feat(prospecting): add batch delay + fix Celery error_message field

- Add PROSPECTING_BATCH_DELAY_SECONDS config (default 1.0s) — polite
  delay between prospects in batch scans to avoid rate limiting
- Apply delay to all 5 batch API endpoints and all Celery tasks
- Fix Celery tasks: error_message → error_log (matches model field)
- Add batch-scanning.md docs with rate limiting guide, scaling estimates
  for 70k+ URL imports, and pipeline order recommendations

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-04-01 21:55:24 +02:00
parent 30f3dae5a3
commit 50a4fc38a7
4 changed files with 120 additions and 15 deletions

View File

@@ -4,9 +4,11 @@ Celery tasks for batch prospect scanning and enrichment.
"""
import logging
import time
from datetime import UTC, datetime
from app.core.celery_config import celery_app
from app.modules.prospecting.config import config as prospecting_config
from app.modules.prospecting.models import ProspectScanJob
from app.modules.task_base import ModuleTask
@@ -53,6 +55,8 @@ def batch_http_check(self, job_id: int, limit: int = 100):
job.processed_items = processed
if processed % 10 == 0:
db.flush()
if processed < len(prospects):
time.sleep(prospecting_config.batch_delay_seconds)
job.status = "completed"
job.completed_at = datetime.now(UTC)
@@ -61,7 +65,7 @@ def batch_http_check(self, job_id: int, limit: int = 100):
except Exception as e:
logger.error("batch_http_check job %d failed: %s", job_id, e, exc_info=True)
job.status = "failed"
job.error_message = str(e)[:500]
job.error_log = str(e)[:500]
job.completed_at = datetime.now(UTC)
db.commit() # SVC-006 - persist failure status
raise
@@ -110,6 +114,8 @@ def batch_tech_scan(self, job_id: int, limit: int = 100):
job.processed_items = processed
if processed % 10 == 0:
db.flush()
if processed < len(prospects):
time.sleep(prospecting_config.batch_delay_seconds)
job.status = "completed"
job.completed_at = datetime.now(UTC)
@@ -118,7 +124,7 @@ def batch_tech_scan(self, job_id: int, limit: int = 100):
except Exception as e:
logger.error("batch_tech_scan job %d failed: %s", job_id, e, exc_info=True)
job.status = "failed"
job.error_message = str(e)[:500]
job.error_log = str(e)[:500]
job.completed_at = datetime.now(UTC)
db.commit() # SVC-006 - persist failure status
raise
@@ -167,6 +173,8 @@ def batch_performance_scan(self, job_id: int, limit: int = 50):
job.processed_items = processed
if processed % 5 == 0:
db.flush()
if processed < len(prospects):
time.sleep(prospecting_config.batch_delay_seconds)
job.status = "completed"
job.completed_at = datetime.now(UTC)
@@ -175,7 +183,7 @@ def batch_performance_scan(self, job_id: int, limit: int = 50):
except Exception as e:
logger.error("batch_performance_scan job %d failed: %s", job_id, e, exc_info=True)
job.status = "failed"
job.error_message = str(e)[:500]
job.error_log = str(e)[:500]
job.completed_at = datetime.now(UTC)
db.commit() # SVC-006 - persist failure status
raise
@@ -223,6 +231,8 @@ def batch_contact_scrape(self, job_id: int, limit: int = 100):
job.processed_items = processed
if processed % 10 == 0:
db.flush()
if processed < len(prospects):
time.sleep(prospecting_config.batch_delay_seconds)
job.status = "completed"
job.completed_at = datetime.now(UTC)
@@ -231,7 +241,7 @@ def batch_contact_scrape(self, job_id: int, limit: int = 100):
except Exception as e:
logger.error("batch_contact_scrape job %d failed: %s", job_id, e, exc_info=True)
job.status = "failed"
job.error_message = str(e)[:500]
job.error_log = str(e)[:500]
job.completed_at = datetime.now(UTC)
db.commit() # SVC-006 - persist failure status
raise
@@ -270,7 +280,7 @@ def batch_score_compute(self, job_id: int, limit: int = 500):
except Exception as e:
logger.error("batch_score_compute job %d failed: %s", job_id, e, exc_info=True)
job.status = "failed"
job.error_message = str(e)[:500]
job.error_log = str(e)[:500]
job.completed_at = datetime.now(UTC)
db.commit() # SVC-006 - persist failure status
raise
@@ -331,7 +341,7 @@ def full_enrichment(self, job_id: int, prospect_id: int):
except Exception as e:
logger.error("full_enrichment job %d failed: %s", job_id, e, exc_info=True)
job.status = "failed"
job.error_message = str(e)[:500]
job.error_log = str(e)[:500]
job.completed_at = datetime.now(UTC)
db.commit() # SVC-006 - persist failure status
raise