feat(cleanup): walk every backend, reap smolmachines orphans too

`./cli.py cleanup` previously called only the env-var-selected
backend's `prepare_cleanup` / `cleanup` — so a leftover smolvm
machine + bundle container + bundle network from a crashed
smolmachines bottle would survive a default `docker`-mode cleanup
indefinitely.

Smolmachines now has a real `cleanup` module (alongside
`enumerate.py` from issue #77) that walks:

  - smolvm machines named `claude-bottle-*` (via
    `smolvm machine ls --json`)
  - bundle containers `claude-bottle-sidecars-*`
  - bundle networks `claude-bottle-bundle-*`

Cleanup runs stop+delete on the machines, force-rm on the
containers, network rm on the networks. Each step is best-effort
so a failed rm doesn't block the rest.

`cli.py cleanup` walks every backend in `known_backend_names()`
and runs each backend's `cleanup` after a single y/N prompt that
shows a combined plan.

State dirs (`~/.claude-bottle/state/<slug>/`) are shared layout
with the docker backend, which still owns the orphan-state-dir
bucket. It now consults `enumerate_active_bottles()` for the
cross-backend live identity set so a running smolmachines
bottle's state dir isn't reaped during a cleanup.

Tests: smolmachines cleanup (prepare + cleanup ordering + failure
handling); cross-backend orphan protection on the docker
state-dir check; CLI cmd_cleanup walks both backends, short-
circuits on all-empty, aborts on N. 617 unit tests pass.

End-to-end verified on this host:
  $ smolvm machine ls --json | jq '.[].name'
  "claude-bottle-researcher-m3hxd"
  $ ./cli.py cleanup
  --- smolmachines backend ---
  smolvm machine:  claude-bottle-researcher-m3hxd
  remove all of the above? [y/N]

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

claude_bottle/backend/docker/cleanup.py

@@ -83,11 +83,18 @@ def _list_prefixed_networks() -> list[str]:
     return sorted(set(out))
 
 
-def _list_orphan_state_dirs(live_projects: set[str]) -> list[str]:
+def _list_orphan_state_dirs(
+    live_projects: set[str], protected_identities: set[str],
+) -> list[str]:
     """State identities whose compose project isn't running and
     that don't have a `.preserve` marker. `.preserve` means the
     user (or an auto-preserve-on-crash) wants the state kept for
-    `resume`."""
+    `resume`.
+
+    `protected_identities` is the set of slugs that are live in
+    ANY backend — used so this docker-side check doesn't reap a
+    running smolmachines bottle's state dir (the layout is shared
+    across both backends)."""
     state_root = _supervise.claude_bottle_root() / "state"
     if not state_root.is_dir():
         return []
@@ -99,6 +106,8 @@ def _list_orphan_state_dirs(live_projects: set[str]) -> list[str]:
         project = f"{COMPOSE_PROJECT_PREFIX}{identity}"
         if project in live_projects:
             continue
+        if identity in protected_identities:
+            continue
         if is_preserved(identity):
             continue
         orphans.append(identity)
@@ -106,15 +115,25 @@ def _list_orphan_state_dirs(live_projects: set[str]) -> list[str]:
 
 
 def prepare_cleanup() -> DockerBottleCleanupPlan:
-    """Enumerate everything cleanup will touch. No removals."""
+    """Enumerate everything cleanup will touch. No removals.
+
+    Pulls the union of live identities across backends via
+    `enumerate_active_agents()` so the orphan-state-dir bucket
+    doesn't include slugs whose smolmachines VM is still up."""
     docker_mod.require_docker()
     projects = list_compose_projects()
     project_set = set(projects)
+    # Late import to avoid a circular at module-load time —
+    # the backend package's __init__ imports this module.
+    from .. import enumerate_active_agents
+    protected = {a.slug for a in enumerate_active_agents()}
     return DockerBottleCleanupPlan(
         projects=tuple(projects),
         stray_containers=tuple(_list_prefixed_containers()),
         stray_networks=tuple(_list_prefixed_networks()),
-        orphan_state_dirs=tuple(_list_orphan_state_dirs(project_set)),
+        orphan_state_dirs=tuple(
+            _list_orphan_state_dirs(project_set, protected),
+        ),
     )
 
 

claude_bottle/backend/smolmachines/backend.py

@@ -8,6 +8,7 @@ from pathlib import Path
 from typing import Generator, Sequence
 
 from .. import ActiveAgent, BottleBackend, BottleSpec
+from . import cleanup as _cleanup
 from . import enumerate as _enumerate
 from . import launch as _launch
 from . import prepare as _prepare
@@ -76,12 +77,10 @@ class SmolmachinesBottleBackend(
         _supervise.provision_supervise(plan, target)
 
     def prepare_cleanup(self) -> SmolmachinesBottleCleanupPlan:
-        return SmolmachinesBottleCleanupPlan()
+        return _cleanup.prepare_cleanup()
 
     def cleanup(self, plan: SmolmachinesBottleCleanupPlan) -> None:
-        del plan
-        # Nothing to clean in chunks 1-3 — see
-        # SmolmachinesBottleCleanupPlan docstring.
+        _cleanup.cleanup(plan)
 
     def enumerate_active(self) -> Sequence[ActiveAgent]:
         return _enumerate.enumerate_active()

claude_bottle/backend/smolmachines/bottle_cleanup_plan.py

@@ -1,13 +1,29 @@
-"""SmolmachinesBottleCleanupPlan — concrete BottleCleanupPlan stub
-(PRD 0023 chunk 1).
+"""SmolmachinesBottleCleanupPlan — concrete BottleCleanupPlan (issue #77).
 
-Chunk 1 always reports nothing-to-clean. Real enumeration —
-orphaned smolvm machines, stranded gvproxy sockets, leftover
-sidecar bundle containers — lands in chunk 4 alongside the
-integration-test sweep that exercises teardown."""
+Tracks the resources `SmolmachinesBottleBackend.cleanup` will
+remove:
+
+  - machines:  smolvm machines whose name starts with
+               `claude-bottle-` (running or stopped). Stopped +
+               deleted via `smolvm machine stop` + `machine delete -f`.
+  - bundles:   docker containers `claude-bottle-sidecars-<slug>`
+               left over from a smolmachines bottle (the bundle's
+               port-forwards stay published on lo0 aliases until
+               the container is gone). Removed via `docker rm -f`.
+  - networks:  docker networks `claude-bottle-bundle-<slug>`
+               attached to the bundles. Removed via
+               `docker network rm`.
+
+Smolmachines state dirs live under the same `~/.claude-bottle/state/`
+path the docker backend uses; the docker backend's
+`prepare_cleanup` already enumerates orphan state dirs and is the
+single source of truth for that bucket (consults
+`enumerate_active_bottles()` so it doesn't reap a live
+smolmachines bottle's dir)."""
 
 from __future__ import annotations
 
+import sys
 from dataclasses import dataclass
 
 from ...log import info
@@ -16,10 +32,24 @@ from .. import BottleCleanupPlan
 
 @dataclass(frozen=True)
 class SmolmachinesBottleCleanupPlan(BottleCleanupPlan):
-    def print(self) -> None:
-        info("smolmachines cleanup: nothing to remove (chunk 4 will "
-             "enumerate orphan machines + gvproxy sockets)")
+    """Resources SmolmachinesBottleBackend.cleanup will remove.
+    Produced by `prepare_cleanup`; sorted so the y/N output is
+    stable."""
+
+    machines: tuple[str, ...] = ()
+    bundles: tuple[str, ...] = ()
+    networks: tuple[str, ...] = ()
 
     @property
     def empty(self) -> bool:
-        return True
+        return not self.machines and not self.bundles and not self.networks
+
+    def print(self) -> None:
+        print(file=sys.stderr)
+        for name in self.machines:
+            info(f"smolvm machine:  {name}")
+        for name in self.bundles:
+            info(f"bundle container:{name}")
+        for name in self.networks:
+            info(f"bundle network:  {name}")
+        print(file=sys.stderr)

claude_bottle/backend/smolmachines/cleanup.py

@@ -0,0 +1,159 @@
+"""Cleanup + active-listing for the smolmachines backend (issue #77).
+
+`prepare_cleanup` enumerates leftover smolmachines resources:
+
+  - smolvm machines (`smolvm machine ls --json`) whose name starts
+    with `claude-bottle-`.
+  - bundle docker containers (`claude-bottle-sidecars-<slug>`).
+  - bundle docker networks (`claude-bottle-bundle-<slug>`).
+
+State dirs live under `~/.claude-bottle/state/<identity>/` —
+shared layout with the docker backend, which has the single
+orphan-state-dir enumerator (it already consults
+`enumerate_active_agents()` so a live smolmachines bottle's dir
+is preserved).
+
+`cleanup` removes everything in the plan: stop + delete each VM,
+force-rm each container, rm each network. Each step is
+best-effort — a failure on one resource doesn't block the others."""
+
+from __future__ import annotations
+
+import json
+import subprocess
+
+from ...log import info, warn
+from . import sidecar_bundle as _bundle
+from . import smolvm as _smolvm
+from .bottle_cleanup_plan import SmolmachinesBottleCleanupPlan
+
+
+# Both names start with the same prefix the launcher uses.
+_VM_PREFIX = "claude-bottle-"
+_BUNDLE_PREFIX = _bundle.bundle_container_name("")          # `claude-bottle-sidecars-`
+_NETWORK_PREFIX = _bundle.bundle_network_name("")           # `claude-bottle-bundle-`
+
+
+def prepare_cleanup() -> SmolmachinesBottleCleanupPlan:
+    """Enumerate every smolmachines-owned resource on the host.
+    No side effects. Returns an empty plan when smolvm isn't on
+    PATH (no machines to reap) — `cleanup` is a no-op in that
+    case too."""
+    machines = _list_claude_bottle_machines()
+    bundles = _list_bundle_containers()
+    networks = _list_bundle_networks()
+    return SmolmachinesBottleCleanupPlan(
+        machines=tuple(sorted(machines)),
+        bundles=tuple(sorted(bundles)),
+        networks=tuple(sorted(networks)),
+    )
+
+
+def cleanup(plan: SmolmachinesBottleCleanupPlan) -> None:
+    """Remove everything in the plan. Order matters: stop VMs
+    first (they hold ports on lo0 aliases via libkrun), then the
+    bundle containers (which hold the host port-forwards), then
+    the networks (which docker won't reap until the containers
+    are gone)."""
+    for name in plan.machines:
+        info(f"stopping smolvm machine {name}")
+        subprocess.run(
+            ["smolvm", "machine", "stop", "--name", name],
+            stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL,
+            check=False,
+        )
+        info(f"deleting smolvm machine {name}")
+        r = subprocess.run(
+            ["smolvm", "machine", "delete", "-f", name],
+            capture_output=True, text=True, check=False,
+        )
+        if r.returncode != 0:
+            warn(
+                f"smolvm machine delete -f {name} failed: "
+                f"{(r.stderr or '').strip()}"
+            )
+
+    for name in plan.bundles:
+        info(f"removing bundle container {name}")
+        subprocess.run(
+            ["docker", "rm", "-f", name],
+            stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL,
+            check=False,
+        )
+
+    for name in plan.networks:
+        info(f"removing bundle network {name}")
+        r = subprocess.run(
+            ["docker", "network", "rm", name],
+            capture_output=True, text=True, check=False,
+        )
+        if r.returncode != 0 and "no such network" not in (r.stderr or "").lower():
+            warn(
+                f"docker network rm {name} failed: "
+                f"{(r.stderr or '').strip()}"
+            )
+
+
+def _list_claude_bottle_machines() -> list[str]:
+    """All smolvm machines named `claude-bottle-*`, regardless of
+    state (running / stopped / created). Empty when smolvm isn't
+    installed."""
+    if not _smolvm.is_available():
+        return []
+    r = subprocess.run(
+        ["smolvm", "machine", "ls", "--json"],
+        capture_output=True, text=True, check=False,
+    )
+    if r.returncode != 0:
+        return []
+    try:
+        machines = json.loads(r.stdout or "[]")
+    except json.JSONDecodeError:
+        return []
+    return [
+        m["name"] for m in machines
+        if isinstance(m, dict)
+        and m.get("name", "").startswith(_VM_PREFIX)
+    ]
+
+
+def _list_bundle_containers() -> list[str]:
+    """All docker containers named `claude-bottle-sidecars-*`,
+    running or stopped. Empty when docker isn't installed."""
+    # Late import: `backend/__init__` imports this module
+    # transitively via the smolmachines backend.
+    from .. import has_backend
+    if not has_backend("docker"):
+        return []
+    r = subprocess.run(
+        ["docker", "ps", "-a",
+         "--filter", f"name=^{_BUNDLE_PREFIX}",
+         "--format", "{{.Names}}"],
+        capture_output=True, text=True, check=False,
+    )
+    if r.returncode != 0:
+        return []
+    return [
+        line for line in (r.stdout or "").splitlines()
+        if line and line.startswith(_BUNDLE_PREFIX)
+    ]
+
+
+def _list_bundle_networks() -> list[str]:
+    """All docker networks named `claude-bottle-bundle-*`. Empty
+    when docker isn't installed."""
+    from .. import has_backend
+    if not has_backend("docker"):
+        return []
+    r = subprocess.run(
+        ["docker", "network", "ls",
+         "--filter", f"name={_NETWORK_PREFIX}",
+         "--format", "{{.Name}}"],
+        capture_output=True, text=True, check=False,
+    )
+    if r.returncode != 0:
+        return []
+    return [
+        line for line in (r.stdout or "").splitlines()
+        if line and line.startswith(_NETWORK_PREFIX)
+    ]

claude_bottle/cli/cleanup.py

@@ -1,11 +1,16 @@
 """cleanup: stop and remove all orphaned claude-bottle resources.
 
-PRD 0018 chunk 4: backend's prepare_cleanup carries everything in
-one plan — live compose projects (whose `compose down` removes
-containers + networks atomically), legacy stray containers/networks
-that aren't in any project, and orphan state dirs (per-bottle
-state with no live project AND no `.preserve` marker). One prompt,
-one cleanup call.
+Walks every registered backend (docker + smolmachines) so a single
+`./cli.py cleanup` reaps both backends' leftovers — orphaned
+smolvm machines won't survive a docker-only cleanup pass (issue
+addressed alongside #77).
+
+Each backend's `prepare_cleanup` enumerates its own resources;
+docker's `_list_orphan_state_dirs` consults
+`enumerate_active_agents()` for the union of live identities so
+state dirs of running smolmachines bottles aren't reaped. State
+dirs are shared layout, so docker is the single owner of that
+bucket.
 
 State dirs with `.preserve` are intentionally never touched — they
 hold capability-block rebuilds or crash snapshots the operator may
@@ -17,25 +22,37 @@ from __future__ import annotations
 
 import sys
 
-from ..backend import get_bottle_backend
+from ..backend import get_bottle_backend, known_backend_names
 from ..log import info
 from ._common import read_tty_line
 
 
 def cmd_cleanup(_argv: list[str]) -> int:
-    backend = get_bottle_backend()
-    plan = backend.prepare_cleanup()
+    # Order: stable backend iteration so the y/N output is
+    # deterministic across runs.
+    plans = [
+        (name, get_bottle_backend(name)) for name in known_backend_names()
+    ]
+    prepared = [(name, b, b.prepare_cleanup()) for name, b in plans]
 
-    if plan.empty:
+    if all(p.empty for _, _, p in prepared):
         info("no claude-bottle resources to clean up")
         return 0
 
-    plan.print()
+    for name, _, plan in prepared:
+        if plan.empty:
+            continue
+        info(f"--- {name} backend ---")
+        plan.print()
+
     if not _prompt_yes("remove all of the above?"):
         info("cleanup: skipped")
         return 0
 
-    backend.cleanup(plan)
+    for name, backend, plan in prepared:
+        if plan.empty:
+            continue
+        backend.cleanup(plan)
     info("cleanup: done")
     return 0