Files
FabledSteward/steward/hosts/routes.py
T
bvandeusenandClaude Opus 5.5 c9f5c049db
CI / lint (push) Successful in 3s
CI / integration (push) Successful in 50s
CI / unit (push) Successful in 1m6s
CI / publish (push) Successful in 1m2s
feat(alerts): renames carry their alerts — monitor and host renames move rules, windows and history (#5065)
#5065 "Renames carry their alerts". Alert rules, maintenance-window scopes
and metric history key a thing by (source, name), so a rename used to leave
the rules watching a name nothing reported under, and split the history.

- core/renames.carry_rename moves AlertRule.resource_name,
  MaintenanceWindow.scope_resource, plugin_metrics and plugin_metrics_hourly
  to the new name in the caller's transaction. A host rename also carries
  its parts: host_agent "<host>:…" and docker "<host>/…" (HOST_SOURCES).
  Matching is exact (a prefix compare, not LIKE or a collation range).
  History left under the new name by something deleted is dropped first
  rather than merged in.
- Web monitor edit, MCP update_monitor and web host edit call it; MCP
  answers with `carried` (it used to return a warning naming stranded rules).
- A name another monitor of the same type, or another host, already has is
  refused on create and rename: two would share one history.
- The rename is audited (monitor.updated / host.renamed) with what moved.

Tests: an integration test renames a firing monitor through the web route
and finds its rule still firing and cleared by a sample on the new name,
its window and raw+hourly history moved and an orphan's history dropped; a
host rename moves agent and container parts but not a longer-named host's
or another source's; a guard that every host_agent resource is "<host>" or
"<host>:…".

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-06 14:02:43 -04:00

322 lines
13 KiB
Python

from __future__ import annotations
import asyncio
import uuid
from quart import Blueprint, render_template, request, redirect, url_for, current_app, session
from sqlalchemy import select
from steward.ansible import executor, sources as ansible_src
from steward.auth.middleware import require_role
from steward.core import renames
from steward.core.audit import audit_request, log_audit
from steward.models.ansible import AnsibleRun, AnsibleRunStatus
from steward.models.hosts import Host
from steward.models.users import UserRole
from steward.hosts import service as host_svc
hosts_bp = Blueprint("hosts", __name__, url_prefix="/hosts")
def _ansible_source_names() -> list[str]:
try:
return [s["name"] for s in ansible_src.get_sources(current_app.config.get("ANSIBLE", {}))]
except Exception:
return []
@hosts_bp.get("/overview/widget")
@require_role(UserRole.viewer)
async def overview_widget():
"""Dashboard widget: unified per-host monitor + agent glance, linking to the hub."""
async with current_app.db_sessionmaker() as db:
hosts = (await db.execute(select(Host).order_by(Host.name))).scalars().all()
host_status = await host_svc.host_status(db, [h.id for h in hosts])
uptime = await host_svc.compute_uptime(db)
host_names = [h.name for h in hosts]
agent = await host_svc.agent_overview_by_host(
db, host_names, host_svc.agent_stale_after_seconds(current_app.config))
cpu_sparks = await host_svc.agent_cpu_sparks_by_host(db, host_names)
return await render_template(
"hosts/overview_widget.html",
hosts=hosts, host_status=host_status,
uptime=uptime, agent=agent, cpu_sparks=cpu_sparks,
)
@hosts_bp.get("/")
@require_role(UserRole.viewer)
async def list_hosts():
async with current_app.db_sessionmaker() as db:
result = await db.execute(select(Host).order_by(Host.name))
hosts = result.scalars().all()
host_status = await host_svc.host_status(db, [h.id for h in hosts])
uptime = await host_svc.compute_uptime(db)
agent_metrics = await host_svc.agent_metrics_by_host(db, [h.name for h in hosts])
return await render_template(
"hosts/list.html",
hosts=hosts,
host_status=host_status,
uptime=uptime,
agent_metrics=agent_metrics,
)
@hosts_bp.get("/<host_id>")
@require_role(UserRole.viewer)
async def host_detail(host_id: str):
"""The host hub: monitors + agent (embedded fragment) + Ansible, one view."""
from steward.models.ansible_inventory import AnsibleTarget
from sqlalchemy.orm import selectinload
async with current_app.db_sessionmaker() as db:
host = (await db.execute(
select(Host).where(Host.id == host_id))).scalar_one_or_none()
if host is None:
return "Not found", 404
monitors = await host_svc.host_monitors(db, host_id)
uptime = (await host_svc.compute_uptime(db)).get(host_id)
linked_target = (await db.execute(
select(AnsibleTarget).where(AnsibleTarget.host_id == host_id)
.options(selectinload(AnsibleTarget.groups)))).scalar_one_or_none()
linkable_targets = (await db.execute(
select(AnsibleTarget).where(AnsibleTarget.host_id.is_(None))
.order_by(AnsibleTarget.name))).scalars().all()
from steward.models.monitors import MonitorType
return await render_template(
"hosts/detail.html",
host=host, monitors=monitors, uptime=uptime,
monitor_types=list(MonitorType),
linked_target=linked_target, linkable_targets=linkable_targets,
ansible_sources=_ansible_source_names(),
)
@hosts_bp.get("/new")
@require_role(UserRole.operator)
async def new_host():
return await render_template("hosts/form.html", host=None)
@hosts_bp.post("/")
@require_role(UserRole.operator)
async def create_host():
form = await request.form
host = Host(
name=form["name"].strip(),
address=form["address"].strip(),
)
async with current_app.db_sessionmaker() as db:
async with db.begin():
try:
await host_svc.check_name_free(db, host.name)
except ValueError as exc:
return str(exc), 400
db.add(host)
await log_audit(current_app, session.get("user_id"), session.get("username", ""),
"host.created", entity_type="host", entity_id=host.name,
detail={"address": host.address})
# Land on the new host's hub so monitors/agent/ansible can be set up next.
return redirect(url_for("hosts.host_detail", host_id=host.id))
@hosts_bp.get("/<host_id>/edit")
@require_role(UserRole.operator)
async def edit_host(host_id: str):
# Pure host config (name/address/monitors). Agent, Ansible target linking,
# and playbook runs live on the host detail page (the hub), not here.
async with current_app.db_sessionmaker() as db:
result = await db.execute(select(Host).where(Host.id == host_id))
host = result.scalar_one_or_none()
if host is None:
return "Not found", 404
return await render_template("hosts/form.html", host=host)
@hosts_bp.post("/<host_id>")
@require_role(UserRole.operator)
async def update_host(host_id: str):
form = await request.form
async with current_app.db_sessionmaker() as db:
async with db.begin():
result = await db.execute(select(Host).where(Host.id == host_id))
host = result.scalar_one_or_none()
if host is None:
return "Not found", 404
old_name, name = host.name, form["name"].strip()
if name != old_name:
try:
await host_svc.check_name_free(db, name, exclude_id=host.id)
except ValueError as exc:
return str(exc), 400
host.name = name
host.address = form["address"].strip()
# Agent and container metrics, and the rules and windows on them,
# go by the host's name: move them with it.
moved = await renames.carry_rename(db, renames.HOST_SOURCES, old_name, name)
if moved:
await audit_request("host.renamed", "host", name,
{"host_id": host_id, "renamed_from": old_name, "carried": moved})
return redirect(url_for("hosts.host_detail", host_id=host_id))
@hosts_bp.post("/<host_id>/ansible-link")
@require_role(UserRole.operator)
async def ansible_link(host_id: str):
"""Link, unlink, or create an AnsibleTarget from this host."""
from steward.models.ansible_inventory import AnsibleTarget
form = await request.form
action = form.get("action", "")
async with current_app.db_sessionmaker() as db:
async with db.begin():
if action == "unlink":
linked_result = await db.execute(
select(AnsibleTarget).where(AnsibleTarget.host_id == host_id)
)
linked = linked_result.scalar_one_or_none()
if linked:
linked.host_id = None
elif action == "link":
target_id = form.get("target_id", "").strip()
if target_id:
result = await db.execute(
select(AnsibleTarget).where(AnsibleTarget.id == target_id)
)
target = result.scalar_one_or_none()
if target:
# Clear any previous link for this host first
old_result = await db.execute(
select(AnsibleTarget).where(AnsibleTarget.host_id == host_id)
)
old = old_result.scalar_one_or_none()
if old and old.id != target_id:
old.host_id = None
target.host_id = host_id
elif action == "create":
host_result = await db.execute(select(Host).where(Host.id == host_id))
host = host_result.scalar_one_or_none()
if host:
new_target = AnsibleTarget(
id=str(uuid.uuid4()),
name=host.name,
address=host.address,
host_id=host_id,
)
db.add(new_target)
return redirect(f"/hosts/{host_id}")
@hosts_bp.post("/<host_id>/run-playbook")
@require_role(UserRole.operator)
async def run_playbook(host_id: str):
"""Run an Ansible playbook against just this host (ephemeral one-host inventory)."""
form = await request.form
async with current_app.db_sessionmaker() as db:
host = (await db.execute(select(Host).where(Host.id == host_id))).scalar_one_or_none()
if host is None:
return "Not found", 404
source_name = (form.get("source_name", "") or "").strip()
playbook = (form.get("playbook_path", "") or "").strip()
if not source_name or not playbook:
return "source and playbook are required", 400
try:
srcs = ansible_src.get_sources(current_app.config.get("ANSIBLE", {}))
except Exception:
return "Ansible sources are misconfigured", 400
source = next((s for s in srcs if s["name"] == source_name), None)
if source is None:
return "Source not found", 404
if playbook not in ansible_src.discover_playbooks(source["path"]):
return f"Playbook '{playbook}' not found in source '{source_name}'", 404
# Shared parser: discovered var__ fields → extra_vars_map, secret__ → secret_vars
# (unpersisted), plus tags/check. No --limit — there's exactly one host.
from steward.ansible.routes import _parse_run_params, _run_vars, check_run_form
params_or_none, secret_vars, err = _parse_run_params(form)
if err:
return err, 400
err = check_run_form(form, source, playbook, params_or_none, secret_vars)
if err:
return err, 400
run_id = str(uuid.uuid4())
inv_content = ansible_src.host_inventory_content(host)
run = AnsibleRun(
id=run_id,
playbook_path=playbook,
inventory_path=f"host: {host.name}",
source_name=source_name,
triggered_by=session.get("user_id"),
status=AnsibleRunStatus.running,
params=params_or_none,
)
async with current_app.db_sessionmaker() as db:
async with db.begin():
db.add(run)
task = asyncio.create_task(
executor.start_run(
current_app._get_current_object(), # type: ignore[attr-defined]
run_id, playbook, f"host: {host.name}", source["path"],
params_or_none, inv_content, secret_vars=secret_vars,
)
)
task.add_done_callback(
lambda t: t.exception() and current_app.logger.error(
"Host playbook run %s raised: %s", run_id, t.exception()))
await log_audit(current_app, session.get("user_id"), session.get("username", ""),
"ansible.host_run", entity_type="host", entity_id=host.name,
detail={"playbook": playbook, "source": source_name, "run_id": run_id,
"check": bool((params_or_none or {}).get("check")),
"vars": sorted(_run_vars(params_or_none, secret_vars))})
return redirect(url_for("ansible.run_detail", run_id=run_id))
@hosts_bp.post("/<host_id>/delete")
@require_role(UserRole.admin)
async def delete_host(host_id: str):
host_name = None
async with current_app.db_sessionmaker() as db:
async with db.begin():
result = await db.execute(select(Host).where(Host.id == host_id))
host = result.scalar_one_or_none()
if host:
host_name = host.name
await db.delete(host)
if host_name:
await log_audit(current_app, session.get("user_id"), session.get("username", ""),
"host.deleted", entity_type="host", entity_id=host_name)
return redirect(url_for("hosts.list_hosts"))
@hosts_bp.get("/uptime")
@require_role(UserRole.viewer)
async def uptime_page():
async with current_app.db_sessionmaker() as db:
result = await db.execute(select(Host).order_by(Host.name))
hosts = result.scalars().all()
uptime = await host_svc.compute_uptime(db)
return await render_template("hosts/uptime.html", hosts=hosts, uptime=uptime)
@hosts_bp.get("/uptime/widget")
@require_role(UserRole.viewer)
async def uptime_widget():
async with current_app.db_sessionmaker() as db:
result = await db.execute(select(Host).order_by(Host.name))
hosts = result.scalars().all()
uptime = await host_svc.compute_uptime(db)
return await render_template(
"hosts/uptime_widget.html",
hosts=hosts,
uptime=uptime,
)