feat(tasks): add retry logic with exponential backoff and jitter
- Rewrite app/tasks/retry_config.py with compute_countdown() function implementing per-retry delays with ±20% jitter (default: 60s, 300s, 900s) - Add BaseTaskWithRetry.retry() override to inject proper countdown - Add OcrTaskWithRetry (120s, 600s, 1800s) for OCR/AI tasks - Add UploadTaskWithRetry for cloud-storage upload tasks - Add config settings: TASK_RETRY_MAX_RETRIES, TASK_RETRY_DELAYS, TASK_RETRY_JITTER - Update process_with_ocr and process_with_azure tasks to use OcrTaskWithRetry - Update all 11 upload tasks to use UploadTaskWithRetry - Add 38 unit tests in tests/test_retry_config.py - Update docs/ConfigurationGuide.md and .env.demo Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
This commit is contained in:
@@ -23,7 +23,7 @@ from app.celery_app import celery
|
||||
from app.config import settings
|
||||
from app.database import SessionLocal
|
||||
from app.models import FileRecord
|
||||
from app.tasks.retry_config import BaseTaskWithRetry
|
||||
from app.tasks.retry_config import OcrTaskWithRetry
|
||||
from app.tasks.rotate_pdf_pages import rotate_pdf_pages
|
||||
from app.utils import log_task_progress
|
||||
from app.utils.ocr_provider import OCRResult, embed_text_layer, get_ocr_providers, merge_ocr_results
|
||||
@@ -32,7 +32,7 @@ from app.utils.text_quality import TextSource, check_text_quality, compare_text_
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@celery.task(base=BaseTaskWithRetry, bind=True)
|
||||
@celery.task(base=OcrTaskWithRetry, bind=True)
|
||||
def process_with_ocr(self, filename: str, file_id: Optional[int] = None, original_text: Optional[str] = None):
|
||||
"""Run the configured OCR providers on *filename* and continue the pipeline.
|
||||
|
||||
|
||||
Reference in New Issue
Block a user