feat(status): what is wrong first — down monitors and active alerts, and since when (#5120)

#5120 "Status page: what is wrong first".

- A "Needs attention" card heads the Status board: each down monitor with
  how long it has been down, and each active alert (firing, acknowledged,
  pending, no data) with its condition and how long, linking to its history.
- StatusEntry.since / since_at_least: when the current up/down run began,
  from the recent checks (streak_start); "for at least" when every check we
  have agrees.
- Counts as stat tiles (Down, Active alerts, Pending, Up); names wrap
  instead of being cut off; dots carry their label.
- Uptime and TLS are coloured by status_class against Settings → Thresholds
  instead of literal cutoffs; heartbeat pills and DOWN/UP use tokens and
  status_badge rather than hex and bold.
- tests/core/test_status_page.py: streak_start cases, and the rows render
  with the problem card before the list, each since-time, threshold tones
  and no hex colour.

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

.forgejo/workflows/ci.yml

@@ -14,6 +14,17 @@ on:
   # pull_request intentionally absent — push on [dev, main] already fires CI for
   # every dev commit and dev→main PRs. Single-operator repo, no fork PRs.
 
+# Serialize CI runs per ref so the publish lane never shares the runner's docker
+# daemon with another run. Two publishes racing on one daemon evict each other's
+# freshly-built image mid-push, breaking the post-build tag/push (issue #1093).
+# cancel-in-progress:false is deliberate — rule 46 requires EVERY dev/main push to
+# publish its own immutable :<sha> image, so a superseded run must still run to
+# completion (never cancelled) to emit its SHA. (Forgejo honors `concurrency:` —
+# CI-runner's build workflows use it.)
+concurrency:
+  group: ci-${{ github.ref }}
+  cancel-in-progress: false
+
 jobs:
   # Fast-fail lint lane. ruff is pre-installed in the ci-python image, so this
   # runs with NO dependency install and surfaces lint bounces in seconds.
@@ -69,14 +80,24 @@ jobs:
         # act_runner (swarm-runner) puts service containers on the default bridge
         # with no embedded DNS, so the hostname `postgres` won't resolve — we
         # discover the service container's bridge IP via the docker socket. The
-        # job name `integration` (no underscore) is the docker-ps name filter.
+        # job container and its Postgres share a task-number name prefix.
         run: |
           set -euxo pipefail
           echo "=== container landscape (diagnostic for filter scoping) ==="
           docker ps -a --format '{{.ID}} {{.Image}} -> {{.Names}}'
           echo "=== end landscape ==="
-          PG=$(docker ps --filter "name=integration" --filter "ancestor=postgres:16-alpine" -q | head -n1)
-          test -n "$PG"
+          # The runner's daemon is shared: another repo's integration job can be
+          # running beside this one, and `name=integration` matches its Postgres
+          # too (run 8358 took the wrong one and every test failed to connect).
+          # Scope to this job's own task: act_runner names every container of a
+          # task GITEA-ACTIONS-TASK-<n>-…, so read <n> from our own container
+          # (its id is in the /etc/hostname bind mount) and require one match.
+          SELF=$(grep -o '/containers/[0-9a-f]\{64\}/' /proc/self/mountinfo | head -n1 | cut -d/ -f3 || true)
+          SELF=${SELF:-$(hostname)}
+          TASK=$(docker inspect -f '{{.Name}}' "$SELF" | grep -o 'GITEA-ACTIONS-TASK-[0-9]*-')
+          test -n "$TASK"
+          PG=$(docker ps --filter "name=$TASK" --filter "ancestor=postgres:16-alpine" -q)
+          test "$(printf '%s\n' "$PG" | grep -c .)" -eq 1
           PG_IP=$(docker inspect -f '{{range .NetworkSettings.Networks}}{{.IPAddress}}{{end}}' "$PG")
           test -n "$PG_IP"
           export STEWARD_DATABASE_URL="postgresql+asyncpg://steward:steward@$PG_IP:5432/steward"
@@ -115,14 +136,25 @@ jobs:
         run: |
           set -euxo pipefail
           IMAGE=git.fabledsword.com/bvandeusen/steward
-          docker build -t "$IMAGE:${{ github.sha }}" .
-          docker push "$IMAGE:${{ github.sha }}"
+          # The moving tag for this ref: dev→:dev, main→:latest (rule 46). main IS
+          # the production line, so :latest tracks main's tip; there is no :main.
+          MOVING=""
           if [ "${{ github.ref }}" = "refs/heads/dev" ]; then
-            docker tag "$IMAGE:${{ github.sha }}" "$IMAGE:dev"
-            docker push "$IMAGE:dev"
+            MOVING="dev"
           elif [ "${{ github.ref }}" = "refs/heads/main" ]; then
-            docker tag "$IMAGE:${{ github.sha }}" "$IMAGE:latest"
-            docker push "$IMAGE:latest"
+            MOVING="latest"
+          fi
+          # Tag BOTH targets at build time (mirrors CI-runner's build workflows):
+          # one `docker build -t :<sha> -t :<moving>` points both tags at the image
+          # atomically, so we never run a post-push `docker tag` of an image a
+          # concurrent run could have evicted from the shared daemon (issue #1093).
+          if [ -n "$MOVING" ]; then
+            docker build -t "$IMAGE:${{ github.sha }}" -t "$IMAGE:$MOVING" .
+            docker push "$IMAGE:${{ github.sha }}"
+            docker push "$IMAGE:$MOVING"
+          else
+            docker build -t "$IMAGE:${{ github.sha }}" .
+            docker push "$IMAGE:${{ github.sha }}"
           fi
       - name: Prune dangling layers
         if: always()

Dockerfile

@@ -19,10 +19,11 @@ WORKDIR /app
 
 COPY pyproject.toml .
 COPY steward/ steward/
-# Bundle the extras whose first-party plugins ship in the image: [ansible] for
-# the playbook runner, [snmp] (pysnmp) for the SNMP poller. Without them those
-# bundled plugins load but silently no-op for want of their runtime dependency.
-RUN pip install --no-cache-dir '.[ansible,snmp]'
+# Bundle the extras whose features ship in the image: [ansible] for the
+# playbook runner, [snmp] (pysnmp) for the SNMP poller, [ldap] (ldap3, pure
+# Python) for LDAP sign-in under Settings -> Auth. Without them those features
+# load but fail for want of their runtime dependency.
+RUN pip install --no-cache-dir '.[ansible,snmp,ldap]'
 
 COPY alembic.ini .
 # First-party plugins ship inside the image (bundled root at /app/plugins).

ci-requirements.md

@@ -46,7 +46,7 @@ git.fabledsword.com/bvandeusen/ci-python:3.14
 
 - Steward has **no frontend and no Redis/Celery** (no external workers), so there
   is no frontend-build lane and the only service container is Postgres.
-- Integration uses Forgejo Actions `services:` + a socket-discovered bridge IP
+- Integration uses Fabled-Git Actions `services:` + a socket-discovered bridge IP
   because `act_runner` (swarm-runner v0.6+) puts services on the default bridge
   with no embedded DNS. FabledCurator's `ci.yml` is the canonical example of the
   pattern; Steward's is the same shape minus Redis and minus sharding.

config.example.yaml

@@ -13,6 +13,14 @@
 database:
   url: "postgresql+asyncpg://steward:password@localhost/steward"
 
+  # Optional: seconds to wait at startup for the database to become reachable
+  # before giving up (default: 60). Steward retries with backoff rather than
+  # crashing when the DB is merely slow to arrive — replaying WAL after an
+  # unclean shutdown, or container DNS not yet resolving after a host reboot.
+  # Raise it if your database is routinely slower than this to accept
+  # connections. Env var: STEWARD_DB_CONNECT_TIMEOUT
+  # connect_timeout: 60
+
 # Optional: override the auto-generated secret key.
 # If not set, a key is auto-generated on first run and saved to /data/secret.key.
 # secret_key: "change-me-to-a-random-string"

docs/architecture.md

@@ -44,6 +44,30 @@ All routes are Quart Blueprints registered in `app.py`:
 
 Plugin blueprints are mounted automatically by `load_plugins()` using the plugin directory name as the URL prefix.
 
+`/ai-access/` (`ai_access_bp`, `steward/ai_access/routes.py`) is where a signed-in user manages their API tokens.
+
+### `/mcp`: outside the blueprint pipeline
+
+`mount_mcp(app)` (`steward/mcp/server.py`) wraps `app.asgi_app`. A request to
+`/mcp` is handed to the MCP SDK's streamable-HTTP app before Quart sees it, so
+no blueprint, session cookie or `before_request` hook runs for it. Each
+request then goes through these steps:
+
+1. **Database gate.** If the database is unreachable, the request gets a 503
+   with a readable message.
+2. **Bearer resolution.** `api_tokens.resolve_token()` turns the token into a
+   `Caller` (user, effective role, token id). A missing, revoked or expired
+   token gets a 401.
+3. **Caller context.** The `Caller` and the app are set in ContextVars
+   (`steward/mcp/_context.py`). Tools read them through `current_caller()` and
+   `mcp_app()`, because Quart's `current_app` and `session` do not exist there.
+4. **Role gate.** `StewardMCPServer.refusal()` hides and refuses tools above
+   the caller's role, and plugin tools whose plugin is disabled.
+
+The SDK's session manager runs in Quart's `before_serving`/`after_serving`
+lifecycle. The server is stateless: no MCP session outlives a request. See
+[MCP server](core/mcp.md) for the security model and the tools.
+
 ---
 
 ## Scheduler

docs/core/mcp.md

@@ -0,0 +1,132 @@
+# MCP server
+
+Steward serves the [Model Context Protocol](https://modelcontextprotocol.io) at
+`/mcp`. An AI client connected to it can look into everything Steward watches
+(hosts, monitors, alerts, metrics, containers, playbook runs) and, with a
+high enough role, change it. A token's role sets that ceiling.
+
+**Source:** `steward/mcp/`. The tools live in `steward/mcp/tools/`, and a
+plugin's tools live in `plugins/<name>/mcp_tools.py`.
+**Transport:** streamable HTTP, stateless. Every request carries its own
+token, so a client survives a Steward restart without reconnecting.
+
+---
+
+## Connecting
+
+1. In Steward, open **AI access** and create a token. Pick the lowest role
+   that does the job.
+2. Copy the token (it is shown once) and use one of the recipes on that
+   page. They carry the real endpoint URL and the new token. For Claude Code:
+
+   ```sh
+   claude mcp add --transport http steward https://steward.example/mcp \
+     --header "Authorization: Bearer stw_…"
+   ```
+
+3. Ask the client to call `whoami`. It answers with the user, the effective
+   role and what that role allows.
+
+Claude Desktop connects through `mcp-remote`. Open WebUI and other clients
+need an MCP server with the **Streamable HTTP** transport and bearer
+authentication. The AI access page shows the recipes for both.
+
+### Behind a reverse proxy
+
+- The URL on the AI access page is **Settings → General → Public base URL**
+  plus `/mcp`. If that setting is empty, the URL is built from the request's
+  host instead.
+- The proxy must pass the `Authorization` header through unchanged.
+- It must not buffer responses. Replies may arrive as server-sent events
+  (`text/event-stream`). For nginx, set `proxy_buffering off;` on the
+  location.
+- Steward does no Host-header (DNS-rebinding) check on `/mcp`, because the
+  bearer token is the security boundary. Serve it over HTTPS.
+
+---
+
+## Security model
+
+| Rule | How it is enforced |
+|---|---|
+| Bearer tokens only, no OAuth | `steward/core/api_tokens.py`. Only a hash is stored, and the token is shown once. |
+| A token never acts above its user | Effective role = min(token role, user's **current** role). Lowering a user lowers every token they hold; disabling the user stops them all. |
+| Default deny | A tool is reachable only if it was registered with a role (`register_tool(fn, role=..., read_only=...)`). `tools/list` shows a caller only the tools their role allows. A call above the role is refused, and the refusal names the role it needs. |
+| Plugin tools follow the plugin | A disabled plugin's tools are hidden and refused. |
+| Dry run first | `run_playbook`, `create_schedule` and `set_alert_action` default to Ansible check mode (`--check --diff`). Changes are applied only when the caller passes `check=false`. A playbook its author flagged `# steward:confirm: true` also needs `confirmed=true`. `prune_docker` previews unless `check=false`. |
+| Secrets stay put | Playbook variables Steward detects as secret reach the run but are never stored, audited or returned. Schedules and alert actions refuse them, since they would have to store them. Inventory variables are listed by name only, and HTTP monitor header values are redacted. |
+| Every change is audited | Each write records an audit event as `<user> via MCP`, with the token id in its detail. `list_audit_events(user="<user>")` includes those events. |
+| Unknown arguments are refused | A misspelt argument is rejected with a "did you mean", rather than silently dropped. |
+
+Tokens never mint or revoke tokens; that happens only on the AI access
+page, in a browser session.
+
+---
+
+## Tools by role
+
+Each role includes the tools of the roles above it in this list.
+
+### Viewer: read everything
+
+| Area | Tools |
+|---|---|
+| Start here | `whoami`, `get_overview` (what is wrong now, ranked, each finding with the call that shows its evidence) |
+| Hosts and metrics | `list_hosts`, `get_host`, `get_host_metrics`, `query_metrics` |
+| Monitors | `list_monitors`, `get_monitor` |
+| Alerts | `list_alerts`, `get_alert_history`, `list_alert_rules`, `get_alert_rule_options`, `list_maintenance_windows` |
+| Automation | `list_playbooks`, `get_playbook`, `list_inventory`, `list_ansible_runs`, `get_ansible_run`, `wait_for_run`, `list_schedules` |
+| Audit | `list_audit_events` |
+| Docker plugin | `list_containers`, `get_container`, `list_swarm_services`, `search_container_logs`, `get_docker_disk_usage` |
+| Host agent plugin | `list_agents` |
+
+### Operator: run playbooks, change monitoring
+
+| Area | Tools |
+|---|---|
+| Automation | `run_playbook`, `cancel_ansible_run`, `create_schedule`, `update_schedule`, `delete_schedule` |
+| Monitors | `create_monitor`, `update_monitor`, `set_monitor_enabled` |
+| Alerts | `create_alert_rule`, `update_alert_rule`, `acknowledge_alert`, `create_maintenance_window`, `end_maintenance_window` |
+
+### Admin: destructive and remediation
+
+`set_alert_action` (the playbook a rule runs when it fires), `delete_monitor`,
+`delete_alert_rule`, `prune_docker`.
+
+The client sees each tool's full contract: arguments, what an empty value
+means, and what comes back. That contract is the tool's docstring, so read the
+docstrings in `steward/mcp/tools/` for the detail.
+
+---
+
+## Response conventions
+
+Every tool follows these conventions (`steward/mcp/tools/_shape.py`):
+
+- **Times** are ISO-8601 UTC with a `Z`. Anything with a "when" also carries
+  `age_s`, so the client never does clock arithmetic.
+- **Lists are bounded.** A list response carries `total` and `truncated`. When
+  it was cut, `more` names the argument that fetches the rest. Nothing is cut
+  silently.
+- **Time series** come back as a summary (min/avg/max/p95/last) plus a series
+  of at most 60 points, never raw rows.
+- **Lookup by name or id.** A miss suggests close matches and names the tool
+  that lists the valid choices.
+- **Refusals are readable.** Bad input becomes a tool error that says what was
+  wrong, why, and what to do instead, and nothing is changed. The tools share
+  their validation with the web forms (`monitors/service.py`,
+  `alerts/service.py`), so a value the UI refuses is refused here for the same
+  reason.
+- **Database outages** return a plain "Steward cannot reach its database"
+  rather than a stack trace.
+
+---
+
+## Adding tools
+
+Core tools: add an `async def` to a module in `steward/mcp/tools/` and list it
+in that module's `register()` with its minimum role and `read_only`. A plugin
+exposes `register_mcp_tools(register)`, and optionally `mcp_overview(db)` to
+contribute findings to `get_overview`. See
+[Writing a plugin](../plugins/writing-a-plugin.md). A tool that changes
+anything calls `audit_mcp(...)` from `steward/mcp/tools/_audit.py`.

docs/plugins/host-agent-design.md

@@ -74,8 +74,15 @@ token = a1b2c3d4...
 interval_seconds = 30
 hostname = myhost              # optional; defaults to uname -n
 mounts = /, /mnt/data          # optional; defaults to all real mounts (excluding tmpfs/devtmpfs/etc.)
+docker_logs_enabled = true     # optional; on by default — per-host container-log kill-switch
+docker_log_exclude = watchtower, noisy-svc   # optional; container names whose logs this host skips collecting
 ```
 
+Container-log collection is on by default (no config needed). The two keys above
+are the per-host opt-outs; the operator-facing global toggle + exclude live in
+Settings and are enforced server-side (the push model has no channel to command
+an agent), so they don't require touching a host's conf.
+
 ### Agent internals (function list, not classes)
 
 - `read_config(path)` — parses the conf file into a dict.
@@ -85,10 +92,17 @@ mounts = /, /mnt/data          # optional; defaults to all real mounts (excludin
 - `collect_load()` — reads `/proc/loadavg`, returns `[1m, 5m, 15m]`.
 - `collect_uptime()` — reads `/proc/uptime`, returns seconds since boot (int).
 - `collect_metadata()` — `os.uname()` for kernel + arch, `/etc/os-release` for distro. Called once at startup and cached.
+- `collect_docker_logs(socket, containers, state, exclude)` — (m79) per running
+  container, fetches new log lines over the Docker socket with an incremental
+  `since` cursor kept per container in `state` (a container's first interval
+  seeds from a short tail). Demuxes the multiplexed stream, parses each line's
+  RFC3339 timestamp, caps the whole batch at a byte limit (a marker line records
+  a truncation; the deferred lines come next interval). Folded into the sample as
+  `docker_logs`; omitted when empty.
 - `build_payload()` — assembles a snapshot from all collectors into one dict.
 - `post_payload(url, token, payloads)` — POSTs a list of samples, returns success/failure.
 - `RingBuffer(maxlen=20)` — tiny FIFO wrapper, drops oldest when full.
-- `main_loop()` — the 30s loop: collect → try POST → on failure push to buffer + backoff → on success flush buffer.
+- `main_loop()` — the 30s loop: collect → try POST → on failure push to buffer + backoff → on success flush buffer. Container logs are stripped from a sample before it's buffered (metrics survive an outage; stale logs are dropped).
 
 **Target: ~300 lines total including docstrings.** More than that is a smell that the agent is over-scoping.
 
@@ -255,6 +269,7 @@ Content-Type: application/json
 - **`metadata` is sent on every POST**, not just on change. Server-side diff detects actual changes and only writes on change. Cost per POST is one dict — negligible. Benefit: server can cleanly detect agent restarts.
 - **Raw bytes, not percentages, for memory and storage.** Percentages are derived server-side. Changing the "what counts as used" math doesn't require re-releasing the agent.
 - **CPU is the one exception** — reported as a percentage because it's inherently a derivative (delta over time), not a snapshot. The agent must sample twice to compute it.
+- **Container logs (m79) ride in the same push** as `docker_logs`: a list of `{container, stream, ts, line}` records — incremental since the previous interval. This pushes the *same direction* as metrics, so batched log history needs no inbound channel (only sub-second live-follow would). The server ingests them into `docker_logs`, enforces the global toggle + exclude list on ingest, and bounds storage with a per-container size+age ring. `docker_logs` is omitted when there's nothing new.
 
 ### Server expansion into `PluginMetric` rows
 

docs/plugins/writing-a-plugin.md

@@ -323,6 +323,61 @@ Role hierarchy: `admin > operator > viewer`. Requiring `viewer` grants access to
 
 ---
 
+## Agent Tools (MCP)
+
+Steward serves an MCP endpoint at `/mcp` that AI clients reach with a personal API token created on the AI access page. A plugin adds tools to it by exporting an optional `register_mcp_tools(register)` from `__init__.py`:
+
+```python
+# plugins/myplugin/__init__.py
+def register_mcp_tools(register) -> None:
+    from .mcp_tools import list_targets, rescan_target
+    from steward.models.users import UserRole
+    register(list_targets, role=UserRole.viewer, read_only=True)
+    register(rescan_target, role=UserRole.operator, read_only=False)
+```
+
+```python
+# plugins/myplugin/mcp_tools.py
+from steward.mcp._context import current_caller, mcp_app
+
+
+async def list_targets(limit: int = 50) -> dict:
+    """What this tool is for, when to use it over its siblings, what each
+    argument's empty value means, and what comes back. This docstring is the
+    tool's description: it is all the agent knows about it."""
+    app = mcp_app()                 # Quart's current_app does not exist here
+    async with app.db_sessionmaker() as db:
+        ...
+    return {"targets": [...], "total": n, "truncated": n > limit}
+```
+
+- `role` and `read_only` are required. A tool is listed and callable only for callers whose role reaches `role`, and only while the plugin is enabled.
+- Tools run outside Quart's request pipeline: use `mcp_app()` and `current_caller()` from `steward.mcp._context`, never `current_app` or `session`.
+- Refuse by raising `ValueError("what was wrong, and what to do instead")`. The agent reads that text. Any other exception reaches it only as a generic failure.
+- Tool names are global across core and every plugin; a name already taken fails registration and the plugin contributes no tools (logged).
+- Hot-reloading the plugin replaces its tools.
+- Follow the response conventions the core tools use (`steward/mcp/tools/_shape.py`): times via `iso()` plus `age_s()`, lists through `bounded()` so a cut is never silent, series through `summarize()`, and lookups by name or id through `pick()`.
+
+### Contributing to get_overview
+
+`get_overview` is the agent's first call: what is wrong right now, ranked. A plugin adds its own problems to it by exporting an optional `mcp_overview(db)` that returns findings built with `steward.mcp.tools.overview.finding`:
+
+```python
+# plugins/myplugin/__init__.py
+async def mcp_overview(db) -> list[dict]:
+    from steward.mcp.tools.overview import finding
+    return [
+        finding("warning", "target_unreachable", t.name, f"{t.name} has not answered for {t.misses} scans",
+                since=t.last_ok_at, ids={"target_id": t.id}, next=f'get_target(target="{t.id}")')
+        for t in await _unreachable_targets(db)
+    ]
+```
+
+- `severity` is `"critical"` (something is down or about to be) or `"warning"` (degraded, or heading that way). Report problems only; a healthy plugin returns `[]`.
+- It is called only while the plugin is enabled, with its own session. If it raises, the overview still returns, and names the plugin under `unavailable`.
+
+---
+
 ## Publishing to the Catalog
 
 The official plugin catalog is hosted at `https://git.fabledsword.com/bvandeusen/Steward-plugins`. Anyone can submit a plugin by opening a pull request — first-party and third-party plugins are treated identically by the catalog system.
@@ -413,6 +468,7 @@ Hot-reload works reliably for brand-new plugin installs. Updates to already-acti
 - [ ] Revision IDs prefixed with plugin name
 - [ ] `record_metric()` called inside `session.begin()`
 - [ ] Routes use `@require_role` decorator
+- [ ] MCP tools (if any) registered via `register_mcp_tools(register)` with a role and `read_only`
 - [ ] Templates namespaced under `templates/myplugin/`
 - [ ] Plugin enabled in app settings
 - [ ] `index.yaml` entry added with `download_url` and `checksum_sha256`

docs/reference/code-map.md

@@ -136,3 +136,25 @@ Quick reference for where key functions, models, and entry points live in the co
 | `steward/migrations/versions/` | Core schema (hosts, users, monitors, alerts, app_settings) |
 | `plugins/traefik/migrations/versions/` | `traefik_metrics` table |
 | `alembic.ini` | Alembic config; `version_locations` lists all migration directories |
+
+---
+
+## MCP server and API tokens
+
+| What | File | Function / Class |
+|---|---|---|
+| Mount `/mcp` (ASGI dispatch, bearer auth, DB gate) | `steward/mcp/server.py` | `mount_mcp(app)` |
+| Server, role registry, refusals | `steward/mcp/server.py` | `StewardMCPServer`, `register_tool()`, `refusal()` |
+| Plugin tools and overview findings | `steward/mcp/server.py` | `register_plugin(name, module)` |
+| Caller and app inside a tool | `steward/mcp/_context.py` | `current_caller()`, `mcp_app()` |
+| Core tool modules | `steward/mcp/tools/` | `register_all()`; one module per area |
+| Response conventions | `steward/mcp/tools/_shape.py` | `iso`, `age_s`, `bounded`, `lookback`, `summarize`, `pick` |
+| Audit a write as "<user> via MCP" | `steward/mcp/tools/_audit.py` | `audit_mcp()` |
+| "What is wrong now" | `steward/mcp/tools/overview.py` | `get_overview()` |
+| Playbooks, runs, schedules, alert actions | `steward/mcp/tools/automation.py` | `run_playbook()`, `wait_for_run()`, … |
+| Monitor validation (forms and tools) | `steward/monitors/service.py` | `monitor_fields()`, `build_config()` |
+| Alert rule / window validation | `steward/alerts/service.py` | `rule_fields()`, `window_fields()`, `acknowledge()` |
+| Docker and host-agent tools | `plugins/docker/mcp_tools.py`, `plugins/host_agent/mcp_tools.py` | `register_tools()`, `mcp_overview()` |
+| Token model | `steward/models/api_tokens.py` | `ApiToken` |
+| Mint, resolve, revoke tokens | `steward/core/api_tokens.py` | `create_token()`, `resolve_token()`, `revoke_token()` |
+| Token management page and connect card | `steward/ai_access/routes.py`, `steward/templates/ai_access/` | `ai_access_bp` |

plugins/docker/__init__.py

@@ -49,6 +49,23 @@ def get_blueprint():
     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"]}

plugins/docker/ingest.py

@@ -92,6 +92,55 @@ def _derive_events(old_state: dict, new_containers: list) -> list:
     return events
 
 
+def _log_rows(log_batches, host_id: str):
+    """Pure: flatten the agent's log batches → docker_logs row kwargs (no DB).
+
+    `log_batches` is a list of (recorded_at, records) where each record is
+    {"container", "stream", "ts", "line"}. A line's own Docker timestamp wins;
+    recorded_at is the fallback when the agent couldn't parse one. Drops the
+    agent's advisory truncation marker (container "_steward" — it signals a
+    deferral, not a real container), malformed records, and lineless records;
+    normalises an unknown stream to stdout. Unit-testable in isolation.
+    """
+    for recorded_at, records in log_batches:
+        if not isinstance(records, list):
+            continue
+        for rec in records:
+            if not isinstance(rec, dict):
+                continue
+            name = rec.get("container")
+            line = rec.get("line")
+            if not name or name == "_steward" or line is None:
+                continue
+            ts = _parse_started_at(rec.get("ts")) or recorded_at
+            stream = rec.get("stream")
+            if stream not in ("stdout", "stderr"):
+                stream = "stdout"
+            yield {"host_id": host_id, "container_name": str(name)[:255],
+                   "ts": ts, "stream": stream, "line": str(line)}
+
+
+async def _persist_logs(session, host, log_batches) -> None:
+    """Append pushed container log lines (one row per line) for this host.
+
+    Time-series / append-only — the per-container size+age ring (retention)
+    bounds growth, so a chatty container just keeps a shorter window. The global
+    toggle + exclude list (Settings, no restart) are enforced here: this is the
+    authoritative drop point, since the push model has no channel to tell an
+    agent to stop collecting.
+    """
+    from steward.core.settings import get_setting
+    from .models import DockerLog
+
+    if not await get_setting(session, "docker.logs.enabled"):
+        return
+    exclude = set(await get_setting(session, "docker.logs.exclude") or ())
+    for row in _log_rows(log_batches, host.id):
+        if row["container_name"] in exclude:
+            continue
+        session.add(DockerLog(**row))
+
+
 async def _persist_swarm(session, host, swarm: dict) -> None:
     """Upsert this manager's swarm topology; drop rows no longer reported.
 
@@ -120,6 +169,7 @@ async def _persist_swarm(session, host, swarm: dict) -> None:
         row.running = int(s.get("running") or 0)
         row.image = s.get("image")
         row.placement_json = json.dumps(s.get("placement") or [])
+        row.tasks_json = json.dumps(s.get("tasks") or [])
         row.updated_at = now
     stale_services = delete(DockerSwarmService).where(
         DockerSwarmService.host_id == host.id)
@@ -201,7 +251,8 @@ async def _persist_disk(session, host, disk: dict) -> None:
     await session.execute(stale)
 
 
-async def persist_host_docker(session, host, snapshots, swarm=None, disk=None) -> None:
+async def persist_host_docker(session, host, snapshots, swarm=None, disk=None,
+                              logs=None) -> None:
     """Upsert containers + time-series + lifecycle events + swarm for one host.
 
     `snapshots` is a list of (recorded_at: datetime, containers: list[dict]) —
@@ -211,15 +262,19 @@ async def persist_host_docker(session, host, snapshots, swarm=None, disk=None) -
     alert pipeline, and lifecycle-event derivation. `swarm` is the newest
     sample's swarm object (or None off managers) — persisted when present.
     `disk` is the newest sample's /system/df summary (or None on Docker-less
-    hosts) — persisted when present.
+    hosts) — persisted when present. `logs` is a list of (recorded_at, records)
+    log batches (m79) — appended one row per line when present, independent of
+    whether this sample also carried container metrics.
     """
-    from steward.core.alerts import record_metric
+    from steward.core.alerts import MetricBatch
     from .models import DockerContainer, DockerEvent, DockerMetric
 
     if swarm is not None:
         await _persist_swarm(session, host, swarm)
     if disk is not None:
         await _persist_disk(session, host, disk)
+    if logs:
+        await _persist_logs(session, host, logs)
 
     if not snapshots:
         return
@@ -258,6 +313,7 @@ async def persist_host_docker(session, host, snapshots, swarm=None, disk=None) -
             ))
 
     # Current state + alerts from the newest snapshot only.
+    batch = MetricBatch()
     for c in latest_containers:
         name = c.get("name")
         if not name:
@@ -295,19 +351,19 @@ async def persist_host_docker(session, host, snapshots, swarm=None, disk=None) -
         # on different hosts don't collide in the metric/alert namespace.
         resource = f"{host.name}/{name}"
         if c.get("status") == "running" and c.get("cpu_pct") is not None:
-            await record_metric(
-                session=session, source_module="docker",
+            batch.add(
+                source_module="docker",
                 resource_name=resource, metric_name="cpu_pct", value=c["cpu_pct"],
             )
             if c.get("mem_pct") is not None:
-                await record_metric(
-                    session=session, source_module="docker",
+                batch.add(
+                    source_module="docker",
                     resource_name=resource, metric_name="mem_pct", value=c["mem_pct"],
                 )
         # Restart count is alertable regardless of state (crash-looping matters
         # most while the container is down/restarting).
-        await record_metric(
-            session=session, source_module="docker",
+        batch.add(
+            source_module="docker",
             resource_name=resource, metric_name="restart_count",
             value=float(c.get("restart_count", 0) or 0),
         )
@@ -316,12 +372,14 @@ async def persist_host_docker(session, host, snapshots, swarm=None, disk=None) -
         # container).
         health = c.get("health")
         if health in ("healthy", "unhealthy", "starting"):
-            await record_metric(
-                session=session, source_module="docker",
+            batch.add(
+                source_module="docker",
                 resource_name=resource, metric_name="is_healthy",
                 value=1.0 if health == "healthy" else 0.0,
             )
 
+    await batch.record(session)
+
     # Reap containers that vanished from the host's latest listing. Without this,
     # removed one-shot containers (CI job runners, buildkit builders, codex jobs)
     # accumulate forever as permanent "stopped" rows and inflate every count.

plugins/docker/mcp_tools.py

@@ -0,0 +1,703 @@
+"""The docker plugin's MCP tools and its get_overview findings.
+
+Registered through register_mcp_tools() in __init__.py, so they exist only
+while the plugin is enabled. Reads go through service.py, the same functions
+the plugin's pages use.
+"""
+from __future__ import annotations
+
+import json
+from dataclasses import dataclass
+from datetime import datetime, timedelta
+
+from sqlalchemy import select
+
+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
+
+from . import service as docker_svc
+from .dedup import dedup_by_container_id
+from .models import DockerDiskUsage, DockerSwarmNode, DockerSwarmService
+from .swarm_view import build_swarm_services, replaced_tasks, task_time
+
+PROBLEMS = ("restarting", "crash_looping", "unhealthy", "oom_killed", "exited_nonzero")
+CRASH_LOOP_DEATHS = docker_svc.CRASH_LOOP_DEATHS
+LOG_LINE_CHARS = 2000
+
+
+# ── pure helpers ─────────────────────────────────────────────────────────────
+
+def container_problems(c, failures_1h: int, failed_24h: bool,
+                       crash_loop_deaths: int = CRASH_LOOP_DEATHS) -> list[str]:
+    """What is wrong with one container, most severe first; [] when nothing is."""
+    status = (c.status or "").lower()
+    out = []
+    if status == "restarting":
+        out.append("restarting")
+    if failures_1h >= crash_loop_deaths:
+        out.append("crash_looping")
+    if status == "running" and (c.health or "") == "unhealthy":
+        out.append("unhealthy")
+    if c.oom_killed:
+        out.append("oom_killed")
+    if status in ("exited", "dead") and (c.exit_code or 0) != 0 and failed_24h:
+        out.append("exited_nonzero")
+    return out
+
+
+def problem_since(problems: list[str], deaths: list, hour_ago: datetime,
+                  unhealthy_at: datetime | None = None) -> datetime | None:
+    """When a container's worst problem began; None when the retained events
+    cannot say. `deaths` are its die/oom events of the last 24h, newest first.
+
+    A restart or crash loop dates from its first death in the last hour, an
+    OOM kill or error exit from the death that ended it, and a failing
+    healthcheck from when its health last turned unhealthy.
+    """
+    if not problems:
+        return None
+    worst = problems[0]
+    if worst in ("restarting", "crash_looping"):
+        in_hour = [e.at for e in deaths if e.at >= hour_ago]
+        return min(in_hour) if in_hour else (deaths[0].at if deaths else None)
+    if worst == "unhealthy":
+        return unhealthy_at
+    if worst == "oom_killed":
+        ooms = [e.at for e in deaths if e.event == "oom"]
+        return ooms[0] if ooms else (deaths[0].at if deaths else None)
+    return deaths[0].at if deaths else None
+
+
+def cut_middle(text: str, limit: int = LOG_LINE_CHARS) -> str:
+    """Keep both ends of an over-long line and say how much of the middle went."""
+    if text is None or len(text) <= limit:
+        return text
+    keep = limit // 2
+    return f"{text[:keep]} [… {len(text) - 2 * keep} characters omitted …] {text[-keep:]}"
+
+
+def container_row(c, host_names: dict, problems: list[str], now: datetime,
+                  replaced: bool = False, since: datetime | None = None) -> dict:
+    running = (c.status or "").lower() == "running"
+    return {
+        "container_name": c.name,
+        "host_id": c.host_id,
+        "host_name": host_names.get(c.host_id),
+        "image": c.image,
+        "status": c.status,
+        "health": c.health,
+        "problems": problems,
+        # When the worst problem began, from the container's retained events.
+        "problem_since": iso(since),
+        "problem_age_s": age_s(since, now),
+        "exit_code": c.exit_code,
+        "oom_killed": bool(c.oom_killed),
+        "restart_count": c.restart_count,
+        "cpu_pct": rnd(c.cpu_pct),
+        "mem_pct": rnd(c.mem_pct),
+        "mem_usage_bytes": c.mem_usage_bytes,
+        "mem_limit_bytes": c.mem_limit_bytes,
+        "started_at": iso(c.started_at),
+        "uptime_s": age_s(c.started_at, now) if running and c.started_at else None,
+        "compose_project": c.compose_project,
+        "swarm_service": c.service_name,
+        # A swarm task Swarm has replaced: history, judged on its service.
+        "swarm_replaced": replaced if c.service_name else None,
+        "reported_at": iso(c.scraped_at),
+        "reported_age_s": age_s(c.scraped_at, now),
+    }
+
+
+_SEVERITY = {"restarting": "critical", "crash_looping": "critical", "unhealthy": "critical",
+             "oom_killed": "warning", "exited_nonzero": "warning"}
+_SAYS = {"restarting": "is restarting", "crash_looping": "keeps dying",
+         "unhealthy": "fails its healthcheck", "oom_killed": "was OOM-killed",
+         "exited_nonzero": "exited with an error"}
+
+
+def _from_iso(text: str | None) -> datetime | None:
+    return datetime.fromisoformat(text.replace("Z", "+00:00")) if text else None
+
+
+def container_findings(rows: list[dict]) -> list[dict]:
+    out = []
+    for r in rows:
+        if not r["problems"]:
+            continue
+        worst = r["problems"][0]
+        where = f" on {r['host_name']}" if r["host_name"] else ""
+        detail = f" (exit {r['exit_code']})" if r["exit_code"] not in (None, 0) else ""
+        out.append(finding(
+            _SEVERITY[worst], f"container_{worst}", r["container_name"],
+            f"container {r['container_name']}{where} {' and '.join(_SAYS[p] for p in r['problems'])}{detail}",
+            since=_from_iso(r["problem_since"]),
+            ids={"host_id": r["host_id"], "container_name": r["container_name"]},
+            next=f'get_container(container="{r["container_name"]}", host="{r["host_id"]}")'))
+    return out
+
+
+def task_error_text(err: dict | None) -> str:
+    """Swarm's own account of a task's end, as one clause."""
+    if not err:
+        return ""
+    why = err.get("error") or err.get("message") or err.get("state") or "unknown"
+    code = f", exit {err['exit_code']}" if err.get("exit_code") not in (None, 0) else ""
+    where = f" on {err['node']}" if err.get("node") else ""
+    return f"{why}{code}{where}"
+
+
+def service_findings(services: list[dict]) -> list[dict]:
+    """Swarm services that are failing: crash-looping, under-replicated, or that
+    lost a task to an error in the last 24h. Each names Swarm's last task error."""
+    out = []
+    for s in services:
+        replicas = f"{s['running']} of {s['desired']} replicas running"
+        last = task_error_text(s.get("last_error"))
+        tail = f"; last task error: {last}" if last else ""
+        ids = {"service_name": s["name"]}
+        since = s.get("trouble_since")
+        if s.get("crash_looping"):
+            out.append(finding(
+                "critical", "swarm_service_crash_looping", s["name"],
+                f"swarm service {s['name']} keeps failing: {s['failures_1h']} tasks failed in the "
+                f"last hour, {replicas}{tail}", since=since, ids=ids,
+                next="list_swarm_services()"))
+        elif s["state"] != "healthy":
+            out.append(finding(
+                "critical" if s["state"] == "down" else "warning", f"swarm_service_{s['state']}",
+                s["name"], f"swarm service {s['name']} has {replicas}{tail}",
+                since=since, ids=ids, next="list_swarm_services()"))
+        elif s.get("failures_24h"):
+            n = s["failures_24h"]
+            out.append(finding(
+                "warning", "swarm_task_failed", s["name"],
+                f"swarm service {s['name']} had {n} failed task{'s' if n != 1 else ''} in the last "
+                f"24h and is now {replicas}{tail}", since=since, ids=ids,
+                next="list_swarm_services()"))
+    return out
+
+
+# ── loading ──────────────────────────────────────────────────────────────────
+
+async def _host_names(db) -> dict[str, str]:
+    return dict((await db.execute(select(Host.id, Host.name))).all())
+
+
+def _crash_loop_deaths() -> int:
+    return docker_svc.crash_loop_deaths(mcp_app().config)
+
+
+async def _replaced(db, containers) -> set[tuple]:
+    services = list((await db.execute(select(DockerSwarmService))).scalars())
+    return replaced_tasks(containers, services)
+
+
+async def _rows(db, now: datetime) -> list[dict]:
+    """Every container with its problems. A swarm task Swarm replaced has none:
+    its failure, if it was one, belongs to its service (service_findings)."""
+    containers = dedup_by_container_id(await docker_svc.list_containers(db))
+    replaced = await _replaced(db, containers)
+    failures = await docker_svc.recent_failures_by_container(db, now - timedelta(hours=24))
+    hour_ago = now - timedelta(hours=1)
+    host_names = await _host_names(db)
+    deaths = _crash_loop_deaths()
+    sick = await docker_svc.unhealthy_since(
+        db, [(c.host_id, c.name) for c in containers if (c.health or "") == "unhealthy"])
+    rows = []
+    for c in containers:
+        key = (c.host_id, c.name)
+        gone = key in replaced
+        events = failures.get(key, [])
+        recent = sum(1 for e in events if e.at >= hour_ago)
+        problems = [] if gone else container_problems(c, recent, bool(events), deaths)
+        since = problem_since(problems, events, hour_ago, sick.get(key))
+        rows.append(container_row(c, host_names, problems, now, replaced=gone, since=since))
+    return rows
+
+
+async def _swarm(db, now: datetime):
+    containers = dedup_by_container_id(await docker_svc.list_containers(db))
+    services = list((await db.execute(select(DockerSwarmService))).scalars())
+    nodes = list((await db.execute(select(DockerSwarmNode))).scalars())
+    host_names = await _host_names(db)
+    node_hostname = {n.node_id: n.hostname for n in nodes if n.hostname}
+    built = build_swarm_services(containers, services, node_hostname, host_names,
+                                 now=now, crash_loop_deaths=_crash_loop_deaths())
+    return built["services"], nodes, host_names
+
+
+async def mcp_overview(db) -> list[dict]:
+    """get_overview findings: failing containers and under-replicated swarm services."""
+    now = now_utc()
+    rows = await _rows(db, now)
+    services, _, _ = await _swarm(db, now)
+    return container_findings(rows) + service_findings(services)
+
+
+# ── tools ────────────────────────────────────────────────────────────────────
+
+async def list_containers(host: str = "", status: str = "", problem: str = "",
+                          compose_project: str = "", limit: int = 100) -> dict:
+    """Docker containers across every host that runs a Steward agent with Docker.
+
+    host: a host's name or id (list_hosts); empty for all hosts.
+    status: Docker's state — "running", "exited", "restarting", "paused",
+      "created" or "dead"; empty for all.
+    problem: "any" for containers with something wrong, or one of
+      "restarting", "crash_looping" (died repeatedly within the last hour;
+      the count is set under Settings → Thresholds, default 3), "unhealthy"
+      (failing its healthcheck), "oom_killed", "exited_nonzero" (died with an
+      error in the last 24h); empty for no filter.
+    compose_project: only containers from this Compose project.
+    limit: default 100, max 500.
+
+    Containers with problems come first. Each row's `problems` lists what is
+    wrong, most severe first, and `problem_since` / `problem_age_s` say when
+    the worst of them began (null when Steward's retained events cannot say).
+    `reported_age_s` is how old the agent's last report is, so a large value
+    means the row may be stale.
+
+    A swarm task's container that Swarm has replaced (a rolling update, or a
+    retry after a failure) has `swarm_replaced: true` and no problems: Swarm
+    restarts a task as a new container, so failures are counted on the
+    service — list_swarm_services shows them.
+    """
+    if problem and problem != "any" and problem not in PROBLEMS:
+        raise ValueError(f"problem {problem!r} is not 'any' or one of {', '.join(PROBLEMS)}.")
+    limit = clamp_limit(limit, 100, 500)
+    now = now_utc()
+    async with db_session() as db:
+        rows = await _rows(db, now)
+        if host:
+            hosts = list((await db.execute(select(Host))).scalars())
+            h = pick(host, hosts, kind="host", list_tool="list_hosts")
+            rows = [r for r in rows if r["host_id"] == h.id]
+    if status:
+        rows = [r for r in rows if (r["status"] or "").lower() == status.lower()]
+    if problem == "any":
+        rows = [r for r in rows if r["problems"]]
+    elif problem:
+        rows = [r for r in rows if problem in r["problems"]]
+    if compose_project:
+        rows = [r for r in rows if r["compose_project"] == compose_project]
+    rows.sort(key=lambda r: (not r["problems"], (r["status"] or "") != "running",
+                             (r["host_name"] or "").lower(), r["container_name"]))
+    return bounded(rows, limit, key="containers",
+                   more="Pass a larger `limit` (max 500), or filter by `host`, `status` or `problem`.")
+
+
+@dataclass
+class RemovedContainer:
+    """A container Docker has removed, known only by its retained logs and events."""
+    host_id: str
+    name: str
+    last_seen: datetime
+
+
+_REMOVED_HINT = ("It may have been removed: Swarm replaces a dead task with a new container under "
+                 "a new name. list_containers(status=\"exited\") lists stopped containers, and "
+                 "search_container_logs(host=...) searches a whole host.")
+
+
+async def _pick_container(db, container: str, host: str, *, removed: bool = False):
+    """The container named `container`: a live one, else (with `removed`) one
+    Docker has removed whose logs or events Steward still holds, returned as a
+    RemovedContainer. Exact names beat partial ones, and live beats removed."""
+    containers = await docker_svc.list_containers(db)
+    host_id = None
+    if host:
+        hosts = list((await db.execute(select(Host))).scalars())
+        host_id = pick(host, hosts, kind="host", list_tool="list_hosts").id
+        containers = [c for c in containers if c.host_id == host_id]
+    want = (container or "").strip()
+    if not want:
+        raise ValueError("pass a container name; list_containers lists them.")
+    live = {(c.host_id, c.name) for c in containers}
+
+    def _one(found, what):
+        if len(found) > 1:
+            raise ValueError(f"{len(found)} hosts have {what} named {want!r}; pass `host` "
+                             f"(one of: {', '.join(sorted(f[0] for f in found))}).")
+        return found[0] if found else None
+
+    same = [c for c in containers if c.name == want] or \
+           [c for c in containers if c.name.lower() == want.lower()]
+    if same:
+        return _one([(c.host_id, c) for c in same], "a container")[1]
+    if removed:
+        gone = [r for r in await docker_svc.retained_names(db, want, exact=True, host_id=host_id)
+                if (r[0], r[1]) not in live]
+        if gone:
+            return RemovedContainer(*_one(gone, "a removed container"))
+    # One more chance: a unique container whose name contains it (swarm task
+    # names look like "stack_svc.1.k2j…").
+    partial = [c for c in containers if want.lower() in c.name.lower()]
+    if len(partial) == 1:
+        return partial[0]
+    gone = []
+    if removed and not partial:
+        gone = [r for r in await docker_svc.retained_names(db, want, exact=False, host_id=host_id)
+                if (r[0], r[1]) not in live]
+        if len(gone) == 1:
+            return RemovedContainer(*gone[0])
+    names = sorted(c.name for c in partial)[:10] + [f"{r[1]} (removed)" for r in gone[:10]]
+    hint = f" Containers whose names contain it: {', '.join(names)}." if names else ""
+    raise ValueError(f"no container named {want!r}{' on that host' if host else ''}.{hint} "
+                     f"{'' if names else _REMOVED_HINT + ' '}list_containers lists them.")
+
+
+def _removed_note(c: RemovedContainer) -> str:
+    return (f"{c.name} no longer exists: Docker removed it (Swarm replaces a failed task with a new "
+            f"container). This is what Steward retained; it was last seen {iso(c.last_seen)}.")
+
+
+async def get_container(container: str, host: str = "", range: str = "24h", events: int = 20) -> dict:
+    """One container in depth: state, resources over time and lifecycle events.
+
+    container: the container's name, as list_containers shows. A unique part of
+      a name also works (swarm task names are long).
+    host: the host's name or id. Needed only when several hosts run a
+      container with this name.
+    range: the window for `cpu_pct_history` and `mem_pct_history` (min, avg,
+      max, p95, last and a ≤60-point series) — "1h", "6h", "24h" (default),
+      "7d" or "30d". `cpu_pct` and `mem_pct` are the latest reported values.
+    events: how many lifecycle events (start, stop, die, oom, health_change)
+      to return, newest first (default 20, max 100).
+
+    A container Docker has since removed (a dead Swarm task, a `docker rm`)
+    still resolves by its exact name, or by a part of it that matches one
+    removed container, while Steward retains its logs or events: the reply
+    has `removed: true`, `last_seen_at`, its history and its events, and no
+    live state. A live container has `removed: false`.
+    """
+    since, key = lookback(range)
+    events = clamp_limit(events, 20, 100)
+    now = now_utc()
+    async with db_session() as db:
+        c = await _pick_container(db, container, host, removed=True)
+        if isinstance(c, RemovedContainer):
+            return await _removed_container(db, c, since, key, events, now)
+        gone = (c.host_id, c.name) in await _replaced(db, await docker_svc.list_containers(db))
+        failures = (await docker_svc.recent_failures_by_container(
+            db, now - timedelta(hours=24))).get((c.host_id, c.name), [])
+        host_names = await _host_names(db)
+        cpu = await docker_svc.container_points(db, c.host_id, c.name, "cpu_pct", since)
+        mem = await docker_svc.container_points(db, c.host_id, c.name, "mem_pct", since)
+        evs = await docker_svc.container_events(db, c.host_id, c.name, events)
+        sick = await docker_svc.unhealthy_since(db, [(c.host_id, c.name)])
+    hour_ago = now - timedelta(hours=1)
+    recent = sum(1 for e in failures if e.at >= hour_ago)
+    try:
+        ports = json.loads(c.ports_json or "[]")
+    except ValueError:
+        ports = []
+    problems = [] if gone else container_problems(c, recent, bool(failures), _crash_loop_deaths())
+    began = problem_since(problems, failures, hour_ago, sick.get((c.host_id, c.name)))
+    return {
+        **container_row(c, host_names, problems, now, replaced=gone, since=began),
+        "removed": False,
+        "container_id": c.container_id,
+        "ports": ports,
+        "net_rx_bytes": c.net_rx_bytes, "net_tx_bytes": c.net_tx_bytes,
+        "blk_read_bytes": c.blk_read_bytes, "blk_write_bytes": c.blk_write_bytes,
+        "range": key,
+        "cpu_pct_history": summarize(cpu),
+        "mem_pct_history": summarize(mem),
+        "events": _event_rows(evs, now),
+        "next": f'search_container_logs(container="{c.name}", host="{c.host_id}")',
+    }
+
+
+def _event_rows(evs, now: datetime) -> list[dict]:
+    return [{"event": e.event, "detail": e.detail, "at": iso(e.at), "age_s": age_s(e.at, now)}
+            for e in evs]
+
+
+async def _removed_container(db, c: RemovedContainer, since, key: str, events: int,
+                             now: datetime) -> dict:
+    """get_container for a container Docker has removed: what Steward kept."""
+    host_names = await _host_names(db)
+    cpu = await docker_svc.container_points(db, c.host_id, c.name, "cpu_pct", since)
+    mem = await docker_svc.container_points(db, c.host_id, c.name, "mem_pct", since)
+    evs = await docker_svc.container_events(db, c.host_id, c.name, events)
+    return {
+        "container_name": c.name, "host_id": c.host_id, "host_name": host_names.get(c.host_id),
+        "removed": True, "note": _removed_note(c),
+        "last_seen_at": iso(c.last_seen), "last_seen_age_s": age_s(c.last_seen, now),
+        "range": key,
+        "cpu_pct_history": summarize(cpu),
+        "mem_pct_history": summarize(mem),
+        "events": _event_rows(evs, now),
+        "next": f'search_container_logs(container="{c.name}", host="{c.host_id}", range="24h")',
+    }
+
+
+async def list_swarm_services(limit: int = 100) -> dict:
+    """Docker Swarm services with their replicas per node, and the swarm's nodes.
+
+    `state` is "healthy" (all desired replicas running), "degraded" (some) or
+    "down" (none). `replicas` are the service's current tasks: each names its
+    host and container status, and one marked `ghost` runs on a node with no
+    Steward agent, so Steward knows only how many tasks are placed there.
+    Tasks Swarm replaced (rolling updates, retries) are left out and counted
+    in `previous_tasks`.
+
+    From Swarm's own task records (a manager's agent 1.8.0 or later;
+    `tasks_known: false` and nulls otherwise):
+    - `failures_1h` / `failures_24h`: tasks that failed or were rejected.
+      Swarm retries a failed task as a new one, so this, not any container's
+      restart count, is how a crash loop shows. Swarm keeps about 5 old tasks
+      per replica, which bounds the count.
+    - `crash_looping`: failures_1h reached the crash-loop count set under
+      Settings → Thresholds (default 3).
+    - `last_error`: the newest task that failed, was rejected, or carries an
+      error while Swarm retries it — `error` is Swarm's own text (e.g. "No
+      such image", "task: non-zero exit (1)"), with `exit_code`, `node`, `at`.
+    - `trouble_since` / `trouble_age_s`: when the current trouble began — a
+      crash loop's first failure in the hour, a short service's first failed
+      task in its failing slots, a recovered service's first failure in 24h.
+      Swarm keeps few old tasks, so a long outage reads as a lower bound.
+
+    Services with a problem come first. `nodes` lists every swarm node once,
+    with its role (manager/worker), availability and status.
+    limit: default 100, max 500.
+    """
+    limit = clamp_limit(limit, 100, 500)
+    now = now_utc()
+    async with db_session() as db:
+        services, nodes, host_names = await _swarm(db, now)
+    seen, node_rows = set(), []
+    for n in sorted(nodes, key=lambda n: n.updated_at, reverse=True):
+        if n.node_id in seen:
+            continue
+        seen.add(n.node_id)
+        node_rows.append({"node_id": n.node_id, "hostname": n.hostname, "role": n.role,
+                          "leader": n.leader, "availability": n.availability, "status": n.status,
+                          "reported_by": host_names.get(n.host_id)})
+    node_rows.sort(key=lambda n: n["hostname"].lower())
+    order = {"down": 0, "degraded": 1, "healthy": 2}
+
+    def _rank(s):
+        return (not s["crash_looping"], order.get(s["state"], 3), not s["failures_24h"], s["name"])
+
+    def _error_row(err):
+        if err is None:
+            return None
+        at = task_time(err)
+        return {"error": err["error"], "message": err["message"], "state": err["state"],
+                "exit_code": err["exit_code"], "node": err["node"],
+                "at": iso(at), "age_s": age_s(at, now) if at else None}
+
+    rows = [
+        {
+            "service_name": s["name"], "mode": s["mode"], "state": s["state"],
+            "running": s["running"], "desired": s["desired"],
+            "crash_looping": s["crash_looping"],
+            "failures_1h": s["failures_1h"], "failures_24h": s["failures_24h"],
+            "last_error": _error_row(s["last_error"]),
+            "trouble_since": iso(s["trouble_since"]),
+            "trouble_age_s": age_s(s["trouble_since"], now),
+            "previous_tasks": s["previous_tasks"], "tasks_known": s["tasks_known"],
+            "replicas": [
+                {"ghost": True, "host": r["host"], "count": r["count"]} if r["ghost"] else
+                {"ghost": False, "host": r["host"], "host_id": r["host_id"], "container_name": r["name"],
+                 "status": r["status"], "health": r["health"], "restart_count": r["restart_count"],
+                 "cpu_pct": rnd(r["cpu_pct"]), "mem_pct": rnd(r["mem_pct"])}
+                for r in s["replicas"]
+            ],
+        }
+        for s in sorted(services, key=_rank)
+    ]
+    return {"nodes": node_rows, **bounded(rows, limit, key="services")}
+
+
+async def search_container_logs(container: str = "", host: str = "", text: str = "",
+                                range: str = "1h", stream: str = "", before: str = "",
+                                context: int = 0, limit: int = 50) -> dict:
+    """Search the container log lines Steward has retained, newest first.
+
+    container: one container's name (as list_containers shows); empty searches
+      every container (narrow with `host`). A container Docker has removed
+      still works while its lines are retained: the reply then has
+      `container_removed: true` and a `note` saying when it was last seen.
+    host: a host's name or id; empty for all hosts.
+    text: case-insensitive substring to match; empty matches every line.
+    range: how far back — "1h" (default), "6h", "24h", "7d" or "30d". Logs are
+      kept per container up to a size and age limit, so older lines may be gone.
+    stream: "stdout" or "stderr"; empty for both.
+    before: an ISO time; returns only lines older than it. Pass a response's
+      `next_before` to page further back.
+    context: lines of surrounding log (0-5) to include with each match, from
+      the same container. Only with `container` set.
+    limit: matches to return, default 50, max 200.
+
+    Lines longer than 2000 characters keep both ends, and the middle is
+    replaced by a marker saying how much was cut.
+    """
+    since, key = lookback(range)
+    limit = clamp_limit(limit, 50, 200)
+    context = max(0, min(int(context or 0), 5))
+    if context and not container:
+        raise ValueError("context needs `container`: it shows lines around a match within one container's log.")
+    if stream and stream not in ("stdout", "stderr"):
+        raise ValueError(f"stream {stream!r} is not 'stdout' or 'stderr'.")
+    before_dt = None
+    if before:
+        try:
+            before_dt = datetime.fromisoformat(before.replace("Z", "+00:00"))
+        except ValueError as exc:
+            raise ValueError(f"before {before!r} is not an ISO-8601 time; pass a response's next_before.") from exc
+    async with db_session() as db:
+        host_id = name = removed = None
+        if container:
+            c = await _pick_container(db, container, host, removed=True)
+            host_id, name = c.host_id, c.name
+            removed = c if isinstance(c, RemovedContainer) else None
+        elif host:
+            hosts = list((await db.execute(select(Host))).scalars())
+            host_id = pick(host, hosts, kind="host", list_tool="list_hosts").id
+        rows = await docker_svc.search_logs(db, since=since, host_id=host_id, name=name, text=text,
+                                            stream=stream, before=before_dt, limit=limit + 1)
+        more = len(rows) > limit
+        rows = rows[:limit]
+        host_names = await _host_names(db)
+        matches = []
+        for r in rows:
+            m = {"at": iso(r.ts), "container_name": r.container_name, "host_id": r.host_id,
+                 "host_name": host_names.get(r.host_id), "stream": r.stream, "line": cut_middle(r.line)}
+            if context:
+                pre, post = await docker_svc.log_context(db, r.host_id, r.container_name, r.ts, context)
+                m["before"] = [cut_middle(x.line) for x in pre]
+                m["after"] = [cut_middle(x.line) for x in post]
+            matches.append(m)
+    out = {"range": key, "matches": matches, "returned": len(matches), "truncated": more}
+    if removed is not None:
+        out["container_removed"] = True
+        out["note"] = _removed_note(removed)
+        if removed.last_seen < since:
+            out["note"] += " That is before this range; pass a longer `range`."
+    if more:
+        # Full precision: `at` is cut to the second for reading, and a cursor
+        # cut the same way would skip lines logged earlier in that second.
+        out["next_before"] = rows[-1].ts.isoformat()
+        out["more"] = "More matches are older; pass next_before as `before`, or narrow with `text`."
+    return out
+
+
+async def get_docker_disk_usage(host: str = "") -> dict:
+    """Docker disk usage per host: images, containers, volumes and build cache, in bytes.
+
+    host: a host's name or id; empty for every host. `images_reclaimable_bytes`
+    is what pruning unused images would free. An admin can prune from
+    Steward's Docker → Disk page.
+    """
+    async with db_session() as db:
+        summaries = list((await db.execute(select(DockerDiskUsage))).scalars())
+        host_names = await _host_names(db)
+        if host:
+            hosts = list((await db.execute(select(Host))).scalars())
+            hid = pick(host, hosts, kind="host", list_tool="list_hosts").id
+            summaries = [s for s in summaries if s.host_id == hid]
+    rows = [
+        {
+            "host_id": s.host_id, "host_name": host_names.get(s.host_id),
+            "images_total": s.images_total, "images_active": s.images_active,
+            "images_bytes": s.images_size, "images_reclaimable_bytes": s.images_reclaimable,
+            "containers_count": s.containers_count, "containers_bytes": s.containers_size,
+            "volumes_count": s.volumes_count, "volumes_bytes": s.volumes_size,
+            "build_cache_bytes": s.build_cache_size,
+            "reported_at": iso(s.updated_at), "reported_age_s": age_s(s.updated_at),
+        }
+        for s in summaries
+    ]
+    rows.sort(key=lambda r: -(r["images_reclaimable_bytes"] or 0))
+    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)

plugins/docker/migrations/versions/docker_009_container_logs.py

@@ -0,0 +1,48 @@
+"""Docker container logs table
+
+Adds docker_logs — one row per container log line, pushed by the host agent and
+folded into its metrics push. Time-series, host-scoped (container names are only
+unique within a host). Bounded by a per-container size+age ring in retention, so
+a chatty container keeps a shorter window rather than growing without limit.
+Additive create_table + twin indexes (viewer lookup by (host, container, ts);
+age-cutoff prune by ts).
+
+Revision ID: docker_009_container_logs
+Revises: docker_008_bigint_mem
+Create Date: 2026-07-19
+"""
+from typing import Sequence, Union
+from alembic import op
+import sqlalchemy as sa
+
+revision: str = "docker_009_container_logs"
+down_revision: Union[str, None] = "docker_008_bigint_mem"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.create_table(
+        "docker_logs",
+        sa.Column("id", sa.String(length=36), nullable=False),
+        sa.Column("host_id", sa.String(length=36), nullable=False),
+        sa.Column("container_name", sa.String(length=255), nullable=False),
+        sa.Column("ts", sa.DateTime(timezone=True), nullable=False),
+        sa.Column("stream", sa.String(length=8), nullable=False, server_default="stdout"),
+        sa.Column("line", sa.Text(), nullable=False, server_default=""),
+        sa.ForeignKeyConstraint(["host_id"], ["hosts.id"], ondelete="CASCADE"),
+        sa.PrimaryKeyConstraint("id"),
+    )
+    op.create_index("ix_docker_logs_host_id", "docker_logs", ["host_id"])
+    op.create_index("ix_docker_logs_container_name", "docker_logs", ["container_name"])
+    op.create_index("ix_docker_logs_host_container_time",
+                    "docker_logs", ["host_id", "container_name", "ts"])
+    op.create_index("ix_docker_logs_ts", "docker_logs", ["ts"])
+
+
+def downgrade() -> None:
+    op.drop_index("ix_docker_logs_ts", table_name="docker_logs")
+    op.drop_index("ix_docker_logs_host_container_time", table_name="docker_logs")
+    op.drop_index("ix_docker_logs_container_name", table_name="docker_logs")
+    op.drop_index("ix_docker_logs_host_id", table_name="docker_logs")
+    op.drop_table("docker_logs")

plugins/docker/migrations/versions/docker_010_swarm_tasks.py

@@ -0,0 +1,30 @@
+"""Docker swarm service tasks column
+
+Adds docker_swarm_services.tasks_json — each service's newest tasks as a
+manager's agent (≥ 1.8.0) reports them: slot, node, desired and current state,
+Swarm's error and message, exit code and time. Lets Steward tell a task Swarm
+replaced from one that crashed, count a service's failures across task
+retries, and say why its last task failed. Additive column; no DROP+recreate.
+
+Revision ID: docker_010_swarm_tasks
+Revises: docker_009_container_logs
+Create Date: 2026-10-06
+"""
+from typing import Sequence, Union
+from alembic import op
+import sqlalchemy as sa
+
+revision: str = "docker_010_swarm_tasks"
+down_revision: Union[str, None] = "docker_009_container_logs"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    op.add_column("docker_swarm_services",
+                  sa.Column("tasks_json", sa.Text, nullable=False,
+                            server_default="[]"))
+
+
+def downgrade() -> None:
+    op.drop_column("docker_swarm_services", "tasks_json")

plugins/docker/models.py

@@ -163,6 +163,43 @@ class DockerEvent(Base):
     )
 
 
+class DockerLog(Base):
+    """Container log lines pushed by the host agent — one row per line.
+
+    Time-series, scoped to the reporting host (container names are only unique
+    within a host, same identity as docker_metrics). The agent tails each running
+    container incrementally and folds new lines into its metrics push; `ts` is the
+    line's own Docker timestamp. Bounded by a per-container size+age ring
+    (retention), so a chatty container just keeps a shorter window rather than
+    growing without limit.
+    """
+    __tablename__ = "docker_logs"
+
+    id: Mapped[str] = mapped_column(
+        String(36), primary_key=True, default=lambda: str(uuid.uuid4())
+    )
+    host_id: Mapped[str] = mapped_column(
+        String(36), ForeignKey("hosts.id", ondelete="CASCADE"), nullable=False, index=True
+    )
+    container_name: Mapped[str] = mapped_column(String(255), nullable=False, index=True)
+    ts: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), nullable=False,
+        default=lambda: datetime.now(timezone.utc),
+    )
+    stream: Mapped[str] = mapped_column(String(8), nullable=False, default="stdout")
+    # stdout | stderr
+    line: Mapped[str] = mapped_column(Text, nullable=False, default="")
+
+    # Viewer filters on (host_id, container_name) and sorts by time; the ring
+    # prune walks the same key newest-first. A second index on `ts` alone serves
+    # the age-cutoff delete. Twin-index idiom, mirroring docker_events.
+    __table_args__ = (
+        Index("ix_docker_logs_host_container_time",
+              "host_id", "container_name", "ts"),
+        Index("ix_docker_logs_ts", "ts"),
+    )
+
+
 class DockerSwarmService(Base):
     """A Swarm service as seen by a manager host: desired vs running replicas.
 
@@ -186,6 +223,11 @@ class DockerSwarmService(Base):
     # A manager sees every task, so this captures cross-node placement that the
     # local docker_containers rows (this host only) can't.
     placement_json: Mapped[str] = mapped_column(Text, nullable=False, default="[]")
+    # The service's newest tasks, newest first, as the manager's agent shaped
+    # them: [{"task_id", "slot", "node_id", "desired_state", "state", "message",
+    # "error", "exit_code", "at"}], JSON. Swarm's own record of which tasks it
+    # replaced and why each one stopped; "[]" from agents older than 1.8.0.
+    tasks_json: Mapped[str] = mapped_column(Text, nullable=False, default="[]")
     updated_at: Mapped[datetime] = mapped_column(
         DateTime(timezone=True), nullable=False,
         default=lambda: datetime.now(timezone.utc),

plugins/docker/retention.py

@@ -38,6 +38,8 @@ async def run_docker_retention(
     events_days: int,
     metrics_raw_days: int,
     metrics_rollup_days: int,
+    logs_retention_days: int = 3,
+    logs_max_bytes_per_container: int = 5_000_000,
     now: datetime | None = None,
 ) -> dict:
     """Roll up + prune Docker time-series. Returns a counts dict for logging.
@@ -47,18 +49,22 @@ async def run_docker_retention(
        re-run is idempotent, then delete those raw rows.
     2. Prune rolled-up rows older than the rollup window.
     3. Prune docker_events older than the events window.
+    4. Prune docker_logs with a per-container size+age ring (m79): drop lines
+       older than the age window, then keep only the newest ~cap bytes per
+       (host, container).
     """
     from datetime import timezone
 
     from sqlalchemy import delete, func, select
     from sqlalchemy.dialects.postgresql import insert as pg_insert
 
-    from .models import DockerEvent, DockerMetric, DockerMetricHourly
+    from .models import DockerEvent, DockerLog, DockerMetric, DockerMetricHourly
 
     if now is None:
         now = datetime.now(timezone.utc)
 
     rolled = rolled_rows = events_pruned = rollup_pruned = 0
+    logs_age_pruned = logs_size_pruned = 0
 
     # ── 1. Roll up raw metrics older than the raw window into hourly buckets ──
     raw_cutoff = _rollup_cutoff(now, metrics_raw_days)
@@ -120,9 +126,35 @@ async def run_docker_retention(
     )
     events_pruned = res.rowcount or 0
 
+    # ── 4. Container-log ring: age cutoff, then per-container byte cap (m79) ──
+    logs_cutoff = now - timedelta(days=logs_retention_days)
+    res = await session.execute(
+        delete(DockerLog).where(DockerLog.ts < logs_cutoff)
+    )
+    logs_age_pruned = res.rowcount or 0
+
+    # Size ring: per (host, container), sum line bytes newest-first; delete a row
+    # once its strictly-newer siblings already fill the cap. Using the EXCLUSIVE
+    # prefix (running total minus this row) means the newest row always survives,
+    # so a single line larger than the cap is never wiped out.
+    running = func.sum(func.length(DockerLog.line)).over(
+        partition_by=[DockerLog.host_id, DockerLog.container_name],
+        order_by=[DockerLog.ts.desc(), DockerLog.id.desc()],
+    )
+    prefix_excl = (running - func.length(DockerLog.line)).label("prefix_excl")
+    ranked = select(DockerLog.id, prefix_excl).subquery()
+    over_cap = select(ranked.c.id).where(
+        ranked.c.prefix_excl >= logs_max_bytes_per_container)
+    res = await session.execute(
+        delete(DockerLog).where(DockerLog.id.in_(over_cap))
+    )
+    logs_size_pruned = res.rowcount or 0
+
     return {
         "buckets_rolled": rolled,
         "raw_rows_rolled": rolled_rows,
         "rollup_pruned": rollup_pruned,
         "events_pruned": events_pruned,
+        "logs_age_pruned": logs_age_pruned,
+        "logs_size_pruned": logs_size_pruned,
     }

plugins/docker/routes.py

@@ -3,54 +3,39 @@ from __future__ import annotations
 import json
 from datetime import datetime, timedelta, timezone
 
-from quart import Blueprint, current_app, render_template, request
+from quart import (
+    Blueprint, current_app, jsonify, redirect, render_template, request,
+    session, url_for,
+)
 from sqlalchemy import func, select
 
 from steward.auth.middleware import require_role
 from steward.models.users import UserRole
 from steward.models.hosts import Host
+from steward.core.formatting import human_bytes, human_duration, seconds_since
 from steward.core.time_range import parse_range, DEFAULT_RANGE
+from . import service as docker_svc
 from .dedup import dedup_by_container_id
-from .swarm_view import build_swarm_services
+from .swarm_view import build_swarm_services, parse_tasks, task_summary
 from .models import (
-    DockerContainer, DockerDiskUsage, DockerEvent, DockerImage, DockerMetric,
+    DockerContainer, DockerDiskUsage, DockerEvent, DockerImage,
     DockerSwarmNode, DockerSwarmService,
 )
 
 docker_bp = Blueprint("docker", __name__, template_folder="templates")
 
 
-def _human_bytes(n: int | None) -> str:
-    """Compact binary size string (e.g. '1.4 GiB', '512 MiB', '0 B')."""
-    if n is None:
-        return "—"
-    size = float(n)
-    for unit in ("B", "KiB", "MiB", "GiB", "TiB"):
-        if abs(size) < 1024.0 or unit == "TiB":
-            if unit == "B":
-                return f"{int(size)} {unit}"
-            return f"{size:.1f} {unit}"
-        size /= 1024.0
-    return f"{size:.1f} TiB"
+def _error(status: int, code: str, detail: str | None = None):
+    body: dict = {"ok": False, "error": code}
+    if detail:
+        body["detail"] = detail
+    return jsonify(body), status
 
 
-def _human_uptime(started_at: datetime | None) -> str | None:
-    """Compact 'how long running' string (e.g. '3d 4h', '5h 12m', '8m')."""
-    if started_at is None:
-        return None
-    if started_at.tzinfo is None:
-        started_at = started_at.replace(tzinfo=timezone.utc)
-    secs = int((datetime.now(timezone.utc) - started_at).total_seconds())
-    if secs < 0:
-        return None
-    d, rem = divmod(secs, 86400)
-    h, rem = divmod(rem, 3600)
-    m, _ = divmod(rem, 60)
-    if d:
-        return f"{d}d {h}h"
-    if h:
-        return f"{h}h {m}m"
-    return f"{m}m"
+def _uptime(started_at: datetime | None) -> str | None:
+    """How long a container has run ('3d 4h'), or None if unknown."""
+    secs = seconds_since(started_at)
+    return None if secs is None or secs < 0 else human_duration(secs)
 
 
 def _sparkline(values: list[float], width: int = 80, height: int = 20) -> str:
@@ -74,38 +59,6 @@ def _sparkline(values: list[float], width: int = 80, height: int = 20) -> str:
     )
 
 
-def _bucket(values: list[float], target: int = 40) -> list[float]:
-    """Bucket-average a series down to ~target points (DB-agnostic, in Python).
-
-    Replaces the old SQL strftime() bucketing, which was SQLite-only and broke
-    on Postgres. Agent cadence is dense, so a multi-hour window is hundreds of
-    rows — averaging into a readable point count keeps the sparkline's shape.
-    """
-    n = len(values)
-    if n <= target:
-        return values
-    size = (n + target - 1) // target
-    out: list[float] = []
-    for i in range(0, n, size):
-        chunk = values[i:i + size]
-        out.append(sum(chunk) / len(chunk))
-    return out
-
-
-async def _container_history(db, host_id: str, name: str, since) -> tuple[list, list]:
-    """Return (cpu_series, mem_series) sparkline-ready for one host's container."""
-    rows = (await db.execute(
-        select(DockerMetric.cpu_pct, DockerMetric.mem_pct)
-        .where(DockerMetric.host_id == host_id)
-        .where(DockerMetric.container_name == name)
-        .where(DockerMetric.scraped_at >= since)
-        .order_by(DockerMetric.scraped_at)
-    )).all()
-    cpu = _bucket([r.cpu_pct or 0.0 for r in rows])
-    mem = _bucket([r.mem_pct or 0.0 for r in rows])
-    return cpu, mem
-
-
 @docker_bp.get("/")
 @require_role(UserRole.viewer)
 async def index():
@@ -127,15 +80,6 @@ async def index():
     )
 
 
-async def _host_map(db, host_ids: set[str]) -> dict[str, Host]:
-    if not host_ids:
-        return {}
-    return {
-        h.id: h for h in (await db.execute(
-            select(Host).where(Host.id.in_(host_ids)))).scalars().all()
-    }
-
-
 @docker_bp.get("/rows")
 @require_role(UserRole.viewer)
 async def rows():
@@ -144,15 +88,10 @@ async def rows():
     since, range_key = parse_range(request.args.get("range"))
 
     async with current_app.db_sessionmaker() as db:
-        containers = list((await db.execute(
-            select(DockerContainer).order_by(
-                (DockerContainer.status == "running").desc(),
-                DockerContainer.name,
-            )
-        )).scalars())
+        containers = await docker_svc.list_containers(db)
         services = list((await db.execute(select(DockerSwarmService))).scalars())
         nodes = list((await db.execute(select(DockerSwarmNode))).scalars())
-        hosts = await _host_map(
+        hosts = await docker_svc.host_map(
             db,
             {c.host_id for c in containers}
             | {n.host_id for n in nodes} | {s.host_id for s in services},
@@ -163,7 +102,9 @@ async def rows():
         # from the managers' placement). Non-swarm containers keep the host view.
         node_hostname = {n.node_id: n.hostname for n in nodes if n.hostname}
         host_name = {h.id: h.name for h in hosts.values()}
-        swarm_view = build_swarm_services(containers, services, node_hostname, host_name)
+        swarm_view = build_swarm_services(
+            containers, services, node_hostname, host_name,
+            crash_loop_deaths=docker_svc.crash_loop_deaths(current_app.config))
 
         standalone = [c for c in containers if not c.service_name]
         groups: dict[str, dict] = {}
@@ -177,11 +118,11 @@ async def rows():
                     "host_name": host.name if host else c.host_id,
                     "containers": [], "running": 0, "stopped": 0,
                 }
-            cpu_hist, mem_hist = await _container_history(db, c.host_id, c.name, since)
+            cpu_hist, mem_hist = await docker_svc.container_history(db, c.host_id, c.name, since)
             g["containers"].append({
                 "container": c,
                 "ports": json.loads(c.ports_json) if c.ports_json else [],
-                "uptime": _human_uptime(c.started_at) if c.status == "running" else None,
+                "uptime": _uptime(c.started_at) if c.status == "running" else None,
                 "sparkline_cpu": _sparkline(cpu_hist),
                 "sparkline_mem": _sparkline(mem_hist),
             })
@@ -239,14 +180,14 @@ async def widget():
         )).scalars()))
         services = list((await db.execute(select(DockerSwarmService))).scalars())
         nodes = list((await db.execute(select(DockerSwarmNode))).scalars())
-        # Recent failures are more actionable than a static "stopped" tally. Count
+        # Recent failures are more actionable than a static "stopped" tally. Read
         # DISTINCT container names so the two managers' duplicate die/oom events
-        # don't double it.
-        failed_24h = (await db.execute(
-            select(func.count(func.distinct(DockerEvent.container_name)))
+        # don't double it; swarm tasks are counted on their service below.
+        dead_names = list((await db.execute(
+            select(func.distinct(DockerEvent.container_name))
             .where(DockerEvent.event.in_(("die", "oom")), DockerEvent.at >= since_24h)
-        )).scalar() or 0
-        hosts = await _host_map(
+        )).scalars())
+        hosts = await docker_svc.host_map(
             db,
             {c.host_id for c in all_containers}
             | {n.host_id for n in nodes} | {s.host_id for s in services},
@@ -256,7 +197,10 @@ async def widget():
     # host); non-swarm containers stay grouped by host.
     node_hostname = {n.node_id: n.hostname for n in nodes if n.hostname}
     host_name = {h.id: h.name for h in hosts.values()}
-    swarm_services = build_swarm_services(all_containers, services, node_hostname, host_name)["services"]
+    swarm_services = build_swarm_services(
+        all_containers, services, node_hostname, host_name,
+        crash_loop_deaths=docker_svc.crash_loop_deaths(current_app.config))["services"]
+    failed_24h = docker_svc.failed_24h(dead_names, swarm_services)
 
     standalone = [c for c in all_containers if not c.service_name]
     running = [c for c in standalone if c.status == "running"]
@@ -301,7 +245,7 @@ async def widget_resources():
             .where(DockerContainer.status == "running")
             .order_by(DockerContainer.cpu_pct.desc().nullslast())
         )).scalars()))[:limit]
-        hosts = await _host_map(db, {c.host_id for c in containers})
+        hosts = await docker_svc.host_map(db, {c.host_id for c in containers})
 
     rows_data = [
         {"c": c, "host_name": hosts[c.host_id].name if c.host_id in hosts else c.host_id}
@@ -324,14 +268,7 @@ async def host_panel(host_id: str):
     don't carry an empty card.
     """
     async with current_app.db_sessionmaker() as db:
-        containers = list((await db.execute(
-            select(DockerContainer)
-            .where(DockerContainer.host_id == host_id)
-            .order_by(
-                (DockerContainer.status == "running").desc(),
-                DockerContainer.name,
-            )
-        )).scalars())
+        containers = await docker_svc.list_containers(db, host_id)
 
     if not containers:
         return ""
@@ -361,15 +298,7 @@ async def container_detail(host_id: str, name: str):
     async with current_app.db_sessionmaker() as db:
         c = await db.get(DockerContainer, (host_id, name))
         host = await db.get(Host, host_id)
-        events = []
-        if c is not None:
-            events = list((await db.execute(
-                select(DockerEvent)
-                .where(DockerEvent.host_id == host_id)
-                .where(DockerEvent.container_name == name)
-                .order_by(DockerEvent.at.desc())
-                .limit(50)
-            )).scalars())
+        events = await docker_svc.container_events(db, host_id, name) if c is not None else []
 
     if c is None:
         return await render_template(
@@ -384,9 +313,9 @@ async def container_detail(host_id: str, name: str):
         host_id=host_id,
         name=name,
         ports=json.loads(c.ports_json) if c.ports_json else [],
-        uptime=_human_uptime(c.started_at) if c.status == "running" else None,
-        net_rx=_human_bytes(c.net_rx_bytes), net_tx=_human_bytes(c.net_tx_bytes),
-        blk_read=_human_bytes(c.blk_read_bytes), blk_write=_human_bytes(c.blk_write_bytes),
+        uptime=_uptime(c.started_at) if c.status == "running" else None,
+        net_rx=human_bytes(c.net_rx_bytes), net_tx=human_bytes(c.net_tx_bytes),
+        blk_read=human_bytes(c.blk_read_bytes), blk_write=human_bytes(c.blk_write_bytes),
         events=[
             {"event": e.event, "detail": e.detail, "at": e.at,
              "glyph": _EVENT_STYLE.get(e.event, ("•", "var(--text-muted)"))[0],
@@ -417,7 +346,7 @@ async def swarm():
             select(DockerSwarmNode).order_by(
                 DockerSwarmNode.role, DockerSwarmNode.hostname)
         )).scalars())
-        hosts = await _host_map(db, {s.host_id for s in services} | {n.host_id for n in nodes})
+        hosts = await docker_svc.host_map(db, {s.host_id for s in services} | {n.host_id for n in nodes})
 
     # ── Group reporting managers into swarms by shared node membership ──────────
     manager_ids = {s.host_id for s in services} | {n.host_id for n in nodes}
@@ -463,6 +392,8 @@ async def swarm():
                 node_by_id[n.node_id] = n
 
         node_names = {nid: (nrow.hostname or nid) for nid, nrow in node_by_id.items()}
+        now = datetime.now(timezone.utc)
+        deaths = docker_svc.crash_loop_deaths(current_app.config)
         svc_dicts = []
         for s in sorted(svc_by_name.values(), key=lambda s: s.service_name):
             placement = []
@@ -478,7 +409,10 @@ async def swarm():
                 "healthy": s.running >= s.desired and s.desired > 0,
                 "degraded": 0 < s.running < s.desired,
                 "down": s.running == 0 and s.desired > 0,
+                "state": ("healthy" if s.running >= s.desired and s.desired > 0
+                          else "degraded" if s.running > 0 else "down"),
                 "placement": placement,
+                **task_summary(parse_tasks(s), now, deaths, node_names),
             })
         node_rows = sorted(
             node_by_id.values(), key=lambda n: (n.role, (n.hostname or n.node_id).lower())
@@ -499,9 +433,13 @@ async def swarm():
 async def disk():
     """Image/disk usage page: reclaimable space, per-image sizes, stopped count.
 
-    Read-only — prune actions are deferred to the cleanup-actions milestone, so
-    this surfaces the numbers and notes where reclaim lives.
+    Admins can reclaim space per host via the prune buttons, which fire the
+    audited bundled prune playbook through Ansible (m78) — the collection agent
+    itself stays read-only.
     """
+    from steward.core.capabilities import has_capability
+    from steward.models.ansible_inventory import AnsibleTarget
+
     async with current_app.db_sessionmaker() as db:
         summaries = list((await db.execute(select(DockerDiskUsage))).scalars())
         images = list((await db.execute(
@@ -515,13 +453,23 @@ async def disk():
         stopped_by_host: dict[str, int] = {}
         for hid in stopped_rows:
             stopped_by_host[hid] = stopped_by_host.get(hid, 0) + 1
-        hosts = await _host_map(db, {s.host_id for s in summaries})
+        hosts = await docker_svc.host_map(db, {s.host_id for s in summaries})
+        # Which hosts have a linked Ansible target — gates the prune buttons
+        # (a target is required to route the playbook run to that host).
+        host_ids = {s.host_id for s in summaries}
+        target_by_host: dict[str, str] = {}
+        if host_ids:
+            for hid, tid in (await db.execute(
+                select(AnsibleTarget.host_id, AnsibleTarget.id)
+                .where(AnsibleTarget.host_id.in_(host_ids))
+            )).all():
+                target_by_host[hid] = tid
 
     images_by_host: dict[str, list] = {}
     for im in images:
         images_by_host.setdefault(im.host_id, []).append({
-            "repo_tag": im.repo_tag, "size": _human_bytes(im.size),
-            "shared": _human_bytes(im.shared_size), "containers": im.containers,
+            "repo_tag": im.repo_tag, "size": human_bytes(im.size),
+            "shared": human_bytes(im.shared_size), "containers": im.containers,
             "reclaimable": im.containers == 0,
         })
 
@@ -531,22 +479,71 @@ async def disk():
             "host_name": hosts[s.host_id].name if s.host_id in hosts else s.host_id,
             "summary": {
                 "images_total": s.images_total, "images_active": s.images_active,
-                "images_size": _human_bytes(s.images_size),
-                "images_reclaimable": _human_bytes(s.images_reclaimable),
-                "layers_size": _human_bytes(s.layers_size),
+                "images_size": human_bytes(s.images_size),
+                "images_reclaimable": human_bytes(s.images_reclaimable),
+                "layers_size": human_bytes(s.layers_size),
                 "containers_count": s.containers_count,
-                "containers_size": _human_bytes(s.containers_size),
+                "containers_size": human_bytes(s.containers_size),
                 "volumes_count": s.volumes_count,
-                "volumes_size": _human_bytes(s.volumes_size),
-                "build_cache_size": _human_bytes(s.build_cache_size),
+                "volumes_size": human_bytes(s.volumes_size),
+                "build_cache_size": human_bytes(s.build_cache_size),
             },
             "stopped": stopped_by_host.get(s.host_id, 0),
             "images": images_by_host.get(s.host_id, []),
+            "has_target": s.host_id in target_by_host,
         }
         for s in summaries
     ]
     host_groups.sort(key=lambda g: g["host_name"].lower())
-    return await render_template("docker/disk.html", host_groups=host_groups)
+    return await render_template(
+        "docker/disk.html", host_groups=host_groups,
+        ansible_available=has_capability("ansible.run_playbook"),
+    )
+
+
+@docker_bp.post("/disk/<host_id>/prune")
+@require_role(UserRole.admin)
+async def disk_prune(host_id: str):
+    """Reclaim Docker disk on a host by firing the bundled prune playbook via
+    Ansible (audited, admin-gated) — the collection agent stays read-only (m78).
+    `target` selects the scope: containers | images | system.
+    """
+    from steward.core.capabilities import has_capability, invoke_capability
+    from steward.ansible.sources import BUILTIN_SOURCE_NAME
+    from steward.models.ansible_inventory import AnsibleTarget
+
+    if not has_capability("ansible.run_playbook"):
+        return _error(400, "ansible_unavailable", "Ansible is not available")
+
+    form = await request.form
+    prune_target = (form.get("target", "") or "").strip()
+    if prune_target not in docker_svc.PRUNE_TARGETS:
+        return _error(400, "bad_target", "Unknown prune target")
+
+    async with current_app.db_sessionmaker() as db:
+        target = (await db.execute(
+            select(AnsibleTarget).where(AnsibleTarget.host_id == host_id)
+        )).scalar_one_or_none()
+    if target is None:
+        return _error(400, "no_target",
+                      "Link an Ansible target to this host before pruning")
+
+    # extra_vars_map outranks the playbook's own `vars:` defaults.
+    extra_vars = docker_svc.prune_extra_vars(prune_target)
+
+    actor_role = UserRole(session.get("user_role", "viewer"))
+    run, _source, err = await invoke_capability(
+        "ansible.run_playbook", actor_role,
+        current_app._get_current_object(),  # type: ignore[attr-defined]
+        source_name=BUILTIN_SOURCE_NAME,
+        playbook_path="maintenance/docker_prune.yml",
+        inventory_scope=f"steward:target:{target.id}",
+        params={"extra_vars_map": extra_vars},
+        triggered_by=session.get("user_id"),
+    )
+    if err:
+        return _error(400, "prune_failed", err)
+    return redirect(url_for("ansible.run_detail", run_id=run.id))
 
 
 @docker_bp.get("/container/<host_id>/<name>/history")
@@ -555,7 +552,7 @@ async def container_history(host_id: str, name: str):
     """HTMX fragment: CPU + memory sparklines for the selected time range."""
     since, range_key = parse_range(request.args.get("range"))
     async with current_app.db_sessionmaker() as db:
-        cpu_hist, mem_hist = await _container_history(db, host_id, name, since)
+        cpu_hist, mem_hist = await docker_svc.container_history(db, host_id, name, since)
     return await render_template(
         "docker/_container_history.html",
         sparkline_cpu=_sparkline(cpu_hist, width=320, height=48),
@@ -563,3 +560,36 @@ async def container_history(host_id: str, name: str):
         have_data=len(cpu_hist) >= 2,
         range_key=range_key,
     )
+
+
+# Newest lines returned per fetch — the retained window is bounded by the ring,
+# but a container can still hold thousands of lines; cap what one fetch renders.
+_LOG_TAIL_DEFAULT = 500
+
+
+@docker_bp.get("/container/<host_id>/<name>/logs")
+@require_role(UserRole.viewer)
+async def container_logs(host_id: str, name: str):
+    """Full log-viewer page for one container (lines load via an HTMX fragment)."""
+    async with current_app.db_sessionmaker() as db:
+        host = await db.get(Host, host_id)
+    return await render_template(
+        "docker/container_logs.html", host=host, host_id=host_id, name=name,
+    )
+
+
+@docker_bp.get("/container/<host_id>/<name>/logs/lines")
+@require_role(UserRole.viewer)
+async def container_logs_lines(host_id: str, name: str):
+    """HTMX fragment: the recent retained log lines, stream + text filtered.
+    Polled every few seconds by the viewer for near-live follow."""
+    stream = request.args.get("stream", "all")
+    query = (request.args.get("q") or "").strip()
+    async with current_app.db_sessionmaker() as db:
+        rows = await docker_svc.query_logs(db, host_id, name, stream, query, _LOG_TAIL_DEFAULT)
+    return await render_template(
+        "docker/_container_logs_lines.html",
+        lines=[{"ts": r.ts, "stream": r.stream, "line": r.line} for r in rows],
+        name=name, tail=_LOG_TAIL_DEFAULT,
+        filtered=bool(query) or stream in ("stdout", "stderr"),
+    )

plugins/docker/service.py

@@ -0,0 +1,280 @@
+"""Docker queries shared by the plugin's pages and its MCP tools.
+
+Each function takes an open session and returns rows or plain data, with no
+Quart request context, so the routes and the /mcp tools (which run outside
+Quart's pipeline) call the same code.
+"""
+from __future__ import annotations
+
+from datetime import datetime
+
+from sqlalchemy import func, select
+
+from steward.core.time_range import bucket_seconds
+from steward.models.hosts import Host
+
+from .models import DockerContainer, DockerEvent, DockerLog, DockerMetric, DockerMetricHourly
+
+
+CRASH_LOOP_DEATHS = 3  # default; Settings → Thresholds sets it
+
+
+def crash_loop_deaths(config) -> int:
+    """Deaths within an hour that make a container or a swarm service a crash
+    loop, from Settings → Thresholds (app.config["THRESHOLDS"])."""
+    th = (config.get("THRESHOLDS") or {}).get("crash_loop") or {}
+    return int(th.get("warn") or CRASH_LOOP_DEATHS)
+
+
+def failed_24h(dead_names, swarm_services) -> int:
+    """Failures in the last 24h for the dashboard: distinct plain containers
+    that died or were OOM-killed, plus each swarm service's failed tasks.
+
+    A swarm task's container dies whenever Swarm replaces it (a rolling update
+    kills it with 137), so its die event is not a failure. Services with
+    Swarm's task records count their failed tasks instead; a service without
+    them (an agent older than 1.8.0) falls back to its tasks' die events.
+    """
+    by_prefix = {s["name"] + ".": s for s in swarm_services}
+    plain, fallback = 0, set()
+    for name in dead_names:
+        svc = next((s for p, s in by_prefix.items() if name.startswith(p)), None)
+        if svc is None:
+            plain += 1
+        elif not svc["tasks_known"]:
+            fallback.add(name)
+    tasks = sum(s["failures_24h"] or 0 for s in swarm_services if s["tasks_known"])
+    return plain + len(fallback) + tasks
+
+
+def bucket(values: list[float], target: int = 40) -> list[float]:
+    """Bucket-average a series down to ~target points (DB-agnostic, in Python).
+
+    Replaces the old SQL strftime() bucketing, which was SQLite-only and broke
+    on Postgres. Agent cadence is dense, so a multi-hour window is hundreds of
+    rows — averaging into a readable point count keeps the sparkline's shape.
+    """
+    n = len(values)
+    if n <= target:
+        return values
+    size = (n + target - 1) // target
+    out: list[float] = []
+    for i in range(0, n, size):
+        chunk = values[i:i + size]
+        out.append(sum(chunk) / len(chunk))
+    return out
+
+
+async def container_history(db, host_id: str, name: str, since) -> tuple[list, list]:
+    """Return (cpu_series, mem_series) sparkline-ready for one host's container."""
+    rows = (await db.execute(
+        select(DockerMetric.cpu_pct, DockerMetric.mem_pct)
+        .where(DockerMetric.host_id == host_id)
+        .where(DockerMetric.container_name == name)
+        .where(DockerMetric.scraped_at >= since)
+        .order_by(DockerMetric.scraped_at)
+    )).all()
+    cpu = bucket([r.cpu_pct or 0.0 for r in rows])
+    mem = bucket([r.mem_pct or 0.0 for r in rows])
+    return cpu, mem
+
+
+async def host_map(db, host_ids: set[str]) -> dict[str, Host]:
+    if not host_ids:
+        return {}
+    return {
+        h.id: h for h in (await db.execute(
+            select(Host).where(Host.id.in_(host_ids)))).scalars().all()
+    }
+
+
+def escape_like(text: str) -> str:
+    """Make `text` match literally inside a LIKE/ILIKE pattern (escape char \\)."""
+    return text.replace("\\", "\\\\").replace("%", "\\%").replace("_", "\\_")
+
+
+async def list_containers(db, host_id: str | None = None) -> list[DockerContainer]:
+    """Containers, running first then by name; one host's when host_id is given."""
+    stmt = select(DockerContainer)
+    if host_id is not None:
+        stmt = stmt.where(DockerContainer.host_id == host_id)
+    stmt = stmt.order_by((DockerContainer.status == "running").desc(), DockerContainer.name)
+    return list((await db.execute(stmt)).scalars())
+
+
+async def container_events(db, host_id: str, name: str, limit: int = 50) -> list[DockerEvent]:
+    """A container's lifecycle events (start/stop/die/oom/health), newest first."""
+    return list((await db.execute(
+        select(DockerEvent)
+        .where(DockerEvent.host_id == host_id)
+        .where(DockerEvent.container_name == name)
+        .order_by(DockerEvent.at.desc())
+        .limit(limit)
+    )).scalars())
+
+
+async def query_logs(db, host_id: str, name: str, stream: str, query: str,
+                     limit: int) -> list:
+    """The recent retained lines for one container, newest-first, optionally
+    filtered by stream and a case-insensitive substring.
+
+    Newest-first is deliberate: the viewer replaces the list on each poll, which
+    resets scroll to the top — so the latest lines stay visible without any
+    scroll handling, and older lines are a scroll away.
+    """
+    stmt = (select(DockerLog.ts, DockerLog.stream, DockerLog.line)
+            .where(DockerLog.host_id == host_id)
+            .where(DockerLog.container_name == name))
+    if stream in ("stdout", "stderr"):
+        stmt = stmt.where(DockerLog.stream == stream)
+    if query:
+        stmt = stmt.where(DockerLog.line.ilike(f"%{escape_like(query)}%", escape="\\"))
+    stmt = stmt.order_by(DockerLog.ts.desc(), DockerLog.id.desc()).limit(limit)
+    return (await db.execute(stmt)).all()
+
+
+CONTAINER_SERIES = ("cpu_pct", "mem_pct", "mem_usage_bytes")
+
+
+async def container_points(db, host_id: str, name: str, metric: str, since,
+                           target: int = 120) -> list[tuple]:
+    """(time, average) points of one container metric since `since`, oldest first.
+
+    Raw samples are bucket-averaged in SQL; the part of the range older than
+    the oldest raw sample (already rolled up and pruned by retention) comes
+    from the hourly table.
+    """
+    if metric not in CONTAINER_SERIES:
+        raise ValueError(f"metric must be one of {', '.join(CONTAINER_SERIES)}")
+    raw_col = getattr(DockerMetric, metric)
+    width_s = bucket_seconds(since, target)
+    rbucket = func.date_bin(
+        func.make_interval(0, 0, 0, 0, 0, 0, width_s), DockerMetric.scraped_at, func.to_timestamp(0),
+    ).label("bucket")
+    raw = (await db.execute(
+        select(rbucket, func.avg(raw_col))
+        .where(DockerMetric.host_id == host_id, DockerMetric.container_name == name,
+               DockerMetric.scraped_at >= since)
+        .group_by(rbucket).order_by(rbucket)
+    )).all()
+    oldest_raw = raw[0][0] if raw else None
+    hourly_stmt = (
+        select(DockerMetricHourly.bucket, getattr(DockerMetricHourly, metric))
+        .where(DockerMetricHourly.host_id == host_id,
+               DockerMetricHourly.container_name == name,
+               DockerMetricHourly.bucket >= since)
+        .order_by(DockerMetricHourly.bucket)
+    )
+    if oldest_raw is not None:
+        hourly_stmt = hourly_stmt.where(DockerMetricHourly.bucket < oldest_raw)
+    hourly = (await db.execute(hourly_stmt)).all()
+    return [(t, float(v)) for t, v in hourly] + [(t, float(v)) for t, v in raw]
+
+
+async def search_logs(db, *, since, host_id: str | None = None, name: str | None = None,
+                      text: str = "", stream: str = "", before=None, limit: int = 50) -> list:
+    """Retained log lines matching a filter, newest first (limit + 1 fetched by callers
+    that need to know whether more exist)."""
+    stmt = (select(DockerLog.id, DockerLog.host_id, DockerLog.container_name,
+                   DockerLog.ts, DockerLog.stream, DockerLog.line)
+            .where(DockerLog.ts >= since))
+    if host_id:
+        stmt = stmt.where(DockerLog.host_id == host_id)
+    if name:
+        stmt = stmt.where(DockerLog.container_name == name)
+    if stream in ("stdout", "stderr"):
+        stmt = stmt.where(DockerLog.stream == stream)
+    if text:
+        stmt = stmt.where(DockerLog.line.ilike(f"%{escape_like(text)}%", escape="\\"))
+    if before is not None:
+        stmt = stmt.where(DockerLog.ts < before)
+    stmt = stmt.order_by(DockerLog.ts.desc(), DockerLog.id.desc()).limit(limit)
+    return list((await db.execute(stmt)).all())
+
+
+async def log_context(db, host_id: str, name: str, ts, n: int) -> tuple[list, list]:
+    """Up to n lines either side of `ts` in one container's log, each oldest first."""
+    cols = (DockerLog.id, DockerLog.ts, DockerLog.stream, DockerLog.line)
+    base = select(*cols).where(DockerLog.host_id == host_id, DockerLog.container_name == name)
+    before = (await db.execute(
+        base.where(DockerLog.ts < ts).order_by(DockerLog.ts.desc(), DockerLog.id.desc()).limit(n)
+    )).all()
+    after = (await db.execute(
+        base.where(DockerLog.ts > ts).order_by(DockerLog.ts, DockerLog.id).limit(n)
+    )).all()
+    return list(reversed(before)), list(after)
+
+
+async def recent_failures_by_container(db, since) -> dict[tuple[str, str], list]:
+    """{(host_id, container_name): [die/oom events since `since`, newest first]}."""
+    rows = (await db.execute(
+        select(DockerEvent)
+        .where(DockerEvent.event.in_(("die", "oom")), DockerEvent.at >= since)
+        .order_by(DockerEvent.at.desc())
+    )).scalars()
+    out: dict[tuple[str, str], list] = {}
+    for e in rows:
+        out.setdefault((e.host_id, e.container_name), []).append(e)
+    return out
+
+
+async def retained_names(db, want: str, *, exact: bool, host_id: str | None = None,
+                         limit: int = 20) -> list[tuple[str, str, datetime]]:
+    """(host_id, container_name, last seen) of containers Steward still holds
+    logs or events for, newest first — including ones Docker has removed.
+
+    exact: the name itself, from both logs and events. Otherwise names that
+    contain `want` (case-insensitive), from events only: a substring match
+    over every retained log line's name would scan the log table, and a
+    container Steward watched die has a die or stop event.
+    """
+    seen: dict[tuple[str, str], datetime] = {}
+    sources = ((DockerLog, DockerLog.ts), (DockerEvent, DockerEvent.at)) if exact \
+        else ((DockerEvent, DockerEvent.at),)
+    for model, at in sources:
+        match = (model.container_name == want if exact
+                 else model.container_name.ilike(f"%{escape_like(want)}%", escape="\\"))
+        stmt = (select(model.host_id, model.container_name, func.max(at))
+                .where(match).group_by(model.host_id, model.container_name))
+        if host_id:
+            stmt = stmt.where(model.host_id == host_id)
+        for hid, name, last in (await db.execute(stmt)).all():
+            key = (hid, name)
+            if key not in seen or last > seen[key]:
+                seen[key] = last
+    rows = sorted(((h, n, t) for (h, n), t in seen.items()), key=lambda r: r[2], reverse=True)
+    return rows[:limit]
+
+
+async def unhealthy_since(db, keys) -> dict[tuple[str, str], datetime]:
+    """{(host_id, container_name): when it last turned unhealthy} for the given
+    containers, from their health_change events; absent when none is retained."""
+    keys = set(keys)
+    if not keys:
+        return {}
+    rows = (await db.execute(
+        select(DockerEvent)
+        .where(DockerEvent.event == "health_change",
+               DockerEvent.detail.like("%→unhealthy"),
+               DockerEvent.container_name.in_({name for _, name in keys}))
+        .order_by(DockerEvent.at.desc())
+    )).scalars()
+    out: dict[tuple[str, str], datetime] = {}
+    for e in rows:
+        key = (e.host_id, e.container_name)
+        if key in keys and key not in out:
+            out[key] = e.at
+    return out
+
+
+PRUNE_TARGETS = ("containers", "images", "system")
+
+
+def prune_extra_vars(prune_target: str) -> dict:
+    """Extra-vars for the bundled docker_prune playbook. "Prune unused images"
+    means ALL unused (docker image prune -a), not just dangling; the full system
+    prune stays conservative (-f, no -a) per the operator's choice (m78)."""
+    extra_vars: dict = {"prune_target": prune_target}
+    if prune_target == "images":
+        extra_vars["prune_all_images"] = True
+    return extra_vars

plugins/docker/swarm_view.py

@@ -11,12 +11,28 @@ For every swarm service we list the real replicas we have detail for, then add
 "ghost" replicas for the remaining placement count on each node (agent-less
 nodes). Non-swarm containers pass through grouped by host, unchanged.
 
+A third source, DockerSwarmService.tasks_json (agent ≥ 1.8.0), is Swarm's own
+record of each service's newest tasks. It decides which task containers are
+*superseded* — replaced by Swarm, so neither a replica nor a crash — and gives
+each service its failures across task retries and the error of its last
+failed task. Swarm restarts a task by creating a new one (a new container), so
+failures can only be counted per service, never per container.
+
 Kept model-free (no ORM imports) so it's unit-testable and safe to import in
 tests without the plugin-loader "table already defined" gotcha.
 """
 from __future__ import annotations
 
 import json
+from datetime import datetime, timedelta, timezone
+
+# Task states that mean the task ended in error: `failed` (its container exited
+# non-zero or never started) and `rejected` (Swarm could not start it at all,
+# e.g. no such image, a bad mount).
+FAILED_TASK_STATES = ("failed", "rejected")
+# Desired states of a task Swarm still means to run. Anything else (shutdown,
+# remove, complete, orphaned) is a task Swarm has finished with.
+_CURRENT_DESIRED = ("running", "ready", "")
 
 
 def _service_state(running: int, desired: int) -> str:
@@ -36,30 +52,220 @@ def _placement(service) -> list[dict]:
     return [p for p in data if isinstance(p, dict)]
 
 
-def build_swarm_services(containers, services, node_hostname: dict, host_name: dict) -> dict:
-    """Return {"services": [...], "standalone": [...]}.
+def parse_tasks(service) -> list[dict]:
+    """A service row's task records, newest first; [] when its agent sent none."""
+    raw = getattr(service, "tasks_json", None) or "[]"
+    try:
+        data = json.loads(raw)
+    except (ValueError, TypeError):
+        return []
+    return [t for t in data if isinstance(t, dict)]
 
-    services[i] = {name, mode, desired, running, state, replicas:[...]}
-      real replica  = {ghost:False, host, host_id, name, status, cpu_pct, mem_pct,
-                       health, restart_count}
-      ghost replica = {ghost:True, host, count}   # placement with no local row
-    standalone[i] = {host_id, host, containers:[...]}  # non-swarm, by host
+
+def task_time(task: dict) -> datetime | None:
+    """A task's status timestamp. Docker writes nanoseconds; Python ≥ 3.11 keeps
+    the first six digits."""
+    raw = task.get("at") or ""
+    try:
+        at = datetime.fromisoformat(raw.replace("Z", "+00:00"))
+    except ValueError:
+        return None
+    return at if at.tzinfo else at.replace(tzinfo=timezone.utc)
+
+
+def task_failures(tasks: list[dict], since: datetime) -> int:
+    """How many tasks ended in error at or after `since`."""
+    n = 0
+    for t in tasks:
+        at = task_time(t)
+        if t.get("state") in FAILED_TASK_STATES and at is not None and at >= since:
+            n += 1
+    return n
+
+
+def last_task_error(tasks: list[dict]) -> dict | None:
+    """Why the service's newest troubled task is in trouble, from Swarm itself.
+
+    The newest task that failed or was rejected, or that Swarm attached an error
+    to while still trying (a pending task with "no suitable node", say). None
+    when no retained task has a problem.
     """
+    for t in tasks:  # newest first
+        if t.get("state") in FAILED_TASK_STATES or t.get("error"):
+            return {"state": t.get("state"), "error": t.get("error") or None,
+                    "message": t.get("message") or None, "exit_code": t.get("exit_code"),
+                    "node_id": t.get("node_id") or None, "at": t.get("at") or None}
+    return None
+
+
+def task_summary(tasks: list[dict], now: datetime, crash_loop_deaths: int,
+                 node_hostname: dict) -> dict:
+    """What a service's task records say: tasks_known, failures_1h,
+    failures_24h (None without records), crash_looping, and last_error with
+    the node's hostname as `node`."""
+    known = bool(tasks)
+    failures_1h = task_failures(tasks, now - timedelta(hours=1)) if known else None
+    last_error = last_task_error(tasks)
+    if last_error is not None:
+        nid = last_error["node_id"]
+        last_error["node"] = node_hostname.get(nid) or (nid[:12] if nid else None)
+        at = task_time(last_error)
+        last_error["age_s"] = max(0, int((now - at).total_seconds())) if at else None
+    return {
+        "tasks_known": known,
+        "failures_1h": failures_1h,
+        "failures_24h": task_failures(tasks, now - timedelta(hours=24)) if known else None,
+        "crash_looping": bool(known and failures_1h >= crash_loop_deaths),
+        "last_error": last_error,
+    }
+
+
+def _oldest_failure(tasks: list[dict], since: datetime) -> datetime | None:
+    times = [at for t in tasks if t.get("state") in FAILED_TASK_STATES
+             and (at := task_time(t)) is not None and at >= since]
+    return min(times, default=None)
+
+
+def trouble_since(tasks: list[dict], state: str, crash_looping: bool,
+                  now: datetime) -> datetime | None:
+    """When a service's current trouble began, as far as its retained tasks
+    tell; None when it has none, or the tasks cannot say.
+
+    A crash loop dates from its first failure in the last hour, and a healthy
+    service that lost tasks from its first failure in the last 24h. A service
+    short of replicas dates from its troubled slots (replicated: the slot;
+    global: the node): in each slot whose newest task is not running, the
+    oldest of its newest troubled tasks (failed, rejected, or carrying an
+    error), walking back until a running task interrupts them. Swarm keeps few
+    old tasks, so a long outage reads as the oldest one retained: a lower
+    bound.
+    """
+    if crash_looping:
+        return _oldest_failure(tasks, now - timedelta(hours=1))
+    if state == "healthy":
+        return _oldest_failure(tasks, now - timedelta(hours=24))
+    by_slot: dict = {}
+    for t in tasks:  # newest first, so each slot's list is too
+        by_slot.setdefault(t.get("slot") or t.get("node_id"), []).append(t)
+    began = []
+    for slot_tasks in by_slot.values():
+        oldest = None
+        for t in slot_tasks:
+            if t.get("state") == "running":
+                break
+            if t.get("state") in FAILED_TASK_STATES or t.get("error"):
+                oldest = task_time(t) or oldest
+        if oldest is not None:
+            began.append(oldest)
+    return min(began, default=None)
+
+
+def _slot_key(c) -> str:
+    """A task container's slot within its service: "<service>.<slot>.<task>" for
+    replicated services, "<service>.<node id>.<task>" for global ones."""
+    svc, name = c.service_name, c.name or ""
+    rest = name[len(svc) + 1:] if name.startswith(svc + ".") else name
+    return rest.split(".", 1)[0]
+
+
+def superseded_containers(swarm_cs, tasks_by_id: dict[str, dict]) -> set[tuple]:
+    """(host_id, name) of task containers Swarm has replaced.
+
+    With the task on record, its desired state decides: Swarm sets a replaced
+    or failed task's desired state to shutdown. Without it (an older agent, or a
+    task older than the retained history), a container that is not running is
+    superseded when another task in the same slot is running or started later.
+    """
+    out: set[tuple] = set()
+    by_slot: dict[tuple, list] = {}
+    for c in swarm_cs:
+        by_slot.setdefault((c.service_name, _slot_key(c)), []).append(c)
+    for c in swarm_cs:
+        task = tasks_by_id.get(getattr(c, "task_id", None) or "")
+        if task is not None:
+            if task.get("desired_state") not in _CURRENT_DESIRED:
+                out.add((c.host_id, c.name))
+            continue
+        if (getattr(c, "status", "") or "").lower() == "running":
+            continue
+        mine = getattr(c, "started_at", None)
+        for other in by_slot[(c.service_name, _slot_key(c))]:
+            if other is c:
+                continue
+            theirs = getattr(other, "started_at", None)
+            if ((getattr(other, "status", "") or "").lower() == "running"
+                    or (theirs is not None and (mine is None or theirs > mine))):
+                out.add((c.host_id, c.name))
+                break
+    return out
+
+
+def _newest_per_name(services) -> dict[str, object]:
+    """Every manager reports the same cluster-global service set; keep the most
+    recently updated row per name, so a manager on an older agent (no tasks)
+    doesn't shadow one that reports them."""
+    by_name: dict[str, object] = {}
+    for s in services:
+        name = getattr(s, "service_name", None)
+        if not name:
+            continue
+        kept = by_name.get(name)
+        if kept is None:
+            by_name[name] = s
+            continue
+        a, b = getattr(s, "updated_at", None), getattr(kept, "updated_at", None)
+        if a is not None and (b is None or a > b):
+            by_name[name] = s
+    return by_name
+
+
+def replaced_tasks(containers, services) -> set[tuple]:
+    """(host_id, name) of the task containers Swarm has replaced, from the
+    container rows and the managers' service rows. What the container views use
+    to leave history out of their problem lists."""
+    swarm_cs = [c for c in containers if getattr(c, "service_name", None)]
+    tasks_by_id = {t["task_id"]: t for s in _newest_per_name(services).values()
+                   for t in parse_tasks(s) if t.get("task_id")}
+    return superseded_containers(swarm_cs, tasks_by_id)
+
+
+def build_swarm_services(containers, services, node_hostname: dict, host_name: dict,
+                         *, now: datetime | None = None, crash_loop_deaths: int = 3) -> dict:
+    """Return {"services": [...], "standalone": [...], "superseded": {(host_id, name)}}.
+
+    services[i] = {name, mode, desired, running, state, replicas:[...],
+                   previous_tasks, tasks_known, failures_1h, failures_24h,
+                   crash_looping, last_error}
+      real replica  = {ghost:False, host, host_id, name, status, cpu_pct, mem_pct,
+                       health, restart_count}   # current tasks only
+      ghost replica = {ghost:True, host, count}   # placement with no local row
+      previous_tasks = task containers Swarm replaced, left out of replicas
+      failures_*    = tasks that failed or were rejected in the window (None
+                      without task data); crash_looping = failures_1h ≥ the
+                      Settings → Thresholds crash-loop count
+      last_error    = last_task_error(), plus `node` (the node's hostname)
+      trouble_since = trouble_since(): when the current trouble began, or None
+    standalone[i] = {host_id, host, containers:[...]}  # non-swarm, by host
+    superseded    = the task containers Swarm replaced, so callers can skip them
+    """
+    now = now or datetime.now(timezone.utc)
     containers = list(containers)
     swarm_cs = [c for c in containers if getattr(c, "service_name", None)]
     standalone_cs = [c for c in containers if not getattr(c, "service_name", None)]
 
-    # Dedup service rows by name (every manager reports the same cluster-global
-    # set); keep the first — placement is identical across managers.
-    svc_by_name: dict[str, object] = {}
-    for s in services:
-        name = getattr(s, "service_name", None)
-        if name and name not in svc_by_name:
-            svc_by_name[name] = s
+    svc_by_name = _newest_per_name(services)
+    tasks_by_svc = {name: parse_tasks(s) for name, s in svc_by_name.items()}
+    tasks_by_id = {t["task_id"]: t for ts in tasks_by_svc.values() for t in ts
+                   if t.get("task_id")}
+    superseded = superseded_containers(swarm_cs, tasks_by_id)
 
-    # Real containers grouped by service name.
+    # Current task containers grouped by service name; replaced ones are counted.
     cs_by_service: dict[str, list] = {}
+    previous: dict[str, int] = {}
     for c in swarm_cs:
+        if (c.host_id, c.name) in superseded:
+            previous[c.service_name] = previous.get(c.service_name, 0) + 1
+            continue
         cs_by_service.setdefault(c.service_name, []).append(c)
 
     def _host_of(c):
@@ -117,13 +323,19 @@ def build_swarm_services(containers, services, node_hostname: dict, host_name: d
         if desired is None:
             desired = len(replicas)
 
+        tasks = tasks_by_svc.get(name, [])
+        state = _service_state(int(running or 0), int(desired or 0))
+        summary = task_summary(tasks, now, crash_loop_deaths, node_hostname)
         out_services.append({
             "name": name,
             "mode": getattr(svc, "mode", "replicated") if svc is not None else "replicated",
             "running": running,
             "desired": desired,
-            "state": _service_state(int(running or 0), int(desired or 0)),
+            "state": state,
             "replicas": replicas,
+            "previous_tasks": previous.get(name, 0),
+            **summary,
+            "trouble_since": trouble_since(tasks, state, summary["crash_looping"], now),
         })
 
     # Non-swarm containers grouped by host, running-first order preserved.
@@ -137,4 +349,4 @@ def build_swarm_services(containers, services, node_hostname: dict, host_name: d
         g["containers"].append(c)
     standalone = sorted(groups.values(), key=lambda g: g["host"].lower())
 
-    return {"services": out_services, "standalone": standalone}
+    return {"services": out_services, "standalone": standalone, "superseded": superseded}

plugins/docker/templates/docker/_container_logs_lines.html

@@ -0,0 +1,22 @@
+{# docker/_container_logs_lines.html — log-line fragment, HTMX-polled (m79).
+   {{ l.line }} is auto-escaped by Jinja, so log content can't inject markup. #}
+{% if lines %}
+{% for l in lines %}
+<div style="display:flex;gap:0.6rem;white-space:pre-wrap;word-break:break-word;">
+  <span style="color:var(--text-dim);flex-shrink:0;" title="{{ l.ts }}">{{ l.ts.strftime("%m-%d %H:%M:%S") }}</span>
+  <span style="flex-shrink:0;width:3.2rem;color:{% if l.stream == 'stderr' %}var(--red){% else %}var(--text-muted){% endif %};">{{ l.stream }}</span>
+  <span style="flex:1;min-width:0;{% if l.stream == 'stderr' %}color:var(--text);{% endif %}">{{ l.line }}</span>
+</div>
+{% endfor %}
+{% else %}
+<div style="color:var(--text-muted);padding:1rem 0.25rem;">
+  {% if filtered %}
+  No lines match the current filter.
+  {% else %}
+  No logs collected yet for <code>{{ name }}</code>. Lines appear within a few
+  seconds of the container writing to stdout/stderr — unless it's on the log
+  exclude list or log collection is turned off in
+  <a href="/settings/thresholds/">Settings → Thresholds &amp; Retention</a>.
+  {% endif %}
+</div>
+{% endif %}

plugins/docker/templates/docker/_swarm_failures.html

@@ -0,0 +1,25 @@
+{#- One line on a swarm service's task failures, from Swarm's own task records
+    (agent ≥ 1.8.0): a crash loop or the failures of the last 24h, and how the
+    newest troubled task ended, in Swarm's words. Expects `s` with state,
+    crash_looping, failures_1h, failures_24h and last_error; `style` is
+    optional extra CSS for the wrapper. Renders nothing for a healthy service
+    with no recent failures. -#}
+{%- set e = s.last_error -%}
+{%- if s.crash_looping or s.failures_24h or (e and s.state != 'healthy') %}
+<div style="display:flex;flex-wrap:wrap;align-items:baseline;gap:0.2rem 0.6rem;font-size:0.78rem;color:var(--text-muted);{{ style or '' }}">
+  {% if s.crash_looping %}
+  <span style="color:var(--red);font-weight:600;">Crash-looping · {{ s.failures_1h }} tasks failed in the last hour</span>
+  {% elif s.failures_24h %}
+  <span style="color:var(--orange);">{{ s.failures_24h }} task{{ 's' if s.failures_24h != 1 }} failed in the last 24h</span>
+  {% endif %}
+  {% if e %}
+  <span title="How Swarm recorded the end of this service's newest failed task">
+    Last task {{ e.state }}:
+    <span style="color:var(--text);font-family:ui-monospace,monospace;overflow-wrap:anywhere;">{{ e.error or e.message or e.state }}</span>
+    {%- if e.exit_code %} · exit {{ e.exit_code }}{% endif %}
+    {%- if e.node %} · {{ e.node }}{% endif %}
+    {%- if e.age_s is not none %} · {{ e.age_s|duration }} ago{% endif %}
+  </span>
+  {% endif %}
+</div>
+{%- endif %}

plugins/docker/templates/docker/container_detail.html

@@ -26,6 +26,7 @@
 <div style="font-size:0.82rem;color:var(--text-muted);margin-bottom:1.5rem;">
   {{ container.status }}{% if uptime %} · up {{ uptime }}{% endif %}
   {% if host %} · on <a href="/hosts/{{ host.id }}" style="color:var(--text-muted);">{{ host.name }}</a>{% endif %}
+  · <a href="/plugins/docker/container/{{ host_id }}/{{ name }}/logs">View logs</a>
 </div>
 
 {# ── Facts grid ──────────────────────────────────────────────────────────── #}

plugins/docker/templates/docker/container_logs.html

@@ -0,0 +1,51 @@
+{# docker/container_logs.html — per-container log viewer (m79) #}
+{% extends "base.html" %}
+{% from "_macros.html" import crumbs %}
+{% block title %}Logs — {{ name }} — Docker — Steward{% endblock %}
+{% block breadcrumb %}{{ crumbs([
+  ("Docker", "/plugins/docker/"),
+  (name, "/plugins/docker/container/" ~ host_id ~ "/" ~ name),
+  ("Logs", "")]) }}{% endblock %}
+{% block content %}
+
+<div style="display:flex;align-items:baseline;gap:0.6rem;margin-bottom:0.35rem;flex-wrap:wrap;">
+  <h1 class="page-title" style="margin-bottom:0;">{{ name }}</h1>
+  <span style="font-size:0.9rem;color:var(--text-muted);">logs</span>
+</div>
+<div style="font-size:0.82rem;color:var(--text-muted);margin-bottom:1rem;">
+  Recent lines (newest first) collected by the host agent{% if host %} on
+  <a href="/hosts/{{ host.id }}" style="color:var(--text-muted);">{{ host.name }}</a>{% endif %} —
+  updated every few seconds.
+  <a href="/plugins/docker/container/{{ host_id }}/{{ name }}">← back to container</a>
+</div>
+
+{# ── Controls: stream filter + text search (drive the fragment via HTMX) ───── #}
+<form id="log-controls" onsubmit="return false;"
+      style="display:flex;gap:0.6rem;align-items:center;flex-wrap:wrap;margin-bottom:0.6rem;">
+  <label style="font-size:0.8rem;color:var(--text-muted);display:flex;align-items:center;gap:0.35rem;">
+    Stream
+    <select name="stream" style="padding:0.25rem 0.4rem;">
+      <option value="all">all</option>
+      <option value="stdout">stdout</option>
+      <option value="stderr">stderr</option>
+    </select>
+  </label>
+  <input type="search" name="q" placeholder="Filter lines…" autocomplete="off"
+         aria-label="Filter log lines"
+         style="flex:1;min-width:180px;padding:0.3rem 0.5rem;">
+</form>
+
+<div class="card-flush">
+  <div id="log-lines"
+       hx-get="/plugins/docker/container/{{ host_id }}/{{ name }}/logs/lines"
+       hx-trigger="load, every 5s, change from:#log-controls, keyup changed delay:400ms from:#log-controls"
+       hx-include="#log-controls"
+       hx-swap="innerHTML"
+       role="log" aria-live="polite" tabindex="0"
+       style="max-height:70vh;overflow:auto;padding:0.5rem 0.75rem;
+              font-family:ui-monospace,monospace;font-size:0.8rem;line-height:1.5;">
+    <div style="color:var(--text-muted);">Loading…</div>
+  </div>
+</div>
+
+{% endblock %}

plugins/docker/templates/docker/disk.html

@@ -7,8 +7,8 @@
 
 <h1 class="page-title" style="margin-bottom:0.4rem;">Image &amp; disk usage</h1>
 <p style="font-size:0.82rem;color:var(--text-muted);margin-bottom:1.5rem;">
-  Reclaimable = space held by images no container references. Cleanup actions
-  (prune) arrive in a later release — these are read-only figures for now.
+  Reclaimable = space held by images no container references. Admins can prune
+  per host below; each action runs an audited Ansible playbook on that host.
 </p>
 
 {% if host_groups %}
@@ -47,6 +47,40 @@
     </div>
   </div>
 
+  {# ── Cleanup actions (admin only; audited Ansible prune run) ───────────── #}
+  {% if session.user_role == 'admin' %}
+  <div style="margin-bottom:1rem;">
+    {% if ansible_available and g.has_target %}
+    <div style="display:flex;flex-wrap:wrap;gap:0.5rem;align-items:center;">
+      <form method="post" action="/plugins/docker/disk/{{ g.host_id }}/prune" style="margin:0;"
+            data-confirm="Remove all STOPPED containers on {{ g.host_name }}? This cannot be undone.">{{ csrf_field() }}
+        <input type="hidden" name="target" value="containers">
+        <button type="submit" class="btn btn-sm">Prune stopped containers</button>
+      </form>
+      <form method="post" action="/plugins/docker/disk/{{ g.host_id }}/prune" style="margin:0;"
+            data-confirm="Remove ALL unused images on {{ g.host_name }} (docker image prune -a)? Any image not used by a container is deleted.">{{ csrf_field() }}
+        <input type="hidden" name="target" value="images">
+        <button type="submit" class="btn btn-sm">Prune unused images</button>
+      </form>
+      <form method="post" action="/plugins/docker/disk/{{ g.host_id }}/prune" style="margin:0;"
+            data-confirm="Run a full system prune on {{ g.host_name }}? Removes stopped containers, unused networks, dangling images and build cache.">{{ csrf_field() }}
+        <input type="hidden" name="target" value="system">
+        <button type="submit" class="btn btn-sm btn-danger">System prune…</button>
+      </form>
+    </div>
+    <div style="font-size:0.72rem;color:var(--text-muted);margin-top:0.4rem;">
+      Reclaimed space appears on the next agent sample.
+    </div>
+    {% elif not ansible_available %}
+    <div style="font-size:0.74rem;color:var(--text-muted);">Cleanup needs the Ansible runner (currently unavailable).</div>
+    {% else %}
+    <div style="font-size:0.74rem;color:var(--text-muted);">
+      Link an <a href="/hosts/{{ g.host_id }}">Ansible target</a> to this host to enable prune actions.
+    </div>
+    {% endif %}
+  </div>
+  {% endif %}
+
   {# ── Per-image table ──────────────────────────────────────────────────── #}
   <div class="card-flush">
     <table class="table">

plugins/docker/templates/docker/rows.html

@@ -26,9 +26,10 @@
   </div>
 </div>
 
-{# ── Swarm services: collapsed per-service, each replica labelled with its host.
-   Ghost replicas (tasks on nodes with no Steward agent) come from the managers'
-   placement data so the picture is cluster-complete. ──────────────────────── #}
+{# ── Swarm services: collapsed per-service, each current replica labelled with
+   its host (tasks Swarm replaced are left out). Ghost replicas (tasks on nodes
+   with no Steward agent) come from the managers' placement data so the picture
+   is cluster-complete. A failing service names Swarm's last task error. ───── #}
 {% if swarm_services %}
 <div class="card-flush" style="margin-bottom:1.5rem;">
   <div style="display:flex;align-items:baseline;gap:0.6rem;padding:0.5rem 0.75rem;border-bottom:1px solid var(--border);">
@@ -46,6 +47,7 @@
           {{ s.running }}/{{ s.desired }} running
         </span>
       </div>
+      {% with style="padding-left:1.1rem;margin-bottom:0.35rem;" %}{% include "docker/_swarm_failures.html" %}{% endwith %}
       <div style="display:grid;grid-template-columns:repeat(auto-fill,minmax(210px,1fr));gap:0.4rem;padding-left:1.1rem;">
         {% for r in s.replicas %}
         {% if r.ghost %}

plugins/docker/templates/docker/swarm.html

@@ -22,7 +22,7 @@
     <table class="table">
       <thead>
         <tr>
-          <th>Service</th><th>Mode</th><th>Replicas</th><th>Image</th><th>Placement</th>
+          <th>Service</th><th>Mode</th><th>Replicas</th><th>Image</th><th>Placement</th><th>Task failures</th>
         </tr>
       </thead>
       <tbody>
@@ -39,9 +39,14 @@
           <td style="font-size:0.78rem;color:var(--text-muted);">
             {% for p in s.placement %}{{ p.node }} ({{ p.running }}){% if not loop.last %}, {% endif %}{% else %}—{% endfor %}
           </td>
+          <td style="max-width:360px;">
+            {% include "docker/_swarm_failures.html" %}
+            {%- if not s.tasks_known %}<span style="font-size:0.78rem;color:var(--text-dim);" title="The reporting manager's agent predates task reporting (1.8.0); update it to see task failures.">—</span>
+            {%- elif not (s.crash_looping or s.failures_24h or (s.last_error and s.state != 'healthy')) %}<span style="font-size:0.78rem;color:var(--text-dim);">none in 24h</span>{% endif %}
+          </td>
         </tr>
         {% else %}
-        <tr><td colspan="5" style="color:var(--text-muted);font-size:0.85rem;text-align:center;padding:1.5rem;">No services in this swarm.</td></tr>
+        <tr><td colspan="6" style="color:var(--text-muted);font-size:0.85rem;text-align:center;padding:1.5rem;">No services in this swarm.</td></tr>
         {% endfor %}
       </tbody>
     </table>

plugins/docker/templates/docker/widget.html

@@ -8,7 +8,7 @@
     <span style="font-size:1.4rem;font-weight:700;line-height:1;color:var(--green);">{{ running_count }}</span>
     <span style="font-size:0.78rem;color:var(--text-muted);margin-left:0.25rem;">running</span>
   </div>
-  <div title="Distinct containers with a die or OOM event in the last 24h">
+  <div title="Containers that died or were OOM-killed in the last 24h, plus swarm tasks that failed (a task Swarm replaced is not a failure)">
     <span style="font-size:1.4rem;font-weight:700;line-height:1;color:{% if failed_24h %}var(--red){% else %}var(--text-muted){% endif %};">{{ failed_24h }}</span>
     <span style="font-size:0.78rem;color:var(--text-muted);margin-left:0.25rem;">failed (24h)</span>
   </div>
@@ -24,6 +24,7 @@
     <div style="display:flex;align-items:center;gap:0.4rem;font-size:0.82rem;">
       <span class="dot {% if s.state == 'healthy' %}dot-up{% elif s.state == 'degraded' %}dot-warn{% else %}dot-down{% endif %}"></span>
       <span style="font-weight:500;min-width:0;white-space:nowrap;overflow:hidden;text-overflow:ellipsis;">{{ s.name }}</span>
+      {% if s.crash_looping %}<span style="color:var(--red);font-size:0.7rem;font-weight:600;flex-shrink:0;" title="{{ s.failures_1h }} tasks failed in the last hour{% if s.last_error %}: {{ s.last_error.error or s.last_error.message or s.last_error.state }}{% endif %}">crash-looping</span>{% endif %}
       <span style="color:var(--text-muted);font-family:ui-monospace,monospace;font-size:0.74rem;margin-left:auto;flex-shrink:0;">{{ s.running }}/{{ s.desired }}</span>
     </div>
     <div style="display:flex;flex-wrap:wrap;gap:0.25rem;margin:0.2rem 0 0 1rem;">

plugins/host_agent/__init__.py

@@ -21,3 +21,24 @@ def get_scheduled_tasks() -> list:
 def get_blueprint():
     from .routes import host_agent_bp
     return host_agent_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_alert_metrics() -> dict[str, list[str]]:
+    """Host metrics ingest records for alert rules (resource = the host name;
+    disk_used_pct per mount, resource "<host>:<mount>"). seconds_since_seen
+    comes from the scheduler, not the agent: "agent offline" is > 180."""
+    return {"host_agent": [
+        "cpu_pct", "mem_used_pct", "mem_available_bytes", "swap_used_bytes",
+        "disk_used_pct_worst", "disk_used_pct", "load_1m", "load_5m", "load_15m",
+        "uptime_secs", "seconds_since_seen",
+    ]}

plugins/host_agent/agent.py

@@ -20,7 +20,7 @@ from collections import deque
 from concurrent.futures import ThreadPoolExecutor
 from datetime import datetime, timezone
 
-AGENT_VERSION = "1.6.0"
+AGENT_VERSION = "1.8.0"
 
 # Default path to the local Docker Engine socket. Overridable via the
 # `docker_socket` config key; collection is silently skipped if it's absent or
@@ -34,7 +34,10 @@ class ConfigError(Exception):
 
 REQUIRED_KEYS = ("url", "token")
 INT_KEYS = ("interval_seconds",)
-LIST_KEYS = ("mounts",)
+LIST_KEYS = ("mounts", "docker_log_exclude")
+# Truthy strings for bool keys; anything else (incl. empty) is False.
+BOOL_KEYS = ("docker_logs_enabled",)
+_BOOL_TRUE = ("1", "true", "yes", "on")
 
 
 def read_config(path: str) -> dict:
@@ -58,6 +61,8 @@ def read_config(path: str) -> dict:
                         raise ConfigError(f"{path}:{lineno}: {key} must be int")
                 elif key in LIST_KEYS:
                     cfg[key] = [v.strip() for v in value.split(",") if v.strip()]
+                elif key in BOOL_KEYS:
+                    cfg[key] = value.lower() in _BOOL_TRUE
                 else:
                     cfg[key] = value
     except FileNotFoundError:
@@ -69,6 +74,10 @@ def read_config(path: str) -> dict:
 
     cfg.setdefault("interval_seconds", 30)
     cfg.setdefault("docker_socket", DEFAULT_DOCKER_SOCKET)
+    # Container-log collection is on by default (operator preference); a host can
+    # opt out with `docker_logs_enabled = false` or thin it with docker_log_exclude.
+    cfg.setdefault("docker_logs_enabled", True)
+    cfg.setdefault("docker_log_exclude", [])
     return cfg
 
 
@@ -403,6 +412,15 @@ def _rates(cur: dict, prev: dict, dt: float) -> dict:
 
 DOCKER_API_TIMEOUT = 5.0
 
+# Container-log collection (m79). Logs ride in the same push as metrics, so one
+# interval's batch is capped to keep a chatty container from bloating a POST (and
+# the backoff ring): once the cap is hit a marker line is emitted and collection
+# stops — the deferred lines come on the next interval. On a container's first
+# interval we seed from a short tail, then switch to an incremental since-cursor
+# kept per container in the agent's rate-state.
+DOCKER_LOG_BATCH_MAX_BYTES = 262144   # 256 KiB of log text per push, all containers
+DOCKER_LOG_FIRST_TAIL = 50            # lines seeded on a container's first interval
+
 
 def _dechunk(body: bytes) -> bytes:
     """Decode an HTTP/1.1 chunked-transfer body into the raw payload."""
@@ -650,6 +668,198 @@ def collect_docker(socket_path: str) -> list:
         return list(ex.map(lambda c: _collect_one_container(socket_path, c), containers))
 
 
+# ─── container logs (m79) ─────────────────────────────────────────────────────
+#
+# The logs endpoint returns a raw multiplexed byte stream, not JSON, so it needs
+# a sibling of _docker_request that hands back bytes. Non-TTY containers frame
+# stdout/stderr with an 8-byte header (stream byte + 4-byte big-endian length);
+# TTY containers emit unframed bytes. We request timestamps=1, so every line is
+# prefixed with an RFC3339Nano timestamp we parse for the since-cursor.
+
+_LOG_STREAM_NAMES = {0: "stdout", 1: "stdout", 2: "stderr"}
+
+
+def _docker_request_raw(socket_path: str, path: str,
+                        timeout: float = DOCKER_API_TIMEOUT) -> bytes:
+    """GET `path` from the Docker API over the Unix socket; return the raw body.
+
+    Sibling of `_docker_request` for non-JSON endpoints (container logs). Reuses
+    the connect / send / de-chunk scaffolding; raises OSError on any transport
+    problem or non-2xx status so callers can silent-skip. A 200 with an empty
+    body (no new lines since the cursor) returns b"".
+    """
+    sock = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
+    sock.settimeout(timeout)
+    try:
+        sock.connect(socket_path)
+        req = (
+            "GET " + path + " HTTP/1.1\r\n"
+            "Host: docker\r\n"
+            "Accept: application/octet-stream\r\n"
+            "Connection: close\r\n"
+            "\r\n"
+        )
+        sock.sendall(req.encode("ascii"))
+        chunks = []
+        while True:
+            buf = sock.recv(65536)
+            if not buf:
+                break
+            chunks.append(buf)
+    finally:
+        sock.close()
+
+    raw = b"".join(chunks)
+    head, _, body = raw.partition(b"\r\n\r\n")
+    header_text = head.decode("latin-1")
+    status_line = header_text.split("\r\n", 1)[0]
+    parts = status_line.split(None, 2)
+    status = int(parts[1]) if len(parts) >= 2 and parts[1].isdigit() else 0
+    if not (200 <= status < 300):
+        raise OSError(f"docker API {path} returned {status}")
+    if "transfer-encoding: chunked" in header_text.lower():
+        body = _dechunk(body)
+    return body
+
+
+def _demux_docker_logs(raw: bytes) -> list:
+    """Split a Docker logs stream into [(stream_name, payload_bytes), …].
+
+    Non-TTY containers multiplex with an 8-byte frame header (stream byte in
+    {0,1,2} + 4-byte big-endian length). The stream is treated as framed only if
+    the whole buffer parses as clean back-to-back frames; anything else (a TTY
+    container's raw stream, or a malformed header) falls back to a single stdout
+    blob so no bytes are lost.
+    """
+    if not raw:
+        return []
+    frames = []
+    i, n = 0, len(raw)
+    while i + 8 <= n:
+        stream = raw[i]
+        if stream > 2 or raw[i + 1] or raw[i + 2] or raw[i + 3]:
+            break  # not a valid frame header → not framed
+        size = int.from_bytes(raw[i + 4:i + 8], "big")
+        if i + 8 + size > n:
+            break  # frame overruns the buffer → not framed
+        frames.append((_LOG_STREAM_NAMES.get(stream, "stdout"),
+                       raw[i + 8:i + 8 + size]))
+        i += 8 + size
+    if frames and i == n:
+        return frames
+    return [("stdout", raw)]
+
+
+def _parse_log_ts(token: str):
+    """Parse a Docker RFC3339Nano timestamp token into a datetime, or None.
+
+    Normalises `Z` → `+00:00` and trims Docker's nanosecond precision to the
+    microseconds datetime.fromisoformat accepts (stdlib, Python 3.8+ safe).
+    """
+    t = token.strip()
+    if not t:
+        return None
+    if t.endswith("Z"):
+        t = t[:-1] + "+00:00"
+    m = re.match(r"^(\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2})(\.\d+)?(.*)$", t)
+    if m:
+        frac = m.group(2) or ""
+        if len(frac) > 7:               # "." + up to 6 fractional digits
+            frac = frac[:7]
+        t = m.group(1) + frac + m.group(3)
+    try:
+        return datetime.fromisoformat(t)
+    except ValueError:
+        return None
+
+
+def _parse_container_logs(raw: bytes) -> list:
+    """Demux + line-split a logs stream → [(dt|None, stream, line), …] in order.
+
+    Each line is timestamp-prefixed (we request timestamps=1); an unparseable
+    prefix yields dt=None with the full raw line kept.
+    """
+    out = []
+    for stream, payload in _demux_docker_logs(raw):
+        text = payload.decode("utf-8", "replace")
+        for raw_line in text.split("\n"):
+            if not raw_line:
+                continue
+            token, _, msg = raw_line.partition(" ")
+            dt = _parse_log_ts(token)
+            if dt is not None:
+                out.append((dt, stream, msg))
+            else:
+                out.append((None, stream, raw_line))
+    return out
+
+
+def collect_docker_logs(socket_path: str, containers: list, state: dict,
+                        exclude=None,
+                        max_bytes: int = DOCKER_LOG_BATCH_MAX_BYTES) -> list:
+    """New container-log lines since the last interval, for running containers.
+
+    Keeps a per-container since-cursor in `state["docker_log_cursors"]`
+    (name → unix ts) so each interval fetches only what's new; a container's
+    first interval seeds from a short tail. The whole batch is capped at
+    `max_bytes` of log text — once exceeded a truncation marker is appended and
+    collection stops (logs must never balloon a push). `exclude` container names
+    are skipped entirely (a per-host bandwidth opt-out). Best-effort: a
+    per-container transport error just contributes nothing this interval.
+    Returns [{"container", "stream", "ts", "line"}, …].
+    """
+    exclude_set = set(exclude or ())
+    cursors = state.setdefault("docker_log_cursors", {})
+    running = {c.get("name") for c in (containers or [])
+               if c.get("name") and c.get("status") == "running"}
+    # Forget cursors for containers no longer running so state can't grow without
+    # bound over the agent's lifetime.
+    for gone in [k for k in cursors if k not in running]:
+        del cursors[gone]
+
+    out: list = []
+    total = 0
+    truncated = False
+    for c in (containers or []):
+        name = c.get("name")
+        if not name or name not in running or name in exclude_set:
+            continue
+        prev = cursors.get(name)
+        base = f"/containers/{name}/logs?stdout=1&stderr=1&timestamps=1"
+        # since accepts a fractional Unix ts; we still dedup the boundary line.
+        path = (f"{base}&tail={DOCKER_LOG_FIRST_TAIL}" if prev is None
+                else f"{base}&since={prev:.9f}")
+        try:
+            raw = _docker_request_raw(socket_path, path)
+        except (OSError, ValueError):
+            continue
+        newest = prev
+        for dt, stream, line in _parse_container_logs(raw):
+            ts_unix = dt.timestamp() if dt is not None else None
+            if prev is not None and ts_unix is not None and ts_unix <= prev:
+                continue  # boundary line already sent last interval
+            if total >= max_bytes:
+                truncated = True
+                break
+            out.append({"container": name, "stream": stream,
+                        "ts": dt.isoformat() if dt is not None else None,
+                        "line": line})
+            total += len(line)
+            if ts_unix is not None and (newest is None or ts_unix > newest):
+                newest = ts_unix
+        if newest is not None:
+            cursors[name] = newest
+        if truncated:
+            break
+
+    if truncated:
+        out.append({"container": "_steward", "stream": "stderr",
+                    "ts": datetime.now(timezone.utc).isoformat(),
+                    "line": (f"[steward] log batch truncated at {max_bytes} bytes; "
+                             "remaining lines deferred to the next interval")})
+    return out
+
+
 # ─── swarm (manager-only) ────────────────────────────────────────────────────
 
 
@@ -664,14 +874,46 @@ def _swarm_is_manager(info: dict) -> bool:
     return bool((info or {}).get("Swarm", {}).get("ControlAvailable"))
 
 
+# Newest tasks kept per service. Swarm retains about 5 per slot by default, so
+# this covers a replicated service's recent history and a crash loop's deaths
+# without shipping a global service's whole fleet every sample.
+SWARM_TASKS_PER_SERVICE = 10
+_TASK_TEXT_CHARS = 300
+
+
+def _swarm_task(t: dict) -> dict:
+    """One task as Steward stores it: where it ran, what Swarm wants of it,
+    what it is doing, and why it stopped (Err/Message, exit code)."""
+    status = t.get("Status") or {}
+    cstatus = status.get("ContainerStatus") or {}
+    exit_code = cstatus.get("ExitCode")
+    return {
+        "task_id": t.get("ID", "") or "",
+        "slot": t.get("Slot"),
+        "node_id": t.get("NodeID", "") or "",
+        "desired_state": (t.get("DesiredState") or "").lower(),
+        "state": (status.get("State") or "").lower(),
+        "message": (status.get("Message") or "")[:_TASK_TEXT_CHARS],
+        "error": (status.get("Err") or "")[:_TASK_TEXT_CHARS],
+        "exit_code": exit_code if isinstance(exit_code, int) else None,
+        "at": status.get("Timestamp") or t.get("UpdatedAt") or "",
+    }
+
+
 def _swarm_services(services: list, tasks: list) -> list:
     """Roll desired-vs-running replicas per service up from the task list.
 
     Replica health isn't on the service object — it's derived by counting tasks:
     `running` = tasks currently in state running; `desired` = the service's
     configured replica count (replicated) or the count of tasks the scheduler
-    wants running (global, which has no fixed number).
+    wants running (global, which has no fixed number). Each service also
+    carries its newest tasks (`tasks`), so Steward can tell a task Swarm
+    replaced from one that crashed, and say why the last one failed.
     """
+    tasks_by_svc: dict = {}
+    for t in (tasks or []):
+        if t.get("ServiceID"):
+            tasks_by_svc.setdefault(t["ServiceID"], []).append(_swarm_task(t))
     running_by_svc: dict = {}
     desired_by_svc: dict = {}  # only used for global-mode services
     placement: dict = {}       # svc_id -> {node_id: running_count}
@@ -711,6 +953,8 @@ def _swarm_services(services: list, tasks: list) -> list:
             # sees every task, even ones whose containers live on other hosts).
             "placement": [{"node_id": n, "running": cnt}
                           for n, cnt in sorted(placement.get(sid, {}).items())],
+            "tasks": sorted(tasks_by_svc.get(sid, []), key=lambda t: t["at"],
+                            reverse=True)[:SWARM_TASKS_PER_SERVICE],
         })
     return out
 
@@ -852,13 +1096,17 @@ class RingBuffer:
 
 
 def build_sample(mounts: list[str], state: dict,
-                 docker_socket: str = DEFAULT_DOCKER_SOCKET) -> dict:
+                 docker_socket: str = DEFAULT_DOCKER_SOCKET, *,
+                 docker_logs_enabled: bool = True,
+                 docker_log_exclude=None) -> dict:
     """Collect one full sample. Partial samples allowed if a collector fails.
 
     `state` carries the previous network/disk counters + monotonic timestamp so
-    throughput rates can be derived from deltas; it is mutated in place.
-    `docker_socket` is probed best-effort — the `docker` key is omitted entirely
-    when no containers are found, so non-Docker hosts add nothing to the payload.
+    throughput rates can be derived from deltas (and the per-container log
+    since-cursors); it is mutated in place. `docker_socket` is probed
+    best-effort — the `docker` key is omitted entirely when no containers are
+    found, so non-Docker hosts add nothing to the payload. `docker_logs_enabled`
+    / `docker_log_exclude` gate incremental container-log collection.
     """
     sample: dict = {"ts": datetime.now(timezone.utc).isoformat()}
     try:
@@ -940,6 +1188,18 @@ def build_sample(mounts: list[str], state: dict,
         if disk is not None:
             sample["docker_disk"] = disk
 
+    # Container logs (m79): incremental per-container tail folded into the same
+    # push as metrics. Skipped when there are no containers or logging is off;
+    # the key is omitted when nothing new arrived this interval.
+    if docker and docker_logs_enabled:
+        try:
+            logs = collect_docker_logs(docker_socket, docker, state,
+                                       exclude=docker_log_exclude)
+        except Exception:
+            logs = []
+        if logs:
+            sample["docker_logs"] = logs
+
     return sample
 
 
@@ -958,6 +1218,18 @@ def build_payload(samples: list[dict], hostname: str, metadata: dict) -> dict:
 BACKOFF_CAP = 300
 
 
+def _drop_logs(sample: dict) -> dict:
+    """Strip container logs from a sample before it's buffered for retry.
+
+    Logs are the one payload we never carry across a backoff — they'd bloat the
+    ring buffer and go stale — while metrics are kept so an outage doesn't lose
+    them. The since-cursor already advanced when the logs were collected, so the
+    dropped lines are simply not re-sent (accepted loss during an outage).
+    """
+    sample.pop("docker_logs", None)
+    return sample
+
+
 def next_backoff(current: int) -> int:
     if current <= 0:
         return 30
@@ -1022,6 +1294,8 @@ def main_loop(conf_path: str) -> int:
     hostname = cfg.get("hostname") or socket.gethostname()
     mounts = cfg.get("mounts") or default_mounts()
     docker_socket = cfg.get("docker_socket") or DEFAULT_DOCKER_SOCKET
+    docker_logs_enabled = cfg.get("docker_logs_enabled", True)
+    docker_log_exclude = cfg.get("docker_log_exclude") or []
     buffer = RingBuffer(maxlen=20)
     backoff = 0
     # Carries previous net/disk counters + monotonic ts for rate computation.
@@ -1036,13 +1310,17 @@ def main_loop(conf_path: str) -> int:
                 cfg = read_config(conf_path)
                 mounts = cfg.get("mounts") or default_mounts()
                 docker_socket = cfg.get("docker_socket") or DEFAULT_DOCKER_SOCKET
+                docker_logs_enabled = cfg.get("docker_logs_enabled", True)
+                docker_log_exclude = cfg.get("docker_log_exclude") or []
                 metadata = collect_metadata()  # refresh host_ip/distro on reload
                 _log("INFO", "config reloaded")
             except ConfigError as e:
                 _log("ERROR", f"reload failed: {e}")
             _reload_requested = False
 
-        sample = build_sample(mounts, rate_state, docker_socket)
+        sample = build_sample(mounts, rate_state, docker_socket,
+                              docker_logs_enabled=docker_logs_enabled,
+                              docker_log_exclude=docker_log_exclude)
         buffered = buffer.drain()
         payload = build_payload(
             samples=buffered + [sample],
@@ -1061,12 +1339,12 @@ def main_loop(conf_path: str) -> int:
                 _log("ERROR", "server rejected payload (400) — dropping sample")
             elif status == 401:
                 _log("ERROR", "token rejected (401) — check config + UI")
-                buffer.push(sample)
+                buffer.push(_drop_logs(sample))
             else:
                 _log("WARN", f"POST failed (status={status}); buffering")
                 for s in buffered:
-                    buffer.push(s)
-                buffer.push(sample)
+                    buffer.push(_drop_logs(s))
+                buffer.push(_drop_logs(sample))
             backoff = next_backoff(backoff)
             sleep_for = backoff
 

plugins/host_agent/mcp_tools.py

@@ -0,0 +1,81 @@
+"""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)

plugins/host_agent/routes.py

@@ -9,7 +9,7 @@ from pathlib import Path
 
 import secrets
 from quart import Blueprint, current_app, jsonify, request, Response, render_template, redirect, url_for, session
-from steward.auth.middleware import require_role
+from steward.auth.middleware import public_route, require_role
 from steward.models.users import UserRole
 from sqlalchemy import select, func, or_, and_
 from datetime import timedelta
@@ -166,6 +166,7 @@ def _error(status: int, code: str, detail: str | None = None) -> tuple[Any, int]
 
 
 @host_agent_bp.post("/ingest")
+@public_route("the agent authenticates with its bearer token")
 async def ingest():
     auth = request.headers.get("Authorization", "")
     if not auth.startswith("Bearer "):
@@ -200,8 +201,10 @@ async def ingest():
             return _error(401, "invalid_token")
 
         accepted = 0
+        metric_rows: list[PluginMetric] = []
         latest_ts: datetime | None = None
         docker_snapshots: list[tuple[datetime, list]] = []
+        docker_log_batches: list[tuple[datetime, list]] = []
         latest_swarm: dict | None = None
         latest_swarm_ts: datetime | None = None
         latest_disk: dict | None = None
@@ -211,12 +214,15 @@ async def ingest():
                 recorded_at = _parse_ts(sample["ts"])
             except (KeyError, ValueError):
                 continue
-            metrics = _expand_sample_to_metrics(sample, host.name, recorded_at)
-            for m in metrics:
-                session.add(m)
+            metric_rows.extend(_expand_sample_to_metrics(sample, host.name, recorded_at))
             docker = sample.get("docker")
             if isinstance(docker, list) and docker:
                 docker_snapshots.append((recorded_at, docker))
+            # Container logs are time-series (append every line, not newest-only);
+            # each record carries its own Docker ts, recorded_at is the fallback.
+            docker_logs = sample.get("docker_logs")
+            if isinstance(docker_logs, list) and docker_logs:
+                docker_log_batches.append((recorded_at, docker_logs))
             # Swarm is current-state, not time-series — keep only the newest
             # sample's topology (a manager re-reports it every interval).
             swarm = sample.get("swarm")
@@ -236,11 +242,16 @@ async def ingest():
             await session.rollback()
             return _error(400, "malformed_payload", "no valid samples")
 
+        # Through the alert pipeline, so rules on host metrics can fire.
+        from steward.core.alerts import record_metrics
+        await record_metrics(session, metric_rows)
+
         # Hand host-scoped container data to the docker plugin if it's enabled
         # (opportunistic synergy via the capability registry — no hard import,
         # no-op when docker is disabled). A failure here must never sink the
         # whole ingest, so the metrics above still land.
-        if docker_snapshots or latest_swarm is not None or latest_disk is not None:
+        if (docker_snapshots or latest_swarm is not None
+                or latest_disk is not None or docker_log_batches):
             from steward.core.capabilities import has_capability, invoke_capability
             if has_capability("docker.persist_host_samples"):
                 try:
@@ -250,7 +261,7 @@ async def ingest():
                         await invoke_capability(
                             "docker.persist_host_samples", UserRole.admin,
                             session, host, docker_snapshots, latest_swarm,
-                            latest_disk,
+                            latest_disk, docker_log_batches,
                         )
                 except Exception:
                     current_app.logger.exception(
@@ -306,6 +317,7 @@ def _agent_version() -> str:
 
 
 @host_agent_bp.get("/install.sh")
+@public_route("fetched by curl on the host being enrolled; carries an enrolment token")
 async def install_script():
     token = request.args.get("token", "")
     if not token:
@@ -337,6 +349,7 @@ async def install_script():
 
 
 @host_agent_bp.get("/agent.py")
+@public_route("fetched by the installer and by agent self-update; holds no secrets")
 async def agent_source():
     try:
         body = AGENT_SOURCE_PATH.read_text(encoding="utf-8")
@@ -463,6 +476,7 @@ async def _fleet_rows(session) -> list[dict]:
 
 
 @host_agent_bp.get("/widget")
+@require_role(UserRole.viewer)
 async def widget_table():
     """Fleet-glance dashboard widget: one row per monitored host, latest metrics."""
     async with current_app.db_sessionmaker() as session:
@@ -471,6 +485,7 @@ async def widget_table():
 
 
 @host_agent_bp.get("/widget/history")
+@require_role(UserRole.viewer)
 async def widget_history():
     host_id = request.args.get("host_id", "")
     try:
@@ -947,6 +962,7 @@ async def deploy_via_ansible():
         playbook_path="host_agent/install.yml",
         inventory_content=inventory_content,
         inventory_scope=scope,
+        redact=list(tokens.values()),
         # extra-vars outrank the playbook's `vars:` defaults; token stays per-host.
         params={"extra_vars_map": {"steward_url": url, "agent_interval": interval}},
         triggered_by=session.get("user_id"),
@@ -1024,6 +1040,7 @@ async def provision_via_ansible():
         playbook_path="host_agent/provision.yml",
         inventory_content=inventory_content,
         inventory_scope=scope,
+        redact=list(tokens.values()),
         # extra_vars_map → a JSON -e @file: highest precedence (beats play vars)
         # and space-safe (steward_pubkey carries a comment with a space).
         params={"extra_vars_map": {

plugins/host_agent/scheduler.py

@@ -1,11 +1,12 @@
 # plugins/host_agent/scheduler.py
 from __future__ import annotations
 import logging
-from datetime import datetime, timedelta, timezone
+from datetime import datetime, timezone
 from typing import Iterable
 
 from sqlalchemy import select
 
+from steward.core.alerts import MetricBatch
 from steward.core.scheduler import ScheduledTask
 from steward.models.hosts import Host
 from .models import HostAgentRegistration
@@ -13,66 +14,52 @@ from .models import HostAgentRegistration
 logger = logging.getLogger(__name__)
 
 
-def _filter_stale(
-    regs: Iterable,
-    *,
-    now: datetime,
-    stale_after_seconds: int,
-) -> list:
-    """Pure staleness filter: returns the subset with last_seen_at strictly
-    older than (now - stale_after_seconds). Rows with last_seen_at=None are
-    never stale (they are unregistered-in-practice)."""
-    cutoff = now - timedelta(seconds=stale_after_seconds)
-    return [
-        r for r in regs
-        if r.last_seen_at is not None and r.last_seen_at < cutoff
-    ]
+def seconds_since_seen(regs: Iterable, host_names: dict[str, str],
+                       now: datetime) -> list[tuple[str, float]]:
+    """(host name, seconds since its agent last reported) per registration.
+
+    An agent that has never reported counts from when it was registered. A
+    registration whose host is gone is skipped.
+    """
+    out = []
+    for r in regs:
+        name = host_names.get(r.host_id)
+        seen = r.last_seen_at or r.created_at
+        if name is None or seen is None:
+            continue
+        out.append((name, max(0.0, (now - seen).total_seconds())))
+    return out
 
 
-async def find_stale_registrations(app, stale_after_seconds: int = 180) -> list[dict]:
+async def record_seconds_since_seen(app) -> None:
+    """Record host_agent/<host>/seconds_since_seen for every registered agent,
+    so "agent offline" is an ordinary alert rule (seconds_since_seen > 180)."""
+    now = datetime.now(timezone.utc)
     async with app.db_sessionmaker() as session:
-        all_regs = (await session.execute(
-            select(HostAgentRegistration)
-        )).scalars().all()
-        stale_rows = _filter_stale(
-            all_regs,
-            now=datetime.now(timezone.utc),
-            stale_after_seconds=stale_after_seconds,
-        )
-        if not stale_rows:
-            return []
-        hosts = {
-            h.id: h for h in (await session.execute(
-                select(Host).where(Host.id.in_([r.host_id for r in stale_rows]))
-            )).scalars().all()
-        }
-    return [
-        {
-            "host_id": r.host_id,
-            "host_name": hosts[r.host_id].name if r.host_id in hosts else "?",
-            "last_seen_at": r.last_seen_at,
-        }
-        for r in stale_rows
-    ]
+        async with session.begin():
+            regs = (await session.execute(select(HostAgentRegistration))).scalars().all()
+            if not regs:
+                return
+            host_names = dict((await session.execute(
+                select(Host.id, Host.name).where(Host.id.in_([r.host_id for r in regs]))
+            )).all())
+            batch = MetricBatch()
+            for name, seconds in seconds_since_seen(regs, host_names, now):
+                batch.add(source_module="host_agent", resource_name=name,
+                          metric_name="seconds_since_seen", value=seconds, recorded_at=now)
+            await batch.record(session)
 
 
 def make_task(app) -> ScheduledTask:
-    async def _check_stale():
+    async def _record():
         try:
-            stale = await find_stale_registrations(app)
+            await record_seconds_since_seen(app)
         except Exception:
-            logger.exception("host_agent stale check failed")
-            return
-        if stale:
-            logger.info(
-                "host_agent: %d stale agent(s): %s",
-                len(stale),
-                [s["host_name"] for s in stale],
-            )
+            logger.exception("host_agent: recording seconds_since_seen failed")
 
     return ScheduledTask(
-        name="host_agent_stale_check",
-        coro_factory=_check_stale,
+        name="host_agent_seconds_since_seen",
+        coro_factory=_record,
         interval_seconds=60,
         run_on_startup=False,
     )

plugins/host_agent/templates/_host_metrics.html

@@ -1,22 +1,5 @@
 {# Current-state fragment for the full-metrics page — polled live via HTMX.
-   Self-contained (defines its own format macros) so each poll re-renders the
-   latest snapshot the server has. #}
-{% macro fmt_bps(v) %}
-{%- if v is none -%}—
-{%- elif v >= 1048576 -%}{{ "%.1f"|format(v / 1048576) }} MB/s
-{%- elif v >= 1024 -%}{{ "%.1f"|format(v / 1024) }} KB/s
-{%- else -%}{{ "%.0f"|format(v) }} B/s
-{%- endif -%}
-{% endmacro %}
-{% macro fmt_bytes(v) %}
-{%- if v is none -%}—
-{%- elif v >= 1125899906842624 -%}{{ "%.1f"|format(v / 1125899906842624) }} PB
-{%- elif v >= 1099511627776 -%}{{ "%.1f"|format(v / 1099511627776) }} TB
-{%- elif v >= 1073741824 -%}{{ "%.1f"|format(v / 1073741824) }} GB
-{%- elif v >= 1048576 -%}{{ "%.0f"|format(v / 1048576) }} MB
-{%- else -%}{{ "%.0f"|format(v / 1024) }} KB
-{%- endif -%}
-{% endmacro %}
+   Each poll re-renders the latest snapshot the server has. #}
 {% macro bar(pct) %}
 {%- set p = pct if pct is not none else 0 -%}
 <div style="height:8px;background:var(--bg-elevated);border-radius:4px;overflow:hidden;border:1px solid var(--border);">
@@ -34,7 +17,7 @@
   {% if reg.arch %}<span><span style="color:var(--text-dim);">Arch</span> {{ reg.arch }}</span>{% endif %}
   {% if reg.agent_version %}<span><span style="color:var(--text-dim);">Agent</span> v{{ reg.agent_version }}</span>{% endif %}
   {% set up = hostlvl.get('uptime_secs') %}
-  {% if up %}<span><span style="color:var(--text-dim);">Uptime</span> {{ (up // 86400)|int }}d {{ ((up % 86400) // 3600)|int }}h</span>{% endif %}
+  {% if up %}<span><span style="color:var(--text-dim);">Uptime</span> {{ up|duration }}</span>{% endif %}
   <span><span style="color:var(--text-dim);">Last seen</span> {{ reg.last_seen_at.strftime("%Y-%m-%d %H:%M:%S") ~ " UTC" if reg.last_seen_at else "never" }}</span>
   {% else %}
   <span>No agent registration found for this host.</span>
@@ -59,7 +42,7 @@
     <span class="stat-val" style="font-size:1.6rem;color:{% if mp is none %}var(--text-dim){% elif mp < 70 %}var(--green){% elif mp < 90 %}var(--yellow){% else %}var(--red){% endif %};">{% if mp is not none %}{{ "%.0f"|format(mp) }}%{% else %}—{% endif %}</span>
     <div style="margin-top:0.5rem;">{{ bar(mp) }}</div>
     <div style="margin-top:0.45rem;font-size:0.72rem;color:var(--text-dim);">
-      avail {{ fmt_bytes(hostlvl.get('mem_available_bytes')) }} · cache {{ fmt_bytes(hostlvl.get('mem_cached_bytes')) }} · swap {{ fmt_bytes(hostlvl.get('swap_used_bytes')) }}
+      avail {{ hostlvl.get('mem_available_bytes')|bytes }} · cache {{ hostlvl.get('mem_cached_bytes')|bytes }} · swap {{ hostlvl.get('swap_used_bytes')|bytes }}
     </div>
   </div>
   <div class="card" style="margin-bottom:0;">
@@ -73,15 +56,15 @@
   <div class="card" style="margin-bottom:0;">
     <div class="section-title" style="margin-bottom:0.35rem;">Network</div>
     <div style="font-size:0.95rem;font-variant-numeric:tabular-nums;">
-      <div><span style="color:var(--green);">↓</span> {{ fmt_bps(hostlvl.get('net_rx_bps')) }}</div>
-      <div><span style="color:var(--red);">↑</span> {{ fmt_bps(hostlvl.get('net_tx_bps')) }}</div>
+      <div><span style="color:var(--green);">↓</span> {{ hostlvl.get('net_rx_bps')|rate }}</div>
+      <div><span style="color:var(--red);">↑</span> {{ hostlvl.get('net_tx_bps')|rate }}</div>
     </div>
   </div>
   <div class="card" style="margin-bottom:0;">
     <div class="section-title" style="margin-bottom:0.35rem;">Disk I/O</div>
     <div style="font-size:0.95rem;font-variant-numeric:tabular-nums;">
-      <div><span style="color:var(--text-dim);">rd</span> {{ fmt_bps(hostlvl.get('disk_read_bps')) }}</div>
-      <div><span style="color:var(--text-dim);">wr</span> {{ fmt_bps(hostlvl.get('disk_write_bps')) }}</div>
+      <div><span style="color:var(--text-dim);">rd</span> {{ hostlvl.get('disk_read_bps')|rate }}</div>
+      <div><span style="color:var(--text-dim);">wr</span> {{ hostlvl.get('disk_write_bps')|rate }}</div>
     </div>
   </div>
   {% if hostlvl.get('temp_c_max') is not none %}
@@ -128,7 +111,7 @@
   <div style="margin-bottom:0.6rem;">
     <div style="display:flex;justify-content:space-between;font-size:0.8rem;margin-bottom:0.2rem;">
       <span style="font-family:ui-monospace,monospace;">{{ mount }}</span>
-      <span style="color:var(--text-muted);">{{ fmt_bytes(m.get('disk_used_bytes')) }} / {{ fmt_bytes(m.get('disk_total_bytes')) }}{% if m.get('disk_used_pct') is not none %} · {{ "%.0f"|format(m.get('disk_used_pct')) }}%{% endif %}</span>
+      <span style="color:var(--text-muted);">{{ m.get('disk_used_bytes')|bytes }} / {{ m.get('disk_total_bytes')|bytes }}{% if m.get('disk_used_pct') is not none %} · {{ "%.0f"|format(m.get('disk_used_pct')) }}%{% endif %}</span>
     </div>
     {{ bar(m.get('disk_used_pct')) }}
   </div>
@@ -145,7 +128,7 @@
     {% for iface, m in nets.items() %}
     <div style="display:flex;justify-content:space-between;gap:0.75rem;font-size:0.8rem;padding:0.15rem 0;">
       <span style="font-family:ui-monospace,monospace;">{{ iface }}</span>
-      <span style="color:var(--text-muted);font-variant-numeric:tabular-nums;white-space:nowrap;">↓ {{ fmt_bps(m.get('net_rx_bps')) }} · ↑ {{ fmt_bps(m.get('net_tx_bps')) }}</span>
+      <span style="color:var(--text-muted);font-variant-numeric:tabular-nums;white-space:nowrap;">↓ {{ m.get('net_rx_bps')|rate }} · ↑ {{ m.get('net_tx_bps')|rate }}</span>
     </div>
     {% endfor %}
   </div>
@@ -156,7 +139,7 @@
     {% for dev, m in disks_io.items() %}
     <div style="display:flex;justify-content:space-between;gap:0.75rem;font-size:0.8rem;padding:0.15rem 0;">
       <span style="font-family:ui-monospace,monospace;">{{ dev }}</span>
-      <span style="color:var(--text-muted);font-variant-numeric:tabular-nums;white-space:nowrap;">rd {{ fmt_bps(m.get('disk_read_bps')) }} · wr {{ fmt_bps(m.get('disk_write_bps')) }}</span>
+      <span style="color:var(--text-muted);font-variant-numeric:tabular-nums;white-space:nowrap;">rd {{ m.get('disk_read_bps')|rate }} · wr {{ m.get('disk_write_bps')|rate }}</span>
     </div>
     {% endfor %}
   </div>

plugins/host_agent/templates/install.sh.j2

@@ -45,6 +45,10 @@ cat > "$CONF_FILE" <<EOF
 url = $STEWARD_URL
 token = $AGENT_TOKEN
 interval_seconds = 30
+# Container logs are collected by default. To opt this host out entirely:
+#   docker_logs_enabled = false
+# To skip specific noisy containers (comma-separated names):
+#   docker_log_exclude = watchtower, some-chatty-service
 EOF
 chown "root:$AGENT_USER" "$CONF_FILE"
 chmod 0640 "$CONF_FILE"

plugins/host_agent/templates/panel.html

@@ -20,17 +20,17 @@
     <a href="/plugins/host_agent/{{ host.id }}/" class="btn btn-sm btn-ghost">Full metrics →</a>
     {% if session.user_role == 'admin' %}
     {% if ansible_available and target %}
-    <form method="post" action="/plugins/host_agent/update" style="margin:0;">
+    <form method="post" action="/plugins/host_agent/update" style="margin:0;">{{ csrf_field() }}
       <input type="hidden" name="inventory_scope" value="{{ scope }}">
       <button type="submit" class="btn btn-sm" title="Refresh agent.py + restart (token preserved)">Update agent</button>
     </form>
     {% endif %}
     <form method="post" action="/plugins/host_agent/fleet/{{ host.id }}/rotate-token" style="margin:0;"
-          onsubmit="return confirm('Rotate token? The agent stops reporting until reinstalled/updated with the new token.');">
+          data-confirm="Rotate token? The agent stops reporting until reinstalled/updated with the new token.">{{ csrf_field() }}
       <button type="submit" class="btn btn-sm btn-ghost">Rotate token</button>
     </form>
     <form method="post" action="/plugins/host_agent/fleet/{{ host.id }}/delete" style="margin:0;"
-          onsubmit="return confirm('Remove this agent registration? Metrics stop until re-registered.');">
+          data-confirm="Remove this agent registration? Metrics stop until re-registered.">{{ csrf_field() }}
       <button type="submit" class="btn btn-sm btn-danger">Remove</button>
     </form>
     {% endif %}
@@ -49,7 +49,7 @@
       Connects over a one-time bootstrap user + password (not stored).
     </p>
     <form method="post" action="/plugins/host_agent/provision"
-          style="display:flex;gap:0.6rem;align-items:flex-end;flex-wrap:wrap;">
+          style="display:flex;gap:0.6rem;align-items:flex-end;flex-wrap:wrap;">{{ csrf_field() }}
       <input type="hidden" name="inventory_scope" value="{{ scope }}">
       <div class="form-group" style="margin:0;">
         <label>Bootstrap user</label>
@@ -96,7 +96,7 @@
               border-radius:6px;padding:0.7rem 0.9rem;display:flex;align-items:center;gap:0.8rem;flex-wrap:wrap;">
     <span style="color:var(--yellow);">⚠</span>
     <span style="font-size:0.84rem;flex:1;min-width:13rem;">No managed SSH key yet — Steward needs one to log into hosts.</span>
-    <form method="post" action="/settings/ansible/generate-key" style="margin:0;">
+    <form method="post" action="/settings/ansible/generate-key" style="margin:0;">{{ csrf_field() }}
       <input type="hidden" name="next" value="/hosts/{{ host.id }}">
       <button type="submit" class="btn btn-sm">Generate managed key</button>
     </form>
@@ -115,7 +115,7 @@
   </p>
   {# Provision: brand-new host (creates steward account + key over a one-time password) #}
   <form method="post" action="/plugins/host_agent/provision"
-        style="display:flex;gap:0.6rem;align-items:flex-end;flex-wrap:wrap;margin-bottom:0.75rem;">
+        style="display:flex;gap:0.6rem;align-items:flex-end;flex-wrap:wrap;margin-bottom:0.75rem;">{{ csrf_field() }}
     <input type="hidden" name="inventory_scope" value="{{ scope }}">
     <div style="font-size:0.78rem;color:var(--text-muted);width:100%;">Provision (first contact — fresh host):</div>
     <div class="form-group" style="margin:0;">
@@ -129,7 +129,7 @@
     <button type="submit" class="btn btn-sm">Provision</button>
   </form>
   {# Install: host already has the steward account (managed key works) #}
-  <form method="post" action="/plugins/host_agent/deploy" style="display:flex;gap:0.6rem;align-items:center;">
+  <form method="post" action="/plugins/host_agent/deploy" style="display:flex;gap:0.6rem;align-items:center;">{{ csrf_field() }}
     <input type="hidden" name="inventory_scope" value="{{ scope }}">
     <span style="font-size:0.78rem;color:var(--text-muted);">Already provisioned?</span>
     <button type="submit" class="btn btn-sm btn-ghost">Install agent (managed key)</button>
@@ -138,7 +138,7 @@
 
   {% if reg and session.user_role == 'admin' %}
   <form method="post" action="/plugins/host_agent/fleet/{{ host.id }}/delete" style="margin:0.75rem 0 0;"
-        onsubmit="return confirm('Clear this pending registration? Its token is discarded.');">
+        data-confirm="Clear this pending registration? Its token is discarded.">{{ csrf_field() }}
     <button type="submit" class="btn btn-sm btn-ghost">Clear pending registration</button>
   </form>
   {% endif %}

plugins/host_agent/templates/settings_list.html

@@ -12,7 +12,7 @@
 </p>
 
 {% if new_token %}
-<div class="card" style="background:var(--accent-bg);">
+<div class="card" style="background:var(--fs-accent-faint);">
   <h3>New token — copy this install command now</h3>
   <p style="font-size:0.82rem;color:var(--text-muted);">
     This is the only time the raw token is shown. Rotate if you lose it.
@@ -23,7 +23,7 @@
 
 <div class="card">
   <form method="post" action="/plugins/host_agent/fleet/add-host"
-        style="display:flex;gap:0.75rem;align-items:flex-end;flex-wrap:wrap;">
+        style="display:flex;gap:0.75rem;align-items:flex-end;flex-wrap:wrap;">{{ csrf_field() }}
     <div class="form-group" style="margin-bottom:0;">
       <label>Host name</label>
       <input type="text" name="name" required>
@@ -63,7 +63,7 @@
     <span style="font-size:0.84rem;flex:1;min-width:14rem;">
       No managed SSH key yet — Steward needs one to log into hosts as <code>steward</code>.
     </span>
-    <form method="post" action="/settings/ansible/generate-key" style="margin:0;">
+    <form method="post" action="/settings/ansible/generate-key" style="margin:0;">{{ csrf_field() }}
       <input type="hidden" name="next" value="/plugins/host_agent/fleet/">
       <button type="submit" class="btn btn-sm">Generate managed key</button>
     </form>
@@ -85,7 +85,7 @@
     agent. Run this once per host.
   </p>
   <form method="post" action="/plugins/host_agent/provision"
-        style="display:flex;gap:0.75rem;align-items:flex-end;flex-wrap:wrap;">
+        style="display:flex;gap:0.75rem;align-items:flex-end;flex-wrap:wrap;">{{ csrf_field() }}
     <div class="form-group" style="margin-bottom:0;">{{ scope_select }}</div>
     <div class="form-group" style="margin-bottom:0;">
       <label>Bootstrap user</label>
@@ -111,7 +111,7 @@
     mints a fresh token, and installs the agent. No <code>curl | sh</code> needed.
   </p>
   <form method="post" action="/plugins/host_agent/deploy"
-        style="display:flex;gap:0.75rem;align-items:flex-end;flex-wrap:wrap;">
+        style="display:flex;gap:0.75rem;align-items:flex-end;flex-wrap:wrap;">{{ csrf_field() }}
     <div class="form-group" style="margin-bottom:0;">{{ scope_select }}</div>
     <div class="form-group" style="margin-bottom:0;">
       <label>Report interval (s)</label>
@@ -129,7 +129,7 @@
     so identity is preserved.
   </p>
   <form method="post" action="/plugins/host_agent/update"
-        style="display:flex;gap:0.75rem;align-items:flex-end;flex-wrap:wrap;">
+        style="display:flex;gap:0.75rem;align-items:flex-end;flex-wrap:wrap;">{{ csrf_field() }}
     <div class="form-group" style="margin-bottom:0;">{{ scope_select }}</div>
     <button type="submit" class="btn">Update</button>
   </form>
@@ -156,12 +156,12 @@
         <td class="td-actions">
           <form method="post" action="/plugins/host_agent/fleet/{{ item.reg.host_id }}/rotate-token"
                 style="display:inline;"
-                onsubmit="return confirm('Rotate the token for this host? The existing agent will stop working until reinstalled with the new token.');">
+                data-confirm="Rotate the token for this host? The existing agent will stop working until reinstalled with the new token.">{{ csrf_field() }}
             <button type="submit" class="btn btn-ghost btn-sm">Rotate token</button>
           </form>
           <form method="post" action="/plugins/host_agent/fleet/{{ item.reg.host_id }}/delete"
                 style="display:inline;"
-                onsubmit="return confirm('Delete this host registration? The agent will be unable to report metrics until re-registered.');">
+                data-confirm="Delete this host registration? The agent will be unable to report metrics until re-registered.">{{ csrf_field() }}
             <button type="submit" class="btn btn-danger btn-sm">Delete</button>
           </form>
         </td>

plugins/host_agent/templates/widget_history.html

@@ -22,7 +22,7 @@
     {% endif %}
     <span class="hist-range" style="margin-left:auto;display:inline-flex;border:1px solid var(--border-mid);border-radius:5px;overflow:hidden;">
       {% for opt in [1, 6, 24] %}
-      <button type="button" onclick="histRange({{ wid }}, '{{ host.id }}', {{ opt }})"
+      <button type="button" onclick="histRange({{ wid|int }}, {{ opt|int }})"
         style="border:0;cursor:pointer;padding:0.1rem 0.45rem;font-size:0.72rem;
                background:{% if opt == hours %}var(--accent){% else %}transparent{% endif %};
                color:{% if opt == hours %}#fff{% else %}var(--text-muted){% endif %};">{{ opt }}h</button>
@@ -36,11 +36,15 @@
 <script>
 // Live time-range switch. Rewrites the parent cell's hx-get so the choice sticks
 // across polls (htmx re-reads the attribute each poll), then fetches immediately.
-window.histRange = function (wid, hostId, hours) {
+// Only `hours` changes: the rest of the query (host, widget id, a share link's
+// token) is kept, so the switch also works on a shared dashboard.
+window.histRange = function (wid, hours) {
   var cell = document.getElementById("widget-" + wid);
   if (!cell) return;
-  var base = (cell.getAttribute("hx-get") || "").split("?")[0];
-  var url = base + "?host_id=" + encodeURIComponent(hostId) + "&hours=" + hours + "&wid=" + wid;
+  var parts = (cell.getAttribute("hx-get") || "").split("?");
+  var query = new URLSearchParams(parts[1] || "");
+  query.set("hours", hours);
+  var url = parts[0] + "?" + query.toString();
   cell.setAttribute("hx-get", url);
   if (window.htmx) window.htmx.ajax("GET", url, { target: cell, swap: "innerHTML" });
 };

plugins/host_agent/templates/widget_table.html

@@ -13,21 +13,13 @@
   <div style="line-height:0;height:16px;">{{ svg | safe }}</div>
 </div>
 {% endmacro %}
-{# Human-readable throughput, matching the host-detail page. #}
-{% macro fmt_bps(v) %}
-{%- if v is none -%}—
-{%- elif v >= 1048576 -%}{{ "%.1f"|format(v / 1048576) }} MB/s
-{%- elif v >= 1024 -%}{{ "%.1f"|format(v / 1024) }} KB/s
-{%- else -%}{{ "%.0f"|format(v) }} B/s
-{%- endif -%}
-{% endmacro %}
 {# Two-line down/up (or read/write) throughput cell. #}
 {% macro io_cell(label, down_sym, down_val, up_sym, up_val, title="") %}
 <div style="min-width:80px;flex:0 0 auto;" title="{{ title }}">
   <div style="font-size:0.62rem;color:var(--text-dim);text-transform:uppercase;letter-spacing:0.03em;">{{ label }}</div>
   <div style="font-size:0.72rem;font-variant-numeric:tabular-nums;line-height:1.3;">
-    <div>{{ down_sym }} {{ fmt_bps(down_val) }}</div>
-    <div>{{ up_sym }} {{ fmt_bps(up_val) }}</div>
+    <div>{{ down_sym }} {{ down_val|rate }}</div>
+    <div>{{ up_sym }} {{ up_val|rate }}</div>
   </div>
 </div>
 {% endmacro %}

plugins/snmp/__init__.py

@@ -26,3 +26,9 @@ def get_blueprint():
 def get_nav() -> list[dict]:
     # Surfaces in the sidebar's Infrastructure group (SNMP device readings).
     return [{"label": "SNMP", "href": "/plugins/snmp/"}]
+
+
+def get_alert_metrics() -> dict[str, list[str]]:
+    """SNMP metric names are the OID labels each device is configured with, so
+    the list is empty here and the rule form offers the labels recorded so far."""
+    return {"snmp": []}

plugins/snmp/scheduler.py

@@ -27,7 +27,7 @@ def make_poll_task(app: "Quart") -> ScheduledTask:
 
 async def _do_poll(app: "Quart") -> None:
     from .poller import poll_device
-    from steward.core.alerts import record_metric
+    from steward.core.alerts import MetricBatch
 
     devices: list[dict] = app.config["PLUGINS"]["snmp"].get("devices", [])
     if not devices:
@@ -35,6 +35,7 @@ async def _do_poll(app: "Quart") -> None:
 
     async with app.db_sessionmaker() as session:
         async with session.begin():
+            batch = MetricBatch()
             for device in devices:
                 if not isinstance(device, dict):
                     continue
@@ -55,8 +56,7 @@ async def _do_poll(app: "Quart") -> None:
                     continue
 
                 for label, value in readings.items():
-                    await record_metric(
-                        session=session,
+                    batch.add(
                         source_module="snmp",
                         resource_name=name,
                         metric_name=label,
@@ -67,3 +67,4 @@ async def _do_poll(app: "Quart") -> None:
                     logger.debug("SNMP polled %s (%s): %d OID(s)", name, host, len(readings))
                 else:
                     logger.debug("SNMP polled %s (%s): no readings", name, host)
+            await batch.record(session)

plugins/snmp/templates/snmp/index.html

@@ -31,7 +31,7 @@
     {% for oid_cfg in device.oids %}
     {% set label = oid_cfg.label if oid_cfg.label else oid_cfg.oid %}
     {% set val = device.readings.get(label) %}
-    <div style="background:var(--bg-alt);border-radius:6px;padding:0.6rem 0.9rem;">
+    <div style="background:var(--bg-elevated);border-radius:6px;padding:0.6rem 0.9rem;">
       <div style="font-size:0.72rem;color:var(--text-dim);margin-bottom:0.2rem;font-family:monospace;">{{ label }}</div>
       {% if val is not none %}
       <div style="font-size:1.1rem;font-weight:600;font-variant-numeric:tabular-nums;">

plugins/snmp/templates/snmp/widget.html

@@ -36,7 +36,7 @@
   {% endif %}
 </div>
 {% if not loop.last %}
-<div style="height:1px;background:var(--border-low);margin:0.1rem 0;"></div>
+<div style="height:1px;background:var(--border);margin:0.1rem 0;"></div>
 {% endif %}
 {% endfor %}
 {% if total > devices|length %}

plugins/traefik/__init__.py

@@ -33,3 +33,11 @@ def get_blueprint():
 def get_nav() -> list[dict]:
     # Surfaces in the sidebar's Infrastructure group (Traefik services view).
     return [{"label": "Traefik", "href": "/plugins/traefik/"}]
+
+
+def get_alert_metrics() -> dict[str, list[str]]:
+    """What scheduler.py records for alert rules: per router (resource = the
+    router name) and cert_expiry_days per certificate (resource = its CN)."""
+    return {"traefik": ["request_rate", "error_rate_4xx_pct", "error_rate_5xx_pct",
+                        "latency_p50_ms", "latency_p95_ms", "latency_p99_ms",
+                        "response_bytes_rate", "cert_expiry_days"]}

plugins/traefik/scheduler.py

@@ -48,7 +48,7 @@ async def _do_scrape(app: "Quart") -> None:
         extract_certs,
         fetch_metrics,
     )
-    from steward.core.alerts import record_metric
+    from steward.core.alerts import MetricBatch
 
     metrics_url: str = app.config["PLUGINS"]["traefik"]["metrics_url"]
 
@@ -71,6 +71,7 @@ async def _do_scrape(app: "Quart") -> None:
 
     async with app.db_sessionmaker() as session:
         async with session.begin():
+            batch = MetricBatch()
             # ── Per-service metrics ───────────────────────────────────────────
             for router_name, metrics in router_metrics.items():
                 row = TraefikMetric(
@@ -95,8 +96,7 @@ async def _do_scrape(app: "Quart") -> None:
                     ("latency_p99_ms", metrics["latency_p99_ms"]),
                     ("response_bytes_rate", metrics["response_bytes_rate"]),
                 ]:
-                    await record_metric(
-                        session=session,
+                    batch.add(
                         source_module="traefik",
                         resource_name=router_name,
                         metric_name=metric_name,
@@ -125,14 +125,15 @@ async def _do_scrape(app: "Quart") -> None:
 
                 # Emit cert_expiry_days for alert rules
                 days_remaining = (cert["not_after"] - scraped_at).total_seconds() / 86400.0
-                await record_metric(
-                    session=session,
+                batch.add(
                     source_module="traefik",
                     resource_name=cert["cn"] or cert["serial"],
                     metric_name="cert_expiry_days",
                     value=max(0.0, days_remaining),
                 )
 
+            await batch.record(session)
+
     logger.debug(
         "Traefik scrape: %d router(s), %d cert(s)",
         len(router_metrics),

plugins/traefik/templates/traefik/rows.html

@@ -2,7 +2,7 @@
 
 {# ── Global stats bar ──────────────────────────────────────────────────────── #}
 {% if global_stat %}
-<div style="display:flex;flex-wrap:wrap;gap:1.5rem;margin-bottom:1.25rem;padding:0.75rem 1rem;background:var(--card-bg);border:1px solid var(--border);border-radius:6px;font-size:0.85rem;font-variant-numeric:tabular-nums;">
+<div style="display:flex;flex-wrap:wrap;gap:1.5rem;margin-bottom:1.25rem;padding:0.75rem 1rem;background:var(--bg-card);border:1px solid var(--border);border-radius:6px;font-size:0.85rem;font-variant-numeric:tabular-nums;">
 
   {% if global_stat.open_conns_total is not none %}
   <span>
@@ -28,9 +28,8 @@
   {% if global_stat.process_memory_bytes is not none %}
   <span>
     <span style="color:var(--text-muted);">Memory</span>
-    {% set mb = (global_stat.process_memory_bytes / 1048576) %}
     <span style="margin-left:0.4rem;">
-      {% if mb >= 1024 %}{{ "%.1f"|format(mb / 1024) }} GB{% else %}{{ "%.0f"|format(mb) }} MB{% endif %}
+      {{ global_stat.process_memory_bytes|bytes }}
     </span>
   </span>
   {% endif %}
@@ -58,9 +57,7 @@
             <td style="color:var(--text-muted);padding:0.2rem 0;">Bandwidth</td>
             <td style="padding:0.2rem 0.5rem;">
               {% set bps = r.latest.response_bytes_rate %}
-              {% if bps >= 1048576 %}{{ "%.1f"|format(bps / 1048576) }} MB/s
-              {% elif bps >= 1024 %}{{ "%.1f"|format(bps / 1024) }} KB/s
-              {% else %}{{ "%.0f"|format(bps) }} B/s{% endif %}
+              {{ bps|rate }}
             </td>
             <td style="padding:0.2rem 0;"></td>
         </tr>
@@ -122,6 +119,6 @@
 </div>
 {% else %}
 <div class="card">
-    <p style="color:#606080;">No Traefik metrics yet. Configure <code>metrics_url</code> in <code>config.yaml</code> under <code>plugins.traefik</code>.</p>
+    <p style="color:var(--text-dim);">No Traefik metrics yet. Configure <code>metrics_url</code> in <code>config.yaml</code> under <code>plugins.traefik</code>.</p>
 </div>
 {% endif %}

plugins/traefik/templates/traefik/traffic.html

@@ -2,7 +2,7 @@
 {% if summary %}
 
 {# ── Overview bar ─────────────────────────────────────────────────────────── #}
-<div style="display:flex;flex-wrap:wrap;gap:1.5rem;margin-bottom:1.25rem;padding:0.75rem 1rem;background:var(--card-bg);border:1px solid var(--border);border-radius:6px;font-size:0.85rem;font-variant-numeric:tabular-nums;align-items:center;">
+<div style="display:flex;flex-wrap:wrap;gap:1.5rem;margin-bottom:1.25rem;padding:0.75rem 1rem;background:var(--bg-card);border:1px solid var(--border);border-radius:6px;font-size:0.85rem;font-variant-numeric:tabular-nums;align-items:center;">
   <span>
     <span style="color:var(--text-muted);">Total</span>
     <span style="margin-left:0.4rem;font-weight:600;">{{ summary.total }}</span>
@@ -20,8 +20,7 @@
   <span>
     <span style="color:var(--text-muted);">Bytes</span>
     <span style="margin-left:0.4rem;">
-      {% set mb = summary.total_bytes / 1048576 %}
-      {% if mb >= 1024 %}{{ "%.1f"|format(mb / 1024) }} GB{% else %}{{ "%.1f"|format(mb) }} MB{% endif %}
+      {{ summary.total_bytes|bytes }}
     </span>
   </span>
 

plugins/traefik/templates/traefik/widget.html

@@ -26,9 +26,7 @@
       <span style="color:var(--text-muted);">bw</span>
       <span style="margin-left:0.3rem;">
         {% set bps = r.latest.response_bytes_rate %}
-        {% if bps >= 1048576 %}{{ "%.1f"|format(bps / 1048576) }}MB/s
-        {% elif bps >= 1024 %}{{ "%.0f"|format(bps / 1024) }}KB/s
-        {% else %}{{ "%.0f"|format(bps) }}B/s{% endif %}
+        {{ bps|rate }}
       </span>
     </span>
     <span title="p95 latency">

plugins/unifi/__init__.py

@@ -31,3 +31,9 @@ def get_blueprint():
 def get_nav() -> list[dict]:
     # Surfaces in the sidebar's Infrastructure group (UniFi network overview).
     return [{"label": "UniFi", "href": "/plugins/unifi/"}]
+
+
+def get_alert_metrics() -> dict[str, list[str]]:
+    """What scheduler.py records: the WAN (resource "wan") and the client count
+    (resource "clients")."""
+    return {"unifi": ["is_up", "latency_ms", "total_clients"]}

plugins/unifi/scheduler.py

@@ -54,7 +54,7 @@ async def _do_poll(app: "Quart") -> None:
 
     from .client import UnifiClient
     from .models import UnifiClientSnapshot, UnifiDevice, UnifiWanStat
-    from steward.core.alerts import record_metric
+    from steward.core.alerts import MetricBatch
 
     cfg = app.config["PLUGINS"]["unifi"]
 
@@ -171,28 +171,27 @@ async def _do_poll(app: "Quart") -> None:
                     ))
 
             # ── Alert metrics ─────────────────────────────────────────────────
+            batch = MetricBatch()
             if wan_stat.latency_ms is not None:
-                await record_metric(
-                    session=session,
+                batch.add(
                     source_module="unifi",
                     resource_name="wan",
                     metric_name="latency_ms",
                     value=wan_stat.latency_ms,
                 )
-            await record_metric(
-                session=session,
+            batch.add(
                 source_module="unifi",
                 resource_name="wan",
                 metric_name="is_up",
                 value=1.0 if wan_stat.is_up else 0.0,
             )
-            await record_metric(
-                session=session,
+            batch.add(
                 source_module="unifi",
                 resource_name="clients",
                 metric_name="total_clients",
                 value=float(len(clients)),
             )
+            await batch.record(session)
 
     logger.debug(
         "UniFi poll: wan=%s, clients=%d, devices=%d",

plugins/unifi/templates/unifi/dpi.html

@@ -21,10 +21,7 @@
       <tr>
         <td style="padding:0.25rem 0.5rem 0.25rem 0;">{{ cat.cat_name or cat.cat_id }}</td>
         <td style="padding:0.25rem 0.3rem;text-align:right;color:var(--text-muted);font-size:0.78rem;white-space:nowrap;">
-          {% if bytes >= 1073741824 %}{{ "%.1f"|format(bytes / 1073741824) }} GB
-          {% elif bytes >= 1048576 %}{{ "%.1f"|format(bytes / 1048576) }} MB
-          {% elif bytes >= 1024 %}{{ "%.0f"|format(bytes / 1024) }} KB
-          {% else %}{{ bytes }} B{% endif %}
+          {{ bytes|bytes }}
         </td>
         <td style="padding:0.25rem 0;width:4rem;">
           <div style="background:var(--border);border-radius:2px;height:6px;overflow:hidden;">
@@ -50,10 +47,7 @@
         </td>
         <td style="padding:0.25rem 0;text-align:right;font-size:0.78rem;color:var(--text-muted);white-space:nowrap;">
           {% set bytes = c.bytes %}
-          {% if bytes >= 1073741824 %}{{ "%.1f"|format(bytes / 1073741824) }} GB
-          {% elif bytes >= 1048576 %}{{ "%.1f"|format(bytes / 1048576) }} MB
-          {% elif bytes >= 1024 %}{{ "%.0f"|format(bytes / 1024) }} KB
-          {% else %}{{ bytes }} B{% endif %}
+          {{ bytes|bytes }}
         </td>
       </tr>
       {% endfor %}

plugins/unifi/templates/unifi/events.html

@@ -23,7 +23,7 @@
       <th style="text-align:left;font-weight:normal;padding:0 0 0.4rem;">Message</th>
     </tr>
     {% for ev in events %}
-    <tr style="{% if loop.index is divisibleby 2 %}background:var(--row-alt,rgba(255,255,255,0.02));{% endif %}">
+    <tr style="{% if loop.index is divisibleby 2 %}background:var(--fs-table-stripe);{% endif %}">
       <td style="padding:0.25rem 0.5rem 0.25rem 0;color:var(--text-dim);font-size:0.77rem;white-space:nowrap;">
         {{ ev.event_time.strftime("%Y-%m-%d %H:%M:%S") }}
       </td>

plugins/unifi/templates/unifi/rows.html

@@ -2,7 +2,7 @@
 
 {# ── WAN health bar ───────────────────────────────────────────────────────── #}
 {% if latest_wan %}
-<div style="display:flex;flex-wrap:wrap;gap:1.5rem;margin-bottom:1.25rem;padding:0.75rem 1rem;background:var(--card-bg);border:1px solid var(--border);border-radius:6px;font-size:0.85rem;font-variant-numeric:tabular-nums;align-items:center;">
+<div style="display:flex;flex-wrap:wrap;gap:1.5rem;margin-bottom:1.25rem;padding:0.75rem 1rem;background:var(--bg-card);border:1px solid var(--border);border-radius:6px;font-size:0.85rem;font-variant-numeric:tabular-nums;align-items:center;">
   <span>
     <span style="color:var(--text-muted);">WAN</span>
     <span style="margin-left:0.4rem;font-weight:600;color:{% if latest_wan.is_up %}var(--green){% else %}var(--red){% endif %};">
@@ -29,9 +29,7 @@
     <span style="color:var(--text-muted);">&#8595; RX</span>
     <span style="margin-left:0.3rem;">
       {% set bps = latest_wan.rx_bytes_rate %}
-      {% if bps >= 1048576 %}{{ "%.1f"|format(bps / 1048576) }} MB/s
-      {% elif bps >= 1024 %}{{ "%.0f"|format(bps / 1024) }} KB/s
-      {% else %}{{ "%.0f"|format(bps) }} B/s{% endif %}
+      {{ bps|rate }}
     </span>
     <span style="margin-left:0.3rem;">{{ sparkline_rx | safe }}</span>
   </span>
@@ -39,9 +37,7 @@
     <span style="color:var(--text-muted);">&#8593; TX</span>
     <span style="margin-left:0.3rem;">
       {% set bps = latest_wan.tx_bytes_rate %}
-      {% if bps >= 1048576 %}{{ "%.1f"|format(bps / 1048576) }} MB/s
-      {% elif bps >= 1024 %}{{ "%.0f"|format(bps / 1024) }} KB/s
-      {% else %}{{ "%.0f"|format(bps) }} B/s{% endif %}
+      {{ bps|rate }}
     </span>
     <span style="margin-left:0.3rem;">{{ sparkline_tx | safe }}</span>
   </span>
@@ -49,7 +45,7 @@
 
   {% if latest_wan.uptime_seconds is not none %}
   <span style="color:var(--text-dim);font-size:0.8rem;">
-    up {{ (latest_wan.uptime_seconds // 3600) }}h {{ ((latest_wan.uptime_seconds % 3600) // 60) }}m
+    up {{ latest_wan.uptime_seconds|duration }}
   </span>
   {% endif %}
 </div>
@@ -96,7 +92,7 @@
       {% if d.state == 1 and d.uptime_seconds %}
       <tr>
         <td colspan="3" style="padding:0 0 0.3rem 1.2rem;color:var(--text-dim);font-size:0.75rem;">
-          up {{ (d.uptime_seconds // 86400) }}d {{ ((d.uptime_seconds % 86400) // 3600) }}h
+          up {{ d.uptime_seconds|duration }}
         </td>
       </tr>
       {% endif %}
@@ -121,13 +117,9 @@
         <td style="text-align:right;padding:0.2rem 0;white-space:nowrap;font-size:0.78rem;">
           {% set rx = c.rx_rate %}{% set tx = c.tx_rate %}
           <span style="color:var(--text-muted);">&#8595;</span>
-          {% if rx >= 1048576 %}{{ "%.1f"|format(rx/1048576) }}M
-          {% elif rx >= 1024 %}{{ "%.0f"|format(rx/1024) }}K
-          {% else %}{{ "%.0f"|format(rx) }}B{% endif %}
+          {{ rx|rate }}
           <span style="color:var(--text-muted);margin-left:0.3rem;">&#8593;</span>
-          {% if tx >= 1048576 %}{{ "%.1f"|format(tx/1048576) }}M
-          {% elif tx >= 1024 %}{{ "%.0f"|format(tx/1024) }}K
-          {% else %}{{ "%.0f"|format(tx) }}B{% endif %}
+          {{ tx|rate }}
         </td>
       </tr>
       {% endfor %}

plugins/unifi/templates/unifi/widget.html

@@ -37,16 +37,12 @@
     <span>
       <span style="color:var(--text-muted);">&#8595;</span>
       {% set bps = latest_wan.rx_bytes_rate %}
-      {% if bps >= 1048576 %}{{ "%.1f"|format(bps / 1048576) }}MB/s
-      {% elif bps >= 1024 %}{{ "%.0f"|format(bps / 1024) }}KB/s
-      {% else %}{{ "%.0f"|format(bps) }}B/s{% endif %}
+      {{ bps|rate }}
     </span>
     <span>
       <span style="color:var(--text-muted);">&#8593;</span>
       {% set bps = latest_wan.tx_bytes_rate %}
-      {% if bps >= 1048576 %}{{ "%.1f"|format(bps / 1048576) }}MB/s
-      {% elif bps >= 1024 %}{{ "%.0f"|format(bps / 1024) }}KB/s
-      {% else %}{{ "%.0f"|format(bps) }}B/s{% endif %}
+      {{ bps|rate }}
     </span>
     {% endif %}
   </div>
@@ -76,14 +72,10 @@
       {% set total_bps = c.tx_rate + c.rx_rate %}
       <span style="color:var(--text-muted);">&#8595;</span>
       {% set rx = c.rx_rate %}
-      {% if rx >= 1048576 %}{{ "%.1f"|format(rx / 1048576) }}M
-      {% elif rx >= 1024 %}{{ "%.0f"|format(rx / 1024) }}K
-      {% else %}{{ "%.0f"|format(rx) }}B{% endif %}
+      {{ rx|rate }}
       <span style="color:var(--text-muted);margin-left:0.4rem;">&#8593;</span>
       {% set tx = c.tx_rate %}
-      {% if tx >= 1048576 %}{{ "%.1f"|format(tx / 1048576) }}M
-      {% elif tx >= 1024 %}{{ "%.0f"|format(tx / 1024) }}K
-      {% else %}{{ "%.0f"|format(tx) }}B{% endif %}
+      {{ tx|rate }}
     </div>
   </div>
   {% endfor %}

pyproject.toml

@@ -18,6 +18,9 @@ dependencies = [
     "click>=8.0",
     "httpx>=0.27",
     "cryptography>=42",
+    # Floor, not a cap: MCPServer (mcp.server.mcpserver) and the mcp.types
+    # mirror that steward/mcp/ is written against first ship in SDK 2.2.
+    "mcp>=2.2",
 ]
 
 [project.optional-dependencies]

steward/ai_access/routes.py

@@ -0,0 +1,108 @@
+"""AI access: personal API tokens for MCP clients.
+
+Every logged-in user manages their own tokens here, whatever their role — a
+token acts as its user, capped at the role it was given. These routes are
+session-only: a share-link viewer has no user to mint tokens for, and no token
+can reach them (MCP tools never mint or revoke tokens).
+"""
+from __future__ import annotations
+from datetime import datetime, timezone
+
+from quart import Blueprint, abort, current_app, redirect, render_template, request
+from sqlalchemy import select
+
+from steward.auth.middleware import current_user_id, require_role
+from steward.core import api_tokens
+from steward.core.audit import log_audit
+from steward.core.settings import public_base_url
+from steward.mcp.server import MCP_PATH
+from steward.models.users import User, UserRole
+
+ai_access_bp = Blueprint("ai_access", __name__, url_prefix="/ai-access")
+
+_EXPIRY_CHOICES = [("", "Never"), ("30", "30 days"), ("90", "90 days"), ("365", "1 year")]
+
+
+def _mcp_url() -> str:
+    """The /mcp endpoint as a client outside this request reaches it."""
+    return public_base_url(request) + MCP_PATH
+
+
+async def _session_user(db) -> User:
+    user_id = current_user_id()
+    if not user_id:
+        abort(403)
+    user = (await db.execute(select(User).where(User.id == user_id))).scalar_one_or_none()
+    if user is None or not user.is_active:
+        abort(403)
+    return user
+
+
+async def _render_index(db, user: User, *, error: str | None = None, status: int = 200):
+    tokens = await api_tokens.list_tokens(db, user.id)
+    now = datetime.now(timezone.utc)
+    rows = [{"token": t, "state": api_tokens.token_state(t, now)} for t in tokens]
+    body = await render_template(
+        "ai_access/index.html",
+        rows=rows,
+        user_role=user.role,
+        grantable=api_tokens.grantable_roles(user.role),
+        expiry_choices=_EXPIRY_CHOICES,
+        error=error,
+        mcp_url=_mcp_url(),
+    )
+    return body, status
+
+
+@ai_access_bp.get("/")
+@require_role(UserRole.viewer)
+async def index():
+    async with current_app.db_sessionmaker() as db:
+        user = await _session_user(db)
+        return await _render_index(db, user)
+
+
+@ai_access_bp.post("/tokens")
+@require_role(UserRole.viewer)
+async def create():
+    form = await request.form
+    name = form.get("name", "")
+    expires = form.get("expires_in_days", "")
+    try:
+        role = UserRole(form.get("role", UserRole.viewer.value))
+    except ValueError:
+        role = None
+
+    async with current_app.db_sessionmaker() as db:
+        user = await _session_user(db)
+        if role is None:
+            return await _render_index(db, user, error="Pick a role for the token.", status=400)
+        try:
+            raw, token = await api_tokens.create_token(
+                db, user_id=user.id, user_role=user.role, name=name, role=role,
+                expires_in_days=int(expires) if expires.isdigit() and int(expires) > 0 else None,
+            )
+        except ValueError as exc:
+            return await _render_index(db, user, error=str(exc), status=400)
+        await db.commit()
+
+    await log_audit(current_app, user.id, user.username, "api_token.create",
+                    entity_type="api_token", entity_id=str(token.id),
+                    detail={"name": token.name, "role": token.role.value})
+    return await render_template("ai_access/created.html", raw_token=raw, token=token,
+                                 mcp_url=_mcp_url())
+
+
+@ai_access_bp.post("/tokens/<int:token_id>/revoke")
+@require_role(UserRole.viewer)
+async def revoke(token_id: int):
+    async with current_app.db_sessionmaker() as db:
+        user = await _session_user(db)
+        token = await api_tokens.revoke_token(db, user_id=user.id, token_id=token_id)
+        await db.commit()
+    if token is None:
+        abort(404)
+    await log_audit(current_app, user.id, user.username, "api_token.revoke",
+                    entity_type="api_token", entity_id=str(token_id),
+                    detail={"name": token.name})
+    return redirect("/ai-access/")

steward/alerts/routes.py

@@ -4,64 +4,37 @@ from quart import Blueprint, render_template, request, redirect, url_for, curren
 from steward.core.audit import log_audit
 from sqlalchemy import select
 from steward.auth.middleware import require_role
+from steward.alerts import service as alert_svc
+from steward.core.time_range import parse_range
 from steward.ansible import sources as src_module
-from steward.models.alerts import AlertRule, AlertState, AlertStateEnum, AlertOperator, MaintenanceWindow
-from steward.models.metrics import PluginMetric
+from steward.models.alerts import AlertRule, AlertOperator, MaintenanceWindow
 from steward.models.users import UserRole
 
 alerts_bp = Blueprint("alerts", __name__, url_prefix="/alerts")
 
 _OPERATORS = [(op.value, op.value) for op in AlertOperator]
 
-# Static catalog: source_module → available metric names.
-# Unified monitors emit metrics under their TYPE (icmp/tcp/dns/http), each with
-# is_up (1.0 up / 0.0 down) and response_ms (where the probe times it).
-METRIC_CATALOG: dict[str, list[str]] = {
-    "icmp":    ["is_up", "response_ms"],
-    "tcp":     ["is_up", "response_ms"],
-    "dns":     ["is_up", "response_ms"],
-    "http":    ["is_up", "response_ms"],
-    "traefik": ["request_rate", "error_rate", "latency_p50_ms", "latency_p95_ms",
-                "latency_p99_ms", "response_bytes_rate", "cert_expiry_days"],
-    "unifi":   ["is_up", "latency_ms", "total_clients"],
-    # restart_count = cumulative restarts (alert on crash-looping); is_healthy =
-    # 1.0 healthy / 0.0 unhealthy from the container HEALTHCHECK (alert on <1).
-    "docker":  ["cpu_pct", "mem_pct", "restart_count", "is_healthy"],
-    "host_agent": [
-        "cpu_pct", "mem_used_pct", "mem_available_bytes", "swap_used_bytes",
-        "disk_used_pct_worst", "load_1m", "load_5m", "load_15m", "uptime_secs",
-    ],
-    # snmp metrics are user-defined OID labels — populated dynamically from plugin_metrics
-    "snmp":    [],
-}
-
-# Ordered list for source module picker
-_SOURCE_MODULES = list(METRIC_CATALOG.keys())
+def _rule_form(form) -> dict:
+    """The rule form's fields, as alert_svc.rule_fields takes them."""
+    return {
+        "name": form.get("name", ""),
+        "source_module": form.get("source_module", ""),
+        "resource_name": form.get("resource_name", ""),
+        "metric_name": form.get("metric_name", ""),
+        "operator": form.get("operator", ""),
+        "threshold": form.get("threshold"),
+        "consecutive_failures_required": form.get("consecutive_failures_required"),
+        "consecutive_ok_required": form.get("consecutive_ok_required"),
+        "notify_no_data": "notify_no_data" in form,
+    }
 
 
-async def _get_resources(db, source_module: str) -> list[str]:
-    """Return sorted distinct resource names for a source module.
-
-    For monitor types (icmp/tcp/dns/http), supplements with monitor names so
-    the list is populated even before any metrics have been recorded.
-    """
-    result = await db.execute(
-        select(PluginMetric.resource_name)
-        .where(PluginMetric.source_module == source_module)
-        .distinct()
-        .order_by(PluginMetric.resource_name)
-    )
-    resources: set[str] = {r for (r,) in result}
-
-    if source_module in ("icmp", "tcp", "dns", "http"):
-        from steward.models.monitors import Monitor
-        mon_result = await db.execute(
-            select(Monitor.name).where(Monitor.type == source_module).order_by(Monitor.name)
-        )
-        for (name,) in mon_result:
-            resources.add(name)
-
-    return sorted(resources)
+def _form_time(value) -> datetime:
+    """A datetime-local field, read as UTC."""
+    try:
+        return datetime.fromisoformat((value or "").strip()).replace(tzinfo=timezone.utc)
+    except ValueError:
+        raise ValueError(f"{value!r} is not a date and time.") from None
 
 
 def _is_admin() -> bool:
@@ -123,24 +96,56 @@ def _parse_ansible_action(form) -> tuple[dict | None, str | None]:
 @require_role(UserRole.viewer)
 async def list_alerts():
     async with current_app.db_sessionmaker() as db:
-        result = await db.execute(
-            select(AlertState, AlertRule)
-            .join(AlertRule, AlertState.rule_id == AlertRule.id)
-            .where(AlertState.state.in_([
-                AlertStateEnum.firing, AlertStateEnum.acknowledged, AlertStateEnum.pending
-            ]))
-            .order_by(AlertState.last_transition_at.desc())
-        )
-        active = result.all()
-
-        rules_result = await db.execute(
-            select(AlertRule).order_by(AlertRule.name)
-        )
-        rules = rules_result.scalars().all()
+        active = await alert_svc.active_alerts(db)
+        rules = await alert_svc.list_rules(db)
 
     return await render_template("alerts/list.html", active=active, rules=rules, operators=_OPERATORS)
 
 
+HISTORY_LIMIT = 200
+
+
+def _history_row(event, rule) -> dict:
+    """One transition as the history page shows it."""
+    from steward.core.alerts import MUTED, RELEASED
+    notes, muted_by, released = [], None, False
+    for part in (event.note or "").split("; "):
+        if part.startswith(MUTED):
+            muted_by = part[len(MUTED):].strip() or "a maintenance window"
+        elif part == RELEASED:
+            released = True
+        elif part:
+            notes.append(part)
+    value = "no data" if event.metric_value is None else f"{event.metric_value:g}"
+    return {
+        "at": event.transitioned_at, "rule": rule,
+        "from_state": event.from_state, "to_state": event.to_state,
+        "value": value, "condition": f"{rule.operator.value} {rule.threshold:g}",
+        "notes": notes, "muted_by": muted_by, "released": released,
+        "deliveries": [(label, sent, error) for label, sent, error in (
+            ("email", event.email_sent, event.email_error),
+            ("webhook", event.webhook_sent, event.webhook_error)) if sent is not None],
+        "ansible_run_id": event.ansible_run_id,
+    }
+
+
+@alerts_bp.get("/history")
+@require_role(UserRole.viewer)
+async def alert_history():
+    """Every alert transition in a range, newest first; one rule's with ?rule=."""
+    since, range_key = parse_range(request.args.get("range") or "7d")
+    async with current_app.db_sessionmaker() as db:
+        rules = await alert_svc.list_rules(db)
+        chosen = next((r for r in rules if r.id == request.args.get("rule")), None)
+        rows = await alert_svc.history(db, since, chosen.id if chosen else None, HISTORY_LIMIT)
+    ctx = {"events": [_history_row(e, r) for e, r in rows[:HISTORY_LIMIT]],
+           "truncated": len(rows) > HISTORY_LIMIT, "limit": HISTORY_LIMIT,
+           "rules": rules, "chosen": chosen, "current_range": range_key}
+    if request.headers.get("HX-Request"):
+        return await render_template("alerts/_history_rows.html", **ctx)
+    return await render_template("alerts/history.html", **ctx)
+
+
 @alerts_bp.get("/api/rule_fields")
 @require_role(UserRole.viewer)
 async def rule_fields_api():
@@ -148,18 +153,9 @@ async def rule_fields_api():
     current_resource = request.args.get("current_resource", "")
     current_metric = request.args.get("current_metric", "")
     async with current_app.db_sessionmaker() as db:
-        resources = await _get_resources(db, source) if source else []
-    metrics = METRIC_CATALOG.get(source, [])
-    # Dynamic sources (e.g. snmp) have empty static catalog — query live metric names
-    if source and not metrics:
-        async with current_app.db_sessionmaker() as db:
-            m_result = await db.execute(
-                select(PluginMetric.metric_name)
-                .where(PluginMetric.source_module == source)
-                .distinct()
-                .order_by(PluginMetric.metric_name)
-            )
-            metrics = [r for (r,) in m_result]
+        resources = await alert_svc.resources_for(db, source) if source else []
+    async with current_app.db_sessionmaker() as db:
+        metrics = await alert_svc.metrics_for(db, source)
     return await render_template(
         "alerts/_rule_fields.html",
         resources=resources,
@@ -172,17 +168,17 @@ async def rule_fields_api():
 @alerts_bp.get("/rules/new")
 @require_role(UserRole.operator)
 async def new_rule():
-    first_source = _SOURCE_MODULES[0]
+    first_source = alert_svc.source_modules()[0]
     async with current_app.db_sessionmaker() as db:
-        resources = await _get_resources(db, first_source)
+        resources = await alert_svc.resources_for(db, first_source)
     return await render_template(
         "alerts/rules_form.html",
         rule=None,
         operators=_OPERATORS,
-        source_modules=_SOURCE_MODULES,
+        source_modules=alert_svc.source_modules(),
         initial_source=first_source,
         resources=resources,
-        metrics=METRIC_CATALOG.get(first_source, []),
+        metrics=alert_svc.metric_catalog().get(first_source, []),
         ansible_sources=_ansible_source_names(),
     )
 
@@ -195,15 +191,15 @@ async def edit_rule(rule_id: str):
         rule = result.scalar_one_or_none()
         if rule is None:
             return "Not found", 404
-        resources = await _get_resources(db, rule.source_module)
+        resources = await alert_svc.resources_for(db, rule.source_module)
     return await render_template(
         "alerts/rules_form.html",
         rule=rule,
         operators=_OPERATORS,
-        source_modules=_SOURCE_MODULES,
+        source_modules=alert_svc.source_modules(),
         initial_source=rule.source_module,
         resources=resources,
-        metrics=METRIC_CATALOG.get(rule.source_module, []),
+        metrics=alert_svc.metric_catalog().get(rule.source_module, []),
         ansible_sources=_ansible_source_names(),
     )
 
@@ -213,36 +209,20 @@ async def edit_rule(rule_id: str):
 async def create_rule():
     form = await request.form
     user_id = session.get("user_id")
-    now = datetime.now(timezone.utc)
     # Ansible action is admin-only; non-admins simply can't set one.
     ansible_action = None
     if _is_admin():
         ansible_action, err = _parse_ansible_action(form)
         if err:
             return err, 400
-    rule = AlertRule(
-        name=form["name"].strip(),
-        source_module=form["source_module"].strip(),
-        resource_name=form["resource_name"].strip(),
-        metric_name=form["metric_name"].strip(),
-        operator=AlertOperator(form["operator"]),
-        threshold=float(form["threshold"]),
-        consecutive_failures_required=int(form.get("consecutive_failures_required") or 1),
-        enabled=True,
-        ansible_action=ansible_action,
-        created_by=user_id,
-    )
-    state = AlertState(
-        rule_id=rule.id,
-        state=AlertStateEnum.inactive,
-        last_transition_at=now,
-    )
     async with current_app.db_sessionmaker() as db:
         async with db.begin():
-            db.add(rule)
-            await db.flush()
-            state.rule_id = rule.id
-            db.add(state)
+            try:
+                fields = await alert_svc.rule_fields(db, **_rule_form(form))
+            except ValueError as exc:
+                return str(exc), 400
+            rule = await alert_svc.add_rule(db, fields, created_by=user_id,
+                                            ansible_action=ansible_action)
     await log_audit(current_app, user_id, session.get("username", ""), "alert_rule.created",
                     entity_type="alert_rule", entity_id=rule.name,
                     detail={"source": rule.source_module, "resource": rule.resource_name,
@@ -267,13 +247,11 @@ async def update_rule(rule_id: str):
             rule = result.scalar_one_or_none()
             if rule is None:
                 return "Not found", 404
-            rule.name = form["name"].strip()
-            rule.source_module = form["source_module"].strip()
-            rule.resource_name = form["resource_name"].strip()
-            rule.metric_name = form["metric_name"].strip()
-            rule.operator = AlertOperator(form["operator"])
-            rule.threshold = float(form["threshold"])
-            rule.consecutive_failures_required = int(form.get("consecutive_failures_required") or 1)
+            try:
+                fields = await alert_svc.rule_fields(db, **_rule_form(form))
+            except ValueError as exc:
+                return str(exc), 400
+            await alert_svc.apply_rule_change(db, rule, fields)
             if apply_action:
                 rule.ansible_action = ansible_action
     await log_audit(current_app, session.get("user_id"), session.get("username", ""),
@@ -290,7 +268,7 @@ async def toggle_rule(rule_id: str):
             rule = result.scalar_one_or_none()
             if rule is None:
                 return "Not found", 404
-            rule.enabled = not rule.enabled
+            await alert_svc.apply_rule_change(db, rule, {}, enabled=not rule.enabled)
     action = "alert_rule.enabled" if rule.enabled else "alert_rule.disabled"
     await log_audit(current_app, session.get("user_id"), session.get("username", ""),
                     action, entity_type="alert_rule", entity_id=rule.name)
@@ -319,15 +297,12 @@ async def delete_rule(rule_id: str):
 async def list_maintenance():
     now = datetime.now(timezone.utc)
     async with current_app.db_sessionmaker() as db:
-        result = await db.execute(
-            select(MaintenanceWindow).order_by(MaintenanceWindow.start_at.desc())
-        )
-        windows = result.scalars().all()
+        windows = await alert_svc.list_maintenance_windows(db)
     return await render_template(
         "alerts/maintenance.html",
         windows=windows,
         now=now,
-        source_modules=_SOURCE_MODULES,
+        source_modules=alert_svc.source_modules(),
     )
 
 
@@ -337,7 +312,7 @@ async def new_maintenance():
     return await render_template(
         "alerts/maintenance_form.html",
         window=None,
-        source_modules=_SOURCE_MODULES,
+        source_modules=alert_svc.source_modules(),
     )
 
 
@@ -346,26 +321,18 @@ async def new_maintenance():
 async def create_maintenance():
     form = await request.form
     user_id = session.get("user_id")
-    start_at = datetime.fromisoformat(form["start_at"]).replace(tzinfo=timezone.utc)
-    end_at = datetime.fromisoformat(form["end_at"]).replace(tzinfo=timezone.utc)
-    scope_source = form.get("scope_source", "").strip() or None
-    scope_resource = form.get("scope_resource", "").strip() or None
-    if scope_source is None:
-        scope_resource = None  # can't have resource without source
-    window = MaintenanceWindow(
-        name=form["name"].strip(),
-        start_at=start_at,
-        end_at=end_at,
-        scope_source=scope_source,
-        scope_resource=scope_resource,
-        created_by=user_id,
-    )
+    try:
+        fields = alert_svc.window_fields(
+            name=form.get("name", ""),
+            start_at=_form_time(form.get("start_at")), end_at=_form_time(form.get("end_at")),
+            scope_source=form.get("scope_source"), scope_resource=form.get("scope_resource"))
+    except ValueError as exc:
+        return str(exc), 400
+    window = MaintenanceWindow(created_by=user_id, **fields)
     async with current_app.db_sessionmaker() as db:
         async with db.begin():
             db.add(window)
-    scope_desc = "all" if not scope_source else (
-        f"{scope_source}/{scope_resource}" if scope_resource else f"{scope_source}/*"
-    )
+    scope_desc = alert_svc.window_scope(window)
     await log_audit(current_app, user_id, session.get("username", ""),
                     "maintenance_window.created", entity_type="maintenance_window",
                     entity_id=window.name, detail={"scope": scope_desc})
@@ -396,19 +363,12 @@ async def delete_maintenance(window_id: str):
 @require_role(UserRole.operator)
 async def acknowledge(rule_id: str):
     user_id = session.get("user_id")
-    now = datetime.now(timezone.utc)
     async with current_app.db_sessionmaker() as db:
         async with db.begin():
-            result = await db.execute(
-                select(AlertState).where(AlertState.rule_id == rule_id)
-            )
-            state = result.scalar_one_or_none()
-            if state is None:
+            try:
+                await alert_svc.acknowledge(db, rule_id, user_id)
+            except LookupError:
                 return "Not found", 404
-            if state.state != AlertStateEnum.firing:
-                return "Conflict: alert is not in FIRING state", 409
-            state.state = AlertStateEnum.acknowledged
-            state.acknowledged_by = user_id
-            state.acknowledged_at = now
-            state.last_transition_at = now
+            except ValueError as exc:
+                return f"Conflict: {exc}", 409
     return redirect(url_for("alerts.list_alerts"))

steward/alerts/service.py

@@ -0,0 +1,289 @@
+"""Alert queries and validation shared by the alerts pages and the MCP tools.
+
+Each function takes an open session (or plain values), with no Quart request
+context, so the routes and the /mcp tools (which run outside Quart's
+pipeline) call the same code and refuse the same input for the same reasons.
+"""
+from __future__ import annotations
+
+import logging
+from datetime import datetime, timezone
+
+from sqlalchemy import or_, select
+
+from steward.models.alerts import (
+    AlertEvent, AlertOperator, AlertRule, AlertState, AlertStateEnum, MaintenanceWindow,
+)
+from steward.models.metrics import PluginMetric
+from steward.models.monitors import MONITOR_TYPE_VALUES, Monitor
+
+logger = logging.getLogger(__name__)
+
+# What core itself records. Unified monitors emit metrics under their TYPE
+# (icmp/tcp/dns/http), each with is_up (1.0 up / 0.0 down) and response_ms
+# (where the probe times it); "steward" is the app watching itself.
+CORE_METRICS: dict[str, list[str]] = {
+    "icmp":    ["is_up", "response_ms"],
+    "tcp":     ["is_up", "response_ms"],
+    "dns":     ["is_up", "response_ms"],
+    "http":    ["is_up", "response_ms"],
+    "steward": ["open_fds", "open_fds_pct"],
+}
+
+
+def metric_catalog() -> dict[str, list[str]]:
+    """Every source an alert rule can watch, and its metric names.
+
+    Core's own sources, then each loaded plugin's get_alert_metrics() export
+    ({source: [metric names]}), so the catalog is written by whatever emits
+    the metrics and a disabled plugin's sources drop out. An empty list means
+    the names are dynamic (snmp: the OID labels recorded so far).
+    """
+    from steward.core.plugin_manager import get_loaded_plugin_modules
+    catalog = {src: list(names) for src, names in CORE_METRICS.items()}
+    for name, module in get_loaded_plugin_modules().items():
+        hook = getattr(module, "get_alert_metrics", None)
+        if hook is None:
+            continue
+        try:
+            contributed = hook() or {}
+        except Exception:
+            logger.exception("Plugin %r: get_alert_metrics() raised; its metrics are skipped", name)
+            continue
+        for src, names in contributed.items():
+            catalog[str(src)] = [str(n) for n in names]
+    return catalog
+
+
+def source_modules() -> list[str]:
+    """The sources in picker order: core's first, then plugins'."""
+    return list(metric_catalog())
+
+
+# States that need someone's attention: pending (breaching, not yet for long
+# enough), firing, and acknowledged-but-still-breaching.
+ACTIVE_STATES = (AlertStateEnum.firing, AlertStateEnum.acknowledged, AlertStateEnum.pending)
+
+
+async def active_alerts(db) -> list:
+    """(AlertState, AlertRule) rows that need attention, latest transition
+    first: not yet resolved, or with a series that has gone silent (no_data)."""
+    return list((await db.execute(
+        select(AlertState, AlertRule)
+        .join(AlertRule, AlertState.rule_id == AlertRule.id)
+        .where(or_(AlertState.state.in_(ACTIVE_STATES), AlertState.no_data_since.is_not(None)))
+        .order_by(AlertState.last_transition_at.desc())
+    )).all())
+
+
+def alert_label(state: AlertState) -> str:
+    """What an alert is, in one word: its state, or "no_data" for a quiet rule
+    whose series has gone silent (a firing alert that goes silent stays
+    "firing"; check no_data_since for the mark)."""
+    if state.no_data_since is not None and state.state == AlertStateEnum.inactive:
+        return "no_data"
+    return state.state.value
+
+
+async def list_rules(db) -> list[AlertRule]:
+    return list((await db.execute(select(AlertRule).order_by(AlertRule.name))).scalars())
+
+
+async def history(db, since: datetime, rule_id: str | None = None,
+                  limit: int = 200) -> list[tuple[AlertEvent, AlertRule]]:
+    """Alert transitions since `since`, newest first, with their rule; one
+    rule's when `rule_id` is given. Returns up to limit+1 rows so a caller can
+    tell the list was cut."""
+    stmt = (select(AlertEvent, AlertRule)
+            .join(AlertRule, AlertEvent.rule_id == AlertRule.id)
+            .where(AlertEvent.transitioned_at >= since)
+            .order_by(AlertEvent.transitioned_at.desc())
+            .limit(limit + 1))
+    if rule_id:
+        stmt = stmt.where(AlertEvent.rule_id == rule_id)
+    return [tuple(row) for row in (await db.execute(stmt)).all()]
+
+
+async def list_maintenance_windows(db) -> list[MaintenanceWindow]:
+    """Every window, latest start first."""
+    return list((await db.execute(
+        select(MaintenanceWindow).order_by(MaintenanceWindow.start_at.desc())
+    )).scalars())
+
+
+async def resources_for(db, source_module: str) -> list[str]:
+    """Sorted distinct resource names for a source module.
+
+    For monitor types (icmp/tcp/dns/http), supplements with monitor names so
+    the list is populated even before any metrics have been recorded.
+    """
+    result = await db.execute(
+        select(PluginMetric.resource_name)
+        .where(PluginMetric.source_module == source_module)
+        .distinct()
+        .order_by(PluginMetric.resource_name)
+    )
+    resources: set[str] = {r for (r,) in result}
+    if source_module in MONITOR_TYPE_VALUES:
+        mon_result = await db.execute(
+            select(Monitor.name).where(Monitor.type == source_module).order_by(Monitor.name))
+        resources.update(name for (name,) in mon_result)
+    return sorted(resources)
+
+
+async def metrics_for(db, source_module: str) -> list[str]:
+    """The metric names a rule on this source can watch: the static catalog, or
+    for dynamic sources (snmp) the names recorded so far."""
+    metrics = metric_catalog().get(source_module, [])
+    if source_module and not metrics:
+        result = await db.execute(
+            select(PluginMetric.metric_name)
+            .where(PluginMetric.source_module == source_module)
+            .distinct()
+            .order_by(PluginMetric.metric_name))
+        metrics = [r for (r,) in result]
+    return metrics
+
+
+def _choices(values: list[str], limit: int = 20) -> str:
+    if not values:
+        return "none yet"
+    shown = ", ".join(values[:limit])
+    return shown + (f" (and {len(values) - limit} more)" if len(values) > limit else "")
+
+
+async def rule_fields(db, *, name: str, source_module: str, resource_name: str, metric_name: str,
+                      operator: str, threshold, consecutive_failures_required=1,
+                      consecutive_ok_required=1, notify_no_data=True) -> dict:
+    """Validated column values for a new or edited alert rule.
+
+    The same choices the rule form offers: a known source, a resource that
+    source has reported (or, for monitors, a monitor of that type), and a
+    metric it emits. ValueError says what was wrong and what is valid.
+    """
+    name = (name or "").strip()
+    if not name:
+        raise ValueError("an alert rule needs a name.")
+    source_module = (source_module or "").strip()
+    catalog = metric_catalog()
+    if source_module not in catalog:
+        raise ValueError(f"source_module {source_module!r} is not one of {', '.join(catalog)}.")
+    resource_name = (resource_name or "").strip()
+    resources = await resources_for(db, source_module)
+    if resource_name not in resources:
+        raise ValueError(f"{source_module} has no resource {resource_name!r}. "
+                         f"Known: {_choices(resources)}.")
+    metric_name = (metric_name or "").strip()
+    metrics = await metrics_for(db, source_module)
+    if metric_name not in metrics:
+        raise ValueError(f"{source_module} does not report {metric_name!r}. "
+                         f"Its metrics: {_choices(metrics)}.")
+    try:
+        op = AlertOperator((operator or "").strip())
+    except ValueError:
+        raise ValueError(f"operator {operator!r} is not one of "
+                         f"{', '.join(o.value for o in AlertOperator)}.") from None
+    try:
+        threshold = float(threshold)
+    except (TypeError, ValueError):
+        raise ValueError(f"threshold must be a number, got {threshold!r}.") from None
+    try:
+        consecutive = (1 if consecutive_failures_required in (None, "")
+                       else int(consecutive_failures_required))
+    except (TypeError, ValueError):
+        raise ValueError("consecutive checks must be a whole number.") from None
+    if consecutive < 1:
+        raise ValueError("consecutive checks must be at least 1.")
+    try:
+        ok_checks = (1 if consecutive_ok_required in (None, "")
+                     else int(consecutive_ok_required))
+    except (TypeError, ValueError):
+        raise ValueError("checks to clear must be a whole number.") from None
+    if ok_checks < 1:
+        raise ValueError("checks to clear must be at least 1.")
+    return {"name": name[:128], "source_module": source_module, "resource_name": resource_name,
+            "metric_name": metric_name, "operator": op, "threshold": threshold,
+            "consecutive_failures_required": consecutive,
+            "consecutive_ok_required": ok_checks, "notify_no_data": bool(notify_no_data)}
+
+
+# Changing any of these changes what the rule is watching, so whatever state
+# it had built up no longer means anything.
+WATCHED_FIELDS = ("source_module", "resource_name", "metric_name", "operator", "threshold")
+
+
+async def apply_rule_change(db, rule: AlertRule, fields: dict, *, enabled: bool | None = None) -> None:
+    """Apply validated fields (and optionally enabled) to a rule, in the
+    caller's transaction. A change to what it watches, or disabling or
+    re-enabling it, puts its alert back to inactive and starts its silence
+    watch over (core.alerts.reset_rule_state)."""
+    from steward.core.alerts import reset_rule_state
+    changed = [k for k in WATCHED_FIELDS if k in fields and getattr(rule, k) != fields[k]]
+    for k, v in fields.items():
+        setattr(rule, k, v)
+    disabling = enabled is False and rule.enabled
+    enabling = enabled is True and not rule.enabled
+    if enabled is not None:
+        rule.enabled = bool(enabled)
+    if disabling:
+        await reset_rule_state(db, rule, "rule disabled")
+    elif enabling:
+        await reset_rule_state(db, rule, "rule enabled")
+    elif changed:
+        await reset_rule_state(db, rule, "rule changed: " + ", ".join(changed))
+
+
+async def add_rule(db, fields: dict, *, created_by: str, enabled: bool = True,
+                   ansible_action: dict | None = None) -> AlertRule:
+    """Insert a rule and its inactive state row, in the caller's transaction."""
+    rule = AlertRule(enabled=enabled, ansible_action=ansible_action, created_by=created_by, **fields)
+    db.add(rule)
+    await db.flush()
+    db.add(AlertState(rule_id=rule.id, state=AlertStateEnum.inactive,
+                      last_transition_at=datetime.now(timezone.utc)))
+    return rule
+
+
+async def acknowledge(db, rule_id: str, user_id: str) -> AlertState:
+    """Acknowledge a firing alert, in the caller's transaction.
+
+    LookupError when the rule has no state; ValueError when it is not firing.
+    """
+    state = (await db.execute(
+        select(AlertState).where(AlertState.rule_id == rule_id))).scalar_one_or_none()
+    if state is None:
+        raise LookupError(rule_id)
+    if state.state != AlertStateEnum.firing:
+        raise ValueError(f"the alert is {state.state.value}, not firing; only a firing alert "
+                         "can be acknowledged.")
+    now = datetime.now(timezone.utc)
+    state.state = AlertStateEnum.acknowledged
+    state.acknowledged_by = user_id
+    state.acknowledged_at = now
+    state.last_transition_at = now
+    return state
+
+
+def window_fields(*, name: str, start_at: datetime, end_at: datetime,
+                  scope_source: str | None, scope_resource: str | None) -> dict:
+    """Validated columns for a maintenance window. A resource needs a source."""
+    name = (name or "").strip()
+    if not name:
+        raise ValueError("a maintenance window needs a name.")
+    if end_at <= start_at:
+        raise ValueError("the window must end after it starts.")
+    scope_source = (scope_source or "").strip() or None
+    scope_resource = (scope_resource or "").strip() or None
+    catalog = metric_catalog()
+    if scope_source is not None and scope_source not in catalog:
+        raise ValueError(f"source {scope_source!r} is not one of {', '.join(catalog)}.")
+    if scope_source is None:
+        scope_resource = None  # can't have resource without source
+    return {"name": name[:128], "start_at": start_at, "end_at": end_at,
+            "scope_source": scope_source, "scope_resource": scope_resource}
+
+
+def window_scope(w) -> str:
+    if not w.scope_source:
+        return "all"
+    return f"{w.scope_source}/{w.scope_resource}" if w.scope_resource else f"{w.scope_source}/*"

steward/ansible/bundled/host_agent/install.yml

@@ -61,6 +61,8 @@
       notify: restart steward-agent
 
     - name: Write agent config
+      # The content carries steward_token; --diff and a failure would print it.
+      no_log: true
       ansible.builtin.copy:
         dest: /etc/steward-agent.conf
         owner: root

steward/ansible/bundled/host_agent/provision.yml

@@ -117,6 +117,8 @@
       notify: restart steward-agent
 
     - name: Write agent config
+      # The content carries steward_token; --diff and a failure would print it.
+      no_log: true
       ansible.builtin.copy:
         dest: /etc/steward-agent.conf
         owner: root

steward/ansible/bundled/maintenance/docker_prune.yml

@@ -1,29 +1,64 @@
 ---
-# description: Reclaim disk on Docker / Swarm nodes by pruning unused images, containers, networks and build cache.
+# description: Reclaim disk on Docker / Swarm nodes — prune stopped containers, unused images, or a full system prune.
 # steward:category: maintenance
 # steward:confirm: true
 # Reclaim disk on Docker / Docker Swarm nodes by removing unused data.
-# Safe by default: prunes dangling images, stopped containers, unused networks
-# and build cache. Set extra-vars to widen scope:
-#   prune_all_images=true   also remove ALL unused images (not just dangling)
-#   prune_volumes=true      also remove unused named volumes (data loss risk)
-- name: Docker system prune
+# `prune_target` selects the scope (default `system` preserves the original
+# behavior for existing manual/scheduled callers that don't set it):
+#   prune_target=containers   remove stopped containers only (docker container prune)
+#   prune_target=images       remove unused images (docker image prune;
+#                             + prune_all_images=true → -a, i.e. ALL unused, not just dangling)
+#   prune_target=system       docker system prune (dangling images, stopped
+#                             containers, unused networks, build cache). Widen with:
+#                               prune_all_images=true   also ALL unused images
+#                               prune_volumes=true       also unused named volumes (data loss risk)
+- name: Docker prune
   hosts: all
   gather_facts: false
   become: true
   vars:
+    prune_target: system
     prune_all_images: false
     prune_volumes: false
   tasks:
+    - name: Validate prune_target
+      ansible.builtin.assert:
+        that: prune_target in ['containers', 'images', 'system']
+        fail_msg: "prune_target must be one of: containers, images, system (got '{{ prune_target }}')"
+        quiet: true
+
+    # ── Stopped containers only ───────────────────────────────────────────────
+    - name: Prune stopped containers
+      ansible.builtin.command:
+        argv: ['docker', 'container', 'prune', '-f']
+      register: container_prune
+      changed_when: "'Total reclaimed space: 0B' not in container_prune.stdout"
+      when: prune_target == 'containers'
+
+    # ── Unused images (dangling, or all unused with -a) ───────────────────────
+    - name: Prune unused images
+      ansible.builtin.command:
+        argv: >-
+          {{ ['docker', 'image', 'prune', '-f']
+             + (['-a'] if prune_all_images | bool else []) }}
+      register: image_prune
+      changed_when: "'Total reclaimed space: 0B' not in image_prune.stdout"
+      when: prune_target == 'images'
+
+    # ── Full system prune (default) ───────────────────────────────────────────
     - name: Run docker system prune
       ansible.builtin.command:
         argv: >-
           {{ ['docker', 'system', 'prune', '-f']
              + (['-a'] if prune_all_images | bool else [])
              + (['--volumes'] if prune_volumes | bool else []) }}
-      register: prune_result
-      changed_when: "'Total reclaimed space: 0B' not in prune_result.stdout"
+      register: system_prune
+      changed_when: "'Total reclaimed space: 0B' not in system_prune.stdout"
+      when: prune_target == 'system'
 
     - name: Report reclaimed space
       ansible.builtin.debug:
-        msg: "{{ prune_result.stdout_lines | select | list }}"
+        msg: >-
+          {{ ((container_prune.stdout_lines | default([]))
+              + (image_prune.stdout_lines | default([]))
+              + (system_prune.stdout_lines | default([]))) | select | list }}

steward/ansible/executor.py

@@ -293,6 +293,45 @@ def cancel_run(run_id: str) -> bool:
 
 # ── Run execution ─────────────────────────────────────────────────────────────
 
+# ── Secret scrubbing ──────────────────────────────────────────────────────────
+# Ansible echoes values back: a failed task prints its args, -v prints vars,
+# --diff prints templated files. Each line is masked before it is broadcast,
+# written to the log artifact or stored on the run, so a secret the run was
+# handed never leaves it.
+MASK = "***"
+_MIN_SECRET_LEN = 4  # masking "on" or "1" would mangle the output and hide nothing
+
+
+def _strings(value) -> list[str]:
+    if isinstance(value, str):
+        return [value]
+    if isinstance(value, dict):
+        return [s for v in value.values() for s in _strings(v)]
+    if isinstance(value, (list, tuple, set)):
+        return [s for v in value for s in _strings(v)]
+    return []
+
+
+def run_secrets(creds: dict | None, connection: dict | None,
+                secret_vars: dict | None, redact: list[str] | None) -> list[str]:
+    """Every secret value this run is handed: the global become/vault
+    passwords, the bootstrap passwords, the sensitive run variables and any
+    the caller names (a per-host agent token)."""
+    creds, connection = creds or {}, connection or {}
+    values = [creds.get("become_password"), creds.get("vault_password"),
+              connection.get("password"), connection.get("become_password"),
+              *_strings(secret_vars), *(redact or [])]
+    found = {v for v in values if isinstance(v, str) and len(v) >= _MIN_SECRET_LEN}
+    return sorted(found, key=len, reverse=True)  # longest first: no partial masks
+
+
+def scrub(line: str, secrets: list[str]) -> str:
+    for value in secrets:
+        if value in line:
+            line = line.replace(value, MASK)
+    return line
+
+
 async def start_run(
     app: "Quart",
     run_id: str,
@@ -303,6 +342,7 @@ async def start_run(
     inventory_content: str | None = None,
     connection: dict | None = None,
     secret_vars: dict | None = None,
+    redact: list[str] | None = None,
 ) -> None:
     """Execute ansible-playbook as a subprocess and update the DB run row.
 
@@ -315,10 +355,12 @@ async def start_run(
     never persisted on the AnsibleRun row, never placed on argv, and not logged.
     secret_vars are run-time playbook variables flagged sensitive; like
     connection they reach the subprocess (merged into the extra-vars file) but
-    are never persisted.
+    are never persisted. Every value in run_secrets() — redact names more — is
+    masked in each output line before it goes anywhere.
     """
     from steward.models.ansible import AnsibleRunStatus
 
+    secrets = run_secrets(app.config.get("ANSIBLE", {}), connection, secret_vars, redact)
     _run_lines[run_id] = []
     db_output = ""
     truncated = False
@@ -432,7 +474,7 @@ async def start_run(
             assert proc.stdout is not None
 
             async for raw_line in proc.stdout:
-                line = raw_line.decode(errors="replace").rstrip("\n\r")
+                line = scrub(raw_line.decode(errors="replace").rstrip("\n\r"), secrets)
                 _broadcast(run_id, line)
                 if logf is not None:
                     logf.write(line + "\n")
@@ -478,7 +520,7 @@ async def start_run(
         final_status = "cancelled" if run_id in _cancelled else "failed"
         # Surface WHY in the run output instead of an empty "failed" (e.g. ENOSPC
         # when the temp dir can't be created — the run never reaches Ansible).
-        msg = f"[run error] {type(exc).__name__}: {exc}"
+        msg = scrub(f"[run error] {type(exc).__name__}: {exc}", secrets)
         _broadcast(run_id, msg)
         if len(failures) < _FAILURE_CAP:
             failures.append(msg[:500])

steward/ansible/guards.py

@@ -0,0 +1,86 @@
+"""What a playbook run may be pointed at, and which variables only an admin
+may set.
+
+Ansible runs inside the Steward container, so a run is code on the Steward
+server unless it is held to playbooks its source lists and to variables that
+only shape what happens on the target. An operator may run playbooks and set
+their variables. Three things would let one run commands on Steward itself,
+and are refused for anyone but an admin:
+
+- a playbook or inventory path outside what the source lists;
+- an `ansible_*` variable that changes how or where Ansible connects
+  (`ansible_connection: local`, `ansible_ssh_common_args` with a
+  ProxyCommand, an interpreter or executable path);
+- a Jinja expression in any value (`{{ lookup('pipe', …) }}` is evaluated
+  on the controller when the value is used).
+
+Playbook files themselves are admin-only to write (ansible/routes.py).
+"""
+from __future__ import annotations
+
+from steward.ansible import sources as src_module
+from steward.models.users import UserRole
+
+# The ansible_* variables an operator may set: which address, port and user
+# to reach a target as, and whether to become another user there.
+OPERATOR_ANSIBLE_VARS = frozenset({
+    "ansible_host", "ansible_port", "ansible_user", "ansible_password",
+    "ansible_become", "ansible_become_user", "ansible_become_password",
+})
+_JINJA = ("{{", "{%", "{#")
+
+
+def check_playbook(source: dict, playbook_path: str) -> str | None:
+    """None when the source lists this playbook, else why it is refused."""
+    if playbook_path not in src_module.discover_playbooks(source["path"]):
+        return f"Source {source['name']!r} has no playbook {playbook_path!r}"
+    return None
+
+
+def check_inventory_scope(source: dict, scope: str) -> str | None:
+    """None for a Steward scope or an inventory file the source has, else why not."""
+    if scope.startswith("steward:"):
+        return None
+    if scope.startswith("repo:"):
+        parts = scope.split(":", 2)
+        path = parts[2] if len(parts) == 3 else ""
+        if path in src_module.discover_inventories(source["path"]):
+            return None
+        return f"Source {source['name']!r} has no inventory file {path!r}"
+    return "Invalid inventory_scope"
+
+
+def _has_jinja(value) -> bool:
+    if isinstance(value, str):
+        return any(mark in value for mark in _JINJA)
+    if isinstance(value, dict):
+        return any(_has_jinja(k) or _has_jinja(v) for k, v in value.items())
+    if isinstance(value, (list, tuple)):
+        return any(_has_jinja(v) for v in value)
+    return False
+
+
+def check_vars_for_role(variables: dict | None, role: UserRole | None) -> str | None:
+    """None when `role` may set these variables, else a message naming what
+    only an admin may set. role=None is treated as the least privileged."""
+    if role == UserRole.admin or not variables:
+        return None
+    names = sorted(n for n in variables
+                   if str(n).startswith("ansible_") and n not in OPERATOR_ANSIBLE_VARS)
+    if names:
+        return (f"Only an admin can set {', '.join(names)}: these change how or where "
+                "Ansible connects, and can run commands on the Steward server itself.")
+    templated = sorted(str(k) for k, v in variables.items() if _has_jinja(k) or _has_jinja(v))
+    if templated:
+        return (f"Only an admin can set a value containing {{{{ }}}}, {{% %}} or {{# #}} "
+                f"({', '.join(templated)}): Ansible evaluates it on the Steward server.")
+    return None
+
+
+
+def changed_vars(new: dict | None, old: dict | None) -> dict:
+    """The entries of `new` that are added or differ from `old`. An edit is
+    held to the editor's role only for what it changes, so an operator can
+    still edit a group whose connection vars an admin set."""
+    old = old or {}
+    return {k: v for k, v in (new or {}).items() if k not in old or old[k] != v}

steward/ansible/inventory_gen.py

@@ -106,3 +106,39 @@ async def fetch_scope_targets(db, scope: str) -> list:
 
     result = await db.execute(stmt)
     return list(result.scalars().all())
+
+
+def describe_scope(scope: str, targets: dict[str, str], groups: dict[str, str]) -> str:
+    """A run's inventory scope in words: "target web-1", "group Docker Swarm",
+    "all inventory targets", "<source>/<inventory file>". `targets` and
+    `groups` map id → name; a scope naming a deleted one says so."""
+    scope = scope or ""
+    if scope == "steward:all":
+        return "all inventory targets"
+    for prefix, kind, names in (("steward:target:", "target", targets),
+                                ("steward:group:", "group", groups)):
+        if scope.startswith(prefix):
+            ident = scope[len(prefix):]
+            name = names.get(ident)
+            return f"{kind} {name}" if name else f"{kind} {ident[:8]} (deleted)"
+    if scope.startswith("repo:"):
+        source, _, inv = scope[len("repo:"):].rpartition(":")
+        return f"{source}/{inv}" if source else inv
+    return scope
+
+
+async def scope_labels(db, scopes) -> dict[str, str]:
+    """{scope: describe_scope(scope)} for the given scopes, in two queries."""
+    from sqlalchemy import select
+    from steward.models.ansible_inventory import AnsibleGroup, AnsibleTarget
+
+    scopes = {s for s in scopes if s}
+    t_ids = {s[len("steward:target:"):] for s in scopes if s.startswith("steward:target:")}
+    g_ids = {s[len("steward:group:"):] for s in scopes if s.startswith("steward:group:")}
+    targets = dict((await db.execute(
+        select(AnsibleTarget.id, AnsibleTarget.name).where(AnsibleTarget.id.in_(t_ids))
+    )).all()) if t_ids else {}
+    groups = dict((await db.execute(
+        select(AnsibleGroup.id, AnsibleGroup.name).where(AnsibleGroup.id.in_(g_ids))
+    )).all()) if g_ids else {}
+    return {s: describe_scope(s, targets, groups) for s in scopes}

steward/ansible/inventory_routes.py

@@ -3,11 +3,13 @@ from __future__ import annotations
 import uuid
 import yaml
 
-from quart import Blueprint, current_app, redirect, render_template, request, url_for
+from quart import Blueprint, current_app, redirect, render_template, request, session, url_for
 from sqlalchemy import select
 from sqlalchemy.orm import selectinload
 
+from steward.ansible import guards
 from steward.auth.middleware import require_role
+from steward.core.audit import audit_request as _audit
 from steward.models.ansible_inventory import AnsibleGroup, AnsibleTarget
 from steward.models.users import UserRole
 
@@ -30,6 +32,12 @@ def _parse_ansible_vars(raw: str) -> dict:
     return parsed
 
 
+def _vars_refusal(new: dict, old: dict | None = None) -> str | None:
+    """Why this editor may not make this vars change, or None (ansible/guards.py)."""
+    return guards.check_vars_for_role(guards.changed_vars(new, old),
+                                      UserRole(session.get("user_role", "viewer")))
+
+
 # ---------------------------------------------------------------------------
 # Groups
 # ---------------------------------------------------------------------------
@@ -59,10 +67,16 @@ async def groups_create():
     except ValueError as exc:
         return str(exc), 400
 
+    err = _vars_refusal(ansible_vars)
+    if err:
+        return err, 400
+
     group = AnsibleGroup(id=str(uuid.uuid4()), name=name, ansible_vars=ansible_vars)
     async with current_app.db_sessionmaker() as db:
         async with db.begin():
             db.add(group)
+    await _audit("ansible.group.created", "ansible_group", group.id,
+                 {"name": name, "vars": sorted(ansible_vars)})
     return redirect(url_for("ansible_inventory.groups_list"))
 
 
@@ -111,6 +125,9 @@ async def group_update(group_id: str):
             group = result.scalar_one_or_none()
             if group is None:
                 return "Group not found", 404
+            err = _vars_refusal(ansible_vars, group.ansible_vars)
+            if err:
+                return err, 400
 
             name = form.get("name", group.name).strip()
             if name:
@@ -123,7 +140,10 @@ async def group_update(group_id: str):
             ).scalars().all()
             target_map = {t.id: t for t in all_targets}
             group.targets = [target_map[tid] for tid in new_ids if tid in target_map]
+            detail = {"name": group.name, "vars": sorted(ansible_vars),
+                      "targets": sorted(t.name for t in group.targets)}
 
+    await _audit("ansible.group.updated", "ansible_group", group_id, detail)
     return redirect(url_for("ansible_inventory.group_detail", group_id=group_id))
 
 
@@ -136,8 +156,11 @@ async def group_delete(group_id: str):
                 select(AnsibleGroup).where(AnsibleGroup.id == group_id)
             )
             group = result.scalar_one_or_none()
-            if group is not None:
-                await db.delete(group)
+            if group is None:
+                return redirect(url_for("ansible_inventory.groups_list"))
+            name = group.name
+            await db.delete(group)
+    await _audit("ansible.group.deleted", "ansible_group", group_id, {"name": name})
     return redirect(url_for("ansible_inventory.groups_list"))
 
 
@@ -171,12 +194,18 @@ async def targets_create():
     except ValueError as exc:
         return str(exc), 400
 
+    err = _vars_refusal(ansible_vars)
+    if err:
+        return err, 400
+
     target = AnsibleTarget(
         id=str(uuid.uuid4()), name=name, address=address, ansible_vars=ansible_vars
     )
     async with current_app.db_sessionmaker() as db:
         async with db.begin():
             db.add(target)
+    await _audit("ansible.target.created", "ansible_target", target.id,
+                 {"name": name, "address": address, "vars": sorted(ansible_vars)})
     return redirect(url_for("ansible_inventory.targets_list"))
 
 
@@ -225,6 +254,9 @@ async def target_update(target_id: str):
             target = result.scalar_one_or_none()
             if target is None:
                 return "Target not found", 404
+            err = _vars_refusal(ansible_vars, target.ansible_vars)
+            if err:
+                return err, 400
 
             name = form.get("name", target.name).strip()
             address = form.get("address", target.address).strip()
@@ -238,7 +270,10 @@ async def target_update(target_id: str):
             all_groups_result = await db.execute(select(AnsibleGroup))
             group_map = {g.id: g for g in all_groups_result.scalars().all()}
             target.groups = [group_map[gid] for gid in new_group_ids if gid in group_map]
+            detail = {"name": target.name, "address": target.address, "vars": sorted(ansible_vars),
+                      "groups": sorted(g.name for g in target.groups)}
 
+    await _audit("ansible.target.updated", "ansible_target", target_id, detail)
     return redirect(url_for("ansible_inventory.target_detail", target_id=target_id))
 
 
@@ -251,6 +286,9 @@ async def target_delete(target_id: str):
                 select(AnsibleTarget).where(AnsibleTarget.id == target_id)
             )
             target = result.scalar_one_or_none()
-            if target is not None:
-                await db.delete(target)
+            if target is None:
+                return redirect(url_for("ansible_inventory.targets_list"))
+            name = target.name
+            await db.delete(target)
+    await _audit("ansible.target.deleted", "ansible_target", target_id, {"name": name})
     return redirect(url_for("ansible_inventory.targets_list"))

steward/ansible/routes.py

@@ -8,8 +8,10 @@ from quart import (
 )
 from sqlalchemy import select
 
-from steward.ansible import executor, sources as src_module
+from steward.ansible import executor, guards, sources as src_module
+from steward.ansible.inventory_gen import scope_labels
 from steward.auth.middleware import require_role
+from steward.core.audit import audit_request as _audit
 from steward.models.ansible import AnsibleRun, AnsibleRunStatus
 from steward.models.ansible_schedule import AnsibleSchedule
 from steward.models.users import User, UserRole
@@ -104,6 +106,30 @@ async def view_playbook(source_name: str, playbook_path: str):
     )
 
 
+def _caller_role() -> UserRole:
+    return UserRole(session.get("user_role", "viewer"))
+
+
+def _run_vars(params: dict | None, secret_vars: dict | None = None) -> dict:
+    return {**((params or {}).get("extra_vars_map") or {}), **(secret_vars or {})}
+
+
+def check_run_form(form, source: dict | None, playbook_path: str,
+                   params: dict | None, secret_vars: dict | None) -> str | None:
+    """The server-side gates a web run must pass (the form's own checks are
+    only a convenience): who may set these variables, and the playbook's
+    steward:confirm flag, which a real (non-check) run must have ticked."""
+    err = guards.check_vars_for_role(_run_vars(params, secret_vars), _caller_role())
+    if err:
+        return err
+    content = src_module.read_playbook(source["path"], playbook_path) if source else None
+    meta = src_module.discover_playbook_meta(content or "")
+    if meta["confirm"] and not (params or {}).get("check") and "confirmed" not in form:
+        return (f"{playbook_path} is flagged destructive by its author (steward:confirm). "
+                "Tick the confirmation to run it, or run it in check mode.")
+    return None
+
+
 def _parse_run_params(form) -> tuple[dict | None, dict | None, str | None]:
     """Build executor params + the unpersisted secret-vars dict from form fields.
 
@@ -234,6 +260,10 @@ async def create_run():
         return "playbook_path is required", 400
 
     params_or_none, secret_vars, err = _parse_run_params(form)
+    if err:
+        return err, 400
+    source = next((s for s in _get_sources() if s["name"] == source_name), None)
+    err = check_run_form(form, source, playbook_path, params_or_none, secret_vars)
     if err:
         return err, 400
 
@@ -250,6 +280,10 @@ async def create_run():
         return err, 404
     if err:
         return err, 400
+    await _audit("ansible.run.started", "ansible_run", run.id, {
+        "source": source_name, "playbook": playbook_path, "scope": inventory_scope,
+        "check": bool((params_or_none or {}).get("check")),
+        "vars": sorted(_run_vars(params_or_none, secret_vars))})
 
     return await render_template(
         "ansible/run_started.html",
@@ -306,8 +340,10 @@ async def run_detail(run_id: str):
             res = await db.execute(
                 select(User.username).where(User.id == run.triggered_by))
             triggered_label = res.scalar_one_or_none() or "(deleted user)"
+        scope_label = (await scope_labels(db, [run.inventory_scope])).get(run.inventory_scope)
     return await render_template(
-        "ansible/run_detail.html", run=run, triggered_label=triggered_label)
+        "ansible/run_detail.html", run=run, triggered_label=triggered_label,
+        scope_label=scope_label)
 
 
 @ansible_bp.post("/runs/<run_id>/cancel")
@@ -320,6 +356,8 @@ async def cancel_run(run_id: str):
         return "Not found", 404
     if run.status in (AnsibleRunStatus.running, AnsibleRunStatus.queued):
         executor.cancel_run(run_id)
+        await _audit("ansible.run.cancelled", "ansible_run", run_id,
+                     {"playbook": run.playbook_path})
     return redirect(url_for("ansible.run_detail", run_id=run_id))
 
 
@@ -368,6 +406,7 @@ async def schedules():
             r.id: r for r in (await db.execute(
                 select(AnsibleRun).where(AnsibleRun.id.in_(run_ids)))).scalars().all()
         } if run_ids else {}
+        labels = await scope_labels(db, [s.inventory_scope for s in scheds])
 
     source_data = [
         {"name": s["name"], "playbooks": src_module.discover_playbooks(s["path"])}
@@ -380,6 +419,7 @@ async def schedules():
         rows.append({
             "s": s,
             "last_run": runs.get(s.last_run_id) if s.last_run_id else None,
+            "scope_label": labels.get(s.inventory_scope, s.inventory_scope),
             "next_run": (s.last_run_at + timedelta(seconds=s.interval_seconds)) if s.last_run_at else None,
         })
         if editing_id and s.id == editing_id:
@@ -436,6 +476,15 @@ def _schedule_form_fields(form) -> tuple[dict | None, str | None]:
     }, None
 
 
+def _schedule_detail(fields: dict) -> dict:
+    """What a schedule audit row records: what runs, where, how often — and
+    which variables, by name only."""
+    return {"name": fields["name"], "source": fields["source_name"],
+            "playbook": fields["playbook_path"], "scope": fields["inventory_scope"],
+            "interval_seconds": fields["interval_seconds"],
+            "vars": sorted(_run_vars(fields["params"]))}
+
+
 @ansible_bp.post("/schedules")
 @require_role(UserRole.operator)
 async def create_schedule():
@@ -443,9 +492,14 @@ async def create_schedule():
     fields, err = _schedule_form_fields(form)
     if err:
         return err, 400
+    err = guards.check_vars_for_role(_run_vars(fields["params"]), _caller_role())
+    if err:
+        return err, 400
+    sched = AnsibleSchedule(enabled=True, **fields)
     async with current_app.db_sessionmaker() as db:
         async with db.begin():
-            db.add(AnsibleSchedule(enabled=True, **fields))
+            db.add(sched)
+    await _audit("ansible.schedule.created", "ansible_schedule", sched.id, _schedule_detail(fields))
     return redirect(url_for("ansible.schedules"))
 
 
@@ -461,8 +515,14 @@ async def update_schedule(schedule_id: str):
             sched = await db.get(AnsibleSchedule, schedule_id)
             if sched is None:
                 return "Not found", 404
+            err = guards.check_vars_for_role(
+                guards.changed_vars(_run_vars(fields["params"]), _run_vars(sched.params)),
+                _caller_role())
+            if err:
+                return err, 400
             for k, v in fields.items():
                 setattr(sched, k, v)
+    await _audit("ansible.schedule.updated", "ansible_schedule", schedule_id, _schedule_detail(fields))
     return redirect(url_for("ansible.schedules"))
 
 
@@ -475,6 +535,9 @@ async def toggle_schedule(schedule_id: str):
             if sched is None:
                 return "Not found", 404
             sched.enabled = not sched.enabled
+            enabled, name = sched.enabled, sched.name
+    await _audit("ansible.schedule.enabled" if enabled else "ansible.schedule.disabled",
+                 "ansible_schedule", schedule_id, {"name": name})
     return redirect(url_for("ansible.schedules"))
 
 
@@ -484,8 +547,11 @@ async def delete_schedule(schedule_id: str):
     async with current_app.db_sessionmaker() as db:
         async with db.begin():
             sched = await db.get(AnsibleSchedule, schedule_id)
-            if sched is not None:
-                await db.delete(sched)
+            if sched is None:
+                return redirect(url_for("ansible.schedules"))
+            name = sched.name
+            await db.delete(sched)
+    await _audit("ansible.schedule.deleted", "ansible_schedule", schedule_id, {"name": name})
     return redirect(url_for("ansible.schedules"))
 
 
@@ -514,6 +580,8 @@ async def run_schedule_now(schedule_id: str):
                 fresh.last_run_at = datetime.now(timezone.utc)
                 fresh.last_run_id = run.id if run else None
                 fresh.last_error = err
+    await _audit("ansible.schedule.run_now", "ansible_schedule", schedule_id,
+                 {"playbook": playbook_path, "run_id": run.id if run else None, "error": err})
     if run:
         return redirect(url_for("ansible.run_detail", run_id=run.id))
     return redirect(url_for("ansible.schedules"))
@@ -590,6 +658,9 @@ async def save_playbook():
             content=content, error=err,
         ), 400
 
+    await _audit("ansible.playbook.updated" if editing else "ansible.playbook.created",
+                 "ansible_playbook", f"{source_name}:{playbook_path}",
+                 {"source": source_name, "playbook": playbook_path, "bytes": len(content)})
     return redirect(url_for(
         "ansible.view_playbook", source_name=source_name, playbook_path=playbook_path))
 
@@ -601,9 +672,12 @@ async def delete_playbook():
     source = _editable_source((form.get("source_name", "") or "").strip())
     if source is None:
         return "Source is not editable", 400
-    ok, err = src_module.delete_playbook(source["path"], (form.get("playbook_path", "") or "").strip())
+    playbook_path = (form.get("playbook_path", "") or "").strip()
+    ok, err = src_module.delete_playbook(source["path"], playbook_path)
     if not ok:
         return err, 400
+    await _audit("ansible.playbook.deleted", "ansible_playbook", f"{source['name']}:{playbook_path}",
+                 {"source": source["name"], "playbook": playbook_path})
     return redirect(url_for("ansible.browse"))
 
 

steward/ansible/runner.py

@@ -10,7 +10,7 @@ import asyncio
 import uuid
 from datetime import datetime, timezone
 
-from steward.ansible import executor, sources as src_module
+from steward.ansible import executor, guards, sources as src_module
 from steward.ansible.inventory_gen import (
     fetch_scope_targets, generate_inventory, inventory_to_yaml,
 )
@@ -28,6 +28,7 @@ async def trigger_run(
     inventory_content: str | None = None,
     connection: dict | None = None,
     secret_vars: dict | None = None,
+    redact: list[str] | None = None,
 ):
     """Resolve inventory for the scope, persist an AnsibleRun, and launch it.
 
@@ -39,7 +40,8 @@ async def trigger_run(
     first-contact provisioning — passed to the executor but deliberately NOT
     stored on the AnsibleRun row (params), so the password never lands in the DB.
     secret_vars (sensitive run-time playbook variables) are likewise passed
-    through to the executor but never persisted.
+    through to the executor but never persisted. redact names further values
+    to mask in the run's output (a bespoke inventory's per-host tokens).
     Returns (run, source, error): on success error is None; on failure run is
     None and error is a short human-readable reason.
     """
@@ -47,6 +49,13 @@ async def trigger_run(
     source = next((s for s in sources if s["name"] == source_name), None)
     if source is None:
         return None, None, "Source not found"
+    # Every run path (web, MCP, alerts, schedules, plugins) arrives here, so
+    # this is where a run is held to what its source lists (ansible/guards.py).
+    err = guards.check_playbook(source, playbook_path)
+    if err is None and inventory_content is None:
+        err = guards.check_inventory_scope(source, inventory_scope)
+    if err:
+        return None, source, err
 
     inventory_path: str | None = None
     if inventory_content is not None:
@@ -55,11 +64,8 @@ async def trigger_run(
         async with app.db_sessionmaker() as db:
             targets = await fetch_scope_targets(db, inventory_scope)
         inventory_content = inventory_to_yaml(generate_inventory(targets))
-    elif inventory_scope.startswith("repo:"):
-        parts = inventory_scope.split(":", 2)
-        inventory_path = parts[2] if len(parts) == 3 else ""
     else:
-        return None, source, "Invalid inventory_scope"
+        inventory_path = inventory_scope.split(":", 2)[2]
 
     run_id = str(uuid.uuid4())
     run = AnsibleRun(
@@ -81,7 +87,7 @@ async def trigger_run(
         executor.start_run(
             app, run_id, playbook_path, inventory_path or "",
             source["path"], params or None, inventory_content,
-            connection=connection, secret_vars=secret_vars,
+            connection=connection, secret_vars=secret_vars, redact=redact,
         )
     )
     task.add_done_callback(

steward/ansible/sources.py

@@ -108,6 +108,13 @@ def is_editable_source(source: dict) -> bool:
     return source.get("type") == "local" and source.get("name") != BUILTIN_SOURCE_NAME
 
 
+def _open_token(src: dict) -> str:
+    """The source's git token in the clear (it is stored sealed)."""
+    from steward.core.crypto import decrypt_secret
+    from steward.core.settings import source_token_key
+    return decrypt_secret(src.get("http_token") or "", context=source_token_key(src.get("name", "?")))
+
+
 def get_sources(ansible_cfg: dict) -> list[dict]:
     """Return resolved source list from ansible config section.
 
@@ -149,7 +156,7 @@ def get_sources(ansible_cfg: dict) -> list[dict]:
             "url": src.get("url"),
             "branch": src.get("branch", "main"),
             "pull_interval_seconds": int(src.get("pull_interval_seconds", 3600)),
-            "http_token": src.get("http_token", "") if src_type == "git" else "",
+            "http_token": _open_token(src) if src_type == "git" else "",
         })
     return result
 
@@ -323,11 +330,25 @@ def validate_playbook_yaml(content: str) -> tuple[bool, str | None]:
     return True, None
 
 
+# The askpass script holds no secret: git runs it with the token in its
+# environment, and printf prints it as data, so no character in a token can
+# become shell syntax.
+ASKPASS_TOKEN_ENV = "STEWARD_GIT_TOKEN"
+ASKPASS_SCRIPT = (
+    "#!/bin/sh\n"
+    'case "$1" in\n'
+    "  Username*) printf '%s\\n' oauth2 ;;\n"
+    f"  Password*) printf '%s\\n' \"${ASKPASS_TOKEN_ENV}\" ;;\n"
+    "esac\n"
+)
+
+
 async def git_pull(source: dict) -> None:
     """Clone the git repo if absent; pull if already present.
 
-    When source['http_token'] is set, injects credentials via a temporary
-    GIT_ASKPASS script so they never touch .git/config or process args.
+    When source['http_token'] is set, git asks a temporary GIT_ASKPASS script,
+    which prints the token from the child's environment, so it never touches
+    .git/config, process args or a file.
     """
     path = Path(source["path"])
     token = source.get("http_token", "")
@@ -337,18 +358,11 @@ async def git_pull(source: dict) -> None:
     if token:
         fd, askpass_path = tempfile.mkstemp(prefix="steward-askpass-", suffix=".sh")
         try:
-            script = (
-                "#!/bin/sh\n"
-                'case "$1" in\n'
-                '  Username*) echo "oauth2" ;;\n'
-                f'  Password*) echo "{token}" ;;\n'
-                "esac\n"
-            )
-            os.write(fd, script.encode())
+            os.write(fd, ASKPASS_SCRIPT.encode())
         finally:
             os.close(fd)
         os.chmod(askpass_path, stat.S_IRWXU)
-        env = {**os.environ, "GIT_ASKPASS": askpass_path}
+        env = {**os.environ, "GIT_ASKPASS": askpass_path, ASKPASS_TOKEN_ENV: token}
 
     try:
         if not (path / ".git").exists():

steward/app.py

@@ -3,9 +3,12 @@ from __future__ import annotations
 import asyncio
 import logging
 from pathlib import Path
-from quart import Quart, render_template
+from quart import Quart, render_template, request
 from .config import load_bootstrap
-from .database import init_db
+from .database import (
+    init_db, ensure_database_reachable, DatabaseUnavailable,
+    DB_CONNECT_TIMEOUT_SECONDS,
+)
 
 logger = logging.getLogger(__name__)
 
@@ -23,6 +26,7 @@ def create_app(
         bootstrap = {
             "database_url": "postgresql+asyncpg://test/test",
             "secret_key": "test-secret-key",
+            "db_connect_timeout": DB_CONNECT_TIMEOUT_SECONDS,
             "plugin_dirs": ["plugins"],
             "plugin_install_dir": "plugins",
         }
@@ -33,6 +37,9 @@ def create_app(
         PLUGIN_DIRS=bootstrap["plugin_dirs"],
         PLUGIN_INSTALL_DIR=bootstrap["plugin_install_dir"],
         TESTING=testing,
+        # Lax keeps the session cookie off cross-site POSTs and iframes; the
+        # CSRF token below is the check that does not depend on the browser.
+        SESSION_COOKIE_SAMESITE="Lax",
     )
 
     # ── 2. Init DB engine ──────────────────────────────────────────────────────
@@ -42,6 +49,19 @@ def create_app(
         from unittest.mock import MagicMock
         app.db_sessionmaker = MagicMock()
 
+    # ── 2b. Block until the database is actually reachable ────────────────────
+    # Everything from here down touches the DB synchronously (migrations,
+    # secret re-encryption, settings load). Gate all of it behind one readiness
+    # check so a DB that is merely slow to come up — WAL recovery after an
+    # unclean shutdown, or Docker DNS not yet serving the `db` name after a host
+    # reboot — is waited out instead of crashing the container on a traceback.
+    if not testing:
+        from .database import wait_for_database
+        wait_for_database(
+            app.config["DATABASE_URL"],
+            timeout_seconds=bootstrap["db_connect_timeout"],
+        )
+
     # ── 3. Core migrations only (creates app_settings table) ──────────────────
     if not testing:
         from .core.migration_runner import run_core_migrations
@@ -70,13 +90,14 @@ def create_app(
         from .core.settings import (
             load_settings_sync, to_smtp_cfg, to_webhook_cfg,
             to_ansible_cfg, to_plugins_cfg, to_oidc_cfg, to_ldap_cfg,
-            to_thresholds_cfg,
+            to_thresholds_cfg, to_access_cfg,
         )
         _settings = load_settings_sync(app.config["DATABASE_URL"])
+        app.config.update(to_access_cfg(_settings))
         app.config.update(
-            SESSION_LIFETIME_HOURS=_settings.get("session.lifetime_hours", 8),
             DATA_RETENTION_DAYS=_settings.get("data.retention_days", 90),
             MONITORS_POLL_INTERVAL=_settings.get("monitors.poll_interval_seconds", 60),
+            PUBLIC_BASE_URL=_settings.get("general.public_base_url", ""),
             SMTP=to_smtp_cfg(_settings),
             WEBHOOK=to_webhook_cfg(_settings),
             ANSIBLE=to_ansible_cfg(_settings),
@@ -86,11 +107,12 @@ def create_app(
             THRESHOLDS=to_thresholds_cfg(_settings),
         )
     else:
-        from .core.settings import to_thresholds_cfg
+        from .core.settings import to_access_cfg, to_thresholds_cfg
+        app.config.update(to_access_cfg({}))
         app.config.update(
-            SESSION_LIFETIME_HOURS=8,
             DATA_RETENTION_DAYS=90,
             MONITORS_POLL_INTERVAL=60,
+            PUBLIC_BASE_URL="",
             SMTP={},
             WEBHOOK={},
             ANSIBLE={},
@@ -108,6 +130,51 @@ def create_app(
         lambda value, kind: _ts_for(value, kind, app.config.get("THRESHOLDS", {}))
     )
 
+    # One way to write a size, a rate, a span and a moment, and to grade a
+    # reading ('ok' / 'warn' / 'crit' / 'unknown') against the same cutoffs.
+    from .core import formatting as _fmt
+    app.jinja_env.filters["bytes"] = _fmt.human_bytes
+    app.jinja_env.filters["rate"] = _fmt.human_rate
+    app.jinja_env.filters["duration"] = _fmt.human_duration
+    app.jinja_env.filters["ago"] = _fmt.ago
+    app.jinja_env.globals["status_class"] = (
+        lambda value, kind: _fmt.status_class(value, kind, app.config.get("THRESHOLDS", {}))
+    )
+    # The status and layout macros in _macros.html read these.
+    app.jinja_env.globals["status_info"] = _fmt.status_info
+    app.jinja_env.globals["required"] = _fmt.required
+
+    # Forged-request protection: every POST form renders csrf_field(), HTMX and
+    # fetch() send csrf_token() as X-CSRF-Token, and one check refuses any
+    # unsafe request without it (steward/auth/csrf.py).
+    from .auth import csrf as _csrf
+    app.jinja_env.globals["csrf_token"] = _csrf.csrf_token
+    app.jinja_env.globals["csrf_field"] = _csrf.csrf_field
+    app.before_request(_csrf.check_request)
+    # The session cookie is Secure, and HSTS is sent, only on requests that
+    # arrived over HTTPS — directly or as a trusted proxy reports it
+    # (steward/core/proxy.py). Plain-HTTP and LAN use keep working.
+    from quart import has_request_context
+    from quart.sessions import SecureCookieSessionInterface
+    from .core.proxy import is_https
+
+    class _SessionInterface(SecureCookieSessionInterface):
+        def get_cookie_secure(self, app):
+            return bool(app.config.get("SESSION_COOKIE_SECURE")) or (
+                has_request_context() and is_https())
+
+    app.session_interface = _SessionInterface()
+
+    @app.after_request
+    async def _hsts(response):
+        if is_https():
+            response.headers.setdefault("Strict-Transport-Security", "max-age=31536000")
+        return response
+
+    # Default-deny: a view with neither require_role nor public_route is refused.
+    from .auth.middleware import check_view_is_marked, public_route
+    app.before_request(check_view_is_marked)
+
     # ── 5. Plugin migrations ───────────────────────────────────────────────────
     # Step 3 already applied all plugin migrations via discover_all_plugin_migration_dirs,
     # so this is a no-op on normal startup. We still run it with all discovered dirs so
@@ -133,6 +200,7 @@ def create_app(
     from .ansible.inventory_routes import inventory_bp
     from .settings.routes import settings_bp
     from .audit.routes import audit_bp
+    from .ai_access.routes import ai_access_bp
 
     app.register_blueprint(auth_bp)
     app.register_blueprint(dashboard_bp)
@@ -144,6 +212,7 @@ def create_app(
     app.register_blueprint(inventory_bp)
     app.register_blueprint(settings_bp)
     app.register_blueprint(audit_bp)
+    app.register_blueprint(ai_access_bp)
 
     # Register the unified Monitor status source for the Status page. Plugins
     # may register additional sources from setup(). Idempotent.
@@ -201,36 +270,50 @@ def create_app(
     # ── 11. Share-token middleware ─────────────────────────────────────────────
     @app.before_request
     async def _validate_share_token():
-        """If ?s=<token> is present, validate it and set g.share_viewer."""
+        """A share link's token (?s=) opens, read-only, exactly the widget
+        fragments its own dashboard loads (steward/dashboard/share.py)."""
         from quart import request, g
         raw = request.args.get("s")
-        if not raw:
+        if not raw or request.method != "GET":
             return
         try:
-            import hashlib
-            from datetime import datetime, timezone
-            from sqlalchemy import select
-            from .models.dashboard import DashboardShareToken
-            token_hash = hashlib.sha256(raw.encode()).hexdigest()
+            from .dashboard.share import share_grants
             async with app.db_sessionmaker() as db:
-                result = await db.execute(
-                    select(DashboardShareToken)
-                    .where(DashboardShareToken.token_hash == token_hash)
-                )
-                share = result.scalar_one_or_none()
-            if share:
-                now = datetime.now(timezone.utc)
-                if share.expires_at is None or share.expires_at > now:
+                if await share_grants(db, raw, request.path, request.args):
                     g.share_viewer = True
-                    g.share_dashboard_id = share.dashboard_id
         except Exception:
-            pass  # never block a request due to token validation failure
+            # A failed check grants nothing; the request falls through to login.
+            logging.getLogger(__name__).exception("Share token check failed")
 
     # ── 11. Health check ───────────────────────────────────────────────────────
     @app.get("/health")
+    @public_route("liveness probe for the container")
     async def health():
         return {"status": "ok"}
 
+    # ── 11b. Database availability gate ────────────────────────────────────────
+    # Every page in Steward reads the database, so a database that has gone away
+    # under a running app turns each request into an opaque 500 (this is how a
+    # login attempt surfaced a bare gaierror). Acquire a connection up front,
+    # retrying briefly to ride out a restart, and answer honestly if it stays
+    # down rather than failing deep inside a handler with a generic error.
+    if not testing:
+        @app.before_request
+        async def _database_gate():
+            # /health is a liveness probe for the container itself — it must
+            # stay answerable while the database is down, or a restart loop
+            # gets triggered by a dependency outage. Static files need no DB.
+            if request.endpoint in ("health", "static"):
+                return None
+            try:
+                await ensure_database_reachable(app._db_engine)
+            except DatabaseUnavailable as exc:
+                logger.error("Database unreachable while serving %s: %s",
+                             request.path, exc)
+                return await render_template(
+                    "errors/database_unavailable.html"), 503
+            return None
+
     # ── 12. Error handlers ─────────────────────────────────────────────────────
     @app.errorhandler(404)
     async def not_found(_):
@@ -240,6 +323,17 @@ def create_app(
     async def server_error(_):
         return await render_template("errors/500.html"), 500
 
+    # ── Session freshness: lifetime, deactivation and role changes apply per request
+    if not testing:
+        from .auth.middleware import refresh_session_user
+        app.before_request(refresh_session_user)
+
+    # ── MCP endpoint (/mcp) ───────────────────────────────────────────────────
+    # Mounted after plugins load so their register_mcp_tools() hooks are seen.
+    # It wraps app.asgi_app: /mcp never enters Quart's pipeline (see mcp/server.py).
+    from .mcp import mount_mcp
+    mount_mcp(app)
+
     # ── 11. Startup hook ───────────────────────────────────────────────────────
     @app.before_serving
     async def startup():
@@ -264,6 +358,14 @@ def _register_core_tasks(app: Quart) -> None:
         from .core.cleanup import run_cleanup as _cleanup
         await _cleanup(app)
 
+    async def run_alert_reconcile():
+        from .core.alerts import check_silence, notify_after_maintenance
+        for step in (check_silence, notify_after_maintenance):
+            try:
+                await step(app)
+            except Exception:
+                app.logger.exception("alert_reconcile: %s failed", step.__name__)
+
     async def run_report_check():
         from .core.reports import check_and_send
         await check_and_send(app)
@@ -288,6 +390,14 @@ def _register_core_tasks(app: Quart) -> None:
             interval_seconds=60,
             run_on_startup=True,
         ),
+        # Rules whose series has gone quiet get a visible no_data mark; alerts
+        # a maintenance window muted notify once it ends.
+        ScheduledTask(
+            name="alert_reconcile",
+            coro_factory=run_alert_reconcile,
+            interval_seconds=60,
+            run_on_startup=False,
+        ),
         ScheduledTask(
             name="monitor_check",
             coro_factory=run_monitor_checks,

steward/auth/csrf.py

@@ -0,0 +1,63 @@
+"""Forged-request (CSRF) protection for the browser side of Steward.
+
+A page on another site can make a logged-in browser POST to Steward, and the
+browser sends Steward's session cookie with it. Every state-changing request
+from a browser therefore has to carry a token that only Steward's own pages
+know: a random value kept in the session, written into each form by
+`csrf_field()` and sent by HTMX and fetch() as the `X-CSRF-Token` header (set
+once on <body> in base.html).
+
+One check in a before_request covers every route, so a new route cannot
+forget it. Callers that authenticate with a bearer token instead of the
+session cookie (the host agent's ingest; /mcp never reaches Quart) are exempt:
+a forged browser request cannot carry their token.
+"""
+from __future__ import annotations
+
+import hmac
+import secrets
+
+from markupsafe import Markup, escape
+from quart import Response, request, session
+
+SESSION_KEY = "_csrf"
+FORM_FIELD = "csrf_token"
+HEADER = "X-CSRF-Token"
+UNSAFE_METHODS = ("POST", "PUT", "PATCH", "DELETE")
+# Bearer-authenticated endpoints: no session cookie, nothing to forge.
+EXEMPT_PATHS = frozenset({"/plugins/host_agent/ingest"})
+
+
+def csrf_token() -> str:
+    """This session's token, created on first use."""
+    token = session.get(SESSION_KEY)
+    if not token:
+        token = session[SESSION_KEY] = secrets.token_urlsafe(32)
+    return token
+
+
+def csrf_field() -> Markup:
+    """The hidden input every POST form carries."""
+    return Markup(f'<input type="hidden" name="{FORM_FIELD}" value="{escape(csrf_token())}">')
+
+
+def rotate() -> None:
+    """Drop the token, so a new one is issued — at login, where the session
+    changes hands."""
+    session.pop(SESSION_KEY, None)
+
+
+async def check_request() -> Response | None:
+    """before_request hook: refuse an unsafe request without the session's token."""
+    if request.method not in UNSAFE_METHODS or request.path in EXEMPT_PATHS:
+        return None
+    expected = session.get(SESSION_KEY)
+    sent = request.headers.get(HEADER, "")
+    if not sent:
+        form = await request.form
+        sent = form.get(FORM_FIELD, "")
+    if expected and sent and hmac.compare_digest(expected, sent):
+        return None
+    return Response(
+        "This form has expired or did not come from Steward. Reload the page and try again.",
+        status=400, content_type="text/plain; charset=utf-8")

steward/auth/ldap_auth.py

@@ -18,6 +18,34 @@ def _ldap_available() -> bool:
         return False
 
 
+def filter_value(value: str) -> str:
+    """Escape a value for an LDAP search filter (RFC 4515), so a login name
+    like `*)(uid=*` matches only itself."""
+    out = []
+    for ch in value:
+        if ch in "\\*()\x00":
+            out.append("\\%02x" % ord(ch))
+        else:
+            out.append(ch)
+    return "".join(out)
+
+
+def transport(cfg: dict) -> tuple[bool, bool]:
+    """(use_ssl, start_tls) for the configured server: port 636 is LDAPS,
+    otherwise the TLS setting means StartTLS before any bind."""
+    if int(cfg.get("port", 389)) == 636:
+        return True, False
+    return False, bool(cfg.get("tls", False))
+
+
+def _tls(ldap3, cfg: dict):
+    """Certificate-checked TLS: against the CA the operator pasted in, else the
+    system's CAs. A server whose certificate does not check is refused."""
+    import ssl
+    ca = (cfg.get("ca_cert") or "").strip()
+    return ldap3.Tls(validate=ssl.CERT_REQUIRED, ca_certs_data=ca or None)
+
+
 def _ldap_authenticate_sync(cfg: dict, username: str, password: str) -> dict | None:
     """Synchronous LDAP auth. Returns user info dict or None on failure.
 
@@ -27,22 +55,23 @@ def _ldap_authenticate_sync(cfg: dict, username: str, password: str) -> dict | N
 
     host = cfg.get("host", "")
     port = int(cfg.get("port", 389))
-    use_tls = cfg.get("tls", False)
     bind_dn = cfg.get("bind_dn", "")
     bind_password = cfg.get("bind_password", "")
     base_dn = cfg.get("base_dn", "")
-    user_filter = cfg.get("user_filter", "(uid={username})").format(username=username)
+    user_filter = cfg.get("user_filter", "(uid={username})").replace("{username}", filter_value(username))
     admin_group_dn = cfg.get("admin_group_dn", "")
     operator_group_dn = cfg.get("operator_group_dn", "")
     attr_username = cfg.get("attr_username", "uid")
     attr_email = cfg.get("attr_email", "mail")
 
-    tls = ldap3.Tls() if use_tls else None
-    server = ldap3.Server(host, port=port, tls=tls, get_info=ldap3.ALL)
+    use_ssl, start_tls = transport(cfg)
+    tls = _tls(ldap3, cfg) if (use_ssl or start_tls) else None
+    server = ldap3.Server(host, port=port, use_ssl=use_ssl, tls=tls, get_info=ldap3.ALL)
+    auto_bind = ldap3.AUTO_BIND_TLS_BEFORE_BIND if start_tls else ldap3.AUTO_BIND_NO_TLS
 
     # Service account bind to search for user DN
     try:
-        svc_conn = ldap3.Connection(server, user=bind_dn, password=bind_password, auto_bind=True)
+        svc_conn = ldap3.Connection(server, user=bind_dn, password=bind_password, auto_bind=auto_bind)
     except Exception as exc:
         logger.error("LDAP service bind failed: %s", exc)
         return None
@@ -69,7 +98,7 @@ def _ldap_authenticate_sync(cfg: dict, username: str, password: str) -> dict | N
 
     # Bind as the user to verify password
     try:
-        user_conn = ldap3.Connection(server, user=user_dn, password=password, auto_bind=True)
+        user_conn = ldap3.Connection(server, user=user_dn, password=password, auto_bind=auto_bind)
         user_conn.unbind()
     except Exception:
         logger.debug("LDAP password verify failed for %s", username)
@@ -83,6 +112,7 @@ def _ldap_authenticate_sync(cfg: dict, username: str, password: str) -> dict | N
         role = "operator"
 
     return {
+        "subject": user_dn,
         "username": ldap_username,
         "email": ldap_email,
         "role": role,
@@ -90,7 +120,12 @@ def _ldap_authenticate_sync(cfg: dict, username: str, password: str) -> dict | N
 
 
 async def ldap_authenticate(cfg: dict, username: str, password: str) -> dict | None:
-    """Async wrapper around synchronous LDAP auth. Returns user info or None."""
+    """Async wrapper around synchronous LDAP auth. Returns user info or None.
+
+    An empty password is refused here: LDAP treats a simple bind with a DN
+    and no password as an anonymous bind, which succeeds."""
+    if not username or not password:
+        return None
     if not _ldap_available():
         logger.warning("ldap3 not installed — LDAP auth unavailable")
         return None

steward/auth/middleware.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 import functools
+import time
 from urllib.parse import quote, urlsplit
 from quart import session, redirect, url_for, abort, g, request, Response
 from steward.models.users import UserRole
@@ -77,15 +78,74 @@ def require_role(minimum_role: UserRole):
             if _ROLE_ORDER.index(user_role) < _ROLE_ORDER.index(minimum_role):
                 abort(403)
             return await f(*args, **kwargs)
+        wrapper.steward_role = minimum_role
         return wrapper
     return decorator
 
 
+def public_route(reason: str):
+    """Mark a view that is deliberately reachable without a role — login,
+    the health probe, a bearer-authenticated endpoint. Every other view must
+    carry require_role; check_view_is_marked refuses one that has neither, so
+    a route that forgets its decorator is closed rather than open."""
+    def decorator(f):
+        f.steward_public = reason
+        return f
+    return decorator
+
+
+async def check_view_is_marked() -> Response | None:
+    """before_request hook: default-deny for views with neither require_role
+    nor public_route. Static files and unmatched paths (404) pass through."""
+    from quart import current_app
+    endpoint = request.endpoint
+    if endpoint is None or endpoint == "static" or endpoint.endswith(".static"):
+        return None
+    view = current_app.view_functions.get(endpoint)
+    if view is None or hasattr(view, "steward_role") or hasattr(view, "steward_public"):
+        return None
+    current_app.logger.error("Refused %s: view %r has no require_role or public_route",
+                             request.path, endpoint)
+    abort(403)
+
+
 def login_user(user) -> None:
-    """Write user identity into the session."""
+    """Write user identity into the session, with a fresh CSRF token."""
+    from steward.auth.csrf import rotate
+    rotate()
+    session.permanent = True
     session["user_id"] = user.id
     session["user_role"] = user.role.value
     session["username"] = user.username
+    session["login_at"] = time.time()
+
+
+async def refresh_session_user() -> None:
+    """before_request: a session speaks for the user as they are now.
+
+    A login ends once Settings → General's session lifetime has passed since
+    it began (not since the last request: the cookie is re-signed on every
+    response, so the cookie's own age would let an active session live
+    forever). A user who has been deleted or deactivated is logged out on
+    their next request, and a role change applies at once.
+    """
+    user_id = session.get("user_id")
+    if not user_id:
+        return
+    from quart import current_app
+    from steward.models.users import User
+    lifetime = current_app.config.get("PERMANENT_SESSION_LIFETIME")
+    started = session.get("login_at") or 0
+    if lifetime is not None and time.time() - started > lifetime.total_seconds():
+        session.clear()
+        return
+    async with current_app.db_sessionmaker() as db:
+        user = await db.get(User, user_id)
+    if user is None or not user.is_active:
+        session.clear()
+        return
+    if session.get("user_role") != user.role.value:
+        session["user_role"] = user.role.value
 
 
 def logout_user() -> None:

steward/auth/oidc.py

@@ -95,6 +95,25 @@ def decode_id_token_payload(id_token: str) -> dict:
         return {}
 
 
+def id_token_refusal(id_token: str, nonce: str | None, userinfo_sub: str) -> str | None:
+    """Why this sign-in's ID token does not belong to it, or None when it does.
+
+    The token must carry the nonce this browser was sent off with, so a token
+    from another sign-in cannot be replayed into this one, and name the same
+    subject as the userinfo response (OIDC Core 5.3.2). The signature is not
+    checked (see the module note)."""
+    if not userinfo_sub:
+        return "SSO returned no subject (sub) for this user."
+    claims = decode_id_token_payload(id_token) if id_token else {}
+    if not claims:
+        return "SSO returned no ID token. Check that the scopes include openid."
+    if not nonce or claims.get("nonce") != nonce:
+        return "This SSO sign-in does not match the one Steward started. Try again."
+    if claims.get("sub") != userinfo_sub:
+        return "SSO returned an ID token for a different user. Try again."
+    return None
+
+
 def map_role(groups: list[str], admin_group: str, operator_group: str) -> str:
     """Map IdP groups to a local role string."""
     if admin_group and admin_group in groups:

steward/auth/routes.py

@@ -2,37 +2,71 @@ from __future__ import annotations
 import bcrypt
 from quart import Blueprint, render_template, request, redirect, url_for, session
 from sqlalchemy import select, func
-from steward.auth.middleware import login_user, logout_user, safe_next_url
+from steward.auth.middleware import login_user, logout_user, public_route, safe_next_url
+from steward.auth.throttle import login_throttle
+from steward.core.proxy import client_ip
 from steward.models.users import User, UserRole
 
 auth_bp = Blueprint("auth", __name__)
 
 
-async def _provision_external_user(app, username: str, email: str, role_str: str):
-    """Create or update a user from an external auth provider (OIDC/LDAP).
+_SOURCE_LABEL = {"ldap": "LDAP", "oidc": "SSO"}
 
-    External users get a randomised unusable password so local login is blocked.
-    Their role is updated on every login to reflect current IdP group membership.
+
+async def _provision_external_user(app, source: str, subject: str, username: str,
+                                   email: str, role_str: str) -> tuple[User | None, str | None]:
+    """The Steward user for an identity a provider vouched for: (user, None),
+    or (None, the reason to show at the login page).
+
+    Found by (source, subject) only. A first sign-in creates the user with an
+    unusable password; a username or email another account already holds is
+    refused rather than merged, so a directory entry named `admin` cannot sign
+    in as the local admin. The role follows the provider's groups on every
+    sign-in; a user disabled in Steward stays out.
     """
     import secrets
-    from steward.models.users import UserRole
+    from sqlalchemy.exc import IntegrityError
+    label = _SOURCE_LABEL[source]
+    if not subject or len(subject) > 512 or not username or len(username) > 64:
+        return None, f"{label} returned a username or id Steward cannot store (at most 64 characters)."
+    new_role = UserRole(role_str)
     async with app.db_sessionmaker() as db:
-        result = await db.execute(select(User).where(User.username == username))
-        user = result.scalar_one_or_none()
-        new_role = UserRole(role_str)
-        async with db.begin():
-            if user is None:
-                unusable_hash = bcrypt.hashpw(secrets.token_bytes(32), bcrypt.gensalt()).decode()
-                user = User(username=username, email=email or f"{username}@external",
-                            password_hash=unusable_hash, role=new_role)
-                db.add(user)
-            else:
-                if user.role != new_role:
+        try:
+            async with db.begin():
+                user = (await db.execute(select(User).where(
+                    User.auth_source == source, User.external_id == subject))).scalar_one_or_none()
+                if user is not None:
+                    if not user.is_active:
+                        return None, "This account is disabled in Steward."
                     user.role = new_role
-    # Re-fetch committed user
-    async with app.db_sessionmaker() as db:
-        result = await db.execute(select(User).where(User.username == username))
-        return result.scalar_one()
+                else:
+                    email = email or f"{username}@{source}"
+                    clash = (await db.execute(select(User.username).where(
+                        (User.username == username) | (User.email == email)))).first()
+                    if clash is not None:
+                        return None, (
+                            f"Steward already has an account named {clash[0]} with this username "
+                            f"or email, and it does not sign in with {label}. An admin must rename "
+                            f"or remove it before this {label} account can sign in.")
+                    user = User(username=username, email=email, role=new_role,
+                                password_hash=bcrypt.hashpw(secrets.token_bytes(32),
+                                                            bcrypt.gensalt()).decode(),
+                                auth_source=source, external_id=subject)
+                    db.add(user)
+        except IntegrityError:
+            # Another sign-in created the same name between our check and insert.
+            return None, f"Could not create the {label} account; try signing in again."
+        db.expunge(user)
+    return user, None
+
+
+async def _login_refused(message: str, next_url: str | None = None):
+    """The login page with why a provider-vouched sign-in was still refused."""
+    from quart import current_app
+    return await render_template(
+        "auth/login.html", error=message,
+        oidc_enabled=current_app.config.get("OIDC", {}).get("enabled", False),
+        next_url=safe_next_url(next_url)), 403
 
 
 async def get_user_count(app) -> int:
@@ -48,6 +82,7 @@ async def get_user_by_username(app, username: str) -> User | None:
 
 
 @auth_bp.get("/login")
+@public_route("the login page")
 async def login():
     from quart import current_app
     if await get_user_count(current_app) == 0:
@@ -59,6 +94,7 @@ async def login():
 
 
 @auth_bp.post("/login")
+@public_route("the login form")
 async def login_post():
     from quart import current_app
     from steward.core.audit import log_audit
@@ -68,9 +104,26 @@ async def login_post():
     password = password_str.encode()
     dest = safe_next_url(form.get("next")) or url_for("dashboard.index")
 
+    # Too many recent failures from this address: refuse before checking anything.
+    ip = client_ip()
+    wait_s = login_throttle.retry_after(
+        ip, current_app.config.get("LOGIN_MAX_FAILURES", 5),
+        current_app.config.get("LOGIN_LOCKOUT_MINUTES", 15) * 60)
+    if wait_s:
+        oidc_cfg = current_app.config.get("OIDC", {})
+        return await render_template(
+            "auth/login.html",
+            error=f"Too many failed logins from this address. Try again in "
+                  f"{max(1, round(wait_s / 60))} minute{'s' if wait_s > 90 else ''}.",
+            oidc_enabled=oidc_cfg.get("enabled", False),
+            next_url=safe_next_url(form.get("next")),
+        ), 429
+
     # Try local auth first
     user = await get_user_by_username(current_app, username)
-    if user and user.is_active and bcrypt.checkpw(password, user.password_hash.encode()):
+    if (user and user.auth_source == "local" and user.is_active
+            and bcrypt.checkpw(password, user.password_hash.encode())):
+        login_throttle.succeeded(ip)
         login_user(user)
         await log_audit(current_app, user.id, user.username, "auth.login",
                         detail={"method": "local", "role": user.role.value})
@@ -82,14 +135,20 @@ async def login_post():
         from steward.auth.ldap_auth import ldap_authenticate
         ldap_info = await ldap_authenticate(ldap_cfg, username, password_str)
         if ldap_info:
-            user = await _provision_external_user(
-                current_app, ldap_info["username"], ldap_info["email"], ldap_info["role"]
-            )
+            user, refusal = await _provision_external_user(
+                current_app, "ldap", ldap_info["subject"], ldap_info["username"],
+                ldap_info["email"], ldap_info["role"])
+            if refusal:
+                return await _login_refused(refusal, form.get("next"))
+            login_throttle.succeeded(ip)
             login_user(user)
             await log_audit(current_app, user.id, user.username, "auth.login",
                             detail={"method": "ldap", "role": user.role.value})
             return redirect(dest)
 
+    login_throttle.failed(ip)
+    await log_audit(current_app, None, username or "(blank)", "auth.login_failed",
+                    detail={"address": ip})
     oidc_cfg = current_app.config.get("OIDC", {})
     return await render_template(
         "auth/login.html",
@@ -100,6 +159,7 @@ async def login_post():
 
 
 @auth_bp.get("/login/oidc")
+@public_route("starts SSO login")
 async def login_oidc():
     from quart import current_app
     from steward.auth.oidc import get_discovery, build_authorize_url, generate_state
@@ -125,9 +185,11 @@ async def login_oidc():
 
 
 @auth_bp.get("/login/oidc/callback")
+@public_route("SSO login callback")
 async def login_oidc_callback():
     from quart import current_app
-    from steward.auth.oidc import get_discovery, exchange_code, get_userinfo, map_role
+    from steward.auth.oidc import (get_discovery, exchange_code, get_userinfo, map_role,
+                                    id_token_refusal)
     from steward.core.audit import log_audit
 
     oidc_cfg = current_app.config.get("OIDC", {})
@@ -143,6 +205,7 @@ async def login_oidc_callback():
         return await render_template("auth/login.html", error="Invalid SSO state — try again.",
                                      oidc_enabled=True), 400
 
+    nonce = session.pop("oidc_nonce", None)
     try:
         doc = await get_discovery(oidc_cfg["discovery_url"])
         redirect_uri = url_for("auth.login_oidc_callback", _external=True)
@@ -154,23 +217,25 @@ async def login_oidc_callback():
         return await render_template("auth/login.html", error=f"SSO login failed: {exc}",
                                      oidc_enabled=True), 502
 
+    refusal = id_token_refusal(tokens.get("id_token", ""), nonce, userinfo.get("sub", ""))
+    if refusal:
+        return await render_template("auth/login.html", error=refusal, oidc_enabled=True), 400
+
     username_claim = oidc_cfg.get("username_claim", "preferred_username")
     email_claim = oidc_cfg.get("email_claim", "email")
     groups_claim = oidc_cfg.get("groups_claim", "groups")
 
-    username = userinfo.get(username_claim) or userinfo.get("sub", "")
-    email = userinfo.get(email_claim, "") or f"{username}@oidc"
+    subject = userinfo["sub"]
+    username = userinfo.get(username_claim) or subject
+    email = userinfo.get(email_claim, "")
     groups = userinfo.get(groups_claim, [])
     if not isinstance(groups, list):
         groups = []
     role = map_role(groups, oidc_cfg.get("admin_group", ""), oidc_cfg.get("operator_group", ""))
 
-    if not username:
-        return await render_template("auth/login.html",
-                                     error="SSO returned no username.",
-                                     oidc_enabled=True), 400
-
-    user = await _provision_external_user(current_app, username, email, role)
+    user, refusal = await _provision_external_user(current_app, "oidc", subject, username, email, role)
+    if refusal:
+        return await _login_refused(refusal, session.pop("oidc_next", None))
     login_user(user)
     await log_audit(current_app, user.id, user.username, "auth.login",
                     detail={"method": "oidc", "role": role})
@@ -178,13 +243,15 @@ async def login_oidc_callback():
     return redirect(dest)
 
 
-@auth_bp.get("/logout")
+@auth_bp.post("/logout")
+@public_route("ends the session")
 async def logout():
     logout_user()
     return redirect(url_for("auth.login"))
 
 
 @auth_bp.get("/setup")
+@public_route("first-run setup (refuses once a user exists)")
 async def setup():
     from quart import current_app
     if await get_user_count(current_app) > 0:
@@ -196,6 +263,7 @@ async def setup():
 
 
 @auth_bp.post("/setup")
+@public_route("first-run setup (refuses once a user exists)")
 async def setup_post():
     from quart import current_app
     from steward.core.audit import log_audit

steward/auth/throttle.py

@@ -0,0 +1,48 @@
+"""Pause password guessing: after too many failed logins from one address,
+that address's logins are refused for a while.
+
+Keyed by client address (steward/core/proxy.py: behind a trusted proxy, the
+address it reports), not by username, so nobody can lock a user out by
+failing logins in their name. Held in memory: a restart forgets it, which
+costs an attacker nothing they couldn't get by waiting, and keeps it free of
+the database. The limits are Settings → General (login.max_failures,
+login.lockout_minutes).
+"""
+from __future__ import annotations
+
+import time
+from collections import deque
+
+
+class LoginThrottle:
+    def __init__(self) -> None:
+        self._failures: dict[str, deque[float]] = {}
+
+    def _recent(self, key: str, window_s: float, now: float) -> deque[float]:
+        times = self._failures.get(key)
+        if times is None:
+            return deque()
+        while times and times[0] <= now - window_s:
+            times.popleft()
+        if not times:
+            del self._failures[key]
+        return times
+
+    def retry_after(self, key: str, max_failures: int, window_s: float,
+                    now: float | None = None) -> int:
+        """Seconds until `key` may try again; 0 when it may try now."""
+        now = time.monotonic() if now is None else now
+        times = self._recent(key, window_s, now)
+        if len(times) < max_failures:
+            return 0
+        return max(1, int(times[-max_failures] + window_s - now) + 1)
+
+    def failed(self, key: str, now: float | None = None) -> None:
+        now = time.monotonic() if now is None else now
+        self._failures.setdefault(key, deque()).append(now)
+
+    def succeeded(self, key: str) -> None:
+        self._failures.pop(key, None)
+
+
+login_throttle = LoginThrottle()

steward/config.py

@@ -49,6 +49,8 @@ def load_bootstrap(config_path: Path | str | None = None) -> dict[str, Any]:
 
     secret_key = _resolve_secret_key(raw)
 
+    db_connect_timeout = _resolve_db_connect_timeout(raw)
+
     # Plugin discovery spans two roots (see load_plugins / migration_runner):
     #   • bundled  — first-party plugins shipped inside the image at repo-root
     #     `plugins/`; they version atomically with core and are read-only at runtime.
@@ -68,12 +70,47 @@ def load_bootstrap(config_path: Path | str | None = None) -> dict[str, Any]:
     return {
         "database_url": database_url,
         "secret_key": secret_key,
+        "db_connect_timeout": db_connect_timeout,
         "plugin_dirs": plugin_dirs,
         # Installs/downloads target the external (writable, persistent) dir.
         "plugin_install_dir": external_plugin_dir or bundled_plugin_dir,
     }
 
 
+def _resolve_db_connect_timeout(raw: dict) -> float:
+    """How long to wait for the database at startup, in seconds.
+
+    Bootstrap-only by necessity: this governs reaching the DB, so it cannot
+    itself be read from the DB like the rest of Steward's settings.
+
+    A deployment whose database is slower to come up than the default (a large
+    cluster replaying WAL, a remote DB behind a link that takes a while) can
+    raise it rather than crash-looping the container.
+    """
+    from .database import DB_CONNECT_TIMEOUT_SECONDS
+
+    value = _env("DB_CONNECT_TIMEOUT") or raw.get("database", {}).get("connect_timeout")
+    if value is None or value == "":
+        return DB_CONNECT_TIMEOUT_SECONDS
+    try:
+        parsed = float(value)
+    except (TypeError, ValueError):
+        logger.warning(
+            "Invalid database connect timeout %r — using default %.0fs",
+            value, DB_CONNECT_TIMEOUT_SECONDS,
+        )
+        return DB_CONNECT_TIMEOUT_SECONDS
+    if parsed <= 0:
+        # 0/negative would mean "never wait", which is the broken behaviour this
+        # setting exists to fix — treat it as a mistake, not as an opt-out.
+        logger.warning(
+            "Database connect timeout %.0fs is not positive — using default %.0fs",
+            parsed, DB_CONNECT_TIMEOUT_SECONDS,
+        )
+        return DB_CONNECT_TIMEOUT_SECONDS
+    return parsed
+
+
 def _resolve_secret_key(raw: dict) -> str:
     """Resolve secret_key: env var → file → auto-generate.
 

steward/core/alerts.py

@@ -2,10 +2,11 @@ from __future__ import annotations
 import asyncio
 import logging
 import uuid
-from datetime import datetime, timezone
+from dataclasses import dataclass
+from datetime import datetime, timedelta, timezone
 from typing import TYPE_CHECKING
 
-from sqlalchemy import and_, or_, select
+from sqlalchemy import event as sa_event, select
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from steward.models.alerts import (
@@ -16,6 +17,7 @@ from steward.models.alerts import (
     AlertStateEnum,
     MaintenanceWindow,
 )
+from steward.core.formatting import human_duration
 from steward.models.metrics import PluginMetric
 
 if TYPE_CHECKING:
@@ -56,82 +58,227 @@ async def record_metric(
     metric_name: str,
     value: float,
 ) -> None:
-    """Write a metric row and evaluate alert rules inline.
+    """One metric sample: record_metrics with a single row."""
+    await record_metrics(session, [PluginMetric(
+        source_module=source_module, resource_name=resource_name,
+        metric_name=metric_name, value=value)])
 
-    Must be called inside an active transaction:
-        async with session.begin():
-            await record_metric(session, ...)
 
-    Notification I/O is deferred via asyncio.create_task() so no network
-    calls occur while the transaction is open.
+class MetricBatch:
+    """Gathers one transaction's samples so they are recorded, and their alert
+    rules evaluated, in a single record_metrics call:
+
+        batch = MetricBatch()
+        batch.add(source_module="unifi", resource_name="wan", metric_name="is_up", value=1.0)
+        await batch.record(session)
     """
-    now = datetime.now(timezone.utc)
 
-    # Write metric row
-    metric = PluginMetric(
-        source_module=source_module,
-        resource_name=resource_name,
-        metric_name=metric_name,
-        value=value,
-        recorded_at=now,
-    )
-    session.add(metric)
+    def __init__(self) -> None:
+        self.rows: list[PluginMetric] = []
+
+    def add(self, source_module: str, resource_name: str, metric_name: str, value: float,
+            recorded_at: datetime | None = None) -> None:
+        self.rows.append(PluginMetric(source_module=source_module, resource_name=resource_name,
+                                      metric_name=metric_name, value=float(value),
+                                      recorded_at=recorded_at))
+
+    async def record(self, session: AsyncSession) -> None:
+        rows, self.rows = self.rows, []
+        await record_metrics(session, rows)
+
+
+def _in_window(w: MaintenanceWindow, source_module: str, resource_name: str) -> bool:
+    if w.scope_source is None:
+        return True
+    return w.scope_source == source_module and w.scope_resource in (None, resource_name)
+
+
+MUTED = "notification muted: maintenance window"
+RELEASED = "notified when the window ended"
+
+
+def _muted_by(windows, rule: AlertRule) -> str | None:
+    """The note an event carries when a maintenance window holds back its
+    notification, or None when no window covers the rule."""
+    w = next((w for w in windows if _in_window(w, rule.source_module, rule.resource_name)), None)
+    return f"{MUTED} {w.name}" if w else None
+
+
+# Notification and action tasks in flight. Held here so the event loop's weak
+# references are not the only ones (a dropped task is silently never run).
+_background: set[asyncio.Task] = set()
+
+_AFTER_COMMIT = "steward_alert_after_commit"
+
+
+def _spawn(coro) -> None:
+    task = asyncio.create_task(coro)
+    _background.add(task)
+    task.add_done_callback(_background.discard)
+
+
+def _after_commit(session: AsyncSession, fn, *args) -> None:
+    """Run fn(app, *args) once the session's transaction commits, and never if
+    it rolls back: a notification or a playbook run must describe what was
+    actually stored."""
+    if _app is None:
+        return
+    info = session.info
+    if _AFTER_COMMIT not in info:
+        info[_AFTER_COMMIT] = []
+        app = _app
+
+        def _committed(_sync_session) -> None:
+            jobs, info[_AFTER_COMMIT] = info[_AFTER_COMMIT], []
+            for job_fn, job_args in jobs:
+                _spawn(job_fn(app, *job_args))
+
+        def _rolled_back(_sync_session) -> None:
+            info[_AFTER_COMMIT] = []
+
+        sa_event.listen(session.sync_session, "after_commit", _committed)
+        sa_event.listen(session.sync_session, "after_rollback", _rolled_back)
+    info[_AFTER_COMMIT].append((fn, args))
+
+
+async def record_metrics(session: AsyncSession, rows: list[PluginMetric]) -> None:
+    """Write metric rows and evaluate the alert rules that watch them.
+
+    Every ingest path comes through here, so a rule on any metric Steward
+    records can fire. Must be called inside an active transaction:
+        async with session.begin():
+            await record_metrics(session, rows)
+
+    Maintenance windows, rules and their states are read once per batch, not
+    once per row. Each rule sees its key's samples oldest first, so a backlog
+    (an agent catching up after an outage) counts consecutive checks as they
+    happened. A maintenance window holds back notifications and actions, not
+    evaluation: the state still moves, and the event says it was muted.
+    Notifications and actions start only once the transaction commits.
+    """
+    if not rows:
+        return
+    now = datetime.now(timezone.utc)
+    for row in rows:
+        if row.recorded_at is None:
+            row.recorded_at = now
+    session.add_all(rows)
     await session.flush()
 
-    # Check active maintenance windows — skip rule evaluation if suppressed
-    mw_result = await session.execute(
-        select(MaintenanceWindow).where(
-            MaintenanceWindow.start_at <= now,
-            MaintenanceWindow.end_at >= now,
-            or_(
-                MaintenanceWindow.scope_source.is_(None),
-                and_(
-                    MaintenanceWindow.scope_source == source_module,
-                    or_(
-                        MaintenanceWindow.scope_resource.is_(None),
-                        MaintenanceWindow.scope_resource == resource_name,
-                    ),
-                ),
-            ),
-        ).limit(1)
-    )
-    if mw_result.scalar_one_or_none() is not None:
-        return  # suppressed by maintenance window
+    by_key: dict[tuple[str, str, str], list[PluginMetric]] = {}
+    for row in rows:
+        by_key.setdefault((row.source_module, row.resource_name, row.metric_name), []).append(row)
+    sources = {k[0] for k in by_key}
+    metric_names = {k[2] for k in by_key}
 
-    # Load matching enabled rules
-    result = await session.execute(
+    rules = (await session.execute(
         select(AlertRule).where(
-            AlertRule.source_module == source_module,
-            AlertRule.resource_name == resource_name,
-            AlertRule.metric_name == metric_name,
+            AlertRule.source_module.in_(sources),
+            AlertRule.metric_name.in_(metric_names),
             AlertRule.enabled.is_(True),
         )
-    )
-    rules = result.scalars().all()
+    )).scalars().all()
+    rules = [r for r in rules if (r.source_module, r.resource_name, r.metric_name) in by_key]
+    if not rules:
+        return
+
+    windows = (await session.execute(
+        select(MaintenanceWindow).where(
+            MaintenanceWindow.start_at <= now, MaintenanceWindow.end_at >= now)
+    )).scalars().all()
+    states = {st.rule_id: st for st in (await session.execute(
+        select(AlertState).where(AlertState.rule_id.in_([r.id for r in rules]))
+    )).scalars()}
 
     for rule in rules:
-        state_result = await session.execute(
-            select(AlertState).where(AlertState.rule_id == rule.id)
-        )
-        alert_state = state_result.scalar_one_or_none()
+        alert_state = states.get(rule.id)
         if alert_state is None:
-            logger.warning(f"No alert_state row for rule {rule.id}, skipping")
+            logger.warning("No alert_state row for rule %s, skipping", rule.id)
             continue
-
-        notifications = await _evaluate_rule(session, rule, alert_state, value, now)
-
-        for notif_type, event_id in notifications:
-            if _app is not None:
-                asyncio.create_task(
-                    _dispatch_notification(
-                        _app, notif_type, rule, value, event_id
-                    )
-                )
+        samples = sorted(by_key[(rule.source_module, rule.resource_name, rule.metric_name)],
+                         key=lambda r: r.recorded_at)
+        muted = _muted_by(windows, rule)
+        resumed = _track_samples(session, rule, alert_state, samples, now, muted)
+        if resumed and rule.notify_no_data and not muted:
+            event_id, value, note = resumed
+            _after_commit(session, _dispatch_notification, "data_resumed", rule, value,
+                          event_id, note)
+        for sample in samples:
+            notifications = await _evaluate_rule(session, rule, alert_state, sample.value,
+                                                 sample.recorded_at, note=muted)
+            if muted:
+                continue
+            for notif_type, event_id in notifications:
+                _after_commit(session, _dispatch_notification, notif_type, rule, sample.value,
+                              event_id)
                 # Admin-configured Ansible action runs only on transition-to-firing.
                 if notif_type == "firing" and rule.ansible_action:
-                    asyncio.create_task(
-                        _run_ansible_action(_app, rule, value, event_id)
-                    )
+                    _after_commit(session, _run_ansible_action, rule, sample.value, event_id)
+
+
+# A series is silent once it has gone this long without a sample, or three of
+# its usual gaps if that is longer. Until its cadence is known (fewer than two
+# samples seen), it gets an hour: a monitor may check only every ten minutes.
+NO_DATA_FLOOR_S = 300.0
+NO_DATA_GAPS = 3
+NO_DATA_UNKNOWN_S = 3600.0
+
+
+def next_interval(interval: float | None, gap: float) -> float:
+    """A series' usual gap between samples, updated with one more gap.
+
+    A smoothed average, so one late sample barely moves it. A gap longer than
+    the silence threshold counts only as that threshold: an outage is not the
+    series' cadence. A real change of cadence still gets learned, a step at a
+    time (each step at most 1.5x).
+    """
+    gap = max(0.0, gap)
+    if interval is None or interval <= 0:
+        return gap
+    return 0.75 * interval + 0.25 * min(gap, NO_DATA_GAPS * interval)
+
+
+def no_data_after(interval: float | None) -> float:
+    """Seconds without a sample before a series counts as silent."""
+    if not interval:
+        return NO_DATA_UNKNOWN_S
+    return max(NO_DATA_FLOOR_S, NO_DATA_GAPS * interval)
+
+
+def silent_since(last_sample_at: datetime | None, interval: float | None,
+                 watching_since: datetime, now: datetime) -> datetime | None:
+    """When a series went silent, or None while it is still reporting.
+
+    A series that has never had a sample counts from when the rule started
+    watching it (created, changed or re-enabled).
+    """
+    last = last_sample_at or watching_since
+    limit = timedelta(seconds=no_data_after(interval))
+    return last + limit if now - last > limit else None
+
+
+def _track_samples(session: AsyncSession, rule: AlertRule, state: AlertState,
+                   samples: list[PluginMetric], now: datetime, muted: str | None = None
+                   ) -> tuple[str, float, str] | None:
+    """Note a rule's new samples (oldest first) for silence tracking. When the
+    series had been marked no_data, clear it and record a resume event,
+    returned as (event_id, value, note) for the caller to notify. `muted` is
+    added to the event's note when a maintenance window holds it back."""
+    for sample in samples:
+        if state.last_sample_at is not None:
+            if sample.recorded_at <= state.last_sample_at:
+                continue  # late or duplicate: not a gap
+            gap = (sample.recorded_at - state.last_sample_at).total_seconds()
+            state.sample_interval_s = next_interval(state.sample_interval_s, gap)
+        state.last_sample_at = sample.recorded_at
+    if state.no_data_since is None or not samples:
+        return None
+    note = f"data resumed after {human_duration((now - state.no_data_since).total_seconds())} silent"
+    value = samples[-1].value
+    event_id = _add_event(session, rule.id, "no_data", state.state.value, value, now,
+                          note=f"{note}; {muted}" if muted else note)
+    state.no_data_since = None
+    return event_id, value, note
 
 
 def _is_breached(value: float, operator: AlertOperator, threshold: float) -> bool:
@@ -151,80 +298,109 @@ def _is_breached(value: float, operator: AlertOperator, threshold: float) -> boo
     return False
 
 
+@dataclass(frozen=True)
+class Step:
+    """One sample's effect on an alert: the state after it, the two run
+    counters, and the event to record ("firing" / "resolved") if any."""
+    state: AlertStateEnum
+    fail_count: int
+    ok_count: int
+    event: str | None = None
+
+
+def next_step(state: AlertStateEnum, fail_count: int, ok_count: int, breached: bool,
+              fail_required: int, ok_required: int) -> Step:
+    """The alert state machine, as a pure function of one sample.
+
+    inactive → pending → firing when `fail_required` breaching checks run in a
+    row; a non-breaching check while pending goes back to inactive.
+    firing and acknowledged resolve (to inactive, with a resolved event) only
+    after `ok_required` non-breaching checks in a row; a breaching check
+    resets that run. An acknowledgement holds while the alert is still
+    breached: only a resolve clears it.
+    """
+    fail_required, ok_required = max(1, fail_required), max(1, ok_required)
+    S = AlertStateEnum
+    if state in (S.firing, S.acknowledged):
+        if breached:
+            return Step(state, fail_count + 1, 0)
+        if ok_count + 1 >= ok_required:
+            return Step(S.inactive, 0, 0, "resolved")
+        return Step(state, fail_count, ok_count + 1)
+    # inactive, pending (and the transient resolved, read as inactive)
+    if not breached:
+        return Step(S.inactive, 0, 0)
+    fails = fail_count + 1 if state == S.pending else 1
+    if fails >= fail_required:
+        return Step(S.firing, fails, 0, "firing")
+    return Step(S.pending, fails, 0)
+
+
 async def _evaluate_rule(
     session: AsyncSession,
     rule: AlertRule,
     state: AlertState,
     value: float,
     now: datetime,
+    note: str | None = None,
 ) -> list[tuple[str, str]]:
-    """Evaluate a single rule against a metric value. Returns list of (notif_type, event_id)."""
-    breached = _is_breached(value, rule.operator, rule.threshold)
+    """Apply one sample to a rule's state. Returns [(notif_type, event_id)];
+    an event it records carries `note`."""
     from_state = state.state
+    step = next_step(from_state, state.consecutive_failure_count, state.consecutive_ok_count,
+                     _is_breached(value, rule.operator, rule.threshold),
+                     rule.consecutive_failures_required, rule.consecutive_ok_required)
+    state.consecutive_failure_count = step.fail_count
+    state.consecutive_ok_count = step.ok_count
     notifications: list[tuple[str, str]] = []
-
-    if state.state == AlertStateEnum.inactive:
-        if breached:
-            state.consecutive_failure_count = 1
-            if state.consecutive_failure_count >= rule.consecutive_failures_required:
-                state.state = AlertStateEnum.firing
-                state.last_transition_at = now
-                event_id = _add_event(session, rule.id, from_state.value, "firing", value, now)
-                notifications.append(("firing", event_id))
-            else:
-                state.state = AlertStateEnum.pending
-                state.last_transition_at = now
-
-    elif state.state == AlertStateEnum.pending:
-        if breached:
-            state.consecutive_failure_count += 1
-            if state.consecutive_failure_count >= rule.consecutive_failures_required:
-                state.state = AlertStateEnum.firing
-                state.last_transition_at = now
-                event_id = _add_event(session, rule.id, from_state.value, "firing", value, now)
-                notifications.append(("firing", event_id))
-        else:
-            state.consecutive_failure_count = 0
-            state.state = AlertStateEnum.inactive
-            state.last_transition_at = now
-
-    elif state.state == AlertStateEnum.firing:
-        if not breached:
-            # RESOLVED is transient: record event, notify, then immediately go inactive
-            event_id = _add_event(session, rule.id, from_state.value, "resolved", value, now)
-            notifications.append(("resolved", event_id))
-            state.consecutive_failure_count = 0
-            state.state = AlertStateEnum.inactive
-            state.last_transition_at = now
-
-    elif state.state == AlertStateEnum.acknowledged:
-        if not breached:
-            event_id = _add_event(session, rule.id, from_state.value, "resolved", value, now)
-            notifications.append(("resolved", event_id))
-            state.consecutive_failure_count = 0
-            state.state = AlertStateEnum.inactive
-            state.last_transition_at = now
+    if step.state != from_state:
+        state.state = step.state
+        state.last_transition_at = now
+        if step.state == AlertStateEnum.inactive:
             state.acknowledged_by = None
             state.acknowledged_at = None
-        else:
-            state.consecutive_failure_count += 1
-            if state.consecutive_failure_count >= rule.consecutive_failures_required:
-                state.state = AlertStateEnum.firing
-                state.last_transition_at = now
-                event_id = _add_event(session, rule.id, from_state.value, "firing", value, now)
-                notifications.append(("firing", event_id))
-
+    if step.event:
+        event_id = _add_event(session, rule.id, from_state.value, step.event, value, now,
+                              note=note)
+        notifications.append((step.event, event_id))
     await session.flush()
     return notifications
 
 
+async def reset_rule_state(session: AsyncSession, rule: AlertRule, note: str) -> None:
+    """Put a rule's alert back to inactive because the rule itself changed
+    (what it watches, its threshold, or it was disabled or re-enabled), and
+    start its silence watch over. An alert that was
+    firing or acknowledged gets a resolved event carrying `note`; nobody is
+    notified, since nothing about the watched resource changed."""
+    state = (await session.execute(
+        select(AlertState).where(AlertState.rule_id == rule.id))).scalar_one_or_none()
+    if state is None:
+        return
+    now = datetime.now(timezone.utc)
+    if state.state in (AlertStateEnum.firing, AlertStateEnum.acknowledged):
+        _add_event(session, rule.id, state.state.value, "resolved", None, now, note=note)
+    # The watch starts over now: silence is measured from here, against the
+    # cadence of whatever the rule watches from now on.
+    state.last_transition_at = now
+    state.last_sample_at = None
+    state.sample_interval_s = None
+    state.no_data_since = None
+    state.state = AlertStateEnum.inactive
+    state.consecutive_failure_count = 0
+    state.consecutive_ok_count = 0
+    state.acknowledged_by = None
+    state.acknowledged_at = None
+
+
 def _add_event(
     session: AsyncSession,
     rule_id: str,
     from_state: str,
     to_state: str,
-    value: float,
+    value: float | None,
     now: datetime,
+    note: str | None = None,
 ) -> str:
     """Add an AlertEvent row and return its ID."""
     event_id = str(uuid.uuid4())
@@ -235,6 +411,7 @@ def _add_event(
         to_state=to_state,
         metric_value=value,
         transitioned_at=now,
+        note=note,
     )
     session.add(event)
     return event_id
@@ -244,8 +421,9 @@ async def _dispatch_notification(
     app: "Quart",
     notif_type: str,
     rule: AlertRule,
-    value: float,
+    value: float | None,
     event_id: str,
+    note: str | None = None,
 ) -> None:
     """Run after the transaction commits. Sends notifications and updates the event row."""
     from steward.core.notifications import dispatch_notifications
@@ -258,6 +436,7 @@ async def _dispatch_notification(
         "threshold": rule.threshold,
         "resource": rule.resource_name,
         "source_module": rule.source_module,
+        "note": note,
         "timestamp": datetime.now(timezone.utc).isoformat(),
     }
 
@@ -291,32 +470,17 @@ async def _run_ansible_action(
 ) -> None:
     """Run the rule's configured Ansible playbook (system-triggered).
 
-    Runs after the evaluation transaction commits (scheduled via create_task).
-    Creates a system-triggered AnsibleRun, links it to the firing AlertEvent,
-    then executes it with the static params plus injected alert context vars.
+    Starts after the evaluation transaction commits. Goes through
+    runner.trigger_run like every other run path, so the playbook and the
+    inventory must be ones the source lists (ansible/guards.py). The firing
+    event links to the run, or says why the action did not start.
     """
-    from steward.ansible import executor, sources as src_module
-    from steward.models.ansible import AnsibleRun, AnsibleRunStatus
+    from steward.ansible.runner import trigger_run
 
     action = rule.ansible_action or {}
-    playbook = action.get("playbook")
-    inventory = action.get("inventory")
-    if not playbook or not inventory:
-        logger.error("Ansible action for rule %r missing playbook/inventory", rule.name)
-        return
-
-    try:
-        srcs = src_module.get_sources(app.config.get("ANSIBLE", {}))
-    except Exception:
-        logger.exception("Ansible action for rule %r: could not load sources", rule.name)
-        return
-    source = next((s for s in srcs if s["name"] == action.get("source")), None)
-    if source is None:
-        logger.error("Ansible action for rule %r: source %r not configured",
-                     rule.name, action.get("source"))
-        return
-
-    # Static params + auto-injected alert context (all argv, never shell).
+    playbook = action.get("playbook") or ""
+    inventory = action.get("inventory") or ""
+    source_name = action.get("source") or ""
     params: dict = {
         "extra_vars": list(action.get("extra_vars") or []) + alert_extra_vars(rule, value),
     }
@@ -326,22 +490,116 @@ async def _run_ansible_action(
         params["tags"] = action["tags"]
     if action.get("check"):
         params["check"] = True
+    scope = inventory if inventory.startswith("steward:") else f"repo:{source_name}:{inventory}"
+
+    if not playbook or not inventory:
+        run, err = None, "the action has no playbook or inventory"
+    else:
+        try:
+            run, _source, err = await trigger_run(
+                app, source_name=source_name, playbook_path=playbook,
+                inventory_scope=scope, params=params, triggered_by=None)
+        except Exception as exc:
+            logger.exception("Ansible action for rule %r failed to start", rule.name)
+            run, err = None, str(exc)
+    if err:
+        logger.error("Ansible action for rule %r not started: %s", rule.name, err)
 
-    run_id = str(uuid.uuid4())
     async with app.db_sessionmaker() as db:
         async with db.begin():
-            db.add(AnsibleRun(
-                id=run_id,
-                playbook_path=playbook,
-                inventory_path=inventory,
-                source_name=source["name"],
-                triggered_by=None,
-                status=AnsibleRunStatus.running,
-                params=params,
-            ))
-            event = (await db.execute(
+            ev = (await db.execute(
                 select(AlertEvent).where(AlertEvent.id == event_id))).scalar_one_or_none()
-            if event:
-                event.ansible_run_id = run_id
+            if ev is None:
+                return
+            if run is not None:
+                ev.ansible_run_id = run.id
+            else:
+                why = f"Ansible action not started: {err}"
+                ev.note = f"{ev.note}; {why}" if ev.note else why
 
-    await executor.start_run(app, run_id, playbook, inventory, source["path"], params)
+
+async def check_silence(app: "Quart") -> None:
+    """Mark the enabled rules whose series has gone silent (no_data).
+
+    Run every minute by the core scheduler. A rule is silent once its series
+    has had no sample for no_data_after(its usual gap); one that never had a
+    sample counts from when the rule started watching. The mark sits beside
+    the state, so a firing alert that goes silent stays firing. Each silence
+    is recorded once, as an event, and notified once (rule.notify_no_data,
+    outside maintenance windows), after the transaction commits.
+    """
+    now = datetime.now(timezone.utc)
+    notify: list[tuple[AlertRule, str, str]] = []
+    async with app.db_sessionmaker() as session:
+        async with session.begin():
+            rows = (await session.execute(
+                select(AlertState, AlertRule)
+                .join(AlertRule, AlertState.rule_id == AlertRule.id)
+                .where(AlertRule.enabled.is_(True), AlertState.no_data_since.is_(None))
+            )).all()
+            if not rows:
+                return
+            windows = (await session.execute(
+                select(MaintenanceWindow).where(
+                    MaintenanceWindow.start_at <= now, MaintenanceWindow.end_at >= now)
+            )).scalars().all()
+            for state, rule in rows:
+                watching_since = max(rule.created_at, state.last_transition_at)
+                since = silent_since(state.last_sample_at, state.sample_interval_s,
+                                     watching_since, now)
+                if since is None:
+                    continue
+                state.no_data_since = since
+                if state.last_sample_at is None:
+                    note = (f"no sample yet, {human_duration((now - watching_since).total_seconds())}"
+                            " after the rule started watching")
+                else:
+                    note = f"no sample for {human_duration((now - state.last_sample_at).total_seconds())}"
+                    if state.sample_interval_s:
+                        note += f" (usually every {human_duration(state.sample_interval_s)})"
+                muted = _muted_by(windows, rule)
+                event_id = _add_event(session, rule.id, state.state.value, "no_data", None,
+                                      now, note=f"{note}; {muted}" if muted else note)
+                if rule.notify_no_data and not muted:
+                    notify.append((rule, event_id, note))
+    for rule, event_id, note in notify:
+        _spawn(_dispatch_notification(app, "no_data", rule, None, event_id, note))
+
+
+async def notify_after_maintenance(app: "Quart") -> None:
+    """Notify the alerts that started firing inside a maintenance window and
+    are still firing now that no window covers them, and run their actions:
+    a window delays what it mutes, it does not discard it. Run every minute
+    by the core scheduler; each muted firing is released once."""
+    now = datetime.now(timezone.utc)
+    release: list[tuple[AlertRule, str, float | None]] = []
+    async with app.db_sessionmaker() as session:
+        async with session.begin():
+            rows = (await session.execute(
+                select(AlertState, AlertRule)
+                .join(AlertRule, AlertState.rule_id == AlertRule.id)
+                .where(AlertRule.enabled.is_(True), AlertState.state == AlertStateEnum.firing)
+            )).all()
+            if not rows:
+                return
+            windows = (await session.execute(
+                select(MaintenanceWindow).where(
+                    MaintenanceWindow.start_at <= now, MaintenanceWindow.end_at >= now)
+            )).scalars().all()
+            for state, rule in rows:
+                if _muted_by(windows, rule):
+                    continue
+                fired = (await session.execute(
+                    select(AlertEvent)
+                    .where(AlertEvent.rule_id == rule.id, AlertEvent.to_state == "firing")
+                    .order_by(AlertEvent.transitioned_at.desc()).limit(1)
+                )).scalar_one_or_none()
+                note = (fired.note or "") if fired else ""
+                if MUTED not in note or RELEASED in note:
+                    continue
+                fired.note = f"{note}; {RELEASED}"
+                release.append((rule, fired.id, fired.metric_value))
+    for rule, event_id, value in release:
+        _spawn(_dispatch_notification(app, "firing", rule, value, event_id))
+        if rule.ansible_action:
+            _spawn(_run_ansible_action(app, rule, value, event_id))

steward/core/api_tokens.py

@@ -0,0 +1,160 @@
+"""steward/core/api_tokens.py
+
+Personal API tokens: the credential an AI client (MCP) presents as
+`Authorization: Bearer stw_…` to act as its user.
+
+Tokens are high-entropy (`secrets.token_urlsafe(32)`), so they are stored as a
+plain sha256 — bcrypt is for low-entropy passwords — the same scheme as
+dashboard share tokens and the host-agent ingest token. The plaintext exists
+only in the create response.
+
+A token's `role` is a CEILING. Every resolution re-reads the user's current
+role and acts with the lower of the two, so demoting or disabling a user takes
+effect on their tokens at the next request with nothing to revoke by hand.
+"""
+from __future__ import annotations
+import hashlib
+import secrets
+from dataclasses import dataclass
+from datetime import datetime, timedelta, timezone
+
+from sqlalchemy import select, update
+
+from steward.auth.middleware import role_meets
+from steward.models.api_tokens import ApiToken
+from steward.models.users import User, UserRole
+
+TOKEN_PREFIX = "stw_"
+# How many plaintext characters the UI keeps to tell tokens apart.
+_DISPLAY_CHARS = 12
+# last_used_at is a "roughly when" signal; don't write a row per MCP call.
+_LAST_USED_RESOLUTION = timedelta(seconds=60)
+
+
+@dataclass(frozen=True)
+class Caller:
+    """Who an authenticated token request acts as, with its effective role."""
+    user_id: str
+    username: str
+    role: UserRole
+    token_id: int
+
+
+def generate_token() -> str:
+    return TOKEN_PREFIX + secrets.token_urlsafe(32)
+
+
+def hash_token(raw: str) -> str:
+    return hashlib.sha256(raw.encode()).hexdigest()
+
+
+def display_prefix(raw: str) -> str:
+    return raw[:_DISPLAY_CHARS]
+
+
+def effective_role(ceiling: UserRole, user_role: UserRole) -> UserRole:
+    """The lower of a token's ceiling and its user's current role."""
+    return ceiling if role_meets(user_role, ceiling) else user_role
+
+
+def grantable_roles(user_role: UserRole) -> list[UserRole]:
+    """Roles a user may give a new token: their own and anything below it."""
+    return [r for r in (UserRole.viewer, UserRole.operator, UserRole.admin)
+            if role_meets(user_role, r)]
+
+
+def token_state(token: ApiToken, now: datetime | None = None) -> str:
+    """'active', 'expired' or 'revoked' — for display and resolution alike."""
+    now = now or datetime.now(timezone.utc)
+    if token.revoked_at is not None:
+        return "revoked"
+    if token.expires_at is not None and token.expires_at <= now:
+        return "expired"
+    return "active"
+
+
+async def create_token(
+    db, *, user_id: str, user_role: UserRole, name: str, role: UserRole,
+    expires_in_days: int | None = None,
+) -> tuple[str, ApiToken]:
+    """Mint a token. Returns (plaintext, row); the plaintext is never stored.
+
+    Raises ValueError when the requested ceiling is above the user's own role
+    or the name is empty. The caller owns the transaction and commits it.
+    """
+    name = (name or "").strip()[:128]
+    if not name:
+        raise ValueError("Give the token a name, so you can tell it apart later.")
+    if not role_meets(user_role, role):
+        raise ValueError(
+            f"A token can't carry a higher role than yours ({user_role.value})."
+        )
+    now = datetime.now(timezone.utc)
+    raw = generate_token()
+    token = ApiToken(
+        user_id=user_id,
+        name=name,
+        token_hash=hash_token(raw),
+        prefix=display_prefix(raw),
+        role=role,
+        created_at=now,
+        expires_at=now + timedelta(days=expires_in_days) if expires_in_days else None,
+    )
+    db.add(token)
+    await db.flush()
+    return raw, token
+
+
+async def list_tokens(db, user_id: str) -> list[ApiToken]:
+    result = await db.execute(
+        select(ApiToken).where(ApiToken.user_id == user_id)
+        .order_by(ApiToken.created_at.desc())
+    )
+    return list(result.scalars())
+
+
+async def revoke_token(db, *, user_id: str, token_id: int) -> ApiToken | None:
+    """Revoke one of the user's own tokens. Returns it, or None if not theirs."""
+    result = await db.execute(
+        select(ApiToken).where(ApiToken.id == token_id, ApiToken.user_id == user_id)
+    )
+    token = result.scalar_one_or_none()
+    if token is not None and token.revoked_at is None:
+        token.revoked_at = datetime.now(timezone.utc)
+    return token
+
+
+async def resolve_token(app, raw: str | None) -> Caller | None:
+    """Resolve a bearer token's plaintext to the Caller it acts as.
+
+    None for a missing, unknown, revoked or expired token, or one whose user is
+    disabled. Never raises on a bad token; a database failure propagates so
+    the transport can report the outage rather than a misleading 401.
+    """
+    if not raw or not raw.startswith(TOKEN_PREFIX):
+        return None
+    now = datetime.now(timezone.utc)
+    async with app.db_sessionmaker() as db:
+        async with db.begin():
+            result = await db.execute(
+                select(ApiToken, User)
+                .join(User, User.id == ApiToken.user_id)
+                .where(ApiToken.token_hash == hash_token(raw))
+            )
+            row = result.first()
+            if row is None:
+                return None
+            token, user = row
+            if token_state(token, now) != "active" or not user.is_active:
+                return None
+            if token.last_used_at is None or now - token.last_used_at >= _LAST_USED_RESOLUTION:
+                await db.execute(
+                    update(ApiToken).where(ApiToken.id == token.id)
+                    .values(last_used_at=now)
+                )
+            return Caller(
+                user_id=user.id,
+                username=user.username,
+                role=effective_role(token.role, user.role),
+                token_id=token.id,
+            )

steward/core/audit.py

@@ -38,3 +38,11 @@ async def log_audit(
                 ))
     except Exception:
         logger.exception("Failed to write audit event action=%r", action)
+
+
+async def audit_request(action: str, entity_type: str | None = None,
+                        entity_id: str | None = None, detail: dict | None = None) -> None:
+    """log_audit for the logged-in user of the current web request."""
+    from quart import current_app, session
+    await log_audit(current_app, session.get("user_id"), session.get("username", ""),
+                    action, entity_type=entity_type, entity_id=entity_id, detail=detail)

steward/core/cleanup.py

@@ -76,10 +76,14 @@ async def _run_docker_retention(session, now: datetime) -> None:
         raw_days = int(await get_setting(session, "docker.retention.metrics_raw_days") or 7)
         rollup_days = int(await get_setting(session, "docker.retention.metrics_rollup_days") or 90)
         events_days = int(await get_setting(session, "docker.retention.events_days") or 30)
+        logs_days = int(await get_setting(session, "docker.logs.retention_days") or 3)
+        logs_cap = int(
+            await get_setting(session, "docker.logs.max_bytes_per_container") or 5_000_000)
         counts = await invoke_capability(
             "docker.run_retention", UserRole.viewer, session,
             events_days=events_days, metrics_raw_days=raw_days,
-            metrics_rollup_days=rollup_days, now=now,
+            metrics_rollup_days=rollup_days, logs_retention_days=logs_days,
+            logs_max_bytes_per_container=logs_cap, now=now,
         )
     if counts and any(counts.values()):
         logger.info("Docker retention: %s", counts)

steward/core/formatting.py

@@ -0,0 +1,131 @@
+"""steward/core/formatting.py
+
+How Steward writes a size, a rate, a span of time and a moment, and how it
+grades a reading against Settings → Thresholds — once, for every page and
+plugin (#5093). Registered as Jinja filters (|bytes, |rate, |duration, |ago)
+and the status_class global in app.py; Python callers import them from here.
+"""
+from __future__ import annotations
+
+from datetime import datetime, timezone
+from typing import Any
+
+from markupsafe import Markup, escape
+
+NONE = "—"
+_UNITS = ("B", "KiB", "MiB", "GiB", "TiB", "PiB")
+_SPANS = (("d", 86400), ("h", 3600), ("m", 60), ("s", 1))
+
+
+def human_bytes(n: float | None) -> str:
+    """Binary units: '0 B', '512 B', '1.5 KiB', '1.4 GiB'."""
+    if n is None:
+        return NONE
+    size = float(n)
+    for unit in _UNITS:
+        if abs(size) < 1024 or unit == _UNITS[-1]:
+            return f"{int(size)} B" if unit == "B" else f"{size:.1f} {unit}"
+        size /= 1024
+    raise AssertionError("unreachable")
+
+
+def human_rate(bytes_per_s: float | None) -> str:
+    """Bytes per second in binary units: '12.3 MiB/s'."""
+    return NONE if bytes_per_s is None else f"{human_bytes(bytes_per_s)}/s"
+
+
+def human_duration(seconds: float | None) -> str:
+    """The two largest units of a span: '45s', '8m', '1m 30s', '2h 5m', '3d 4h'.
+    The second unit is dropped when it is zero. Negative spans read as None."""
+    if seconds is None or seconds < 0:
+        return NONE
+    left = int(seconds)
+    if left == 0:
+        return "0s"
+    parts = []
+    for i, (unit, size) in enumerate(_SPANS):
+        count, left = divmod(left, size)
+        if count:
+            parts.append(f"{count}{unit}")
+            nxt = _SPANS[i + 1] if i + 1 < len(_SPANS) else None
+            if nxt and left // nxt[1]:
+                parts.append(f"{left // nxt[1]}{nxt[0]}")
+            break
+    return " ".join(parts)
+
+
+def _utc(when: datetime) -> datetime:
+    return when.replace(tzinfo=timezone.utc) if when.tzinfo is None else when.astimezone(timezone.utc)
+
+
+def seconds_since(when: datetime | None, now: datetime | None = None) -> float | None:
+    """Seconds from `when` to now; a naive datetime is taken as UTC."""
+    if when is None:
+        return None
+    return ((now or datetime.now(timezone.utc)) - _utc(when)).total_seconds()
+
+
+def ago(when: datetime | None, now: datetime | None = None) -> Markup:
+    """'3m ago' (or 'in 3m' for a future moment) in a <time> element whose
+    title is the absolute UTC time, so a hover gives the exact moment."""
+    if when is None:
+        return Markup(NONE)
+    when = _utc(when)
+    secs = seconds_since(when, now)
+    if abs(secs) < 1:
+        text = "just now"
+    elif secs > 0:
+        text = f"{human_duration(secs)} ago"
+    else:
+        text = f"in {human_duration(-secs)}"
+    return Markup('<time datetime="{}" title="{}">{}</time>').format(
+        when.strftime("%Y-%m-%dT%H:%M:%SZ"), when.strftime("%Y-%m-%d %H:%M:%S UTC"), escape(text))
+
+
+def status_class(value: Any, kind: str, thresholds: dict) -> str:
+    """Grade a reading against Settings → Thresholds (to_thresholds_cfg):
+    'ok', 'warn' or 'crit', or 'unknown' when there is no reading.
+
+    A kind the thresholds don't name is a mistake in the caller, not a
+    reading to colour as healthy, so it raises."""
+    if value is None:
+        return "unknown"
+    th = thresholds[kind]
+    warn, crit = th["warn"], th["crit"]
+    if th.get("dir", "high") == "low":
+        return "crit" if value < crit else "warn" if value < warn else "ok"
+    return "crit" if value >= crit else "warn" if value >= warn else "ok"
+
+
+# Every state a page shows, and the tone it is drawn in: ok (green), warn
+# (amber), crit (red), info (blue) or dim. The status_badge and status_dot
+# macros read this, so one state looks the same on every page.
+STATES: dict[str, tuple[str, str]] = {
+    "up": ("ok", "Up"),
+    "ok": ("ok", "OK"),
+    "resolved": ("ok", "Resolved"),
+    "down": ("crit", "Down"),
+    "firing": ("crit", "Firing"),
+    "crit": ("crit", "Critical"),
+    "warn": ("warn", "Warning"),
+    "pending": ("warn", "Pending"),
+    "stale": ("warn", "Stale"),
+    "no_data": ("warn", "No data"),
+    "acknowledged": ("info", "Acknowledged"),
+    "inactive": ("dim", "Inactive"),
+    "unknown": ("dim", "Unknown"),
+}
+
+
+def status_info(state: Any) -> tuple[str, str]:
+    """(tone, label) for a state name or enum. A state the map doesn't know
+    is drawn dim under its own name rather than breaking the page."""
+    key = str(getattr(state, "value", state) or "unknown").lower()
+    return STATES.get(key, ("dim", key.replace("_", " ").capitalize()))
+
+
+def required(value: Any, what: str) -> Any:
+    """For a macro argument that must be given: raise if it is empty."""
+    if value is None or not str(value).strip():
+        raise ValueError(f"{what} is required")
+    return value

steward/core/metric_series.py

@@ -0,0 +1,122 @@
+"""Reads over the generic metric store (plugin_metrics + its hourly rollup).
+
+Any source that records into PluginMetric — host_agent, traefik, unifi, snmp,
+the monitor types, Steward's self-monitor — is readable through these without
+importing the plugin that wrote it.
+"""
+from __future__ import annotations
+
+from datetime import datetime, timedelta, timezone
+
+from sqlalchemy import func, or_, select, text
+
+from steward.core.time_range import bucket_seconds
+from steward.models.metrics import PluginMetric, PluginMetricHourly
+
+# Raw rows older than this are rolled into plugin_metrics_hourly and deleted
+# (see core/metrics_retention.py), so a range reaching past it reads the rollup.
+RAW_DAYS = 7
+
+# Loose index scans: step through the distinct leading values of the
+# (source_module, resource_name, …) index one probe at a time instead of
+# scanning every sample. Postgres has no native skip scan before 18.
+_SOURCES_SQL = text("""
+    WITH RECURSIVE s(v) AS (
+        SELECT min(source_module) FROM plugin_metrics
+        UNION ALL
+        SELECT (SELECT min(source_module) FROM plugin_metrics WHERE source_module > s.v)
+        FROM s WHERE s.v IS NOT NULL
+    )
+    SELECT v FROM s WHERE v IS NOT NULL
+""")
+
+_RESOURCES_SQL = text("""
+    WITH RECURSIVE r(v) AS (
+        SELECT min(resource_name) FROM plugin_metrics WHERE source_module = :src
+        UNION ALL
+        SELECT (SELECT min(resource_name) FROM plugin_metrics
+                WHERE source_module = :src AND resource_name > r.v)
+        FROM r WHERE r.v IS NOT NULL
+    )
+    SELECT v FROM r WHERE v IS NOT NULL
+""")
+
+
+async def sources(db) -> list[str]:
+    """Every source_module with raw samples on record."""
+    return [v for (v,) in await db.execute(_SOURCES_SQL)]
+
+
+async def resources(db, source_module: str) -> list[str]:
+    """Every resource a source has raw samples for, sorted."""
+    return [v for (v,) in await db.execute(_RESOURCES_SQL, {"src": source_module})]
+
+
+async def latest_values(db, source_module: str, resource: str, *,
+                        include_children: bool = False) -> list[PluginMetric]:
+    """The newest sample of each metric for a resource, sorted by (resource, metric).
+
+    include_children also returns the resource's sub-resources, named
+    "<resource>:<part>" (a host's mounts, interfaces, sensors).
+    """
+    match = PluginMetric.resource_name == resource
+    if include_children:
+        like = resource.replace("\\", "\\\\").replace("%", "\\%").replace("_", "\\_") + ":%"
+        match = or_(match, PluginMetric.resource_name.like(like, escape="\\"))
+    return list((await db.execute(
+        select(PluginMetric)
+        .where(PluginMetric.source_module == source_module, match)
+        .distinct(PluginMetric.resource_name, PluginMetric.metric_name)
+        .order_by(PluginMetric.resource_name, PluginMetric.metric_name,
+                  PluginMetric.recorded_at.desc())
+    )).scalars())
+
+
+async def points(db, source_module: str, resource: str, metric: str, since: datetime,
+                 *, target: int = 120) -> list[tuple[datetime, float]]:
+    """(time, average) points for one metric since `since`, oldest first.
+
+    The part of the range older than the raw window comes from the hourly
+    rollup; the rest is bucket-averaged in SQL (buckets no wider than an hour
+    when both are present, so the series is evenly grained across the seam).
+    """
+    now = datetime.now(timezone.utc)
+    raw_cutoff = (now - timedelta(days=RAW_DAYS)).replace(minute=0, second=0, microsecond=0)
+    out: list[tuple[datetime, float]] = []
+
+    if since < raw_cutoff:
+        hourly = await db.execute(
+            select(PluginMetricHourly.bucket, PluginMetricHourly.value_avg)
+            .where(
+                PluginMetricHourly.source_module == source_module,
+                PluginMetricHourly.resource_name == resource,
+                PluginMetricHourly.metric_name == metric,
+                PluginMetricHourly.bucket >= since,
+                PluginMetricHourly.bucket < raw_cutoff,
+            )
+            .order_by(PluginMetricHourly.bucket)
+        )
+        out.extend((b, float(v)) for b, v in hourly)
+
+    raw_since = max(since, raw_cutoff)
+    width_s = bucket_seconds(raw_since, target)
+    if since < raw_cutoff:
+        width_s = min(width_s, 3600)
+    bucket = func.date_bin(
+        func.make_interval(0, 0, 0, 0, 0, 0, width_s),
+        PluginMetric.recorded_at,
+        func.to_timestamp(0),
+    ).label("bucket")
+    raw = await db.execute(
+        select(bucket, func.avg(PluginMetric.value))
+        .where(
+            PluginMetric.source_module == source_module,
+            PluginMetric.resource_name == resource,
+            PluginMetric.metric_name == metric,
+            PluginMetric.recorded_at >= raw_since,
+        )
+        .group_by(bucket)
+        .order_by(bucket)
+    )
+    out.extend((b, float(v)) for b, v in raw)
+    return out

steward/core/notifications.py

@@ -8,7 +8,7 @@ import types
 from email.message import EmailMessage
 
 import httpx
-from jinja2 import Template
+from jinja2.sandbox import SandboxedEnvironment
 
 logger = logging.getLogger(__name__)
 
@@ -30,20 +30,38 @@ async def dispatch_notifications(
     return results
 
 
+SMTP_TIMEOUT_S = 15
+
+
+def smtp_mode(port, tls) -> str:
+    """How to talk to the SMTP server: "ssl" (implicit TLS, port 465),
+    "starttls" (upgrade a plain connection, when TLS is ticked) or "plain"."""
+    if int(port or 0) == 465:
+        return "ssl"
+    return "starttls" if tls else "plain"
+
+
+def email_body(alert: dict) -> str:
+    value = "no data" if alert.get("value") is None else alert["value"]
+    return (
+        f"Alert: {alert['state']}\n"
+        f"Rule: {alert['rule_name']}\n"
+        f"Resource: {alert['resource']}\n"
+        f"Metric: {alert['metric']} = {value}\n"
+        f"Threshold: {alert['threshold']}\n"
+        + (f"Note: {alert['note']}\n" if alert.get("note") else "")
+        + f"Time: {alert['timestamp']}\n"
+    )
+
+
 async def _send_email(cfg: dict, alert: dict) -> dict:
     try:
         msg = EmailMessage()
-        msg["Subject"] = f"[Steward] {alert['state']} — {alert['rule_name']}"
-        msg["From"] = cfg.get("username", "steward@localhost")
+        # A header may not hold a line break; a rule name can (MCP takes any string).
+        msg["Subject"] = " ".join(f"[Steward] {alert['state']} — {alert['rule_name']}".split())
+        msg["From"] = cfg.get("from") or cfg.get("username") or "steward@localhost"
         msg["To"] = ", ".join(cfg["recipients"])
-        msg.set_content(
-            f"Alert: {alert['state']}\n"
-            f"Rule: {alert['rule_name']}\n"
-            f"Resource: {alert['resource']}\n"
-            f"Metric: {alert['metric']} = {alert['value']}\n"
-            f"Threshold: {alert['threshold']}\n"
-            f"Time: {alert['timestamp']}\n"
-        )
+        msg.set_content(email_body(alert))
         loop = asyncio.get_running_loop()
         await loop.run_in_executor(None, _smtp_send_sync, cfg, msg)
         return {"sent": True, "error": None}
@@ -53,37 +71,59 @@ async def _send_email(cfg: dict, alert: dict) -> dict:
 
 
 def _smtp_send_sync(cfg: dict, msg: EmailMessage) -> None:
-    ctx = ssl.create_default_context() if cfg.get("tls", True) else None
-    with smtplib.SMTP(cfg["host"], cfg.get("port", 587)) as smtp:
-        if ctx:
+    port = int(cfg.get("port") or 587)
+    mode = smtp_mode(port, cfg.get("tls", True))
+    ctx = ssl.create_default_context()
+    if mode == "ssl":
+        smtp = smtplib.SMTP_SSL(cfg["host"], port, timeout=SMTP_TIMEOUT_S, context=ctx)
+    else:
+        smtp = smtplib.SMTP(cfg["host"], port, timeout=SMTP_TIMEOUT_S)
+    with smtp:
+        if mode == "starttls":
             smtp.starttls(context=ctx)
         if cfg.get("username"):
             smtp.login(cfg["username"], cfg.get("password", ""))
         smtp.send_message(msg)
 
 
-async def _send_webhook(cfg: dict, alert: dict) -> dict:
-    template_str = cfg.get(
-        "template",
-        '{"content": "{{ alert.state }} — {{ alert.rule_name }}"}',
-    )
+def _json_str(value) -> str:
+    """A value as it may sit between the quotes of a JSON string."""
+    return json.dumps("" if value is None else str(value))[1:-1]
 
-    # Render Jinja2 template with alert as a namespace object (attribute access)
+
+def render_webhook(template_str: str, alert: dict) -> str:
+    """The webhook body for an alert, checked to be JSON.
+
+    In the template, `alert.<field>` is escaped to sit inside a JSON string
+    ("{{ alert.rule_name }}" stays valid whatever the name holds), with a
+    missing value reading "no data"; `raw.<field>` is the plain value for use
+    with |tojson ({{ raw.value | tojson }} gives a number or null). The
+    template runs sandboxed. ValueError says why a body could not be made.
+    """
+    shown = dict(alert)
+    if shown.get("value") is None:
+        shown["value"] = "no data"
+    env = SandboxedEnvironment()
     try:
-        alert_ns = types.SimpleNamespace(**alert)
-        rendered = Template(template_str).render(alert=alert_ns)
+        rendered = env.from_string(template_str).render(
+            alert=types.SimpleNamespace(**{k: _json_str(v) for k, v in shown.items()}),
+            raw=types.SimpleNamespace(**alert))
     except Exception as exc:
-        error = f"Template render failed: {exc}"
-        logger.error(error)
-        return {"sent": False, "error": error}
-
-    # Validate JSON before sending
+        raise ValueError(f"Template render failed: {exc}") from None
     try:
         json.loads(rendered)
     except json.JSONDecodeError as exc:
-        error = f"Rendered webhook template is not valid JSON: {exc}"
-        logger.error(error)
-        return {"sent": False, "error": error}
+        raise ValueError(f"Rendered webhook template is not valid JSON: {exc}") from None
+    return rendered
+
+
+async def _send_webhook(cfg: dict, alert: dict) -> dict:
+    template_str = cfg.get("template") or '{"content": "{{ alert.state }} — {{ alert.rule_name }}"}'
+    try:
+        rendered = render_webhook(template_str, alert)
+    except ValueError as exc:
+        logger.error(str(exc))
+        return {"sent": False, "error": str(exc)}
 
     try:
         async with httpx.AsyncClient(timeout=10) as client:
@@ -95,6 +135,8 @@ async def _send_webhook(cfg: dict, alert: dict) -> dict:
             response.raise_for_status()
         return {"sent": True, "error": None}
     except Exception as exc:
-        error = str(exc)
+        # The URL is a secret (it usually carries its own token) and httpx
+        # puts it in its error messages.
+        error = str(exc).replace(cfg["url"], "<webhook URL>")
         logger.error(f"Webhook notification failed: {error}")
         return {"sent": False, "error": error}

steward/core/plugin_manager.py

@@ -3,8 +3,8 @@ from __future__ import annotations
 import hashlib
 import logging
 import os
+import shutil
 import sys
-import tempfile
 import zipfile
 from pathlib import Path
 from typing import TYPE_CHECKING
@@ -29,6 +29,11 @@ _FAILED_PLUGINS: dict[str, str] = {}
 #   {"plugin": <name>, "label": str, "href": str, "section": str}
 _PLUGIN_NAV: list[dict] = []
 
+# Loaded plugin modules, by name, for the MCP server: a plugin contributes
+# agent tools through an optional register_mcp_tools(register) export, which
+# steward/mcp/server.py calls when it mounts (and on hot-reload, below).
+_PLUGIN_MODULES: dict[str, object] = {}
+
 
 def get_plugin_failures() -> dict[str, str]:
     """Return a copy of the failed-plugin registry (name → error message)."""
@@ -70,6 +75,23 @@ def _collect_plugin_nav(name: str, module) -> None:
         })
 
 
+def get_loaded_plugin_modules() -> dict[str, object]:
+    """Loaded plugin modules by name (a copy), for hooks consumed after loading."""
+    return dict(_PLUGIN_MODULES)
+
+
+def _collect_plugin_module(app: "Quart", name: str, module) -> None:
+    """Remember a loaded plugin module; hand it to a live MCP server if mounted.
+
+    At boot the MCP server mounts after plugins load and reads them via
+    get_loaded_plugin_modules(); a plugin hot-loaded later is registered here.
+    """
+    _PLUGIN_MODULES[name] = module
+    mcp_server = getattr(app, "mcp_server", None)
+    if mcp_server is not None:
+        mcp_server.register_plugin(name, module)
+
+
 def resolve_plugin_path(plugin_dirs: list[Path], name: str) -> Path | None:
     """Return the first plugin root that contains `name`, else None.
 
@@ -87,7 +109,8 @@ def _import_plugin(name: str, plugin_path: Path):
     """Load a plugin module by file path, avoiding sys.modules stdlib collisions.
 
     Using importlib.import_module(name) fails for plugins whose names shadow
-    Python stdlib modules (e.g. the 'http' plugin vs stdlib's 'http' package).
+    Python stdlib modules (e.g. a plugin named 'json' or 'http' vs the stdlib
+    package of the same name).
     This helper loads from the filesystem path directly and registers the module
     under a namespaced key so relative imports within the plugin still work.
     """
@@ -263,22 +286,112 @@ def load_plugins(app: "Quart") -> None:
         _FAILED_PLUGINS.pop(name, None)  # clear any stale failure from a previous reload attempt
         _LOADED_PLUGINS.add(name)
         _collect_plugin_nav(name, module)
+        _collect_plugin_module(app, name, module)
         logger.info("Plugin %r loaded (v%s)", name, meta.get("version", "?"))
 
 
+# Bounds on what an install may bring in: the download itself, and what it
+# unpacks to (a small zip can expand to fill the disk).
+MAX_PLUGIN_DOWNLOAD_BYTES = 50 * 1024 * 1024
+MAX_PLUGIN_UNPACKED_BYTES = 200 * 1024 * 1024
+
+
+class PluginInstallError(Exception):
+    """An install refused or failed; the message is shown to the admin."""
+
+
+def check_plugin_name(name: str) -> None:
+    """A plugin is imported by its folder name, so the name must be a plain
+    Python identifier — which also keeps it from naming a path."""
+    if not (name.isascii() and name.isidentifier()):
+        raise PluginInstallError(f"{name!r} is not a valid plugin name")
+
+
+def verify_checksum(content: bytes, expected_sha256: str) -> None:
+    """Refuse a download whose sha256 is missing from the catalog or differs."""
+    if not expected_sha256:
+        raise PluginInstallError(
+            "The catalog lists no checksum for this plugin, so Steward cannot "
+            "tell it is the file the catalog meant. Not installed.")
+    actual = hashlib.sha256(content).hexdigest()
+    if actual != expected_sha256.strip().lower():
+        raise PluginInstallError(f"Checksum mismatch: expected {expected_sha256}, got {actual}")
+
+
+def extract_plugin(content: bytes, name: str, dest: Path) -> None:
+    """Unpack a plugin zip into `dest`, which must not exist yet.
+
+    One top-level folder whose name starts with the plugin name is stripped:
+        name/                         (clean plugin zip)
+        name-v1.0.0/                  (release tag archive)
+    otherwise the zip is unpacked as it stands. Every member must land inside
+    `dest` — an absolute path or a `..` that climbs out refuses the whole zip —
+    and the unpacked total is capped.
+    """
+    import io
+    root = dest.resolve()
+    with zipfile.ZipFile(io.BytesIO(content)) as zf:
+        infos = zf.infolist()
+        if sum(i.file_size for i in infos) > MAX_PLUGIN_UNPACKED_BYTES:
+            raise PluginInstallError(
+                f"Unpacks to more than {MAX_PLUGIN_UNPACKED_BYTES // (1024 * 1024)} MB")
+        top_level = {i.filename.split("/")[0] for i in infos}
+        prefix = ""
+        if len(top_level) == 1:
+            candidate = next(iter(top_level))
+            if candidate.lower().startswith(name.lower()) and any(
+                    i.filename.startswith(candidate + "/") for i in infos):
+                prefix = candidate + "/"
+        planned: list[tuple[zipfile.ZipInfo, Path]] = []
+        for info in infos:
+            if prefix and not info.filename.startswith(prefix):
+                continue
+            rel = info.filename[len(prefix):]
+            if not rel:
+                continue
+            target = (root / rel).resolve()
+            if not target.is_relative_to(root) or target == root:
+                raise PluginInstallError(f"Refused: {info.filename!r} points outside the plugin folder")
+            planned.append((info, target))
+        root.mkdir(parents=True)
+        for info, target in planned:
+            if info.is_dir():
+                target.mkdir(parents=True, exist_ok=True)
+                continue
+            target.parent.mkdir(parents=True, exist_ok=True)
+            with zf.open(info) as src, open(target, "wb") as out:
+                shutil.copyfileobj(src, out)
+
+
+async def _download(url: str) -> bytes:
+    import httpx
+    chunks: list[bytes] = []
+    size = 0
+    async with httpx.AsyncClient(timeout=60, follow_redirects=True) as client:
+        async with client.stream("GET", url) as resp:
+            resp.raise_for_status()
+            async for chunk in resp.aiter_bytes():
+                size += len(chunk)
+                if size > MAX_PLUGIN_DOWNLOAD_BYTES:
+                    raise PluginInstallError(
+                        f"Download is larger than {MAX_PLUGIN_DOWNLOAD_BYTES // (1024 * 1024)} MB")
+                chunks.append(chunk)
+    return b"".join(chunks)
+
+
 async def download_and_install_plugin(
     app: "Quart",
     name: str,
     download_url: str,
     expected_sha256: str,
 ) -> tuple[bool, str]:
-    """Download a plugin zip, verify its checksum, and extract it to PLUGIN_DIR.
+    """Download a plugin zip named by the catalog, verify its checksum, and
+    unpack it into the install dir, replacing any earlier copy whole.
 
-    Returns (success, message). Does NOT hot-reload — call hot_reload_plugin()
-    after this to activate the plugin without a restart (new plugins only).
+    The URL and checksum must come from the catalog entry, never from the
+    request. Returns (success, message). Does NOT hot-reload — call
+    hot_reload_plugin() after this to activate a new plugin without a restart.
     """
-    import httpx
-
     # Downloads always land in the external (writable, persistent) install dir,
     # never the read-only bundled dir.
     plugin_dir = Path(app.config["PLUGIN_INSTALL_DIR"]).resolve()
@@ -290,68 +403,46 @@ async def download_and_install_plugin(
         sys.path.insert(0, plugin_dir_str)
 
     try:
+        check_plugin_name(name)
+        if not download_url:
+            raise PluginInstallError("The catalog lists no download URL for this plugin")
         logger.info("Downloading plugin %r from %s", name, download_url)
-        async with httpx.AsyncClient(timeout=60, follow_redirects=True) as client:
-            resp = await client.get(download_url)
-            resp.raise_for_status()
-        content = resp.content
-    except Exception as exc:
-        msg = f"Download failed: {exc}"
-        logger.error("Plugin %r: %s", name, msg)
-        return False, msg
+        try:
+            content = await _download(download_url)
+        except PluginInstallError:
+            raise
+        except Exception as exc:
+            raise PluginInstallError(f"Download failed: {exc}") from exc
+        verify_checksum(content, expected_sha256)
 
-    # Verify checksum if provided
-    if expected_sha256:
-        actual = hashlib.sha256(content).hexdigest()
-        if actual != expected_sha256.lower():
-            msg = f"Checksum mismatch: expected {expected_sha256}, got {actual}"
-            logger.error("Plugin %r: %s", name, msg)
-            return False, msg
-
-    # Extract the zip
-    try:
-        with tempfile.TemporaryDirectory() as tmpdir:
-            zip_path = Path(tmpdir) / f"{name}.zip"
-            zip_path.write_bytes(content)
-            with zipfile.ZipFile(zip_path) as zf:
-                members = zf.namelist()
-                # Collect unique top-level names (dirs and loose files)
-                top_level = {m.split("/")[0] for m in members}
-
-                dest = plugin_dir / name
-                dest.mkdir(parents=True, exist_ok=True)
-
-                # Detect a single top-level directory to strip. Handles:
-                #   name/               (clean plugin zip)
-                #   name-v1.0.0/        (GitHub release tag archive)
-                #   steward-plugins-main/name/  (whole-repo archive)
-                # Strategy: if there is exactly one top-level item and it is a
-                # directory whose name starts with the plugin name (case-insensitive),
-                # strip it. Otherwise extract flat into dest.
-                prefix: str | None = None
-                if len(top_level) == 1:
-                    candidate = list(top_level)[0]
-                    if candidate.lower().startswith(name.lower()):
-                        prefix = candidate + "/"
-
-                for member in members:
-                    if prefix:
-                        if not member.startswith(prefix):
-                            continue
-                        rel = member[len(prefix):]
-                    else:
-                        rel = member
-                    if not rel or rel.endswith("/"):
-                        if rel:
-                            (dest / rel.rstrip("/")).mkdir(parents=True, exist_ok=True)
-                        continue
-                    target = dest / rel
-                    target.parent.mkdir(parents=True, exist_ok=True)
-                    target.write_bytes(zf.read(member))
-    except Exception as exc:
-        msg = f"Extraction failed: {exc}"
-        logger.error("Plugin %r: %s", name, msg)
-        return False, msg
+        # Unpack beside the live copy, then swap: a failed or refused zip
+        # leaves the installed plugin untouched, and an update drops files the
+        # new version no longer ships.
+        plugin_dir.mkdir(parents=True, exist_ok=True)
+        dest = plugin_dir / name
+        staging = plugin_dir / f".{name}.installing"
+        old = plugin_dir / f".{name}.replaced"
+        for leftover in (staging, old):
+            shutil.rmtree(leftover, ignore_errors=True)
+        try:
+            extract_plugin(content, name, staging)
+        except PluginInstallError:
+            raise
+        except Exception as exc:
+            raise PluginInstallError(f"Extraction failed: {exc}") from exc
+        try:
+            if dest.exists():
+                dest.rename(old)
+            staging.rename(dest)
+        except OSError as exc:
+            if old.exists() and not dest.exists():
+                old.rename(dest)  # put the previous version back
+            raise PluginInstallError(f"Could not move the plugin into place: {exc}") from exc
+        shutil.rmtree(old, ignore_errors=True)
+    except PluginInstallError as exc:
+        shutil.rmtree(plugin_dir / f".{name}.installing", ignore_errors=True)
+        logger.error("Plugin %r: %s", name, exc)
+        return False, str(exc)
 
     # Run migrations for the newly installed plugin.
     # Include all plugin migration dirs so Alembic can resolve any previously-stamped
@@ -482,6 +573,7 @@ def hot_reload_plugin(app: "Quart", name: str) -> tuple[bool, str]:
 
     _LOADED_PLUGINS.add(name)
     _collect_plugin_nav(name, module)
+    _collect_plugin_module(app, name, module)
     logger.info("Plugin %r hot-reloaded (v%s)", name, meta.get("version", "?"))
     return True, f"Plugin activated (v{meta.get('version', '?')})"
 

steward/core/proxy.py

@@ -0,0 +1,50 @@
+"""What the request looked like before the reverse proxy.
+
+Steward serves plain HTTP; TLS ends at the operator's proxy (Traefik, often
+with Cloudflare in front). The proxy reports the original scheme and client
+in X-Forwarded-Proto / X-Forwarded-For, but anyone can send those headers,
+so they are believed only as far as the configured number of trusted proxy
+hops (Settings → General, default 1). 0 means no proxy is trusted.
+
+Each proxy appends to the header, so the value the nearest trusted proxy
+wrote is the hops-th from the right. HTTPS-only behaviour (the session
+cookie's Secure flag, HSTS) turns on per request from is_https(); nothing
+here ever redirects to https.
+"""
+from __future__ import annotations
+
+from quart import current_app, request
+
+
+def trusted_value(header_values: list[str], hops: int) -> str | None:
+    """The value written by the outermost trusted proxy, or None when there
+    are fewer values than trusted hops (or hops is 0)."""
+    if hops <= 0:
+        return None
+    values = [v.strip() for line in header_values for v in line.split(",") if v.strip()]
+    if len(values) < hops:
+        return None
+    return values[-hops]
+
+
+def _hops() -> int:
+    try:
+        return max(0, int(current_app.config.get("TRUSTED_PROXY_HOPS", 1)))
+    except (TypeError, ValueError):
+        return 1
+
+
+def is_https() -> bool:
+    """True when this request reached Steward over HTTPS, directly or as
+    reported by a trusted proxy."""
+    if request.scheme == "https":
+        return True
+    proto = trusted_value(request.headers.getlist("X-Forwarded-Proto"), _hops())
+    return (proto or "").lower() == "https"
+
+
+def client_ip() -> str:
+    """The client's address as the outermost trusted proxy saw it, else the
+    socket peer."""
+    forwarded = trusted_value(request.headers.getlist("X-Forwarded-For"), _hops())
+    return forwarded or (request.remote_addr or "")

steward/core/renames.py

@@ -0,0 +1,82 @@
+"""steward/core/renames.py
+
+Alert rules, maintenance-window scopes and metric history all key a thing
+by (source, name). When a monitor or host is renamed, carry_rename moves
+every one of them to the new name, in the caller's transaction, so the
+thing's rules keep watching it and its history stays in one piece (#5065).
+"""
+from __future__ import annotations
+
+from sqlalchemy import and_, delete, func, or_, update
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from steward.models.alerts import AlertRule, MaintenanceWindow
+from steward.models.metrics import PluginMetric, PluginMetricHourly
+
+# What a host's name keys, and how each source names a part of the host:
+# host_agent "web01:/var", "web01:core3"; docker "web01/nginx".
+HOST_SOURCES: tuple[tuple[str, str | None], ...] = (("host_agent", ":"), ("docker", "/"))
+
+
+def _matches(source_col, name_col, sources, name: str):
+    """(source, name) itself, or a sub-resource "<name><sep>…" of it."""
+    clauses = []
+    for source, sep in sources:
+        under = [name_col == name]
+        if sep:
+            # An exact prefix: LIKE would read % or _ in a name as wildcards, and
+            # a >=/< range follows the collation, which may ignore punctuation.
+            under.append(func.left(name_col, len(name) + len(sep)) == name + sep)
+        clauses.append(and_(source_col == source, or_(*under)))
+    return or_(*clauses)
+
+
+def _renamed(name_col, old: str, new: str):
+    return func.concat(new, func.substr(name_col, len(old) + 1))
+
+
+async def carry_rename(session: AsyncSession, sources, old: str, new: str) -> dict[str, int]:
+    """Point everything keyed by `old` under each (source, separator) in
+    `sources` at `new`. A separator also carries the sub-resources named
+    "<old><sep>…"; None carries the exact name only.
+
+    The caller has already refused a `new` that a live thing holds, so any
+    history under `new` belongs to something deleted: it is dropped first,
+    rather than merged into this thing's history. Returns rows moved, by kind.
+    """
+    if not old or old == new:
+        return {}
+    sources = tuple(sources)
+    for model in (PluginMetric, PluginMetricHourly):
+        await session.execute(delete(model).where(
+            _matches(model.source_module, model.resource_name, sources, new)))
+    moved = {}
+    for kind, model, src, res in (
+        ("rules", AlertRule, AlertRule.source_module, AlertRule.resource_name),
+        ("maintenance_windows", MaintenanceWindow, MaintenanceWindow.scope_source,
+         MaintenanceWindow.scope_resource),
+        ("metric_rows", PluginMetric, PluginMetric.source_module, PluginMetric.resource_name),
+        ("hourly_rows", PluginMetricHourly, PluginMetricHourly.source_module,
+         PluginMetricHourly.resource_name),
+    ):
+        result = await session.execute(
+            update(model).where(_matches(src, res, sources, old))
+            .values({res: _renamed(res, old, new)})
+            .execution_options(synchronize_session=False))
+        moved[kind] = result.rowcount
+    return moved
+
+
+def describe(moved: dict[str, int]) -> str:
+    """'2 alert rules, 1 maintenance window and 18,204 metric samples', or ''."""
+    parts = []
+    for kind, one, many in (("rules", "alert rule", "alert rules"),
+                            ("maintenance_windows", "maintenance window", "maintenance windows")):
+        if moved.get(kind):
+            parts.append(f"{moved[kind]} {one if moved[kind] == 1 else many}")
+    samples = moved.get("metric_rows", 0) + moved.get("hourly_rows", 0)
+    if samples:
+        parts.append(f"{samples:,} metric sample{'' if samples == 1 else 's'}")
+    if len(parts) > 1:
+        return ", ".join(parts[:-1]) + " and " + parts[-1]
+    return "".join(parts)

steward/core/reports.py

@@ -11,7 +11,8 @@ from email.message import EmailMessage
 
 from sqlalchemy import and_, case, func, select
 
-from steward.models.alerts import AlertRule, AlertState, AlertStateEnum, AlertEvent
+from steward.alerts import service as alert_svc
+from steward.models.alerts import AlertEvent
 from steward.models.metrics import PluginMetric
 from steward.models.monitors import Monitor, MonitorResult
 
@@ -51,24 +52,17 @@ async def build_report_data(app) -> dict:
         ]
 
         # ── Active alerts ─────────────────────────────────────────────────────
-        active_result = await db.execute(
-            select(AlertState, AlertRule)
-            .join(AlertRule, AlertState.rule_id == AlertRule.id)
-            .where(AlertState.state.in_([
-                AlertStateEnum.firing, AlertStateEnum.acknowledged, AlertStateEnum.pending,
-            ]))
-            .order_by(AlertState.last_transition_at.desc())
-        )
+        active_rows = await alert_svc.active_alerts(db)
         active_alerts = [
             {
-                "state": state.state.value.upper(),
+                "state": alert_svc.alert_label(state).upper(),
                 "name": rule.name,
                 "resource": rule.resource_name,
                 "metric": rule.metric_name,
                 "operator": rule.operator.value,
                 "threshold": rule.threshold,
             }
-            for state, rule in active_result.all()
+            for state, rule in active_rows
         ]
 
         # ── Alert event counts (7d) ───────────────────────────────────────────

steward/core/self_monitor.py

@@ -80,28 +80,28 @@ async def record_self_metrics(app) -> None:
         logger.debug("self_monitor: /proc/self/fd unavailable — skipping fd metrics")
         return
 
-    from .alerts import record_metric
+    from .alerts import MetricBatch
 
     soft = fd_soft_limit()
     pct = (fds / soft * 100.0) if soft else None
 
     async with app.db_sessionmaker() as session:
         async with session.begin():
-            await record_metric(
-                session=session,
+            batch = MetricBatch()
+            batch.add(
                 source_module="steward",
                 resource_name="process",
                 metric_name="open_fds",
                 value=float(fds),
             )
             if pct is not None:
-                await record_metric(
-                    session=session,
+                batch.add(
                     source_module="steward",
                     resource_name="process",
                     metric_name="open_fds_pct",
                     value=pct,
                 )
+            await batch.record(session)
 
     if pct is not None and pct >= FD_WARN_PCT:
         if not _warned:

steward/core/settings.py

@@ -18,6 +18,7 @@ from __future__ import annotations
 import asyncio
 import json
 import logging
+from collections.abc import Iterable, Mapping
 from datetime import datetime, timezone
 from typing import Any
 
@@ -39,7 +40,13 @@ DEFAULTS: dict[str, Any] = {
     # General — external URL for install scripts, share links, alert deep-links.
     # Empty = fall back to the current request's Host header.
     "general.public_base_url": "",
+    # Reverse proxies in front of Steward whose X-Forwarded-* headers are
+    # believed (steward/core/proxy.py). 0 = trust none.
+    "general.trusted_proxy_hops": 1,
     "session.lifetime_hours": 8,
+    # Failed logins from one address before it is refused for the window.
+    "login.max_failures": 5,
+    "login.lockout_minutes": 15,
     "data.retention_days": 90,
     "monitors.poll_interval_seconds": 60,
     "smtp.host": "",
@@ -48,6 +55,7 @@ DEFAULTS: dict[str, Any] = {
     "smtp.username": "",
     "smtp.password": "",
     "smtp.recipients": [],
+    "smtp.from": "",
     "webhook.url": "",
     "webhook.template": _DEFAULT_WEBHOOK_TEMPLATE,
     "ansible.sources": [],
@@ -78,12 +86,24 @@ DEFAULTS: dict[str, Any] = {
     "thresholds.load_warn": 80, "thresholds.load_crit": 100,
     "thresholds.temp_warn": 70, "thresholds.temp_crit": 85,
     "thresholds.uptime_warn": 99.0, "thresholds.uptime_crit": 95.0,
+    # Days left on an HTTPS monitor's certificate (lower is worse), and how
+    # many container deaths within an hour count as crash-looping.
+    "thresholds.tls_warn_days": 14, "thresholds.tls_crit_days": 3,
+    "thresholds.crash_loop_deaths": 3,
     # Docker time-series retention (rule 25 — tunable, no restart). Raw 30s
     # samples are heavy, so keep a short raw window then roll up to hourly
     # averages kept much longer; lifecycle events are light, keep a month.
     "docker.retention.metrics_raw_days": 7,
     "docker.retention.metrics_rollup_days": 90,
     "docker.retention.events_days": 30,
+    # Container logs (m79): on by default for every container (operator
+    # preference). `exclude` names containers the server drops on ingest; the
+    # per-container ring bounds storage (rotate oldest past whichever of ~age or
+    # ~bytes hits first — a chatty container just keeps a shorter window).
+    "docker.logs.enabled": True,
+    "docker.logs.exclude": [],
+    "docker.logs.retention_days": 3,
+    "docker.logs.max_bytes_per_container": 5_000_000,
     # Host/plugin metrics retention (plugin_metrics): keep a short raw window at
     # the agent's ~30s cadence, then roll up to hourly averages kept much longer.
     "metrics.retention.raw_days": 7,
@@ -98,7 +118,6 @@ DEFAULTS: dict[str, Any] = {
     # Per-plugin yaml config defaults are merged on top at load time.
     "plugin.docker": {"enabled": True},
     "plugin.host_agent": {"enabled": True},
-    "plugin.http": {"enabled": True},
     "plugin.snmp": {"enabled": True},
     # OIDC single-sign-on
     "oidc.enabled": False,
@@ -116,6 +135,7 @@ DEFAULTS: dict[str, Any] = {
     "ldap.host": "",
     "ldap.port": 389,
     "ldap.tls": False,
+    "ldap.ca_cert": "",
     "ldap.bind_dn": "",
     "ldap.bind_password": "",
     "ldap.base_dn": "",
@@ -141,6 +161,9 @@ SECRET_KEYS: set[str] = {
     "ansible.ssh_private_key",
     "ansible.become_password",
     "ansible.vault_password",
+    # A webhook URL carries its own credential (Discord, Slack and ntfy put the
+    # token in the path).
+    "webhook.url",
 }
 
 
@@ -182,6 +205,31 @@ def _is_undecryptable(stored: Any, key: str = "") -> bool:
     )
 
 
+# Git sources live as a list under one setting, so their tokens are sealed
+# field by field rather than through SECRET_KEYS.
+SOURCES_KEY = "ansible.sources"
+
+
+def seal_source_tokens(sources: Any) -> tuple[Any, int]:
+    """Encrypt each source's plaintext http_token; returns (sources, how many)."""
+    from steward.core.crypto import encrypt_secret, is_encrypted
+    if not isinstance(sources, list):
+        return sources, 0
+    sealed, count = [], 0
+    for src in sources:
+        token = src.get("http_token") if isinstance(src, dict) else None
+        if isinstance(token, str) and token and not is_encrypted(token):
+            src = {**src, "http_token": encrypt_secret(token)}
+            count += 1
+        sealed.append(src)
+    return sealed, count
+
+
+def source_token_key(name: str) -> str:
+    """How a source's token is named in logs and the undecryptable-secrets banner."""
+    return f"{SOURCES_KEY}[{name}].http_token"
+
+
 # ─────────────────────────────────────────────────────────────────────────────
 # Async helpers (use inside request handlers / scheduled tasks)
 # ─────────────────────────────────────────────────────────────────────────────
@@ -221,6 +269,82 @@ async def set_setting(session: AsyncSession, key: str, value: Any) -> None:
         _undecryptable_secrets.discard(key)
 
 
+async def delete_setting(session: AsyncSession, key: str) -> bool:
+    """Remove a stored setting row. Returns True if a row was actually deleted.
+
+    Call in a transaction. Deleting a key that also has a DEFAULT reverts it to
+    that default rather than unsetting it — so this only meaningfully *removes*
+    a setting when no default declares it.
+    """
+    result = await session.execute(
+        select(AppSetting).where(AppSetting.key == key)
+    )
+    row = result.scalar_one_or_none()
+    if row is None:
+        return False
+    await session.delete(row)
+    return True
+
+
+async def get_stored_plugin_names(session: AsyncSession) -> list[str]:
+    """Plugin names that have a real stored row, ignoring DEFAULTS.
+
+    Deliberately NOT derived from get_all_settings: that merges DEFAULTS in, and
+    a plugin.* key present only as a default is a code-level declaration rather
+    than operator data. Offering to "remove" such a key would be a lie — the
+    default would simply reassert it on the next load (exactly the bug behind
+    the phantom `plugin.http` entry). Only stored rows can actually be cleaned up.
+
+    Returns names only, never values: plugin config can hold credentials, and
+    nothing that lists orphans needs to read them.
+    """
+    prefix = "plugin."
+    result = await session.execute(
+        select(AppSetting.key).where(AppSetting.key.like(f"{prefix}%"))
+    )
+    return sorted(
+        key[len(prefix):] for key in result.scalars() if key != prefix
+    )
+
+
+def find_orphaned_plugins(
+    stored_names: Iterable[str],
+    installed_names: Iterable[str],
+    failures: Mapping[str, str] | None = None,
+) -> list[dict[str, Any]]:
+    """Plugins that are configured or failed to load, but are not installed.
+
+    Pure so it can be tested without a DB or a filesystem. "Not installed" is
+    intentionally not treated as "safe to delete" — an external plugin under
+    /data/plugins can be missing merely because the volume isn't mounted or an
+    install failed, so the caller surfaces these for an explicit operator
+    decision instead of removing them automatically.
+
+    Driven by the UNION of stored settings and load failures, not by stored
+    settings alone. `load_plugins` records a failure for any enabled plugin
+    whose directory it cannot find, and the admin banner counts those — so a
+    failure with no stored row (a plugin enabled by a DEFAULTS entry) would
+    otherwise be counted in the banner and shown nowhere, which is exactly the
+    dead end this section exists to close.
+
+    Each row carries `removable`: only a plugin with a real stored row can
+    actually be cleaned up. Offering Remove for a default-declared plugin would
+    be a lie — deleting nothing, while the default reasserts it on next load.
+    """
+    installed = set(installed_names)
+    failures = dict(failures or {})
+    stored = {name for name in stored_names if name}
+    candidates = (stored | set(failures)) - installed
+    return [
+        {
+            "name": name,
+            "reason": failures.get(name),
+            "removable": name in stored,
+        }
+        for name in sorted(candidates)
+    ]
+
+
 async def get_all_settings(session: AsyncSession) -> dict[str, Any]:
     """Return flat key→value dict with defaults filled in for missing keys."""
     result = await session.execute(select(AppSetting))
@@ -247,6 +371,7 @@ def to_smtp_cfg(settings: dict[str, Any]) -> dict:
         "username": settings.get("smtp.username", ""),
         "password": settings.get("smtp.password", ""),
         "recipients": settings.get("smtp.recipients", []),
+        "from": settings.get("smtp.from", ""),
     }
 
 
@@ -278,13 +403,33 @@ def to_ldap_cfg(settings: dict[str, Any]) -> dict:
     return {k[len("ldap."):]: settings.get(k, DEFAULTS[k]) for k in DEFAULTS if k.startswith("ldap.")}
 
 
+def _int(settings: dict[str, Any], key: str) -> int:
+    try:
+        return int(settings.get(key, DEFAULTS[key]))
+    except (TypeError, ValueError):
+        return int(DEFAULTS[key])
+
+
+def to_access_cfg(settings: dict[str, Any]) -> dict:
+    """app.config keys for sessions, logins and the trusted proxy."""
+    from datetime import timedelta
+    hours = max(1, _int(settings, "session.lifetime_hours"))
+    return {
+        "SESSION_LIFETIME_HOURS": hours,
+        "PERMANENT_SESSION_LIFETIME": timedelta(hours=hours),
+        "TRUSTED_PROXY_HOPS": max(0, _int(settings, "general.trusted_proxy_hops")),
+        "LOGIN_MAX_FAILURES": max(1, _int(settings, "login.max_failures")),
+        "LOGIN_LOCKOUT_MINUTES": max(1, _int(settings, "login.lockout_minutes")),
+    }
+
+
 def to_thresholds_cfg(settings: dict[str, Any]) -> dict:
     """Per-metric (warn, crit, direction) policy for degraded-value coloring.
 
     Centralizes "what counts as degraded" so templates just name a metric kind
-    via the threshold_style() jinja global. `dir` is "high" (higher is worse,
-    e.g. CPU) or "low" (lower is worse, e.g. uptime %). Latency reuses the
-    existing ping good/warn thresholds.
+    via the status_class() and threshold_style() jinja globals. `dir` is
+    "high" (higher is worse, e.g. CPU) or "low" (lower is worse, e.g. uptime
+    %). Latency reuses the existing ping good/warn thresholds.
     """
     g = settings.get
     return {
@@ -295,34 +440,23 @@ def to_thresholds_cfg(settings: dict[str, Any]) -> dict:
         "temp":    {"warn": g("thresholds.temp_warn", 70), "crit": g("thresholds.temp_crit", 85), "dir": "high"},
         "latency": {"warn": g("ping.threshold.good_ms", 50), "crit": g("ping.threshold.warn_ms", 200), "dir": "high"},
         "uptime":  {"warn": g("thresholds.uptime_warn", 99.0), "crit": g("thresholds.uptime_crit", 95.0), "dir": "low"},
+        "tls_days": {"warn": g("thresholds.tls_warn_days", 14), "crit": g("thresholds.tls_crit_days", 3), "dir": "low"},
+        "crash_loop": {"warn": g("thresholds.crash_loop_deaths", 3), "crit": g("thresholds.crash_loop_deaths", 3), "dir": "high"},
     }
 
 
-def threshold_style_for(value: Any, kind: str, thresholds: dict) -> str:
-    """Return an inline-style fragment (amber at warn, red at crit) for a metric.
+_STATUS_STYLE = {"warn": "color:var(--yellow);font-weight:500;",
+                 "crit": "color:var(--red);font-weight:500;"}
 
-    The Python twin of the old _macros.metric_style, but reading configurable
-    cutoffs from `thresholds` (see to_thresholds_cfg) and handling both
-    directions. Empty string when normal/unknown/None — drop straight into a
+
+def threshold_style_for(value: Any, kind: str, thresholds: dict) -> str:
+    """Return an inline-style fragment (amber at warn, red at crit) for a metric,
+    graded by formatting.status_class against `thresholds` (to_thresholds_cfg).
+    Empty string when the reading is normal or missing — drop straight into a
     span's style="".
     """
-    if value is None:
-        return ""
-    th = thresholds.get(kind)
-    if not th:
-        return ""
-    warn, crit, direction = th["warn"], th["crit"], th.get("dir", "high")
-    if direction == "low":
-        if value < crit:
-            return "color:var(--red);font-weight:700;"
-        if value < warn:
-            return "color:var(--yellow);font-weight:600;"
-    else:
-        if value >= crit:
-            return "color:var(--red);font-weight:700;"
-        if value >= warn:
-            return "color:var(--yellow);font-weight:600;"
-    return ""
+    from steward.core.formatting import status_class
+    return _STATUS_STYLE.get(status_class(value, kind, thresholds), "")
 
 
 def to_plugins_cfg(settings: dict[str, Any]) -> dict:
@@ -390,6 +524,13 @@ def migrate_plaintext_secrets(db_url: str) -> int:
                         if isinstance(val, str) and val and not is_encrypted(val):
                             row.value_json = json.dumps(encrypt_secret(val))
                             converted += 1
+                    row = (await session.execute(
+                        select(AppSetting).where(AppSetting.key == SOURCES_KEY))).scalar_one_or_none()
+                    if row is not None:
+                        sources, sealed = seal_source_tokens(json.loads(row.value_json))
+                        if sealed:
+                            row.value_json = json.dumps(sources)
+                            converted += sealed
         finally:
             await engine.dispose()
         return converted
@@ -418,6 +559,14 @@ def scan_undecryptable_secrets(db_url: str) -> list[str]:
                 for row in result.scalars():
                     if _is_undecryptable(json.loads(row.value_json), row.key):
                         bad.append(row.key)
+                row = (await session.execute(
+                    select(AppSetting).where(AppSetting.key == SOURCES_KEY))).scalar_one_or_none()
+                sources = json.loads(row.value_json) if row is not None else []
+                for src in sources if isinstance(sources, list) else []:
+                    if isinstance(src, dict):
+                        key = source_token_key(src.get("name", "?"))
+                        if _is_undecryptable(src.get("http_token"), key):
+                            bad.append(key)
         finally:
             await engine.dispose()
         return bad

steward/core/status.py

@@ -38,6 +38,10 @@ class StatusEntry:
     spark_svg: str = ""             # filled by the route via sparkline_svg()
     tls_days: float | None = None   # days until TLS expiry (http only)
     detail_url: str | None = None
+    # When the current up/down state began, as far as the recent checks show;
+    # since_at_least means every check we have agrees, so it began earlier.
+    since: datetime | None = None
+    since_at_least: bool = False
 
 
 StatusSource = Callable[[object], Awaitable[list[StatusEntry]]]
@@ -158,6 +162,17 @@ async def _uptime_by_monitor(db, monitor_ids: list[str]) -> dict[str, dict]:
     return out
 
 
+def streak_start(results) -> tuple[datetime | None, bool]:
+    """(checked_at of the first check in the latest run of the same result,
+    whether that run fills every check given). Results are oldest-first."""
+    if not results:
+        return None, False
+    i = len(results) - 1
+    while i > 0 and results[i - 1].is_up == results[-1].is_up:
+        i -= 1
+    return results[i].checked_at, i == 0
+
+
 def _heartbeat_title(mtype: str, r) -> str:
     """Type-aware tooltip for one heartbeat cell."""
     ts = f"{r.checked_at:%H:%M:%S} UTC"
@@ -191,6 +206,7 @@ async def monitor_status_source(db) -> list[StatusEntry]:
         rows = recent.get(m.id, [])
         latest = rows[-1] if rows else None
         status = "pending" if latest is None else ("up" if latest.is_up else "down")
+        since, since_at_least = streak_start(rows)
         tls_days = None
         if latest and latest.tls_expires_at:
             tls_days = (latest.tls_expires_at - now).total_seconds() / 86400.0
@@ -203,5 +219,6 @@ async def monitor_status_source(db) -> list[StatusEntry]:
             latency_ms=latest.response_ms if latest else None,
             spark=[r.response_ms for r in rows if r.response_ms is not None],
             tls_days=tls_days, detail_url="/monitors/",
+            since=since, since_at_least=since_at_least,
         ))
     return entries

steward/dashboard/routes.py

@@ -6,7 +6,7 @@ from datetime import datetime, timezone, timedelta
 from urllib.parse import urlencode
 from quart import Blueprint, render_template, current_app, abort, redirect, request, session
 from sqlalchemy import select, func, update
-from steward.auth.middleware import require_role, current_user_id
+from steward.auth.middleware import public_route, require_role, current_user_id
 from steward.models.users import UserRole
 from steward.models.hosts import Host
 from steward.models.dashboard import Dashboard, DashboardWidget, DashboardShareToken
@@ -513,6 +513,7 @@ async def revoke_share_token(dash_id: int, token_id: int):
 # ── Public share view (no login required) ────────────────────────────────────
 
 @dashboard_bp.get("/share/<raw_token>")
+@public_route("a share link; the token is the credential")
 async def public_share(raw_token: str):
     token_hash = hashlib.sha256(raw_token.encode()).hexdigest()
     now        = datetime.now(timezone.utc)

steward/dashboard/share.py

@@ -0,0 +1,58 @@
+"""What a dashboard share link opens.
+
+A share link's page (/share/<token>) loads each of its dashboard's widgets
+from a fragment URL with `&s=<token>` appended. The token opens exactly those
+URLs, read-only: the same path and the same configured parameters (which host,
+which container). Only the time window a viewer can switch on the widget
+itself (VIEW_PARAMS) may differ. Every other page, and the same widget aimed
+at a different host, still needs a login.
+"""
+from __future__ import annotations
+
+import hashlib
+from datetime import datetime, timezone
+from urllib.parse import parse_qsl
+
+from sqlalchemy import select
+
+from steward.models.dashboard import DashboardShareToken
+
+# Parameters a shared widget may change in place: they pick a time window,
+# never which thing is shown.
+VIEW_PARAMS = frozenset({"hours", "range"})
+
+
+def share_allows(widget_urls: list[str], path: str, args) -> bool:
+    """True when `path` + `args` (minus the token) is one of `widget_urls`,
+    allowing only VIEW_PARAMS to differ."""
+    got: dict[str, str] = {}
+    for key in args:
+        if key == "s":
+            continue
+        values = args.getlist(key)
+        if len(values) != 1:
+            return False
+        got[key] = values[0]
+    for url in widget_urls:
+        wpath, _, query = url.partition("?")
+        if wpath != path:
+            continue
+        want = {k: v for k, v in parse_qsl(query, keep_blank_values=True) if k not in VIEW_PARAMS}
+        if all(got.get(k) == v for k, v in want.items()) and set(got) <= set(want) | VIEW_PARAMS:
+            return True
+    return False
+
+
+async def share_grants(db, raw_token: str, path: str, args) -> bool:
+    """True when `raw_token` is a live share token whose dashboard loads this URL."""
+    token_hash = hashlib.sha256(raw_token.encode()).hexdigest()
+    share = (await db.execute(
+        select(DashboardShareToken).where(DashboardShareToken.token_hash == token_hash)
+    )).scalar_one_or_none()
+    if share is None:
+        return False
+    if share.expires_at is not None and share.expires_at <= datetime.now(timezone.utc):
+        return False
+    from .routes import _get_widgets, _resolve_widgets
+    widgets = _resolve_widgets(await _get_widgets(db, share.dashboard_id))
+    return share_allows([w["hx_url"] for w in widgets], path, args)

steward/database.py

@@ -1,10 +1,49 @@
 from __future__ import annotations
+import asyncio
+import logging
+import time
 from typing import TYPE_CHECKING
-from sqlalchemy.ext.asyncio import create_async_engine, async_sessionmaker, AsyncSession
+from sqlalchemy import text
+from sqlalchemy.exc import SQLAlchemyError
+from sqlalchemy.ext.asyncio import (
+    create_async_engine, async_sessionmaker, AsyncEngine, AsyncSession,
+)
+from sqlalchemy.pool import NullPool
 
 if TYPE_CHECKING:
     from quart import Quart
 
+logger = logging.getLogger(__name__)
+
+# Recycle pooled connections after 30 minutes. Nothing in Postgres closes an
+# idle connection by default, but the path to it is not always durable: NAT and
+# conntrack tables drop idle flows, and a Docker network rebuild silently
+# strands existing sockets. Capping connection age means a stranded connection
+# is retired on a timer instead of surfacing as a failed query later.
+POOL_RECYCLE_SECONDS = 1800
+
+# Total budget for the database to become reachable at startup, and the backoff
+# ceiling between attempts. 60s comfortably covers Postgres WAL recovery after
+# an unclean shutdown (observed ~7s) plus Docker DNS coming up on a host reboot.
+DB_CONNECT_TIMEOUT_SECONDS = 60.0
+_BACKOFF_INITIAL_SECONDS = 0.5
+_BACKOFF_MAX_SECONDS = 5.0
+
+# Per-REQUEST retry schedule (seconds between attempts), total ~1.75s across 4
+# tries. Far shorter than the startup budget on purpose: nobody is watching a
+# container boot, but somebody is watching this page load. Long enough to ride
+# out a pool blip or a fast reconnect, short enough that a genuinely-down
+# database gets an honest answer instead of a spinner.
+_REQUEST_RETRY_DELAYS = (0.25, 0.5, 1.0)
+
+# Postgres SQLSTATEs that will never resolve by waiting — retrying these just
+# delays a clear error behind a full timeout budget.
+_FATAL_SQLSTATES = {
+    "28P01",  # invalid_password
+    "28000",  # invalid_authorization_specification
+    "3D000",  # invalid_catalog_name — database does not exist
+}
+
 
 def init_db(app: "Quart") -> None:
     """Create async engine and attach db_sessionmaker to app.
@@ -13,8 +52,162 @@ def init_db(app: "Quart") -> None:
     Does not create tables — Alembic handles migrations.
     """
     db_url: str = app.config["DATABASE_URL"]
-    engine = create_async_engine(db_url, echo=False)
+    engine = create_async_engine(
+        db_url,
+        echo=False,
+        # Check a pooled connection is still alive before handing it out. When
+        # the database restarts, every connection already in the pool is dead
+        # at the socket level; without this, SQLAlchemy only discovers that by
+        # failing a real query, so the first operation after a DB restart
+        # errors out on whatever triggered it (a request, a scheduled poll).
+        # The check is a cheap round-trip and it makes a DB restart invisible.
+        pool_pre_ping=True,
+        pool_recycle=POOL_RECYCLE_SECONDS,
+    )
     app.db_sessionmaker: async_sessionmaker[AsyncSession] = async_sessionmaker(
         engine, expire_on_commit=False
     )
     app._db_engine = engine
+
+
+def _fatal_sqlstate(exc: BaseException) -> str | None:
+    """Return the SQLSTATE if this error chain carries a non-retryable one."""
+    seen: set[int] = set()
+    cur: BaseException | None = exc
+    while cur is not None and id(cur) not in seen:
+        seen.add(id(cur))
+        sqlstate = getattr(cur, "sqlstate", None)
+        if sqlstate in _FATAL_SQLSTATES:
+            return sqlstate
+        cur = cur.__cause__ or cur.__context__
+    return None
+
+
+def _describe(exc: BaseException) -> str:
+    """Innermost cause, which is the part that says what actually went wrong.
+
+    SQLAlchemy wraps DBAPI errors several layers deep; the outer message is
+    boilerplate, so surface the root for the waiting-for-database log line.
+    """
+    cur: BaseException = exc
+    seen: set[int] = {id(cur)}
+    while True:
+        nxt = cur.__cause__ or cur.__context__
+        if nxt is None or id(nxt) in seen:
+            return f"{type(cur).__name__}: {cur}"
+        seen.add(id(nxt))
+        cur = nxt
+
+
+def wait_for_database(
+    db_url: str,
+    timeout_seconds: float = DB_CONNECT_TIMEOUT_SECONDS,
+) -> None:
+    """Block until the database accepts a connection, or raise after the budget.
+
+    Steward otherwise assumes the database is both resolvable and *ready* the
+    first time it asks, which is false in two ordinary situations:
+
+      • Host reboot / full stack restart — the app container can try to resolve
+        the `db` service name before Docker's embedded DNS has the record,
+        giving `gaierror -2 Name or service not known`.
+      • Unclean shutdown — Postgres is listening but still replaying WAL, and
+        refuses connections with "the database system is not yet accepting
+        connections" until recovery reaches a consistent state.
+
+    compose's `depends_on: service_healthy` covers ordering on a clean `up`,
+    but not either of the above. Both are transient and self-healing, so retry
+    rather than dumping a traceback and dying. Credential and missing-database
+    errors are NOT transient and fail immediately.
+    """
+    deadline = time.monotonic() + timeout_seconds
+    delay = _BACKOFF_INITIAL_SECONDS
+    attempt = 0
+    last_exc: BaseException | None = None
+
+    while True:
+        attempt += 1
+        try:
+            asyncio.run(_probe(db_url))
+        except Exception as exc:  # broad by design — classified just below
+            sqlstate = _fatal_sqlstate(exc)
+            if sqlstate is not None:
+                # Wrong password / missing database: waiting cannot fix it.
+                raise
+            last_exc = exc
+            remaining = deadline - time.monotonic()
+            if remaining <= 0:
+                break
+            logger.warning(
+                "Database not ready (attempt %d, %.0fs budget left): %s — "
+                "retrying in %.1fs",
+                attempt, remaining, _describe(exc), min(delay, remaining),
+            )
+            time.sleep(min(delay, remaining))
+            delay = min(delay * 2, _BACKOFF_MAX_SECONDS)
+        else:
+            if attempt > 1:
+                logger.info("Database ready after %d attempt(s)", attempt)
+            return
+
+    detail = f" Last error: {_describe(last_exc)}" if last_exc is not None else ""
+    raise RuntimeError(
+        f"Database did not become available within {timeout_seconds:.0f}s "
+        f"({attempt} attempts).{detail}"
+    ) from last_exc
+
+
+class DatabaseUnavailable(Exception):
+    """The database could not be reached while serving a request."""
+
+
+async def ensure_database_reachable(engine: AsyncEngine) -> None:
+    """Check out one pooled connection, retrying briefly, or raise.
+
+    Startup readiness (wait_for_database) does not help once the app is already
+    serving: if the database goes away underneath a running Steward, the next
+    request needs a connection, the pooled ones are dead, and establishing a new
+    one fails — which is how a login attempt turned into an opaque 500.
+
+    pool_pre_ping already makes recovery automatic *once the database is back*.
+    What it cannot do is wait: while the container is genuinely down, its
+    replacement connect fails too. So retry briefly here to ride out a restart,
+    then give up and let the caller render an honest "database unavailable"
+    page rather than a generic error.
+
+    The budget is deliberately short — a person is waiting on this request, and
+    a page that hangs for half a minute is worse than one that says plainly
+    what is wrong and offers a retry.
+    """
+    last_exc: BaseException | None = None
+    for attempt, delay in enumerate(_REQUEST_RETRY_DELAYS + (None,)):
+        try:
+            async with engine.connect():
+                if attempt:
+                    logger.info(
+                        "Database reachable again after %d retry attempt(s)", attempt)
+                return
+        except (SQLAlchemyError, OSError) as exc:
+            # Bad credentials / missing database will never resolve by waiting,
+            # and they are not what this guard is for — let them surface.
+            if _fatal_sqlstate(exc) is not None:
+                raise
+            last_exc = exc
+            if delay is not None:
+                await asyncio.sleep(delay)
+
+    raise DatabaseUnavailable(_describe(last_exc)) from last_exc
+
+
+async def _probe(db_url: str) -> None:
+    """Open one throwaway connection and round-trip a trivial query.
+
+    Uses its own engine with NullPool: this runs before the app engine exists,
+    and a probe connection must never be left in a pool for real work to reuse.
+    """
+    engine = create_async_engine(db_url, echo=False, poolclass=NullPool)
+    try:
+        async with engine.connect() as conn:
+            await conn.execute(text("SELECT 1"))
+    finally:
+        await engine.dispose()

steward/hosts/routes.py

@@ -1,17 +1,16 @@
 from __future__ import annotations
 import asyncio
 import uuid
-from datetime import datetime, timedelta, timezone
 from quart import Blueprint, render_template, request, redirect, url_for, current_app, session
-from sqlalchemy import and_, case, select, func
+from sqlalchemy import select
 from steward.ansible import executor, sources as ansible_src
 from steward.auth.middleware import require_role
-from steward.core.audit import log_audit
+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.monitors import Monitor, MonitorResult
 from steward.models.users import UserRole
-from steward.core.status import _last_n_results, _uptime_by_monitor, _heartbeat_title
+from steward.hosts import service as host_svc
 
 hosts_bp = Blueprint("hosts", __name__, url_prefix="/hosts")
 
@@ -23,235 +22,18 @@ def _ansible_source_names() -> list[str]:
         return []
 
 
-async def _compute_uptime(db) -> dict[str, dict]:
-    """Per-host uptime % for 24h/7d/30d, aggregated over the host's monitors.
-
-    Returns {host_id: {"24h": float|None, "7d": float|None, "30d": float|None}}.
-    """
-    now = datetime.now(timezone.utc)
-    cutoff_30d = now - timedelta(days=30)
-    cutoff_7d  = now - timedelta(days=7)
-    cutoff_24h = now - timedelta(hours=24)
-
-    result = await db.execute(
-        select(
-            Monitor.host_id,
-            func.count(MonitorResult.id).label("total_30d"),
-            func.sum(case((MonitorResult.is_up.is_(True), 1), else_=0)).label("up_30d"),
-            func.sum(case((MonitorResult.checked_at >= cutoff_7d, 1), else_=0)).label("total_7d"),
-            func.sum(case(
-                (and_(MonitorResult.checked_at >= cutoff_7d, MonitorResult.is_up.is_(True)), 1),
-                else_=0,
-            )).label("up_7d"),
-            func.sum(case((MonitorResult.checked_at >= cutoff_24h, 1), else_=0)).label("total_24h"),
-            func.sum(case(
-                (and_(MonitorResult.checked_at >= cutoff_24h, MonitorResult.is_up.is_(True)), 1),
-                else_=0,
-            )).label("up_24h"),
-        )
-        .join(Monitor, Monitor.id == MonitorResult.monitor_id)
-        .where(Monitor.host_id.isnot(None), MonitorResult.checked_at >= cutoff_30d)
-        .group_by(Monitor.host_id)
-    )
-
-    def _pct(up, total):
-        return round(float(up) / float(total) * 100, 2) if total else None
-
-    stats: dict[str, dict] = {}
-    for row in result:
-        stats[row.host_id] = {
-            "24h": _pct(row.up_24h, row.total_24h),
-            "7d":  _pct(row.up_7d,  row.total_7d),
-            "30d": _pct(row.up_30d, row.total_30d),
-        }
-    return stats
-
-
-async def _host_status(db, host_ids: list[str]) -> dict[str, dict]:
-    """Per-host status rollup from the latest result of each linked monitor.
-
-    {host_id: {"state": "up"|"down"|"pending", "latency_ms": float|None,
-               "count": int}}. State is down if ANY linked monitor's latest
-    result is down (worst-case), up if at least one is up, else pending.
-    """
-    if not host_ids:
-        return {}
-    rn = func.row_number().over(
-        partition_by=MonitorResult.monitor_id, order_by=MonitorResult.checked_at.desc()
-    ).label("rn")
-    subq = (
-        select(MonitorResult.id, rn)
-        .join(Monitor, Monitor.id == MonitorResult.monitor_id)
-        .where(Monitor.host_id.in_(host_ids), Monitor.enabled.is_(True))
-        .subquery()
-    )
-    rows = (await db.execute(
-        select(MonitorResult, Monitor.host_id)
-        .join(subq, MonitorResult.id == subq.c.id)
-        .join(Monitor, Monitor.id == MonitorResult.monitor_id)
-        .where(subq.c.rn == 1)
-    )).all()
-    out: dict[str, dict] = {}
-    for res, host_id in rows:
-        d = out.setdefault(host_id, {"state": "pending", "latency_ms": None, "count": 0})
-        d["count"] += 1
-        if not res.is_up:
-            d["state"] = "down"
-        elif d["state"] != "down":
-            d["state"] = "up"
-        if res.is_up and res.response_ms is not None:
-            d["latency_ms"] = (res.response_ms if d["latency_ms"] is None
-                               else min(d["latency_ms"], res.response_ms))
-    return out
-
-
-async def _host_monitors(db, host_id: str) -> list[dict]:
-    """Display rows for the monitors linked to one host (host hub section)."""
-    monitors = (await db.execute(
-        select(Monitor).where(Monitor.host_id == host_id).order_by(Monitor.name)
-    )).scalars().all()
-    ids = [m.id for m in monitors]
-    recent = await _last_n_results(db, ids)
-    uptime = await _uptime_by_monitor(db, ids)
-    data = []
-    for m in monitors:
-        mrows = recent.get(m.id, [])
-        latest = mrows[-1] if mrows else None
-        data.append({
-            "monitor": m, "latest": latest,
-            "heartbeat": [{"state": "up" if r.is_up else "down",
-                           "title": _heartbeat_title(m.type, r)} for r in mrows],
-            "uptime_pct": uptime.get(m.id, {}).get("24h"),
-        })
-    return data
-
-
-async def _agent_metrics_by_host(db, host_names: list[str]) -> dict[str, dict]:
-    """Latest agent cpu/mem per host name from the generic PluginMetric table.
-
-    Read directly (PluginMetric is a core model) so the Hosts list can show an
-    at-a-glance agent column without importing the host_agent plugin.
-    """
-    from steward.models.metrics import PluginMetric
-    if not host_names:
-        return {}
-    wanted = ("cpu_pct", "mem_used_pct")
-    subq = (
-        select(
-            PluginMetric.resource_name, PluginMetric.metric_name,
-            func.max(PluginMetric.recorded_at).label("m"),
-        )
-        .where(
-            PluginMetric.source_module == "host_agent",
-            PluginMetric.metric_name.in_(wanted),
-            PluginMetric.resource_name.in_(host_names),
-        )
-        .group_by(PluginMetric.resource_name, PluginMetric.metric_name)
-    ).subquery()
-    rows = (await db.execute(
-        select(PluginMetric).join(
-            subq,
-            (PluginMetric.resource_name == subq.c.resource_name)
-            & (PluginMetric.metric_name == subq.c.metric_name)
-            & (PluginMetric.recorded_at == subq.c.m),
-        )
-    )).scalars().all()
-    out: dict[str, dict] = {}
-    for r in rows:
-        out.setdefault(r.resource_name, {})[r.metric_name] = r.value
-    return out
-
-
-async def _agent_overview_by_host(db, host_names: list[str]) -> dict[str, dict]:
-    """Per-host agent glance (cpu/mem/root-disk + freshness) from PluginMetric.
-
-    Core-safe (no host_agent import). Freshness compares the latest host-level
-    sample against the plugin's stale window (config), defaulting to 180s.
-    """
-    from steward.models.metrics import PluginMetric
-    if not host_names:
-        return {}
-    now = datetime.now(timezone.utc)
-    stale_after = int(
-        (current_app.config.get("PLUGINS", {}).get("host_agent", {}) or {})
-        .get("stale_after_seconds", 180))
-    resources = list(host_names) + [h + ":/" for h in host_names]
-    subq = (
-        select(
-            PluginMetric.resource_name, PluginMetric.metric_name,
-            func.max(PluginMetric.recorded_at).label("m"),
-        )
-        .where(
-            PluginMetric.source_module == "host_agent",
-            PluginMetric.resource_name.in_(resources),
-            PluginMetric.metric_name.in_(("cpu_pct", "mem_used_pct", "disk_used_pct")),
-        )
-        .group_by(PluginMetric.resource_name, PluginMetric.metric_name)
-    ).subquery()
-    rows = (await db.execute(
-        select(PluginMetric).join(
-            subq,
-            (PluginMetric.resource_name == subq.c.resource_name)
-            & (PluginMetric.metric_name == subq.c.metric_name)
-            & (PluginMetric.recorded_at == subq.c.m),
-        ).where(PluginMetric.source_module == "host_agent")
-    )).scalars().all()
-    out: dict[str, dict] = {}
-    for r in rows:
-        if r.resource_name.endswith(":/") and r.metric_name == "disk_used_pct":
-            out.setdefault(r.resource_name[:-2], {})["disk_root"] = r.value
-        elif r.resource_name in host_names:
-            d = out.setdefault(r.resource_name, {})
-            d[r.metric_name] = r.value
-            if d.get("_ts") is None or r.recorded_at > d["_ts"]:
-                d["_ts"] = r.recorded_at
-    for d in out.values():
-        ts = d.pop("_ts", None)
-        d["fresh"] = bool(ts and (now - ts).total_seconds() <= stale_after)
-    return out
-
-
-async def _agent_cpu_sparks_by_host(db, host_names: list[str], hours: int = 1) -> dict[str, str]:
-    """{host_name: inline-SVG cpu sparkline} over the last `hours` (core-safe).
-
-    A tiny at-a-glance trend in each row — the host-view sparkline, on the widget.
-    """
-    from steward.models.metrics import PluginMetric
-    from steward.core.status import sparkline_svg
-    if not host_names:
-        return {}
-    cutoff = datetime.now(timezone.utc) - timedelta(hours=hours)
-    rows = (await db.execute(
-        select(PluginMetric.resource_name, PluginMetric.value, PluginMetric.recorded_at)
-        .where(
-            PluginMetric.source_module == "host_agent",
-            PluginMetric.metric_name == "cpu_pct",
-            PluginMetric.resource_name.in_(host_names),
-            PluginMetric.recorded_at >= cutoff,
-        )
-        .order_by(PluginMetric.recorded_at)
-    )).all()
-    by_host: dict[str, list[float]] = {}
-    for r in rows:
-        by_host.setdefault(r.resource_name, []).append(r.value)
-    # Amber line to read as "CPU"; only draw when there are a couple of points.
-    return {
-        name: sparkline_svg(vals[-40:], width=64, height=18, stroke="#c8a840")
-        for name, vals in by_host.items() if len(vals) >= 2
-    }
-
-
 @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_status(db, [h.id for h in hosts])
-        uptime = await _compute_uptime(db)
+        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 _agent_overview_by_host(db, host_names)
-        cpu_sparks = await _agent_cpu_sparks_by_host(db, host_names)
+        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",
@@ -266,9 +48,9 @@ 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_status(db, [h.id for h in hosts])
-        uptime = await _compute_uptime(db)
-        agent_metrics = await _agent_metrics_by_host(db, [h.name for h in hosts])
+        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",
@@ -291,8 +73,8 @@ async def host_detail(host_id: str):
             select(Host).where(Host.id == host_id))).scalar_one_or_none()
         if host is None:
             return "Not found", 404
-        monitors = await _host_monitors(db, host_id)
-        uptime = (await _compute_uptime(db)).get(host_id)
+        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()
@@ -326,6 +108,10 @@ async def create_host():
     )
     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,
@@ -358,8 +144,20 @@ async def update_host(host_id: str):
             host = result.scalar_one_or_none()
             if host is None:
                 return "Not found", 404
-            host.name = form["name"].strip()
+            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))
 
 
@@ -440,8 +238,11 @@ async def run_playbook(host_id: str):
 
     # 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
+    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
 
@@ -473,7 +274,9 @@ async def run_playbook(host_id: str):
 
     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})
+                    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))
 
 
@@ -500,21 +303,19 @@ 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 _compute_uptime(db)
+        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():
-    share_token = request.args.get("s")
     async with current_app.db_sessionmaker() as db:
         result = await db.execute(select(Host).order_by(Host.name))
         hosts = result.scalars().all()
-        uptime = await _compute_uptime(db)
+        uptime = await host_svc.compute_uptime(db)
     return await render_template(
         "hosts/uptime_widget.html",
         hosts=hosts,
         uptime=uptime,
-        share_token=share_token,
     )

steward/hosts/service.py

@@ -0,0 +1,263 @@
+"""Host queries shared by the Hosts pages, dashboard widgets and MCP tools.
+
+Every function takes an open session and returns plain data; none reads
+Quart's request context, so the web routes and the /mcp tools (which run
+outside Quart's pipeline) call the same code.
+"""
+from __future__ import annotations
+from datetime import datetime, timedelta, timezone
+
+from sqlalchemy import and_, case, func, select
+
+from steward.core.status import _heartbeat_title, _last_n_results, _uptime_by_monitor
+from steward.models.hosts import Host
+from steward.models.monitors import Monitor, MonitorResult
+
+
+# Host-level agent metrics read for the at-a-glance views (plus the root
+# mount's disk_used_pct, read from the "<host>:/" sub-resource).
+AGENT_GLANCE_METRICS = ("cpu_pct", "mem_used_pct", "disk_used_pct", "disk_used_pct_worst")
+
+
+async def check_name_free(db, name: str, exclude_id: str | None = None) -> None:
+    """ValueError when another host already has this name, or it is blank.
+
+    Agent metrics, container metrics and the alert rules on them go by the
+    host's name, so two hosts sharing one would share one history.
+    """
+    if not name:
+        raise ValueError("a host needs a name.")
+    q = select(Host.id).where(Host.name == name)
+    if exclude_id:
+        q = q.where(Host.id != exclude_id)
+    if (await db.execute(q.limit(1))).first():
+        raise ValueError(f"another host is already named {name!r}; pick a different name.")
+
+
+def agent_stale_after_seconds(config) -> int:
+    """The host_agent plugin's freshness window from app config (default 180s)."""
+    return int(((config.get("PLUGINS") or {}).get("host_agent") or {})
+               .get("stale_after_seconds", 180))
+
+
+async def compute_uptime(db) -> dict[str, dict]:
+    """Per-host uptime % for 24h/7d/30d, aggregated over the host's monitors.
+
+    Returns {host_id: {"24h": float|None, "7d": float|None, "30d": float|None}}.
+    """
+    now = datetime.now(timezone.utc)
+    cutoff_30d = now - timedelta(days=30)
+    cutoff_7d  = now - timedelta(days=7)
+    cutoff_24h = now - timedelta(hours=24)
+
+    result = await db.execute(
+        select(
+            Monitor.host_id,
+            func.count(MonitorResult.id).label("total_30d"),
+            func.sum(case((MonitorResult.is_up.is_(True), 1), else_=0)).label("up_30d"),
+            func.sum(case((MonitorResult.checked_at >= cutoff_7d, 1), else_=0)).label("total_7d"),
+            func.sum(case(
+                (and_(MonitorResult.checked_at >= cutoff_7d, MonitorResult.is_up.is_(True)), 1),
+                else_=0,
+            )).label("up_7d"),
+            func.sum(case((MonitorResult.checked_at >= cutoff_24h, 1), else_=0)).label("total_24h"),
+            func.sum(case(
+                (and_(MonitorResult.checked_at >= cutoff_24h, MonitorResult.is_up.is_(True)), 1),
+                else_=0,
+            )).label("up_24h"),
+        )
+        .join(Monitor, Monitor.id == MonitorResult.monitor_id)
+        .where(Monitor.host_id.isnot(None), MonitorResult.checked_at >= cutoff_30d)
+        .group_by(Monitor.host_id)
+    )
+
+    def _pct(up, total):
+        return round(float(up) / float(total) * 100, 2) if total else None
+
+    stats: dict[str, dict] = {}
+    for row in result:
+        stats[row.host_id] = {
+            "24h": _pct(row.up_24h, row.total_24h),
+            "7d":  _pct(row.up_7d,  row.total_7d),
+            "30d": _pct(row.up_30d, row.total_30d),
+        }
+    return stats
+
+
+async def host_status(db, host_ids: list[str]) -> dict[str, dict]:
+    """Per-host status rollup from the latest result of each linked monitor.
+
+    {host_id: {"state": "up"|"down"|"pending", "latency_ms": float|None,
+               "count": int}}. State is down if ANY linked monitor's latest
+    result is down (worst-case), up if at least one is up, else pending.
+    """
+    if not host_ids:
+        return {}
+    rn = func.row_number().over(
+        partition_by=MonitorResult.monitor_id, order_by=MonitorResult.checked_at.desc()
+    ).label("rn")
+    subq = (
+        select(MonitorResult.id, rn)
+        .join(Monitor, Monitor.id == MonitorResult.monitor_id)
+        .where(Monitor.host_id.in_(host_ids), Monitor.enabled.is_(True))
+        .subquery()
+    )
+    rows = (await db.execute(
+        select(MonitorResult, Monitor.host_id)
+        .join(subq, MonitorResult.id == subq.c.id)
+        .join(Monitor, Monitor.id == MonitorResult.monitor_id)
+        .where(subq.c.rn == 1)
+    )).all()
+    out: dict[str, dict] = {}
+    for res, host_id in rows:
+        d = out.setdefault(host_id, {"state": "pending", "latency_ms": None, "count": 0})
+        d["count"] += 1
+        if not res.is_up:
+            d["state"] = "down"
+        elif d["state"] != "down":
+            d["state"] = "up"
+        if res.is_up and res.response_ms is not None:
+            d["latency_ms"] = (res.response_ms if d["latency_ms"] is None
+                               else min(d["latency_ms"], res.response_ms))
+    return out
+
+
+async def host_monitors(db, host_id: str) -> list[dict]:
+    """Display rows for the monitors linked to one host (host hub section)."""
+    monitors = (await db.execute(
+        select(Monitor).where(Monitor.host_id == host_id).order_by(Monitor.name)
+    )).scalars().all()
+    ids = [m.id for m in monitors]
+    recent = await _last_n_results(db, ids)
+    uptime = await _uptime_by_monitor(db, ids)
+    data = []
+    for m in monitors:
+        mrows = recent.get(m.id, [])
+        latest = mrows[-1] if mrows else None
+        data.append({
+            "monitor": m, "latest": latest,
+            "heartbeat": [{"state": "up" if r.is_up else "down",
+                           "title": _heartbeat_title(m.type, r)} for r in mrows],
+            "uptime_pct": uptime.get(m.id, {}).get("24h"),
+        })
+    return data
+
+
+async def agent_metrics_by_host(db, host_names: list[str]) -> dict[str, dict]:
+    """Latest agent cpu/mem per host name from the generic PluginMetric table.
+
+    Read directly (PluginMetric is a core model) so the Hosts list can show an
+    at-a-glance agent column without importing the host_agent plugin.
+    """
+    from steward.models.metrics import PluginMetric
+    if not host_names:
+        return {}
+    wanted = ("cpu_pct", "mem_used_pct")
+    subq = (
+        select(
+            PluginMetric.resource_name, PluginMetric.metric_name,
+            func.max(PluginMetric.recorded_at).label("m"),
+        )
+        .where(
+            PluginMetric.source_module == "host_agent",
+            PluginMetric.metric_name.in_(wanted),
+            PluginMetric.resource_name.in_(host_names),
+        )
+        .group_by(PluginMetric.resource_name, PluginMetric.metric_name)
+    ).subquery()
+    rows = (await db.execute(
+        select(PluginMetric).join(
+            subq,
+            (PluginMetric.resource_name == subq.c.resource_name)
+            & (PluginMetric.metric_name == subq.c.metric_name)
+            & (PluginMetric.recorded_at == subq.c.m),
+        )
+    )).scalars().all()
+    out: dict[str, dict] = {}
+    for r in rows:
+        out.setdefault(r.resource_name, {})[r.metric_name] = r.value
+    return out
+
+
+async def agent_overview_by_host(
+    db, host_names: list[str], stale_after_seconds: int = 180,
+) -> dict[str, dict]:
+    """Per-host agent glance (cpu/mem/disk + freshness) from PluginMetric.
+
+    {host_name: {cpu_pct, mem_used_pct, disk_used_pct_worst, disk_root,
+                 last_at, fresh}} for each host with any agent samples.
+
+    Core-safe (no host_agent import). Freshness compares the latest host-level
+    sample against the host_agent plugin's stale window (stale_after_seconds;
+    callers pass agent_stale_after_seconds(app.config)).
+    """
+    from steward.models.metrics import PluginMetric
+    if not host_names:
+        return {}
+    now = datetime.now(timezone.utc)
+    stale_after = int(stale_after_seconds)
+    resources = list(host_names) + [h + ":/" for h in host_names]
+    subq = (
+        select(
+            PluginMetric.resource_name, PluginMetric.metric_name,
+            func.max(PluginMetric.recorded_at).label("m"),
+        )
+        .where(
+            PluginMetric.source_module == "host_agent",
+            PluginMetric.resource_name.in_(resources),
+            PluginMetric.metric_name.in_(AGENT_GLANCE_METRICS),
+        )
+        .group_by(PluginMetric.resource_name, PluginMetric.metric_name)
+    ).subquery()
+    rows = (await db.execute(
+        select(PluginMetric).join(
+            subq,
+            (PluginMetric.resource_name == subq.c.resource_name)
+            & (PluginMetric.metric_name == subq.c.metric_name)
+            & (PluginMetric.recorded_at == subq.c.m),
+        ).where(PluginMetric.source_module == "host_agent")
+    )).scalars().all()
+    out: dict[str, dict] = {}
+    for r in rows:
+        if r.resource_name.endswith(":/") and r.metric_name == "disk_used_pct":
+            out.setdefault(r.resource_name[:-2], {})["disk_root"] = r.value
+        elif r.resource_name in host_names:
+            d = out.setdefault(r.resource_name, {})
+            d[r.metric_name] = r.value
+            if d.get("_ts") is None or r.recorded_at > d["_ts"]:
+                d["_ts"] = r.recorded_at
+    for d in out.values():
+        ts = d.pop("_ts", None)
+        d["last_at"] = ts
+        d["fresh"] = bool(ts and (now - ts).total_seconds() <= stale_after)
+    return out
+
+
+async def agent_cpu_sparks_by_host(db, host_names: list[str], hours: int = 1) -> dict[str, str]:
+    """{host_name: inline-SVG cpu sparkline} over the last `hours` (core-safe).
+
+    A tiny at-a-glance trend in each row — the host-view sparkline, on the widget.
+    """
+    from steward.models.metrics import PluginMetric
+    from steward.core.status import sparkline_svg
+    if not host_names:
+        return {}
+    cutoff = datetime.now(timezone.utc) - timedelta(hours=hours)
+    rows = (await db.execute(
+        select(PluginMetric.resource_name, PluginMetric.value, PluginMetric.recorded_at)
+        .where(
+            PluginMetric.source_module == "host_agent",
+            PluginMetric.metric_name == "cpu_pct",
+            PluginMetric.resource_name.in_(host_names),
+            PluginMetric.recorded_at >= cutoff,
+        )
+        .order_by(PluginMetric.recorded_at)
+    )).all()
+    by_host: dict[str, list[float]] = {}
+    for r in rows:
+        by_host.setdefault(r.resource_name, []).append(r.value)
+    # Amber line to read as "CPU"; only draw when there are a couple of points.
+    return {
+        name: sparkline_svg(vals[-40:], width=64, height=18, stroke="#c8a840")
+        for name, vals in by_host.items() if len(vals) >= 2
+    }

steward/mcp/__init__.py

@@ -0,0 +1,4 @@
+"""The MCP endpoint (/mcp): Steward as a server an LLM client can inspect and drive."""
+from .server import mount_mcp
+
+__all__ = ["mount_mcp"]

steward/mcp/_context.py

@@ -0,0 +1,50 @@
+"""Per-request MCP context: who is calling, and which app they are calling.
+
+The /mcp transport bypasses Quart's request pipeline, so neither `session`
+nor `current_app` exists inside a tool. The ASGI auth wrapper in server.py
+sets these from the resolved bearer token before dispatching; tools read them
+through `current_caller()` and `mcp_app()`.
+
+Neither falls back to a default: a tool reached without an authenticated
+caller is a bug in the transport, and it raises rather than acting for nobody.
+"""
+from __future__ import annotations
+from contextvars import ContextVar
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    from quart import Quart
+    from steward.core.api_tokens import Caller
+
+_caller_ctx: ContextVar["Caller | None"] = ContextVar("steward_mcp_caller", default=None)
+_app_ctx: ContextVar["Quart | None"] = ContextVar("steward_mcp_app", default=None)
+# The scheme and host the caller reached /mcp on, e.g. "https://steward.example".
+_base_url_ctx: ContextVar[str] = ContextVar("steward_mcp_base_url", default="")
+
+
+def current_caller() -> "Caller":
+    caller = _caller_ctx.get()
+    if caller is None:
+        raise RuntimeError("no MCP caller in context: the request was not bearer-authenticated")
+    return caller
+
+
+def current_caller_or_none() -> "Caller | None":
+    return _caller_ctx.get()
+
+
+def mcp_app() -> "Quart":
+    app = _app_ctx.get()
+    if app is None:
+        raise RuntimeError("no Steward app in MCP context")
+    return app
+
+
+def public_url() -> str:
+    """Steward's externally reachable base URL, as the web side's
+    public_base_url() gives it: Settings → General → Public base URL when set,
+    else the scheme and host this MCP request arrived on; "" when neither is
+    known."""
+    app = _app_ctx.get()
+    configured = (app.config.get("PUBLIC_BASE_URL") or "").strip() if app is not None else ""
+    return (configured or _base_url_ctx.get()).rstrip("/")

steward/mcp/server.py

@@ -0,0 +1,302 @@
+"""Steward's MCP server: the StewardMCPServer instance and its mount at /mcp.
+
+The /mcp path is dispatched to the MCP SDK's streamable-HTTP ASGI app BEFORE
+Quart sees it (wrapping `app.asgi_app`), so Quart's session, before_request
+hooks and error pages do not apply. This module supplies the equivalents:
+
+- bearer auth: a personal API token resolves to a Caller (user + effective
+  role), set in a ContextVar for the tools — 401 otherwise;
+- the database gate: the same ride-out-a-restart probe the web pipeline uses,
+  answering 503 rather than failing deep in a tool;
+- role gating, default-deny: every tool is registered with a minimum role and
+  a tool the caller's role doesn't reach is neither listed nor callable.
+"""
+from __future__ import annotations
+
+import difflib
+import functools
+import json
+import logging
+
+from mcp.server.mcpserver import MCPServer
+from mcp.server.mcpserver.exceptions import ToolError, UnexpectedToolError
+from mcp.server.transport_security import TransportSecuritySettings
+from mcp.types import ToolAnnotations
+from sqlalchemy.exc import SQLAlchemyError
+
+from steward.auth.middleware import role_meets
+from steward.models.users import UserRole
+
+from . import _context
+
+logger = logging.getLogger(__name__)
+
+MCP_PATH = "/mcp"
+
+# Claude Code injects only the first ~2,048 characters of a server's
+# instructions; keep this well under (test_instructions_fit). The workflow
+# across tools lives here; each tool's own contract lives in its docstring.
+INSTRUCTIONS = """\
+Steward is a self-hosted monitoring and infrastructure hub: hosts, uptime
+monitors, host-agent metrics, Docker containers and logs, alerts, and Ansible
+automation. You act as the user who created your token, at that token's role.
+
+Start broad, then narrow: get_overview says what is wrong right now; follow
+its ids into get_host / get_monitor / get_container, then metrics and logs.
+List tools are bounded: a response with `truncated: true` says which argument
+fetches more. Times are UTC ISO-8601; units are in field names (_pct, _ms,
+_bytes).
+
+Changes are audited under the user's name. run_playbook is a dry run (Ansible
+check mode) unless you pass check=false; dry-run first and show the user the
+diff before applying. If a tool refuses for lack of role, whoami says what
+this token can do.
+"""
+
+_DB_UNAVAILABLE = (
+    "Steward is running but can't reach its database right now, so nothing was "
+    "read or changed. This is usually a database restart; retry in a minute."
+)
+
+
+def _is_db_failure(exc: BaseException | None) -> bool:
+    seen: set[int] = set()
+    while exc is not None and id(exc) not in seen:
+        seen.add(id(exc))
+        if isinstance(exc, (SQLAlchemyError, OSError, TimeoutError)):
+            return True
+        exc = exc.__cause__ or exc.__context__
+    return False
+
+
+class StewardMCPServer(MCPServer):
+    """MCPServer with per-tool minimum roles, plugin-scoped tools and strict args."""
+
+    def __init__(self, app, **kwargs):
+        super().__init__("steward", instructions=INSTRUCTIONS.strip(), **kwargs)
+        self._steward_app = app
+        self.tool_roles: dict[str, UserRole] = {}
+        self.tool_plugins: dict[str, str] = {}
+        # plugin name -> its `mcp_overview(db)`: findings it adds to get_overview.
+        self.overview_sources: dict[str, object] = {}
+
+    # ── registration ─────────────────────────────────────────────────────────
+    def register_tool(self, fn, *, role: UserRole, read_only: bool, plugin: str | None = None) -> None:
+        """The only way a tool reaches the server: name, minimum role, effect.
+
+        `role` and `read_only` are required — there is no default for a
+        mutating tool to inherit by omission.
+        """
+        name = fn.__name__
+        if name in self.tool_roles:
+            raise ValueError(f"MCP tool {name!r} is already registered")
+        if not isinstance(role, UserRole):
+            raise TypeError(f"MCP tool {name!r}: role must be a UserRole, got {role!r}")
+        self.add_tool(
+            fn, name=name,
+            annotations=ToolAnnotations(read_only_hint=read_only,
+                                        destructive_hint=None if read_only else True),
+        )
+        self.tool_roles[name] = role
+        if plugin:
+            self.tool_plugins[name] = plugin
+
+    def register_plugin(self, name: str, module) -> None:
+        """Add a plugin's tools via its optional `register_mcp_tools(register)`,
+        and its optional `mcp_overview(db)` as a get_overview findings source.
+
+        Idempotent per plugin (hot-reload drops its previous tools first) and
+        tolerant: a raising hook is logged and leaves the plugin with no tools,
+        never a broken server.
+        """
+        self._drop_plugin_tools(name)
+        self.overview_sources.pop(name, None)
+        overview = getattr(module, "mcp_overview", None)
+        if callable(overview):
+            self.overview_sources[name] = overview
+        hook = getattr(module, "register_mcp_tools", None)
+        if hook is None:
+            return
+        try:
+            hook(functools.partial(self.register_tool, plugin=name))
+        except Exception:
+            # All or nothing: a hook that fails halfway leaves no partial set.
+            self._drop_plugin_tools(name)
+            logger.exception("Plugin %r: register_mcp_tools() raised; its MCP tools are unavailable", name)
+
+    def _drop_plugin_tools(self, name: str) -> None:
+        for tool_name in [t for t, p in self.tool_plugins.items() if p == name]:
+            self.remove_tool(tool_name)
+            self.tool_roles.pop(tool_name, None)
+            self.tool_plugins.pop(tool_name, None)
+
+    # ── gating ───────────────────────────────────────────────────────────────
+    def plugin_enabled(self, plugin: str) -> bool:
+        cfg = (self._steward_app.config.get("PLUGINS") or {}).get(plugin)
+        return isinstance(cfg, dict) and bool(cfg.get("enabled"))
+
+    def refusal(self, name: str, caller) -> str | None:
+        """Why `caller` may not use tool `name`, or None if they may."""
+        required = self.tool_roles.get(name)
+        if required is None:
+            return f"There is no Steward tool named {name!r}."
+        plugin = self.tool_plugins.get(name)
+        if plugin and not self.plugin_enabled(plugin):
+            return (f"{name} belongs to the {plugin} plugin, which is disabled in this "
+                    "Steward. An admin can enable it under Settings → Plugins.")
+        if caller is None:
+            return "This request is not authenticated."
+        if not role_meets(caller.role, required):
+            return (f"{name} needs the {required.value} role; this connection acts as "
+                    f"{caller.role.value}. A token's role is capped at its user's role — "
+                    "create a token with a higher role on Steward's AI access page if "
+                    "your account allows it.")
+        return None
+
+    async def list_tools(self):
+        caller = _context.current_caller_or_none()
+        tools = await super().list_tools()
+        return [t for t in tools if self.refusal(t.name, caller) is None]
+
+    async def call_tool(self, name, arguments, context=None):
+        refusal = self.refusal(name, _context.current_caller_or_none())
+        if refusal:
+            raise ToolError(refusal)
+
+        # Reject undeclared arguments: pydantic would silently drop a misnamed
+        # one and run the tool with that field's default.
+        tool = self._tool_manager.get_tool(name)
+        declared = set((tool.parameters or {}).get("properties", {})) if tool else set()
+        unknown = sorted(set(arguments or {}) - declared)
+        if unknown:
+            hints = []
+            for arg in unknown:
+                close = difflib.get_close_matches(arg, sorted(declared), n=1)
+                hints.append(f"'{arg}'" + (f" (did you mean '{close[0]}'?)" if close else ""))
+            raise ToolError(
+                f"{name} does not accept {', '.join(hints)}. It accepts: "
+                f"{', '.join(sorted(declared)) or 'no arguments'}. Nothing was run."
+            )
+
+        try:
+            return await super().call_tool(name, arguments, context)
+        except UnexpectedToolError as exc:
+            cause = exc.__cause__
+            # ValueError is how a Steward tool refuses: what, why, what instead.
+            if isinstance(cause, ValueError):
+                raise ToolError(f"{name}: {cause}") from cause
+            if _is_db_failure(cause):
+                logger.warning("MCP tool %s hit a database failure: %r", name, cause)
+                raise ToolError(_DB_UNAVAILABLE) from cause
+            raise
+
+
+def build_mcp_server(app) -> StewardMCPServer:
+    from .tools import register_all
+    mcp = StewardMCPServer(app)
+    register_all(mcp.register_tool)
+    return mcp
+
+
+async def _send_json(send, status: int, payload: dict, extra_headers=()) -> None:
+    await send({
+        "type": "http.response.start",
+        "status": status,
+        "headers": [(b"content-type", b"application/json"), *extra_headers],
+    })
+    await send({"type": "http.response.body", "body": json.dumps(payload).encode()})
+
+
+def mount_mcp(app) -> StewardMCPServer:
+    """Mount the MCP endpoint at /mcp and return the server.
+
+    stateless_http: every request stands alone on its bearer token. The
+    stateful default strands Claude Code after a redeploy — it reconnects with
+    a session id the new process never issued and won't re-initialize on the
+    404 — so stateless is what makes a restart invisible to clients.
+
+    DNS-rebinding protection is off: its default allow-list is localhost only,
+    so any deployment behind a reverse proxy would get 421s. That protection
+    guards a browser rebinding DNS onto a localhost server; here the bearer
+    token is the security boundary.
+    """
+    # Looked up through their modules per request (not bound here) so a test
+    # can stand in for the token store or the database probe.
+    from steward import database
+    from steward.core import api_tokens
+
+    from steward.core.plugin_manager import get_loaded_plugin_modules
+
+    mcp = build_mcp_server(app)
+    for name, module in sorted(get_loaded_plugin_modules().items()):
+        mcp.register_plugin(name, module)
+    mcp_asgi = mcp.streamable_http_app(
+        streamable_http_path=MCP_PATH,
+        stateless_http=True,
+        transport_security=TransportSecuritySettings(enable_dns_rebinding_protection=False),
+    )
+    app.mcp_server = mcp
+
+    # The SDK's session manager owns a task group that must be running before
+    # it serves; host it in Quart's serving lifecycle.
+    @app.before_serving
+    async def _start_mcp() -> None:
+        cm = mcp.session_manager.run()
+        await cm.__aenter__()
+        app._mcp_session_cm = cm
+
+    @app.after_serving
+    async def _stop_mcp() -> None:
+        cm = getattr(app, "_mcp_session_cm", None)
+        if cm is not None:
+            await cm.__aexit__(None, None, None)
+
+    async def handle_mcp(scope, receive, send):
+        headers = {k.decode("latin-1").lower(): v.decode("latin-1")
+                   for k, v in scope.get("headers", [])}
+        auth = headers.get("authorization", "")
+        raw = auth[7:].strip() if auth[:7].lower() == "bearer " else ""
+
+        engine = getattr(app, "_db_engine", None)
+        try:
+            if engine is not None:
+                await database.ensure_database_reachable(engine)
+            caller = await api_tokens.resolve_token(app, raw)
+        except (database.DatabaseUnavailable, SQLAlchemyError, OSError) as exc:
+            logger.error("MCP request refused, database unreachable: %r", exc)
+            await _send_json(send, 503, {"error": "database_unavailable", "message": _DB_UNAVAILABLE})
+            return
+
+        if caller is None:
+            await _send_json(
+                send, 401,
+                {"error": "unauthorized",
+                 "message": "Send a Steward API token as 'Authorization: Bearer stw_…'. "
+                            "Create one on Steward's AI access page."},
+                extra_headers=[(b"www-authenticate", b'Bearer realm="steward-mcp"')],
+            )
+            return
+
+        caller_token = _context._caller_ctx.set(caller)
+        app_token = _context._app_ctx.set(app)
+        host = headers.get("host", "")
+        url_token = _context._base_url_ctx.set(f"{scope.get('scheme', 'http')}://{host}" if host else "")
+        try:
+            await mcp_asgi(scope, receive, send)
+        finally:
+            _context._caller_ctx.reset(caller_token)
+            _context._app_ctx.reset(app_token)
+            _context._base_url_ctx.reset(url_token)
+
+    original_asgi = app.asgi_app
+
+    async def dispatch(scope, receive, send):
+        if scope["type"] == "http":
+            path = scope.get("path", "")
+            if path == MCP_PATH or path.startswith(MCP_PATH + "/"):
+                # Path passes through untouched: the SDK app routes on /mcp itself.
+                return await handle_mcp(scope, receive, send)
+        return await original_asgi(scope, receive, send)
+
+    app.asgi_app = dispatch
+    return mcp

steward/mcp/tools/__init__.py

@@ -0,0 +1,22 @@
+"""Core MCP tool modules.
+
+Each module defines plain `async def` tools at module level (tests call them
+directly) and a `register(register_tool)` that lists them with their minimum
+role. `register_tool(fn, role=..., read_only=...)` takes both as required
+keywords: a tool with no declared role is unreachable, and there is no default
+read_only for a mutating tool to inherit by forgetting.
+
+A tool's docstring IS its contract with the agent — it ships as the tool's
+description. Say what it is for, when to reach for it over its siblings, what
+each argument's empty value means, and what comes back.
+"""
+from __future__ import annotations
+
+from . import alerts, audit, automation, hosts, metrics, monitors, overview, session
+
+_MODULES = (session, overview, hosts, monitors, alerts, metrics, audit, automation)
+
+
+def register_all(register_tool) -> None:
+    for module in _MODULES:
+        module.register(register_tool)

steward/mcp/tools/_audit.py

@@ -0,0 +1,24 @@
+"""Audit trail for changes made through MCP.
+
+Every mutating tool records its change with `audit_mcp`, under the calling
+user's id and the username "<user> via MCP" (an operator ruling on the API
+Surface), so the audit log separates what a person did from what an agent
+did on their token. The token id goes into the detail.
+"""
+from __future__ import annotations
+
+from steward.core.audit import log_audit
+from steward.mcp._context import current_caller, mcp_app
+
+VIA = " via MCP"
+
+
+def mcp_username(username: str) -> str:
+    return (username + VIA)[:64]
+
+
+async def audit_mcp(action: str, entity_type: str | None = None, entity_id: str | None = None,
+                    detail: dict | None = None) -> None:
+    caller = current_caller()
+    await log_audit(mcp_app(), caller.user_id, mcp_username(caller.username), action,
+                    entity_type, entity_id, {**(detail or {}), "token_id": caller.token_id})