feat(mcp): automation tools — playbooks, runs, schedules, alert actions, docker prune

MCP-6 #4970 "Automation tools: playbooks, runs, schedules, alert actions".

Viewer: list_playbooks, get_playbook (secret defaults masked), list_inventory
(variable names only), list_ansible_runs, get_ansible_run (log tail + grep),
list_schedules, wait_for_run (polls, 120s cap).

Operator: run_playbook (check mode unless check=false; a steward:confirm
playbook applies only with confirmed=true; secret variables reach the run
but are never stored, audited or returned), cancel_ansible_run, and
create/update/delete_schedule (secrets refused, check by default).

Admin: set_alert_action, and the docker plugin's prune_docker, which
previews from the disk report unless check=false (Ansible's check mode
skips the prune commands, so a check run would show nothing).

Every write is audited as "<user> via MCP" with the token id; the audit
tool's user filter includes those rows. prune_extra_vars moves to the
docker service so the page and the tool share it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

plugins/docker/mcp_tools.py

@@ -11,11 +11,15 @@ from datetime import datetime, timedelta
 
 from sqlalchemy import select
 
-from steward.mcp._context import mcp_app
+from steward.ansible.runner import trigger_run
+from steward.ansible.sources import BUILTIN_SOURCE_NAME
+from steward.mcp._context import current_caller, mcp_app
+from steward.mcp.tools._audit import audit_mcp
 from steward.mcp.tools._shape import (
     age_s, bounded, clamp_limit, db_session, iso, lookback, now_utc, pick, rnd, summarize,
 )
 from steward.mcp.tools.overview import finding
+from steward.models.ansible_inventory import AnsibleTarget
 from steward.models.hosts import Host
 from steward.models.users import UserRole
 
@@ -412,7 +416,81 @@ async def get_docker_disk_usage(host: str = "") -> dict:
     return {"hosts": rows, "total": len(rows)}
 
 
+PRUNE_BUILTIN_PLAYBOOK = "maintenance/docker_prune.yml"
+_STOPPED = ("exited", "created", "dead")
+
+
+def prune_preview(what: str, usage, stopped: int) -> dict:
+    """What a prune of `what` would remove, from the host's latest disk report."""
+    out: dict = {}
+    if what in ("containers", "system"):
+        out["stopped_containers"] = stopped
+    if what == "images":
+        out["unused_images_bytes"] = usage.images_reclaimable if usage else None
+    if what == "system":
+        out["dangling_images"] = "yes (unused but tagged images stay)"
+        out["build_cache_bytes"] = usage.build_cache_size if usage else None
+        out["unused_networks"] = "yes"
+    return out
+
+
+async def prune_docker(host: str, what: str, check: bool = True) -> dict:
+    """Reclaim Docker disk on a host. Previews unless check=false.
+
+    host: the Steward host's name or id. It needs a linked Ansible target
+      (list_inventory shows the links); the prune runs through Ansible as
+      Steward's built-in docker_prune playbook.
+    what: "containers" removes stopped containers; "images" removes ALL
+      unused images, not only dangling ones; "system" is `docker system
+      prune -f`: stopped containers, dangling images, unused networks and
+      build cache. Volumes are never pruned.
+    check: true (default) starts nothing and returns `would_remove`, sized
+      from the host's latest Docker disk report. Ansible's own check mode
+      skips the prune commands, so a check-mode run would show nothing.
+      Pass false to run the prune.
+
+    Admin only, as on the Docker → Disk page. A real prune returns `run_id`
+    (follow it with wait_for_run) and is recorded in the audit log.
+    """
+    what = (what or "").strip()
+    if what not in docker_svc.PRUNE_TARGETS:
+        raise ValueError(f"what {what!r} is not one of {', '.join(docker_svc.PRUNE_TARGETS)}.")
+    async with db_session() as db:
+        h = pick(host, (await db.execute(select(Host))).scalars(), kind="host", list_tool="list_hosts")
+        target = (await db.execute(
+            select(AnsibleTarget).where(AnsibleTarget.host_id == h.id))).scalars().first()
+        usage = await db.get(DockerDiskUsage, h.id)
+        stopped = sum(1 for c in await docker_svc.list_containers(db, h.id)
+                      if (c.status or "").lower() in _STOPPED)
+    if target is None:
+        raise ValueError(f"host {h.name!r} has no linked Ansible target, so Steward cannot reach it "
+                         "to prune. Link one under Ansible → Inventory. Nothing was run.")
+    preview = {
+        "host": h.name,
+        "what": what,
+        "ansible_target": target.name,
+        "would_remove": prune_preview(what, usage, stopped),
+        "disk_report_age_s": age_s(usage.updated_at) if usage else None,
+    }
+    if check:
+        return {**preview, "check": True,
+                "summary": f"Nothing was run. Pass check=false to prune {what} on {h.name}."}
+    caller = current_caller()
+    run, _src, err = await trigger_run(
+        mcp_app(), source_name=BUILTIN_SOURCE_NAME, playbook_path=PRUNE_BUILTIN_PLAYBOOK,
+        inventory_scope=f"steward:target:{target.id}",
+        params={"extra_vars_map": docker_svc.prune_extra_vars(what)},
+        triggered_by=caller.user_id)
+    if err:
+        raise ValueError(f"the prune could not start: {err}.")
+    await audit_mcp("docker.prune.started", "host", h.name,
+                    {"host_id": h.id, "what": what, "run_id": run.id})
+    return {**preview, "check": False, "run_id": run.id,
+            "next": f'wait_for_run(run_id="{run.id}")'}
+
+
 def register_tools(register) -> None:
     for fn in (list_containers, get_container, list_swarm_services,
                search_container_logs, get_docker_disk_usage):
         register(fn, role=UserRole.viewer, read_only=True)
+    register(prune_docker, role=UserRole.admin, read_only=False)