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>
81 lines
3.7 KiB
Python
81 lines
3.7 KiB
Python
"""The docker plugin's MCP tools: what counts as a problem, and how it is reported."""
|
|
from datetime import datetime, timedelta, timezone
|
|
from types import SimpleNamespace as NS
|
|
from unittest.mock import MagicMock
|
|
|
|
import plugins.docker as docker_plugin
|
|
from plugins.docker import mcp_tools as t
|
|
|
|
NOW = datetime(2026, 10, 6, 12, 0, tzinfo=timezone.utc)
|
|
|
|
|
|
def _c(**kw):
|
|
base = dict(name="web", host_id="h1", image="nginx", status="running", health=None,
|
|
exit_code=None, oom_killed=False, restart_count=0, cpu_pct=1.0, mem_pct=2.0,
|
|
mem_usage_bytes=1, mem_limit_bytes=2, started_at=NOW - timedelta(hours=1),
|
|
compose_project=None, service_name=None, scraped_at=NOW - timedelta(seconds=30))
|
|
base.update(kw)
|
|
return NS(**base)
|
|
|
|
|
|
def test_container_problems_most_severe_first():
|
|
assert t.container_problems(_c(), 0, False) == []
|
|
assert t.container_problems(_c(status="restarting"), 4, True) == ["restarting", "crash_looping"]
|
|
# The crash-loop count comes from Settings → Thresholds.
|
|
assert t.container_problems(_c(), 2, True) == []
|
|
assert t.container_problems(_c(), 2, True, crash_loop_deaths=2) == ["crash_looping"]
|
|
assert t.container_problems(_c(health="unhealthy", oom_killed=True), 0, False) == ["unhealthy", "oom_killed"]
|
|
# An unhealthy flag on a stopped container is stale; it isn't failing a healthcheck now.
|
|
assert t.container_problems(_c(status="exited", health="unhealthy", exit_code=0), 0, False) == []
|
|
|
|
|
|
def test_exited_nonzero_needs_a_recent_death():
|
|
crashed = _c(status="exited", exit_code=137)
|
|
assert t.container_problems(crashed, 1, True) == ["exited_nonzero"]
|
|
# A container that died weeks ago and was left stopped is not news.
|
|
assert t.container_problems(crashed, 0, False) == []
|
|
|
|
|
|
def test_cut_middle_keeps_both_ends_and_sizes_the_gap():
|
|
assert t.cut_middle("short") == "short"
|
|
line = "A" * 10 + "B" * 100 + "C" * 10
|
|
cut = t.cut_middle(line, limit=20)
|
|
assert cut.startswith("A" * 10) and cut.endswith("C" * 10)
|
|
assert "[… 100 characters omitted …]" in cut
|
|
|
|
|
|
def test_container_row_uptime_only_while_running():
|
|
row = t.container_row(_c(), {"h1": "nas"}, [], NOW)
|
|
assert row["host_name"] == "nas" and row["uptime_s"] == 3600 and row["reported_age_s"] == 30
|
|
assert t.container_row(_c(status="exited"), {}, [], NOW)["uptime_s"] is None
|
|
|
|
|
|
def test_container_findings_one_per_container_with_every_problem_named():
|
|
rows = [t.container_row(_c(name="db", status="restarting", exit_code=1), {"h1": "nas"},
|
|
["restarting", "crash_looping"], NOW),
|
|
t.container_row(_c(name="ok"), {}, [], NOW)]
|
|
(f,) = t.container_findings(rows)
|
|
assert f["severity"] == "critical" and f["kind"] == "container_restarting"
|
|
assert "is restarting and keeps dying" in f["summary"] and "on nas" in f["summary"]
|
|
assert "(exit 1)" in f["summary"]
|
|
assert f["next"] == 'get_container(container="db", host="h1")'
|
|
|
|
|
|
def test_service_findings_by_state():
|
|
svcs = [{"name": "a", "state": "healthy", "running": 2, "desired": 2},
|
|
{"name": "b", "state": "degraded", "running": 1, "desired": 3},
|
|
{"name": "c", "state": "down", "running": 0, "desired": 1}]
|
|
got = {f["subject"]: f["severity"] for f in t.service_findings(svcs)}
|
|
assert got == {"b": "warning", "c": "critical"}
|
|
|
|
|
|
def test_plugin_exposes_the_mcp_hooks():
|
|
reg = MagicMock()
|
|
docker_plugin.register_mcp_tools(reg)
|
|
names = {call.args[0].__name__ for call in reg.call_args_list}
|
|
assert names == {"list_containers", "get_container", "list_swarm_services",
|
|
"search_container_logs", "get_docker_disk_usage"}
|
|
for call in reg.call_args_list:
|
|
assert call.kwargs["read_only"] is True
|
|
assert callable(docker_plugin.mcp_overview)
|