bvandeusenandClaude Opus 5.5
0742b7a2b7
#5061 "Metric catalog belongs to what emits: plugins register their metrics; names match what is recorded". - The static METRIC_CATALOG is gone. metric_catalog() is core's own sources (the four monitor types and "steward", the app's open_fds/open_fds_pct, which were recorded but never offered) plus each loaded plugin's get_alert_metrics() export. A disabled plugin's sources leave the picker. - traefik offers what it records: error_rate_4xx_pct and error_rate_5xx_pct. The old "error_rate" was never recorded, so a rule on it could not fire. - tests/core/test_metric_catalog.py walks every MetricBatch.add / record_metric call (traefik's tuple loop included) and fails on a recorded metric the catalog lacks; it shows on a synthetic writer that it can fail. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
72 lines
2.6 KiB
Python
72 lines
2.6 KiB
Python
# plugins/docker/__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 DockerContainer, DockerMetric # noqa: F401 — register with Base
|
|
|
|
# Publish the per-host persist hook so the host agent can hand off the
|
|
# `docker` array from each sample without importing our models (opportunistic
|
|
# synergy — host_agent gates on has_capability and no-ops if we're disabled).
|
|
# required_role=viewer: this is a trusted server-side data-plane write driven
|
|
# by the authenticated agent ingest, not a user-facing privileged action.
|
|
from steward.core.capabilities import register_capability
|
|
from steward.models.users import UserRole
|
|
from .ingest import persist_host_docker
|
|
from .retention import run_docker_retention
|
|
register_capability(
|
|
"docker.persist_host_samples", persist_host_docker,
|
|
label="Persist host Docker samples",
|
|
description="Store per-host container state + metrics pushed by the host agent.",
|
|
required_role=UserRole.viewer,
|
|
)
|
|
# Roll up + prune Docker time-series, driven by the core cleanup task without
|
|
# it importing our models. Same trusted server-side data-plane role as above.
|
|
register_capability(
|
|
"docker.run_retention", run_docker_retention,
|
|
label="Run Docker retention",
|
|
description="Roll up old docker_metrics to hourly + prune stale metrics/events.",
|
|
required_role=UserRole.viewer,
|
|
)
|
|
|
|
|
|
def get_scheduled_tasks() -> list:
|
|
# Collection is now agent-driven (pushed to the host_agent ingest); the
|
|
# central socket scrape was removed. No periodic task to register.
|
|
return []
|
|
|
|
|
|
def get_blueprint():
|
|
from .routes import docker_bp
|
|
return docker_bp
|
|
|
|
|
|
def register_mcp_tools(register) -> None:
|
|
from .mcp_tools import register_tools
|
|
register_tools(register)
|
|
|
|
|
|
async def mcp_overview(db) -> list[dict]:
|
|
from .mcp_tools import mcp_overview as findings
|
|
return await findings(db)
|
|
|
|
|
|
def get_nav() -> list[dict]:
|
|
# Surfaces in the sidebar's Infrastructure group (fleet-wide container view).
|
|
return [{"label": "Docker", "href": "/plugins/docker/"}]
|
|
|
|
|
|
def get_alert_metrics() -> dict[str, list[str]]:
|
|
"""What ingest.py records per container (resource "<host>/<container>"):
|
|
restart_count is cumulative (alert on crash-looping); is_healthy is 1.0 /
|
|
0.0 from the container's HEALTHCHECK, only for containers that define one."""
|
|
return {"docker": ["cpu_pct", "mem_pct", "restart_count", "is_healthy"]}
|