viktor/wrongmove
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Add structured JSON logging, OTel business metrics, and Grafana dashboard

Browse source 
Structured logging via JsonFormatter replaces uvicorn's default format so
Loki can parse timestamps and fields.  14 business metrics (scrape stats,
throttle events, circuit breaker state, cache hit rate, OCR success rate,
Celery task lifecycle) are defined in a shared metrics module and
instrumented across the scraper pipeline, API, and workers.  Celery
workers expose a Prometheus HTTP endpoint on configurable ports.
This commit is contained in:
Viktor Barzin 2026-02-14 10:59:12 +00:00
parent a1829957c1
commit d6edb747d2
No known key found for this signature in database
GPG key ID: 0EB088298288D958
12 changed files with 742 additions and 49 deletions
Download patch file Download diff file Expand all files Collapse all files

25
tasks/listing_tasks.py
View file

@ -23,15 +23,8 @@ from services.task_progress_publisher import publish_task_progress
logger = logging.getLogger("uvicorn.error")
# Also configure a celery-specific logger that always outputs to stdout
# Central logging is now configured in celery_app.py via logging_config
celery_logger = logging.getLogger("celery.task")
if not celery_logger.handlers:
handler = logging.StreamHandler()
handler.setFormatter(logging.Formatter(
"%(asctime)s [%(levelname)s] %(name)s: %(message)s"
))
celery_logger.addHandler(handler)
celery_logger.setLevel(logging.INFO)
SCRAPE_LOCK_NAME = "scrape_listings"
LOG_BUFFER_MAX_LINES = 200
@ -574,6 +567,22 @@ async def _dump_listings_full_inner(
)
celery_logger.info("=" * 60)
# Record scrape metrics
from api.metrics import (
scrape_listings_found,
scrape_listings_processed,
scrape_listings_failed,
scrape_duration_seconds,
scrape_pages_fetched,
scrape_subqueries_total as scrape_subqueries_metric,
)
scrape_listings_found.add(state.ids_collected)
scrape_listings_processed.add(state.processed_count)
scrape_listings_failed.add(state.failed_count)
scrape_duration_seconds.record(elapsed)
scrape_pages_fetched.add(state.total_pages_fetched)
scrape_subqueries_metric.add(state.completed_subqueries)
invalidate_cache()
_update_task_state(task, "Completed", {

8
tasks/poi_tasks.py
View file

@ -14,14 +14,8 @@ from services.task_progress_publisher import publish_task_progress
logger = logging.getLogger(__name__)
# Central logging is now configured in celery_app.py via logging_config
celery_logger = logging.getLogger("celery.task")
if not celery_logger.handlers:
handler = logging.StreamHandler()
handler.setFormatter(logging.Formatter(
"%(asctime)s [%(levelname)s] %(name)s: %(message)s"
))
celery_logger.addHandler(handler)
celery_logger.setLevel(logging.INFO)
@app.task(