gendesign/backend/app/workers/celery_app.py
Light1YT ea42d29a4a feat(site-finder): live CBR key-rate scraper → macro_indicator (#945 PR B)
Site Finder v2 / GG-форсайт. Deterministic, no LLM. Fills the key_rate series
(empty after PR A) into macro_indicator from the live CBR source.

- services/scrapers/cbr_macro.py: fetch_key_rate via CBR SOAP DailyInfoWebServ
  KeyRateXML(fromDate, ToDate) (POST soap+xml; ToDate capital-T + dateTime
  suffix required — flat GET returns empty). Pure parse_key_rate_xml (TZ-safe
  date, empty/malformed → []). Live-verified: 85 rows, current rate 14.5%.
- workers/tasks/cbr_macro_sync.py: upsert (key_rate, rf, daily, %) into
  macro_indicator ON CONFLICT DO UPDATE; SAVEPOINT per row; fetch-fail → raise.
- beat: cbr-macro-sync-weekly (Mon 05:30 МСК, Europe/Moscow tz).
- 15 tests (pure parse + mocked upsert). No migration (table from #963 PR A).
2026-06-03 00:05:25 +05:00

74 lines
2.8 KiB
Python

"""Celery app — single source of truth для Celery configuration.
Beat schedule build → app/workers/beat_schedule.py.
Worker lifecycle hooks (process_init, worker_ready) → app/workers/lifecycle.py.
"""
import logging
import os
import sentry_sdk
from celery import Celery
from sentry_sdk.integrations.celery import CeleryIntegration
from sentry_sdk.integrations.httpx import HttpxIntegration
from sentry_sdk.integrations.logging import LoggingIntegration
from sentry_sdk.integrations.sqlalchemy import SqlalchemyIntegration
from app.core.config import settings
from app.observability.sentry_scrub import scrub_sensitive_query
logger = logging.getLogger(__name__)
# SDK инициализируется в обоих процессах (FastAPI-сервер и Celery-воркер),
# чтобы события из тасков попадали в GlitchTip. SDK безопасен для двойного
# вызова — повторный sentry_sdk.init() в одном процессе заменяет клиента.
if settings.glitchtip_dsn:
sentry_sdk.init(
dsn=settings.glitchtip_dsn,
environment=settings.environment,
release=os.getenv("GIT_SHA") or os.getenv("SENTRY_RELEASE") or "unknown",
traces_sample_rate=settings.glitchtip_traces_sample_rate,
profiles_sample_rate=0.0,
send_default_pii=False,
before_send_transaction=scrub_sensitive_query,
integrations=[
CeleryIntegration(monitor_beat_tasks=True),
SqlalchemyIntegration(),
HttpxIntegration(),
LoggingIntegration(level=logging.INFO, event_level=logging.ERROR),
],
)
logger.info(
"GlitchTip SDK initialised in Celery worker (env=%s)",
settings.environment,
)
celery_app = Celery(
"gendesign",
broker=settings.redis_url,
backend=settings.redis_url,
include=[
"app.workers.tasks.scrape_kn",
"app.workers.tasks.scrape_kn_catalog_objects",
"app.workers.tasks.refresh_analytics",
"app.workers.tasks.scrape_objective",
"app.workers.tasks.objective_etl",
"app.workers.tasks.nspd_geo",
"app.workers.tasks.nspd_sync",
"app.workers.tasks.poi_sync",
"app.workers.tasks.noise_sync",
"app.workers.tasks.pzz_sync",
"app.workers.tasks.scrape_cadastre",
"app.workers.tasks.ekburg_permits_sync",
"app.workers.tasks.cbr_macro_sync",
],
)
celery_app.conf.timezone = "Europe/Moscow"
# Apply beat schedule (DB → fallback → hardcoded entries)
from app.workers.beat_schedule import build_beat_schedule # noqa: E402
celery_app.conf.beat_schedule = build_beat_schedule()
# Register lifecycle hooks (import for side-effect — signal decorator registration)
from app.workers import lifecycle # noqa: E402, F401