bvandeusenandClaude Opus 5.5
21338dbcd9
MCP-5 of milestone 461 "MCP server: Steward as an LLM-inspectable, LLM-operable hub". Contributed through each plugin's register_mcp_tools hook, so they exist only while the plugin is enabled. docker (viewer, read-only): - list_containers: filter by host, status, compose project, or problem (restarting, crash_looping, unhealthy, oom_killed, exited_nonzero); problems sort first and each row names what is wrong. - get_container: state, CPU/memory history across the raw/hourly seam, lifecycle events. A unique part of a swarm task name is enough. - list_swarm_services: replicas per node (agent-less placements as ghosts) and the swarm's nodes. - search_container_logs: text (% and _ literal), stream, range, context lines, paging by a full-precision `before` cursor; over-long lines keep both ends and say how much of the middle was cut. - get_docker_disk_usage: bytes per host, reclaimable first. - mcp_overview: failing containers and under-replicated swarm services join get_overview. host_agent: list_agents (reporting / stale / pending, version, OS), and an overview finding for agents registered over 30 minutes ago that never checked in. Settings > Thresholds gains the TLS-expiry warn/crit days (were 14/3 in code) and the crash-loop deaths-per-hour count (3), which get_overview and the docker tools now read. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
82 lines
3.2 KiB
Python
82 lines
3.2 KiB
Python
"""The host_agent plugin's MCP tools and its get_overview findings."""
|
|
from __future__ import annotations
|
|
|
|
from datetime import timedelta
|
|
|
|
from sqlalchemy import select
|
|
|
|
from steward.hosts import service as host_svc
|
|
from steward.mcp._context import mcp_app
|
|
from steward.mcp.tools._shape import age_s, db_session, iso, now_utc
|
|
from steward.mcp.tools.overview import finding
|
|
from steward.models.hosts import Host
|
|
from steward.models.users import UserRole
|
|
|
|
from .models import HostAgentRegistration
|
|
|
|
# A registration this old that has never checked in is a failed install, not one in progress.
|
|
PENDING_GRACE = timedelta(minutes=30)
|
|
|
|
|
|
def agent_state(reg, now, stale_after_s: int) -> str:
|
|
"""The agent's state: reporting, stale (stopped checking in) or pending (never has)."""
|
|
if reg.last_seen_at is None:
|
|
return "pending"
|
|
return "reporting" if (now - reg.last_seen_at).total_seconds() <= stale_after_s else "stale"
|
|
|
|
|
|
async def _agents(db):
|
|
return (await db.execute(
|
|
select(HostAgentRegistration, Host)
|
|
.join(Host, Host.id == HostAgentRegistration.host_id)
|
|
.order_by(Host.name)
|
|
)).all()
|
|
|
|
|
|
async def list_agents() -> dict:
|
|
"""Every host agent Steward has registered, with its version and whether it is reporting.
|
|
|
|
`state` is "reporting", "stale" (it checked in before but its last
|
|
check-in is older than the stale window, `stale_after_s`) or "pending"
|
|
(registered, never checked in, usually an install that is still running
|
|
or that failed). Each row carries the agent version, kernel, distro, arch
|
|
and the IP the agent reports. get_host shows an agent's latest metrics.
|
|
"""
|
|
now = now_utc()
|
|
stale_after = host_svc.agent_stale_after_seconds(mcp_app().config)
|
|
async with db_session() as db:
|
|
rows = await _agents(db)
|
|
agents = [
|
|
{
|
|
"host_id": h.id, "host_name": h.name,
|
|
"state": agent_state(reg, now, stale_after),
|
|
"last_seen_at": iso(reg.last_seen_at), "last_seen_age_s": age_s(reg.last_seen_at, now),
|
|
"agent_version": reg.agent_version, "kernel": reg.kernel, "distro": reg.distro,
|
|
"arch": reg.arch, "reported_ip": reg.host_ip,
|
|
"registered_at": iso(reg.created_at),
|
|
}
|
|
for reg, h in rows
|
|
]
|
|
counts = {s: sum(1 for a in agents if a["state"] == s) for s in ("reporting", "stale", "pending")}
|
|
return {"stale_after_s": stale_after, "counts": counts, "agents": agents, "total": len(agents)}
|
|
|
|
|
|
async def mcp_overview(db) -> list[dict]:
|
|
"""Agents registered more than PENDING_GRACE ago that have never checked in.
|
|
|
|
Agents that stopped reporting are already flagged by the core overview
|
|
from their metrics, so they are not repeated here.
|
|
"""
|
|
now = now_utc()
|
|
return [
|
|
finding("warning", "agent_never_reported", h.name,
|
|
"host agent was registered but has never checked in; the install may have failed",
|
|
since=reg.created_at, ids={"host_id": h.id}, next="list_agents()")
|
|
for reg, h in await _agents(db)
|
|
if reg.last_seen_at is None and now - reg.created_at > PENDING_GRACE
|
|
]
|
|
|
|
|
|
def register_tools(register) -> None:
|
|
register(list_agents, role=UserRole.viewer, read_only=True)
|