feat(web): add Glances integration for host resource stats (#124)

Makes the entry searchable by typing "github" in the command palette.

.gitignore

@@ -37,6 +37,7 @@ ENV/
 .coverage
 .pytest_cache/
 htmlcov/
+.code/
 
 # Local config (don't commit real configs)
 compose-farm.yaml
@@ -45,3 +46,4 @@ coverage.xml
 .env
 homepage/
 site/
+.playwright-mcp/

.pre-commit-config.yaml

@@ -21,7 +21,7 @@ repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
     rev: v0.14.9
     hooks:
-      - id: ruff
+      - id: ruff-check
         args: [--fix]
       - id: ruff-format
 

README.md

@@ -43,8 +43,8 @@ A minimal CLI tool to run Docker Compose commands across multiple hosts via SSH.
   - [What Compose Farm doesn't do](#what-compose-farm-doesnt-do)
 - [Installation](#installation)
 - [SSH Authentication](#ssh-authentication)
-  - [SSH Agent (default)](#ssh-agent-default)
-  - [Dedicated SSH Key (recommended for Docker/Web UI)](#dedicated-ssh-key-recommended-for-dockerweb-ui)
+  - [SSH Agent](#ssh-agent)
+  - [Dedicated SSH Key (default for Docker)](#dedicated-ssh-key-default-for-docker)
 - [Configuration](#configuration)
   - [Single-host example](#single-host-example)
   - [Multi-host example](#multi-host-example)
@@ -54,6 +54,7 @@ A minimal CLI tool to run Docker Compose commands across multiple hosts via SSH.
   - [CLI `--help` Output](#cli---help-output)
   - [Auto-Migration](#auto-migration)
 - [Traefik Multihost Ingress (File Provider)](#traefik-multihost-ingress-file-provider)
+- [Host Resource Monitoring (Glances)](#host-resource-monitoring-glances)
 - [Comparison with Alternatives](#comparison-with-alternatives)
 - [License](#license)
 
@@ -208,9 +209,9 @@ cp .envrc.example .envrc && direnv allow
 
 Compose Farm uses SSH to run commands on remote hosts. There are two authentication methods:
 
-### SSH Agent (default)
+### SSH Agent
 
-Works out of the box if you have an SSH agent running with your keys loaded:
+Works out of the box when running locally if you have an SSH agent running with your keys loaded:
 
 ```bash
 # Verify your agent has keys
@@ -220,9 +221,9 @@ ssh-add -l
 cf up --all
 ```
 
-### Dedicated SSH Key (recommended for Docker/Web UI)
+### Dedicated SSH Key (default for Docker)
 
-When running compose-farm in Docker, the SSH agent connection can be lost (e.g., after container restart). The `cf ssh` command sets up a dedicated key that persists:
+When running in Docker, SSH agent sockets are ephemeral and can be lost after container restarts. The `cf ssh` command sets up a dedicated key that persists:
 
 ```bash
 # Generate key and copy to all configured hosts
@@ -250,6 +251,13 @@ volumes:
   - cf-ssh:${CF_HOME:-/root}/.ssh
 ```
 
+**Option 3: SSH agent forwarding** - if you prefer using your host's ssh-agent
+```yaml
+volumes:
+  - ${SSH_AUTH_SOCK}:/ssh-agent:ro
+```
+Note: Requires `SSH_AUTH_SOCK` environment variable to be set. The socket path is ephemeral and changes across sessions.
+
 Run setup once after starting the container (while the SSH agent still works):
 
 ```bash
@@ -342,18 +350,14 @@ When you run `cf up autokuma`, it starts the stack on all hosts in parallel. Mul
 Compose Farm includes a `config` subcommand to help manage configuration files:
 
 ```bash
-cf config init              # Create a new config file with documented example
-cf config init --discover   # Auto-detect compose files and interactively create config
-cf config show              # Display current config with syntax highlighting
-cf config path              # Print the config file path (useful for scripting)
-cf config validate          # Validate config syntax and schema
-cf config edit              # Open config in $EDITOR
-cf config example --list    # List available example templates
-cf config example whoami    # Generate sample stack files
-cf config example full      # Generate complete Traefik + whoami setup
+cf config init      # Create a new config file with documented example
+cf config show      # Display current config with syntax highlighting
+cf config path      # Print the config file path (useful for scripting)
+cf config validate  # Validate config syntax and schema
+cf config edit      # Open config in $EDITOR
 ```
 
-Use `cf config init` to get started with a template, or `cf config init --discover` if you already have compose files.
+Use `cf config init` to get started with a fully documented template.
 
 ## Usage
 
@@ -999,7 +1003,6 @@ Full `--help` output for each command. See the [Usage](#usage) table above for a
 │ validate   Validate the config file syntax and schema.                       │
 │ symlink    Create a symlink from the default config location to a config     │
 │            file.                                                             │
-│ example    Generate example stack files from built-in templates.             │
 ╰──────────────────────────────────────────────────────────────────────────────╯
 
 ```
@@ -1323,6 +1326,52 @@ Update your Traefik config to use directory watching instead of a single file:
 - --providers.file.watch=true
 ```
 
+## Host Resource Monitoring (Glances)
+
+The web UI can display real-time CPU, memory, and load stats for all configured hosts. This uses [Glances](https://nicolargo.github.io/glances/), a cross-platform system monitoring tool with a REST API.
+
+**Setup**
+
+1. Deploy a Glances stack that runs on all hosts:
+
+```yaml
+# glances/compose.yaml
+name: glances
+services:
+  glances:
+    image: nicolargo/glances:latest
+    container_name: glances
+    restart: unless-stopped
+    pid: host
+    ports:
+      - "61208:61208"
+    environment:
+      - GLANCES_OPT=-w  # Enable web server mode
+    volumes:
+      - /var/run/docker.sock:/var/run/docker.sock:ro
+```
+
+2. Add it to your config as a multi-host stack:
+
+```yaml
+# compose-farm.yaml
+stacks:
+  glances: all  # Runs on every host
+
+glances_stack: glances  # Enables resource stats in web UI
+```
+
+3. Deploy: `cf up glances`
+
+The web UI dashboard will now show a "Host Resources" section with live stats from all hosts. Hosts where Glances is unreachable show an error indicator.
+
+**Live Stats Page**
+
+With Glances configured, a Live Stats page (`/live-stats`) shows all running containers across all hosts:
+
+- **Columns**: Stack, Service, Host, Image, Status, Uptime, CPU, Memory, Net I/O
+- **Features**: Sorting, filtering, live updates (no SSH required—uses Glances REST API)
+
 ## Comparison with Alternatives
 
 There are many ways to run containers on multiple hosts. Here is where Compose Farm sits:

docker-compose.yml

@@ -6,7 +6,6 @@ services:
     # Defaults to root (0:0) for backwards compatibility
     user: "${CF_UID:-0}:${CF_GID:-0}"
     volumes:
-      - ${SSH_AUTH_SOCK}:/ssh-agent:ro
       # Compose directory (contains compose files AND compose-farm.yaml config)
       - ${CF_COMPOSE_DIR:-/opt/stacks}:${CF_COMPOSE_DIR:-/opt/stacks}
       # SSH keys for passwordless auth (generated by `cf ssh setup`)
@@ -15,6 +14,8 @@ services:
       - ${CF_SSH_DIR:-~/.ssh/compose-farm}:${CF_HOME:-/root}/.ssh/compose-farm
       # Option 2: Named volume - managed by Docker, shared between services
       # - cf-ssh:${CF_HOME:-/root}/.ssh
+      # Option 3: SSH agent forwarding (uncomment if using ssh-agent)
+      # - ${SSH_AUTH_SOCK}:/ssh-agent:ro
     environment:
       - SSH_AUTH_SOCK=/ssh-agent
       # Config file path (state stored alongside it)
@@ -31,13 +32,14 @@ services:
     # Run as current user to preserve file ownership on mounted volumes
     user: "${CF_UID:-0}:${CF_GID:-0}"
     volumes:
-      - ${SSH_AUTH_SOCK}:/ssh-agent:ro
       - ${CF_COMPOSE_DIR:-/opt/stacks}:${CF_COMPOSE_DIR:-/opt/stacks}
       # SSH keys - use the SAME option as cf service above
       # Option 1: Host path (default)
       - ${CF_SSH_DIR:-~/.ssh/compose-farm}:${CF_HOME:-/root}/.ssh/compose-farm
       # Option 2: Named volume
       # - cf-ssh:${CF_HOME:-/root}/.ssh
+      # Option 3: SSH agent forwarding (uncomment if using ssh-agent)
+      # - ${SSH_AUTH_SOCK}:/ssh-agent:ro
       # XDG config dir for backups and image digest logs (persists across restarts)
       - ${CF_XDG_CONFIG:-~/.config/compose-farm}:${CF_HOME:-/root}/.config/compose-farm
     environment:

docs/assets/config-example.gif

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:611d6fef767a8e0755367bf0c008dad016f38fa8b3be2362825ef7ef6ec2ec1a
-size 2444902

docs/assets/config-example.webm

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1e851879acc99234628abce0f8dadeeaf500effe4f78bebc63c4b17a0ae092f1
-size 900800

docs/assets/web-live_stats.gif

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4135888689a10c5ae2904825d98f2a6d215c174a4bd823e25761f619590f04ff
+size 3990104

docs/assets/web-live_stats.webm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87739cd6f6576a81100392d8d1e59d3e776fecc8f0721a31332df89e7fc8593d
+size 5814274

docs/commands.md

@@ -578,10 +578,6 @@ cf traefik-file plex jellyfin -o /opt/traefik/cf.yml
 
 Manage configuration files.
 
-<video autoplay loop muted playsinline>
-  <source src="/assets/config-example.webm" type="video/webm">
-</video>
-
 ```bash
 cf config COMMAND
 ```
@@ -596,19 +592,17 @@ cf config COMMAND
 | `validate` | Validate syntax and schema |
 | `edit` | Open in $EDITOR |
 | `symlink` | Create symlink from default location |
-| `example` | Generate example stack files |
 
 **Options by subcommand:**
 
 | Subcommand | Options |
 |------------|---------|
-| `init` | `--path/-p PATH`, `--force/-f`, `--discover/-d` |
+| `init` | `--path/-p PATH`, `--force/-f` |
 | `show` | `--path/-p PATH`, `--raw/-r` |
 | `edit` | `--path/-p PATH` |
 | `path` | `--path/-p PATH` |
 | `validate` | `--path/-p PATH` |
 | `symlink` | `--force/-f` |
-| `example` | `--list/-l`, `--output/-o PATH`, `--force/-f` |
 
 **Examples:**
 
@@ -616,9 +610,6 @@ cf config COMMAND
 # Create config at default location
 cf config init
 
-# Auto-discover compose files and interactively create config
-cf config init --discover
-
 # Create config at custom path
 cf config init --path /opt/compose-farm/config.yaml
 
@@ -642,18 +633,6 @@ cf config symlink
 
 # Create symlink to specific file
 cf config symlink /opt/compose-farm/config.yaml
-
-# List available example templates
-cf config example --list
-
-# Generate a sample stack (whoami, nginx, postgres)
-cf config example whoami
-
-# Generate complete Traefik + whoami setup
-cf config example full
-
-# Generate example in specific directory
-cf config example nginx --output /opt/compose
 ```
 
 ---

docs/demos/cli/README.md

@@ -27,7 +27,6 @@ python docs/demos/cli/record.py quickstart migration
 | `update.tape` | `cf update` |
 | `migration.tape` | Service migration |
 | `apply.tape` | `cf apply` |
-| `config-example.tape` | `cf config example` - generate example stacks |
 
 ## Output
 

docs/demos/cli/config-example.tape

@@ -1,110 +0,0 @@
-# Config Example Demo
-# Shows cf config example command
-
-Output docs/assets/config-example.gif
-Output docs/assets/config-example.webm
-
-Set Shell "bash"
-Set FontSize 14
-Set Width 900
-Set Height 600
-Set Theme "Catppuccin Mocha"
-Set FontFamily "FiraCode Nerd Font"
-Set TypingSpeed 50ms
-Env BAT_PAGING "always"
-
-Type "# Generate example stacks with cf config example"
-Enter
-Sleep 500ms
-
-Type "# List available templates"
-Enter
-Sleep 500ms
-
-Type "cf config example --list"
-Enter
-Wait+Screen /Usage:/
-Sleep 2s
-
-Type "# Create a directory for our stacks"
-Enter
-Sleep 500ms
-
-Type "mkdir -p ~/compose && cd ~/compose"
-Enter
-Wait
-Sleep 500ms
-
-Type "# Generate the full Traefik + whoami setup"
-Enter
-Sleep 500ms
-
-Type "cf config example full"
-Enter
-Wait
-Sleep 2s
-
-Type "# See what was created"
-Enter
-Sleep 500ms
-
-Type "tree ."
-Enter
-Wait
-Sleep 2s
-
-Type "# View the generated config"
-Enter
-Sleep 500ms
-
-Type "bat compose-farm.yaml"
-Enter
-Sleep 3s
-Type "q"
-Sleep 500ms
-
-Type "# View the traefik compose file"
-Enter
-Sleep 500ms
-
-Type "bat traefik/compose.yaml"
-Enter
-Sleep 3s
-Type "q"
-Sleep 500ms
-
-Type "# Validate the config"
-Enter
-Sleep 500ms
-
-Type "cf check --local"
-Enter
-Wait
-Sleep 2s
-
-Type "# Create the Docker network"
-Enter
-Sleep 500ms
-
-Type "cf init-network"
-Enter
-Wait
-Sleep 1s
-
-Type "# Deploy traefik and whoami"
-Enter
-Sleep 500ms
-
-Type "cf up traefik whoami"
-Enter
-Wait
-Sleep 3s
-
-Type "# Verify it's running"
-Enter
-Sleep 500ms
-
-Type "cf ps"
-Enter
-Wait
-Sleep 2s

docs/demos/web/conftest.py

@@ -21,24 +21,37 @@ import uvicorn
 
 from compose_farm.config import Config as CFConfig
 from compose_farm.config import load_config
+from compose_farm.executor import (
+    get_container_compose_labels as _original_get_compose_labels,
+)
+from compose_farm.glances import ContainerStats
+from compose_farm.glances import fetch_container_stats as _original_fetch_container_stats
 from compose_farm.state import load_state as _original_load_state
-from compose_farm.web.app import create_app
 from compose_farm.web.cdn import CDN_ASSETS, ensure_vendor_cache
 
+# NOTE: Do NOT import create_app here - it must be imported AFTER patches are applied
+# to ensure the patched get_config is used by all route modules
+
 if TYPE_CHECKING:
     from collections.abc import Generator
 
     from playwright.sync_api import BrowserContext, Page, Route
 
-# Stacks to exclude from demo recordings (exact match)
-DEMO_EXCLUDE_STACKS = {"arr"}
+# Substrings to exclude from demo recordings (case-insensitive)
+DEMO_EXCLUDE_PATTERNS = {"arr", "vpn", "tash"}
+
+
+def _should_exclude(name: str) -> bool:
+    """Check if a stack/container name should be excluded from demo."""
+    name_lower = name.lower()
+    return any(pattern in name_lower for pattern in DEMO_EXCLUDE_PATTERNS)
 
 
 def _get_filtered_config() -> CFConfig:
     """Load config but filter out excluded stacks."""
     config = load_config()
     filtered_stacks = {
-        name: host for name, host in config.stacks.items() if name not in DEMO_EXCLUDE_STACKS
+        name: host for name, host in config.stacks.items() if not _should_exclude(name)
     }
     return CFConfig(
         compose_dir=config.compose_dir,
@@ -46,6 +59,7 @@ def _get_filtered_config() -> CFConfig:
         stacks=filtered_stacks,
         traefik_file=config.traefik_file,
         traefik_stack=config.traefik_stack,
+        glances_stack=config.glances_stack,
         config_path=config.config_path,
     )
 
@@ -53,7 +67,37 @@ def _get_filtered_config() -> CFConfig:
 def _get_filtered_state(config: CFConfig) -> dict[str, str | list[str]]:
     """Load state but filter out excluded stacks."""
     state = _original_load_state(config)
-    return {name: host for name, host in state.items() if name not in DEMO_EXCLUDE_STACKS}
+    return {name: host for name, host in state.items() if not _should_exclude(name)}
+
+
+async def _filtered_fetch_container_stats(
+    host_name: str,
+    host_address: str,
+    port: int = 61208,
+    request_timeout: float = 10.0,
+) -> tuple[list[ContainerStats] | None, str | None]:
+    """Fetch container stats but filter out excluded containers."""
+    containers, error = await _original_fetch_container_stats(
+        host_name, host_address, port, request_timeout
+    )
+    if containers:
+        # Filter by container name (stack is empty at this point)
+        containers = [c for c in containers if not _should_exclude(c.name)]
+    return containers, error
+
+
+async def _filtered_get_compose_labels(
+    config: CFConfig,
+    host_name: str,
+) -> dict[str, tuple[str, str]]:
+    """Get compose labels but filter out excluded stacks."""
+    labels = await _original_get_compose_labels(config, host_name)
+    # Filter out containers whose stack (project) name should be excluded
+    return {
+        name: (stack, service)
+        for name, (stack, service) in labels.items()
+        if not _should_exclude(stack)
+    }
 
 
 @pytest.fixture(scope="session")
@@ -84,19 +128,23 @@ def server_url() -> Generator[str, None, None]:
 
     # Patch at source module level so all callers get filtered versions
     patches = [
-        # Patch load_state at source - all functions calling it get filtered state
+        # Patch load_config at source - get_config() calls this internally
+        patch("compose_farm.config.load_config", _get_filtered_config),
+        # Patch load_state at source and where imported
         patch("compose_farm.state.load_state", _get_filtered_state),
-        # Patch get_config where imported
-        patch("compose_farm.web.routes.pages.get_config", _get_filtered_config),
-        patch("compose_farm.web.routes.api.get_config", _get_filtered_config),
-        patch("compose_farm.web.routes.actions.get_config", _get_filtered_config),
-        patch("compose_farm.web.app.get_config", _get_filtered_config),
-        patch("compose_farm.web.ws.get_config", _get_filtered_config),
+        patch("compose_farm.web.routes.pages.load_state", _get_filtered_state),
+        # Patch container fetch to filter out excluded containers (Live Stats page)
+        patch("compose_farm.glances.fetch_container_stats", _filtered_fetch_container_stats),
+        # Patch compose labels to filter out excluded stacks
+        patch("compose_farm.executor.get_container_compose_labels", _filtered_get_compose_labels),
     ]
 
     for p in patches:
         p.start()
 
+    # Import create_app AFTER patches are started so route modules see patched get_config
+    from compose_farm.web.app import create_app  # noqa: PLC0415
+
     with socket.socket() as s:
         s.bind(("127.0.0.1", 0))
         port = s.getsockname()[1]
@@ -160,6 +208,7 @@ def recording_context(
             if url.startswith(url_prefix):
                 route.fulfill(status=200, content_type=content_type, body=filepath.read_bytes())
                 return
+        print(f"UNCACHED CDN request: {url}")
         route.abort("failed")
 
     context.route(re.compile(r"https://(cdn\.jsdelivr\.net|unpkg\.com)/.*"), handle_cdn)
@@ -176,6 +225,35 @@ def recording_page(recording_context: BrowserContext) -> Generator[Page, None, N
     page.close()
 
 
+@pytest.fixture
+def wide_recording_context(
+    browser: Any,  # pytest-playwright's browser fixture
+    recording_output_dir: Path,
+) -> Generator[BrowserContext, None, None]:
+    """Browser context with wider viewport for demos needing more horizontal space.
+
+    NOTE: This fixture does NOT use CDN interception (unlike recording_context).
+    CDN interception was causing inline scripts from containers.html to be
+    removed from the DOM, likely due to Tailwind's browser plugin behavior.
+    """
+    context = browser.new_context(
+        viewport={"width": 1920, "height": 1080},
+        record_video_dir=str(recording_output_dir),
+        record_video_size={"width": 1920, "height": 1080},
+    )
+
+    yield context
+    context.close()
+
+
+@pytest.fixture
+def wide_recording_page(wide_recording_context: BrowserContext) -> Generator[Page, None, None]:
+    """Page with wider viewport for demos needing more horizontal space."""
+    page = wide_recording_context.new_page()
+    yield page
+    page.close()
+
+
 # Demo helper functions
 
 

docs/demos/web/demo_live_stats.py

@@ -0,0 +1,85 @@
+"""Demo: Live Stats page.
+
+Records a ~20 second demo showing:
+- Navigating to Live Stats via command palette
+- Container table with real-time stats
+- Filtering containers
+- Sorting by different columns
+- Auto-refresh countdown
+
+Run: pytest docs/demos/web/demo_live_stats.py -v --no-cov
+"""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import pytest
+from conftest import (
+    open_command_palette,
+    pause,
+    slow_type,
+    wait_for_sidebar,
+)
+
+if TYPE_CHECKING:
+    from playwright.sync_api import Page
+
+
+@pytest.mark.browser  # type: ignore[misc]
+def test_demo_live_stats(wide_recording_page: Page, server_url: str) -> None:
+    """Record Live Stats page demo."""
+    page = wide_recording_page
+
+    # Start on dashboard
+    page.goto(server_url)
+    wait_for_sidebar(page)
+    pause(page, 1000)
+
+    # Navigate to Live Stats via command palette
+    open_command_palette(page)
+    pause(page, 400)
+    slow_type(page, "#cmd-input", "live", delay=100)
+    pause(page, 500)
+    page.keyboard.press("Enter")
+    page.wait_for_url("**/live-stats", timeout=5000)
+
+    # Wait for containers to load (may take ~10s on first load due to SSH)
+    page.wait_for_selector("#container-rows tr:not(:has(.loading))", timeout=30000)
+    pause(page, 2000)  # Let viewer see the full table with timer
+
+    # Demonstrate filtering
+    slow_type(page, "#filter-input", "grocy", delay=100)
+    pause(page, 1500)  # Show filtered results
+
+    # Clear filter
+    page.fill("#filter-input", "")
+    pause(page, 1000)
+
+    # Sort by memory (click header)
+    page.click("th:has-text('Mem')")
+    pause(page, 1500)
+
+    # Sort by CPU
+    page.click("th:has-text('CPU')")
+    pause(page, 1500)
+
+    # Sort by host
+    page.click("th:has-text('Host')")
+    pause(page, 1500)
+
+    # Watch auto-refresh timer count down
+    pause(page, 3500)  # Wait for refresh to happen
+
+    # Hover on action menu to show pause behavior
+    action_btn = page.locator('button[onclick^="openActionMenu"]').first
+    action_btn.scroll_into_view_if_needed()
+    action_btn.hover()
+    pause(page, 2000)  # Show paused state (timer shows ⏸) and action menu
+
+    # Move away to close menu and resume refresh
+    page.locator("h2").first.hover()  # Move to header
+    pause(page, 3500)  # Watch countdown resume and refresh happen
+
+    # Final pause
+    pause(page, 1000)

docs/demos/web/record.py

@@ -37,6 +37,7 @@ DEMOS = [
     "workflow",
     "console",
     "shell",
+    "live_stats",
 ]
 
 # High-quality ffmpeg settings for VP8 encoding

docs/getting-started.md

@@ -149,24 +149,6 @@ cd /opt/stacks
 cf config init
 ```
 
-**Already have compose files?** Use `--discover` to auto-detect them and interactively build your config:
-
-```bash
-cf config init --discover
-```
-
-This scans for directories containing compose files, lets you select which stacks to include, and generates a ready-to-use config.
-
-**Starting fresh?** Generate example stacks to learn from:
-
-```bash
-# List available examples
-cf config example --list
-
-# Generate a complete Traefik + whoami setup
-cf config example full
-```
-
 Alternatively, use `~/.config/compose-farm/compose-farm.yaml` for a global config. You can also symlink a working directory config to the global location:
 
 ```bash

docs/web-ui.md

@@ -51,10 +51,32 @@ Press `Ctrl+K` (or `Cmd+K` on macOS) to open the command palette. Use fuzzy sear
 ### Dashboard (`/`)
 
 - Stack overview with status indicators
-- Host statistics
+- Host statistics (CPU, memory, disk, load via Glances)
 - Pending operations (migrations, orphaned stacks)
 - Quick actions via command palette
 
+### Live Stats (`/live-stats`)
+
+Real-time container monitoring across all hosts, powered by [Glances](https://nicolargo.github.io/glances/).
+
+- **Live metrics**: CPU, memory, network I/O for every container
+- **Auto-refresh**: Updates every 3 seconds (pauses when dropdown menus are open)
+- **Filtering**: Type to filter containers by name, stack, host, or image
+- **Sorting**: Click column headers to sort by any metric
+- **Update detection**: Shows when container images have updates available
+
+<video autoplay loop muted playsinline>
+  <source src="/assets/web-live_stats.webm" type="video/webm">
+</video>
+
+#### Requirements
+
+Live Stats requires Glances to be deployed on all hosts:
+
+1. Add `glances_stack: glances` to your `compose-farm.yaml`
+2. Deploy a Glances stack that runs on all hosts (see [example](https://github.com/basnijholt/compose-farm/tree/main/examples/glances))
+3. Glances must expose its REST API on port 61208
+
 ### Stack Detail (`/stack/{name}`)
 
 - Compose file editor (Monaco)

pyproject.toml

@@ -53,6 +53,7 @@ web = [
     "fastapi[standard]>=0.109.0",
     "jinja2>=3.1.0",
     "websockets>=12.0",
+    "humanize>=4.0.0",
 ]
 
 [project.urls]

src/compose_farm/cli/config.py

@@ -37,12 +37,6 @@ _RawOption = Annotated[
     bool,
     typer.Option("--raw", "-r", help="Output raw file contents (for copy-paste)."),
 ]
-_DiscoverOption = Annotated[
-    bool,
-    typer.Option(
-        "--discover", "-d", help="Auto-detect compose files and interactively select stacks."
-    ),
-]
 
 
 def _get_editor() -> str:
@@ -74,117 +68,6 @@ def _get_config_file(path: Path | None) -> Path | None:
     return config_path.resolve() if config_path else None
 
 
-def _generate_discovered_config(
-    compose_dir: Path,
-    hostname: str,
-    host_address: str,
-    selected_stacks: list[str],
-) -> str:
-    """Generate config YAML from discovered stacks."""
-    import yaml  # noqa: PLC0415
-
-    config_data = {
-        "compose_dir": str(compose_dir),
-        "hosts": {hostname: host_address},
-        "stacks": dict.fromkeys(selected_stacks, hostname),
-    }
-
-    header = """\
-# Compose Farm configuration
-# Documentation: https://github.com/basnijholt/compose-farm
-#
-# Generated by: cf config init --discover
-
-"""
-    return header + yaml.dump(config_data, default_flow_style=False, sort_keys=False)
-
-
-def _interactive_stack_selection(stacks: list[str]) -> list[str]:
-    """Interactively select stacks to include."""
-    from rich.prompt import Confirm, Prompt  # noqa: PLC0415
-
-    console.print("\n[bold]Found stacks:[/bold]")
-    for stack in stacks:
-        console.print(f"  [cyan]{stack}[/cyan]")
-
-    console.print()
-
-    # Fast path: include all
-    if Confirm.ask(f"Include all {len(stacks)} stacks?", default=True):
-        return stacks
-
-    # Let user specify which to exclude
-    console.print(
-        "\n[dim]Enter stack names to exclude (comma-separated), or press Enter to select individually:[/dim]"
-    )
-    exclude_input = Prompt.ask("Exclude", default="")
-
-    if exclude_input.strip():
-        exclude = {s.strip() for s in exclude_input.split(",")}
-        return [s for s in stacks if s not in exclude]
-
-    # Fall back to individual selection
-    console.print()
-    return [
-        stack for stack in stacks if Confirm.ask(f"  Include [cyan]{stack}[/cyan]?", default=True)
-    ]
-
-
-def _run_discovery_flow() -> str | None:
-    """Run the interactive discovery flow and return generated config content."""
-    import socket  # noqa: PLC0415
-
-    from rich.prompt import Prompt  # noqa: PLC0415
-
-    console.print("[bold]Compose Farm Config Discovery[/bold]")
-    console.print("[dim]This will scan for compose files and generate a config.[/dim]\n")
-
-    # Step 1: Get compose directory
-    default_dir = Path.cwd()
-    compose_dir_str = Prompt.ask(
-        "Compose directory",
-        default=str(default_dir),
-    )
-    compose_dir = Path(compose_dir_str).expanduser().resolve()
-
-    if not compose_dir.exists():
-        print_error(f"Directory does not exist: {compose_dir}")
-        return None
-
-    if not compose_dir.is_dir():
-        print_error(f"Path is not a directory: {compose_dir}")
-        return None
-
-    # Step 2: Discover stacks
-    from compose_farm.config import discover_compose_dirs  # noqa: PLC0415
-
-    console.print(f"\n[dim]Scanning {compose_dir}...[/dim]")
-    stacks = discover_compose_dirs(compose_dir)
-
-    if not stacks:
-        print_error(f"No compose files found in {compose_dir}")
-        console.print("[dim]Each stack should be in a subdirectory with a compose.yaml file.[/dim]")
-        return None
-
-    console.print(f"[green]Found {len(stacks)} stack(s)[/green]")
-
-    # Step 3: Interactive selection
-    selected_stacks = _interactive_stack_selection(stacks)
-
-    if not selected_stacks:
-        console.print("\n[yellow]No stacks selected.[/yellow]")
-        return None
-
-    # Step 4: Get hostname and address
-    default_hostname = socket.gethostname()
-    hostname = Prompt.ask("\nHost name", default=default_hostname)
-    host_address = Prompt.ask("Host address", default="localhost")
-
-    # Step 5: Generate config
-    console.print(f"\n[dim]Generating config with {len(selected_stacks)} stack(s)...[/dim]")
-    return _generate_discovered_config(compose_dir, hostname, host_address, selected_stacks)
-
-
 def _report_missing_config(explicit_path: Path | None = None) -> None:
     """Report that a config file was not found."""
     console.print("[yellow]Config file not found.[/yellow]")
@@ -202,15 +85,11 @@ def _report_missing_config(explicit_path: Path | None = None) -> None:
 def config_init(
     path: _PathOption = None,
     force: _ForceOption = False,
-    discover: _DiscoverOption = False,
 ) -> None:
     """Create a new config file with documented example.
 
     The generated config file serves as a template showing all available
     options with explanatory comments.
-
-    Use --discover to auto-detect compose files and interactively select
-    which stacks to include.
     """
     target_path = (path.expanduser().resolve() if path else None) or default_config_path()
 
@@ -222,17 +101,11 @@ def config_init(
             console.print("[dim]Aborted.[/dim]")
             raise typer.Exit(0)
 
-    if discover:
-        template_content = _run_discovery_flow()
-        if template_content is None:
-            raise typer.Exit(0)
-    else:
-        template_content = _generate_template()
-
     # Create parent directories
     target_path.parent.mkdir(parents=True, exist_ok=True)
 
-    # Write config file
+    # Generate and write template
+    template_content = _generate_template()
     target_path.write_text(template_content, encoding="utf-8")
 
     print_success(f"Config file created at: {target_path}")
@@ -420,115 +293,5 @@ def config_symlink(
     console.print(f"    -> {target_path}")
 
 
-_ListOption = Annotated[
-    bool,
-    typer.Option("--list", "-l", help="List available example templates."),
-]
-
-
-@config_app.command("example")
-def config_example(
-    name: Annotated[
-        str | None,
-        typer.Argument(help="Example template name (e.g., whoami, full)"),
-    ] = None,
-    output_dir: Annotated[
-        Path | None,
-        typer.Option("--output", "-o", help="Output directory. Defaults to current directory."),
-    ] = None,
-    list_examples: _ListOption = False,
-    force: _ForceOption = False,
-) -> None:
-    """Generate example stack files from built-in templates.
-
-    Examples:
-        cf config example --list           # List available examples
-        cf config example whoami           # Generate whoami stack in ./whoami/
-        cf config example full             # Generate complete Traefik + whoami setup
-        cf config example nginx -o /opt/compose  # Generate in specific directory
-
-    """
-    from compose_farm.examples import (  # noqa: PLC0415
-        EXAMPLES,
-        SINGLE_STACK_EXAMPLES,
-        list_example_files,
-    )
-
-    # List mode
-    if list_examples:
-        console.print("[bold]Available example templates:[/bold]\n")
-        console.print("[dim]Single stack examples:[/dim]")
-        for example_name, description in SINGLE_STACK_EXAMPLES.items():
-            console.print(f"  [cyan]{example_name}[/cyan] - {description}")
-        console.print()
-        console.print("[dim]Complete setup:[/dim]")
-        console.print(f"  [cyan]full[/cyan] - {EXAMPLES['full']}")
-        console.print()
-        console.print("[dim]Usage: cf config example <name>[/dim]")
-        return
-
-    # Interactive selection if no name provided
-    if name is None:
-        from rich.prompt import Prompt  # noqa: PLC0415
-
-        console.print("[bold]Available example templates:[/bold]\n")
-        example_names = list(EXAMPLES.keys())
-        for i, (example_name, description) in enumerate(EXAMPLES.items(), 1):
-            console.print(f"  [{i}] [cyan]{example_name}[/cyan] - {description}")
-
-        console.print()
-        choice = Prompt.ask(
-            "Select example",
-            choices=[str(i) for i in range(1, len(example_names) + 1)] + example_names,
-            default="1",
-        )
-
-        # Handle numeric or name input
-        name = example_names[int(choice) - 1] if choice.isdigit() else choice
-
-    # Validate example name
-    if name not in EXAMPLES:
-        print_error(f"Unknown example: {name}")
-        console.print(f"Available examples: {', '.join(EXAMPLES.keys())}")
-        raise typer.Exit(1)
-
-    # Determine output directory
-    base_dir = (output_dir or Path.cwd()).expanduser().resolve()
-    # For 'full' example, use current dir; for single stacks, create subdir
-    target_dir = base_dir if name == "full" else base_dir / name
-
-    # Check for existing files
-    files = list_example_files(name)
-    existing_files = [f for f, _ in files if (target_dir / f).exists()]
-    if existing_files and not force:
-        console.print(f"[yellow]Files already exist in:[/yellow] {target_dir}")
-        console.print(f"[dim]  {len(existing_files)} file(s) would be overwritten[/dim]")
-        if not typer.confirm("Overwrite existing files?"):
-            console.print("[dim]Aborted.[/dim]")
-            raise typer.Exit(0)
-
-    # Create directories and copy files
-    for rel_path, content in files:
-        file_path = target_dir / rel_path
-        file_path.parent.mkdir(parents=True, exist_ok=True)
-        file_path.write_text(content, encoding="utf-8")
-        console.print(f"  [green]Created[/green] {file_path}")
-
-    print_success(f"Example '{name}' created at: {target_dir}")
-
-    # Show appropriate next steps
-    if name == "full":
-        console.print("\n[dim]Next steps:[/dim]")
-        console.print(f"  1. Edit [cyan]{target_dir}/compose-farm.yaml[/cyan] with your host IP")
-        console.print("  2. Edit [cyan].env[/cyan] files with your domain")
-        console.print("  3. Create Docker network: [cyan]docker network create mynetwork[/cyan]")
-        console.print("  4. Deploy: [cyan]cf up traefik whoami[/cyan]")
-    else:
-        console.print("\n[dim]Next steps:[/dim]")
-        console.print(f"  1. Edit [cyan]{target_dir}/.env[/cyan] with your settings")
-        console.print(f"  2. Add to compose-farm.yaml: [cyan]{name}: <hostname>[/cyan]")
-        console.print(f"  3. Deploy with: [cyan]cf up {name}[/cyan]")
-
-
 # Register config subcommand on the shared app
 app.add_typer(config_app, name="config", rich_help_panel="Configuration")

src/compose_farm/cli/management.py

@@ -37,24 +37,23 @@ from compose_farm.console import (
 )
 from compose_farm.executor import (
     CommandResult,
+    get_running_stacks_on_host,
     is_local,
     run_command,
 )
 from compose_farm.logs import (
     DEFAULT_LOG_PATH,
     SnapshotEntry,
-    collect_stack_entries,
+    collect_stacks_entries_on_host,
     isoformat,
     load_existing_entries,
     merge_entries,
     write_toml,
 )
 from compose_farm.operations import (
-    StackDiscoveryResult,
+    build_discovery_results,
     check_host_compatibility,
     check_stack_requirements,
-    discover_stack_host,
-    discover_stack_on_all_hosts,
 )
 from compose_farm.state import get_orphaned_stacks, load_state, save_state
 from compose_farm.traefik import generate_traefik_config, render_traefik_config
@@ -62,38 +61,39 @@ from compose_farm.traefik import generate_traefik_config, render_traefik_config
 # --- Sync helpers ---
 
 
-def _discover_stacks(cfg: Config, stacks: list[str] | None = None) -> dict[str, str | list[str]]:
-    """Discover running stacks with a progress bar."""
-    stack_list = stacks if stacks is not None else list(cfg.stacks)
-    results = run_parallel_with_progress(
-        "Discovering",
-        stack_list,
-        lambda s: discover_stack_host(cfg, s),
-    )
-    return {svc: host for svc, host in results if host is not None}
-
-
 def _snapshot_stacks(
     cfg: Config,
-    stacks: list[str],
+    discovered: dict[str, str | list[str]],
     log_path: Path | None,
 ) -> Path:
-    """Capture image digests with a progress bar."""
+    """Capture image digests using batched SSH calls (1 per host).
+
+    Args:
+        cfg: Configuration
+        discovered: Dict mapping stack -> host(s) where it's running
+        log_path: Optional path to write the log file
+
+    Returns:
+        Path to the written log file.
+
+    """
     effective_log_path = log_path or DEFAULT_LOG_PATH
     now_dt = datetime.now(UTC)
     now_iso = isoformat(now_dt)
 
-    async def collect_stack(stack: str) -> tuple[str, list[SnapshotEntry]]:
-        try:
-            return stack, await collect_stack_entries(cfg, stack, now=now_dt)
-        except RuntimeError:
-            return stack, []
+    # Group stacks by host for batched SSH calls
+    stacks_by_host: dict[str, set[str]] = {}
+    for stack, hosts in discovered.items():
+        # Use first host for multi-host stacks (they use the same images)
+        host = hosts[0] if isinstance(hosts, list) else hosts
+        stacks_by_host.setdefault(host, set()).add(stack)
 
-    results = run_parallel_with_progress(
-        "Capturing",
-        stacks,
-        collect_stack,
-    )
+    # Collect entries with 1 SSH call per host (with progress bar)
+    async def collect_on_host(host: str) -> tuple[str, list[SnapshotEntry]]:
+        entries = await collect_stacks_entries_on_host(cfg, host, stacks_by_host[host], now=now_dt)
+        return host, entries
+
+    results = run_parallel_with_progress("Capturing", list(stacks_by_host.keys()), collect_on_host)
     snapshot_entries = [entry for _, entries in results for entry in entries]
 
     if not snapshot_entries:
@@ -155,39 +155,20 @@ def _discover_stacks_full(
 ) -> tuple[dict[str, str | list[str]], dict[str, list[str]], dict[str, list[str]]]:
     """Discover running stacks with full host scanning for stray detection.
 
-    Returns:
-        Tuple of (discovered, strays, duplicates):
-        - discovered: stack -> host(s) where running correctly
-        - strays: stack -> list of unauthorized hosts
-        - duplicates: stack -> list of all hosts (for single-host stacks on multiple)
-
+    Queries each host once for all running stacks (with progress bar),
+    then delegates to build_discovery_results for categorization.
     """
-    stack_list = stacks if stacks is not None else list(cfg.stacks)
-    results: list[StackDiscoveryResult] = run_parallel_with_progress(
-        "Discovering",
-        stack_list,
-        lambda s: discover_stack_on_all_hosts(cfg, s),
-    )
+    all_hosts = list(cfg.hosts.keys())
 
-    discovered: dict[str, str | list[str]] = {}
-    strays: dict[str, list[str]] = {}
-    duplicates: dict[str, list[str]] = {}
+    # Query each host for running stacks (with progress bar)
+    async def get_stacks_on_host(host: str) -> tuple[str, set[str]]:
+        running = await get_running_stacks_on_host(cfg, host)
+        return host, running
 
-    for result in results:
-        correct_hosts = [h for h in result.running_hosts if h in result.configured_hosts]
-        if correct_hosts:
-            if result.is_multi_host:
-                discovered[result.stack] = correct_hosts
-            else:
-                discovered[result.stack] = correct_hosts[0]
+    host_results = run_parallel_with_progress("Discovering", all_hosts, get_stacks_on_host)
+    running_on_host: dict[str, set[str]] = dict(host_results)
 
-        if result.is_stray:
-            strays[result.stack] = result.stray_hosts
-
-        if result.is_duplicate:
-            duplicates[result.stack] = result.running_hosts
-
-    return discovered, strays, duplicates
+    return build_discovery_results(cfg, running_on_host, stacks)
 
 
 def _report_stray_stacks(
@@ -554,10 +535,10 @@ def refresh(
         save_state(cfg, new_state)
         print_success(f"State updated: {len(new_state)} stacks tracked.")
 
-    # Capture image digests for running stacks
+    # Capture image digests for running stacks (1 SSH call per host)
     if discovered:
         try:
-            path = _snapshot_stacks(cfg, list(discovered.keys()), log_path)
+            path = _snapshot_stacks(cfg, discovered, log_path)
             print_success(f"Digests written to {path}")
         except RuntimeError as exc:
             print_warning(str(exc))

src/compose_farm/config.py

@@ -15,17 +15,6 @@ from .paths import config_search_paths, find_config_path
 COMPOSE_FILENAMES = ("compose.yaml", "compose.yml", "docker-compose.yml", "docker-compose.yaml")
 
 
-def discover_compose_dirs(compose_dir: Path) -> list[str]:
-    """Find all directories in compose_dir that contain a compose file."""
-    if not compose_dir.exists():
-        return []
-    return sorted(
-        subdir.name
-        for subdir in compose_dir.iterdir()
-        if subdir.is_dir() and any((subdir / f).exists() for f in COMPOSE_FILENAMES)
-    )
-
-
 class Host(BaseModel, extra="forbid"):
     """SSH host configuration."""
 
@@ -42,6 +31,9 @@ class Config(BaseModel, extra="forbid"):
     stacks: dict[str, str | list[str]]  # stack_name -> host_name or list of hosts
     traefik_file: Path | None = None  # Auto-regenerate traefik config after up/down
     traefik_stack: str | None = None  # Stack name for Traefik (skip its host in file-provider)
+    glances_stack: str | None = (
+        None  # Stack name for Glances (enables host resource stats in web UI)
+    )
     config_path: Path = Path()  # Set by load_config()
 
     def get_state_path(self) -> Path:
@@ -116,7 +108,13 @@ class Config(BaseModel, extra="forbid"):
 
     def discover_compose_dirs(self) -> set[str]:
         """Find all directories in compose_dir that contain a compose file."""
-        return set(discover_compose_dirs(self.compose_dir))
+        found: set[str] = set()
+        if not self.compose_dir.exists():
+            return found
+        for subdir in self.compose_dir.iterdir():
+            if subdir.is_dir() and any((subdir / f).exists() for f in COMPOSE_FILENAMES):
+                found.add(subdir.name)
+        return found
 
 
 def _parse_hosts(raw_hosts: dict[str, Any]) -> dict[str, Host]:

src/compose_farm/examples/__init__.py

@@ -1,41 +0,0 @@
-"""Example stack templates for compose-farm."""
-
-from __future__ import annotations
-
-from importlib import resources
-from pathlib import Path
-
-# All available examples: name -> description
-# "full" is special: multi-stack setup with config file
-EXAMPLES = {
-    "whoami": "Simple HTTP service that returns hostname (great for testing Traefik)",
-    "nginx": "Basic nginx web server with static files",
-    "postgres": "PostgreSQL database with persistent volume",
-    "full": "Complete setup with Traefik + whoami (includes compose-farm.yaml)",
-}
-
-# Examples that are single stacks (everything except "full")
-SINGLE_STACK_EXAMPLES = {k: v for k, v in EXAMPLES.items() if k != "full"}
-
-
-def list_example_files(name: str) -> list[tuple[str, str]]:
-    """List files in an example template, returning (relative_path, content) tuples."""
-    if name not in EXAMPLES:
-        msg = f"Unknown example: {name}. Available: {', '.join(EXAMPLES.keys())}"
-        raise ValueError(msg)
-
-    example_dir = resources.files("compose_farm.examples") / name
-    example_path = Path(str(example_dir))
-    files: list[tuple[str, str]] = []
-
-    def walk_dir(directory: Path, prefix: str = "") -> None:
-        for item in sorted(directory.iterdir()):
-            rel_path = f"{prefix}{item.name}" if prefix else item.name
-            if item.is_file():
-                content = item.read_text(encoding="utf-8")
-                files.append((rel_path, content))
-            elif item.is_dir() and not item.name.startswith("__"):
-                walk_dir(item, f"{rel_path}/")
-
-    walk_dir(example_path)
-    return files

src/compose_farm/examples/full/README.md

@@ -1,41 +0,0 @@
-# Compose Farm Full Example
-
-A complete starter setup with Traefik reverse proxy and a test service.
-
-## Quick Start
-
-1. **Create the Docker network** (once per host):
-   ```bash
-   docker network create --subnet=172.20.0.0/16 --gateway=172.20.0.1 mynetwork
-   ```
-
-2. **Create data directory for Traefik**:
-   ```bash
-   mkdir -p /mnt/data/traefik
-   ```
-
-3. **Edit configuration**:
-   - Update `compose-farm.yaml` with your host IP
-   - Update `.env` files with your domain
-
-4. **Start the stacks**:
-   ```bash
-   cf up traefik whoami
-   ```
-
-5. **Test**:
-   - Dashboard: http://localhost:8080
-   - Whoami: Add `whoami.example.com` to /etc/hosts pointing to your host
-
-## Files
-
-```
-full/
-├── compose-farm.yaml    # Compose Farm config
-├── traefik/
-│   ├── compose.yaml     # Traefik reverse proxy
-│   └── .env
-└── whoami/
-    ├── compose.yaml     # Test HTTP service
-    └── .env
-```

src/compose_farm/examples/full/compose-farm.yaml

@@ -1,17 +0,0 @@
-# Compose Farm configuration
-# Edit the host address to match your setup
-
-compose_dir: .
-
-hosts:
-  local: localhost  # For remote hosts, use: myhost: 192.168.1.100
-
-stacks:
-  traefik: local
-  whoami: local
-  nginx: local
-  postgres: local
-
-# Traefik file-provider integration (optional)
-# traefik_file: ./traefik/dynamic.d/compose-farm.yml
-traefik_stack: traefik

src/compose_farm/examples/full/nginx/.env

@@ -1,2 +0,0 @@
-# Environment variables for nginx stack
-DOMAIN=example.com

src/compose_farm/examples/full/nginx/compose.yaml

@@ -1,26 +0,0 @@
-# Nginx - Basic web server
-services:
-  nginx:
-    image: nginx:alpine
-    container_name: cf-nginx
-    user: "1000:1000"
-    networks:
-      - mynetwork
-    volumes:
-      - /mnt/data/nginx/html:/usr/share/nginx/html:ro
-    ports:
-      - "9082:80"  # Use 80:80 or 8080:80 in production
-    restart: unless-stopped
-    labels:
-      - traefik.enable=true
-      - traefik.http.routers.nginx.rule=Host(`nginx.${DOMAIN}`)
-      - traefik.http.routers.nginx.entrypoints=websecure
-      - traefik.http.routers.nginx-local.rule=Host(`nginx.local`)
-      - traefik.http.routers.nginx-local.entrypoints=web
-      - traefik.http.services.nginx.loadbalancer.server.port=80
-      - kuma.nginx.http.name=Nginx
-      - kuma.nginx.http.url=https://nginx.${DOMAIN}
-
-networks:
-  mynetwork:
-    external: true

src/compose_farm/examples/full/postgres/.env

@@ -1,5 +0,0 @@
-# Environment variables for postgres stack
-# IMPORTANT: Change these values before deploying!
-POSTGRES_USER=postgres
-POSTGRES_PASSWORD=changeme
-POSTGRES_DB=myapp

src/compose_farm/examples/full/postgres/compose.yaml

@@ -1,26 +0,0 @@
-# PostgreSQL - Database with persistent storage
-services:
-  postgres:
-    image: postgres:16-alpine
-    container_name: cf-postgres
-    networks:
-      - mynetwork
-    environment:
-      - POSTGRES_USER=${POSTGRES_USER:-postgres}
-      - POSTGRES_PASSWORD=${POSTGRES_PASSWORD:?POSTGRES_PASSWORD is required}
-      - POSTGRES_DB=${POSTGRES_DB:-postgres}
-      - PGDATA=/var/lib/postgresql/data/pgdata
-    volumes:
-      - /mnt/data/postgres:/var/lib/postgresql/data
-    ports:
-      - "5433:5432"  # Use 5432:5432 in production
-    restart: unless-stopped
-    healthcheck:
-      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-postgres}"]
-      interval: 30s
-      timeout: 10s
-      retries: 3
-
-networks:
-  mynetwork:
-    external: true

src/compose_farm/examples/full/traefik/.env

@@ -1 +0,0 @@
-DOMAIN=example.com

src/compose_farm/examples/full/traefik/compose.yaml

@@ -1,37 +0,0 @@
-# Traefik - Reverse proxy and load balancer
-services:
-  traefik:
-    image: traefik:v2.11
-    container_name: cf-traefik
-    networks:
-      - mynetwork
-    ports:
-      - "9080:80"    # HTTP (use 80:80 in production)
-      - "9443:443"   # HTTPS (use 443:443 in production)
-      - "9081:8080"  # Dashboard - remove in production
-    volumes:
-      - /var/run/docker.sock:/var/run/docker.sock:ro
-      - /mnt/data/traefik:/etc/traefik
-    command:
-      - --api.dashboard=true
-      - --api.insecure=true
-      - --providers.docker=true
-      - --providers.docker.exposedbydefault=false
-      - --providers.docker.network=mynetwork
-      - --entrypoints.web.address=:80
-      - --entrypoints.websecure.address=:443
-      - --log.level=INFO
-    labels:
-      - traefik.enable=true
-      - traefik.http.routers.traefik.rule=Host(`traefik.${DOMAIN}`)
-      - traefik.http.routers.traefik.entrypoints=websecure
-      - traefik.http.routers.traefik-local.rule=Host(`traefik.local`)
-      - traefik.http.routers.traefik-local.entrypoints=web
-      - traefik.http.services.traefik.loadbalancer.server.port=8080
-      - kuma.traefik.http.name=Traefik
-      - kuma.traefik.http.url=https://traefik.${DOMAIN}
-    restart: unless-stopped
-
-networks:
-  mynetwork:
-    external: true

src/compose_farm/examples/full/whoami/.env

@@ -1 +0,0 @@
-DOMAIN=example.com

src/compose_farm/examples/full/whoami/compose.yaml

@@ -1,23 +0,0 @@
-# Whoami - Test service for Traefik routing
-services:
-  whoami:
-    image: traefik/whoami:latest
-    container_name: cf-whoami
-    networks:
-      - mynetwork
-    ports:
-      - "9000:80"
-    restart: unless-stopped
-    labels:
-      - traefik.enable=true
-      - traefik.http.routers.whoami.rule=Host(`whoami.${DOMAIN}`)
-      - traefik.http.routers.whoami.entrypoints=websecure
-      - traefik.http.routers.whoami-local.rule=Host(`whoami.local`)
-      - traefik.http.routers.whoami-local.entrypoints=web
-      - traefik.http.services.whoami.loadbalancer.server.port=80
-      - kuma.whoami.http.name=Whoami
-      - kuma.whoami.http.url=https://whoami.${DOMAIN}
-
-networks:
-  mynetwork:
-    external: true

src/compose_farm/examples/nginx/.env

@@ -1,2 +0,0 @@
-# Environment variables for nginx stack
-DOMAIN=example.com

src/compose_farm/examples/nginx/compose.yaml

@@ -1,26 +0,0 @@
-# Nginx - Basic web server
-services:
-  nginx:
-    image: nginx:alpine
-    container_name: cf-nginx
-    user: "1000:1000"
-    networks:
-      - mynetwork
-    volumes:
-      - /mnt/data/nginx/html:/usr/share/nginx/html:ro
-    ports:
-      - "9082:80"
-    restart: unless-stopped
-    labels:
-      - traefik.enable=true
-      - traefik.http.routers.nginx.rule=Host(`nginx.${DOMAIN}`)
-      - traefik.http.routers.nginx.entrypoints=websecure
-      - traefik.http.routers.nginx-local.rule=Host(`nginx.local`)
-      - traefik.http.routers.nginx-local.entrypoints=web
-      - traefik.http.services.nginx.loadbalancer.server.port=80
-      - kuma.nginx.http.name=Nginx
-      - kuma.nginx.http.url=https://nginx.${DOMAIN}
-
-networks:
-  mynetwork:
-    external: true

src/compose_farm/examples/postgres/.env

@@ -1,5 +0,0 @@
-# Environment variables for postgres stack
-# IMPORTANT: Change these values before deploying!
-POSTGRES_USER=postgres
-POSTGRES_PASSWORD=changeme
-POSTGRES_DB=myapp

src/compose_farm/examples/postgres/compose.yaml

@@ -1,26 +0,0 @@
-# PostgreSQL - Database with persistent storage
-services:
-  postgres:
-    image: postgres:16-alpine
-    container_name: cf-postgres
-    networks:
-      - mynetwork
-    environment:
-      - POSTGRES_USER=${POSTGRES_USER:-postgres}
-      - POSTGRES_PASSWORD=${POSTGRES_PASSWORD:?POSTGRES_PASSWORD is required}
-      - POSTGRES_DB=${POSTGRES_DB:-postgres}
-      - PGDATA=/var/lib/postgresql/data/pgdata
-    volumes:
-      - /mnt/data/postgres:/var/lib/postgresql/data
-    ports:
-      - "5433:5432"
-    restart: unless-stopped
-    healthcheck:
-      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-postgres}"]
-      interval: 30s
-      timeout: 10s
-      retries: 3
-
-networks:
-  mynetwork:
-    external: true

src/compose_farm/examples/whoami/.env

@@ -1,2 +0,0 @@
-# Environment variables for whoami stack
-DOMAIN=example.com

src/compose_farm/examples/whoami/compose.yaml

@@ -1,24 +0,0 @@
-# Whoami - Simple HTTP service for testing
-# Returns the container hostname - useful for testing load balancers and Traefik
-services:
-  whoami:
-    image: traefik/whoami:latest
-    container_name: cf-whoami
-    networks:
-      - mynetwork
-    ports:
-      - "9000:80"
-    restart: unless-stopped
-    labels:
-      - traefik.enable=true
-      - traefik.http.routers.whoami.rule=Host(`whoami.${DOMAIN}`)
-      - traefik.http.routers.whoami.entrypoints=websecure
-      - traefik.http.routers.whoami-local.rule=Host(`whoami.local`)
-      - traefik.http.routers.whoami-local.entrypoints=web
-      - traefik.http.services.whoami.loadbalancer.server.port=80
-      - kuma.whoami.http.name=Whoami
-      - kuma.whoami.http.url=https://whoami.${DOMAIN}
-
-networks:
-  mynetwork:
-    external: true

src/compose_farm/executor.py

@@ -5,6 +5,7 @@ from __future__ import annotations
 import asyncio
 import socket
 import subprocess
+import time
 from dataclasses import dataclass
 from functools import lru_cache
 from typing import TYPE_CHECKING, Any
@@ -23,6 +24,38 @@ LOCAL_ADDRESSES = frozenset({"local", "localhost", "127.0.0.1", "::1"})
 _DEFAULT_SSH_PORT = 22
 
 
+class TTLCache:
+    """Simple TTL cache for async function results."""
+
+    def __init__(self, ttl_seconds: float = 30.0) -> None:
+        """Initialize cache with default TTL in seconds."""
+        # Cache stores: key -> (timestamp, value, item_ttl)
+        self._cache: dict[str, tuple[float, Any, float]] = {}
+        self._default_ttl = ttl_seconds
+
+    def get(self, key: str) -> Any | None:
+        """Get value if exists and not expired."""
+        if key in self._cache:
+            timestamp, value, item_ttl = self._cache[key]
+            if time.monotonic() - timestamp < item_ttl:
+                return value
+            del self._cache[key]
+        return None
+
+    def set(self, key: str, value: Any, ttl_seconds: float | None = None) -> None:
+        """Set value with current timestamp and optional custom TTL."""
+        ttl = ttl_seconds if ttl_seconds is not None else self._default_ttl
+        self._cache[key] = (time.monotonic(), value, ttl)
+
+    def clear(self) -> None:
+        """Clear all cached values."""
+        self._cache.clear()
+
+
+# Cache compose labels per host for 30 seconds
+_compose_labels_cache = TTLCache(ttl_seconds=30.0)
+
+
 def _print_compose_command(
     host_name: str,
     compose_dir: str,
@@ -158,15 +191,20 @@ def ssh_connect_kwargs(host: Host) -> dict[str, Any]:
         "port": host.port,
         "username": host.user,
         "known_hosts": None,
+        "gss_auth": False,  # Disable GSSAPI - causes multi-second delays
     }
-    # Add SSH agent path (auto-detect forwarded agent if needed)
-    agent_path = get_ssh_auth_sock()
-    if agent_path:
-        kwargs["agent_path"] = agent_path
-    # Add key file fallback for when SSH agent is unavailable
+    # Add key file fallback (prioritized over agent if present)
     key_path = get_key_path()
+    agent_path = get_ssh_auth_sock()
+
     if key_path:
+        # If dedicated key exists, force use of it and ignore agent
+        # This avoids issues with stale/broken forwarded agents in Docker
         kwargs["client_keys"] = [str(key_path)]
+    elif agent_path:
+        # Fallback to agent if no dedicated key
+        kwargs["agent_path"] = agent_path
+
     return kwargs
 
 
@@ -497,6 +535,72 @@ async def check_stack_running(
     return result.success and bool(result.stdout.strip())
 
 
+async def get_running_stacks_on_host(
+    config: Config,
+    host_name: str,
+) -> set[str]:
+    """Get all running compose stacks on a host in a single SSH call.
+
+    Uses docker ps with the compose.project label to identify running stacks.
+    Much more efficient than checking each stack individually.
+    """
+    host = config.hosts[host_name]
+
+    # Get unique project names from running containers
+    command = "docker ps --format '{{.Label \"com.docker.compose.project\"}}' | sort -u"
+    result = await run_command(host, command, stack=host_name, stream=False, prefix="")
+
+    if not result.success:
+        return set()
+
+    # Filter out empty lines and return as set
+    return {line.strip() for line in result.stdout.splitlines() if line.strip()}
+
+
+async def get_container_compose_labels(
+    config: Config,
+    host_name: str,
+) -> dict[str, tuple[str, str]]:
+    """Get compose labels for all containers on a host.
+
+    Returns dict of container_name -> (project, service).
+    Includes all containers (-a flag) since Glances shows stopped containers too.
+    Falls back to empty dict on timeout/error (5s timeout).
+    Results are cached for 30 seconds to reduce SSH overhead.
+    """
+    # Check cache first
+    cached: dict[str, tuple[str, str]] | None = _compose_labels_cache.get(host_name)
+    if cached is not None:
+        return cached
+
+    host = config.hosts[host_name]
+    cmd = (
+        "docker ps -a --format "
+        '\'{{.Names}}\t{{.Label "com.docker.compose.project"}}\t'
+        '{{.Label "com.docker.compose.service"}}\''
+    )
+
+    try:
+        async with asyncio.timeout(5.0):
+            result = await run_command(host, cmd, stack=host_name, stream=False, prefix="")
+    except TimeoutError:
+        return {}
+    except Exception:
+        return {}
+
+    labels: dict[str, tuple[str, str]] = {}
+    if result.success:
+        for line in result.stdout.splitlines():
+            parts = line.strip().split("\t")
+            if len(parts) >= 3:  # noqa: PLR2004
+                name, project, service = parts[0], parts[1], parts[2]
+                labels[name] = (project or "", service or "")
+
+    # Cache the result
+    _compose_labels_cache.set(host_name, labels)
+    return labels
+
+
 async def _batch_check_existence(
     config: Config,
     host_name: str,

src/compose_farm/glances.py

@@ -0,0 +1,236 @@
+"""Glances API client for host resource monitoring."""
+
+from __future__ import annotations
+
+import asyncio
+from dataclasses import dataclass
+from typing import TYPE_CHECKING, Any
+
+if TYPE_CHECKING:
+    from .config import Config
+
+# Default Glances REST API port
+DEFAULT_GLANCES_PORT = 61208
+
+
+@dataclass
+class HostStats:
+    """Resource statistics for a host."""
+
+    host: str
+    cpu_percent: float
+    mem_percent: float
+    swap_percent: float
+    load: float
+    disk_percent: float
+    net_rx_rate: float = 0.0  # bytes/sec
+    net_tx_rate: float = 0.0  # bytes/sec
+    error: str | None = None
+
+    @classmethod
+    def from_error(cls, host: str, error: str) -> HostStats:
+        """Create a HostStats with an error."""
+        return cls(
+            host=host,
+            cpu_percent=0,
+            mem_percent=0,
+            swap_percent=0,
+            load=0,
+            disk_percent=0,
+            net_rx_rate=0,
+            net_tx_rate=0,
+            error=error,
+        )
+
+
+async def fetch_host_stats(
+    host_name: str,
+    host_address: str,
+    port: int = DEFAULT_GLANCES_PORT,
+    request_timeout: float = 10.0,
+) -> HostStats:
+    """Fetch stats from a single host's Glances API."""
+    import httpx  # noqa: PLC0415
+
+    base_url = f"http://{host_address}:{port}/api/4"
+
+    try:
+        async with httpx.AsyncClient(timeout=request_timeout) as client:
+            # Fetch quicklook stats (CPU, mem, load)
+            response = await client.get(f"{base_url}/quicklook")
+            if not response.is_success:
+                return HostStats.from_error(host_name, f"HTTP {response.status_code}")
+            data = response.json()
+
+            # Fetch filesystem stats for disk usage (root fs or max across all)
+            disk_percent = 0.0
+            try:
+                fs_response = await client.get(f"{base_url}/fs")
+                if fs_response.is_success:
+                    fs_data = fs_response.json()
+                    root = next((fs for fs in fs_data if fs.get("mnt_point") == "/"), None)
+                    disk_percent = (
+                        root.get("percent", 0)
+                        if root
+                        else max((fs.get("percent", 0) for fs in fs_data), default=0)
+                    )
+            except httpx.HTTPError:
+                pass  # Disk stats are optional
+
+            # Fetch network stats for rate (sum across non-loopback interfaces)
+            net_rx_rate, net_tx_rate = 0.0, 0.0
+            try:
+                net_response = await client.get(f"{base_url}/network")
+                if net_response.is_success:
+                    for iface in net_response.json():
+                        if not iface.get("interface_name", "").startswith("lo"):
+                            net_rx_rate += iface.get("bytes_recv_rate_per_sec") or 0
+                            net_tx_rate += iface.get("bytes_sent_rate_per_sec") or 0
+            except httpx.HTTPError:
+                pass  # Network stats are optional
+
+            return HostStats(
+                host=host_name,
+                cpu_percent=data.get("cpu", 0),
+                mem_percent=data.get("mem", 0),
+                swap_percent=data.get("swap", 0),
+                load=data.get("load", 0),
+                disk_percent=disk_percent,
+                net_rx_rate=net_rx_rate,
+                net_tx_rate=net_tx_rate,
+            )
+    except httpx.TimeoutException:
+        return HostStats.from_error(host_name, "timeout")
+    except httpx.HTTPError as e:
+        return HostStats.from_error(host_name, str(e))
+    except Exception as e:
+        return HostStats.from_error(host_name, str(e))
+
+
+async def fetch_all_host_stats(
+    config: Config,
+    port: int = DEFAULT_GLANCES_PORT,
+) -> dict[str, HostStats]:
+    """Fetch stats from all hosts in parallel."""
+    tasks = [fetch_host_stats(name, host.address, port) for name, host in config.hosts.items()]
+    results = await asyncio.gather(*tasks)
+    return {stats.host: stats for stats in results}
+
+
+@dataclass
+class ContainerStats:
+    """Container statistics from Glances."""
+
+    name: str
+    host: str
+    status: str
+    image: str
+    cpu_percent: float
+    memory_usage: int  # bytes
+    memory_limit: int  # bytes
+    memory_percent: float
+    network_rx: int  # cumulative bytes received
+    network_tx: int  # cumulative bytes sent
+    uptime: str
+    ports: str
+    engine: str  # docker, podman, etc.
+    stack: str = ""  # compose project name (from docker labels)
+    service: str = ""  # compose service name (from docker labels)
+
+
+def _parse_container(data: dict[str, Any], host_name: str) -> ContainerStats:
+    """Parse container data from Glances API response."""
+    # Image can be a list or string
+    image = data.get("image", ["unknown"])
+    if isinstance(image, list):
+        image = image[0] if image else "unknown"
+
+    # Calculate memory percent
+    mem_usage = data.get("memory_usage", 0) or 0
+    mem_limit = data.get("memory_limit", 1) or 1  # Avoid division by zero
+    mem_percent = (mem_usage / mem_limit) * 100 if mem_limit > 0 else 0
+
+    # Network stats
+    network = data.get("network", {}) or {}
+    network_rx = network.get("cumulative_rx", 0) or 0
+    network_tx = network.get("cumulative_tx", 0) or 0
+
+    return ContainerStats(
+        name=data.get("name", "unknown"),
+        host=host_name,
+        status=data.get("status", "unknown"),
+        image=image,
+        cpu_percent=data.get("cpu_percent", 0) or 0,
+        memory_usage=mem_usage,
+        memory_limit=mem_limit,
+        memory_percent=mem_percent,
+        network_rx=network_rx,
+        network_tx=network_tx,
+        uptime=data.get("uptime", ""),
+        ports=data.get("ports", "") or "",
+        engine=data.get("engine", "docker"),
+    )
+
+
+async def fetch_container_stats(
+    host_name: str,
+    host_address: str,
+    port: int = DEFAULT_GLANCES_PORT,
+    request_timeout: float = 10.0,
+) -> tuple[list[ContainerStats] | None, str | None]:
+    """Fetch container stats from a single host's Glances API.
+
+    Returns:
+        (containers, error_message)
+        - Success: ([...], None)
+        - Failure: (None, "error message")
+
+    """
+    import httpx  # noqa: PLC0415
+
+    url = f"http://{host_address}:{port}/api/4/containers"
+
+    try:
+        async with httpx.AsyncClient(timeout=request_timeout) as client:
+            response = await client.get(url)
+            if not response.is_success:
+                return None, f"HTTP {response.status_code}: {response.reason_phrase}"
+            data = response.json()
+            return [_parse_container(c, host_name) for c in data], None
+    except httpx.ConnectError:
+        return None, "Connection refused (Glances offline?)"
+    except httpx.TimeoutException:
+        return None, "Connection timed out"
+    except Exception as e:
+        return None, str(e)
+
+
+async def fetch_all_container_stats(
+    config: Config,
+    port: int = DEFAULT_GLANCES_PORT,
+) -> list[ContainerStats]:
+    """Fetch container stats from all hosts in parallel, enriched with compose labels."""
+    from .executor import get_container_compose_labels  # noqa: PLC0415
+
+    async def fetch_host_data(
+        host_name: str,
+        host_address: str,
+    ) -> list[ContainerStats]:
+        # Fetch Glances stats and compose labels in parallel
+        stats_task = fetch_container_stats(host_name, host_address, port)
+        labels_task = get_container_compose_labels(config, host_name)
+        (containers, _), labels = await asyncio.gather(stats_task, labels_task)
+
+        if containers is None:
+            # Skip failed hosts in aggregate view
+            return []
+
+        # Enrich containers with compose labels (mutate in place)
+        for c in containers:
+            c.stack, c.service = labels.get(c.name, ("", ""))
+        return containers
+
+    tasks = [fetch_host_data(name, host.address) for name, host in config.hosts.items()]
+    results = await asyncio.gather(*tasks)
+    # Flatten list of lists
+    return [container for host_containers in results for container in host_containers]

src/compose_farm/logs.py

@@ -6,21 +6,22 @@ import json
 import tomllib
 from dataclasses import dataclass
 from datetime import UTC, datetime
-from typing import TYPE_CHECKING, Any
+from typing import TYPE_CHECKING
 
-from .executor import run_compose
+from .executor import run_command
 from .paths import xdg_config_home
 
 if TYPE_CHECKING:
-    from collections.abc import Awaitable, Callable, Iterable
+    from collections.abc import Iterable
     from pathlib import Path
 
     from .config import Config
-    from .executor import CommandResult
+
+# Separator used to split output sections
+_SECTION_SEPARATOR = "---CF-SEP---"
 
 
 DEFAULT_LOG_PATH = xdg_config_home() / "compose-farm" / "dockerfarm-log.toml"
-_DIGEST_HEX_LENGTH = 64
 
 
 @dataclass(frozen=True)
@@ -56,87 +57,97 @@ def _escape(value: str) -> str:
     return value.replace("\\", "\\\\").replace('"', '\\"')
 
 
-def _parse_images_output(raw: str) -> list[dict[str, Any]]:
-    """Parse `docker compose images --format json` output.
-
-    Handles both a JSON array and newline-separated JSON objects for robustness.
-    """
-    raw = raw.strip()
-    if not raw:
-        return []
-
+def _parse_image_digests(image_json: str) -> dict[str, str]:
+    """Parse docker image inspect JSON to build image tag -> digest map."""
+    if not image_json:
+        return {}
     try:
-        parsed = json.loads(raw)
+        image_data = json.loads(image_json)
     except json.JSONDecodeError:
-        objects = []
-        for line in raw.splitlines():
-            if not line.strip():
-                continue
-            objects.append(json.loads(line))
-        return objects
+        return {}
 
-    if isinstance(parsed, list):
-        return parsed
-    if isinstance(parsed, dict):
-        return [parsed]
-    return []
+    image_digests: dict[str, str] = {}
+    for img in image_data:
+        tags = img.get("RepoTags") or []
+        digests = img.get("RepoDigests") or []
+        digest = digests[0].split("@")[-1] if digests else img.get("Id", "")
+        for tag in tags:
+            image_digests[tag] = digest
+        if img.get("Id"):
+            image_digests[img["Id"]] = digest
+    return image_digests
 
 
-def _extract_image_fields(record: dict[str, Any]) -> tuple[str, str]:
-    """Extract image name and digest with fallbacks."""
-    image = record.get("Image") or record.get("Repository") or record.get("Name") or ""
-    tag = record.get("Tag") or record.get("Version")
-    if tag and ":" not in image.rsplit("/", 1)[-1]:
-        image = f"{image}:{tag}"
-
-    digest = (
-        record.get("Digest")
-        or record.get("Image ID")
-        or record.get("ImageID")
-        or record.get("ID")
-        or ""
-    )
-
-    if digest and not digest.startswith("sha256:") and len(digest) == _DIGEST_HEX_LENGTH:
-        digest = f"sha256:{digest}"
-
-    return image, digest
-
-
-async def collect_stack_entries(
+async def collect_stacks_entries_on_host(
     config: Config,
-    stack: str,
+    host_name: str,
+    stacks: set[str],
     *,
     now: datetime,
-    run_compose_fn: Callable[..., Awaitable[CommandResult]] = run_compose,
 ) -> list[SnapshotEntry]:
-    """Run `docker compose images` for a stack and normalize results."""
-    result = await run_compose_fn(config, stack, "images --format json", stream=False)
+    """Collect image entries for stacks on one host using 2 docker commands.
+
+    Uses `docker ps` to get running containers + their compose project labels,
+    then `docker image inspect` to get digests for all unique images.
+    Much faster than running N `docker compose images` commands.
+    """
+    if not stacks:
+        return []
+
+    host = config.hosts[host_name]
+
+    # Single SSH call with 2 docker commands:
+    # 1. Get project|image pairs from running containers
+    # 2. Get image info (including digests) for all unique images
+    command = (
+        f"docker ps --format '{{{{.Label \"com.docker.compose.project\"}}}}|{{{{.Image}}}}' && "
+        f"echo '{_SECTION_SEPARATOR}' && "
+        "docker image inspect $(docker ps --format '{{.Image}}' | sort -u) 2>/dev/null || true"
+    )
+    result = await run_command(host, command, host_name, stream=False, prefix="")
+
     if not result.success:
-        msg = result.stderr or f"compose images exited with {result.exit_code}"
-        error = f"[{stack}] Unable to read images: {msg}"
-        raise RuntimeError(error)
+        return []
 
-    records = _parse_images_output(result.stdout)
-    # Use first host for snapshots (multi-host stacks use same images on all hosts)
-    host_name = config.get_hosts(stack)[0]
-    compose_path = config.get_compose_path(stack)
+    # Split output into two sections
+    parts = result.stdout.split(_SECTION_SEPARATOR)
+    if len(parts) != 2:  # noqa: PLR2004
+        return []
 
-    entries: list[SnapshotEntry] = []
-    for record in records:
-        image, digest = _extract_image_fields(record)
-        if not digest:
+    container_lines, image_json = parts[0].strip(), parts[1].strip()
+
+    # Parse project|image pairs, filtering to only stacks we care about
+    stack_images: dict[str, set[str]] = {}
+    for line in container_lines.splitlines():
+        if "|" not in line:
             continue
-        entries.append(
-            SnapshotEntry(
-                stack=stack,
-                host=host_name,
-                compose_file=compose_path,
-                image=image,
-                digest=digest,
-                captured_at=now,
-            )
-        )
+        project, image = line.split("|", 1)
+        if project in stacks:
+            stack_images.setdefault(project, set()).add(image)
+
+    if not stack_images:
+        return []
+
+    # Parse image inspect JSON to build image -> digest map
+    image_digests = _parse_image_digests(image_json)
+
+    # Build entries
+    entries: list[SnapshotEntry] = []
+    for stack, images in stack_images.items():
+        for image in images:
+            digest = image_digests.get(image, "")
+            if digest:
+                entries.append(
+                    SnapshotEntry(
+                        stack=stack,
+                        host=host_name,
+                        compose_file=config.get_compose_path(stack),
+                        image=image,
+                        digest=digest,
+                        captured_at=now,
+                    )
+                )
+
     return entries
 
 

src/compose_farm/operations.py

@@ -76,31 +76,6 @@ def get_stack_paths(cfg: Config, stack: str) -> list[str]:
     return paths
 
 
-async def discover_stack_host(cfg: Config, stack: str) -> tuple[str, str | list[str] | None]:
-    """Discover where a stack is running.
-
-    For multi-host stacks, checks all assigned hosts in parallel.
-    For single-host, checks assigned host first, then others.
-
-    Returns (stack_name, host_or_hosts_or_none).
-    """
-    assigned_hosts = cfg.get_hosts(stack)
-
-    if cfg.is_multi_host(stack):
-        # Check all assigned hosts in parallel
-        checks = await asyncio.gather(*[check_stack_running(cfg, stack, h) for h in assigned_hosts])
-        running = [h for h, is_running in zip(assigned_hosts, checks, strict=True) if is_running]
-        return stack, running if running else None
-
-    # Single-host: check assigned host first, then others
-    if await check_stack_running(cfg, stack, assigned_hosts[0]):
-        return stack, assigned_hosts[0]
-    for host in cfg.hosts:
-        if host != assigned_hosts[0] and await check_stack_running(cfg, stack, host):
-            return stack, host
-    return stack, None
-
-
 class StackDiscoveryResult(NamedTuple):
     """Result of discovering where a stack is running across all hosts."""
 
@@ -134,25 +109,6 @@ class StackDiscoveryResult(NamedTuple):
         return not self.is_multi_host and len(self.running_hosts) > 1
 
 
-async def discover_stack_on_all_hosts(cfg: Config, stack: str) -> StackDiscoveryResult:
-    """Discover where a stack is running across ALL hosts.
-
-    Unlike discover_stack_host(), this checks every host in parallel
-    to detect strays and duplicates.
-    """
-    configured_hosts = cfg.get_hosts(stack)
-    all_hosts = list(cfg.hosts.keys())
-
-    checks = await asyncio.gather(*[check_stack_running(cfg, stack, h) for h in all_hosts])
-    running_hosts = [h for h, is_running in zip(all_hosts, checks, strict=True) if is_running]
-
-    return StackDiscoveryResult(
-        stack=stack,
-        configured_hosts=configured_hosts,
-        running_hosts=running_hosts,
-    )
-
-
 async def check_stack_requirements(
     cfg: Config,
     stack: str,
@@ -518,3 +474,60 @@ async def stop_stray_stacks(
 
     """
     return await _stop_stacks_on_hosts(cfg, strays, label="stray")
+
+
+def build_discovery_results(
+    cfg: Config,
+    running_on_host: dict[str, set[str]],
+    stacks: list[str] | None = None,
+) -> tuple[dict[str, str | list[str]], dict[str, list[str]], dict[str, list[str]]]:
+    """Build discovery results from per-host running stacks.
+
+    Takes the raw data of which stacks are running on which hosts and
+    categorizes them into discovered (running correctly), strays (wrong host),
+    and duplicates (single-host stack on multiple hosts).
+
+    Args:
+        cfg: Config object.
+        running_on_host: Dict mapping host -> set of running stack names.
+        stacks: Optional list of stacks to check. Defaults to all configured stacks.
+
+    Returns:
+        Tuple of (discovered, strays, duplicates):
+        - discovered: stack -> host(s) where running correctly
+        - strays: stack -> list of unauthorized hosts
+        - duplicates: stack -> list of all hosts (for single-host stacks on multiple)
+
+    """
+    stack_list = stacks if stacks is not None else list(cfg.stacks)
+    all_hosts = list(running_on_host.keys())
+
+    # Build StackDiscoveryResult for each stack
+    results: list[StackDiscoveryResult] = [
+        StackDiscoveryResult(
+            stack=stack,
+            configured_hosts=cfg.get_hosts(stack),
+            running_hosts=[h for h in all_hosts if stack in running_on_host[h]],
+        )
+        for stack in stack_list
+    ]
+
+    discovered: dict[str, str | list[str]] = {}
+    strays: dict[str, list[str]] = {}
+    duplicates: dict[str, list[str]] = {}
+
+    for result in results:
+        correct_hosts = [h for h in result.running_hosts if h in result.configured_hosts]
+        if correct_hosts:
+            if result.is_multi_host:
+                discovered[result.stack] = correct_hosts
+            else:
+                discovered[result.stack] = correct_hosts[0]
+
+        if result.is_stray:
+            strays[result.stack] = result.stray_hosts
+
+        if result.is_duplicate:
+            duplicates[result.stack] = result.running_hosts
+
+    return discovered, strays, duplicates

src/compose_farm/registry.py

@@ -0,0 +1,220 @@
+"""Container registry API client for tag discovery."""
+
+from __future__ import annotations
+
+import re
+from dataclasses import dataclass, field
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    import httpx
+
+# Image reference pattern: [registry/][namespace/]name[:tag][@digest]
+IMAGE_PATTERN = re.compile(
+    r"^(?:(?P<registry>[^/]+\.[^/]+)/)?(?:(?P<namespace>[^/:@]+)/)?(?P<name>[^/:@]+)(?::(?P<tag>[^@]+))?(?:@(?P<digest>.+))?$"
+)
+
+# Docker Hub aliases
+DOCKER_HUB_ALIASES = frozenset(
+    {"docker.io", "index.docker.io", "registry.hub.docker.com", "registry-1.docker.io"}
+)
+
+# Token endpoints per registry: (url, extra_params)
+TOKEN_ENDPOINTS: dict[str, tuple[str, dict[str, str]]] = {
+    "docker.io": ("https://auth.docker.io/token", {"service": "registry.docker.io"}),
+    "ghcr.io": ("https://ghcr.io/token", {}),
+}
+
+# Registry URL overrides (Docker Hub uses a different host for API)
+REGISTRY_URLS: dict[str, str] = {
+    "docker.io": "https://registry-1.docker.io",
+}
+
+HTTP_OK = 200
+
+MANIFEST_ACCEPT = (
+    "application/vnd.docker.distribution.manifest.v2+json, "
+    "application/vnd.oci.image.manifest.v1+json, "
+    "application/vnd.oci.image.index.v1+json"
+)
+
+
+@dataclass(frozen=True)
+class ImageRef:
+    """Parsed container image reference."""
+
+    registry: str
+    namespace: str
+    name: str
+    tag: str
+    digest: str | None = None
+
+    @property
+    def full_name(self) -> str:
+        """Full image name with namespace."""
+        return f"{self.namespace}/{self.name}" if self.namespace else self.name
+
+    @property
+    def display_name(self) -> str:
+        """Display name (omits docker.io/library for official images)."""
+        if self.registry in DOCKER_HUB_ALIASES:
+            if self.namespace == "library":
+                return self.name
+            return self.full_name
+        return f"{self.registry}/{self.full_name}"
+
+    @classmethod
+    def parse(cls, image: str) -> ImageRef:
+        """Parse image string into components."""
+        match = IMAGE_PATTERN.match(image)
+        if not match:
+            return cls("docker.io", "library", image.split(":")[0].split("@")[0], "latest")
+
+        groups = match.groupdict()
+        registry = groups.get("registry") or "docker.io"
+        namespace = groups.get("namespace") or ""
+        name = groups.get("name") or image
+        tag = groups.get("tag") or "latest"
+        digest = groups.get("digest")
+
+        # Docker Hub official images have implicit "library" namespace
+        if registry in DOCKER_HUB_ALIASES and not namespace:
+            namespace = "library"
+
+        return cls(registry, namespace, name, tag, digest)
+
+
+@dataclass
+class TagCheckResult:
+    """Result of checking tags for an image."""
+
+    image: ImageRef
+    current_digest: str
+    available_updates: list[str] = field(default_factory=list)
+    error: str | None = None
+
+
+class RegistryClient:
+    """Unified OCI Distribution API client."""
+
+    def __init__(self, registry: str) -> None:
+        """Initialize for a specific registry."""
+        self.registry = registry.lower()
+        # Normalize Docker Hub aliases
+        if self.registry in DOCKER_HUB_ALIASES:
+            self.registry = "docker.io"
+
+        self.registry_url = REGISTRY_URLS.get(self.registry, f"https://{self.registry}")
+        self._token_cache: dict[str, str] = {}
+
+    async def _get_token(self, image: ImageRef, client: httpx.AsyncClient) -> str | None:
+        """Get auth token for the registry (cached per image)."""
+        cache_key = image.full_name
+        if cache_key in self._token_cache:
+            return self._token_cache[cache_key]
+
+        endpoint = TOKEN_ENDPOINTS.get(self.registry)
+        if not endpoint:
+            return None  # No auth needed or unknown registry
+
+        url, extra_params = endpoint
+        params = {"scope": f"repository:{image.full_name}:pull", **extra_params}
+        resp = await client.get(url, params=params)
+
+        if resp.status_code == HTTP_OK:
+            token: str | None = resp.json().get("token")
+            if token:
+                self._token_cache[cache_key] = token
+            return token
+        return None
+
+    async def get_tags(self, image: ImageRef, client: httpx.AsyncClient) -> list[str]:
+        """Fetch available tags for an image."""
+        headers = {}
+        token = await self._get_token(image, client)
+        if token:
+            headers["Authorization"] = f"Bearer {token}"
+
+        url = f"{self.registry_url}/v2/{image.full_name}/tags/list"
+        resp = await client.get(url, headers=headers)
+
+        if resp.status_code != HTTP_OK:
+            return []
+        tags: list[str] = resp.json().get("tags", [])
+        return tags
+
+    async def get_digest(self, image: ImageRef, tag: str, client: httpx.AsyncClient) -> str | None:
+        """Get digest for a specific tag."""
+        headers = {"Accept": MANIFEST_ACCEPT}
+        token = await self._get_token(image, client)
+        if token:
+            headers["Authorization"] = f"Bearer {token}"
+
+        url = f"{self.registry_url}/v2/{image.full_name}/manifests/{tag}"
+        resp = await client.head(url, headers=headers)
+
+        if resp.status_code == HTTP_OK:
+            digest: str | None = resp.headers.get("docker-content-digest")
+            return digest
+        return None
+
+
+def _parse_version(tag: str) -> tuple[int, ...] | None:
+    """Parse version string into comparable tuple."""
+    tag = tag.lstrip("vV")
+    parts = tag.split(".")
+    try:
+        return tuple(int(p) for p in parts)
+    except ValueError:
+        return None
+
+
+def _find_updates(current_tag: str, tags: list[str]) -> list[str]:
+    """Find tags newer than current based on version comparison."""
+    current_version = _parse_version(current_tag)
+    if current_version is None:
+        return []
+
+    updates = []
+    for tag in tags:
+        tag_version = _parse_version(tag)
+        if tag_version and tag_version > current_version:
+            updates.append(tag)
+
+    updates.sort(key=lambda t: _parse_version(t) or (), reverse=True)
+    return updates
+
+
+async def check_image_updates(
+    image_str: str,
+    client: httpx.AsyncClient,
+) -> TagCheckResult:
+    """Check if newer versions are available for an image.
+
+    Args:
+        image_str: Image string like "nginx:1.25" or "ghcr.io/user/repo:tag"
+        client: httpx async client
+
+    Returns:
+        TagCheckResult with available updates
+
+    """
+    image = ImageRef.parse(image_str)
+    registry_client = RegistryClient(image.registry)
+
+    try:
+        tags = await registry_client.get_tags(image, client)
+        updates = _find_updates(image.tag, tags)
+        current_digest = await registry_client.get_digest(image, image.tag, client) or ""
+
+        return TagCheckResult(
+            image=image,
+            current_digest=current_digest,
+            available_updates=updates,
+        )
+    except Exception as e:
+        return TagCheckResult(
+            image=image,
+            current_digest="",
+            error=str(e),
+        )

src/compose_farm/web/app.py

@@ -6,15 +6,16 @@ import asyncio
 import logging
 import sys
 from contextlib import asynccontextmanager, suppress
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, Any, cast
 
 from fastapi import FastAPI
+from fastapi.middleware.gzip import GZipMiddleware
 from fastapi.staticfiles import StaticFiles
 from pydantic import ValidationError
 from rich.logging import RichHandler
 
 from compose_farm.web.deps import STATIC_DIR, get_config
-from compose_farm.web.routes import actions, api, pages
+from compose_farm.web.routes import actions, api, containers, pages
 from compose_farm.web.streaming import TASK_TTL_SECONDS, cleanup_stale_tasks
 
 # Configure logging with Rich handler for compose_farm.web modules
@@ -64,10 +65,14 @@ def create_app() -> FastAPI:
         lifespan=lifespan,
     )
 
+    # Enable Gzip compression for faster transfers over slow networks
+    app.add_middleware(cast("Any", GZipMiddleware), minimum_size=1000)
+
     # Mount static files
     app.mount("/static", StaticFiles(directory=str(STATIC_DIR)), name="static")
 
     app.include_router(pages.router)
+    app.include_router(containers.router)
     app.include_router(api.router, prefix="/api")
     app.include_router(actions.router, prefix="/api")
 

src/compose_farm/web/cdn.py

@@ -39,6 +39,14 @@ CDN_ASSETS: dict[str, tuple[str, str]] = {
         "xterm-fit.js",
         "application/javascript",
     ),
+    "https://unpkg.com/idiomorph/dist/idiomorph.min.js": (
+        "idiomorph.js",
+        "application/javascript",
+    ),
+    "https://unpkg.com/idiomorph/dist/idiomorph-ext.min.js": (
+        "idiomorph-ext.js",
+        "application/javascript",
+    ),
     # Monaco editor - dynamically loaded by app.js
     "https://cdn.jsdelivr.net/npm/monaco-editor@0.52.2/min/vs/loader.js": (
         "monaco-loader.js",

src/compose_farm/web/deps.py

@@ -38,7 +38,17 @@ def get_templates() -> Jinja2Templates:
 def extract_config_error(exc: Exception) -> str:
     """Extract a user-friendly error message from a config exception."""
     if isinstance(exc, ValidationError):
-        return "; ".join(err.get("msg", str(err)) for err in exc.errors())
+        parts = []
+        for err in exc.errors():
+            msg = err.get("msg", str(err))
+            loc = err.get("loc", ())
+            if loc:
+                # Format location as dot-separated path (e.g., "hosts.nas.port")
+                loc_str = ".".join(str(part) for part in loc)
+                parts.append(f"{loc_str}: {msg}")
+            else:
+                parts.append(msg)
+        return "; ".join(parts)
     return str(exc)
 
 

src/compose_farm/web/routes/__init__.py

@@ -1,5 +1,5 @@
 """Web routes."""
 
-from compose_farm.web.routes import actions, api, pages
+from compose_farm.web.routes import actions, api, containers, pages
 
-__all__ = ["actions", "api", "pages"]
+__all__ = ["actions", "api", "containers", "pages"]

src/compose_farm/web/routes/api.py

@@ -21,6 +21,7 @@ from fastapi.responses import HTMLResponse
 
 from compose_farm.compose import get_container_name
 from compose_farm.executor import is_local, run_compose_on_host, ssh_connect_kwargs
+from compose_farm.glances import fetch_all_host_stats
 from compose_farm.paths import backup_dir, find_config_path
 from compose_farm.state import load_state
 from compose_farm.web.deps import get_config, get_templates
@@ -385,3 +386,19 @@ async def write_console_file(
     except Exception as e:
         logger.exception("Failed to write file %s to host %s", path, host)
         raise HTTPException(status_code=500, detail=str(e)) from e
+
+
+@router.get("/glances", response_class=HTMLResponse)
+async def get_glances_stats() -> HTMLResponse:
+    """Get resource stats from Glances for all hosts."""
+    config = get_config()
+
+    if not config.glances_stack:
+        return HTMLResponse("")  # Glances not configured
+
+    stats = await fetch_all_host_stats(config)
+
+    templates = get_templates()
+    template = templates.env.get_template("partials/glances.html")
+    html = template.render(stats=stats)
+    return HTMLResponse(html)

src/compose_farm/web/routes/containers.py

@@ -0,0 +1,370 @@
+"""Container dashboard routes using Glances API."""
+
+from __future__ import annotations
+
+import html
+import re
+from typing import TYPE_CHECKING
+from urllib.parse import quote
+
+import humanize
+from fastapi import APIRouter, Request
+from fastapi.responses import HTMLResponse, JSONResponse
+
+from compose_farm.executor import TTLCache
+from compose_farm.glances import ContainerStats, fetch_all_container_stats
+from compose_farm.registry import DOCKER_HUB_ALIASES, ImageRef
+from compose_farm.web.deps import get_config, get_templates
+
+router = APIRouter(tags=["containers"])
+
+if TYPE_CHECKING:
+    from compose_farm.registry import TagCheckResult
+
+# Cache registry update checks for 5 minutes (300 seconds)
+# Registry calls are slow and often rate-limited
+_update_check_cache = TTLCache(ttl_seconds=300.0)
+
+# Minimum parts needed to infer stack/service from container name
+MIN_NAME_PARTS = 2
+
+# HTML for "no update info" dash
+_DASH_HTML = '<span class="text-xs opacity-50">-</span>'
+
+
+def _format_bytes(bytes_val: int) -> str:
+    """Format bytes to human readable string."""
+    return humanize.naturalsize(bytes_val, binary=True, format="%.1f")
+
+
+def _parse_image(image: str) -> tuple[str, str]:
+    """Parse image string into (name, tag)."""
+    # Handle registry prefix (e.g., ghcr.io/user/repo:tag)
+    if ":" in image:
+        # Find last colon that's not part of port
+        parts = image.rsplit(":", 1)
+        if "/" in parts[-1]:
+            # The "tag" contains a slash, so it's probably a port
+            return image, "latest"
+        return parts[0], parts[1]
+    return image, "latest"
+
+
+def _infer_stack_service(name: str) -> tuple[str, str]:
+    """Fallback: infer stack and service from container name.
+
+    Used when compose labels are not available.
+    Docker Compose naming conventions:
+    - Default: {project}_{service}_{instance} or {project}-{service}-{instance}
+    - Custom: {container_name} from compose file
+    """
+    # Try underscore separator first (older compose)
+    if "_" in name:
+        parts = name.split("_")
+        if len(parts) >= MIN_NAME_PARTS:
+            return parts[0], parts[1]
+    # Try hyphen separator (newer compose)
+    if "-" in name:
+        parts = name.split("-")
+        if len(parts) >= MIN_NAME_PARTS:
+            return parts[0], "-".join(parts[1:-1]) if len(parts) > MIN_NAME_PARTS else parts[1]
+    # Fallback: use name as both stack and service
+    return name, name
+
+
+@router.get("/live-stats", response_class=HTMLResponse)
+async def containers_page(request: Request) -> HTMLResponse:
+    """Container dashboard page."""
+    config = get_config()
+    templates = get_templates()
+
+    # Check if Glances is configured
+    glances_enabled = config.glances_stack is not None
+
+    return templates.TemplateResponse(
+        "containers.html",
+        {
+            "request": request,
+            "glances_enabled": glances_enabled,
+            "hosts": sorted(config.hosts.keys()) if glances_enabled else [],
+        },
+    )
+
+
+_STATUS_CLASSES = {
+    "running": "badge badge-success badge-sm",
+    "exited": "badge badge-error badge-sm",
+    "paused": "badge badge-warning badge-sm",
+}
+
+
+def _status_class(status: str) -> str:
+    """Get CSS class for status badge."""
+    return _STATUS_CLASSES.get(status.lower(), "badge badge-ghost badge-sm")
+
+
+def _progress_class(percent: float) -> str:
+    """Get CSS class for progress bar color."""
+    if percent > 80:  # noqa: PLR2004
+        return "bg-error"
+    if percent > 50:  # noqa: PLR2004
+        return "bg-warning"
+    return "bg-success"
+
+
+def _render_update_cell(image: str, tag: str) -> str:
+    """Render update check cell with client-side batch updates."""
+    encoded_image = quote(image, safe="")
+    encoded_tag = quote(tag, safe="")
+    cached_html = _update_check_cache.get(f"{image}:{tag}")
+    inner = cached_html if cached_html is not None else _DASH_HTML
+    return (
+        f"""<td class="update-cell" data-image="{encoded_image}" data-tag="{encoded_tag}">"""
+        f"{inner}</td>"
+    )
+
+
+def _image_web_url(image: str) -> str | None:
+    """Return a human-friendly registry URL for an image (without tag)."""
+    ref = ImageRef.parse(image)
+    if ref.registry in DOCKER_HUB_ALIASES:
+        if ref.namespace == "library":
+            return f"https://hub.docker.com/_/{ref.name}"
+        return f"https://hub.docker.com/r/{ref.namespace}/{ref.name}"
+    return f"https://{ref.registry}/{ref.full_name}"
+
+
+def _render_row(c: ContainerStats, idx: int | str) -> str:
+    """Render a single container as an HTML table row."""
+    image_name, tag = _parse_image(c.image)
+    stack = c.stack if c.stack else _infer_stack_service(c.name)[0]
+    service = c.service if c.service else _infer_stack_service(c.name)[1]
+
+    cpu = c.cpu_percent
+    mem = c.memory_percent
+    cpu_class = _progress_class(cpu)
+    mem_class = _progress_class(mem)
+
+    # Highlight rows with high resource usage
+    high_cpu = cpu > 80  # noqa: PLR2004
+    high_mem = mem > 90  # noqa: PLR2004
+    row_class = "high-usage" if (high_cpu or high_mem) else ""
+
+    uptime_sec = _parse_uptime_seconds(c.uptime)
+    actions = _render_actions(stack)
+    update_cell = _render_update_cell(image_name, tag)
+    image_label = f"{image_name}:{tag}"
+    image_url = _image_web_url(image_name)
+    if image_url:
+        image_html = (
+            f'<a href="{image_url}" target="_blank" rel="noopener noreferrer" '
+            f'class="link link-hover">'
+            f'<code class="text-xs bg-base-200 px-1 rounded">{image_label}</code></a>'
+        )
+    else:
+        image_html = f'<code class="text-xs bg-base-200 px-1 rounded">{image_label}</code>'
+    # Render as single line to avoid whitespace nodes in DOM
+    row_id = f"c-{c.host}-{c.name}"
+    class_attr = f' class="{row_class}"' if row_class else ""
+    return (
+        f'<tr id="{row_id}" data-host="{c.host}"{class_attr}><td class="text-xs opacity-50">{idx}</td>'
+        f'<td data-sort="{stack.lower()}"><a href="/stack/{stack}" class="link link-hover link-primary" hx-boost="true">{stack}</a></td>'
+        f'<td data-sort="{service.lower()}" class="text-xs opacity-70">{service}</td>'
+        f"<td>{actions}</td>"
+        f'<td data-sort="{c.host.lower()}"><span class="badge badge-outline badge-xs">{c.host}</span></td>'
+        f'<td data-sort="{c.image.lower()}">{image_html}</td>'
+        f"{update_cell}"
+        f'<td data-sort="{c.status.lower()}"><span class="{_status_class(c.status)}">{c.status}</span></td>'
+        f'<td data-sort="{uptime_sec}" class="text-xs text-right font-mono">{c.uptime or "-"}</td>'
+        f'<td data-sort="{cpu}" class="text-right font-mono"><div class="flex flex-col items-end gap-0.5"><div class="w-12 h-2 bg-base-300 rounded-full overflow-hidden"><div class="h-full {cpu_class}" style="width: {min(cpu, 100)}%"></div></div><span class="text-xs">{cpu:.0f}%</span></div></td>'
+        f'<td data-sort="{c.memory_usage}" class="text-right font-mono"><div class="flex flex-col items-end gap-0.5"><div class="w-12 h-2 bg-base-300 rounded-full overflow-hidden"><div class="h-full {mem_class}" style="width: {min(mem, 100)}%"></div></div><span class="text-xs">{_format_bytes(c.memory_usage)}</span></div></td>'
+        f'<td data-sort="{c.network_rx + c.network_tx}" class="text-xs text-right font-mono">↓{_format_bytes(c.network_rx)} ↑{_format_bytes(c.network_tx)}</td>'
+        "</tr>"
+    )
+
+
+def _render_actions(stack: str) -> str:
+    """Render actions dropdown for a container row."""
+    return f"""<button class="btn btn-circle btn-ghost btn-xs" onclick="openActionMenu(event, '{stack}')" aria-label="Actions for {stack}">
+<svg class="h-4 w-4"><use href="#icon-menu" /></svg>
+</button>"""
+
+
+def _parse_uptime_seconds(uptime: str) -> int:
+    """Parse uptime string to seconds for sorting."""
+    if not uptime:
+        return 0
+    uptime = uptime.lower().strip()
+    # Handle "a/an" as 1
+    uptime = uptime.replace("an ", "1 ").replace("a ", "1 ")
+
+    total = 0
+    multipliers = {
+        "second": 1,
+        "minute": 60,
+        "hour": 3600,
+        "day": 86400,
+        "week": 604800,
+        "month": 2592000,
+        "year": 31536000,
+    }
+    for match in re.finditer(r"(\d+)\s*(\w+)", uptime):
+        num = int(match.group(1))
+        unit = match.group(2).rstrip("s")  # Remove plural 's'
+        total += num * multipliers.get(unit, 0)
+    return total
+
+
+@router.get("/api/containers/rows", response_class=HTMLResponse)
+async def get_containers_rows() -> HTMLResponse:
+    """Get container table rows as HTML for HTMX.
+
+    Each cell has data-sort attribute for instant client-side sorting.
+    """
+    config = get_config()
+
+    if not config.glances_stack:
+        return HTMLResponse(
+            '<tr><td colspan="12" class="text-center text-error">Glances not configured</td></tr>'
+        )
+
+    containers = await fetch_all_container_stats(config)
+
+    if not containers:
+        return HTMLResponse(
+            '<tr><td colspan="12" class="text-center py-4 opacity-60">No containers found</td></tr>'
+        )
+
+    rows = "\n".join(_render_row(c, i + 1) for i, c in enumerate(containers))
+    return HTMLResponse(rows)
+
+
+@router.get("/api/containers/rows/{host_name}", response_class=HTMLResponse)
+async def get_containers_rows_by_host(host_name: str) -> HTMLResponse:
+    """Get container rows for a specific host.
+
+    Returns immediately with Glances data. Stack/service are inferred from
+    container names for instant display (no SSH wait).
+    """
+    import logging  # noqa: PLC0415
+    import time  # noqa: PLC0415
+
+    from compose_farm.executor import get_container_compose_labels  # noqa: PLC0415
+    from compose_farm.glances import fetch_container_stats  # noqa: PLC0415
+
+    logger = logging.getLogger(__name__)
+    config = get_config()
+
+    if host_name not in config.hosts:
+        return HTMLResponse("")
+
+    host = config.hosts[host_name]
+
+    t0 = time.monotonic()
+    containers, error = await fetch_container_stats(host_name, host.address)
+    t1 = time.monotonic()
+    fetch_ms = (t1 - t0) * 1000
+
+    if containers is None:
+        logger.error(
+            "Failed to fetch stats for %s in %.1fms: %s",
+            host_name,
+            fetch_ms,
+            error,
+        )
+        return HTMLResponse(
+            f'<tr class="text-error"><td colspan="12" class="text-center py-2">Error: {error}</td></tr>'
+        )
+
+    if not containers:
+        return HTMLResponse("")  # No rows for this host
+
+    labels = await get_container_compose_labels(config, host_name)
+    for c in containers:
+        stack, service = labels.get(c.name, ("", ""))
+        if not stack or not service:
+            stack, service = _infer_stack_service(c.name)
+        c.stack, c.service = stack, service
+
+    # Only show containers from stacks in config (filters out orphaned/unknown stacks)
+    containers = [c for c in containers if not c.stack or c.stack in config.stacks]
+
+    # Use placeholder index (will be renumbered by JS after all hosts load)
+    rows = "\n".join(_render_row(c, "-") for c in containers)
+    t2 = time.monotonic()
+    render_ms = (t2 - t1) * 1000
+
+    logger.info(
+        "Loaded %d rows for %s in %.1fms (fetch) + %.1fms (render)",
+        len(containers),
+        host_name,
+        fetch_ms,
+        render_ms,
+    )
+    return HTMLResponse(rows)
+
+
+def _render_update_badge(result: TagCheckResult) -> str:
+    if result.error:
+        return _DASH_HTML
+    if result.available_updates:
+        updates = result.available_updates
+        count = len(updates)
+        title = f"Newer: {', '.join(updates[:3])}" + ("..." if count > 3 else "")  # noqa: PLR2004
+        tip = html.escape(title, quote=True)
+        return (
+            f'<span class="tooltip" data-tip="{tip}">'
+            f'<span class="badge badge-warning badge-xs cursor-help">{count} new</span>'
+            "</span>"
+        )
+    return '<span class="tooltip" data-tip="Up to date"><span class="text-success text-xs">✓</span></span>'
+
+
+@router.post("/api/containers/check-updates", response_class=JSONResponse)
+async def check_container_updates_batch(request: Request) -> JSONResponse:
+    """Batch update checks for a list of images.
+
+    Payload: {"items": [{"image": "...", "tag": "..."}, ...]}
+    Returns: {"results": [{"image": "...", "tag": "...", "html": "..."}, ...]}
+    """
+    import httpx  # noqa: PLC0415
+
+    payload = await request.json()
+    items = payload.get("items", []) if isinstance(payload, dict) else []
+    if not items:
+        return JSONResponse({"results": []})
+
+    results = []
+
+    from compose_farm.registry import check_image_updates  # noqa: PLC0415
+
+    async with httpx.AsyncClient(timeout=10.0) as client:
+        for item in items:
+            image = item.get("image", "")
+            tag = item.get("tag", "")
+            full_image = f"{image}:{tag}"
+            if not image or not tag:
+                results.append({"image": image, "tag": tag, "html": _DASH_HTML})
+                continue
+
+            # NOTE: Tag-based checks cannot detect digest changes for moving tags
+            # like "latest". A future improvement could compare remote vs local
+            # digests using dockerfarm-log.toml (from `cf refresh`) or a per-host
+            # digest lookup.
+
+            cached_html: str | None = _update_check_cache.get(full_image)
+            if cached_html is not None:
+                results.append({"image": image, "tag": tag, "html": cached_html})
+                continue
+
+            try:
+                result = await check_image_updates(full_image, client)
+                html = _render_update_badge(result)
+                _update_check_cache.set(full_image, html)
+            except Exception:
+                _update_check_cache.set(full_image, _DASH_HTML, ttl_seconds=60.0)
+                html = _DASH_HTML
+
+            results.append({"image": image, "tag": tag, "html": html})
+
+    return JSONResponse({"results": results})

src/compose_farm/web/static/app.js

@@ -9,7 +9,6 @@
 // ANSI escape codes for terminal output
 const ANSI = {
     RED: '\x1b[31m',
-    GREEN: '\x1b[32m',
     DIM: '\x1b[2m',
     RESET: '\x1b[0m',
     CRLF: '\r\n'
@@ -122,7 +121,6 @@ function whenXtermReady(callback, maxAttempts = 20) {
     };
     tryInit(maxAttempts);
 }
-window.whenXtermReady = whenXtermReady;
 
 // ============================================================================
 // TERMINAL
@@ -209,8 +207,6 @@ function initTerminal(elementId, taskId) {
     return { term, ws };
 }
 
-window.initTerminal = initTerminal;
-
 /**
  * Initialize an interactive exec terminal
  */
@@ -432,7 +428,7 @@ function initMonacoEditors() {
  * Save all editors
  */
 async function saveAllEditors() {
-    const saveBtn = document.getElementById('save-btn') || document.getElementById('save-config-btn');
+    const saveBtn = getSaveButton();
     const results = [];
 
     for (const [id, editor] of Object.entries(editors)) {
@@ -468,12 +464,16 @@ async function saveAllEditors() {
  * Initialize save button handler
  */
 function initSaveButton() {
-    const saveBtn = document.getElementById('save-btn') || document.getElementById('save-config-btn');
+    const saveBtn = getSaveButton();
     if (!saveBtn) return;
 
     saveBtn.onclick = saveAllEditors;
 }
 
+function getSaveButton() {
+    return document.getElementById('save-btn') || document.getElementById('save-config-btn');
+}
+
 // ============================================================================
 // UI HELPERS
 // ============================================================================
@@ -607,10 +607,11 @@ function playFabIntro() {
             cmd('action', 'Update All', 'Update all stacks', dashboardAction('update-all'), icons.refresh_cw),
             cmd('app', 'Theme', 'Change color theme', openThemePicker, icons.palette),
             cmd('app', 'Dashboard', 'Go to dashboard', nav('/'), icons.home),
+            cmd('app', 'Live Stats', 'View all containers across hosts', nav('/live-stats'), icons.box),
             cmd('app', 'Console', 'Go to console', nav('/console'), icons.terminal),
             cmd('app', 'Edit Config', 'Edit compose-farm.yaml', nav('/console#editor'), icons.file_code),
             cmd('app', 'Docs', 'Open documentation', openExternal('https://compose-farm.nijho.lt/'), icons.book_open),
-            cmd('app', 'Repo', 'Open GitHub repository', openExternal('https://github.com/basnijholt/compose-farm'), icons.external_link),
+            cmd('app', 'GitHub Repo', 'Open GitHub repository', openExternal('https://github.com/basnijholt/compose-farm'), icons.external_link),
         ];
 
         // Add stack-specific actions if on a stack page
@@ -743,11 +744,6 @@ function playFabIntro() {
         input.focus();
     }
 
-    function close() {
-        dialog.close();
-        restoreTheme();
-    }
-
     function exec() {
         const cmd = filtered[selected];
         if (cmd) {
@@ -869,6 +865,119 @@ function initPage() {
     initMonacoEditors();
     initSaveButton();
     updateShortcutKeys();
+    initLiveStats();
+    initSharedActionMenu();
+    maybeRunStackAction();
+}
+
+function navigateToStack(stack, action = null) {
+    const url = action ? `/stack/${stack}?action=${action}` : `/stack/${stack}`;
+    window.location.href = url;
+}
+
+/**
+ * Initialize shared action menu for container rows
+ */
+function initSharedActionMenu() {
+    const menuEl = document.getElementById('shared-action-menu');
+    if (!menuEl) return;
+    if (menuEl.dataset.bound === '1') return;
+    menuEl.dataset.bound = '1';
+
+    let hoverTimeout = null;
+
+    function showMenuForButton(btn, stack) {
+        menuEl.dataset.stack = stack;
+
+        // Position menu relative to button
+        const rect = btn.getBoundingClientRect();
+        menuEl.classList.remove('hidden');
+        menuEl.style.visibility = 'hidden';
+        const menuRect = menuEl.getBoundingClientRect();
+
+        const left = rect.right - menuRect.width + window.scrollX;
+        const top = rect.bottom + window.scrollY;
+
+        menuEl.style.top = `${top}px`;
+        menuEl.style.left = `${left}px`;
+        menuEl.style.visibility = '';
+
+        if (typeof liveStats !== 'undefined') liveStats.dropdownOpen = true;
+    }
+
+    function closeMenu() {
+        menuEl.classList.add('hidden');
+        if (typeof liveStats !== 'undefined') liveStats.dropdownOpen = false;
+        menuEl.dataset.stack = '';
+    }
+
+    function scheduleClose() {
+        if (hoverTimeout) clearTimeout(hoverTimeout);
+        hoverTimeout = setTimeout(closeMenu, 100);
+    }
+
+    function cancelClose() {
+        if (hoverTimeout) {
+            clearTimeout(hoverTimeout);
+            hoverTimeout = null;
+        }
+    }
+
+    // Button hover: show menu (event delegation on tbody)
+    const tbody = document.getElementById('container-rows');
+    if (tbody) {
+        tbody.addEventListener('mouseenter', (e) => {
+            const btn = e.target.closest('button[onclick^="openActionMenu"]');
+            if (!btn) return;
+
+            // Extract stack from onclick attribute
+            const match = btn.getAttribute('onclick')?.match(/openActionMenu\(event,\s*'([^']+)'\)/);
+            if (!match) return;
+
+            cancelClose();
+            showMenuForButton(btn, match[1]);
+        }, true);
+
+        tbody.addEventListener('mouseleave', (e) => {
+            const btn = e.target.closest('button[onclick^="openActionMenu"]');
+            if (btn) scheduleClose();
+        }, true);
+    }
+
+    // Keep menu open while hovering over it
+    menuEl.addEventListener('mouseenter', cancelClose);
+    menuEl.addEventListener('mouseleave', scheduleClose);
+
+    // Click action in menu
+    menuEl.addEventListener('click', (e) => {
+        const link = e.target.closest('a[data-action]');
+        const stack = menuEl.dataset.stack;
+        if (!link || !stack) return;
+
+        e.preventDefault();
+        navigateToStack(stack, link.dataset.action);
+        closeMenu();
+    });
+
+    // Also support click on button (for touch/accessibility)
+    window.openActionMenu = function(event, stack) {
+        event.stopPropagation();
+        showMenuForButton(event.currentTarget, stack);
+    };
+
+    // Close on outside click
+    document.body.addEventListener('click', (e) => {
+        if (!menuEl.classList.contains('hidden') &&
+            !menuEl.contains(e.target) &&
+            !e.target.closest('button[onclick^="openActionMenu"]')) {
+            closeMenu();
+        }
+    });
+
+    // Close on Escape
+    document.body.addEventListener('keydown', (e) => {
+        if (e.key === 'Escape') closeMenu();
+    });
 }
 
 /**
@@ -889,6 +998,30 @@ function tryReconnectToTask(path) {
     });
 }
 
+function maybeRunStackAction() {
+    const params = new URLSearchParams(window.location.search);
+    const stackEl = document.querySelector('[data-stack-name]');
+    const stackName = stackEl?.dataset?.stackName;
+    if (!stackName) return;
+
+    const action = params.get('action');
+    if (!action) return;
+
+    const button = document.querySelector(`button[hx-post="/api/stack/${stackName}/${action}"]`);
+    if (!button) return;
+
+    params.delete('action');
+    const newQuery = params.toString();
+    const newUrl = newQuery ? `${window.location.pathname}?${newQuery}` : window.location.pathname;
+    history.replaceState({}, '', newUrl);
+
+    if (window.htmx) {
+        htmx.trigger(button, 'click');
+    } else {
+        button.click();
+    }
+}
+
 // Initialize on page load
 document.addEventListener('DOMContentLoaded', function() {
     initPage();
@@ -930,3 +1063,443 @@ document.body.addEventListener('htmx:afterRequest', function(evt) {
         // Not valid JSON, ignore
     }
 });
+
+// ============================================================================
+// LIVE STATS PAGE
+// ============================================================================
+
+// State persists across SPA navigation (intervals must be cleared on re-init)
+let liveStats = {
+    sortCol: 9,
+    sortAsc: false,
+    lastUpdate: 0,
+    dropdownOpen: false,
+    scrolling: false,
+    scrollTimer: null,
+    loadingHosts: new Set(),
+    eventsBound: false,
+    intervals: [],
+    updateCheckTimes: new Map(),
+    autoRefresh: true
+};
+
+const REFRESH_INTERVAL = 5000;
+const UPDATE_CHECK_TTL = 120000;
+const NUMERIC_COLS = new Set([8, 9, 10, 11]);  // uptime, cpu, mem, net
+
+function filterTable() {
+    const textFilter = document.getElementById('filter-input')?.value.toLowerCase() || '';
+    const hostFilter = document.getElementById('host-filter')?.value || '';
+    const rows = document.querySelectorAll('#container-rows tr');
+    let visible = 0;
+    let total = 0;
+
+    rows.forEach(row => {
+        // Skip loading/empty/error rows (they have colspan)
+        if (row.cells[0]?.colSpan > 1) return;
+        total++;
+        const matchesText = !textFilter || row.textContent.toLowerCase().includes(textFilter);
+        const matchesHost = !hostFilter || row.dataset.host === hostFilter;
+        const show = matchesText && matchesHost;
+        row.style.display = show ? '' : 'none';
+        if (show) visible++;
+    });
+
+    const countEl = document.getElementById('container-count');
+    if (countEl) {
+        const isFiltering = textFilter || hostFilter;
+        countEl.textContent = total > 0
+            ? (isFiltering ? `${visible} of ${total} containers` : `${total} containers`)
+            : '';
+    }
+}
+window.filterTable = filterTable;
+
+function sortTable(col) {
+    if (liveStats.sortCol === col) {
+        liveStats.sortAsc = !liveStats.sortAsc;
+    } else {
+        liveStats.sortCol = col;
+        liveStats.sortAsc = false;
+    }
+    updateSortIndicators();
+    doSort();
+}
+window.sortTable = sortTable;
+
+function updateSortIndicators() {
+    document.querySelectorAll('thead th').forEach((th, i) => {
+        const span = th.querySelector('.sort-indicator');
+        if (span) {
+            span.textContent = (i === liveStats.sortCol) ? (liveStats.sortAsc ? '↑' : '↓') : '';
+            span.style.opacity = (i === liveStats.sortCol) ? '1' : '0.3';
+        }
+    });
+}
+
+function doSort() {
+    const tbody = document.getElementById('container-rows');
+    if (!tbody) return;
+
+    const rows = Array.from(tbody.querySelectorAll('tr'));
+    if (rows.length === 0) return;
+    if (rows.length === 1 && rows[0].cells[0]?.colSpan > 1) return;  // Empty state row
+
+    const isNumeric = NUMERIC_COLS.has(liveStats.sortCol);
+    rows.sort((a, b) => {
+        // Pin placeholders/empty rows to the bottom
+        const aLoading = a.classList.contains('loading-row') || a.classList.contains('host-empty') || a.cells[0]?.colSpan > 1;
+        const bLoading = b.classList.contains('loading-row') || b.classList.contains('host-empty') || b.cells[0]?.colSpan > 1;
+        if (aLoading && !bLoading) return 1;
+        if (!aLoading && bLoading) return -1;
+        if (aLoading && bLoading) return 0;
+
+        const aVal = a.cells[liveStats.sortCol]?.dataset?.sort ?? '';
+        const bVal = b.cells[liveStats.sortCol]?.dataset?.sort ?? '';
+        const cmp = isNumeric ? aVal - bVal : aVal.localeCompare(bVal);
+        return liveStats.sortAsc ? cmp : -cmp;
+    });
+
+    let index = 1;
+    const fragment = document.createDocumentFragment();
+    rows.forEach((row) => {
+        if (row.cells.length > 1) {
+            row.cells[0].textContent = index++;
+        }
+        fragment.appendChild(row);
+    });
+    tbody.appendChild(fragment);
+}
+
+function isLoading() {
+    return liveStats.loadingHosts.size > 0;
+}
+
+function getLiveStatsHosts() {
+    const tbody = document.getElementById('container-rows');
+    if (!tbody) return [];
+    const dataHosts = tbody.dataset.hosts || '';
+    return dataHosts.split(',').map(h => h.trim()).filter(Boolean);
+}
+
+function buildHostRow(host, message, className) {
+    return (
+        `<tr class="${className}" data-host="${host}">` +
+        `<td colspan="12" class="text-center py-2">` +
+        `<span class="text-sm opacity-60">${message}</span>` +
+        `</td></tr>`
+    );
+}
+
+async function checkUpdatesForHost(host) {
+    // Update checks always run - they only update small cells, not disruptive
+    const last = liveStats.updateCheckTimes.get(host) || 0;
+    if (Date.now() - last < UPDATE_CHECK_TTL) return;
+
+    const cells = Array.from(
+        document.querySelectorAll(`tr[data-host="${host}"] td.update-cell[data-image][data-tag]`)
+    );
+    if (cells.length === 0) return;
+
+    const items = [];
+    const seen = new Set();
+    cells.forEach(cell => {
+        const image = decodeURIComponent(cell.dataset.image || '');
+        const tag = decodeURIComponent(cell.dataset.tag || '');
+        const key = `${image}:${tag}`;
+        if (!image || seen.has(key)) return;
+        seen.add(key);
+        items.push({ image, tag });
+    });
+
+    if (items.length === 0) return;
+
+    try {
+        const response = await fetch('/api/containers/check-updates', {
+            method: 'POST',
+            headers: { 'Content-Type': 'application/json' },
+            body: JSON.stringify({ items })
+        });
+        if (!response.ok) return;
+        const data = await response.json();
+        const results = Array.isArray(data?.results) ? data.results : [];
+        const htmlMap = new Map();
+        results.forEach(result => {
+            const key = `${result.image}:${result.tag}`;
+            htmlMap.set(key, result.html);
+        });
+
+        cells.forEach(cell => {
+            const image = decodeURIComponent(cell.dataset.image || '');
+            const tag = decodeURIComponent(cell.dataset.tag || '');
+            const key = `${image}:${tag}`;
+            const html = htmlMap.get(key);
+            if (html && cell.innerHTML !== html) {
+                cell.innerHTML = html;
+            }
+        });
+
+        liveStats.updateCheckTimes.set(host, Date.now());
+    } catch (e) {
+        console.error('Update check failed:', e);
+    }
+}
+
+function replaceHostRows(host, html) {
+    const tbody = document.getElementById('container-rows');
+    if (!tbody) return;
+
+    // Remove loading indicator for this host if present
+    const loadingRow = tbody.querySelector(`tr.loading-row[data-host="${host}"]`);
+    if (loadingRow) loadingRow.remove();
+
+    const template = document.createElement('template');
+    template.innerHTML = html.trim();
+    let newRows = Array.from(template.content.children).filter(el => el.tagName === 'TR');
+
+    if (newRows.length === 0) {
+        // Only show empty message if we don't have any rows for this host
+        const existing = tbody.querySelector(`tr[data-host="${host}"]:not(.loading-row)`);
+        if (!existing) {
+            template.innerHTML = buildHostRow(host, `No containers on ${host}`, 'host-empty');
+            newRows = Array.from(template.content.children);
+        }
+    }
+
+    // Track which IDs we've seen in this update
+    const newIds = new Set();
+
+    newRows.forEach(newRow => {
+        const id = newRow.id;
+        if (id) newIds.add(id);
+
+        if (id) {
+            const existing = document.getElementById(id);
+            if (existing) {
+                // Morph in place if Idiomorph is available, otherwise replace
+                if (typeof Idiomorph !== 'undefined') {
+                    Idiomorph.morph(existing, newRow);
+                } else {
+                    existing.replaceWith(newRow);
+                }
+
+                // Re-process HTMX if needed (though inner content usually carries attributes)
+                const morphedRow = document.getElementById(id);
+                if (window.htmx) htmx.process(morphedRow);
+
+                // Trigger refresh animation
+                if (morphedRow) {
+                    morphedRow.classList.add('row-updated');
+                    setTimeout(() => morphedRow.classList.remove('row-updated'), 500);
+                }
+            } else {
+                // New row - append (will be sorted later)
+                tbody.appendChild(newRow);
+                if (window.htmx) htmx.process(newRow);
+                // Animate new rows too
+                newRow.classList.add('row-updated');
+                setTimeout(() => newRow.classList.remove('row-updated'), 500);
+            }
+        } else {
+            // Fallback for rows without ID (like error/empty messages)
+            // Just append them, cleaning up previous generic rows handled below
+            tbody.appendChild(newRow);
+        }
+    });
+
+    // Remove orphaned rows for this host (rows that exist in DOM but not in new response)
+    // Be careful not to remove rows that were just added (if they lack IDs)
+    const currentHostRows = Array.from(tbody.querySelectorAll(`tr[data-host="${host}"]`));
+    currentHostRows.forEach(row => {
+        // Skip if it's one of the new rows we just appended (check presence in newRows?)
+        // Actually, if we just appended it, it is in DOM.
+        // We rely on ID matching.
+        // Error/Empty rows usually don't have ID, but we handle them by clearing old ones?
+        // Let's assume data rows have IDs.
+        if (row.id && !newIds.has(row.id)) {
+            row.remove();
+        }
+        // Also remove old empty/error messages if we now have data
+        if (!row.id && newRows.length > 0 && newRows[0].id) {
+             row.remove();
+        }
+    });
+
+    liveStats.loadingHosts.delete(host);
+    checkUpdatesForHost(host);
+    scheduleRowUpdate();
+}
+
+async function loadHostRows(host) {
+    liveStats.loadingHosts.add(host);
+    try {
+        const response = await fetch(`/api/containers/rows/${encodeURIComponent(host)}`);
+        const html = response.ok ? await response.text() : '';
+        replaceHostRows(host, html);
+    } catch (e) {
+        console.error(`Failed to load ${host}:`, e);
+        const msg = e.message || String(e);
+        // Fallback to simpler error display if replaceHostRows fails (e.g. Idiomorph missing)
+        try {
+            replaceHostRows(host, buildHostRow(host, `Error: ${msg}`, 'text-error'));
+        } catch (err2) {
+            // Last resort: find row and force innerHTML
+            const tbody = document.getElementById('container-rows');
+            const row = tbody?.querySelector(`tr[data-host="${host}"]`);
+            if (row) row.innerHTML = `<td colspan="12" class="text-center text-error">Error: ${msg}</td>`;
+        }
+    } finally {
+        liveStats.loadingHosts.delete(host);
+    }
+}
+
+function refreshLiveStats() {
+    if (liveStats.dropdownOpen || liveStats.scrolling) return;
+    const hosts = getLiveStatsHosts();
+    if (hosts.length === 0) return;
+    liveStats.lastUpdate = Date.now();
+    hosts.forEach(loadHostRows);
+}
+window.refreshLiveStats = refreshLiveStats;
+
+function toggleAutoRefresh() {
+    liveStats.autoRefresh = !liveStats.autoRefresh;
+    const timer = document.getElementById('refresh-timer');
+    if (timer) {
+        timer.classList.toggle('btn-error', !liveStats.autoRefresh);
+        timer.classList.toggle('btn-outline', liveStats.autoRefresh);
+    }
+    if (liveStats.autoRefresh) {
+        // Re-enabling: trigger immediate refresh
+        refreshLiveStats();
+    } else {
+        // Disabling: ensure update checks run for current data
+        const hosts = getLiveStatsHosts();
+        hosts.forEach(host => checkUpdatesForHost(host));
+    }
+}
+window.toggleAutoRefresh = toggleAutoRefresh;
+
+function initLiveStats() {
+    if (!document.getElementById('refresh-timer')) return;
+
+    // Clear previous intervals (important for SPA navigation)
+    liveStats.intervals.forEach(clearInterval);
+    liveStats.intervals = [];
+    liveStats.lastUpdate = Date.now();
+    liveStats.dropdownOpen = false;
+    liveStats.scrolling = false;
+    if (liveStats.scrollTimer) clearTimeout(liveStats.scrollTimer);
+    liveStats.scrollTimer = null;
+    liveStats.loadingHosts.clear();
+    liveStats.updateCheckTimes = new Map();
+    liveStats.autoRefresh = true;
+
+    if (!liveStats.eventsBound) {
+        liveStats.eventsBound = true;
+
+        // Dropdown pauses refresh
+        document.body.addEventListener('click', e => {
+            liveStats.dropdownOpen = !!e.target.closest('.dropdown');
+        });
+        document.body.addEventListener('focusin', e => {
+            if (e.target.closest('.dropdown')) liveStats.dropdownOpen = true;
+        });
+        document.body.addEventListener('focusout', () => {
+            setTimeout(() => {
+                liveStats.dropdownOpen = !!document.activeElement?.closest('.dropdown');
+            }, 150);
+        });
+        document.body.addEventListener('keydown', e => {
+            if (e.key === 'Escape') liveStats.dropdownOpen = false;
+        });
+
+        // Pause refresh while scrolling (helps on slow mobile browsers)
+        window.addEventListener('scroll', () => {
+            liveStats.scrolling = true;
+            if (liveStats.scrollTimer) clearTimeout(liveStats.scrollTimer);
+            liveStats.scrollTimer = setTimeout(() => {
+                liveStats.scrolling = false;
+            }, 200);
+        }, { passive: true });
+    }
+
+    // Auto-refresh every 5 seconds (skip if disabled, loading, or dropdown open)
+    liveStats.intervals.push(setInterval(() => {
+        if (!liveStats.autoRefresh) return;
+        if (liveStats.dropdownOpen || liveStats.scrolling || isLoading()) return;
+        refreshLiveStats();
+    }, REFRESH_INTERVAL));
+
+    // Timer display (updates every 100ms)
+    liveStats.intervals.push(setInterval(() => {
+        const timer = document.getElementById('refresh-timer');
+        if (!timer) {
+            liveStats.intervals.forEach(clearInterval);
+            return;
+        }
+
+        const loading = isLoading();
+        const paused = liveStats.dropdownOpen || liveStats.scrolling;
+        const elapsed = Date.now() - liveStats.lastUpdate;
+        window.refreshPaused = paused || loading || !liveStats.autoRefresh;
+
+        // Update refresh timer button
+        let text;
+        if (!liveStats.autoRefresh) {
+            text = 'OFF';
+        } else if (paused) {
+            text = '❚❚';
+        } else {
+            const remaining = Math.max(0, REFRESH_INTERVAL - elapsed);
+            text = loading ? '↻ …' : `↻ ${Math.ceil(remaining / 1000)}s`;
+        }
+        if (timer.textContent !== text) {
+            timer.textContent = text;
+        }
+
+        // Update "last updated" display
+        const lastUpdatedEl = document.getElementById('last-updated');
+        if (lastUpdatedEl) {
+            const secs = Math.floor(elapsed / 1000);
+            const updatedText = secs < 5 ? 'Updated just now' : `Updated ${secs}s ago`;
+            if (lastUpdatedEl.textContent !== updatedText) {
+                lastUpdatedEl.textContent = updatedText;
+            }
+        }
+    }, 100));
+
+    updateSortIndicators();
+    refreshLiveStats();
+}
+
+function scheduleRowUpdate() {
+    // Sort and filter immediately to prevent flicker
+    doSort();
+    filterTable();
+}
+
+// ============================================================================
+// STACKS BY HOST FILTER
+// ============================================================================
+
+function sbhFilter() {
+    const query = (document.getElementById('sbh-filter')?.value || '').toLowerCase();
+    const hostFilter = document.getElementById('sbh-host-select')?.value || '';
+
+    document.querySelectorAll('.sbh-group').forEach(group => {
+        if (hostFilter && group.dataset.h !== hostFilter) {
+            group.hidden = true;
+            return;
+        }
+
+        let visibleCount = 0;
+        group.querySelectorAll('li[data-s]').forEach(li => {
+            const show = !query || li.dataset.s.includes(query);
+            li.hidden = !show;
+            if (show) visibleCount++;
+        });
+        group.hidden = visibleCount === 0;
+    });
+}
+window.sbhFilter = sbhFilter;

src/compose_farm/web/templates/base.html

@@ -26,6 +26,23 @@
     </script>
 </head>
 <body class="min-h-screen bg-base-200">
+    <svg style="display: none">
+        <symbol id="icon-menu" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
+            <circle cx="12" cy="5" r="1" /><circle cx="12" cy="12" r="1" /><circle cx="12" cy="19" r="1" />
+        </symbol>
+        <symbol id="icon-restart" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
+            <path d="M4 4v5h.582m15.356 2A8.001 8.001 0 004.582 9m0 0H9m11 11v-5h-.581m0 0a8.003 8.003 0 01-15.357-2m15.357 2H15" />
+        </symbol>
+        <symbol id="icon-pull" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
+            <path d="M4 16v1a3 3 0 003 3h10a3 3 0 003-3v-1m-4-4l-4 4m0 0l-4-4m4 4V4" />
+        </symbol>
+        <symbol id="icon-update" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
+            <path d="M4 16v1a3 3 0 003 3h10a3 3 0 003-3v-1m-4-8l-4-4m0 0L8 8m4-4v12" />
+        </symbol>
+        <symbol id="icon-logs" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
+            <path d="M9 12h6m-6 4h6m2 5H7a2 2 0 01-2-2V5a2 2 0 012-2h5.586a1 1 0 01.707.293l5.414 5.414a1 1 0 01.293.707V19a2 2 0 01-2 2z" />
+        </symbol>
+    </svg>
     <div class="drawer lg:drawer-open">
         <input id="drawer-toggle" type="checkbox" class="drawer-toggle" />
 
@@ -80,6 +97,8 @@
 
     <!-- Scripts - HTMX first -->
     <script src="https://unpkg.com/htmx.org@2.0.4" data-vendor="htmx.js"></script>
+    <script src="https://unpkg.com/idiomorph/dist/idiomorph.min.js"></script>
+    <script src="https://unpkg.com/idiomorph/dist/idiomorph-ext.min.js"></script>
     <script src="https://cdn.jsdelivr.net/npm/@xterm/xterm@5.5.0/lib/xterm.js" data-vendor="xterm.js"></script>
     <script src="https://cdn.jsdelivr.net/npm/@xterm/addon-fit@0.10.0/lib/addon-fit.js" data-vendor="xterm-fit.js"></script>
     <script src="/static/app.js"></script>

src/compose_farm/web/templates/containers.html

@@ -0,0 +1,97 @@
+{% extends "base.html" %}
+{% from "partials/components.html" import page_header %}
+{% from "partials/icons.html" import refresh_cw %}
+{% block title %}Live Stats - Compose Farm{% endblock %}
+
+{% block content %}
+<div class="max-w-7xl">
+    {{ page_header("Live Stats", "All running containers across hosts") }}
+
+    {% if not glances_enabled %}
+    <div class="alert alert-warning mb-6">
+        <svg xmlns="http://www.w3.org/2000/svg" class="stroke-current shrink-0 h-6 w-6" fill="none" viewBox="0 0 24 24"><path stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M12 9v2m0 4h.01m-6.938 4h13.856c1.54 0 2.502-1.667 1.732-3L13.732 4c-.77-1.333-2.694-1.333-3.464 0L3.34 16c-.77 1.333.192 3 1.732 3z" /></svg>
+        <div>
+            <h3 class="font-bold">Glances not configured</h3>
+            <div class="text-xs">Add <code class="bg-base-300 px-1 rounded">glances_stack: glances</code> to your config and deploy Glances on all hosts.</div>
+        </div>
+    </div>
+    {% else %}
+
+    <!-- Action Bar -->
+    <div class="flex flex-wrap items-center gap-4 mb-6">
+        <div class="tooltip" data-tip="Refresh now">
+            <button class="btn btn-outline btn-sm" type="button" onclick="refreshLiveStats()">
+                {{ refresh_cw() }} Refresh
+            </button>
+        </div>
+        <div class="tooltip" data-tip="Click to toggle auto-refresh">
+            <button class="btn btn-outline btn-sm font-mono w-20 justify-center"
+                    id="refresh-timer" onclick="toggleAutoRefresh()">↻</button>
+        </div>
+        <input type="text" id="filter-input" placeholder="Filter containers..."
+               class="input input-bordered input-sm w-64" onkeyup="filterTable()">
+        <select id="host-filter" class="select select-bordered select-sm" onchange="filterTable()">
+            <option value="">All hosts</option>
+            {% for host in hosts %}<option value="{{ host }}">{{ host }}</option>{% endfor %}
+        </select>
+        <span id="container-count" class="text-sm text-base-content/60"></span>
+        <span id="last-updated" class="text-sm text-base-content/40 ml-auto"></span>
+    </div>
+
+    <!-- Container Table -->
+    <div class="card bg-base-100 shadow overflow-x-auto">
+        <table class="table table-zebra table-sm w-full">
+            <thead class="sticky top-0 bg-base-200">
+                <tr>
+                    <th class="w-8">#</th>
+                    <th class="cursor-pointer" onclick="sortTable(1)">Stack<span class="sort-indicator"></span></th>
+                    <th class="cursor-pointer" onclick="sortTable(2)">Service<span class="sort-indicator"></span></th>
+                    <th></th>
+                    <th class="cursor-pointer" onclick="sortTable(4)">Host<span class="sort-indicator"></span></th>
+                    <th class="cursor-pointer" onclick="sortTable(5)">Image<span class="sort-indicator"></span></th>
+                    <th class="w-16">Update</th>
+                    <th class="cursor-pointer" onclick="sortTable(7)">Status<span class="sort-indicator"></span></th>
+                    <th class="cursor-pointer text-right" onclick="sortTable(8)">Uptime<span class="sort-indicator"></span></th>
+                    <th class="cursor-pointer text-right" onclick="sortTable(9)">CPU<span class="sort-indicator"></span></th>
+                    <th class="cursor-pointer text-right" onclick="sortTable(10)">Mem<span class="sort-indicator"></span></th>
+                    <th class="cursor-pointer text-right" onclick="sortTable(11)">Net I/O<span class="sort-indicator"></span></th>
+                </tr>
+            </thead>
+            <tbody id="container-rows" data-hosts="{{ hosts | join(',') }}">
+                {% for host in hosts %}
+                <tr class="loading-row" data-host="{{ host }}">
+                    <td colspan="12" class="text-center py-2">
+                        <span class="loading loading-spinner loading-xs"></span>
+                        <span class="text-sm opacity-60">Loading {{ host }}...</span>
+                    </td>
+                </tr>
+                {% endfor %}
+            </tbody>
+        </table>
+    </div>
+    {% endif %}
+
+    <!-- Shared Action Menu -->
+    <ul id="shared-action-menu" class="menu menu-sm bg-base-200 rounded-box shadow-lg w-36 absolute z-50 p-2 hidden">
+        <li><a data-action="restart"><svg class="h-4 w-4"><use href="#icon-restart" /></svg>Restart</a></li>
+        <li><a data-action="pull"><svg class="h-4 w-4"><use href="#icon-pull" /></svg>Pull</a></li>
+        <li><a data-action="update"><svg class="h-4 w-4"><use href="#icon-update" /></svg>Update</a></li>
+        <li><a data-action="logs"><svg class="h-4 w-4"><use href="#icon-logs" /></svg>Logs</a></li>
+    </ul>
+</div>
+{% endblock %}
+
+{% block scripts %}
+{% if glances_enabled %}
+<style>
+.sort-indicator { display: inline-block; width: 1em; text-align: center; opacity: 0.5; }
+.high-usage { background-color: oklch(var(--er) / 0.15) !important; }
+/* Refresh animation */
+@keyframes row-pulse {
+    0% { background-color: oklch(var(--p) / 0.2); }
+    100% { background-color: transparent; }
+}
+.row-updated { animation: row-pulse 0.5s ease-out; }
+</style>
+{% endif %}
+{% endblock %}

src/compose_farm/web/templates/index.html

@@ -53,6 +53,13 @@
         {% include "partials/stacks_by_host.html" %}
     </div>
 
+    <!-- Host Resources (Glances) -->
+    <div id="glances-stats"
+         hx-get="/api/glances"
+         hx-trigger="load, cf:refresh from:body, every 30s"
+         hx-swap="innerHTML">
+    </div>
+
     <!-- Hosts Configuration -->
     {% call collapse("Hosts (" ~ (hosts | length) ~ ")", icon=server()) %}
         {% call table() %}

src/compose_farm/web/templates/partials/glances.html

@@ -0,0 +1,66 @@
+{# Glances resource stats display #}
+{% from "partials/icons.html" import cpu, memory_stick, gauge, server, activity, hard_drive, arrow_down_up, refresh_cw %}
+
+{% macro progress_bar(percent, color="primary") %}
+<div class="flex items-center gap-2 min-w-32">
+    <progress class="progress progress-{{ color }} flex-1" value="{{ percent }}" max="100"></progress>
+    <span class="text-xs w-10 text-right">{{ "%.1f"|format(percent) }}%</span>
+</div>
+{% endmacro %}
+
+{% macro format_rate(bytes_per_sec) %}
+{%- if bytes_per_sec >= 1048576 -%}
+{{ "%.1f"|format(bytes_per_sec / 1048576) }} MB/s
+{%- elif bytes_per_sec >= 1024 -%}
+{{ "%.1f"|format(bytes_per_sec / 1024) }} KB/s
+{%- else -%}
+{{ "%.0f"|format(bytes_per_sec) }} B/s
+{%- endif -%}
+{% endmacro %}
+
+{% macro host_row(host_stats) %}
+<tr>
+    <td class="font-medium">{{ server(14) }} {{ host_stats.host }}</td>
+    {% if host_stats.error %}
+    <td colspan="5" class="text-error text-xs">{{ host_stats.error }}</td>
+    {% else %}
+    <td>{{ progress_bar(host_stats.cpu_percent, "info") }}</td>
+    <td>{{ progress_bar(host_stats.mem_percent, "success") }}</td>
+    <td>{{ progress_bar(host_stats.disk_percent, "warning") }}</td>
+    <td class="text-xs font-mono">↓{{ format_rate(host_stats.net_rx_rate) }} ↑{{ format_rate(host_stats.net_tx_rate) }}</td>
+    <td class="text-sm">{{ "%.1f"|format(host_stats.load) }}</td>
+    {% endif %}
+</tr>
+{% endmacro %}
+
+<div class="card bg-base-100 shadow mt-4 mb-4">
+    <div class="card-body p-4">
+        <div class="flex items-center justify-between">
+            <h2 class="card-title text-base gap-2">{{ activity(18) }} Host Resources</h2>
+            <button class="btn btn-ghost btn-xs opacity-50 hover:opacity-100"
+                    hx-get="/api/glances" hx-target="#glances-stats" hx-swap="innerHTML"
+                    title="Refresh">
+                {{ refresh_cw(14) }}
+            </button>
+        </div>
+        <div class="overflow-x-auto">
+            <table class="table table-sm">
+                <thead>
+                    <tr>
+                        <th>Host</th>
+                        <th>{{ cpu(14) }} CPU</th>
+                        <th>{{ memory_stick(14) }} Memory</th>
+                        <th>{{ hard_drive(14) }} Disk</th>
+                        <th>{{ arrow_down_up(14) }} Net</th>
+                        <th>{{ gauge(14) }} Load</th>
+                    </tr>
+                </thead>
+                <tbody>
+                    {% for host_name, host_stats in stats.items() %}
+                    {{ host_row(host_stats) }}
+                    {% endfor %}
+                </tbody>
+            </table>
+        </div>
+    </div>
+</div>

src/compose_farm/web/templates/partials/icons.html

@@ -176,3 +176,46 @@
     <path d="M15 3h6v6"/><path d="M10 14 21 3"/><path d="M18 13v6a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2V8a2 2 0 0 1 2-2h6"/>
 </svg>
 {% endmacro %}
+
+{# Resource monitoring icons #}
+{% macro cpu(size=16) %}
+<svg xmlns="http://www.w3.org/2000/svg" width="{{ size }}" height="{{ size }}" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
+    <rect width="16" height="16" x="4" y="4" rx="2"/><rect width="6" height="6" x="9" y="9" rx="1"/><path d="M15 2v2"/><path d="M15 20v2"/><path d="M2 15h2"/><path d="M2 9h2"/><path d="M20 15h2"/><path d="M20 9h2"/><path d="M9 2v2"/><path d="M9 20v2"/>
+</svg>
+{% endmacro %}
+
+{% macro memory_stick(size=16) %}
+<svg xmlns="http://www.w3.org/2000/svg" width="{{ size }}" height="{{ size }}" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
+    <path d="M6 19v-3"/><path d="M10 19v-3"/><path d="M14 19v-3"/><path d="M18 19v-3"/><path d="M8 11V9"/><path d="M16 11V9"/><path d="M12 11V9"/><path d="M2 15h20"/><path d="M2 7a2 2 0 0 1 2-2h16a2 2 0 0 1 2 2v1.1a2 2 0 0 0 0 3.837V17a2 2 0 0 1-2 2H4a2 2 0 0 1-2-2v-5.1a2 2 0 0 0 0-3.837z"/>
+</svg>
+{% endmacro %}
+
+{% macro gauge(size=16) %}
+<svg xmlns="http://www.w3.org/2000/svg" width="{{ size }}" height="{{ size }}" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
+    <path d="m12 14 4-4"/><path d="M3.34 19a10 10 0 1 1 17.32 0"/>
+</svg>
+{% endmacro %}
+
+{% macro activity(size=16) %}
+<svg xmlns="http://www.w3.org/2000/svg" width="{{ size }}" height="{{ size }}" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
+    <path d="M22 12h-2.48a2 2 0 0 0-1.93 1.46l-2.35 8.36a.25.25 0 0 1-.48 0L9.24 2.18a.25.25 0 0 0-.48 0l-2.35 8.36A2 2 0 0 1 4.49 12H2"/>
+</svg>
+{% endmacro %}
+
+{% macro arrow_down_up(size=16) %}
+<svg xmlns="http://www.w3.org/2000/svg" width="{{ size }}" height="{{ size }}" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
+    <path d="m3 16 4 4 4-4"/><path d="M7 20V4"/><path d="m21 8-4-4-4 4"/><path d="M17 4v16"/>
+</svg>
+{% endmacro %}
+
+{% macro hard_drive(size=16) %}
+<svg xmlns="http://www.w3.org/2000/svg" width="{{ size }}" height="{{ size }}" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
+    <line x1="22" x2="2" y1="12" y2="12"/><path d="M5.45 5.11 2 12v6a2 2 0 0 0 2 2h16a2 2 0 0 0 2-2v-6l-3.45-6.89A2 2 0 0 0 16.76 4H7.24a2 2 0 0 0-1.79 1.11z"/><line x1="6" x2="6.01" y1="16" y2="16"/><line x1="10" x2="10.01" y1="16" y2="16"/>
+</svg>
+{% endmacro %}
+
+{% macro box(size=16) %}
+<svg xmlns="http://www.w3.org/2000/svg" width="{{ size }}" height="{{ size }}" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round">
+    <path d="M21 8a2 2 0 0 0-1-1.73l-7-4a2 2 0 0 0-2 0l-7 4A2 2 0 0 0 3 8v8a2 2 0 0 0 1 1.73l7 4a2 2 0 0 0 2 0l7-4A2 2 0 0 0 21 16Z"/><path d="m3.3 7 8.7 5 8.7-5"/><path d="M12 22V12"/>
+</svg>
+{% endmacro %}

src/compose_farm/web/templates/partials/sidebar.html

@@ -1,8 +1,9 @@
-{% from "partials/icons.html" import home, search, terminal %}
+{% from "partials/icons.html" import home, search, terminal, box %}
 <!-- Navigation Links -->
 <div class="mb-4">
     <ul class="menu" hx-boost="true" hx-target="#main-content" hx-select="#main-content" hx-swap="outerHTML">
         <li><a href="/" class="font-semibold">{{ home() }} Dashboard</a></li>
+        <li><a href="/live-stats" class="font-semibold">{{ box() }} Live Stats</a></li>
         <li><a href="/console" class="font-semibold">{{ terminal() }} Console</a></li>
     </ul>
 </div>

src/compose_farm/web/templates/partials/stacks_by_host.html

@@ -20,20 +20,4 @@
     {% else %}
     <p class="text-base-content/60 italic">No stacks currently running.</p>
     {% endfor %}
-    <script>
-    function sbhFilter() {
-        const q = (document.getElementById('sbh-filter')?.value || '').toLowerCase();
-        const h = document.getElementById('sbh-host-select')?.value || '';
-        document.querySelectorAll('.sbh-group').forEach(g => {
-            if (h && g.dataset.h !== h) { g.hidden = true; return; }
-            let n = 0;
-            g.querySelectorAll('li[data-s]').forEach(li => {
-                const show = !q || li.dataset.s.includes(q);
-                li.hidden = !show;
-                if (show) n++;
-            });
-            g.hidden = !n;
-        });
-    }
-    </script>
 {% endcall %}

src/compose_farm/web/templates/stack.html

@@ -4,7 +4,7 @@
 {% block title %}{{ name }} - Compose Farm{% endblock %}
 
 {% block content %}
-<div class="max-w-5xl" data-services="{{ services | join(',') }}" data-containers='{{ containers | tojson }}' data-website-urls='{{ website_urls | tojson }}'>
+<div class="max-w-5xl" data-stack-name="{{ name }}" data-services="{{ services | join(',') }}" data-containers='{{ containers | tojson }}' data-website-urls='{{ website_urls | tojson }}'>
     <div class="mb-6">
         <h1 class="text-3xl font-bold rainbow-hover">{{ name }}</h1>
         <div class="flex flex-wrap items-center gap-2 mt-2">

tests/test_config_cmd.py

@@ -228,99 +228,3 @@ class TestConfigValidate:
         # Error goes to stderr
         output = result.stdout + (result.stderr or "")
         assert "Config file not found" in output or "not found" in output.lower()
-
-
-class TestConfigExample:
-    """Tests for cf config example command."""
-
-    def test_example_list(self, runner: CliRunner) -> None:
-        result = runner.invoke(app, ["config", "example", "--list"])
-        assert result.exit_code == 0
-        assert "whoami" in result.stdout
-        assert "nginx" in result.stdout
-        assert "postgres" in result.stdout
-        assert "full" in result.stdout
-
-    def test_example_whoami(self, runner: CliRunner, tmp_path: Path) -> None:
-        result = runner.invoke(app, ["config", "example", "whoami", "-o", str(tmp_path)])
-        assert result.exit_code == 0
-        assert "Example 'whoami' created" in result.stdout
-        assert (tmp_path / "whoami" / "compose.yaml").exists()
-        assert (tmp_path / "whoami" / ".env").exists()
-
-    def test_example_full(self, runner: CliRunner, tmp_path: Path) -> None:
-        result = runner.invoke(app, ["config", "example", "full", "-o", str(tmp_path)])
-        assert result.exit_code == 0
-        assert "Example 'full' created" in result.stdout
-        assert (tmp_path / "compose-farm.yaml").exists()
-        assert (tmp_path / "traefik" / "compose.yaml").exists()
-        assert (tmp_path / "whoami" / "compose.yaml").exists()
-        assert (tmp_path / "nginx" / "compose.yaml").exists()
-        assert (tmp_path / "postgres" / "compose.yaml").exists()
-
-    def test_example_unknown(self, runner: CliRunner, tmp_path: Path) -> None:
-        result = runner.invoke(app, ["config", "example", "unknown", "-o", str(tmp_path)])
-        assert result.exit_code == 1
-        output = result.stdout + (result.stderr or "")
-        assert "Unknown example" in output
-
-    def test_example_force_overwrites(self, runner: CliRunner, tmp_path: Path) -> None:
-        # Create first time
-        runner.invoke(app, ["config", "example", "whoami", "-o", str(tmp_path)])
-        # Overwrite with force
-        result = runner.invoke(app, ["config", "example", "whoami", "-o", str(tmp_path), "-f"])
-        assert result.exit_code == 0
-
-    def test_example_prompts_on_existing(self, runner: CliRunner, tmp_path: Path) -> None:
-        # Create first time
-        runner.invoke(app, ["config", "example", "whoami", "-o", str(tmp_path)])
-        # Try again without force, decline
-        result = runner.invoke(
-            app, ["config", "example", "whoami", "-o", str(tmp_path)], input="n\n"
-        )
-        assert result.exit_code == 0
-        assert "Aborted" in result.stdout
-
-
-class TestExamplesModule:
-    """Tests for the examples module."""
-
-    def test_list_example_files_whoami(self) -> None:
-        from compose_farm.examples import list_example_files
-
-        files = list_example_files("whoami")
-        file_names = [f for f, _ in files]
-        assert ".env" in file_names
-        assert "compose.yaml" in file_names
-
-    def test_list_example_files_full(self) -> None:
-        from compose_farm.examples import list_example_files
-
-        files = list_example_files("full")
-        file_names = [f for f, _ in files]
-        assert "compose-farm.yaml" in file_names
-        assert "traefik/compose.yaml" in file_names
-        assert "whoami/compose.yaml" in file_names
-
-    def test_list_example_files_unknown(self) -> None:
-        from compose_farm.examples import list_example_files
-
-        with pytest.raises(ValueError, match="Unknown example"):
-            list_example_files("unknown")
-
-    def test_examples_dict(self) -> None:
-        from compose_farm.examples import EXAMPLES, SINGLE_STACK_EXAMPLES
-
-        assert "whoami" in EXAMPLES
-        assert "full" in EXAMPLES
-        assert "full" not in SINGLE_STACK_EXAMPLES
-        assert "whoami" in SINGLE_STACK_EXAMPLES
-
-
-class TestConfigInitDiscover:
-    """Tests for cf config init --discover."""
-
-    def test_discover_option_exists(self, runner: CliRunner) -> None:
-        result = runner.invoke(app, ["config", "init", "--help"])
-        assert "--discover" in result.stdout
-        assert "-d" in result.stdout

tests/test_containers.py

@@ -0,0 +1,269 @@
+"""Tests for Containers page routes."""
+
+from pathlib import Path
+from unittest.mock import AsyncMock, patch
+
+import pytest
+from fastapi.testclient import TestClient
+
+from compose_farm.config import Config, Host
+from compose_farm.glances import ContainerStats
+from compose_farm.web.app import create_app
+from compose_farm.web.routes.containers import (
+    _format_bytes,
+    _infer_stack_service,
+    _parse_image,
+    _parse_uptime_seconds,
+)
+
+# Byte size constants for tests
+KB = 1024
+MB = KB * 1024
+GB = MB * 1024
+
+
+class TestFormatBytes:
+    """Tests for _format_bytes function (uses humanize library)."""
+
+    def test_bytes(self) -> None:
+        assert _format_bytes(500) == "500 Bytes"
+        assert _format_bytes(0) == "0 Bytes"
+
+    def test_kilobytes(self) -> None:
+        assert _format_bytes(KB) == "1.0 KiB"
+        assert _format_bytes(KB * 5) == "5.0 KiB"
+        assert _format_bytes(KB + 512) == "1.5 KiB"
+
+    def test_megabytes(self) -> None:
+        assert _format_bytes(MB) == "1.0 MiB"
+        assert _format_bytes(MB * 100) == "100.0 MiB"
+        assert _format_bytes(MB * 512) == "512.0 MiB"
+
+    def test_gigabytes(self) -> None:
+        assert _format_bytes(GB) == "1.0 GiB"
+        assert _format_bytes(GB * 2) == "2.0 GiB"
+
+
+class TestParseImage:
+    """Tests for _parse_image function."""
+
+    def test_simple_image_with_tag(self) -> None:
+        assert _parse_image("nginx:latest") == ("nginx", "latest")
+        assert _parse_image("redis:7") == ("redis", "7")
+
+    def test_image_without_tag(self) -> None:
+        assert _parse_image("nginx") == ("nginx", "latest")
+
+    def test_registry_image(self) -> None:
+        assert _parse_image("ghcr.io/user/repo:v1.0") == ("ghcr.io/user/repo", "v1.0")
+        assert _parse_image("docker.io/library/nginx:alpine") == (
+            "docker.io/library/nginx",
+            "alpine",
+        )
+
+    def test_image_with_port_in_registry(self) -> None:
+        # Registry with port should not be confused with tag
+        assert _parse_image("localhost:5000/myimage") == ("localhost:5000/myimage", "latest")
+
+
+class TestParseUptimeSeconds:
+    """Tests for _parse_uptime_seconds function."""
+
+    def test_seconds(self) -> None:
+        assert _parse_uptime_seconds("17 seconds") == 17
+        assert _parse_uptime_seconds("1 second") == 1
+
+    def test_minutes(self) -> None:
+        assert _parse_uptime_seconds("5 minutes") == 300
+        assert _parse_uptime_seconds("1 minute") == 60
+
+    def test_hours(self) -> None:
+        assert _parse_uptime_seconds("2 hours") == 7200
+        assert _parse_uptime_seconds("an hour") == 3600
+        assert _parse_uptime_seconds("1 hour") == 3600
+
+    def test_days(self) -> None:
+        assert _parse_uptime_seconds("3 days") == 259200
+        assert _parse_uptime_seconds("a day") == 86400
+
+    def test_empty(self) -> None:
+        assert _parse_uptime_seconds("") == 0
+        assert _parse_uptime_seconds("-") == 0
+
+
+class TestInferStackService:
+    """Tests for _infer_stack_service function."""
+
+    def test_underscore_separator(self) -> None:
+        assert _infer_stack_service("mystack_web_1") == ("mystack", "web")
+        assert _infer_stack_service("app_db_1") == ("app", "db")
+
+    def test_hyphen_separator(self) -> None:
+        assert _infer_stack_service("mystack-web-1") == ("mystack", "web")
+        assert _infer_stack_service("compose-farm-api-1") == ("compose", "farm-api")
+
+    def test_simple_name(self) -> None:
+        # No separator - use name for both
+        assert _infer_stack_service("nginx") == ("nginx", "nginx")
+        assert _infer_stack_service("traefik") == ("traefik", "traefik")
+
+    def test_single_part_with_separator(self) -> None:
+        # Edge case: separator with empty second part
+        assert _infer_stack_service("single_") == ("single", "")
+
+
+class TestContainersPage:
+    """Tests for containers page endpoint."""
+
+    @pytest.fixture
+    def client(self) -> TestClient:
+        app = create_app()
+        return TestClient(app)
+
+    @pytest.fixture
+    def mock_config(self) -> Config:
+        return Config(
+            compose_dir=Path("/opt/compose"),
+            hosts={
+                "nas": Host(address="192.168.1.6"),
+                "nuc": Host(address="192.168.1.2"),
+            },
+            stacks={"test": "nas"},
+            glances_stack="glances",
+        )
+
+    def test_containers_page_without_glances(self, client: TestClient) -> None:
+        """Test containers page shows warning when Glances not configured."""
+        with patch("compose_farm.web.routes.containers.get_config") as mock:
+            mock.return_value = Config(
+                compose_dir=Path("/opt/compose"),
+                hosts={"nas": Host(address="192.168.1.6")},
+                stacks={"test": "nas"},
+                glances_stack=None,
+            )
+            response = client.get("/live-stats")
+
+        assert response.status_code == 200
+        assert "Glances not configured" in response.text
+
+    def test_containers_page_with_glances(self, client: TestClient, mock_config: Config) -> None:
+        """Test containers page loads when Glances is configured."""
+        with patch("compose_farm.web.routes.containers.get_config") as mock:
+            mock.return_value = mock_config
+            response = client.get("/live-stats")
+
+        assert response.status_code == 200
+        assert "Live Stats" in response.text
+        assert "container-rows" in response.text
+
+
+class TestContainersRowsAPI:
+    """Tests for containers rows HTML endpoint."""
+
+    @pytest.fixture
+    def client(self) -> TestClient:
+        app = create_app()
+        return TestClient(app)
+
+    def test_rows_without_glances(self, client: TestClient) -> None:
+        """Test rows endpoint returns error when Glances not configured."""
+        with patch("compose_farm.web.routes.containers.get_config") as mock:
+            mock.return_value = Config(
+                compose_dir=Path("/opt/compose"),
+                hosts={"nas": Host(address="192.168.1.6")},
+                stacks={"test": "nas"},
+                glances_stack=None,
+            )
+            response = client.get("/api/containers/rows")
+
+        assert response.status_code == 200
+        assert "Glances not configured" in response.text
+
+    def test_rows_returns_html(self, client: TestClient) -> None:
+        """Test rows endpoint returns HTML table rows."""
+        mock_containers = [
+            ContainerStats(
+                name="nginx",
+                host="nas",
+                status="running",
+                image="nginx:latest",
+                cpu_percent=5.5,
+                memory_usage=104857600,
+                memory_limit=1073741824,
+                memory_percent=9.77,
+                network_rx=1000,
+                network_tx=500,
+                uptime="2 hours",
+                ports="80->80/tcp",
+                engine="docker",
+                stack="web",
+                service="nginx",
+            ),
+        ]
+
+        with (
+            patch("compose_farm.web.routes.containers.get_config") as mock_config,
+            patch(
+                "compose_farm.web.routes.containers.fetch_all_container_stats",
+                new_callable=AsyncMock,
+            ) as mock_fetch,
+        ):
+            mock_config.return_value = Config(
+                compose_dir=Path("/opt/compose"),
+                hosts={"nas": Host(address="192.168.1.6")},
+                stacks={"test": "nas"},
+                glances_stack="glances",
+            )
+            mock_fetch.return_value = mock_containers
+
+            response = client.get("/api/containers/rows")
+
+        assert response.status_code == 200
+        assert "<tr " in response.text  # <tr id="..."> has attributes
+        assert "nginx" in response.text
+        assert "running" in response.text
+
+    def test_rows_have_data_sort_attributes(self, client: TestClient) -> None:
+        """Test rows have data-sort attributes for client-side sorting."""
+        mock_containers = [
+            ContainerStats(
+                name="alpha",
+                host="nas",
+                status="running",
+                image="nginx:latest",
+                cpu_percent=10.0,
+                memory_usage=100,
+                memory_limit=1000,
+                memory_percent=10.0,
+                network_rx=100,
+                network_tx=100,
+                uptime="1 hour",
+                ports="",
+                engine="docker",
+                stack="alpha",
+                service="web",
+            ),
+        ]
+
+        with (
+            patch("compose_farm.web.routes.containers.get_config") as mock_config,
+            patch(
+                "compose_farm.web.routes.containers.fetch_all_container_stats",
+                new_callable=AsyncMock,
+            ) as mock_fetch,
+        ):
+            mock_config.return_value = Config(
+                compose_dir=Path("/opt/compose"),
+                hosts={"nas": Host(address="192.168.1.6")},
+                stacks={"test": "nas"},
+                glances_stack="glances",
+            )
+            mock_fetch.return_value = mock_containers
+
+            response = client.get("/api/containers/rows")
+            assert response.status_code == 200
+            # Check that cells have data-sort attributes
+            assert 'data-sort="alpha"' in response.text  # stack
+            assert 'data-sort="web"' in response.text  # service
+            assert 'data-sort="3600"' in response.text  # uptime (1 hour = 3600s)
+            assert 'data-sort="10' in response.text  # cpu

tests/test_executor.py

@@ -11,6 +11,7 @@ from compose_farm.executor import (
     _run_local_command,
     check_networks_exist,
     check_paths_exist,
+    get_running_stacks_on_host,
     is_local,
     run_command,
     run_compose,
@@ -239,3 +240,31 @@ class TestCheckNetworksExist:
 
         result = await check_networks_exist(config, "local", [])
         assert result == {}
+
+
+@linux_only
+class TestGetRunningStacksOnHost:
+    """Tests for get_running_stacks_on_host function (requires Docker)."""
+
+    async def test_returns_set_of_stacks(self, tmp_path: Path) -> None:
+        """Function returns a set of stack names."""
+        config = Config(
+            compose_dir=tmp_path,
+            hosts={"local": Host(address="localhost")},
+            stacks={},
+        )
+
+        result = await get_running_stacks_on_host(config, "local")
+        assert isinstance(result, set)
+
+    async def test_filters_empty_lines(self, tmp_path: Path) -> None:
+        """Empty project names are filtered out."""
+        config = Config(
+            compose_dir=tmp_path,
+            hosts={"local": Host(address="localhost")},
+            stacks={},
+        )
+
+        # Result should not contain empty strings
+        result = await get_running_stacks_on_host(config, "local")
+        assert "" not in result

tests/test_glances.py

@@ -0,0 +1,349 @@
+"""Tests for Glances integration."""
+
+from pathlib import Path
+from unittest.mock import AsyncMock, patch
+
+import httpx
+import pytest
+
+from compose_farm.config import Config, Host
+from compose_farm.glances import (
+    DEFAULT_GLANCES_PORT,
+    ContainerStats,
+    HostStats,
+    fetch_all_container_stats,
+    fetch_all_host_stats,
+    fetch_container_stats,
+    fetch_host_stats,
+)
+
+
+class TestHostStats:
+    """Tests for HostStats dataclass."""
+
+    def test_host_stats_creation(self) -> None:
+        stats = HostStats(
+            host="nas",
+            cpu_percent=25.5,
+            mem_percent=50.0,
+            swap_percent=10.0,
+            load=2.5,
+            disk_percent=75.0,
+        )
+        assert stats.host == "nas"
+        assert stats.cpu_percent == 25.5
+        assert stats.mem_percent == 50.0
+        assert stats.disk_percent == 75.0
+        assert stats.error is None
+
+    def test_host_stats_from_error(self) -> None:
+        stats = HostStats.from_error("nas", "Connection refused")
+        assert stats.host == "nas"
+        assert stats.cpu_percent == 0
+        assert stats.mem_percent == 0
+        assert stats.error == "Connection refused"
+
+
+class TestFetchHostStats:
+    """Tests for fetch_host_stats function."""
+
+    @pytest.mark.asyncio
+    async def test_fetch_host_stats_success(self) -> None:
+        quicklook_response = httpx.Response(
+            200,
+            json={
+                "cpu": 25.5,
+                "mem": 50.0,
+                "swap": 5.0,
+                "load": 2.5,
+            },
+        )
+        fs_response = httpx.Response(
+            200,
+            json=[
+                {"mnt_point": "/", "percent": 65.0},
+                {"mnt_point": "/mnt/data", "percent": 80.0},
+            ],
+        )
+
+        async def mock_get(url: str) -> httpx.Response:
+            if "quicklook" in url:
+                return quicklook_response
+            return fs_response
+
+        with patch("httpx.AsyncClient") as mock_client:
+            mock_client.return_value.__aenter__ = AsyncMock(return_value=mock_client.return_value)
+            mock_client.return_value.__aexit__ = AsyncMock(return_value=None)
+            mock_client.return_value.get = AsyncMock(side_effect=mock_get)
+
+            stats = await fetch_host_stats("nas", "192.168.1.6")
+
+        assert stats.host == "nas"
+        assert stats.cpu_percent == 25.5
+        assert stats.mem_percent == 50.0
+        assert stats.swap_percent == 5.0
+        assert stats.load == 2.5
+        assert stats.disk_percent == 65.0  # Root filesystem
+        assert stats.error is None
+
+    @pytest.mark.asyncio
+    async def test_fetch_host_stats_http_error(self) -> None:
+        mock_response = httpx.Response(500)
+
+        with patch("httpx.AsyncClient") as mock_client:
+            mock_client.return_value.__aenter__ = AsyncMock(return_value=mock_client.return_value)
+            mock_client.return_value.__aexit__ = AsyncMock(return_value=None)
+            mock_client.return_value.get = AsyncMock(return_value=mock_response)
+
+            stats = await fetch_host_stats("nas", "192.168.1.6")
+
+        assert stats.host == "nas"
+        assert stats.error == "HTTP 500"
+        assert stats.cpu_percent == 0
+
+    @pytest.mark.asyncio
+    async def test_fetch_host_stats_timeout(self) -> None:
+        with patch("httpx.AsyncClient") as mock_client:
+            mock_client.return_value.__aenter__ = AsyncMock(return_value=mock_client.return_value)
+            mock_client.return_value.__aexit__ = AsyncMock(return_value=None)
+            mock_client.return_value.get = AsyncMock(side_effect=httpx.TimeoutException("timeout"))
+
+            stats = await fetch_host_stats("nas", "192.168.1.6")
+
+        assert stats.host == "nas"
+        assert stats.error == "timeout"
+
+    @pytest.mark.asyncio
+    async def test_fetch_host_stats_connection_error(self) -> None:
+        with patch("httpx.AsyncClient") as mock_client:
+            mock_client.return_value.__aenter__ = AsyncMock(return_value=mock_client.return_value)
+            mock_client.return_value.__aexit__ = AsyncMock(return_value=None)
+            mock_client.return_value.get = AsyncMock(
+                side_effect=httpx.ConnectError("Connection refused")
+            )
+
+            stats = await fetch_host_stats("nas", "192.168.1.6")
+
+        assert stats.host == "nas"
+        assert stats.error is not None
+        assert "Connection refused" in stats.error
+
+
+class TestFetchAllHostStats:
+    """Tests for fetch_all_host_stats function."""
+
+    @pytest.mark.asyncio
+    async def test_fetch_all_host_stats(self) -> None:
+        config = Config(
+            compose_dir=Path("/opt/compose"),
+            hosts={
+                "nas": Host(address="192.168.1.6"),
+                "nuc": Host(address="192.168.1.2"),
+            },
+            stacks={"test": "nas"},
+        )
+
+        quicklook_response = httpx.Response(
+            200,
+            json={
+                "cpu": 25.5,
+                "mem": 50.0,
+                "swap": 5.0,
+                "load": 2.5,
+            },
+        )
+        fs_response = httpx.Response(
+            200,
+            json=[{"mnt_point": "/", "percent": 70.0}],
+        )
+
+        async def mock_get(url: str) -> httpx.Response:
+            if "quicklook" in url:
+                return quicklook_response
+            return fs_response
+
+        with patch("httpx.AsyncClient") as mock_client:
+            mock_client.return_value.__aenter__ = AsyncMock(return_value=mock_client.return_value)
+            mock_client.return_value.__aexit__ = AsyncMock(return_value=None)
+            mock_client.return_value.get = AsyncMock(side_effect=mock_get)
+
+            stats = await fetch_all_host_stats(config)
+
+        assert "nas" in stats
+        assert "nuc" in stats
+        assert stats["nas"].cpu_percent == 25.5
+        assert stats["nuc"].cpu_percent == 25.5
+        assert stats["nas"].disk_percent == 70.0
+
+
+class TestDefaultPort:
+    """Tests for default Glances port constant."""
+
+    def test_default_port(self) -> None:
+        assert DEFAULT_GLANCES_PORT == 61208
+
+
+class TestContainerStats:
+    """Tests for ContainerStats dataclass."""
+
+    def test_container_stats_creation(self) -> None:
+        stats = ContainerStats(
+            name="nginx",
+            host="nas",
+            status="running",
+            image="nginx:latest",
+            cpu_percent=5.5,
+            memory_usage=104857600,  # 100MB
+            memory_limit=1073741824,  # 1GB
+            memory_percent=9.77,
+            network_rx=1000000,
+            network_tx=500000,
+            uptime="2 hours",
+            ports="80->80/tcp",
+            engine="docker",
+        )
+        assert stats.name == "nginx"
+        assert stats.host == "nas"
+        assert stats.cpu_percent == 5.5
+
+
+class TestFetchContainerStats:
+    """Tests for fetch_container_stats function."""
+
+    @pytest.mark.asyncio
+    async def test_fetch_container_stats_success(self) -> None:
+        mock_response = httpx.Response(
+            200,
+            json=[
+                {
+                    "name": "nginx",
+                    "status": "running",
+                    "image": ["nginx:latest"],
+                    "cpu_percent": 5.5,
+                    "memory_usage": 104857600,
+                    "memory_limit": 1073741824,
+                    "network": {"cumulative_rx": 1000, "cumulative_tx": 500},
+                    "uptime": "2 hours",
+                    "ports": "80->80/tcp",
+                    "engine": "docker",
+                },
+                {
+                    "name": "redis",
+                    "status": "running",
+                    "image": ["redis:7"],
+                    "cpu_percent": 1.2,
+                    "memory_usage": 52428800,
+                    "memory_limit": 1073741824,
+                    "network": {},
+                    "uptime": "3 hours",
+                    "ports": "",
+                    "engine": "docker",
+                },
+            ],
+        )
+
+        with patch("httpx.AsyncClient") as mock_client:
+            mock_client.return_value.__aenter__ = AsyncMock(return_value=mock_client.return_value)
+            mock_client.return_value.__aexit__ = AsyncMock(return_value=None)
+            mock_client.return_value.get = AsyncMock(return_value=mock_response)
+
+            containers, error = await fetch_container_stats("nas", "192.168.1.6")
+
+        assert error is None
+        assert containers is not None
+        assert len(containers) == 2
+        assert containers[0].name == "nginx"
+        assert containers[0].host == "nas"
+        assert containers[0].cpu_percent == 5.5
+        assert containers[1].name == "redis"
+
+    @pytest.mark.asyncio
+    async def test_fetch_container_stats_empty_on_error(self) -> None:
+        with patch("httpx.AsyncClient") as mock_client:
+            mock_client.return_value.__aenter__ = AsyncMock(return_value=mock_client.return_value)
+            mock_client.return_value.__aexit__ = AsyncMock(return_value=None)
+            mock_client.return_value.get = AsyncMock(side_effect=httpx.TimeoutException("timeout"))
+
+            containers, error = await fetch_container_stats("nas", "192.168.1.6")
+
+        assert containers is None
+        assert error == "Connection timed out"
+
+    @pytest.mark.asyncio
+    async def test_fetch_container_stats_handles_string_image(self) -> None:
+        """Test that image field works as string (not just list)."""
+        mock_response = httpx.Response(
+            200,
+            json=[
+                {
+                    "name": "test",
+                    "status": "running",
+                    "image": "myimage:v1",  # String instead of list
+                    "cpu_percent": 0,
+                    "memory_usage": 0,
+                    "memory_limit": 1,
+                    "network": {},
+                    "uptime": "",
+                    "ports": "",
+                    "engine": "docker",
+                },
+            ],
+        )
+
+        with patch("httpx.AsyncClient") as mock_client:
+            mock_client.return_value.__aenter__ = AsyncMock(return_value=mock_client.return_value)
+            mock_client.return_value.__aexit__ = AsyncMock(return_value=None)
+            mock_client.return_value.get = AsyncMock(return_value=mock_response)
+
+            containers, error = await fetch_container_stats("nas", "192.168.1.6")
+
+        assert error is None
+        assert containers is not None
+        assert len(containers) == 1
+        assert containers[0].image == "myimage:v1"
+
+
+class TestFetchAllContainerStats:
+    """Tests for fetch_all_container_stats function."""
+
+    @pytest.mark.asyncio
+    async def test_fetch_all_container_stats(self) -> None:
+        config = Config(
+            compose_dir=Path("/opt/compose"),
+            hosts={
+                "nas": Host(address="192.168.1.6"),
+                "nuc": Host(address="192.168.1.2"),
+            },
+            stacks={"test": "nas"},
+        )
+
+        mock_response = httpx.Response(
+            200,
+            json=[
+                {
+                    "name": "nginx",
+                    "status": "running",
+                    "image": ["nginx:latest"],
+                    "cpu_percent": 5.5,
+                    "memory_usage": 104857600,
+                    "memory_limit": 1073741824,
+                    "network": {},
+                    "uptime": "2 hours",
+                    "ports": "",
+                    "engine": "docker",
+                },
+            ],
+        )
+
+        with patch("httpx.AsyncClient") as mock_client:
+            mock_client.return_value.__aenter__ = AsyncMock(return_value=mock_client.return_value)
+            mock_client.return_value.__aexit__ = AsyncMock(return_value=None)
+            mock_client.return_value.get = AsyncMock(return_value=mock_response)
+
+            containers = await fetch_all_container_stats(config)
+
+        # 2 hosts x 1 container each = 2 containers
+        assert len(containers) == 2
+        hosts = {c.host for c in containers}
+        assert "nas" in hosts
+        assert "nuc" in hosts

tests/test_logs.py

@@ -10,8 +10,8 @@ import pytest
 from compose_farm.config import Config, Host
 from compose_farm.executor import CommandResult
 from compose_farm.logs import (
-    _parse_images_output,
-    collect_stack_entries,
+    _SECTION_SEPARATOR,
+    collect_stacks_entries_on_host,
     isoformat,
     load_existing_entries,
     merge_entries,
@@ -19,74 +19,252 @@ from compose_farm.logs import (
 )
 
 
-def test_parse_images_output_handles_list_and_lines() -> None:
-    data = [
-        {"Service": "svc", "Image": "redis", "Digest": "sha256:abc"},
-        {"Service": "svc", "Image": "db", "Digest": "sha256:def"},
+def _make_mock_output(
+    project_images: dict[str, list[str]], image_info: list[dict[str, object]]
+) -> str:
+    """Build mock output matching the 2-docker-command format."""
+    # Section 1: project|image pairs from docker ps
+    ps_lines = [
+        f"{project}|{image}" for project, images in project_images.items() for image in images
     ]
-    as_array = _parse_images_output(json.dumps(data))
-    assert len(as_array) == 2
 
-    as_lines = _parse_images_output("\n".join(json.dumps(item) for item in data))
-    assert len(as_lines) == 2
+    # Section 2: JSON array from docker image inspect
+    image_json = json.dumps(image_info)
+
+    return f"{chr(10).join(ps_lines)}\n{_SECTION_SEPARATOR}\n{image_json}"
 
 
-@pytest.mark.asyncio
-async def test_snapshot_preserves_first_seen(tmp_path: Path) -> None:
-    compose_dir = tmp_path / "compose"
-    compose_dir.mkdir()
-    stack_dir = compose_dir / "svc"
-    stack_dir.mkdir()
-    (stack_dir / "docker-compose.yml").write_text("services: {}\n")
+class TestCollectStacksEntriesOnHost:
+    """Tests for collect_stacks_entries_on_host (2 docker commands per host)."""
 
-    config = Config(
-        compose_dir=compose_dir,
-        hosts={"local": Host(address="localhost")},
-        stacks={"svc": "local"},
-    )
+    @pytest.fixture
+    def config_with_stacks(self, tmp_path: Path) -> Config:
+        """Create a config with multiple stacks."""
+        compose_dir = tmp_path / "compose"
+        compose_dir.mkdir()
+        for stack in ["plex", "jellyfin", "sonarr"]:
+            stack_dir = compose_dir / stack
+            stack_dir.mkdir()
+            (stack_dir / "docker-compose.yml").write_text("services: {}\n")
 
-    sample_output = json.dumps([{"Service": "svc", "Image": "redis", "Digest": "sha256:abc"}])
-
-    async def fake_run_compose(
-        _cfg: Config, stack: str, compose_cmd: str, *, stream: bool = True
-    ) -> CommandResult:
-        assert compose_cmd == "images --format json"
-        assert stream is False or stream is True
-        return CommandResult(
-            stack=stack,
-            exit_code=0,
-            success=True,
-            stdout=sample_output,
-            stderr="",
+        return Config(
+            compose_dir=compose_dir,
+            hosts={"host1": Host(address="localhost"), "host2": Host(address="localhost")},
+            stacks={"plex": "host1", "jellyfin": "host1", "sonarr": "host2"},
         )
 
-    log_path = tmp_path / "dockerfarm-log.toml"
+    @pytest.mark.asyncio
+    async def test_single_ssh_call(
+        self, config_with_stacks: Config, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        """Verify only 1 SSH call is made regardless of stack count."""
+        call_count = {"count": 0}
 
-    # First snapshot
-    first_time = datetime(2025, 1, 1, tzinfo=UTC)
-    first_entries = await collect_stack_entries(
-        config, "svc", now=first_time, run_compose_fn=fake_run_compose
-    )
-    first_iso = isoformat(first_time)
-    merged = merge_entries([], first_entries, now_iso=first_iso)
-    meta = {"generated_at": first_iso, "compose_dir": str(config.compose_dir)}
-    write_toml(log_path, meta=meta, entries=merged)
+        async def mock_run_command(
+            host: Host, command: str, stack: str, *, stream: bool, prefix: str
+        ) -> CommandResult:
+            call_count["count"] += 1
+            output = _make_mock_output(
+                {"plex": ["plex:latest"], "jellyfin": ["jellyfin:latest"]},
+                [
+                    {
+                        "RepoTags": ["plex:latest"],
+                        "Id": "sha256:aaa",
+                        "RepoDigests": ["plex@sha256:aaa"],
+                    },
+                    {
+                        "RepoTags": ["jellyfin:latest"],
+                        "Id": "sha256:bbb",
+                        "RepoDigests": ["jellyfin@sha256:bbb"],
+                    },
+                ],
+            )
+            return CommandResult(stack=stack, exit_code=0, success=True, stdout=output)
 
-    after_first = tomllib.loads(log_path.read_text())
-    first_seen = after_first["entries"][0]["first_seen"]
+        monkeypatch.setattr("compose_farm.logs.run_command", mock_run_command)
 
-    # Second snapshot
-    second_time = datetime(2025, 2, 1, tzinfo=UTC)
-    second_entries = await collect_stack_entries(
-        config, "svc", now=second_time, run_compose_fn=fake_run_compose
-    )
-    second_iso = isoformat(second_time)
-    existing = load_existing_entries(log_path)
-    merged = merge_entries(existing, second_entries, now_iso=second_iso)
-    meta = {"generated_at": second_iso, "compose_dir": str(config.compose_dir)}
-    write_toml(log_path, meta=meta, entries=merged)
+        now = datetime(2025, 1, 1, tzinfo=UTC)
+        entries = await collect_stacks_entries_on_host(
+            config_with_stacks, "host1", {"plex", "jellyfin"}, now=now
+        )
 
-    after_second = tomllib.loads(log_path.read_text())
-    entry = after_second["entries"][0]
-    assert entry["first_seen"] == first_seen
-    assert entry["last_seen"].startswith("2025-02-01")
+        assert call_count["count"] == 1
+        assert len(entries) == 2
+
+    @pytest.mark.asyncio
+    async def test_filters_to_requested_stacks(
+        self, config_with_stacks: Config, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        """Only return entries for stacks we asked for, even if others are running."""
+
+        async def mock_run_command(
+            host: Host, command: str, stack: str, *, stream: bool, prefix: str
+        ) -> CommandResult:
+            # Docker ps shows 3 stacks, but we only want plex
+            output = _make_mock_output(
+                {
+                    "plex": ["plex:latest"],
+                    "jellyfin": ["jellyfin:latest"],
+                    "other": ["other:latest"],
+                },
+                [
+                    {
+                        "RepoTags": ["plex:latest"],
+                        "Id": "sha256:aaa",
+                        "RepoDigests": ["plex@sha256:aaa"],
+                    },
+                    {
+                        "RepoTags": ["jellyfin:latest"],
+                        "Id": "sha256:bbb",
+                        "RepoDigests": ["j@sha256:bbb"],
+                    },
+                    {
+                        "RepoTags": ["other:latest"],
+                        "Id": "sha256:ccc",
+                        "RepoDigests": ["o@sha256:ccc"],
+                    },
+                ],
+            )
+            return CommandResult(stack=stack, exit_code=0, success=True, stdout=output)
+
+        monkeypatch.setattr("compose_farm.logs.run_command", mock_run_command)
+
+        now = datetime(2025, 1, 1, tzinfo=UTC)
+        entries = await collect_stacks_entries_on_host(
+            config_with_stacks, "host1", {"plex"}, now=now
+        )
+
+        assert len(entries) == 1
+        assert entries[0].stack == "plex"
+
+    @pytest.mark.asyncio
+    async def test_multiple_images_per_stack(
+        self, config_with_stacks: Config, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        """Stack with multiple containers/images returns multiple entries."""
+
+        async def mock_run_command(
+            host: Host, command: str, stack: str, *, stream: bool, prefix: str
+        ) -> CommandResult:
+            output = _make_mock_output(
+                {"plex": ["plex:latest", "redis:7"]},
+                [
+                    {
+                        "RepoTags": ["plex:latest"],
+                        "Id": "sha256:aaa",
+                        "RepoDigests": ["p@sha256:aaa"],
+                    },
+                    {"RepoTags": ["redis:7"], "Id": "sha256:bbb", "RepoDigests": ["r@sha256:bbb"]},
+                ],
+            )
+            return CommandResult(stack=stack, exit_code=0, success=True, stdout=output)
+
+        monkeypatch.setattr("compose_farm.logs.run_command", mock_run_command)
+
+        now = datetime(2025, 1, 1, tzinfo=UTC)
+        entries = await collect_stacks_entries_on_host(
+            config_with_stacks, "host1", {"plex"}, now=now
+        )
+
+        assert len(entries) == 2
+        images = {e.image for e in entries}
+        assert images == {"plex:latest", "redis:7"}
+
+    @pytest.mark.asyncio
+    async def test_empty_stacks_returns_empty(self, config_with_stacks: Config) -> None:
+        """Empty stack set returns empty entries without making SSH call."""
+        now = datetime(2025, 1, 1, tzinfo=UTC)
+        entries = await collect_stacks_entries_on_host(config_with_stacks, "host1", set(), now=now)
+        assert entries == []
+
+    @pytest.mark.asyncio
+    async def test_ssh_failure_returns_empty(
+        self, config_with_stacks: Config, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        """SSH failure returns empty list instead of raising."""
+
+        async def mock_run_command(
+            host: Host, command: str, stack: str, *, stream: bool, prefix: str
+        ) -> CommandResult:
+            return CommandResult(stack=stack, exit_code=1, success=False, stdout="", stderr="error")
+
+        monkeypatch.setattr("compose_farm.logs.run_command", mock_run_command)
+
+        now = datetime(2025, 1, 1, tzinfo=UTC)
+        entries = await collect_stacks_entries_on_host(
+            config_with_stacks, "host1", {"plex"}, now=now
+        )
+
+        assert entries == []
+
+
+class TestSnapshotMerging:
+    """Tests for merge_entries preserving first_seen."""
+
+    @pytest.fixture
+    def config(self, tmp_path: Path) -> Config:
+        compose_dir = tmp_path / "compose"
+        compose_dir.mkdir()
+        stack_dir = compose_dir / "svc"
+        stack_dir.mkdir()
+        (stack_dir / "docker-compose.yml").write_text("services: {}\n")
+
+        return Config(
+            compose_dir=compose_dir,
+            hosts={"local": Host(address="localhost")},
+            stacks={"svc": "local"},
+        )
+
+    @pytest.mark.asyncio
+    async def test_preserves_first_seen(
+        self, tmp_path: Path, config: Config, monkeypatch: pytest.MonkeyPatch
+    ) -> None:
+        """Repeated snapshots preserve first_seen timestamp."""
+
+        async def mock_run_command(
+            host: Host, command: str, stack: str, *, stream: bool, prefix: str
+        ) -> CommandResult:
+            output = _make_mock_output(
+                {"svc": ["redis:latest"]},
+                [
+                    {
+                        "RepoTags": ["redis:latest"],
+                        "Id": "sha256:abc",
+                        "RepoDigests": ["r@sha256:abc"],
+                    }
+                ],
+            )
+            return CommandResult(stack=stack, exit_code=0, success=True, stdout=output)
+
+        monkeypatch.setattr("compose_farm.logs.run_command", mock_run_command)
+
+        log_path = tmp_path / "dockerfarm-log.toml"
+
+        # First snapshot
+        first_time = datetime(2025, 1, 1, tzinfo=UTC)
+        first_entries = await collect_stacks_entries_on_host(
+            config, "local", {"svc"}, now=first_time
+        )
+        first_iso = isoformat(first_time)
+        merged = merge_entries([], first_entries, now_iso=first_iso)
+        meta = {"generated_at": first_iso, "compose_dir": str(config.compose_dir)}
+        write_toml(log_path, meta=meta, entries=merged)
+
+        after_first = tomllib.loads(log_path.read_text())
+        first_seen = after_first["entries"][0]["first_seen"]
+
+        # Second snapshot
+        second_time = datetime(2025, 2, 1, tzinfo=UTC)
+        second_entries = await collect_stacks_entries_on_host(
+            config, "local", {"svc"}, now=second_time
+        )
+        second_iso = isoformat(second_time)
+        existing = load_existing_entries(log_path)
+        merged = merge_entries(existing, second_entries, now_iso=second_iso)
+        meta = {"generated_at": second_iso, "compose_dir": str(config.compose_dir)}
+        write_toml(log_path, meta=meta, entries=merged)
+
+        after_second = tomllib.loads(log_path.read_text())
+        entry = after_second["entries"][0]
+        assert entry["first_seen"] == first_seen
+        assert entry["last_seen"].startswith("2025-02-01")

tests/test_operations.py

@@ -11,7 +11,10 @@ import pytest
 from compose_farm.cli import lifecycle
 from compose_farm.config import Config, Host
 from compose_farm.executor import CommandResult
-from compose_farm.operations import _migrate_stack
+from compose_farm.operations import (
+    _migrate_stack,
+    build_discovery_results,
+)
 
 
 @pytest.fixture
@@ -109,3 +112,83 @@ class TestUpdateCommandSequence:
         # Verify the sequence is pull, build, down, up
         assert "down" in source
         assert "up -d" in source
+
+
+class TestBuildDiscoveryResults:
+    """Tests for build_discovery_results function."""
+
+    @pytest.fixture
+    def config(self, tmp_path: Path) -> Config:
+        """Create a test config with multiple stacks."""
+        compose_dir = tmp_path / "compose"
+        for stack in ["plex", "jellyfin", "sonarr"]:
+            (compose_dir / stack).mkdir(parents=True)
+            (compose_dir / stack / "docker-compose.yml").write_text("services: {}")
+
+        return Config(
+            compose_dir=compose_dir,
+            hosts={
+                "host1": Host(address="localhost"),
+                "host2": Host(address="localhost"),
+            },
+            stacks={"plex": "host1", "jellyfin": "host1", "sonarr": "host2"},
+        )
+
+    def test_discovers_correctly_running_stacks(self, config: Config) -> None:
+        """Stacks running on correct hosts are discovered."""
+        running_on_host = {
+            "host1": {"plex", "jellyfin"},
+            "host2": {"sonarr"},
+        }
+
+        discovered, strays, duplicates = build_discovery_results(config, running_on_host)
+
+        assert discovered == {"plex": "host1", "jellyfin": "host1", "sonarr": "host2"}
+        assert strays == {}
+        assert duplicates == {}
+
+    def test_detects_stray_stacks(self, config: Config) -> None:
+        """Stacks running on wrong hosts are marked as strays."""
+        running_on_host = {
+            "host1": set(),
+            "host2": {"plex"},  # plex should be on host1
+        }
+
+        discovered, strays, _duplicates = build_discovery_results(config, running_on_host)
+
+        assert "plex" not in discovered
+        assert strays == {"plex": ["host2"]}
+
+    def test_detects_duplicates(self, config: Config) -> None:
+        """Single-host stacks running on multiple hosts are duplicates."""
+        running_on_host = {
+            "host1": {"plex"},
+            "host2": {"plex"},  # plex running on both hosts
+        }
+
+        discovered, strays, duplicates = build_discovery_results(
+            config, running_on_host, stacks=["plex"]
+        )
+
+        # plex is correctly running on host1
+        assert discovered == {"plex": "host1"}
+        # plex is also a stray on host2
+        assert strays == {"plex": ["host2"]}
+        # plex is a duplicate (single-host stack on multiple hosts)
+        assert duplicates == {"plex": ["host1", "host2"]}
+
+    def test_filters_to_requested_stacks(self, config: Config) -> None:
+        """Only returns results for requested stacks."""
+        running_on_host = {
+            "host1": {"plex", "jellyfin"},
+            "host2": {"sonarr"},
+        }
+
+        discovered, _strays, _duplicates = build_discovery_results(
+            config, running_on_host, stacks=["plex"]
+        )
+
+        # Only plex should be in results
+        assert discovered == {"plex": "host1"}
+        assert "jellyfin" not in discovered
+        assert "sonarr" not in discovered

tests/test_registry.py

@@ -0,0 +1,182 @@
+"""Tests for registry module."""
+
+from compose_farm.registry import (
+    DOCKER_HUB_ALIASES,
+    ImageRef,
+    RegistryClient,
+    TagCheckResult,
+    _find_updates,
+    _parse_version,
+)
+
+
+class TestImageRef:
+    """Tests for ImageRef parsing."""
+
+    def test_parse_simple_image(self) -> None:
+        """Test parsing simple image name."""
+        ref = ImageRef.parse("nginx")
+        assert ref.registry == "docker.io"
+        assert ref.namespace == "library"
+        assert ref.name == "nginx"
+        assert ref.tag == "latest"
+
+    def test_parse_image_with_tag(self) -> None:
+        """Test parsing image with tag."""
+        ref = ImageRef.parse("nginx:1.25")
+        assert ref.registry == "docker.io"
+        assert ref.namespace == "library"
+        assert ref.name == "nginx"
+        assert ref.tag == "1.25"
+
+    def test_parse_image_with_namespace(self) -> None:
+        """Test parsing image with namespace."""
+        ref = ImageRef.parse("linuxserver/jellyfin:latest")
+        assert ref.registry == "docker.io"
+        assert ref.namespace == "linuxserver"
+        assert ref.name == "jellyfin"
+        assert ref.tag == "latest"
+
+    def test_parse_ghcr_image(self) -> None:
+        """Test parsing GitHub Container Registry image."""
+        ref = ImageRef.parse("ghcr.io/user/repo:v1.0.0")
+        assert ref.registry == "ghcr.io"
+        assert ref.namespace == "user"
+        assert ref.name == "repo"
+        assert ref.tag == "v1.0.0"
+
+    def test_parse_image_with_digest(self) -> None:
+        """Test parsing image with digest."""
+        ref = ImageRef.parse("nginx:latest@sha256:abc123")
+        assert ref.registry == "docker.io"
+        assert ref.name == "nginx"
+        assert ref.tag == "latest"
+        assert ref.digest == "sha256:abc123"
+
+    def test_full_name_with_namespace(self) -> None:
+        """Test full_name property with namespace."""
+        ref = ImageRef.parse("linuxserver/jellyfin")
+        assert ref.full_name == "linuxserver/jellyfin"
+
+    def test_full_name_without_namespace(self) -> None:
+        """Test full_name property for official images."""
+        ref = ImageRef.parse("nginx")
+        assert ref.full_name == "library/nginx"
+
+    def test_display_name_official_image(self) -> None:
+        """Test display_name for official Docker Hub images."""
+        ref = ImageRef.parse("nginx:latest")
+        assert ref.display_name == "nginx"
+
+    def test_display_name_hub_with_namespace(self) -> None:
+        """Test display_name for Docker Hub images with namespace."""
+        ref = ImageRef.parse("linuxserver/jellyfin")
+        assert ref.display_name == "linuxserver/jellyfin"
+
+    def test_display_name_other_registry(self) -> None:
+        """Test display_name for other registries."""
+        ref = ImageRef.parse("ghcr.io/user/repo")
+        assert ref.display_name == "ghcr.io/user/repo"
+
+
+class TestParseVersion:
+    """Tests for version parsing."""
+
+    def test_parse_semver(self) -> None:
+        """Test parsing semantic version."""
+        assert _parse_version("1.2.3") == (1, 2, 3)
+
+    def test_parse_version_with_v_prefix(self) -> None:
+        """Test parsing version with v prefix."""
+        assert _parse_version("v1.2.3") == (1, 2, 3)
+        assert _parse_version("V1.2.3") == (1, 2, 3)
+
+    def test_parse_two_part_version(self) -> None:
+        """Test parsing two-part version."""
+        assert _parse_version("1.25") == (1, 25)
+
+    def test_parse_single_number(self) -> None:
+        """Test parsing single number version."""
+        assert _parse_version("7") == (7,)
+
+    def test_parse_invalid_version(self) -> None:
+        """Test parsing non-version tags."""
+        assert _parse_version("latest") is None
+        assert _parse_version("stable") is None
+        assert _parse_version("alpine") is None
+
+
+class TestFindUpdates:
+    """Tests for finding available updates."""
+
+    def test_find_updates_with_newer_versions(self) -> None:
+        """Test finding newer versions."""
+        current = "1.0.0"
+        tags = ["0.9.0", "1.0.0", "1.1.0", "2.0.0"]
+        updates = _find_updates(current, tags)
+        assert updates == ["2.0.0", "1.1.0"]
+
+    def test_find_updates_no_newer(self) -> None:
+        """Test when already on latest."""
+        current = "2.0.0"
+        tags = ["1.0.0", "1.5.0", "2.0.0"]
+        updates = _find_updates(current, tags)
+        assert updates == []
+
+    def test_find_updates_non_version_tag(self) -> None:
+        """Test with non-version current tag."""
+        current = "latest"
+        tags = ["1.0.0", "2.0.0"]
+        updates = _find_updates(current, tags)
+        # Can't determine updates for non-version tags
+        assert updates == []
+
+
+class TestRegistryClient:
+    """Tests for unified registry client."""
+
+    def test_docker_hub_normalization(self) -> None:
+        """Test Docker Hub aliases are normalized."""
+        for alias in DOCKER_HUB_ALIASES:
+            client = RegistryClient(alias)
+            assert client.registry == "docker.io"
+            assert client.registry_url == "https://registry-1.docker.io"
+
+    def test_ghcr_client(self) -> None:
+        """Test GitHub Container Registry client."""
+        client = RegistryClient("ghcr.io")
+        assert client.registry == "ghcr.io"
+        assert client.registry_url == "https://ghcr.io"
+
+    def test_generic_registry(self) -> None:
+        """Test generic registry client."""
+        client = RegistryClient("quay.io")
+        assert client.registry == "quay.io"
+        assert client.registry_url == "https://quay.io"
+
+
+class TestTagCheckResult:
+    """Tests for TagCheckResult."""
+
+    def test_create_result(self) -> None:
+        """Test creating a result."""
+        ref = ImageRef.parse("nginx:1.25")
+        result = TagCheckResult(
+            image=ref,
+            current_digest="sha256:abc",
+            available_updates=["1.26", "1.27"],
+        )
+        assert result.image.name == "nginx"
+        assert result.available_updates == ["1.26", "1.27"]
+        assert result.error is None
+
+    def test_result_with_error(self) -> None:
+        """Test result with error."""
+        ref = ImageRef.parse("nginx")
+        result = TagCheckResult(
+            image=ref,
+            current_digest="",
+            error="Connection refused",
+        )
+        assert result.error == "Connection refused"
+        assert result.available_updates == []

tests/test_ssh_keys.py

@@ -219,7 +219,7 @@ class TestSshConnectKwargs:
             assert result["client_keys"] == [str(key_path)]
 
     def test_includes_both_agent_and_key(self, tmp_path: Path) -> None:
-        """Include both agent_path and client_keys when both available."""
+        """Prioritize client_keys over agent_path when both available."""
         host = Host(address="example.com")
         key_path = tmp_path / "compose-farm"
 
@@ -229,7 +229,8 @@ class TestSshConnectKwargs:
         ):
             result = ssh_connect_kwargs(host)
 
-            assert result["agent_path"] == "/tmp/agent.sock"
+            # Agent should be ignored in favor of the dedicated key
+            assert "agent_path" not in result
             assert result["client_keys"] == [str(key_path)]
 
     def test_custom_port(self) -> None:

tests/web/test_helpers.py

@@ -7,11 +7,58 @@ from typing import TYPE_CHECKING
 
 import pytest
 from fastapi import HTTPException
+from pydantic import ValidationError
 
 if TYPE_CHECKING:
     from compose_farm.config import Config
 
 
+class TestExtractConfigError:
+    """Tests for extract_config_error helper."""
+
+    def test_validation_error_with_location(self) -> None:
+        from compose_farm.config import Config, Host
+        from compose_farm.web.deps import extract_config_error
+
+        # Trigger a validation error with an extra field
+        with pytest.raises(ValidationError) as exc_info:
+            Config(
+                hosts={"server": Host(address="192.168.1.1")},
+                stacks={"app": "server"},
+                unknown_field="bad",  # type: ignore[call-arg]
+            )
+
+        msg = extract_config_error(exc_info.value)
+        assert "unknown_field" in msg
+        assert "Extra inputs are not permitted" in msg
+
+    def test_validation_error_nested_location(self) -> None:
+        from compose_farm.config import Host
+        from compose_farm.web.deps import extract_config_error
+
+        # Trigger a validation error with a nested extra field
+        with pytest.raises(ValidationError) as exc_info:
+            Host(address="192.168.1.1", bad_key="value")  # type: ignore[call-arg]
+
+        msg = extract_config_error(exc_info.value)
+        assert "bad_key" in msg
+        assert "Extra inputs are not permitted" in msg
+
+    def test_regular_exception(self) -> None:
+        from compose_farm.web.deps import extract_config_error
+
+        exc = ValueError("Something went wrong")
+        msg = extract_config_error(exc)
+        assert msg == "Something went wrong"
+
+    def test_file_not_found_exception(self) -> None:
+        from compose_farm.web.deps import extract_config_error
+
+        exc = FileNotFoundError("Config file not found")
+        msg = extract_config_error(exc)
+        assert msg == "Config file not found"
+
+
 class TestValidateYaml:
     """Tests for _validate_yaml helper."""
 

tests/web/test_htmx_browser.py

@@ -134,6 +134,13 @@ def test_config(tmp_path_factory: pytest.TempPathFactory) -> Path:
         else:
             (svc / "compose.yaml").write_text(f"services:\n  {name}:\n    image: test/{name}\n")
 
+    # Create glances stack (required for containers page)
+    glances_dir = compose_dir / "glances"
+    glances_dir.mkdir()
+    (glances_dir / "compose.yaml").write_text(
+        "services:\n  glances:\n    image: nicolargo/glances\n"
+    )
+
     # Create config with multiple hosts
     config = tmp / "compose-farm.yaml"
     config.write_text(f"""
@@ -151,6 +158,8 @@ stacks:
   nextcloud: server-2
   jellyfin: server-2
   redis: server-1
+  glances: all
+glances_stack: glances
 """)
 
     # Create state (plex and nextcloud running, grafana and jellyfin not started)
@@ -245,7 +254,7 @@ class TestHTMXSidebarLoading:
 
         # Verify actual stacks from test config appear
         stacks = page.locator("#sidebar-stacks li")
-        assert stacks.count() == 5  # plex, grafana, nextcloud, jellyfin, redis
+        assert stacks.count() == 6  # plex, grafana, nextcloud, jellyfin, redis, glances
 
         # Check specific stacks are present
         content = page.locator("#sidebar-stacks").inner_text()
@@ -348,7 +357,7 @@ class TestDashboardContent:
 
         # From test config: 2 hosts, 5 stacks, 2 running (plex, nextcloud)
         assert "2" in stats  # hosts count
-        assert "5" in stats  # stacks count
+        assert "6" in stats  # stacks count
 
     def test_pending_shows_not_started_stacks(self, page: Page, server_url: str) -> None:
         """Pending operations shows grafana and jellyfin as not started."""
@@ -476,9 +485,9 @@ class TestSidebarFilter:
         page.goto(server_url)
         page.wait_for_selector("#sidebar-stacks", timeout=TIMEOUT)
 
-        # Initially all 4 stacks visible
+        # Initially all 6 stacks visible
         visible_items = page.locator("#sidebar-stacks li:not([hidden])")
-        assert visible_items.count() == 5
+        assert visible_items.count() == 6
 
         # Type in filter to match only "plex"
         self._filter_sidebar(page, "plex")
@@ -493,9 +502,9 @@ class TestSidebarFilter:
         page.goto(server_url)
         page.wait_for_selector("#sidebar-stacks", timeout=TIMEOUT)
 
-        # Initial count should be (5)
+        # Initial count should be (6)
         count_badge = page.locator("#sidebar-count")
-        assert "(5)" in count_badge.inner_text()
+        assert "(6)" in count_badge.inner_text()
 
         # Filter to show only stacks containing "x" (plex, nextcloud)
         self._filter_sidebar(page, "x")
@@ -524,13 +533,14 @@ class TestSidebarFilter:
         # Select server-1 from dropdown
         page.locator("#sidebar-host-select").select_option("server-1")
 
-        # Only plex, grafana, and redis (server-1 stacks) should be visible
+        # plex, grafana, redis (server-1), and glances (all) should be visible
         visible = page.locator("#sidebar-stacks li:not([hidden])")
-        assert visible.count() == 3
+        assert visible.count() == 4
 
         content = visible.all_inner_texts()
         assert any("plex" in s for s in content)
         assert any("grafana" in s for s in content)
+        assert any("glances" in s for s in content)
         assert not any("nextcloud" in s for s in content)
         assert not any("jellyfin" in s for s in content)
 
@@ -562,7 +572,7 @@ class TestSidebarFilter:
         self._filter_sidebar(page, "")
 
         # All stacks visible again
-        assert page.locator("#sidebar-stacks li:not([hidden])").count() == 5
+        assert page.locator("#sidebar-stacks li:not([hidden])").count() == 6
 
 
 class TestCommandPalette:
@@ -884,7 +894,7 @@ class TestContentStability:
 
         # Remember sidebar state
         initial_count = page.locator("#sidebar-stacks li").count()
-        assert initial_count == 5
+        assert initial_count == 6
 
         # Navigate away
         page.locator("#sidebar-stacks a", has_text="plex").click()
@@ -2329,3 +2339,227 @@ class TestTerminalNavigationIsolation:
         # Terminal should still be collapsed (no task to reconnect to)
         terminal_toggle = page.locator("#terminal-toggle")
         assert not terminal_toggle.is_checked(), "Terminal should remain collapsed after navigation"
+
+
+class TestContainersPagePause:
+    """Test containers page auto-refresh pause mechanism.
+
+    The containers page auto-refreshes every 3 seconds. When a user opens
+    an action dropdown, refresh should pause to prevent the dropdown from
+    closing unexpectedly.
+    """
+
+    # Mock HTML for container rows with action dropdowns
+    MOCK_ROWS_HTML = """
+<tr>
+<td>1</td>
+<td data-sort="plex"><a href="/stack/plex" class="link">plex</a></td>
+<td data-sort="server">server</td>
+<td><div class="dropdown dropdown-end">
+<label tabindex="0" class="btn btn-circle btn-ghost btn-xs"><svg class="h-4 w-4"></svg></label>
+<ul tabindex="0" class="dropdown-content menu menu-sm bg-base-200 rounded-box shadow-lg w-36 z-50 p-2">
+<li><a hx-post="/api/stack/plex/restart">Restart</a></li>
+</ul>
+</div></td>
+<td data-sort="nas"><span class="badge">nas</span></td>
+<td data-sort="nginx:latest"><code>nginx:latest</code></td>
+<td data-sort="running"><span class="badge badge-success">running</span></td>
+<td data-sort="3600">1 hour</td>
+<td data-sort="5"><progress class="progress" value="5" max="100"></progress><span>5%</span></td>
+<td data-sort="104857600"><progress class="progress" value="10" max="100"></progress><span>100MB</span></td>
+<td data-sort="1000">↓1KB ↑1KB</td>
+</tr>
+<tr>
+<td>2</td>
+<td data-sort="redis"><a href="/stack/redis" class="link">redis</a></td>
+<td data-sort="redis">redis</td>
+<td><div class="dropdown dropdown-end">
+<label tabindex="0" class="btn btn-circle btn-ghost btn-xs"><svg class="h-4 w-4"></svg></label>
+<ul tabindex="0" class="dropdown-content menu menu-sm bg-base-200 rounded-box shadow-lg w-36 z-50 p-2">
+<li><a hx-post="/api/stack/redis/restart">Restart</a></li>
+</ul>
+</div></td>
+<td data-sort="nas"><span class="badge">nas</span></td>
+<td data-sort="redis:7"><code>redis:7</code></td>
+<td data-sort="running"><span class="badge badge-success">running</span></td>
+<td data-sort="7200">2 hours</td>
+<td data-sort="1"><progress class="progress" value="1" max="100"></progress><span>1%</span></td>
+<td data-sort="52428800"><progress class="progress" value="5" max="100"></progress><span>50MB</span></td>
+<td data-sort="500">↓500B ↑500B</td>
+</tr>
+"""
+
+    def test_dropdown_pauses_refresh(self, page: Page, server_url: str) -> None:
+        """Opening action dropdown pauses auto-refresh.
+
+        Bug: focusin event triggers pause, but focusout fires shortly after
+        when focus moves within the dropdown, causing refresh to resume
+        while dropdown is still visually open.
+        """
+        # Mock container rows and update checks
+        page.route(
+            "**/api/containers/rows/*",
+            lambda route: route.fulfill(
+                status=200,
+                content_type="text/html",
+                body=self.MOCK_ROWS_HTML,
+            ),
+        )
+        page.route(
+            "**/api/containers/check-updates",
+            lambda route: route.fulfill(
+                status=200,
+                content_type="application/json",
+                body='{"results": []}',
+            ),
+        )
+
+        page.goto(f"{server_url}/live-stats")
+
+        # Wait for container rows to load
+        page.wait_for_function(
+            "document.querySelectorAll('#container-rows tr:not(.loading-row)').length > 0",
+            timeout=TIMEOUT,
+        )
+
+        # Wait for timer to start
+        page.wait_for_function(
+            "document.getElementById('refresh-timer')?.textContent?.includes('↻')",
+            timeout=TIMEOUT,
+        )
+
+        # Click on a dropdown to open it
+        dropdown_label = page.locator(".dropdown label").first
+        dropdown_label.click()
+
+        # Wait a moment for focusin to trigger
+        page.wait_for_timeout(200)
+
+        # Verify pause is engaged
+        timer_text = page.locator("#refresh-timer").inner_text()
+
+        assert timer_text == "❚❚", (
+            f"Refresh should be paused after clicking dropdown. timer='{timer_text}'"
+        )
+        assert "❚❚" in timer_text, f"Timer should show pause icon, got '{timer_text}'"
+
+    def test_refresh_stays_paused_while_dropdown_open(self, page: Page, server_url: str) -> None:
+        """Refresh remains paused for duration dropdown is open (>5s refresh interval).
+
+        This is the critical test for the pause bug: refresh should stay paused
+        for longer than the 3-second refresh interval while dropdown is open.
+        """
+        # Mock container rows and update checks
+        page.route(
+            "**/api/containers/rows/*",
+            lambda route: route.fulfill(
+                status=200,
+                content_type="text/html",
+                body=self.MOCK_ROWS_HTML,
+            ),
+        )
+        page.route(
+            "**/api/containers/check-updates",
+            lambda route: route.fulfill(
+                status=200,
+                content_type="application/json",
+                body='{"results": []}',
+            ),
+        )
+
+        page.goto(f"{server_url}/live-stats")
+
+        # Wait for container rows to load
+        page.wait_for_function(
+            "document.querySelectorAll('#container-rows tr:not(.loading-row)').length > 0",
+            timeout=TIMEOUT,
+        )
+
+        # Wait for timer to start
+        page.wait_for_function(
+            "document.getElementById('refresh-timer')?.textContent?.includes('↻')",
+            timeout=TIMEOUT,
+        )
+
+        # Record a marker in the first row to detect if refresh happened
+        page.evaluate("""
+            const firstRow = document.querySelector('#container-rows tr');
+            if (firstRow) firstRow.dataset.testMarker = 'original';
+        """)
+
+        # Click dropdown to pause
+        dropdown_label = page.locator(".dropdown label").first
+        dropdown_label.click()
+        page.wait_for_timeout(200)
+
+        # Confirm paused
+        assert page.locator("#refresh-timer").inner_text() == "❚❚"
+
+        # Wait longer than the 5-second refresh interval
+        page.wait_for_timeout(6000)
+
+        # Check if still paused
+        timer_text = page.locator("#refresh-timer").inner_text()
+
+        # Check if the row was replaced (marker would be gone)
+        marker = page.evaluate("""
+            document.querySelector('#container-rows tr')?.dataset?.testMarker
+        """)
+
+        assert timer_text == "❚❚", f"Refresh should still be paused after 6s. timer='{timer_text}'"
+        assert marker == "original", (
+            "Table was refreshed while dropdown was open - pause mechanism failed"
+        )
+
+    def test_refresh_resumes_after_dropdown_closes(self, page: Page, server_url: str) -> None:
+        """Refresh resumes after dropdown is closed."""
+        # Mock container rows and update checks
+        page.route(
+            "**/api/containers/rows/*",
+            lambda route: route.fulfill(
+                status=200,
+                content_type="text/html",
+                body=self.MOCK_ROWS_HTML,
+            ),
+        )
+        page.route(
+            "**/api/containers/check-updates",
+            lambda route: route.fulfill(
+                status=200,
+                content_type="application/json",
+                body='{"results": []}',
+            ),
+        )
+
+        page.goto(f"{server_url}/live-stats")
+
+        # Wait for container rows to load
+        page.wait_for_function(
+            "document.querySelectorAll('#container-rows tr:not(.loading-row)').length > 0",
+            timeout=TIMEOUT,
+        )
+
+        # Wait for timer to start
+        page.wait_for_function(
+            "document.getElementById('refresh-timer')?.textContent?.includes('↻')",
+            timeout=TIMEOUT,
+        )
+
+        # Click dropdown to pause
+        dropdown_label = page.locator(".dropdown label").first
+        dropdown_label.click()
+        page.wait_for_timeout(200)
+
+        assert page.locator("#refresh-timer").inner_text() == "❚❚"
+
+        # Close dropdown by pressing Escape or clicking elsewhere
+        page.keyboard.press("Escape")
+        page.wait_for_timeout(300)  # Wait for focusout timeout (150ms) + buffer
+
+        # Verify refresh resumed
+        timer_text = page.locator("#refresh-timer").inner_text()
+
+        assert timer_text != "❚❚", (
+            f"Refresh should resume after closing dropdown. timer='{timer_text}'"
+        )
+        assert "↻" in timer_text, f"Timer should show countdown, got '{timer_text}'"

uv.lock

@@ -242,6 +242,7 @@ dependencies = [
 [package.optional-dependencies]
 web = [
     { name = "fastapi", extra = ["standard"] },
+    { name = "humanize" },
     { name = "jinja2" },
     { name = "websockets" },
 ]
@@ -270,6 +271,7 @@ dev = [
 requires-dist = [
     { name = "asyncssh", specifier = ">=2.14.0" },
     { name = "fastapi", extras = ["standard"], marker = "extra == 'web'", specifier = ">=0.109.0" },
+    { name = "humanize", marker = "extra == 'web'", specifier = ">=4.0.0" },
     { name = "jinja2", marker = "extra == 'web'", specifier = ">=3.1.0" },
     { name = "pydantic", specifier = ">=2.0.0" },
     { name = "pyyaml", specifier = ">=6.0" },
@@ -781,6 +783,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/2a/39/e50c7c3a983047577ee07d2a9e53faf5a69493943ec3f6a384bdc792deb2/httpx-0.28.1-py3-none-any.whl", hash = "sha256:d909fcccc110f8c7faf814ca82a9a4d816bc5a6dbfea25d6591d6985b8ba59ad", size = 73517, upload-time = "2024-12-06T15:37:21.509Z" },
 ]
 
+[[package]]
+name = "humanize"
+version = "4.15.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/ba/66/a3921783d54be8a6870ac4ccffcd15c4dc0dd7fcce51c6d63b8c63935276/humanize-4.15.0.tar.gz", hash = "sha256:1dd098483eb1c7ee8e32eb2e99ad1910baefa4b75c3aff3a82f4d78688993b10", size = 83599, upload-time = "2025-12-20T20:16:13.19Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c5/7b/bca5613a0c3b542420cf92bd5e5fb8ebd5435ce1011a091f66bb7693285e/humanize-4.15.0-py3-none-any.whl", hash = "sha256:b1186eb9f5a9749cd9cb8565aee77919dd7c8d076161cf44d70e59e3301e1769", size = 132203, upload-time = "2025-12-20T20:16:11.67Z" },
+]
+
 [[package]]
 name = "identify"
 version = "2.6.15"