# plugins/traefik/__init__.py from __future__ import annotations from typing import TYPE_CHECKING if TYPE_CHECKING: from quart import Quart _app: "Quart | None" = None def setup(app: "Quart") -> None: global _app _app = app from .models import ( # noqa: F401 TraefikAccessSummary, TraefikCert, TraefikGlobalStat, TraefikMetric, TraefikStatusCode, ) from steward.core.cleanup import prune_by_age # Samples older than data.retention_days are pruned by the cleanup (#5155). prune_by_age(TraefikMetric.scraped_at) prune_by_age(TraefikStatusCode.scraped_at) prune_by_age(TraefikGlobalStat.scraped_at) prune_by_age(TraefikAccessSummary.period_end) # Each router's 4xx share and p95 learn their normal (#5741), judged only # while the router answers the Thresholds minimum of requests a window # (read at each pass, so a saved change applies at once). Latency is # learned from the scrape-by-scrape figures only: before #5755 it was a # percentile of every response since Traefik started. from datetime import datetime, timezone from steward.core.norms import floor_setting, learn_normal from .routes import STATE_WINDOW, min_requests gate = ("request_rate", lambda: min_requests(app.config.get("THRESHOLDS", {})) / STATE_WINDOW.total_seconds()) learn_normal("traefik", "error_rate_4xx_pct", floor_setting(app, "router_4xx_pct"), gate=gate) learn_normal("traefik", "latency_p95_ms", floor_setting(app, "router_p95_ms"), gate=gate, since=datetime(2026, 10, 14, 18, 47, tzinfo=timezone.utc)) def get_scheduled_tasks() -> list: from .scheduler import make_scrape_task, make_access_log_task tasks = [make_scrape_task(_app)] access_log_cfg = _app.config["PLUGINS"]["traefik"].get("access_log", {}) if not isinstance(access_log_cfg, dict): access_log_cfg = {} if access_log_cfg.get("enabled", False): tasks.append(make_access_log_task(_app)) return tasks def get_blueprint(): from .routes import traefik_bp return traefik_bp def get_nav() -> list[dict]: # Surfaces in the sidebar's Infrastructure group (Traefik services view). return [{"label": "Traefik", "href": "/plugins/traefik/"}] def get_alert_metrics() -> dict[str, list[str]]: """What scheduler.py records for alert rules: per router (resource = the router name) and cert_expiry_days per certificate (resource = its CN).""" return {"traefik": ["request_rate", "error_rate_4xx_pct", "error_rate_5xx_pct", "latency_p50_ms", "latency_p95_ms", "latency_p99_ms", "response_bytes_rate", "cert_expiry_days"]}