chore: update quality badges

- Coverage: 83%
- Core coverage: 94%

[skip ci]

.coveragerc

@@ -20,3 +20,9 @@ omit =
     bot_bottle/cli/tui.py
     bot_bottle/cli/init.py
     tests/*
+    # Build-time only: setuptools invokes it out-of-process to build the
+    # wheel/sdist (it's never imported by the running app), so in-process
+    # coverage can't reach it. Its one job — bundling the root resources into
+    # bot_bottle/_resources/ — is exercised end-to-end by test_wheel_install,
+    # which builds and installs a real wheel and checks the result.
+    setup.py

.gitea/workflows/test.yml

@@ -212,6 +212,89 @@ jobs:
           name: firecracker-inputs
           path: /var/cache/bot-bottle-fc/dropbear
 
+  # Integration tests against the macOS Apple Container backend. Runs on a
+  # self-hosted macOS runner (label `macos`) registered in HOST mode — Apple
+  # Container needs the host `container` CLI + virtualization framework and
+  # cannot run inside a Linux container, so this cannot reuse the KVM runner.
+  #
+  # Advisory only: workflow_dispatch (manual) exclusively — never push or
+  # pull_request. A single non-redundant laptop that sleeps/roams must not run
+  # unattended on every push to main, let alone block a PR merge, so this job is
+  # deliberately NOT in the `coverage` job's `needs` and its coverage never
+  # feeds the diff-coverage gate. Dispatch-only also means no fork PR (or any
+  # push) ever executes on the host-mode runner.
+  #
+  # The infra container is a singleton (`bot-bottle-mac-infra`); the
+  # `concurrency` group serializes runs so two never collide on it (#425), and
+  # the always-run teardown removes it so a crashed run can't wedge the next.
+  #
+  # Runner prerequisites (provision once; see README "macOS Apple Container"):
+  # the `container` CLI on PATH with `container system status` running, and a
+  # Python >=3.11 with `coverage` importable on the launchd service PATH.
+  integration-macos:
+    runs-on: [self-hosted, macos]
+    if: github.event_name == 'workflow_dispatch'
+    concurrency:
+      group: integration-macos-infra
+      cancel-in-progress: false
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      # Fail loudly if the backend this job promises isn't actually usable,
+      # rather than letting every test silently `unittest.skip` and the job go
+      # green on zero coverage. `backend status` exits non-zero (and prints the
+      # per-check summary) when the `container` CLI or its system service is
+      # missing — the same readiness check the skip guards gate on.
+      - name: Preflight — Apple Container backend is ready
+        run: |
+          command -v container >/dev/null || {
+            echo "container CLI not on PATH — provision the runner (README: macOS Apple Container)"; exit 1; }
+          container system status || {
+            echo "container system service not running — run 'container system start'"; exit 1; }
+          python3 cli.py backend status --backend=macos-container
+
+      # `coverage` comes from the runner's provisioned Python (no pip install
+      # into the host interpreter). Advisory job: report coverage in-line for
+      # visibility but don't upload — it never feeds the combined gate.
+      - name: Run integration tests (macos-container) with coverage
+        env:
+          BOT_BOTTLE_BACKEND: macos-container
+          COVERAGE_FILE: ${{ github.workspace }}/.coverage.macos
+        run: python3 -m coverage run -m unittest discover -t . -s tests/integration -v
+
+      - name: Report macos coverage
+        env:
+          COVERAGE_FILE: ${{ github.workspace }}/.coverage.macos
+        run: python3 -m coverage report -m
+
+      # On failure, capture the infra containers' state and logs BEFORE the
+      # teardown below removes them — otherwise a control-plane crash is
+      # undiagnosable from CI, since `stop()` deletes the orchestrator (and its
+      # logs) on every run. Best-effort: never let the diagnostics themselves
+      # fail the job, and keep going if a container is already gone.
+      - name: Dump infra diagnostics (on failure)
+        if: failure()
+        run: |
+          set +e
+          echo "=== containers ==="
+          container ls -a | grep bot-bottle-mac || echo "(no bot-bottle-mac containers)"
+          echo "=== networks ==="
+          container network ls | grep bot-bottle-mac || echo "(no bot-bottle-mac networks)"
+          for c in bot-bottle-mac-orchestrator bot-bottle-mac-infra; do
+            echo "=== inspect $c ==="
+            container inspect "$c" || echo "($c not found)"
+            echo "=== logs $c ==="
+            container logs "$c" || echo "($c logs unavailable)"
+          done
+          exit 0
+
+      # Remove the singleton infra container so a crashed or cancelled run
+      # cannot leave `bot-bottle-mac-infra` wedged for the next job.
+      - name: Teardown infra singleton
+        if: always()
+        run: python3 -c 'from bot_bottle.backend.macos_container.infra import MacosInfraService; MacosInfraService().stop()'
+
   # Combined coverage gate: aggregates .coverage.* artifacts uploaded by each
   # test job, then runs the diff-coverage gate (new/changed lines >= 90%).
   #

.gitignore

@@ -17,6 +17,9 @@ __pycache__/
 *.py[cod]
 *$py.class
 *.egg-info/
+# setuptools/build_meta output (wheels, sdists, build tree)
+/build/
+/dist/
 .venv/
 venv/
 .pytest_cache/

MANIFEST.in

@@ -0,0 +1,8 @@
+# Root-level build resources copied into bot_bottle/_resources/ at build time
+# (see setup.py). Included in the sdist so `pip install` from an sdist can
+# still bundle them into the wheel.
+include Dockerfile.gateway
+include Dockerfile.orchestrator
+include Dockerfile.orchestrator.fc
+include nix/firecracker-netpool.nix
+include scripts/firecracker-netpool.sh

README.md

@@ -5,7 +5,7 @@
 # bot-bottle
 
 [![test](https://gitea.dideric.is/didericis/bot-bottle/actions/workflows/test.yml/badge.svg?branch=main)](https://gitea.dideric.is/didericis/bot-bottle/actions?workflow=test.yml)
-[![coverage](https://img.shields.io/badge/coverage-84%25-brightgreen)](https://coverage.readthedocs.io/)
+[![coverage](https://img.shields.io/badge/coverage-83%25-brightgreen)](https://coverage.readthedocs.io/)
 [![core coverage](https://img.shields.io/badge/core%20coverage-94%25-brightgreen)](https://gitea.dideric.is/didericis/bot-bottle/src/branch/main/docs/decisions/0004-coverage-policy.md)
 
 **Problem:** Developer wants to run a coding agent without supervision, but they don't want a prompt injected or misbehaving agent wrecking their environment or exfiltrating sensitive data.
@@ -30,7 +30,7 @@
 
 ## Architecture
 
-On the default macOS Apple Container backend, a bottle is an agent container on a host-only internal network plus a gateway attached to both that internal network and a NAT egress network. The agent gets HTTP(S)_PROXY and CA bundle env vars pointing at the gateway's internal-network IP, so HTTP/HTTPS traffic flows through the gateway instead of direct egress. `bottle.git` / git-gate is intentionally deferred on this backend until a safe Apple Container key-delivery path exists.
+On the default macOS Apple Container backend, a bottle is an agent container on a host-only internal network plus a gateway attached to both that internal network and a NAT egress network. The agent gets HTTP(S)_PROXY and CA bundle env vars pointing at the gateway's internal-network IP, so HTTP/HTTPS traffic flows through the gateway instead of direct egress. git-gate runs over the gateway's consolidated `git-http` daemon (the legacy per-bottle `git://` daemon is not used on this backend); keys are provisioned dynamically at launch and revoked on teardown.
 
 On the Firecracker backend, a bottle is an agent microVM plus a Docker gateway for egress, git-gate, and supervise. The VM reaches the gateway over a per-bottle point-to-point TAP link; a dedicated fail-closed `nftables` table (`inet bot_bottle_fc`) confines the guest to that link, so nothing leaves the box except through the gateway. The TAP pool and nft table are provisioned once (root); per-launch needs no privilege.
 
@@ -75,6 +75,8 @@ On compatible macOS hosts, the default backend requires Apple's `container` CLI
 
 Use `BOT_BOTTLE_BACKEND=docker ./cli.py start <agent>` on hosts where neither Apple Container nor KVM is available and Docker is the desired backend.
 
+> **CI (macOS Apple Container):** the `integration-macos` job (`.gitea/workflows/test.yml`) runs the integration suite against `BOT_BOTTLE_BACKEND=macos-container` on a self-hosted macOS runner labelled `macos`, because Apple Container needs the host virtualization framework and cannot run in a Linux container (so it can't reuse the `kvm` runner). Provision an Apple Silicon host with the `container` CLI on `PATH` and `container system status` running, then register the runner in **host mode** (not docker mode) with the `macos` label — `brew install gitea-runner` (the `act_runner` rename). Give it a Python ≥ 3.11 with `coverage` importable on the launchd service's `PATH` (a launchd service doesn't inherit your shell profile, so pin `node` and the Python env explicitly). The job is **advisory** — `workflow_dispatch` (manual) only, never triggered by push or PR — since a single laptop that sleeps/roams must not block merges or churn on every push to main; its coverage doesn't feed the gate. The infra container is a singleton (`bot-bottle-mac-infra`), so keep runner concurrency at 1.
+
 ### Containers inside a bottle
 
 A bottle may set `nested_containers: true`. On the macOS backend this starts a

bot_bottle/backend/docker/gateway.py

@@ -10,9 +10,10 @@ from ...paths import (
     ORCHESTRATOR_AUTH_JWT_ENV,
     host_gateway_ca_dir,
 )
+from ... import resources
 from ...gateway import (
   Gateway, GatewayTransport, GATEWAY_IMAGE, GATEWAY_NAME, GATEWAY_NETWORK,
-  GATEWAY_DOCKERFILE, REPO_ROOT, GATEWAY_LABEL, MITMPROXY_HOME,
+  GATEWAY_DOCKERFILE, GATEWAY_LABEL, MITMPROXY_HOME,
   DEFAULT_CA_TIMEOUT_SECONDS, CA_POLL_SECONDS, GATEWAY_CA_CERT, GatewayError
 )
 
@@ -50,7 +51,9 @@ class DockerGateway(Gateway):
         # `address` / `stop` work on an already-running gateway without it.
         self._orchestrator_url = ""
         self._gateway_token = ""
-        self._build_context = build_context or REPO_ROOT
+        # Resolved lazily in ensure_built() so merely constructing a gateway to
+        # read its CA never stages a build root from an installed wheel.
+        self._build_context = build_context
         self._dockerfile = dockerfile
         # Ports published on the host (0.0.0.0). Used by the Firecracker
         # backend's dev-harness gateway so VMs can reach it via their TAP link;
@@ -72,9 +75,10 @@ class DockerGateway(Gateway):
         forces a full rebuild (parity with `start --no-cache`)."""
         if self._dockerfile is None:
             return
+        context = self._build_context or resources.build_root()
         argv = ["docker", "build", "-t", self.image_ref,
-                "-f", str(self._build_context / self._dockerfile),
+                "-f", str(context / self._dockerfile),
-                str(self._build_context)]
+                str(context)]
         if os.environ.get("BOT_BOTTLE_NO_CACHE"):
             argv.insert(2, "--no-cache")
         proc = run_docker(argv)

bot_bottle/backend/docker/infra.py

@@ -34,6 +34,7 @@ from .orchestrator import (
     ORCHESTRATOR_NETWORK,
 )
 from ...paths import bot_bottle_root
+from ... import resources
 from ...gateway import (
     GATEWAY_IMAGE,
     GATEWAY_NAME,
@@ -50,8 +51,6 @@ from ...orchestrator.lifecycle import (
 # the pair's public identity.
 INFRA_NAME = GATEWAY_NAME  # the container agents attribute against is the gateway
 
-_REPO_ROOT = Path(__file__).resolve().parents[3]
-
 
 class DockerInfraService(InfraService):
     """Composes the per-host control plane + gateway as two containers.
@@ -68,7 +67,7 @@ class DockerInfraService(InfraService):
         control_network: str = ORCHESTRATOR_NETWORK,
         orchestrator_image: str = ORCHESTRATOR_IMAGE,
         gateway_image: str = GATEWAY_IMAGE,
-        repo_root: Path = _REPO_ROOT,
+        repo_root: Path | None = None,
         host_root: Path | None = None,
         orchestrator_name: str = ORCHESTRATOR_NAME,
         orchestrator_label: str = ORCHESTRATOR_LABEL,
@@ -79,7 +78,9 @@ class DockerInfraService(InfraService):
         self.control_network = control_network
         self.orchestrator_image = orchestrator_image
         self.gateway_image = gateway_image
-        self._repo_root = repo_root
+        # Build context / bind-mount source: the repo root in a checkout, a
+        # staged copy from the installed wheel otherwise (bot_bottle.resources).
+        self._repo_root = repo_root if repo_root is not None else resources.build_root()
         self._host_root = host_root or bot_bottle_root()
         self._orchestrator_name = orchestrator_name
         self._orchestrator_label = orchestrator_label

bot_bottle/backend/docker/launch.py

@@ -33,7 +33,6 @@ from __future__ import annotations
 import dataclasses
 import os
 from contextlib import ExitStack, contextmanager
-from pathlib import Path
 from typing import Callable, Generator
 
 from ...agent_provider import runtime_for
@@ -65,10 +64,7 @@ from ...orchestrator.store.config_store import resolve_teardown_timeout
 from .consolidated_launch import launch_consolidated, deprovision_consolidated
 from .infra import INFRA_NAME
 from .gateway import DockerGateway
-
+from ... import resources
-
-# Where the repo root lives, for `docker build` context. Computed once.
-_REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
 
 
 def build_or_load_images(plan: DockerBottlePlan) -> BottleImages:
@@ -88,7 +84,7 @@ def build_or_load_images(plan: DockerBottlePlan) -> BottleImages:
             )
         info(f"using cached agent image {plan.image!r}")
         return BottleImages(agent=plan.image)
-    docker_mod.build_image(plan.image, _REPO_DIR, dockerfile=plan.dockerfile_path)
+    docker_mod.build_image(plan.image, str(resources.build_root()), dockerfile=plan.dockerfile_path)
     docker_mod.verify_agent_image(
         plan.image, runtime_for(plan.agent_provider_template).smoke_test,
     )

bot_bottle/backend/docker/orchestrator.py

@@ -15,11 +15,11 @@ import time
 from pathlib import Path
 
 from ... import log
+from ... import resources
 from .util import run_docker
 from ...paths import (
     ORCHESTRATOR_TOKEN_ENV,
     bot_bottle_root,
-    host_orchestrator_token,
 )
 from ...gateway import GatewayError
 from ...orchestrator.lifecycle import (
@@ -56,8 +56,6 @@ _ROOT_IN_CONTAINER = "/bot-bottle-root"
 
 _HEALTH_POLL_SECONDS = 0.25
 
-_REPO_ROOT = Path(__file__).resolve().parents[3]
-
 
 class DockerOrchestrator(Orchestrator):
     """The control plane as a single fixed-name container. `ensure_built` builds
@@ -72,7 +70,7 @@ class DockerOrchestrator(Orchestrator):
         label: str = ORCHESTRATOR_LABEL,
         port: int = DEFAULT_PORT,
         control_network: str = ORCHESTRATOR_NETWORK,
-        repo_root: Path = _REPO_ROOT,
+        repo_root: Path | None = None,
         host_root: Path | None = None,
         dockerfile: str | None = ORCHESTRATOR_DOCKERFILE,
     ) -> None:
@@ -81,7 +79,9 @@ class DockerOrchestrator(Orchestrator):
         self.label = label
         self.port = port
         self.control_network = control_network
-        self._repo_root = repo_root
+        # Build context / bind-mount source: the repo root in a checkout, a
+        # staged copy from the installed wheel otherwise (bot_bottle.resources).
+        self._repo_root = repo_root if repo_root is not None else resources.build_root()
         self._host_root = host_root or bot_bottle_root()
         self._dockerfile = dockerfile
 
@@ -171,7 +171,9 @@ class DockerOrchestrator(Orchestrator):
         fixed-name container first)."""
         self._ensure_control_network()
         run_docker(["docker", "rm", "--force", self.name])
-        _signing_key = host_orchestrator_token()
+        # The signing key comes through the shared provisioning contract (#476),
+        # which fail-closes rather than yield an empty key that would run OPEN.
+        _signing_key = self.control_plane_key()
         proc = run_docker([
             "docker", "run", "--detach",
             "--name", self.name,

bot_bottle/backend/firecracker/infra_artifact.py

@@ -37,6 +37,7 @@ import urllib.error
 import urllib.request
 from pathlib import Path
 
+from ... import resources
 from ...log import die, info
 from . import util
 
@@ -44,8 +45,6 @@ from . import util
 # scheme can't collide with a cached/published artifact of the old one.
 _ARTIFACT_FORMAT = "1"
 
-_REPO_ROOT = Path(__file__).resolve().parents[3]
-
 # The two per-plane infra VM roles. Each publishes/pulls its own rootfs artifact
 # from its own generic package; the Dockerfiles baked into each differ (only the
 # orchestrator rootfs carries buildah), so the versions are hashed separately.
@@ -74,7 +73,7 @@ def local_build_requested() -> bool:
 
 
 def infra_artifact_version(
-    init_script: str, role: str, *, repo_root: Path = _REPO_ROOT,
+    init_script: str, role: str, *, repo_root: Path | None = None,
 ) -> str:
     """Content hash (16 hex) of everything baked into `role`'s infra rootfs: the
     whole shipped `bot_bottle` package, that role's Dockerfiles, and its guest
@@ -89,6 +88,8 @@ def infra_artifact_version(
     version or a launch host could boot a stale rootfs whose code differs from
     its checkout. `__pycache__`/`.pyc` are the only exclusions — build artifacts,
     never copied."""
+    if repo_root is None:
+        repo_root = resources.build_root()
     h = hashlib.sha256()
     h.update(f"format={_ARTIFACT_FORMAT}\nrole={role}\n".encode())
     pkg = repo_root / "bot_bottle"

bot_bottle/backend/firecracker/infra_vm.py

@@ -42,6 +42,7 @@ from dataclasses import dataclass
 from pathlib import Path
 from typing import Generator
 
+from ... import resources
 from ...log import die, info
 from ..docker import util as docker_mod
 from . import firecracker_vm, infra_artifact, netpool, util
@@ -65,7 +66,6 @@ _GUEST_GATEWAY_JWT_PATH = "/var/lib/bot-bottle/gateway-jwt"
 _GATEWAY_IMAGE = "bot-bottle-gateway:latest"
 _ORCHESTRATOR_IMAGE = "bot-bottle-orchestrator:latest"
 _ORCHESTRATOR_FC_IMAGE = "bot-bottle-orchestrator-fc:latest"
-_REPO_ROOT = Path(__file__).resolve().parents[3]
 
 # Per-role rootfs source image + the extra free space `mke2fs` leaves for the
 # guest to grow into. The orchestrator keeps buildah's large build slack; the
@@ -130,12 +130,13 @@ def build_infra_images_with_docker() -> None:
     orchestrator + buildah). The gateway VM boots the gateway image directly.
     The launch host uses this only in `BOT_BOTTLE_INFRA_BUILD=local` mode;
     `publish_infra` uses it off-host to produce the published artifacts."""
+    root = str(resources.build_root())
     docker_mod.build_image(
-        _ORCHESTRATOR_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.orchestrator")
+        _ORCHESTRATOR_IMAGE, root, dockerfile="Dockerfile.orchestrator")
     docker_mod.build_image(
-        _GATEWAY_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.gateway")
+        _GATEWAY_IMAGE, root, dockerfile="Dockerfile.gateway")
     docker_mod.build_image(
-        _ORCHESTRATOR_FC_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.orchestrator.fc")
+        _ORCHESTRATOR_FC_IMAGE, root, dockerfile="Dockerfile.orchestrator.fc")
 
 
 def build_rootfs_dir(role: str) -> Path:

bot_bottle/backend/firecracker/orchestrator.py

@@ -21,7 +21,6 @@ import time
 from pathlib import Path
 
 from ...log import die, info
-from ...paths import host_orchestrator_token
 from ...orchestrator.lifecycle import (
     DEFAULT_STARTUP_TIMEOUT_SECONDS,
     Orchestrator,
@@ -108,11 +107,13 @@ class FirecrackerOrchestrator(Orchestrator):
             data_drive=self._ensure_registry_volume(),
         )
         # Push the host-canonical signing key (the init waits for it before
-        # starting the control plane). The host token file stays the single
+        # starting the control plane). It comes through the shared provisioning
-        # source of truth, so a co-running docker/macOS control plane keeps
+        # contract (#476) — the same host token file every backend uses, so a
-        # working; the guest verifies tokens with the same key the CLI signs from.
+        # co-running docker/macOS control plane keeps working and the guest
+        # verifies tokens with the same key the CLI signs from; fail-closed, so
+        # the guest is never handed an empty key that would run it OPEN.
         infra_vm.push_secret(
-            vm, host_orchestrator_token(), infra_vm._GUEST_SIGNING_KEY_PATH,
+            vm, self.control_plane_key(), infra_vm._GUEST_SIGNING_KEY_PATH,
             "the control-plane signing key to the orchestrator VM "
             "(its control plane will not start)",
         )

bot_bottle/backend/firecracker/setup.py

@@ -20,6 +20,7 @@ import subprocess
 import sys
 from pathlib import Path
 
+from ... import resources
 from . import netpool
 from . import util
 
@@ -42,13 +43,13 @@ def _has_systemd() -> bool:
 
 
 def _module_path() -> str:
-    """Absolute path to the importable NixOS module in this checkout."""
+    """Absolute path to the importable NixOS module (checkout or wheel)."""
-    return str(Path(__file__).resolve().parents[3] / "nix" / "firecracker-netpool.nix")
+    return str(resources.nix_netpool_module())
 
 
 def _script_path() -> str:
-    """Absolute path to the bundled bring-up script in this checkout."""
+    """Absolute path to the bundled bring-up script (checkout or wheel)."""
-    return str(Path(__file__).resolve().parents[3] / "scripts" / "firecracker-netpool.sh")
+    return str(resources.netpool_script())
 
 
 def _print_prereqs() -> None:

bot_bottle/backend/macos_container/gateway.py

@@ -28,6 +28,7 @@ from ...paths import (
     ORCHESTRATOR_AUTH_JWT_ENV,
     host_gateway_ca_dir,
 )
+from ... import resources
 from .. import util as backend_util
 from . import util as container_mod
 
@@ -52,8 +53,6 @@ GATEWAY_DAEMONS = "egress,git-http,supervise"
 
 GATEWAY_IMAGE = os.environ.get("BOT_BOTTLE_GATEWAY_IMAGE", "bot-bottle-gateway:latest")
 
-_REPO_ROOT = Path(__file__).resolve().parents[3]
-
 
 def ensure_networks(
     network: str = GATEWAY_NETWORK,
@@ -84,14 +83,16 @@ class MacosGateway(Gateway):
         network: str = GATEWAY_NETWORK,
         egress_network: str = GATEWAY_EGRESS_NETWORK,
         control_network: str = CONTROL_NETWORK,
-        repo_root: Path = _REPO_ROOT,
+        repo_root: Path | None = None,
     ) -> None:
         self.image_ref = image_ref
         self.name = name
         self.network = network
         self.egress_network = egress_network
         self.control_network = control_network
-        self._repo_root = repo_root
+        # Build context: the repo root in a checkout, a staged copy from the
+        # installed wheel otherwise (bot_bottle.resources).
+        self._repo_root = repo_root if repo_root is not None else resources.build_root()
         # Set by `connect_to_orchestrator`: the URL the daemons resolve policy
         # against + the pre-minted `gateway` token they present. The gateway
         # never mints, so it never holds the signing key (#469).

bot_bottle/backend/macos_container/infra.py

@@ -24,6 +24,7 @@ from __future__ import annotations
 
 from pathlib import Path
 
+from ... import resources
 from ...orchestrator.lifecycle import (
     DEFAULT_PORT,
     DEFAULT_STARTUP_TIMEOUT_SECONDS,
@@ -53,8 +54,6 @@ from .orchestrator import (
 # still import it (probe / reprovision attribute against the gateway).
 INFRA_NAME = GATEWAY_NAME
 
-_REPO_ROOT = Path(__file__).resolve().parents[3]
-
 
 class MacosInfraService(InfraService):
     """Composes the per-host orchestrator + gateway containers. Callers use
@@ -70,7 +69,7 @@ class MacosInfraService(InfraService):
         control_network: str = CONTROL_NETWORK,
         gateway_image: str = GATEWAY_IMAGE,
         orchestrator_image: str = ORCHESTRATOR_IMAGE,
-        repo_root: Path = _REPO_ROOT,
+        repo_root: Path | None = None,
         orchestrator_name: str = ORCHESTRATOR_NAME,
         gateway_name: str = INFRA_NAME,
         db_volume: str = ORCHESTRATOR_DB_VOLUME,
@@ -81,7 +80,9 @@ class MacosInfraService(InfraService):
         self.control_network = control_network
         self.gateway_image = gateway_image
         self.orchestrator_image = orchestrator_image
-        self._repo_root = repo_root
+        # Build context / bind-mount source: the repo root in a checkout, a
+        # staged copy from the installed wheel otherwise (bot_bottle.resources).
+        self._repo_root = repo_root if repo_root is not None else resources.build_root()
         self._orchestrator_name = orchestrator_name
         self._gateway_name = gateway_name
         self._db_volume = db_volume

bot_bottle/backend/macos_container/launch.py

@@ -36,7 +36,6 @@ import dataclasses
 import os
 import subprocess
 from contextlib import ExitStack, contextmanager
-from pathlib import Path
 from typing import Callable, Generator
 
 from ...bottle_state import (
@@ -49,6 +48,7 @@ from ...git_gate import GitGate
 from ...gateway.git_gate.http_backend import DEFAULT_PORT as _GIT_HTTP_PORT
 from ...image_cache import check_stale
 from ...log import die, info, warn
+from ... import resources
 from .. import BottleImages
 from ...supervisor.types import SUPERVISE_PORT
 from ..docker.egress import EGRESS_PORT
@@ -71,7 +71,6 @@ from .consolidated_launch import (
     deprovision_consolidated,
 )
 
-_REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
 _AGENT_SLEEP_SECONDS = "2147483647"
 
 
@@ -94,7 +93,7 @@ def _agent_image(plan: MacosContainerBottlePlan) -> str:
             )
         info(f"using cached agent image {plan.image!r}")
         return plan.image
-    container_mod.build_image(plan.image, _REPO_DIR, dockerfile=plan.dockerfile_path)
+    container_mod.build_image(plan.image, str(resources.build_root()), dockerfile=plan.dockerfile_path)
     return plan.image
 
 

bot_bottle/backend/macos_container/orchestrator.py

@@ -18,10 +18,8 @@ import urllib.request
 from pathlib import Path
 
 from ... import log
-from ...paths import (
+from ... import resources
-    ORCHESTRATOR_TOKEN_ENV,
+from ...paths import ORCHESTRATOR_TOKEN_ENV
-    host_orchestrator_token,
-)
 from ...orchestrator.lifecycle import (
     DEFAULT_HEALTH_TIMEOUT_SECONDS,
     DEFAULT_PORT,
@@ -48,7 +46,6 @@ _DB_ROOT_IN_CONTAINER = "/var/lib/bot-bottle"
 _SRC_IN_CONTAINER = "/bot-bottle-src"
 
 _HEALTH_POLL_SECONDS = 0.25
-_REPO_ROOT = Path(__file__).resolve().parents[3]
 
 
 class MacosOrchestrator(Orchestrator):
@@ -64,7 +61,7 @@ class MacosOrchestrator(Orchestrator):
         label: str = ORCHESTRATOR_LABEL,
         port: int = DEFAULT_PORT,
         control_network: str = CONTROL_NETWORK,
-        repo_root: Path = _REPO_ROOT,
+        repo_root: Path | None = None,
         db_volume: str = ORCHESTRATOR_DB_VOLUME,
     ) -> None:
         self.image_ref = image_ref
@@ -72,7 +69,9 @@ class MacosOrchestrator(Orchestrator):
         self.label = label
         self.port = port
         self.control_network = control_network
-        self._repo_root = repo_root
+        # Build context / bind-mount source: the repo root in a checkout, a
+        # staged copy from the installed wheel otherwise (bot_bottle.resources).
+        self._repo_root = repo_root if repo_root is not None else resources.build_root()
         self._db_volume = db_volume
 
     def url(self) -> str:
@@ -134,7 +133,9 @@ class MacosOrchestrator(Orchestrator):
 
     def _run_container(self, current_hash: str) -> None:
         container_mod.force_remove_container(self.name)
-        _signing_key = host_orchestrator_token()
+        # The signing key comes through the shared provisioning contract (#476),
+        # which fail-closes rather than yield an empty key that would run OPEN.
+        _signing_key = self.control_plane_key()
         argv = [
             "container", "run", "--detach",
             "--name", self.name,

bot_bottle/cli/commands/__init__.py

@@ -21,6 +21,7 @@ _HANDLERS: dict[str, str] = {
     "backend": "backend:cmd_backend",
     "cleanup": "cleanup:cmd_cleanup",
     "commit": "commit:cmd_commit",
+    "doctor": "doctor:cmd_doctor",
     "edit": "edit:cmd_edit",
     "help": "help:cmd_help",
     "init": "init:cmd_init",
@@ -53,6 +54,6 @@ COMMANDS = {name: _lazy(spec) for name, spec in _HANDLERS.items()}
 # gating it on the schema breaks preflight on a fresh CI runner where stdin
 # isn't a TTY and the migration prompt can't be answered. `help` and `login`
 # likewise never touch the store.
-NO_MIGRATION_COMMANDS = frozenset({"backend", "help", "login"})
+NO_MIGRATION_COMMANDS = frozenset({"backend", "doctor", "help", "login"})
 
 __all__ = ["COMMANDS", "NO_MIGRATION_COMMANDS"]

bot_bottle/cli/commands/doctor.py

@@ -0,0 +1,88 @@
+"""`doctor` CLI command — validate host prerequisites for running
+bot-bottle and report what's ready.
+
+Fails (non-zero exit) only on the two hard requirements: a new-enough
+Python and at least one backend that is *ready* (passes its full status
+checks, so `start` can actually work). The config directory is a soft
+check — `install.sh` creates it, but a missing one only warrants a note,
+not a failure, since `start` provisions what it needs on first run.
+"""
+
+from __future__ import annotations
+
+import argparse
+import sys
+from pathlib import Path
+
+from ...backend import is_backend_ready, known_backend_names
+from ..constants import PROG
+
+MIN_PYTHON = (3, 11)
+CONFIG_DIR = ".bot-bottle"
+
+
+def _ok(label: str, detail: str) -> None:
+    print(f"ok:   {label}: {detail}")
+
+
+def _warn(label: str, detail: str) -> None:
+    print(f"warn: {label}: {detail}")
+
+
+def _fail(label: str, detail: str) -> None:
+    print(f"fail: {label}: {detail}")
+
+
+def _check_python() -> bool:
+    v = sys.version_info
+    detail = f"{v.major}.{v.minor}.{v.micro}"
+    if (v.major, v.minor) >= MIN_PYTHON:
+        _ok("python", detail)
+        return True
+    _fail("python", f"{detail}; need {MIN_PYTHON[0]}.{MIN_PYTHON[1]} or newer")
+    return False
+
+
+def _check_backends() -> bool:
+    """At least one backend must be *ready* to run a bottle — i.e. pass its
+    full status() checks (daemon reachable, network pool present, KVM usable),
+    not merely have a binary on PATH. A binary-only check would report `ok`
+    on a host with a stopped Docker daemon or a half-configured Firecracker,
+    where `start` still can't work. Each not-ready backend prints its own
+    diagnostics (quiet=False) so the operator sees exactly what's missing."""
+    ready = []
+    for name in known_backend_names():
+        if is_backend_ready(name, quiet=False):
+            _ok("backend", f"{name}: ready")
+            ready.append(name)
+        else:
+            _warn("backend", f"{name}: not ready (see diagnostics above)")
+    if ready:
+        return True
+    _fail(
+        "backend",
+        "no backend is ready to run a bottle; start Docker, or finish "
+        "Apple Container (macOS) / Firecracker (Linux) setup",
+    )
+    return False
+
+
+def _check_config_dir() -> None:
+    config = Path.home() / CONFIG_DIR
+    if config.is_dir():
+        _ok("config", str(config))
+    else:
+        _warn("config", f"{config} does not exist yet (created on first use)")
+
+
+def cmd_doctor(argv: list[str]) -> int:
+    parser = argparse.ArgumentParser(
+        prog=f"{PROG} doctor",
+        description="Check host prerequisites for running bot-bottle.",
+    )
+    parser.parse_args(argv)
+
+    # Hard requirements gate the exit code; the config note is advisory.
+    required = [_check_python(), _check_backends()]
+    _check_config_dir()
+    return 0 if all(required) else 1

bot_bottle/cli/commands/help.py

@@ -25,6 +25,7 @@ def cmd_help(argv: list[str] | None = None) -> int:
     w("  backend   set up / check / undo a backend's host prerequisites (setup|status|teardown)\n")
     w("  cleanup   stop and remove all active bot-bottle containers\n")
     w("  commit    snapshot a running bottle's container state to a Docker image\n")
+    w("  doctor    check host prerequisites (Python, backend, config dir)\n")
     w("  edit      open an agent in vim for editing\n")
     w("  help      show this command list\n")
     w("  init      interactively create a new agent and add it to bot-bottle.json\n")

bot_bottle/gateway/__init__.py

@@ -62,7 +62,6 @@ GATEWAY_CA_GLOB = "mitmproxy-ca*"
 # that lands. Env override matches the backend's BOT_BOTTLE_GATEWAY_IMAGE.
 GATEWAY_IMAGE = os.environ.get("BOT_BOTTLE_GATEWAY_IMAGE", "bot-bottle-gateway:latest")
 GATEWAY_DOCKERFILE = "Dockerfile.gateway"
-REPO_ROOT = Path(__file__).resolve().parents[2]
 
 
 def rotate_gateway_ca(ca_dir: Path | None = None) -> list[Path]:

bot_bottle/orchestrator/client.py

@@ -18,8 +18,8 @@ import urllib.request
 from collections.abc import Iterable
 from dataclasses import dataclass
 
-from ..orchestrator_auth import ROLE_CLI, mint
+from ..orchestrator_auth import ROLE_CLI
-from ..paths import host_orchestrator_token
+from ..trust_domain import CONTROL_PLANE
 from .server import ORCHESTRATOR_AUTH_HEADER
 
 DEFAULT_TIMEOUT_SECONDS = 5.0
@@ -32,7 +32,7 @@ def _host_auth_token() -> str:
     "" means 'send no auth header' — correct against an open (unconfigured)
     control plane, and harmlessly rejected by a secured one."""
     try:
-        return mint(ROLE_CLI, host_orchestrator_token())
+        return CONTROL_PLANE.mint(ROLE_CLI)
     except (OSError, ValueError):
         return ""
 

bot_bottle/orchestrator/lifecycle.py

@@ -21,8 +21,7 @@ import urllib.error
 import urllib.request
 from pathlib import Path
 
-from ..orchestrator_auth import ROLE_GATEWAY, mint
+from ..trust_domain import ControlPlaneProvisioning
-from ..paths import host_orchestrator_token
 
 DEFAULT_PORT = 8099
 DEFAULT_STARTUP_TIMEOUT_SECONDS = 45.0
@@ -58,6 +57,12 @@ class Orchestrator(abc.ABC):
     so it — not the gateway — mints the gateway's role-scoped token.
     Backend-neutral."""
 
+    # The shared control-plane auth provisioning contract (#476). Every backend
+    # gets its signing key + gateway token through this one seam rather than
+    # re-deriving the wiring; it is fail-closed for every backend — the
+    # orchestrator never starts without its signing key.
+    provisioning: ControlPlaneProvisioning = ControlPlaneProvisioning()
+
     def ensure_built(self) -> None:
         """Ensure the orchestrator's image / rootfs exists, building it if
         needed. Default: nothing to build (e.g. a pre-pulled image). Call before
@@ -105,9 +110,17 @@ class Orchestrator(abc.ABC):
     def mint_gateway_token(self) -> str:
         """Mint a role-scoped `gateway` JWT from the host signing key for the
         gateway to present. The orchestrator holds the key; the gateway never
-        does (#469). Backend-neutral — the same host token file is the single
+        does (#469). Routed through the shared provisioning contract (#476), so
-        source of truth across backends."""
+        the same host token file is the single source of truth across backends."""
-        return mint(ROLE_GATEWAY, host_orchestrator_token())
+        return self.provisioning.gateway_token()
+
+    def control_plane_key(self) -> str:
+        """The raw signing key the control-plane *process* must receive — the ONE
+        place a backend obtains it (docker/macOS inject it as `key_env`;
+        firecracker pushes it to the guest). Fail-closed via the provisioning
+        contract: it raises rather than yield an empty key that would run the
+        server OPEN (#476)."""
+        return self.provisioning.orchestrator_key()
 
 
 __all__ = [
@@ -117,4 +130,5 @@ __all__ = [
     "OrchestratorStartError",
     "source_hash",
     "Orchestrator",
+    "ControlPlaneProvisioning",
 ]

bot_bottle/orchestrator/server.py

@@ -63,8 +63,8 @@ import sys
 import typing
 from urllib.parse import urlsplit
 
-from ..orchestrator_auth import ROLE_CLI, ROLES, verify
+from ..orchestrator_auth import ROLE_CLI, ROLES
-from ..paths import ORCHESTRATOR_TOKEN_ENV
+from ..trust_domain import CONTROL_PLANE
 from ..supervisor.types import TOOLS
 from .service import OrchestratorCore
 
@@ -413,11 +413,13 @@ class OrchestratorServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
 
     def __init__(self, address: tuple[str, int], orchestrator: OrchestratorCore) -> None:
         self.orchestrator = orchestrator
-        self._signing_key = os.environ.get(ORCHESTRATOR_TOKEN_ENV, "").strip()
+        # The control-plane trust domain's signing key, as injected into THIS
+        # (the owning) process by the launcher (#476). Unset → open mode below.
+        self._signing_key = CONTROL_PLANE.key_from_env()
         if not self._signing_key:
             sys.stderr.write(
                 "orchestrator: WARNING — no control-plane signing key "
-                f"(${ORCHESTRATOR_TOKEN_ENV}); running WITHOUT caller "
+                f"(${CONTROL_PLANE.key_env}); running WITHOUT caller "
                 "authentication. Any client that can reach this port can drive "
                 "it. Backends that put the control plane on an agent-reachable "
                 "network MUST set this.\n"
@@ -433,7 +435,7 @@ class OrchestratorServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
         role (→ per-route 401/403 in `dispatch`)."""
         if not self._signing_key:
             return ROLE_CLI
-        return verify(presented, self._signing_key)
+        return CONTROL_PLANE.verify(presented, self._signing_key)
 
 
 def make_server(

bot_bottle/orchestrator_auth.py

@@ -59,12 +59,17 @@ _HEADER_SEGMENT = _b64url_encode(
 )
 
 
-def mint(role: str, secret: str) -> str:
+def mint(role: str, secret: str, *, roles: frozenset[str] = ROLES) -> str:
     """A compact HS256 token asserting `role`, signed with `secret`.
 
-    Raises ValueError for an unknown role (mint only what the control plane will
+    `roles` is the set the signing key is allowed to sign (default: the
-    accept) or an empty signing key (an unsigned credential is never valid)."""
+    orchestrator's `{gateway, cli}`). A separate service (e.g. the host
-    if role not in ROLES:
+    controller) passes its own key + role set so its tokens can't be forged with
+    the orchestrator's key — see `trust_domain.py`, issues #476/#468.
+
+    Raises ValueError for a role outside `roles`, or an empty signing key (an
+    unsigned credential is never valid)."""
+    if role not in roles:
         raise ValueError(f"unknown control-plane role {role!r}")
     if not secret:
         raise ValueError("cannot mint a control-plane token without a signing key")
@@ -73,10 +78,11 @@ def mint(role: str, secret: str) -> str:
     return f"{signing_input}.{_sign(secret, signing_input)}"
 
 
-def verify(token: str, secret: str) -> str | None:
+def verify(token: str, secret: str, *, roles: frozenset[str] = ROLES) -> str | None:
     """The role a valid `token` carries, or None if it is malformed, wrongly
-    signed, or names an unknown role. Constant-time signature check; rejects any
+    signed, or names a role outside `roles` (the verifying trust domain's set —
-    header whose alg isn't HS256 (no alg-confusion / `none`)."""
+    default `{gateway, cli}`). Constant-time signature check; rejects any header
+    whose alg isn't HS256 (no alg-confusion / `none`)."""
     if not token or not secret:
         return None
     parts = token.split(".")
@@ -94,7 +100,7 @@ def verify(token: str, secret: str) -> str | None:
     if not isinstance(header, dict) or header.get("alg") != _ALG:
         return None
     role = payload.get("role") if isinstance(payload, dict) else None
-    return role if isinstance(role, str) and role in ROLES else None
+    return role if isinstance(role, str) and role in roles else None
 
 
 __all__ = ["ROLE_GATEWAY", "ROLE_CLI", "ROLES", "mint", "verify"]

bot_bottle/paths.py

@@ -97,16 +97,17 @@ def host_gateway_ca_dir() -> Path:
     return ca_dir
 
 
-def host_orchestrator_token() -> str:
+def host_signing_key(filename: str) -> str:
-    """The per-host control-plane secret, minted (256-bit, url-safe) and
+    """A per-host signing key at `<root>/<filename>`, minted (256-bit, url-safe)
-    persisted 0600 on first use, then reused.
+    and persisted 0600 on first use, then reused.
 
-    This is the shared secret the launchers inject into the control-plane and
+    The generic form of `host_orchestrator_token()`: each service names its own
-    gateway containers and that the host CLI presents on every call. It is a
+    key file (`trust_domain.py`), so the orchestrator and a separate service like
-    *host* artifact — the file lives under the root the agent never mounts, and
+    the host controller (#468) get distinct keys neither can read. It is a *host*
-    the env var is set only on the trusted containers — so reading it here is
+    artifact — the file lives under the root the agent never mounts, and its value
-    safe on the host launch path but the value never reaches a bottle."""
+    is injected only into the trusted control-plane process — so reading it here
-    path = bot_bottle_root() / ORCHESTRATOR_TOKEN_FILENAME
+    is safe on the launch path but the value never reaches a bottle."""
+    path = bot_bottle_root() / filename
     try:
         existing = path.read_text().strip()
         if existing:
@@ -128,6 +129,14 @@ def host_orchestrator_token() -> str:
     return token
 
 
+def host_orchestrator_token() -> str:
+    """The per-host control-plane signing key — the host-canonical key the
+    launchers inject into the control-plane process and the host CLI mints its
+    own `cli` token from. The `control-plane` trust domain's specialization of
+    `host_signing_key()`."""
+    return host_signing_key(ORCHESTRATOR_TOKEN_FILENAME)
+
+
 __all__ = [
     "HOST_DB_FILENAME",
     "ORCHESTRATOR_TOKEN_FILENAME",
@@ -138,5 +147,6 @@ __all__ = [
     "host_db_path",
     "host_db_dir",
     "host_gateway_ca_dir",
+    "host_signing_key",
     "host_orchestrator_token",
 ]

bot_bottle/resources.py

@@ -0,0 +1,159 @@
+"""Locate build-time resources whether bot-bottle runs from a source
+checkout or an installed wheel.
+
+The gateway / infra / orchestrator images are built from a Docker (or Apple
+`container`) build context that must contain the `bot_bottle` package,
+`pyproject.toml`, and the root-level Dockerfiles as siblings. In a source
+checkout that context is simply the repo root, one level above the package.
+An installed wheel has no repo root: the same root-level files are shipped
+inside the package under ``bot_bottle/_resources/`` (see ``setup.py``), and a
+repo-root-shaped build context is staged on demand into the app-data dir.
+
+``build_root()`` is the single source of truth — it returns a directory laid
+out like a repo root (has ``bot_bottle/``, ``pyproject.toml``, the
+Dockerfiles, ``nix/``, ``scripts/``). Every caller that needs a build
+context, a Dockerfile path, the nix netpool module, or the netpool script
+derives from it, so checkout and wheel installs share one downstream path.
+"""
+
+from __future__ import annotations
+
+import fcntl
+import hashlib
+import os
+import shutil
+import tempfile
+from pathlib import Path
+
+from .paths import bot_bottle_root
+
+_PKG = Path(__file__).resolve().parent          # …/bot_bottle
+_CHECKOUT_ROOT = _PKG.parent                     # repo root in a checkout
+_BUNDLED = _PKG / "_resources"                   # wheel-shipped copies
+
+# Root-level files bundled into the wheel under ``_resources/`` (paths are
+# relative to the checkout root, and preserved verbatim under ``_resources/``
+# and in the staged build root). ``setup.py`` copies exactly this set; keep
+# the two lists in sync (``test_resources`` guards that every entry exists).
+BUNDLED_RESOURCES: tuple[str, ...] = (
+    "pyproject.toml",
+    "Dockerfile.gateway",
+    "Dockerfile.orchestrator",
+    "Dockerfile.orchestrator.fc",
+    "nix/firecracker-netpool.nix",
+    "scripts/firecracker-netpool.sh",
+)
+
+# Present at a checkout root, never in a bare installed package — the cheap
+# tell for which layout we're in.
+_CHECKOUT_MARKER = "Dockerfile.gateway"
+
+
+class ResourceError(RuntimeError):
+    """Build resources are missing from the install (corrupt/partial wheel)."""
+
+
+def is_source_checkout() -> bool:
+    """True when running from a source tree (the root Dockerfiles sit beside
+    the package); False from an installed wheel."""
+    return (_CHECKOUT_ROOT / _CHECKOUT_MARKER).is_file()
+
+
+def build_root() -> Path:
+    """A directory shaped like a repo root: ``bot_bottle/``, ``pyproject.toml``,
+    the root Dockerfiles, ``nix/``, and ``scripts/``.
+
+    A checkout returns the repo root itself (no copying). An installed wheel
+    returns a staged copy under the app-data dir, materialized once and reused.
+    The stage is keyed by a digest of the installed package + bundled resources
+    (not the distribution version), so a force-reinstall of a newer commit that
+    keeps ``version = 0.1.0`` still rebuilds instead of reusing a stale tree."""
+    if is_source_checkout():
+        return _CHECKOUT_ROOT
+    return _stage_build_root()
+
+
+def dockerfile(name: str) -> Path:
+    """Absolute path to a root-level Dockerfile, e.g. ``Dockerfile.gateway``."""
+    return build_root() / name
+
+
+def nix_netpool_module() -> Path:
+    """Absolute path to the firecracker netpool NixOS module."""
+    return build_root() / "nix" / "firecracker-netpool.nix"
+
+
+def netpool_script() -> Path:
+    """Absolute path to the firecracker netpool bring-up script."""
+    return build_root() / "scripts" / "firecracker-netpool.sh"
+
+
+def _content_digest() -> str:
+    """A 16-hex digest of the installed package + bundled resources.
+
+    Keys the staged build root by *content*, so a force-reinstall over the same
+    version string (the installer defaults to a git branch + ``pipx install
+    --force``, and ``version`` stays ``0.1.0``) yields a different key and
+    re-stages, rather than reusing an old commit's tree. ``_PKG`` already
+    contains ``_resources``, so walking it covers both."""
+    h = hashlib.sha256()
+    for path in sorted(_PKG.rglob("*")):
+        if not path.is_file() or "__pycache__" in path.parts or path.suffix == ".pyc":
+            continue
+        h.update(str(path.relative_to(_PKG)).encode())
+        h.update(b"\0")
+        h.update(path.read_bytes())
+    return h.hexdigest()[:16]
+
+
+def _stage_build_root() -> Path:
+    """Materialize a repo-root-shaped build context from the installed wheel's
+    bundled resources, keyed by content digest. Idempotent and concurrency-safe:
+    a file lock serializes staging, a partial/stale tree is replaced, and the
+    finished tree is published with an atomic rename."""
+    if not _BUNDLED.is_dir():
+        raise ResourceError(
+            "bot-bottle build resources are missing from this install "
+            f"(expected {_BUNDLED}). Reinstall the package."
+        )
+    base = bot_bottle_root() / "build-root"
+    base.mkdir(parents=True, exist_ok=True)
+    dest = base / _content_digest()
+    if (dest / ".complete").is_file():
+        return dest
+
+    # Serialize staging across processes: a concurrent `start` after an install
+    # must not race on the shared tree. The lock is held only around stage +
+    # atomic publish; the fast path above never blocks.
+    with open(base / ".stage.lock", "w", encoding="utf-8") as lock:
+        fcntl.flock(lock, fcntl.LOCK_EX)
+        if (dest / ".complete").is_file():  # another process staged while we waited
+            return dest
+        # Stage into a private temp dir on the same filesystem, then publish by
+        # rename — never populate a shared path other processes might read.
+        staging = Path(tempfile.mkdtemp(prefix=".staging-", dir=base))
+        try:
+            # The package itself, minus caches and the bundled-resource copies,
+            # so the staged ``bot_bottle/`` matches a checkout's (keeps the
+            # firecracker infra-artifact hash stable across checkout and wheel).
+            shutil.copytree(
+                _PKG,
+                staging / "bot_bottle",
+                ignore=shutil.ignore_patterns("__pycache__", "*.pyc", "_resources"),
+            )
+            # The bundled root files, restored to their checkout-relative layout.
+            for rel in BUNDLED_RESOURCES:
+                dst = staging / rel
+                dst.parent.mkdir(parents=True, exist_ok=True)
+                shutil.copy2(_BUNDLED / rel, dst)
+            (staging / ".complete").write_text("")
+            # Replace any partial leftover for this digest (safe: we hold the
+            # lock), then publish atomically.
+            if dest.exists():
+                shutil.rmtree(dest)
+            os.replace(staging, dest)
+            staging = None  # published; nothing to clean up
+        finally:
+            if staging is not None:
+                shutil.rmtree(staging, ignore_errors=True)
+    return dest

bot_bottle/trust_domain.py

@@ -0,0 +1,140 @@
+"""Per-service control-plane signing keys (issue #476).
+
+A `TrustDomain` is one service's signing material: its host-canonical key file,
+the roles that key may sign, and the env vars its key and a pre-minted token ride
+in. Scoping `mint`/`verify` to a domain's roles keeps one service's key from
+signing (or accepting) another service's tokens.
+
+Today there is one domain, `CONTROL_PLANE` — the orchestrator's key (roles
+`{gateway, cli}`): the orchestrator holds it and mints the gateway's and CLI's
+tokens. The host controller (#468) will add a **second** domain with its own key
+the orchestrator never holds. That is the point: the host controller starts and
+stops the orchestrator, so the orchestrator must not be able to mint the
+credentials it uses to talk to it. Adding a `host` role to `CONTROL_PLANE`
+instead would defeat that — the orchestrator holds that key, so it could forge
+`host` tokens.
+
+`ControlPlaneProvisioning` is the one seam every backend launcher uses to get the
+orchestrator its key and the gateway its token, instead of re-deriving that
+wiring per backend (the bug class behind PR #471 — see
+`docs/prds/prd-new-control-plane-auth-provisioning.md`).
+
+Stdlib-only: the HMAC lives in `orchestrator_auth`, the key file in `paths`.
+"""
+
+from __future__ import annotations
+
+import os
+from collections.abc import Mapping
+from dataclasses import dataclass
+
+from . import orchestrator_auth
+from .orchestrator_auth import ROLE_GATEWAY
+from .paths import (
+    ORCHESTRATOR_AUTH_JWT_ENV,
+    ORCHESTRATOR_TOKEN_ENV,
+    ORCHESTRATOR_TOKEN_FILENAME,
+    host_signing_key,
+)
+
+
+class ProvisioningError(RuntimeError):
+    """A control-plane auth invariant would be violated (e.g. starting the
+    orchestrator without its signing key — which would run OPEN)."""
+
+
+@dataclass(frozen=True)
+class TrustDomain:
+    """One service's signing material: a host-canonical key file, the roles that
+    key may sign, and the env vars its key and a minted token ride in.
+
+    The service that *owns* the domain (e.g. the orchestrator) receives the raw
+    key via `key_env`; a delegate (e.g. the gateway) receives only a pre-minted,
+    role-scoped token via `token_env` it cannot rewrite. `mint`/`verify` are
+    scoped to `roles`, so this service's key can neither sign nor accept another
+    service's role."""
+
+    name: str
+    key_filename: str
+    roles: frozenset[str]
+    key_env: str
+    token_env: str
+
+    def signing_key(self) -> str:
+        """This service's host-canonical signing key (minted 0600 on first use).
+        Host-side only — the value is injected into the owning process."""
+        return host_signing_key(self.key_filename)
+
+    def key_from_env(self, environ: Mapping[str, str] | None = None) -> str:
+        """The signing key as the owning process sees it — read from `key_env`
+        (default `os.environ`). "" when unset; the caller decides whether that is
+        fatal (`ControlPlaneProvisioning`) or the open-mode fallback
+        (`OrchestratorServer`)."""
+        env = os.environ if environ is None else environ
+        return env.get(self.key_env, "").strip()
+
+    def mint(self, role: str) -> str:
+        """A role-scoped token for a delegate, signed with this service's key.
+        Raises ValueError for a role this service doesn't sign."""
+        if role not in self.roles:
+            raise ValueError(f"role {role!r} is not in trust domain {self.name!r}")
+        return orchestrator_auth.mint(role, self.signing_key(), roles=self.roles)
+
+    def verify(self, token: str, key: str) -> str | None:
+        """The role `token` carries under `key`, or None. `key` is passed in
+        (not read from disk) because the verifier — the control-plane process —
+        holds it in `key_env`, not on disk in its guest."""
+        return orchestrator_auth.verify(token, key, roles=self.roles)
+
+
+# The orchestrator's domain: the key the orchestrator (and host CLI) holds, the
+# `gateway` token it mints for the data plane, and the `cli` token the CLI mints
+# for itself. #468's host controller will add a second, separate domain.
+CONTROL_PLANE = TrustDomain(
+    name="control-plane",
+    key_filename=ORCHESTRATOR_TOKEN_FILENAME,
+    roles=orchestrator_auth.ROLES,
+    key_env=ORCHESTRATOR_TOKEN_ENV,
+    token_env=ORCHESTRATOR_AUTH_JWT_ENV,
+)
+
+
+@dataclass(frozen=True)
+class ControlPlaneProvisioning:
+    """The one seam every backend launcher uses to provision control-plane auth,
+    instead of re-deriving the four invariants that each cost a PR #471 review
+    round: the orchestrator gets the raw key (`orchestrator_key`), the gateway
+    gets a minted `gateway` token (`gateway_token`), the host CLI mints its own
+    `cli` token from the same host-canonical key, and the orchestrator never
+    starts open."""
+
+    domain: TrustDomain = CONTROL_PLANE
+
+    def orchestrator_key(self) -> str:
+        """The raw signing key the orchestrator process must receive (carry it in
+        `domain.key_env`). Fail-closed: raises rather than return "", since an
+        empty key runs the server open — and being on a separate host does not
+        stop the gateway from reaching the control plane (it must, for
+        `/resolve`), so an open orchestrator would treat that gateway as `cli`."""
+        key = self.domain.signing_key()
+        if not key:
+            raise ProvisioningError(
+                f"refusing to start the {self.domain.name} orchestrator without "
+                "a signing key: an open orchestrator authenticates no one and "
+                "grants every caller that reaches it full `cli` (#476)"
+            )
+        return key
+
+    def gateway_token(self) -> str:
+        """The `gateway`-role token the gateway receives (carry it in
+        `domain.token_env`) — minted from the key, never the key itself, so a
+        compromised gateway cannot forge a `cli` token."""
+        return self.domain.mint(ROLE_GATEWAY)
+
+
+__all__ = [
+    "ProvisioningError",
+    "TrustDomain",
+    "CONTROL_PLANE",
+    "ControlPlaneProvisioning",
+]

docs/ci.md

@@ -2,11 +2,22 @@
 
 The test workflow lives at [`.gitea/workflows/test.yml`](../.gitea/workflows/test.yml).
 It runs the unit suite plus one integration job per backend
-(`integration-docker`, `integration-firecracker`) on:
+(`integration-docker`, `integration-firecracker`, `integration-macos`) on:
 
 - every push to a branch with an open pull request, and
 - every push to `main`.
 
+`integration-macos` is the exception: it is **advisory**, running only on
+`workflow_dispatch` (manual dispatch), never on push or pull requests. It targets the
+Apple Container backend on a self-hosted macOS runner (label `macos`,
+registered in host mode — Apple Container can't run in a Linux container, so it
+can't reuse the `kvm` runner). A single non-redundant laptop must not be able
+to block a PR merge, so the job stays out of the `coverage` job's `needs` and
+its coverage never feeds the diff-coverage gate. Because the infra container is
+a singleton (`bot-bottle-mac-infra`), the job declares a `concurrency` group
+and tears the container down on exit; keep runner concurrency at 1. See the
+README "macOS Apple Container" CI note for runner provisioning.
+
 Each integration job selects its backend via `BOT_BOTTLE_BACKEND` and
 runs a **preflight** (`./cli.py backend status --backend=<name>`) that
 prints a clear per-check readiness summary and fails the job when the

docs/prds/prd-new-control-plane-auth-provisioning.md

@@ -0,0 +1,89 @@
+# PRD prd-new: Per-service signing keys for control-plane auth
+
+- **Status:** Draft
+- **Author:** claude
+- **Created:** 2026-07-26
+- **Issue:** #476
+
+## Summary
+
+Provision control-plane signing keys **per service**, through one shared seam, so
+no service can mint another's credentials. Concretely: the orchestrator holds the
+control-plane key and mints the gateway's and CLI's tokens; the host controller
+(#468, next) gets a **separate** key the orchestrator never holds — so the
+orchestrator cannot forge the credentials it uses to talk to the host controller
+that starts and stops it. Landing this seam also retires the per-backend
+provisioning duplication that made PR #471 take three review rounds.
+
+## Problem
+
+**1. The orchestrator could forge host-controller credentials.** The
+orchestrator's key signs roles `{gateway, cli}`. The tempting way to add the host
+controller (#468) is a third role, `host`, on that same key. But then the
+orchestrator — which holds the key — can mint `host` tokens, and the host
+controller, which owns the orchestrator's lifecycle, must not trust anything the
+orchestrator can mint. The two services need separate keys.
+
+**2. Every backend provisioned auth by hand.** Each launcher (docker
+gateway/infra, macOS infra, firecracker infra) re-derived how to generate the
+signing key, scope it to the orchestrator, mint the gateway JWT, and keep the
+host key file canonical. All three PR #471 High-severity findings were this one
+integration bug in different launchers: the data plane got the full `cli` token;
+the firecracker control plane ran open; the firecracker guest clobbered the host
+key.
+
+## Goals / Success Criteria
+
+- The orchestrator and the host controller sign with **different** keys; neither
+  can mint the other's tokens. (This PR provisions the orchestrator's key and
+  leaves a drop-in seam for the host controller's.)
+- One shared provisioning seam every backend uses — a new backend or daemon
+  implements it instead of rediscovering these four invariants:
+  1. the signing key is host-canonical: a guest is handed it, never generates or
+     overwrites it;
+  2. only the orchestrator process gets the raw key; the gateway gets a
+     pre-minted `gateway` token it can't rewrite into `cli`;
+  3. the host CLI's `cli` token is minted from the same key, so it stays valid
+     across co-running backends;
+  4. the orchestrator never runs open — the signing key is mandatory, with no
+     topology opt-out (a separate host does not stop a caller from reaching the
+     control-plane listener, so it cannot make open mode safe).
+
+## Non-goals
+
+- The host controller itself (#468) — this only provisions the orchestrator's
+  key and the seam #468 plugs into.
+- Rewriting the HMAC primitive: `orchestrator_auth.mint/verify` gain an optional
+  `roles=` arg (default unchanged) so a key can carry a different role set;
+  nothing else changes.
+- Network topology, the plane split (#469), or the server's open-mode fallback
+  for tests.
+
+## Design
+
+A **`TrustDomain`** is one service's signing material: its host-canonical key
+file, the roles that key may sign, and the env vars its key and a pre-minted
+token ride in. `mint`/`verify` are scoped to that domain's roles, so a token
+signed by one service's key neither carries nor verifies another service's role.
+
+- `CONTROL_PLANE` — the orchestrator's domain: key `orchestrator-token`, roles
+  `{gateway, cli}`. The orchestrator process holds the key; the gateway holds
+  only a minted `gateway` token; the host CLI mints its own `cli` token.
+- The host controller (#468) will add a second `TrustDomain` — its own key file
+  and role(s) — that the orchestrator never holds.
+
+**`ControlPlaneProvisioning`** is the seam the backends call.
+`orchestrator_key()` returns the raw key for the control-plane process
+(fail-closed for every backend: it raises rather than hand back an empty key that
+would run the server open). `gateway_token()` mints the gateway's token. Each backend applies these through its own transport —
+docker/macOS inject env vars, firecracker pushes over SSH — but none re-derives
+*which* key or role.
+
+`paths.host_signing_key(filename)` generalizes `host_orchestrator_token()` so each
+domain names its own key file.
+
+## Open questions
+
+None blocking. #468 adds its `TrustDomain` and a second
+`ControlPlaneProvisioning`-shaped consumer; renaming that class to something
+service-neutral is a cosmetic call to make then.

docs/prds/prd-new-install-script.md

@@ -0,0 +1,172 @@
+# PRD prd-new: Quick install script
+
+- **Status:** Draft
+- **Author:** claude
+- **Created:** 2026-07-25
+- **Issue:** #197
+
+## Summary
+
+Add a proper Python package distribution (`pyproject.toml` with a
+`bot-bottle` entry point) plus a thin `install.sh` bootstrapper, so users
+can install bot-bottle with a single command instead of cloning the repo
+and invoking `cli.py` directly. A new `bot-bottle doctor` subcommand
+verifies host prerequisites after install.
+
+## Problem
+
+There is currently no install path for new users. The only way to run
+bot-bottle is to clone the repo and invoke `./cli.py`. This blocks any
+public demo: readers want `curl | sh` or `pipx install`, not a manual
+clone-and-configure flow. There is also no single command that tells a
+user whether their host is actually ready to run a bottle.
+
+## Goals / Success Criteria
+
+- `curl -fsSL <raw-url>/install.sh | sh` leaves a working `bot-bottle`
+  command on PATH.
+- Python-native users can install with `pipx install bot-bottle` or
+  `uv tool install bot-bottle` (once published) — or from a local
+  checkout today.
+- `install.sh` validates prerequisites (Python ≥ 3.11), creates the
+  `~/.bot-bottle/` config tree, installs the package, and runs
+  `bot-bottle doctor`. It never installs Docker or a VM backend silently
+  and never uses `sudo`.
+- `install.sh` is idempotent — safe to re-run.
+- `bot-bottle doctor` reports Python version, backend *readiness*, and
+  config-dir presence, exiting non-zero when a hard prerequisite is unmet.
+- The package keeps **zero runtime pip dependencies** (stdlib-only,
+  matching the existing constraint in `AGENTS.md`).
+
+## Non-goals
+
+- Bundling a Python runtime or producing a standalone binary.
+- Automatic Docker / VM-backend installation.
+- Plugin-architecture changes (issue #197 floats a containerized-plugin
+  direction; that's a separate feature).
+- Publishing to a package index in this PR — the package *structure* is
+  the deliverable; publishing is a follow-up step.
+
+## Design
+
+### Package structure (`pyproject.toml`)
+
+Fill out the previously-stub `pyproject.toml` with project metadata, a
+console-script entry point, and package-data for the non-Python assets the
+runtime reads from inside the package:
+
+```toml
+[project]
+name = "bot-bottle"
+version = "0.1.0"
+requires-python = ">=3.11"
+dependencies = []
+
+[project.scripts]
+bot-bottle = "bot_bottle.cli:main"
+```
+
+`bot_bottle.cli:main` already exists (the `cli.py` shim calls it), so no
+refactor of the entry point is needed. `package-data` ships the non-Python
+assets that live *inside* the package (`egress_entrypoint.sh`, the contrib
+Dockerfiles, the firecracker netpool defaults, the macos-container init
+script).
+
+### Self-contained wheel (build resources)
+
+The gateway / infra / orchestrator images are built from a Docker (or Apple
+`container`) build context that must contain the `bot_bottle` package,
+`pyproject.toml`, and the **root-level** Dockerfiles as siblings. Several
+modules used to locate that context by walking `__file__`'s parents to the
+repo root (`_REPO_ROOT = Path(__file__)…parents[N]`) and reading
+`Dockerfile.gateway`, `nix/firecracker-netpool.nix`, and
+`scripts/firecracker-netpool.sh` from it. In an installed wheel the package
+lives in `site-packages` with no repo root above it, so those reads fail —
+`doctor` passes but `start` / backend setup breaks.
+
+Fix: a single resolver, `bot_bottle/resources.py`.
+
+- `build_root()` returns a directory shaped like a repo root (has
+  `bot_bottle/`, `pyproject.toml`, the Dockerfiles, `nix/`, `scripts/`).
+  In a **checkout** it's the repo root itself — unchanged behavior. From an
+  **installed wheel** it stages a copy under the app-data dir, keyed by a
+  **content digest** of the installed package + bundled resources (not the
+  distribution version): the installer defaults to a git branch and
+  `pipx install --force` while `version` stays `0.1.0`, so a version key
+  would reuse a previous commit's tree — the digest key re-stages instead.
+  Staging is concurrency-safe: a file lock serializes it, each writer builds
+  into a private temp dir, and the finished tree is published with an atomic
+  rename (never populating a shared path another process might read).
+- The root-level resources are shipped inside the wheel under
+  `bot_bottle/_resources/` by a `setup.py` `build_py` step (kept in sync
+  with `resources.BUNDLED_RESOURCES`); `MANIFEST.in` includes them in the
+  sdist.
+- Every former `_REPO_ROOT` / `_REPO_DIR` call site now derives from
+  `resources`: the docker/macos agent-image launch, each backend's
+  `orchestrator` / `gateway` / `infra` service, firecracker `infra_vm` /
+  `infra_artifact` / `setup`, and the shared `gateway` build context. So
+  checkout and wheel installs share one downstream path.
+
+Verification: `test_resources` exercises both layouts — including the staged
+wheel context, a re-stage when package content changes at the same version,
+and a rebuild of a partial (crashed) stage. `test_wheel_install` builds the
+wheel, installs it into an isolated venv, and asserts `bot-bottle doctor`
+runs and `build_root()` produces a valid context; `build` is in
+`requirements-dev.txt` so it runs in CI, and a build/install failure fails
+the test (it does not skip). Running `start` end-to-end still needs a
+Docker/KVM host (CI), not a source checkout.
+
+### `install.sh`
+
+A POSIX `sh` bootstrapper that:
+
+1. Checks `python3` is present and ≥ 3.11; exits with a clear message
+   otherwise.
+2. Checks `git` when installing a `git+` spec, and — when falling back to
+   pip — that pip is usable and the interpreter isn't externally managed
+   (PEP 668), pointing at pipx otherwise.
+3. Creates `~/.bot-bottle/{agents,bottles,contrib}`.
+4. Installs via `pipx` if available, else `python3 -m pip install --user`.
+   The spec defaults to the git URL and is overridable via
+   `BOT_BOTTLE_INSTALL_SPEC` (used by tests / local installs).
+5. Locates the `bot-bottle` entry point: PATH first, else the
+   interpreter's own user-scheme scripts dir resolved via `sysconfig`
+   (`~/.local/bin` on Linux, `~/Library/Python/<X.Y>/bin` on a python.org
+   macOS interpreter — not hardcoded).
+6. Runs `bot-bottle doctor` and reports the result.
+
+It is idempotent and never calls `sudo`.
+
+### `bot-bottle doctor`
+
+A new store-free subcommand (no DB migration required) that checks and
+reports:
+
+- **python** — interpreter version (hard requirement: ≥ 3.11).
+- **backend** — at least one backend *ready* on this host
+  (macos-container / firecracker / docker), via `is_backend_ready()` — a
+  full backend `status()` probe (daemon reachable, network pool present,
+  KVM usable), not a PATH-only check: a stopped daemon or half-configured
+  backend must not report `ok` when `start` can't work. Each not-ready
+  backend prints its own diagnostics. Hard requirement.
+- **config** — whether `~/.bot-bottle/` exists (advisory only; `start`
+  provisions on first run).
+
+Exits 0 when both hard requirements pass, non-zero otherwise.
+
+## Testing strategy
+
+- Unit test `bot-bottle doctor` success/failure paths with backend
+  readiness (`is_backend_ready`) and Python version mocked, including the
+  available-but-not-ready → fail case.
+- Unit test that `pyproject.toml` parses, declares the entry point and an
+  empty `dependencies` list, and that every `package-data` glob resolves
+  to a file that exists on disk (guards against drift).
+- Unit test that `install.sh` is executable, POSIX-ish (`set -eu`), never
+  calls `sudo`, and runs `doctor` after install.
+
+## Open questions
+
+- Should `version` be derived from a git tag at build time (e.g.
+  `hatch-vcs`) or kept static? Static (`0.1.0`) is simpler for now.
+- Publishing target (PyPI vs. a self-hosted index) is deferred.

docs/prds/prd-new-macos-container-ci-runner.md

@@ -0,0 +1,142 @@
+# PRD prd-new: macOS (Apple Container) CI runner
+
+- **Status:** Draft
+- **Author:** Claude
+- **Created:** 2026-07-25
+- **Issue:** #426
+
+## Summary
+
+CI has no runner for the `macos-container` (Apple Container) backend.
+`.gitea/workflows/test.yml` exercises Docker (`ubuntu-latest`) and
+Firecracker (self-hosted `kvm`) but never the macOS backend. This PRD adds a
+self-hosted macOS runner (label `macos`) and an advisory `integration-macos`
+job that runs the integration suite against `BOT_BOTTLE_BACKEND=macos-container`,
+so the backend that is the default on macOS stops shipping unexercised.
+
+## Problem
+
+The gap is not theoretical. `5ad3449` moved `bot_bottle` from flat files under
+`/app` into a pip-installed package but left init scripts spawning the
+supervisor as `python3 /app/gateway_init.py`, which no longer exists. Both the
+Firecracker and macOS backends carried the identical bug:
+
+- **firecracker** — caught and fixed in `127ba49` because the KVM runner
+  (added in `c193b04`, PR #349) runs that backend's integration suite.
+- **macos-container** — survived on `main` and only surfaced when a human ran
+  `bot-bottle start` by hand.
+
+The failure mode is expensive to debug: the supervisor never starts, so
+mitmdump never generates its CA, and launch dies downstream with
+`GatewayError: gateway CA not available`, which points at TLS rather than at
+the supervisor. Unit tests did not help — `test_macos_infra` asserted the
+substring `"gateway_init.py"`, which the *broken* path satisfies. (That
+specific assertion has since been tightened to the module form
+`bot_bottle.gateway_init`, matching its Firecracker twin, so the exact
+regression is now covered on `ubuntu-latest`. What remains missing is the
+end-to-end runner that would catch the *next* macOS-only launch regression.)
+
+PR #470 (#414) already made the integration suite backend-agnostic:
+`skip_unless_selected_backend_available()` gates on the *selected* backend's
+own `is_backend_ready()` rather than `docker_available()`, and each
+integration job runs `./cli.py backend status --backend=<name>` as a preflight
+that fails loudly when the backend is missing. That is the machinery this job
+plugs into; this PRD supplies the runner and the job.
+
+## Goals / Success criteria
+
+- A macOS runner is registered and picks up jobs by the `macos` label.
+- An `integration-macos` job runs the integration suite against
+  `BOT_BOTTLE_BACKEND=macos-container`.
+- The job **fails, not skips**, when the backend is unavailable on the runner
+  (via the `backend status` preflight).
+- Reverting the `macos_container/infra.py` supervisor fix makes the job fail:
+  the broken supervisor path throws `GatewayError` at bottle launch, which is
+  `TestSandboxEscape.setUpClass`, failing the whole class before any individual
+  attack runs.
+
+## Non-goals
+
+- Making `integration-macos` a **required** PR check. It runs on
+  `workflow_dispatch` (manual dispatch) only — never on push or PRs. A single
+  non-redundant laptop that sleeps and roams must never be able to block a PR
+  merge or churn unattended on every push to main, and it is deliberately kept
+  out of the `coverage` job's `needs` so the diff-coverage gate never depends on
+  it.
+- Multi-machine or hosted macOS runners. Apple Container needs the host
+  virtualization framework, so the runner must be a physical/VM macOS host on
+  Apple Silicon — it cannot reuse the KVM runner or run in a Linux container.
+- Coverage aggregation from the macOS job into the combined gate (would couple
+  the gate to the laptop).
+
+## Design
+
+### Runner (operational, provisioned once)
+
+- Apple Silicon macOS host with Apple's `container` CLI installed and
+  `container system status` reporting `running`.
+- Install the runner: `brew install gitea-runner` (the `act_runner` rename),
+  registered in **host mode** with label `macos` — not docker mode, because
+  Apple Container needs the host `container` CLI and virtualization framework,
+  not a nested container.
+- A Python ≥ 3.11 with `coverage` importable on the runner's `PATH`. Because a
+  launchd service does not inherit an interactive shell's `PATH`, pin `node`
+  (for the JS `actions/*`) and the Python env explicitly in the service
+  environment rather than relying on `nvm`/shell profile.
+- Concurrency 1. The infra container is a singleton (`bot-bottle-mac-infra`),
+  so two simultaneous runs on one host collide (#425). The job also declares a
+  `concurrency` group as belt-and-suspenders and tears the singleton down after
+  each run.
+
+### `integration-macos` job
+
+Modeled on `integration-firecracker`:
+
+- `runs-on: [self-hosted, macos]`.
+- `if:` `workflow_dispatch` only (advisory, manual dispatch; never push or PRs,
+  so no fork-PR exposure, no merge-blocking, and no unattended runs on push).
+- `concurrency: { group: integration-macos-infra, cancel-in-progress: false }`
+  to serialize runs against the singleton.
+- **Preflight** — `command -v container`, `container system status`, then
+  `./cli.py backend status --backend=macos-container`; any failure exits
+  non-zero so a misprovisioned runner fails loudly instead of silently
+  skipping.
+- Run the integration suite under coverage with
+  `BOT_BOTTLE_BACKEND=macos-container` and print a `coverage report -m` for
+  visibility (no upload, not in the gate).
+- **Teardown** (`if: always()`) — `MacosInfraService().stop()` removes the
+  singleton so a crashed run cannot wedge the next one.
+
+### The `test_sandbox_escape` CI guard (the trap #470 left)
+
+`TestSandboxEscape` is the only backend-agnostic integration test that boots a
+real bottle, so it is the one that would catch a macOS launch regression. It
+still carries a second guard that skips under `GITEA_ACTIONS` for every backend
+except `firecracker`:
+
+```python
+@unittest.skipIf(
+    os.environ.get("GITEA_ACTIONS") == "true"
+    and os.environ.get("BOT_BOTTLE_BACKEND") != "firecracker",
+    ...,
+)
+```
+
+The skip exists because the *containerized* `act_runner` (docker on
+`ubuntu-latest`) can't see a host bind mount and hides sibling-gateway network
+topology. Those constraints do not apply to a **host-mode** runner — neither
+the KVM host runner nor a macOS host runner is containerized. This PRD relaxes
+the guard to allow both host-mode backends (`firecracker`, `macos-container`)
+through while still skipping on the containerized Docker job. Without this
+change the macOS job would run green while skipping the exact test that proves
+the backend launches — the very false-green this issue is about.
+
+## Open questions
+
+- None known that block the job. git-gate is fully implemented on the macOS
+  backend (the gateway's consolidated `git-http` daemon plus dynamic key
+  provisioning/revocation), so `TestSandboxEscape` attack 5 — secret exfil
+  pushed through git-gate, rejected by the gitleaks hook before the upstream
+  push — runs the same as on the other backends. Any genuinely
+  macOS-specific test adjustment would surface at first runner bring-up, but
+  none is anticipated from the current backend implementation.

install.sh

@@ -0,0 +1,123 @@
+#!/bin/sh
+# bot-bottle quick installer.
+#
+# Usage:
+#   curl -fsSL https://gitea.dideric.is/didericis/bot-bottle/raw/branch/main/install.sh | sh
+#
+# Python-native users can skip this entirely:
+#   pipx install bot-bottle        # from a checkout or a published index
+#   uv tool install bot-bottle
+#
+# This script is a thin bootstrapper: it checks prerequisites, installs the
+# package with pipx (falling back to pip --user), creates the config dir, and
+# runs `bot-bottle doctor`. It is idempotent (safe to re-run) and never uses
+# sudo. It does NOT install Docker or a VM backend for you — `doctor` reports
+# what's missing after install.
+set -eu
+
+PACKAGE_SPEC="${BOT_BOTTLE_INSTALL_SPEC:-git+https://gitea.dideric.is/didericis/bot-bottle.git}"
+MIN_PYTHON_MAJOR=3
+MIN_PYTHON_MINOR=11
+
+say() {
+    printf 'bot-bottle install: %s\n' "$*" >&2
+}
+
+die() {
+    say "error: $*"
+    exit 1
+}
+
+# --- prerequisites -----------------------------------------------------------
+
+command -v python3 >/dev/null 2>&1 \
+    || die "python3 ${MIN_PYTHON_MAJOR}.${MIN_PYTHON_MINOR}+ is required but was not found"
+
+python3 - "$MIN_PYTHON_MAJOR" "$MIN_PYTHON_MINOR" <<'PY' || die "python3 ${MIN_PYTHON_MAJOR}.${MIN_PYTHON_MINOR} or newer is required"
+import sys
+
+want = (int(sys.argv[1]), int(sys.argv[2]))
+raise SystemExit(0 if sys.version_info[:2] >= want else 1)
+PY
+
+# Installing a `git+` spec (the default) shells out to git under the hood,
+# whether via pipx or pip. Fail early with a clear message rather than deep
+# inside the installer's output.
+case "${PACKAGE_SPEC}" in
+    git+*|*.git)
+        command -v git >/dev/null 2>&1 || die \
+            "git is required to install from '${PACKAGE_SPEC}'. Install git, or set "\
+"BOT_BOTTLE_INSTALL_SPEC to a non-git spec (e.g. a wheel path or a package index name)."
+        ;;
+esac
+
+# The pip fallback needs a usable pip. Externally-managed interpreters
+# (PEP 668, common on Debian/Ubuntu/Homebrew) reject `pip install --user`;
+# pipx sidesteps that, so recommend it when pip can't be used.
+if ! command -v pipx >/dev/null 2>&1; then
+    python3 -m pip --version >/dev/null 2>&1 || die \
+        "neither pipx nor a usable 'python3 -m pip' was found. Install pipx "\
+"(recommended): 'python3 -m pip install --user pipx' or your OS package manager."
+    if python3 - <<'PY'
+import os
+import sys
+import sysconfig
+
+# PEP 668: an EXTERNALLY-MANAGED marker in the stdlib dir means pip refuses
+# to install into this interpreter without --break-system-packages.
+marker = os.path.join(sysconfig.get_path("stdlib"), "EXTERNALLY-MANAGED")
+raise SystemExit(0 if os.path.exists(marker) else 1)
+PY
+    then
+        die "this Python is externally managed (PEP 668), so 'pip install --user' is "\
+"blocked. Install pipx and re-run: 'python3 -m pip install --user --break-system-packages pipx', "\
+"then 'pipx ensurepath'."
+    fi
+fi
+
+# --- config directories ------------------------------------------------------
+
+mkdir -p \
+    "${HOME}/.bot-bottle/agents" \
+    "${HOME}/.bot-bottle/bottles" \
+    "${HOME}/.bot-bottle/contrib"
+
+# --- install -----------------------------------------------------------------
+
+if command -v pipx >/dev/null 2>&1; then
+    say "installing with pipx"
+    pipx install --force "${PACKAGE_SPEC}"
+else
+    say "pipx not found; installing with 'python3 -m pip install --user'"
+    python3 -m pip install --user --upgrade "${PACKAGE_SPEC}"
+fi
+
+# --- locate the entry point --------------------------------------------------
+
+# The pip --user scripts directory is platform-specific: ~/.local/bin on Linux,
+# but ~/Library/Python/<X.Y>/bin on a python.org macOS interpreter. Ask the
+# interpreter for its own user-scheme scripts dir instead of hardcoding.
+USER_SCRIPTS="$(python3 - <<'PY'
+import sysconfig
+print(sysconfig.get_path("scripts", sysconfig.get_preferred_scheme("user")))
+PY
+)"
+
+if command -v bot-bottle >/dev/null 2>&1; then
+    BOT_BOTTLE_BIN="bot-bottle"
+elif [ -n "${USER_SCRIPTS}" ] && [ -x "${USER_SCRIPTS}/bot-bottle" ]; then
+    BOT_BOTTLE_BIN="${USER_SCRIPTS}/bot-bottle"
+    say "note: add ${USER_SCRIPTS} to your PATH to run 'bot-bottle' directly"
+else
+    die "bot-bottle was installed but is not on PATH; add ${USER_SCRIPTS:-your user scripts dir} to PATH and re-run"
+fi
+
+# --- verify ------------------------------------------------------------------
+
+say "running '${BOT_BOTTLE_BIN} doctor'"
+if "${BOT_BOTTLE_BIN}" doctor; then
+    say "done. Run '${BOT_BOTTLE_BIN} --help' to get started."
+else
+    say "install completed, but 'doctor' reported unmet prerequisites (see above)."
+    say "resolve them, then re-run '${BOT_BOTTLE_BIN} doctor'."
+fi

pyproject.toml

@@ -4,5 +4,42 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "bot-bottle"
-version = "0.0.0"
+version = "0.1.0"
+description = "Self-hosted sandbox for running AI coding agents with egress controls"
+readme = "README.md"
 requires-python = ">=3.11"
+license = { text = "Apache-2.0" }
+authors = [{ name = "didericis" }]
+keywords = ["ai", "agents", "sandbox", "security", "egress"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+    "Operating System :: POSIX :: Linux",
+    "Operating System :: MacOS",
+]
+# The package itself has no runtime pip dependencies (stdlib-only); the
+# only language runtime is the Python interpreter. Keep this empty.
+dependencies = []
+
+[project.urls]
+Homepage = "https://gitea.dideric.is/didericis/bot-bottle"
+Source = "https://gitea.dideric.is/didericis/bot-bottle"
+
+[project.scripts]
+bot-bottle = "bot_bottle.cli:main"
+
+[tool.setuptools.packages.find]
+include = ["bot_bottle*"]
+
+# Non-Python assets the runtime reads from inside the package (container
+# build contexts, entrypoints, netpool defaults). Keep in sync with the
+# files shipped under bot_bottle/; test_pyproject.py asserts they exist.
+[tool.setuptools.package-data]
+bot_bottle = [
+    "gateway/egress/entrypoint.sh",
+    "contrib/claude/Dockerfile",
+    "contrib/codex/Dockerfile",
+    "contrib/pi/Dockerfile",
+    "backend/firecracker/netpool.defaults.env",
+    "backend/macos_container/nested-containers-init.sh",
+]

requirements-dev.txt

@@ -5,3 +5,6 @@
 pylint>=3.0.0
 pyright>=1.1.411
 coverage>=7.0.0
+# PEP 517 build front-end used by tests/unit/test_wheel_install.py to build and
+# install a real wheel (proves the installed distribution is self-contained).
+build>=1.0.0

setup.py

@@ -0,0 +1,46 @@
+"""Build shim. Project metadata lives in ``pyproject.toml``; this only adds a
+build step that copies the root-level build resources (the Dockerfiles, the
+nix netpool module, the netpool script, and ``pyproject.toml``) into
+``bot_bottle/_resources/`` so an installed wheel is self-contained and can
+build its gateway/infra/orchestrator images without a source checkout.
+
+Kept in sync with ``bot_bottle.resources.BUNDLED_RESOURCES`` — the
+``test_resources`` suite guards against drift between the two lists.
+"""
+
+from __future__ import annotations
+
+import shutil
+from pathlib import Path
+
+from setuptools import setup
+from setuptools.command.build_py import build_py
+
+_ROOT = Path(__file__).resolve().parent
+
+# Must match bot_bottle.resources.BUNDLED_RESOURCES (paths relative to root).
+_BUNDLED_RESOURCES = (
+    "pyproject.toml",
+    "Dockerfile.gateway",
+    "Dockerfile.orchestrator",
+    "Dockerfile.orchestrator.fc",
+    "nix/firecracker-netpool.nix",
+    "scripts/firecracker-netpool.sh",
+)
+
+
+class _BundleResources(build_py):
+    """Copy the root-level build resources into the built package tree so they
+    ship inside the wheel under ``bot_bottle/_resources/``."""
+
+    def run(self) -> None:
+        super().run()
+        pkg_resources = Path(self.build_lib) / "bot_bottle" / "_resources"
+        for rel in _BUNDLED_RESOURCES:
+            src = _ROOT / rel
+            dst = pkg_resources / rel
+            dst.parent.mkdir(parents=True, exist_ok=True)
+            shutil.copy2(src, dst)
+
+
+setup(cmdclass={"build_py": _BundleResources})

tests/integration/test_sandbox_escape.py

@@ -67,14 +67,25 @@ _DUMMY_HOST_KEY = (
 )
 
 
+# Backends whose CI runner is HOST-mode (self-hosted), so the test process
+# and the backend share a host. The containerized act_runner (docker on
+# ubuntu-latest) is the one that can't see the host bind mount egress_tls_init
+# uses and hides sibling-gateway network topology; host-mode runners
+# (firecracker/KVM, macos-container) don't have those constraints, so the test
+# runs there. Keep this in sync with the `runs-on` labels in
+# .gitea/workflows/test.yml.
+_HOST_MODE_CI_BACKENDS = frozenset({"firecracker", "macos-container"})
+
+
 @skip_unless_selected_backend_available()
 @unittest.skipIf(
     os.environ.get("GITEA_ACTIONS") == "true"
-    and os.environ.get("BOT_BOTTLE_BACKEND") != "firecracker",
+    and os.environ.get("BOT_BOTTLE_BACKEND") not in _HOST_MODE_CI_BACKENDS,
-    "skipped under act_runner unless BOT_BOTTLE_BACKEND=firecracker: "
+    "skipped under the containerized act_runner (docker on ubuntu-latest): "
     "egress_tls_init uses a host bind mount the runner container can't "
     "see, and the network topology hides sibling-gateway visibility — "
-    "these constraints don't apply on the self-hosted KVM runner",
+    "these constraints don't apply on the self-hosted host-mode runners "
+    "(firecracker/KVM, macos-container)",
 )
 class TestSandboxEscape(unittest.TestCase):
     """End-to-end attacks against a real bottle. The bottle stays

tests/unit/test_cli_doctor.py

@@ -0,0 +1,98 @@
+"""Unit: `bot-bottle doctor` host prerequisite checks (ADR 0004).
+
+`doctor` is a store-free diagnostic — it must run on a fresh install
+before any DB migration, and its exit code gates only the two hard
+prerequisites (Python and at least one *ready* backend). The config-dir
+check is advisory and never affects the exit code.
+
+Backend readiness is probed with `is_backend_ready()` (a full status()
+check), not the cheap PATH-only `is_backend_available()` — a host with a
+stopped daemon or half-configured backend must not report `ok`.
+"""
+
+from __future__ import annotations
+
+import io
+import tempfile
+import unittest
+from contextlib import redirect_stdout
+from pathlib import Path
+from unittest.mock import patch
+
+from bot_bottle.cli.commands import doctor
+
+
+def _run(argv: list[str] | None = None) -> tuple[int, str]:
+    buf = io.StringIO()
+    with redirect_stdout(buf):
+        code = doctor.cmd_doctor(argv or [])
+    return code, buf.getvalue()
+
+
+class TestDoctor(unittest.TestCase):
+    def test_passes_when_python_and_backend_ready(self):
+        with patch.object(doctor, "known_backend_names", return_value=("docker",)), \
+                patch.object(doctor, "is_backend_ready", return_value=True):
+            code, out = _run()
+        self.assertEqual(0, code)
+        self.assertIn("ok:   python", out)
+        self.assertIn("ok:   backend: docker: ready", out)
+
+    def test_fails_when_no_backend_ready(self):
+        # The regression the reviewer flagged: a backend whose binary is on PATH
+        # but whose daemon/pool isn't ready must NOT pass. is_backend_ready is
+        # the full status() check, so returning False here means "not ready".
+        with patch.object(doctor, "known_backend_names", return_value=("docker", "firecracker")), \
+                patch.object(doctor, "is_backend_ready", return_value=False):
+            code, out = _run()
+        self.assertEqual(1, code)
+        self.assertIn("fail: backend", out)
+        self.assertIn("warn: backend: docker: not ready", out)
+
+    def test_passes_when_at_least_one_backend_ready(self):
+        # docker not ready, firecracker ready → overall pass, mixed report.
+        def ready(name: str, *, quiet: bool = False) -> bool:
+            del quiet
+            return name == "firecracker"
+
+        with patch.object(doctor, "known_backend_names", return_value=("docker", "firecracker")), \
+                patch.object(doctor, "is_backend_ready", side_effect=ready):
+            code, out = _run()
+        self.assertEqual(0, code)
+        self.assertIn("warn: backend: docker: not ready", out)
+        self.assertIn("ok:   backend: firecracker: ready", out)
+
+    def test_fails_when_python_too_old(self):
+        # Force the version gate to fail without touching the interpreter.
+        with patch.object(doctor, "MIN_PYTHON", (99, 0)), \
+                patch.object(doctor, "known_backend_names", return_value=("docker",)), \
+                patch.object(doctor, "is_backend_ready", return_value=True):
+            code, out = _run()
+        self.assertEqual(1, code)
+        self.assertIn("fail: python", out)
+
+    def test_missing_config_dir_is_advisory_not_fatal(self):
+        # A missing ~/.bot-bottle warns but must not fail. Point home at a
+        # fresh empty dir so the shared suite HOME (which other tests may
+        # populate) can't turn this into an "ok: config".
+        with tempfile.TemporaryDirectory() as tmp, \
+                patch.object(doctor.Path, "home", return_value=Path(tmp)), \
+                patch.object(doctor, "known_backend_names", return_value=("docker",)), \
+                patch.object(doctor, "is_backend_ready", return_value=True):
+            code, out = _run()
+        self.assertEqual(0, code)
+        self.assertIn("warn: config", out)
+
+    def test_present_config_dir_reports_ok(self):
+        with tempfile.TemporaryDirectory() as tmp, \
+                patch.object(doctor.Path, "home", return_value=Path(tmp)), \
+                patch.object(doctor, "known_backend_names", return_value=("docker",)), \
+                patch.object(doctor, "is_backend_ready", return_value=True):
+            (Path(tmp) / ".bot-bottle").mkdir()
+            code, out = _run()
+        self.assertEqual(0, code)
+        self.assertIn("ok:   config", out)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/test_docker_orchestrator.py

@@ -19,7 +19,9 @@ _ORCH = "bot_bottle.backend.docker.orchestrator"
 _RUN = f"{_ORCH}.run_docker"
 _SLEEP = f"{_ORCH}.time.sleep"
 _MONOTONIC = f"{_ORCH}.time.monotonic"
-_TOKEN = f"{_ORCH}.host_orchestrator_token"
+# The signing key is read through the shared provisioning contract (#476); patch
+# its host-canonical key file read to keep it off the real host file.
+_TOKEN = "bot_bottle.trust_domain.host_signing_key"
 # The ABC's is_healthy probes /health via urllib in the lifecycle module.
 _URLOPEN = "bot_bottle.orchestrator.lifecycle.urllib.request.urlopen"
 

tests/unit/test_firecracker_orchestrator.py

@@ -44,7 +44,7 @@ class TestEnsureRunning(unittest.TestCase):
         vm = infra_vm.InfraVm(guest_ip="10.243.255.1", private_key=Path("/k"), vm=MagicMock())
         with patch.object(infra_vm, "boot_vm", return_value=vm) as boot, \
                 patch.object(infra_vm, "push_secret") as push, \
-                patch(f"{_ORCH}.host_orchestrator_token", return_value="host-key"), \
+                patch("bot_bottle.trust_domain.host_signing_key", return_value="host-key"), \
                 patch.object(orch, "is_running", return_value=False), \
                 patch.object(orch, "_ensure_registry_volume", return_value=Path("/reg")), \
                 patch.object(orch, "_wait_for_health"):

tests/unit/test_install_script.py

@@ -0,0 +1,101 @@
+"""Unit: install.sh bootstrapper contract.
+
+The installer is a thin, sudo-free, idempotent bootstrapper. These are
+static checks on the script text (no network / no real install) so CI can
+run them anywhere: it must be executable, fail-fast, never call sudo,
+create the config tree, install the package, and verify with `doctor`.
+"""
+
+from __future__ import annotations
+
+import os
+import sysconfig
+import unittest
+from pathlib import Path
+
+REPO_ROOT = Path(__file__).resolve().parents[2]
+INSTALL_SH = REPO_ROOT / "install.sh"
+
+
+class TestInstallScript(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls):
+        cls.text = INSTALL_SH.read_text()
+
+    def test_exists_and_executable(self):
+        self.assertTrue(INSTALL_SH.is_file())
+        self.assertTrue(os.access(INSTALL_SH, os.X_OK), "install.sh must be executable")
+
+    def test_posix_shebang_and_failfast(self):
+        first = self.text.splitlines()[0]
+        self.assertEqual("#!/bin/sh", first)
+        self.assertIn("set -eu", self.text)
+
+    def test_never_uses_sudo(self):
+        # Only executable lines matter; the header comment may mention sudo.
+        code = [
+            ln for ln in self.text.splitlines()
+            if ln.strip() and not ln.lstrip().startswith("#")
+        ]
+        self.assertNotIn("sudo", "\n".join(code))
+
+    def test_creates_config_tree(self):
+        self.assertIn(".bot-bottle/agents", self.text)
+        self.assertIn(".bot-bottle/bottles", self.text)
+
+    def test_installs_via_pipx_with_pip_fallback(self):
+        self.assertIn("pipx install", self.text)
+        self.assertIn("pip install --user", self.text)
+
+    def test_runs_doctor_after_install(self):
+        self.assertIn("doctor", self.text)
+
+    def test_install_spec_is_overridable(self):
+        # Tests / local installs point BOT_BOTTLE_INSTALL_SPEC at a checkout.
+        self.assertIn("BOT_BOTTLE_INSTALL_SPEC", self.text)
+
+    def test_requires_git_for_git_specs(self):
+        # A git+ / .git spec (the default) shells out to git; the script must
+        # gate on it rather than failing opaquely inside pipx/pip.
+        self.assertIn("command -v git", self.text)
+        self.assertIn("git+*|*.git", self.text)
+
+    def test_checks_pip_usable_before_fallback(self):
+        self.assertIn("python3 -m pip --version", self.text)
+
+    def test_detects_externally_managed_python(self):
+        # PEP 668: 'pip install --user' is blocked on externally-managed
+        # interpreters; the script must detect this and point at pipx.
+        self.assertIn("EXTERNALLY-MANAGED", self.text)
+        self.assertIn("pipx", self.text)
+
+    def test_resolves_user_scripts_dir_not_hardcoded(self):
+        # The pip --user scripts dir differs by platform; the script must ask
+        # the interpreter (sysconfig + the preferred *user* scheme) rather than
+        # hardcoding Linux's ~/.local/bin (which is wrong on macOS python.org).
+        self.assertIn("get_preferred_scheme", self.text)
+        self.assertIn("sysconfig", self.text)
+        # No hardcoded Linux path in executable lines (a comment may mention it).
+        code = "\n".join(
+            ln for ln in self.text.splitlines()
+            if ln.strip() and not ln.lstrip().startswith("#")
+        )
+        self.assertNotIn(".local/bin", code)
+
+    def test_macos_user_scheme_is_not_dot_local_bin(self):
+        # The case the fix exists for: a python.org macOS interpreter uses the
+        # osx_framework_user scheme, whose scripts land under
+        # ~/Library/Python/<X.Y>/bin — NOT ~/.local/bin. Drive the same
+        # sysconfig lookup install.sh uses, with a mac-like userbase, to prove
+        # it resolves a non-~/.local/bin directory.
+        self.assertIn("osx_framework_user", sysconfig.get_scheme_names())
+        scripts = sysconfig.get_path(
+            "scripts", "osx_framework_user",
+            vars={"userbase": "/Users/dev/Library/Python/3.11"},
+        )
+        self.assertEqual("/Users/dev/Library/Python/3.11/bin", scripts)
+        self.assertNotIn("/.local/bin", scripts)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/test_macos_nested_containers.py

@@ -283,7 +283,7 @@ class TestBuildOrLoadImages(unittest.TestCase):
             images = launch_mod.build_or_load_images(plan)
 
         build.assert_called_once_with(
-            "agent:base", launch_mod._REPO_DIR,  # pylint: disable=protected-access
+            "agent:base", str(launch_mod.resources.build_root()),
             dockerfile="/repo/Dockerfile",
         )
         derived.assert_called_once_with("agent:base", build)

tests/unit/test_macos_orchestrator.py

@@ -33,7 +33,7 @@ class TestMacosOrchestratorRun(unittest.TestCase):
     def _run(self) -> list[str]:
         run = Mock(return_value=_ok())
         with patch(f"{_ORCH}.container_mod") as mod, \
-                patch(f"{_ORCH}.host_orchestrator_token", return_value="k"):
+                patch("bot_bottle.trust_domain.host_signing_key", return_value="k"):
             mod.dns_server.return_value = "1.1.1.1"
             mod.bind_mount_spec.side_effect = _spec
             mod.run_container_argv = run
@@ -65,7 +65,7 @@ class TestMacosOrchestratorRun(unittest.TestCase):
 
     def test_start_failure_raises(self) -> None:
         with patch(f"{_ORCH}.container_mod") as mod, \
-                patch(f"{_ORCH}.host_orchestrator_token", return_value="k"):
+                patch("bot_bottle.trust_domain.host_signing_key", return_value="k"):
             mod.dns_server.return_value = "1.1.1.1"
             mod.run_container_argv = Mock(return_value=_fail())
             with self.assertRaises(OrchestratorStartError):

tests/unit/test_orchestrator_auth.py

@@ -82,5 +82,26 @@ class TestMintVerify(unittest.TestCase):
             mint(ROLE_GATEWAY, "")
 
 
+class TestCustomRoleSet(unittest.TestCase):
+    """The `roles=` seam a trust domain other than the control plane uses (#476):
+    mint/verify are scoped to the passed role set, not the module default."""
+
+    _ROLES = frozenset({"host"})
+
+    def test_round_trips_a_role_in_the_custom_set(self) -> None:
+        tok = mint("host", _KEY, roles=self._ROLES)
+        self.assertEqual("host", verify(tok, _KEY, roles=self._ROLES))
+
+    def test_mint_rejects_a_role_outside_the_custom_set(self) -> None:
+        with self.assertRaises(ValueError):
+            mint(ROLE_CLI, _KEY, roles=self._ROLES)
+
+    def test_verify_rejects_a_role_outside_the_verifiers_set(self) -> None:
+        # A validly signed token whose role isn't in the verifier's set fails —
+        # this is what keeps one domain's key from asserting another's role.
+        tok = mint(ROLE_CLI, _KEY)  # a control-plane `cli` token
+        self.assertIsNone(verify(tok, _KEY, roles=self._ROLES))
+
+
 if __name__ == "__main__":
     unittest.main()

tests/unit/test_orchestrator_client.py

@@ -20,13 +20,15 @@ _URLOPEN = "bot_bottle.orchestrator.client.urllib.request.urlopen"
 
 class TestHostAuthToken(unittest.TestCase):
     def test_mints_a_cli_token_from_the_host_key(self) -> None:
-        with patch("bot_bottle.orchestrator.client.host_orchestrator_token",
+        # The CLI mints its `cli` token from the control-plane trust domain's
+        # host-canonical key (#476) — patch the key file read underneath it.
+        with patch("bot_bottle.trust_domain.host_signing_key",
                    return_value="signing-key"):
             tok = _host_auth_token()
         self.assertEqual(ROLE_CLI, verify(tok, "signing-key"))
 
     def test_returns_empty_when_key_unreadable(self) -> None:
-        with patch("bot_bottle.orchestrator.client.host_orchestrator_token",
+        with patch("bot_bottle.trust_domain.host_signing_key",
                    side_effect=OSError("no host root")):
             self.assertEqual("", _host_auth_token())
 

tests/unit/test_pyproject.py

@@ -0,0 +1,45 @@
+"""Unit: pyproject.toml packaging contract.
+
+Guards the install/distribution surface: the console-script entry point,
+the stdlib-only (empty) dependency list, and that every package-data glob
+still points at a file that exists (so an installed wheel isn't missing a
+Dockerfile or entrypoint the runtime reads).
+"""
+
+from __future__ import annotations
+
+import tomllib
+import unittest
+from pathlib import Path
+
+REPO_ROOT = Path(__file__).resolve().parents[2]
+PYPROJECT = REPO_ROOT / "pyproject.toml"
+
+
+class TestPyproject(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls):
+        with PYPROJECT.open("rb") as fh:
+            cls.data = tomllib.load(fh)
+
+    def test_entry_point_targets_cli_main(self):
+        scripts = self.data["project"]["scripts"]
+        self.assertEqual("bot_bottle.cli:main", scripts["bot-bottle"])
+
+    def test_no_runtime_dependencies(self):
+        # AGENTS.md: the package has no runtime pip dependencies.
+        self.assertEqual([], self.data["project"]["dependencies"])
+
+    def test_requires_python_311(self):
+        self.assertEqual(">=3.11", self.data["project"]["requires-python"])
+
+    def test_package_data_files_exist(self):
+        pkg_data = self.data["tool"]["setuptools"]["package-data"]["bot_bottle"]
+        self.assertTrue(pkg_data, "expected package-data entries")
+        for rel in pkg_data:
+            path = REPO_ROOT / "bot_bottle" / rel
+            self.assertTrue(path.is_file(), f"package-data missing: {path}")
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/test_resources.py

@@ -0,0 +1,184 @@
+"""Unit: bot_bottle.resources — build-resource resolution for both a source
+checkout and an installed wheel.
+
+The checkout path is what the whole test suite already runs under; the wheel
+path is exercised here by faking an installed layout (a package dir with a
+bundled ``_resources/`` and no sibling Dockerfiles) and asserting that
+``build_root()`` stages a repo-root-shaped context. See
+``test_wheel_install.py`` for the end-to-end build+install check.
+"""
+
+from __future__ import annotations
+
+import tempfile
+import unittest
+from contextlib import contextmanager
+from pathlib import Path
+from unittest.mock import patch
+
+from bot_bottle import resources
+
+from tests.unit import use_bottle_root
+
+
+class TestCheckoutMode(unittest.TestCase):
+    """The environment the suite runs in: a real source checkout."""
+
+    def test_is_source_checkout(self):
+        self.assertTrue(resources.is_source_checkout())
+
+    def test_build_root_is_repo_root(self):
+        root = resources.build_root()
+        self.assertTrue((root / "bot_bottle").is_dir())
+        self.assertTrue((root / "pyproject.toml").is_file())
+        self.assertTrue((root / "Dockerfile.gateway").is_file())
+
+    def test_resource_helpers_resolve(self):
+        self.assertTrue(resources.dockerfile("Dockerfile.gateway").is_file())
+        self.assertTrue(resources.nix_netpool_module().is_file())
+        self.assertTrue(resources.netpool_script().is_file())
+
+    def test_bundled_resources_all_exist_at_root(self):
+        # Drift guard: every path setup.py bundles must exist in the checkout.
+        root = resources.build_root()
+        for rel in resources.BUNDLED_RESOURCES:
+            self.assertTrue((root / rel).is_file(), f"missing bundled resource: {rel}")
+
+
+class TestWheelMode(unittest.TestCase):
+    """Fake an installed wheel: a package dir with _resources/ and no
+    checkout Dockerfiles beside it."""
+
+    def _fake_install(self, tmp: Path) -> Path:
+        pkg = tmp / "site-packages" / "bot_bottle"
+        (pkg / "cli").mkdir(parents=True)
+        (pkg / "__init__.py").write_text("")
+        (pkg / "cli" / "__init__.py").write_text("# module\n")
+        bundled = pkg / "_resources"
+        for rel in resources.BUNDLED_RESOURCES:
+            dst = bundled / rel
+            dst.parent.mkdir(parents=True, exist_ok=True)
+            dst.write_text(f"# fake {rel}\n")
+        return pkg
+
+    @contextmanager
+    def _wheel(self):
+        """Point `resources` at a fake installed wheel with an isolated
+        app-data dir; yields the package dir so a test can mutate it."""
+        with tempfile.TemporaryDirectory() as tmpname:
+            tmp = Path(tmpname)
+            pkg = self._fake_install(tmp)
+            self.addCleanup(use_bottle_root(tmp / "appdata"))
+            with patch.object(resources, "_PKG", pkg), \
+                    patch.object(resources, "_BUNDLED", pkg / "_resources"), \
+                    patch.object(resources, "_CHECKOUT_ROOT", tmp / "no-checkout"):
+                yield pkg
+
+    def test_stage_and_resolve(self):
+        with self._wheel():
+            self.assertFalse(resources.is_source_checkout())
+            root = resources.build_root()
+            # Staged context looks like a repo root.
+            self.assertTrue((root / "bot_bottle" / "__init__.py").is_file())
+            self.assertTrue((root / "bot_bottle" / "cli" / "__init__.py").is_file())
+            self.assertTrue((root / "pyproject.toml").is_file())
+            self.assertTrue((root / "Dockerfile.gateway").is_file())
+            self.assertTrue((root / "nix" / "firecracker-netpool.nix").is_file())
+            self.assertTrue((root / "scripts" / "firecracker-netpool.sh").is_file())
+            # The bundled-resource copies are NOT re-nested under the staged
+            # package (keeps it byte-identical to a checkout package).
+            self.assertFalse((root / "bot_bottle" / "_resources").exists())
+            # Helpers resolve off the staged root.
+            self.assertEqual(root / "Dockerfile.gateway",
+                             resources.dockerfile("Dockerfile.gateway"))
+            # Idempotent: second call returns the same completed dir.
+            self.assertEqual(root, resources.build_root())
+
+    def test_refreshes_when_content_changes_at_same_version(self):
+        # Regression for the stale-cache bug: `pipx install --force` of a newer
+        # commit keeps version 0.1.0, so keying on version would reuse the old
+        # tree. Keying on content must re-stage when a package file changes.
+        with self._wheel() as pkg:
+            root1 = resources.build_root()
+            self.assertTrue((root1 / ".complete").is_file())
+            (pkg / "cli" / "__init__.py").write_text("# new commit, same version\n")
+            root2 = resources.build_root()
+            self.assertNotEqual(root1, root2)
+            self.assertEqual(
+                "# new commit, same version\n",
+                (root2 / "bot_bottle" / "cli" / "__init__.py").read_text(),
+            )
+
+    def test_failed_stage_cleans_up_temp_dir(self):
+        # A failure mid-stage must not leave a half-written temp dir behind.
+        with self._wheel():
+            base = resources.bot_bottle_root() / "build-root"
+            with patch.object(resources.shutil, "copytree", side_effect=OSError("boom")):
+                with self.assertRaises(OSError):
+                    resources.build_root()
+            self.assertEqual([], list(base.glob(".staging-*")))
+
+    def test_rebuilds_when_stage_incomplete(self):
+        # A crash mid-stage can leave a dir without its `.complete` marker; the
+        # next call must rebuild it rather than trust the partial tree.
+        with self._wheel():
+            root = resources.build_root()
+            (root / ".complete").unlink()
+            (root / "sentinel").write_text("stale")
+            again = resources.build_root()
+            self.assertEqual(root, again)  # same content digest → same dir
+            self.assertTrue((again / ".complete").is_file())
+            self.assertFalse((again / "sentinel").exists())  # rebuilt clean
+
+    def test_reuses_peer_stage_after_lock_wait(self):
+        # Regression for the staging race: a caller that loses the lock must,
+        # once it wins, see the peer's completed tree and reuse it — never
+        # re-clobber a shared path. Drive it deterministically: hold the lock,
+        # let a worker block after its fast-path miss, publish a complete tree
+        # as the "peer", then release so the worker takes the reuse path.
+        import fcntl
+        import threading
+        import time
+
+        with self._wheel():
+            base = resources.bot_bottle_root() / "build-root"
+            base.mkdir(parents=True, exist_ok=True)
+            dest = base / resources._content_digest()  # pylint: disable=protected-access
+
+            result: dict[str, Path] = {}
+            with open(base / ".stage.lock", "w", encoding="utf-8") as held:
+                fcntl.flock(held, fcntl.LOCK_EX)
+
+                def worker() -> None:
+                    result["root"] = resources.build_root()
+
+                t = threading.Thread(target=worker)
+                t.start()
+                # Let the worker miss the fast path (dest not yet complete) and
+                # block on the held lock, then publish a complete tree as a peer
+                # would have and release the lock.
+                time.sleep(0.3)
+                dest.mkdir(parents=True)
+                (dest / ".complete").write_text("")
+                fcntl.flock(held, fcntl.LOCK_UN)
+                t.join(timeout=10)
+
+            self.assertEqual(dest, result["root"])
+            self.assertFalse(t.is_alive())
+
+    def test_missing_bundle_raises(self):
+        with tempfile.TemporaryDirectory() as tmpname:
+            tmp = Path(tmpname)
+            pkg = tmp / "bot_bottle"
+            pkg.mkdir()
+            restore = use_bottle_root(tmp / "appdata")
+            self.addCleanup(restore)
+            with patch.object(resources, "_PKG", pkg), \
+                    patch.object(resources, "_BUNDLED", pkg / "_resources"), \
+                    patch.object(resources, "_CHECKOUT_ROOT", tmp / "no-checkout"):
+                with self.assertRaises(resources.ResourceError):
+                    resources.build_root()
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/test_trust_domain.py

@@ -0,0 +1,105 @@
+"""Unit: trust domains + the shared control-plane provisioning contract (#476)."""
+
+from __future__ import annotations
+
+import unittest
+from unittest.mock import patch
+
+from bot_bottle import orchestrator_auth
+from bot_bottle.orchestrator_auth import ROLE_CLI, ROLE_GATEWAY
+from bot_bottle.trust_domain import (
+    CONTROL_PLANE,
+    ControlPlaneProvisioning,
+    ProvisioningError,
+    TrustDomain,
+)
+
+# A second, unrelated domain — the shape #468's host controller would take: its
+# own key file, its own role, its own env vars. Distinct from CONTROL_PLANE.
+_HOST_CTRL = TrustDomain(
+    name="host-controller",
+    key_filename="host-controller-token",
+    roles=frozenset({"host"}),
+    key_env="BOT_BOTTLE_HOST_CONTROLLER_TOKEN",
+    token_env="BOT_BOTTLE_HOST_CONTROLLER_JWT",
+)
+
+
+class TestTrustDomainMintVerify(unittest.TestCase):
+    def test_mint_verify_round_trips_within_a_domain(self) -> None:
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value="k"):
+            tok = CONTROL_PLANE.mint(ROLE_GATEWAY)
+        self.assertEqual(ROLE_GATEWAY, CONTROL_PLANE.verify(tok, "k"))
+
+    def test_mint_rejects_a_role_outside_the_domain(self) -> None:
+        # `host` is a valid role in _HOST_CTRL but not in the control plane —
+        # the control-plane key must refuse to mint it.
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value="k"):
+            with self.assertRaises(ValueError):
+                CONTROL_PLANE.mint("host")
+
+    def test_a_custom_role_set_verifies_its_own_role(self) -> None:
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value="k"):
+            tok = _HOST_CTRL.mint("host")
+        self.assertEqual("host", _HOST_CTRL.verify(tok, "k"))
+
+    def test_key_from_env_reads_the_domains_env_var(self) -> None:
+        self.assertEqual(
+            "secret", CONTROL_PLANE.key_from_env({CONTROL_PLANE.key_env: " secret "}))
+        self.assertEqual("", CONTROL_PLANE.key_from_env({}))
+
+
+class TestDomainBoundary(unittest.TestCase):
+    """The #476/#468 invariant: two domains, two keys, two role sets — one
+    domain's key can neither mint nor verify the other's tokens."""
+
+    def test_a_control_plane_token_does_not_verify_under_another_domains_key(
+        self,
+    ) -> None:
+        # Even with an IDENTICAL underlying key, a `cli` token minted under the
+        # control-plane domain must not verify as a role in the host-controller
+        # domain — the role isn't in that domain's set.
+        cli_tok = orchestrator_auth.mint(ROLE_CLI, "shared-bytes")
+        self.assertIsNone(_HOST_CTRL.verify(cli_tok, "shared-bytes"))
+
+    def test_distinct_keys_do_not_cross_verify(self) -> None:
+        # The realistic case: distinct host-canonical keys per domain. A token
+        # signed by one key never verifies under the other.
+        host_tok = orchestrator_auth.mint(
+            "host", "host-ctrl-key", roles=_HOST_CTRL.roles)
+        self.assertIsNone(_HOST_CTRL.verify(host_tok, "control-plane-key"))
+        self.assertEqual("host", _HOST_CTRL.verify(host_tok, "host-ctrl-key"))
+
+
+class TestControlPlaneProvisioning(unittest.TestCase):
+    def test_orchestrator_key_returns_the_canonical_key(self) -> None:
+        prov = ControlPlaneProvisioning()
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value="key"):
+            self.assertEqual("key", prov.orchestrator_key())
+
+    def test_orchestrator_key_fail_closes_when_empty(self) -> None:
+        # Invariant 4: the orchestrator must never start without a key — it would
+        # run OPEN and grant every caller that reaches it full `cli`. There is no
+        # topology opt-out: a separate host does not stop the gateway (or any
+        # other caller) from reaching the control-plane listener.
+        prov = ControlPlaneProvisioning()
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value=""):
+            with self.assertRaises(ProvisioningError):
+                prov.orchestrator_key()
+
+    def test_gateway_token_is_a_verifiable_gateway_role_token(self) -> None:
+        prov = ControlPlaneProvisioning()
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value="k"):
+            tok = prov.gateway_token()
+        self.assertEqual(ROLE_GATEWAY, CONTROL_PLANE.verify(tok, "k"))
+
+    def test_gateway_token_cannot_be_reused_as_cli(self) -> None:
+        # The data plane's token is `gateway`-scoped: it never carries `cli`.
+        prov = ControlPlaneProvisioning()
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value="k"):
+            tok = prov.gateway_token()
+        self.assertNotEqual(ROLE_CLI, CONTROL_PLANE.verify(tok, "k"))
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/test_wheel_install.py

@@ -0,0 +1,119 @@
+"""Integration: build the wheel, install it into an isolated venv, and prove
+the installed distribution is self-contained.
+
+This is the boundary a source-tree existence test can't reach (issue #197
+review): under an installed wheel the package lives in ``site-packages`` with
+no repo root above it, so anything resolving Dockerfiles / nix / scripts from
+``__file__``'s parents would break. Here we install for real and assert that
+``bot-bottle doctor`` runs from the console script and that
+``bot_bottle.resources`` stages a valid, repo-root-shaped build context.
+
+It does NOT run `start` — building images needs a Docker/KVM host (CI). It
+skips cleanly when the build/venv toolchain isn't available.
+"""
+
+from __future__ import annotations
+
+import subprocess
+import sys
+import tempfile
+import unittest
+from pathlib import Path
+
+REPO_ROOT = Path(__file__).resolve().parents[2]
+
+
+class TestWheelInstall(unittest.TestCase):
+    """`build` is a declared dev dependency (requirements-dev.txt), so this runs
+    in CI. A build/install failure is a real packaging regression and FAILS —
+    only genuinely-unsupported infra (no `venv`/`ensurepip`) skips."""
+
+    _tmp: "tempfile.TemporaryDirectory[str]"
+    venv_py: Path
+    app_root: Path
+
+    @classmethod
+    def setUpClass(cls):
+        cls._tmp = tempfile.TemporaryDirectory(  # pylint: disable=consider-using-with
+            prefix="bb-wheel-")
+        tmp = Path(cls._tmp.name)
+        dist = tmp / "dist"
+
+        # A failed wheel build is exactly the regression this test guards — fail,
+        # don't skip. `build` is installed via requirements-dev.txt.
+        built = subprocess.run(
+            [sys.executable, "-m", "build", "--wheel", "--outdir", str(dist), str(REPO_ROOT)],
+            capture_output=True, text=True, check=False,
+        )
+        if built.returncode != 0:
+            raise AssertionError(f"wheel build failed:\n{built.stderr[-2000:]}")
+        wheels = list(dist.glob("*.whl"))
+        if not wheels:
+            raise AssertionError(f"no wheel produced:\n{built.stdout[-2000:]}")
+
+        # A missing `venv`/`ensurepip` is unsupported optional infra, not a
+        # packaging bug — skip only here.
+        venv = tmp / "venv"
+        made = subprocess.run([sys.executable, "-m", "venv", str(venv)],
+                              capture_output=True, text=True, check=False)
+        if made.returncode != 0:
+            raise unittest.SkipTest(f"venv/ensurepip unavailable:\n{made.stderr[-1500:]}")
+        cls.venv_py = venv / "bin" / "python"
+
+        # Installing the freshly-built wheel must succeed — fail if it doesn't.
+        install = subprocess.run(
+            [str(cls.venv_py), "-m", "pip", "install", "--quiet", str(wheels[0])],
+            capture_output=True, text=True, check=False,
+        )
+        if install.returncode != 0:
+            raise AssertionError(f"pip install of the wheel failed:\n{install.stderr[-2000:]}")
+
+        # Isolate the staged build root the wheel writes under the app-data dir.
+        cls.app_root = tmp / "appdata"
+
+    @classmethod
+    def tearDownClass(cls):
+        cls._tmp.cleanup()
+
+    def _run(self, tail: "list[str]") -> "subprocess.CompletedProcess[str]":
+        """Run the installed venv's python with `tail` appended, from a neutral
+        cwd so the source checkout isn't on sys.path — we must import the
+        *installed* package, not the repo we built from."""
+        env = {"BOT_BOTTLE_ROOT": str(self.app_root), "PATH": "/usr/bin:/bin"}
+        return subprocess.run(
+            [str(self.venv_py), *tail],
+            capture_output=True, text=True, env=env, cwd=self._tmp.name, check=False,
+        )
+
+    def test_console_entry_point_installed(self):
+        # The `bot-bottle` script the wheel declares must exist in the venv.
+        script = self.venv_py.parent / "bot-bottle"
+        self.assertTrue(script.is_file(), "bot-bottle console script not installed")
+
+    def test_doctor_runs_from_installed_package(self):
+        proc = self._run(["-m", "bot_bottle.cli", "doctor"])
+        # doctor exits non-zero here (no backend), but it must RUN and report.
+        self.assertIn("python", proc.stdout)
+        self.assertIn(proc.returncode, (0, 1))
+
+    def test_installed_wheel_is_self_contained(self):
+        # From the installed layout (not a checkout), resources must resolve
+        # Dockerfiles and stage a repo-root-shaped build context.
+        script = (
+            "import bot_bottle.resources as r\n"
+            "assert not r.is_source_checkout(), 'should not look like a checkout'\n"
+            "assert r.dockerfile('Dockerfile.gateway').is_file()\n"
+            "assert r.nix_netpool_module().is_file()\n"
+            "assert r.netpool_script().is_file()\n"
+            "root = r.build_root()\n"
+            "assert (root / 'bot_bottle' / '__init__.py').is_file(), 'no package in context'\n"
+            "assert (root / 'pyproject.toml').is_file(), 'no pyproject in context'\n"
+            "assert (root / 'Dockerfile.gateway').is_file(), 'no Dockerfile in context'\n"
+            "print('SELF_CONTAINED_OK')\n"
+        )
+        proc = self._run(["-c", script])
+        self.assertIn("SELF_CONTAINED_OK", proc.stdout, msg=proc.stderr)
+
+
+if __name__ == "__main__":
+    unittest.main()