -05:00
parent a75ccce13f
commit 103bcea15b
66 changed files with 4469 additions and 13 deletions
@@ -0,0 +1,293 @@
+from __future__ import annotations
+
+import os
+from pathlib import Path
+from typing import Any, Dict, List, Optional
+
+from fastapi import Depends, FastAPI, File, Form, HTTPException, Query, UploadFile
+from fastapi.responses import Response
+from pydantic import BaseModel, Field
+
+from domain.models import JobStatus
+from infrastructure.auth import require_bearer
+from infrastructure.storage_minio import MinioSettings, MinioStorage
+from infrastructure.store import JobStore
+
+store = JobStore()
+minio = MinioStorage(MinioSettings.from_env())
+
+app = FastAPI(title="BotDescarga Remote API", version="1.0.0")
+
+
+class RegisterWorkerBody(BaseModel):
+    worker_id: str
+    hostname: str = ""
+    max_concurrent: int = 1
+
+
+class HeartbeatBody(BaseModel):
+    worker_id: str
+
+
+class EventBody(BaseModel):
+    event_type: str
+    message: str
+    radicado: Optional[str] = None
+    nit: Optional[str] = None
+    index: Optional[int] = None
+    total: Optional[int] = None
+    metadata: Dict[str, Any] = Field(default_factory=dict)
+    timestamp: Optional[str] = None
+
+
+class PatchJobBody(BaseModel):
+    status: Optional[str] = None
+    result: Optional[Dict[str, Any]] = None
+    error: Optional[str] = None
+
+
+@app.get("/health")
+def health() -> dict:
+    return {"status": "ok", "service": "bot-descarga"}
+
+
+@app.post("/workers/register")
+def register_worker(body: RegisterWorkerBody, _: str = Depends(require_bearer)) -> dict:
+    worker = store.register_worker(
+        body.worker_id,
+        hostname=body.hostname,
+        max_concurrent=body.max_concurrent,
+    )
+    return worker.to_dict()
+
+
+@app.post("/workers/heartbeat")
+def heartbeat(body: HeartbeatBody, _: str = Depends(require_bearer)) -> dict:
+    worker = store.heartbeat(body.worker_id)
+    if not worker:
+        raise HTTPException(status_code=404, detail="Worker no registrado")
+    return worker.to_dict()
+
+
+@app.get("/workers")
+def list_workers(_: str = Depends(require_bearer)) -> List[dict]:
+    return [w.to_dict() for w in store.list_workers()]
+
+
+@app.get("/workers/me/pending")
+def claim_pending(
+    worker_id: str = Query(...),
+    _: str = Depends(require_bearer),
+) -> dict:
+    job = store.claim_pending(worker_id)
+    if not job:
+        return {"job": None}
+    return {"job": job.to_dict()}
+
+
+@app.post("/jobs")
+async def create_job(
+    worker_id: str = Form(...),
+    job_id: str = Form(...),
+    title: str = Form(""),
+    file: UploadFile = File(...),
+    _: str = Depends(require_bearer),
+) -> dict:
+    if not worker_id.strip():
+        raise HTTPException(status_code=400, detail="worker_id obligatorio")
+    parent_job_id = job_id.strip()
+    if not parent_job_id:
+        raise HTTPException(status_code=400, detail="job_id (Job Desktop) obligatorio")
+    if not store.parent_job_exists(parent_job_id):
+        raise HTTPException(status_code=404, detail="Trabajo (job) no encontrado")
+
+    if not store.is_worker_online(worker_id):
+        raise HTTPException(
+            status_code=409,
+            detail=f"Worker '{worker_id}' no está online. Enciende el agent primero.",
+        )
+
+    data = await file.read()
+    if not data:
+        raise HTTPException(status_code=400, detail="Archivo vacío")
+
+    original = file.filename or "input.xlsx"
+    content_type = file.content_type or "application/octet-stream"
+    title_clean = title.strip()
+
+    job = store.create_job(
+        worker_id=worker_id.strip(),
+        excel_key="",
+        original_filename=original,
+        title=title_clean,
+        job_id=parent_job_id,
+    )
+    task_id = store.create_downloads_task(
+        parent_job_id=parent_job_id,
+        download_job_id=job.id,
+        worker_id=worker_id.strip(),
+        title=title_clean or f"Bot descarga ({original})",
+        original_filename=original,
+    )
+    job = store.get_job(job.id)
+    assert job is not None
+
+    try:
+        key = minio.upload_excel(job.id, data, original, content_type=content_type)
+    except Exception as e:
+        store.patch_job(job.id, status=JobStatus.FAILED.value, error=f"MinIO upload failed: {e}")
+        raise HTTPException(status_code=502, detail=f"Error subiendo a MinIO: {e}") from e
+
+    job = store.update_excel_key(job.id, key)
+    assert job is not None
+    store.add_event(
+        job.id,
+        "run_started",
+        f"Job creado y asignado a {worker_id}",
+        metadata={
+            "excel_key": key,
+            "worker_id": worker_id,
+            "job_id": parent_job_id,
+            "task_id": task_id,
+        },
+    )
+    return job.to_dict()
+
+
+@app.get("/jobs")
+def list_jobs(
+    limit: int = Query(100, ge=1, le=500),
+    job_id: Optional[str] = Query(None, description="Filtrar por Job Desktop"),
+    _: str = Depends(require_bearer),
+) -> List[dict]:
+    return [j.to_dict() for j in store.list_jobs(limit=limit, job_id=job_id)]
+
+
+@app.get("/jobs/{download_job_id}")
+def get_job(download_job_id: str, _: str = Depends(require_bearer)) -> dict:
+    job = store.get_job(download_job_id)
+    if not job:
+        raise HTTPException(status_code=404, detail="Job no encontrado")
+    return job.to_dict()
+
+
+@app.get("/jobs/{download_job_id}/files")
+def list_job_files(download_job_id: str, _: str = Depends(require_bearer)) -> dict:
+    job = store.get_job(download_job_id)
+    if not job:
+        raise HTTPException(status_code=404, detail="Job no encontrado")
+    try:
+        return minio.list_download_files(download_job_id, prefix=job.downloads_prefix)
+    except Exception as e:
+        raise HTTPException(status_code=502, detail=f"Error listando MinIO: {e}") from e
+
+
+@app.get("/jobs/{download_job_id}/events")
+def get_events(
+    download_job_id: str,
+    since: int = Query(0, ge=0),
+    _: str = Depends(require_bearer),
+) -> dict:
+    if not store.get_job(download_job_id):
+        raise HTTPException(status_code=404, detail="Job no encontrado")
+    events = store.list_events(download_job_id, since_id=since)
+    return {"events": [e.to_dict() for e in events]}
+
+
+@app.post("/jobs/{download_job_id}/cancel")
+def cancel_job(download_job_id: str, _: str = Depends(require_bearer)) -> dict:
+    job = store.request_cancel(download_job_id)
+    if not job:
+        raise HTTPException(status_code=404, detail="Job no encontrado")
+    store.add_event(download_job_id, "warning", "Cancelación solicitada por el usuario")
+    return job.to_dict()
+
+
+@app.get("/jobs/{download_job_id}/file")
+def get_job_file(download_job_id: str, _: str = Depends(require_bearer)):
+    job = store.get_job(download_job_id)
+    if not job:
+        raise HTTPException(status_code=404, detail="Job no encontrado")
+    if not job.excel_key:
+        raise HTTPException(status_code=404, detail="Excel no disponible")
+
+    try:
+        data = minio.get_bytes(job.excel_key)
+    except Exception as e:
+        raise HTTPException(status_code=502, detail=f"Error leyendo MinIO: {e}") from e
+
+    filename = Path(job.excel_key).name
+    return Response(
+        content=data,
+        media_type="application/octet-stream",
+        headers={"Content-Disposition": f'attachment; filename="{filename}"'},
+    )
+
+
+@app.get("/jobs/{download_job_id}/file-url")
+def get_job_file_url(download_job_id: str, _: str = Depends(require_bearer)) -> dict:
+    job = store.get_job(download_job_id)
+    if not job or not job.excel_key:
+        raise HTTPException(status_code=404, detail="Job/archivo no encontrado")
+    try:
+        url = minio.presigned_get(job.excel_key)
+    except Exception as e:
+        raise HTTPException(status_code=502, detail=str(e)) from e
+    return {"url": url, "excel_key": job.excel_key}
+
+
+@app.post("/jobs/{download_job_id}/events")
+def post_event(
+    download_job_id: str,
+    body: EventBody,
+    _: str = Depends(require_bearer),
+) -> dict:
+    if not store.get_job(download_job_id):
+        raise HTTPException(status_code=404, detail="Job no encontrado")
+    event = store.add_event(
+        download_job_id,
+        body.event_type,
+        body.message,
+        radicado=body.radicado,
+        nit=body.nit,
+        index=body.index,
+        total=body.total,
+        metadata=body.metadata,
+        timestamp=body.timestamp,
+    )
+    job = store.get_job(download_job_id)
+    if job and body.index is not None and body.total is not None:
+        result = dict(job.result or {})
+        result["processed"] = body.index
+        result["total"] = body.total
+        if body.nit:
+            result["nit_actual"] = body.nit
+        store.patch_job(download_job_id, result=result)
+    return event.to_dict()
+
+
+@app.patch("/jobs/{download_job_id}")
+def patch_job(
+    download_job_id: str,
+    body: PatchJobBody,
+    _: str = Depends(require_bearer),
+) -> dict:
+    if body.status and body.status not in {s.value for s in JobStatus}:
+        raise HTTPException(status_code=400, detail="status inválido")
+    job = store.patch_job(
+        download_job_id,
+        status=body.status,
+        result=body.result,
+        error=body.error,
+    )
+    if not job:
+        raise HTTPException(status_code=404, detail="Job no encontrado")
+    return job.to_dict()
+
+
+@app.get("/jobs/{download_job_id}/cancel-flag")
+def cancel_flag(download_job_id: str, _: str = Depends(require_bearer)) -> dict:
+    job = store.get_job(download_job_id)
+    if not job:
+        raise HTTPException(status_code=404, detail="Job no encontrado")
+    return {"cancel_requested": job.cancel_requested, "status": job.status}