test(lifecycle): cover edge paths to satisfy diff-coverage gate

Add three new tests:
- noop when healthy but docker inspect fails (returns True → don't churn)
- build failure raises GatewayError
- _ensure_network creates the network when it doesn't exist

Also update the integration test to use new OrchestratorService API
(infra_name/image instead of orchestrator_name/gateway_name/gateway_image).

Brings diff-coverage from 86% to 90.3% against origin/main.

Dockerfile.infra

@@ -1,45 +1,22 @@
-# Firecracker single infra-VM image (PRD 0070 Stage B).
+# Shared infra image: gateway data plane + orchestrator control plane.
 #
-# The per-host infra VM runs the orchestrator control plane, the gateway
-# data plane, AND builds agent images (buildah) — all in one microVM (see
-# backend/firecracker/infra_vm.py). It composes:
-#   * FROM the gateway image (mitmproxy / git / gitleaks / supervise + the
-#     flat daemon modules) — now trixie-based, so buildah 1.39 is available;
-#   * `COPY --from` the orchestrator image's content (the single definition
-#     of the control-plane payload — see Dockerfile.orchestrator), so this
-#     VM and the docker backend share one orchestrator definition; and
-#   * buildah, installed HERE only (the docker orchestrator/gateway images
-#     never carry it).
+# Used directly by the Docker backend (run as one `bot-bottle-infra`
+# container, replacing the prior two-container split). The Firecracker
+# backend extends this via Dockerfile.infra.fc, adding buildah/crun/
+# netavark for in-VM agent-image building.
+#
+# Dockerfile.orchestrator is the single definition of the orchestrator
+# content (the lean `bot_bottle` package on python:3.12-slim). Both this
+# image and Dockerfile.infra.fc pull it in via `COPY --from`.
 #
 # multi-`FROM` can't union two bases (that's multi-stage, not multiple
 # inheritance), so the orchestrator content is pulled in via `COPY --from`
 # rather than a second base. Both images share the trixie `python:3.12-slim`
 # base, so the copy is clean (same python; future installed deps copy too).
-#
-# The docker backend keeps orchestrator + gateway as separate images; this
-# combined image exists only for the Firecracker single-VM cut. Splitting a
-# service back into its own VM later is a routing change, not a repackaging
-# (PRD 0070's "secret concentration"; a disposable builder can boot from
-# this same image on its own TAP).
 FROM bot-bottle-gateway:latest
 
-# --- in-VM agent-image builder (PRD 0069 Stage 3) -------------------
-# The Firecracker backend builds users' agent Dockerfiles *inside this VM*
-# with buildah (rootless, daemonless) instead of on the host — no host
-# Docker daemon, no root-equivalent `docker` group. `crun` is the OCI
-# runtime; `netavark` + `aardvark-dns` are the network backend for `FROM`
-# pulls + `RUN` egress. Requires the trixie base (buildah 1.39: bookworm's
-# 1.28 can't parse Dockerfile heredocs that agent images use).
-RUN apt-get update \
- && apt-get install -y --no-install-recommends \
-      buildah crun netavark aardvark-dns \
- && rm -rf /var/lib/apt/lists/*
-# vfs + chroot: buildah works as root in the bare microVM (no
-# fuse-overlayfs / overlay module / subuid maps). Matches image_builder.
-ENV STORAGE_DRIVER=vfs \
-    BUILDAH_ISOLATION=chroot
-
-# The orchestrator content, pulled from its single definition. The gateway
-# image already has the flat daemon modules under /app; this adds the full
-# `bot_bottle` package so `python3 -m bot_bottle.orchestrator` resolves.
+# The orchestrator content, from its single definition. The gateway image
+# already has the flat daemon modules under /app; this adds the full
+# `bot_bottle` package so `python3 -m bot_bottle.orchestrator` resolves —
+# used by gateway_init when BOT_BOTTLE_GATEWAY_DAEMONS includes `orchestrator`.
 COPY --from=bot-bottle-orchestrator:latest /app/bot_bottle /app/bot_bottle

Dockerfile.infra.fc

@@ -0,0 +1,23 @@
+# Firecracker infra VM image (PRD 0070 Stage B).
+#
+# Extends the shared infra base (Dockerfile.infra: gateway + orchestrator
+# control plane) with the in-VM agent-image builder. The Firecracker backend
+# builds users' agent Dockerfiles *inside this VM* with buildah (rootless,
+# daemonless) instead of on the host — no host Docker daemon, no
+# root-equivalent `docker` group.
+#
+# Requires the trixie base from bot-bottle-gateway (buildah 1.39: bookworm's
+# 1.28 can't parse Dockerfile heredocs that agent images use).
+#
+# `crun` is the OCI runtime; `netavark` + `aardvark-dns` are the network
+# backend for `FROM` pulls + `RUN` egress. `vfs` + `chroot`: buildah works
+# as root in the bare microVM (no fuse-overlayfs / overlay module / subuid
+# maps). Matches image_builder.
+FROM bot-bottle-infra:latest
+
+RUN apt-get update \
+ && apt-get install -y --no-install-recommends \
+      buildah crun netavark aardvark-dns \
+ && rm -rf /var/lib/apt/lists/*
+ENV STORAGE_DRIVER=vfs \
+    BUILDAH_ISOLATION=chroot

bot_bottle/backend/__init__.py

@@ -45,7 +45,8 @@ from typing import TYPE_CHECKING, Any, Generic, Sequence, TypeVar
 from ..agent_provider import AgentProvisionPlan, get_provider, build_agent_provision_plan
 from ..egress import EgressPlan
 from ..git_gate import GitGatePlan
-from ..log import die, info
+from ..log import die, info, warn
+from ..util import read_tty_line
 from ..manifest import Manifest, ManifestIndex
 from ..supervise import SupervisePlan
 from ..util import expand_tilde
@@ -648,19 +649,26 @@ def __getattr__(name: str) -> Any:
 
 def get_bottle_backend(
     name: str | None = None,
+    *,
+    prompt: bool = True,
 ) -> BottleBackend[Any, Any]:
     """Resolve the bottle backend.
 
     `name` precedence:
-      1. explicit arg (CLI `--backend=<name>` passes through here)
+      1. explicit arg (e.g. resume passes the recorded backend name)
       2. BOT_BOTTLE_BACKEND env var
-      3. `macos-container` on compatible macOS hosts
-      4. `firecracker` on KVM-capable Linux hosts
-      5. default `docker`
+      3. auto-selection: VM backend first, docker fallback with prompt
+
+    `prompt` controls whether auto-selection may block on an interactive
+    [i/d/q] prompt when falling back to docker. Pass `prompt=False` in
+    non-interactive contexts (headless launches, CI) so the call dies
+    with an actionable message instead of hanging.
 
     Dies with a pointer at the known backends if the chosen name
     isn't implemented."""
-    resolved = name or os.environ.get("BOT_BOTTLE_BACKEND") or _default_backend_name()
+    resolved = name or os.environ.get("BOT_BOTTLE_BACKEND")
+    if resolved is None:
+        resolved = _auto_select_backend(prompt=prompt)
     backends = _get_backends()
     if resolved not in backends:
         known = ", ".join(sorted(backends))
@@ -668,7 +676,35 @@ def get_bottle_backend(
     return backends[resolved]
 
 
-def _default_backend_name() -> str:
+def _platform_vm_suggestion() -> str:
+    """Platform-appropriate VM backend name for install suggestions."""
+    return "macos-container" if sys.platform == "darwin" else "firecracker"
+
+
+def _print_vm_install_instructions() -> None:
+    """Print platform-appropriate VM backend install instructions to stderr."""
+    vm = _platform_vm_suggestion()
+    if vm == "macos-container":
+        info("Install Apple Container: https://github.com/apple/container/releases")
+        info("Then start the service:  container system start")
+    else:
+        info("Install Firecracker: https://github.com/firecracker-microvm/firecracker/releases")
+        info("Configure the host:  ./cli.py backend setup")
+
+
+def _auto_select_backend(prompt: bool = True) -> str:
+    """Tier-1 / tier-2 backend auto-selection.
+
+    Tier 1: VM backend — macos-container on macOS when Apple Container is
+    installed; firecracker on KVM-capable Linux even before the binary is
+    present (its preflight prints an install pointer).
+
+    Tier 2: docker, with a security warning and an interactive prompt.
+    When `prompt=False` (headless / CI), dies with an actionable message
+    instead of blocking on a TTY read. When docker is also absent, prints
+    VM install instructions and exits.
+    """
+    # --- Tier 1: VM backend -----------------------------------------
     if has_backend("macos-container"):
         return "macos-container"
     # A KVM-capable Linux host defaults to firecracker even when the
@@ -678,7 +714,37 @@ def _default_backend_name() -> str:
     from .firecracker import FirecrackerBottleBackend
     if FirecrackerBottleBackend.is_host_capable():
         return "firecracker"
-    return "docker"
+
+    # --- Tier 2: docker fallback ------------------------------------
+    if not has_backend("docker"):
+        info("No backend available on this host.")
+        _print_vm_install_instructions()
+        die("no backend available; install a VM backend and re-run")
+
+    vm = _platform_vm_suggestion()
+    warn(
+        "docker is less secure than VM backends — "
+        "containers share the host kernel."
+    )
+    if not prompt:
+        die(
+            f"no VM backend available; set BOT_BOTTLE_BACKEND=docker to proceed "
+            f"with docker, or install the {vm!r} backend."
+        )
+    sys.stderr.write(
+        f"bot-bottle: For better isolation, install the {vm!r} backend.\n"
+        f"  [i] show {vm} install instructions and exit\n"
+        "  [d] use docker anyway\n"
+        "  [q] quit\n"
+        "bot-bottle: choice [i/d/q]: "
+    )
+    sys.stderr.flush()
+    reply = read_tty_line().strip().lower()
+    if reply == "d":
+        return "docker"
+    if reply == "i":
+        _print_vm_install_instructions()
+    die("not proceeding with docker; install a VM backend or set BOT_BOTTLE_BACKEND=docker")
 
 
 def known_backend_names() -> tuple[str, ...]:

bot_bottle/backend/consolidated_util.py

@@ -0,0 +1,55 @@
+"""Shared helpers for the consolidated launch sequence (PRD 0070).
+
+Logic that was duplicated across the docker, macos_container, and
+firecracker consolidated_launch modules — extracted so each backend
+imports it rather than re-implementing it.
+"""
+
+from __future__ import annotations
+
+from ..egress import EgressPlan
+from ..git_gate import GitGatePlan
+from ..orchestrator.client import OrchestratorClient
+from ..orchestrator.registration import registration_inputs
+from .docker.gateway_provision import GatewayTransport, deprovision_git_gate, provision_git_gate
+
+
+def provision_bottle(
+    client: OrchestratorClient,
+    source_ip: str,
+    egress_plan: EgressPlan,
+    git_gate_plan: GitGatePlan,
+    transport: GatewayTransport,
+    *,
+    image_ref: str = "",
+    tokens: dict[str, str] | None = None,
+):
+    """Register the bottle and provision its git-gate state. Rolls back the
+    registration if provisioning fails so no orphan is left. Returns the
+    `RegisteredBottle` from the orchestrator."""
+    inputs = registration_inputs(egress_plan)
+    reg = client.register_bottle(
+        source_ip, image_ref=image_ref, policy=inputs.policy,
+        metadata=inputs.metadata, tokens=tokens,
+    )
+    try:
+        provision_git_gate(transport, reg.bottle_id, git_gate_plan)
+    except Exception:
+        client.teardown_bottle(reg.bottle_id)
+        raise
+    return reg
+
+
+def teardown_consolidated(
+    bottle_id: str,
+    transport: GatewayTransport,
+    *,
+    orchestrator_url: str,
+) -> None:
+    """Deregister the bottle and remove its git-gate state. Both steps are
+    idempotent so this is safe from a cleanup trap."""
+    OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
+    deprovision_git_gate(transport, bottle_id)
+
+
+__all__ = ["provision_bottle", "teardown_consolidated"]

bot_bottle/backend/docker/consolidated_launch.py

@@ -1,19 +1,13 @@
 """Consolidated bottle launch sequence for the docker backend (PRD 0070).
 
-Composes the orchestrator primitives into the register/teardown sequence that
-replaces the per-bottle gateway:
+Composes the orchestrator primitives into the register/teardown sequence:
 
-  1. ensure the orchestrator control plane + shared gateway are up;
-  2. allocate the bottle a pinned source IP on the gateway network (the
-     attribution key), skipping the gateway's own address + live bottles;
-  3. register it (egress policy blob + slug metadata) → bottle id + identity
-     token;
-  4. provision its git-gate repos/creds into the running gateway.
+  1. ensure the single infra container (control plane + gateway) is up;
+  2. allocate the bottle a pinned source IP on the gateway network;
+  3. register it and provision its git-gate repos/creds into the gateway.
 
-It returns a `LaunchContext` with everything the agent container needs to
-attach — network, pinned IP, the gateway's address (its proxy target), the
-orchestrator URL, and the identity token. The agent `docker run` itself is
-the backend's job (it owns provider provisioning); this owns the
+Returns a `LaunchContext` with everything the agent container needs to
+attach. The agent `docker run` itself is the backend's job; this owns the
 orchestrator-facing wiring so that sequence stays testable in isolation.
 """
 
@@ -25,15 +19,12 @@ from ...docker_cmd import run_docker
 from ...egress import EgressPlan
 from ...git_gate import GitGatePlan
 from ...orchestrator.client import OrchestratorClient
-from ...orchestrator.gateway import GATEWAY_NAME, GATEWAY_NETWORK
-from ...orchestrator.lifecycle import OrchestratorService
-from ...orchestrator.registration import registration_inputs
+from ...orchestrator.gateway import GATEWAY_NETWORK
+from ...orchestrator.lifecycle import INFRA_NAME, OrchestratorService
+from ..consolidated_util import provision_bottle
+from ..consolidated_util import teardown_consolidated as _teardown_util
+from .gateway_provision import DockerGatewayTransport
 from .gateway_net import next_free_ip
-from .gateway_provision import (
-    DockerGatewayTransport,
-    deprovision_git_gate,
-    provision_git_gate,
-)
 
 
 class ConsolidatedLaunchError(RuntimeError):
@@ -75,24 +66,21 @@ def _container_ip(name: str, network: str) -> str:
     ip = proc.stdout.strip()
     if proc.returncode != 0 or not ip:
         raise ConsolidatedLaunchError(
-            f"gateway {name} has no address on {network}: {proc.stderr.strip()}"
+            f"container {name} has no address on {network}: {proc.stderr.strip()}"
         )
     return ip
 
 
 def _network_container_ips(network: str) -> list[str]:
     """Every address currently assigned on the gateway network — the ground
-    truth for "in use": the gateway + orchestrator infrastructure containers
-    and every live agent. Read from the network so a new bottle can't collide
-    with anything actually attached (a registry-only view would miss the
-    orchestrator/gateway containers)."""
+    truth for "in use": the infra container and every live agent. Read from
+    the network so a new bottle can't collide with anything actually attached."""
     proc = run_docker([
         "docker", "network", "inspect", "--format",
         "{{range .Containers}}{{.IPv4Address}} {{end}}", network,
     ])
     ips: list[str] = []
     for entry in proc.stdout.split():
-        # entries look like "172.20.0.2/16" — keep the address.
         ips.append(entry.split("/", 1)[0])
     return ips
 
@@ -104,33 +92,24 @@ def launch_consolidated(
     image_ref: str = "",
     tokens: dict[str, str] | None = None,
     service: OrchestratorService | None = None,
-    gateway_name: str = GATEWAY_NAME,
+    infra_name: str = INFRA_NAME,
     network: str = GATEWAY_NETWORK,
 ) -> LaunchContext:
-    """Ensure the orchestrator + gateway are up, allocate + register the
-    bottle, and provision its git-gate state. Returns the agent's attach
-    context. Raises `ConsolidatedLaunchError` (or the primitives' own errors)
-    if any step fails — the caller tears down on failure."""
+    """Ensure the infra container is up, allocate + register the bottle, and
+    provision its git-gate state. Returns the agent's attach context."""
     service = service or OrchestratorService()
     url = service.ensure_running()
     client = OrchestratorClient(url)
 
     cidr = _network_cidr(network)
-    gateway_ip = _container_ip(gateway_name, network)
+    gateway_ip = _container_ip(infra_name, network)
     source_ip = next_free_ip(cidr, _network_container_ips(network))
 
-    inputs = registration_inputs(egress_plan)
-    reg = client.register_bottle(
-        source_ip, image_ref=image_ref, policy=inputs.policy,
-        metadata=inputs.metadata, tokens=tokens,
+    transport = DockerGatewayTransport(infra_name)
+    reg = provision_bottle(
+        client, source_ip, egress_plan, git_gate_plan, transport,
+        image_ref=image_ref, tokens=tokens,
     )
-    try:
-        provision_git_gate(
-            DockerGatewayTransport(gateway_name), reg.bottle_id, git_gate_plan)
-    except Exception:
-        # Roll the registration back so a provisioning failure leaves no orphan.
-        client.teardown_bottle(reg.bottle_id)
-        raise
     return LaunchContext(
         bottle_id=reg.bottle_id,
         identity_token=reg.identity_token,
@@ -142,12 +121,11 @@ def launch_consolidated(
 
 
 def teardown_consolidated(
-    bottle_id: str, *, orchestrator_url: str, gateway_name: str = GATEWAY_NAME,
+    bottle_id: str, *, orchestrator_url: str, infra_name: str = INFRA_NAME,
 ) -> None:
-    """Deregister the bottle and remove its git-gate state from the gateway.
-    Both steps are idempotent so this is safe from a cleanup trap."""
-    OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
-    deprovision_git_gate(DockerGatewayTransport(gateway_name), bottle_id)
+    """Deregister the bottle and remove its git-gate state. Idempotent."""
+    _teardown_util(bottle_id, DockerGatewayTransport(infra_name),
+                   orchestrator_url=orchestrator_url)
 
 
 __all__ = [

bot_bottle/backend/firecracker/consolidated_launch.py

@@ -33,8 +33,7 @@ from ...orchestrator.client import OrchestratorClient
 from ...orchestrator.lifecycle import (
     OrchestratorStartError,  # re-exported so callers can catch it
 )
-from ...orchestrator.registration import registration_inputs
-from ..docker.gateway_provision import deprovision_git_gate, provision_git_gate
+from ..consolidated_util import provision_bottle, teardown_consolidated as _teardown_util
 from . import infra_vm
 
 
@@ -68,18 +67,11 @@ def launch_consolidated(
     url = infra.control_plane_url
     client = OrchestratorClient(url)
 
-    inputs = registration_inputs(egress_plan)
-    reg = client.register_bottle(
-        guest_ip, image_ref=image_ref, policy=inputs.policy,
-        metadata=inputs.metadata, tokens=tokens,
+    transport = infra_vm.gateway_transport()
+    reg = provision_bottle(
+        client, guest_ip, egress_plan, git_gate_plan, transport,
+        image_ref=image_ref, tokens=tokens,
     )
-    try:
-        provision_git_gate(
-            infra_vm.gateway_transport(), reg.bottle_id, git_gate_plan)
-    except Exception:
-        client.teardown_bottle(reg.bottle_id)
-        raise
-
     # The shared gateway CA every agent on this host trusts for TLS
     # interception — fetched from the infra VM over SSH.
     return LaunchContext(
@@ -96,8 +88,7 @@ def teardown_consolidated(bottle_id: str, *, orchestrator_url: str) -> None:
     VM. Both steps are idempotent so this is safe from a cleanup trap. Does
     NOT stop the infra VM — it's a persistent per-host singleton shared by
     every bottle."""
-    OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
-    deprovision_git_gate(infra_vm.gateway_transport(), bottle_id)
+    _teardown_util(bottle_id, infra_vm.gateway_transport(), orchestrator_url=orchestrator_url)
 
 
 __all__ = [

bot_bottle/backend/firecracker/infra_artifact.py

@@ -41,7 +41,7 @@ from . import util
 _ARTIFACT_FORMAT = "1"
 
 _REPO_ROOT = Path(__file__).resolve().parents[3]
-_DOCKERFILES = ("Dockerfile.orchestrator", "Dockerfile.gateway", "Dockerfile.infra")
+_DOCKERFILES = ("Dockerfile.orchestrator", "Dockerfile.gateway", "Dockerfile.infra", "Dockerfile.infra.fc")
 
 _DEFAULT_BASE = "https://gitea.dideric.is"
 _DEFAULT_OWNER = "didericis"

bot_bottle/backend/firecracker/infra_vm.py

@@ -125,16 +125,19 @@ def ensure_built() -> None:
 
 
 def build_infra_images_with_docker() -> None:
-    """Build the three fixed images from source with host Docker: orchestrator,
-    gateway, then the combined infra image (`COPY --from` orchestrator, `FROM`
-    gateway). The launch host uses this only in `BOT_BOTTLE_INFRA_BUILD=local`
-    mode; `publish_infra` uses it off-host to produce the published artifact."""
+    """Build the four fixed images from source with host Docker: orchestrator,
+    gateway, the shared infra base (Dockerfile.infra), then the Firecracker
+    infra image (Dockerfile.infra.fc: FROM infra + buildah). The launch host
+    uses this only in `BOT_BOTTLE_INFRA_BUILD=local` mode; `publish_infra`
+    uses it off-host to produce the published artifact."""
     docker_mod.build_image(
         _ORCHESTRATOR_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.orchestrator")
     docker_mod.build_image(
         _GATEWAY_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.gateway")
     docker_mod.build_image(
-        _INFRA_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.infra")
+        "bot-bottle-infra:latest", str(_REPO_ROOT), dockerfile="Dockerfile.infra")
+    docker_mod.build_image(
+        _INFRA_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.infra.fc")
 
 
 def build_infra_rootfs_dir() -> Path:

bot_bottle/backend/firecracker/util.py

@@ -88,7 +88,7 @@ def require_firecracker() -> None:
     booting a VM without it."""
     if not is_linux():
         die("firecracker backend is only supported on Linux (KVM). "
-            "On macOS use --backend=macos-container.")
+            "On macOS use the macos-container backend.")
     if shutil.which("firecracker") is None:
         info("Firecracker is required but was not found on PATH.")
         info("Install: https://github.com/firecracker-microvm/firecracker/releases")

bot_bottle/backend/macos_container/consolidated_launch.py

@@ -37,8 +37,7 @@ from dataclasses import dataclass
 from ...egress import EgressPlan
 from ...git_gate import GitGatePlan
 from ...orchestrator.client import OrchestratorClient
-from ...orchestrator.registration import registration_inputs
-from ..docker.gateway_provision import deprovision_git_gate, provision_git_gate
+from ..consolidated_util import provision_bottle, teardown_consolidated as _teardown_util
 from .gateway import GATEWAY_NETWORK
 from .gateway_provision import AppleGatewayTransport
 from .infra import MacosInfraService, OrchestratorStartError
@@ -103,17 +102,10 @@ def register_agent(
     container — it is the attribution key the gateway resolves policy by.
     Raises on failure; the caller tears down."""
     client = OrchestratorClient(endpoint.orchestrator_url)
-    inputs = registration_inputs(egress_plan)
-    reg = client.register_bottle(
-        source_ip, image_ref=image_ref, policy=inputs.policy,
-        metadata=inputs.metadata, tokens=tokens,
+    reg = provision_bottle(
+        client, source_ip, egress_plan, git_gate_plan, AppleGatewayTransport(),
+        image_ref=image_ref, tokens=tokens,
     )
-    try:
-        provision_git_gate(AppleGatewayTransport(), reg.bottle_id, git_gate_plan)
-    except Exception:
-        # Roll the registration back so a provisioning failure leaves no orphan.
-        client.teardown_bottle(reg.bottle_id)
-        raise
     return LaunchContext(
         bottle_id=reg.bottle_id,
         identity_token=reg.identity_token,
@@ -128,8 +120,7 @@ def teardown_consolidated(bottle_id: str, *, orchestrator_url: str) -> None:
     """Deregister the bottle and remove its git-gate state from the gateway.
     Both steps are idempotent so this is safe from a cleanup trap. Does NOT
     stop the gateway — it's a persistent per-host singleton."""
-    OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
-    deprovision_git_gate(AppleGatewayTransport(), bottle_id)
+    _teardown_util(bottle_id, AppleGatewayTransport(), orchestrator_url=orchestrator_url)
 
 
 __all__ = [

bot_bottle/cli/_common.py

@@ -3,18 +3,10 @@
 from __future__ import annotations
 
 import os
-import sys
 from pathlib import Path
 
+from ..util import read_tty_line as read_tty_line
+
 PROG = "cli.py"
 USER_CWD = os.getcwd()
 REPO_DIR = str(Path(__file__).resolve().parent.parent.parent)
-
-
-def read_tty_line() -> str:
-    """Mirror `IFS= read -r REPLY </dev/tty`. Falls back to stdin."""
-    try:
-        with open("/dev/tty", "r", encoding="utf-8") as tty:
-            return tty.readline().rstrip("\n")
-    except OSError:
-        return sys.stdin.readline().rstrip("\n")

bot_bottle/cli/cleanup.py

@@ -21,16 +21,20 @@ from __future__ import annotations
 
 import sys
 
-from ..backend import get_bottle_backend, known_backend_names
+from ..backend import get_bottle_backend, has_backend, known_backend_names
 from ..log import info
 from ._common import read_tty_line
 
 
 def cmd_cleanup(_argv: list[str]) -> int:
     # Order: stable backend iteration so the y/N output is
-    # deterministic across runs.
+    # deterministic across runs. Skip backends whose runtime
+    # isn't available on this host so e.g. macos-container
+    # doesn't error on Linux.
     plans = [
-        (name, get_bottle_backend(name)) for name in known_backend_names()
+        (name, get_bottle_backend(name))
+        for name in known_backend_names()
+        if has_backend(name)
     ]
     prepared = [(name, b, b.prepare_cleanup()) for name, b in plans]
 

bot_bottle/cli/start.py

@@ -27,7 +27,6 @@ from ..backend import (
     BottleSpec,
     enumerate_active_agents,
     get_bottle_backend,
-    known_backend_names,
 )
 from ..backend.docker import util as docker_mod
 from ..backend.docker.bottle_plan import DockerBottlePlan
@@ -57,15 +56,6 @@ def cmd_start(argv: list[str]) -> int:
             "into a cached layer."
         ),
     )
-    parser.add_argument(
-        "--backend",
-        choices=known_backend_names(),
-        default=None,
-        help=(
-            "backend to launch the bottle on (default: $BOT_BOTTLE_BACKEND "
-            "or host auto-selection). Overrides the env var when set."
-        ),
-    )
     parser.add_argument(
         "--headless",
         action="store_true",
@@ -115,11 +105,10 @@ def cmd_start(argv: list[str]) -> int:
         os.environ["BOT_BOTTLE_NO_CACHE"] = "1"
 
     manifest = ManifestIndex.resolve(USER_CWD)
-    backend_name: str | None = args.backend
 
     if args.headless:
         return _start_headless(
-            manifest, args, dry_run=dry_run, backend_name=backend_name
+            manifest, args, dry_run=dry_run
         )
 
     agent_name: str | None = args.name
@@ -170,7 +159,6 @@ def cmd_start(argv: list[str]) -> int:
     return _launch_bottle(
         spec,
         dry_run=dry_run,
-        backend_name=backend_name,
     )
 
 
@@ -182,7 +170,6 @@ def _start_headless(
     args: argparse.Namespace,
     *,
     dry_run: bool,
-    backend_name: str | None,
 ) -> int:
     """Non-interactive launch path for orchestrators / CI / webhooks.
 
@@ -230,7 +217,6 @@ def _start_headless(
     return _launch_bottle(
         spec,
         dry_run=dry_run,
-        backend_name=backend_name,
         assume_yes=True,
         headless_prompt_text=prompt,
     )
@@ -268,15 +254,18 @@ def prepare_with_preflight(
     injected callable, prompt y/N via the injected callable.
 
     `backend_name` selects which backend prepares the plan
-    (`None` → `$BOT_BOTTLE_BACKEND` → host auto-selection). The CLI
-    passes whatever `--backend` resolved to.
+    (`None` → `$BOT_BOTTLE_BACKEND` → host auto-selection).
+
+    When `spec.headless` is True the docker-fallback prompt is suppressed:
+    auto-selection dies with an actionable message rather than blocking
+    on a TTY read (which would hang CI, webhook dispatch, and orchestrators).
 
     Returns `(plan, identity)`. `plan` is None on dry-run or
     operator-N, but `identity` is set as soon as `backend.prepare`
     returns so callers can reap the prepare-time state dir via
     `settle_state(identity)` in their finally — exactly the existing
     semantics."""
-    backend = get_bottle_backend(backend_name)
+    backend = get_bottle_backend(backend_name, prompt=not spec.headless)
     plan = backend.prepare(spec, stage_dir=stage_dir)
     identity = _identity_from_plan(plan)
 

bot_bottle/gateway_init.py

@@ -61,6 +61,11 @@ class _DaemonSpec:
 _EGRESS_ONLY_ENV_PREFIXES: tuple[str, ...] = ("EGRESS_TOKEN_",)
 _READY_GATED_DAEMONS: tuple[str, ...] = ("git-gate", "git-http")
 
+# Daemons that must be requested explicitly via BOT_BOTTLE_GATEWAY_DAEMONS
+# and are NOT started in the default (env-var-unset) case. The orchestrator
+# only runs in the combined infra container, never in a standalone gateway.
+_OPT_IN_DAEMONS: frozenset[str] = frozenset({"orchestrator"})
+
 
 def _env_for_daemon(name: str, base_env: dict[str, str]) -> dict[str, str]:
     """Egress sees the full bundle env. Everyone else gets a copy
@@ -75,7 +80,14 @@ def _env_for_daemon(name: str, base_env: dict[str, str]) -> dict[str, str]:
     }
 
 
+# The orchestrator is listed first so it starts before the gateway daemons,
+# giving the control plane a head start to accept /resolve calls. The gateway
+# daemons tolerate early /resolve failures and retry per-request.
 _DAEMONS: tuple[_DaemonSpec, ...] = (
+    _DaemonSpec("orchestrator", (
+        "python3", "-m", "bot_bottle.orchestrator",
+        "--host", "0.0.0.0", "--port", "8099", "--broker", "stub",
+    )),
     _DaemonSpec("egress", ("/bin/sh", "/app/egress-entrypoint.sh")),
     _DaemonSpec("git-gate", ("/bin/sh", "/git-gate-entrypoint.sh")),
     _DaemonSpec("git-http", ("python3", "-m", "bot_bottle.git_http_backend")),
@@ -103,18 +115,20 @@ def _selected_daemons(
     env: dict[str, str],
     all_daemons: Sequence[_DaemonSpec] | None = None,
 ) -> tuple[_DaemonSpec, ...]:
-    """Filter the daemon set by the BOT_BOTTLE_GATEWAY_DAEMONS env
-    var. Unknown names in the list are ignored — the caller is the
-    source of truth for which daemons are wired.
+    """Filter the daemon set by the BOT_BOTTLE_GATEWAY_DAEMONS env var.
 
-    `all_daemons` defaults to `_DAEMONS` resolved at call time (not
-    at definition time), so tests can monkey-patch the module-level
-    `_DAEMONS` and have the new value take effect."""
+    When the var is unset/empty, return all non-opt-in daemons (the
+    standard gateway subset). Opt-in daemons (e.g. `orchestrator`) only
+    run when explicitly named — they never start in a plain gateway
+    container that doesn't set the env var. Unknown names are ignored.
+
+    `all_daemons` defaults to `_DAEMONS` resolved at call time (not at
+    definition time), so tests can pass a custom list."""
     if all_daemons is None:
         all_daemons = _DAEMONS
     raw = env.get("BOT_BOTTLE_GATEWAY_DAEMONS", "").strip()
     if not raw:
-        return tuple(all_daemons)
+        return tuple(d for d in all_daemons if d.name not in _OPT_IN_DAEMONS)
     wanted = {n.strip() for n in raw.split(",") if n.strip()}
     return tuple(d for d in all_daemons if d.name in wanted)
 
@@ -136,7 +150,7 @@ def _pump(name: str, stream: IO[bytes]) -> None:
 
 def _spawn(spec: _DaemonSpec) -> subprocess.Popen[bytes]:
     env = _env_for_daemon(spec.name, dict(os.environ))
-    proc = subprocess.Popen(
+    proc = subprocess.Popen(  # pylint: disable=consider-using-with
         _argv_for_daemon(spec.name, spec.argv, env),
         stdout=subprocess.PIPE,
         stderr=subprocess.STDOUT,
@@ -183,6 +197,14 @@ class _Supervisor:
                 except ProcessLookupError:
                     pass
 
+    def _sigkill_all(self) -> None:
+        for _, p in self.procs:
+            if p.poll() is None:
+                try:
+                    p.kill()
+                except ProcessLookupError:
+                    pass
+
     def request_restart(self, daemon_name: str) -> bool:
         """Queue a daemon restart for the main loop to process.
 
@@ -235,12 +257,7 @@ class _Supervisor:
                         f"grace ({_GRACE_SECONDS:.0f}s) elapsed; SIGKILL on "
                         f"{', '.join(still_running)}"
                     )
-                    for _, p in self.procs:
-                        if p.poll() is None:
-                            try:
-                                p.kill()
-                            except ProcessLookupError:
-                                pass
+                    self._sigkill_all()
 
         done = all(p.poll() is not None for _, p in self.procs)
         if done:
@@ -361,7 +378,10 @@ def main(argv: Sequence[str] | None = None) -> int:
     # --signal HUP <bundle>` after writing routes.yaml. The kernel
     # delivers SIGHUP to PID 1 (this supervisor); forward it to
     # mitmdump so it reloads its addon.
-    signal.signal(signal.SIGHUP, lambda *_: sup.forward_signal(signal.SIGHUP, "egress"))  # type: ignore
+    signal.signal(
+        signal.SIGHUP,
+        lambda *_: sup.forward_signal(signal.SIGHUP, "egress"),  # type: ignore[misc]
+    )
 
     while not sup.tick():
         time.sleep(_POLL_INTERVAL)

bot_bottle/orchestrator/lifecycle.py

@@ -1,17 +1,15 @@
 """Orchestrator + gateway lifecycle (PRD 0070, docker slice).
 
-Runs the orchestrator control plane **as a container** on the shared gateway
-network, alongside the gateway container. This is the PRD's "virtualize the
-orchestrator": container↔container between the gateway and the orchestrator
-avoids the host firewall (which drops container→host traffic), and the gateway
-reaches the control plane by container name over docker DNS. The host CLI
-reaches it via a published loopback port.
+Runs both the orchestrator control plane and the gateway data plane inside
+a single `bot-bottle-infra` container on the shared gateway network —
+matching the structure already used by the macOS and Firecracker backends.
+`gateway_init` is PID 1 and supervises both; the infra container is an
+idempotent per-host singleton.
 
-The orchestrator runs with the **register-only broker** — the *backend*
-launches agent containers (compose), so the orchestrator needs no docker
-socket. That keeps this control-plane container unprivileged; the host manages
-both containers. `ensure_running` is an idempotent singleton (fixed container
-names + the published port).
+The combined container replaces the prior two-container split
+(bot-bottle-orchestrator + bot-bottle-orch-gateway). The host CLI reaches
+the control plane via a published loopback port; gateway daemons reach it
+over 127.0.0.1 (same container).
 """
 
 from __future__ import annotations
@@ -26,49 +24,68 @@ from pathlib import Path
 from .. import log
 from ..docker_cmd import run_docker
 from ..paths import CONTROL_PLANE_TOKEN_ENV, bot_bottle_root, host_control_plane_token
-from .gateway import GATEWAY_IMAGE, GATEWAY_NAME, GATEWAY_NETWORK, DockerGateway, GatewayError
+from ..supervise import DB_PATH_IN_CONTAINER
+from .gateway import (
+    GATEWAY_CA_VOLUME,
+    GATEWAY_NETWORK,
+    GatewayError,
+    MITMPROXY_HOME,
+    _host_db_dir,
+)
 
 DEFAULT_PORT = 8099
-ORCHESTRATOR_NAME = "bot-bottle-orchestrator"
-ORCHESTRATOR_LABEL = "bot-bottle-orchestrator=1"
-# The control-plane's own runtime image — lean (python + the stdlib-only
-# `bot_bottle` package, bind-mounted at run time), distinct from the heavy
-# gateway data-plane image it used to borrow (#384). Env override for
-# operators pinning a published build.
+DEFAULT_STARTUP_TIMEOUT_SECONDS = 45.0
+
+INFRA_NAME = "bot-bottle-infra"
+INFRA_LABEL = "bot-bottle-infra=1"
+# The combined infra image: gateway data plane + orchestrator content.
+# Built from Dockerfile.infra (FROM gateway + COPY --from orchestrator).
+INFRA_IMAGE = os.environ.get("BOT_BOTTLE_INFRA_IMAGE", "bot-bottle-infra:latest")
+INFRA_DOCKERFILE = "Dockerfile.infra"
+# Baked as a container label so `ensure_running` can detect whether the
+# running container is executing the current bind-mounted source.
+INFRA_SOURCE_HASH_LABEL = "bot-bottle-infra-source-hash"
+
+# Orchestrator image: the single canonical definition of the control-plane
+# content (lean: python:3.12-slim + bot_bottle package, no mitmproxy/git).
+# Used as a build intermediate: `Dockerfile.infra` COPY --from this image.
 ORCHESTRATOR_IMAGE = os.environ.get(
     "BOT_BOTTLE_ORCHESTRATOR_IMAGE", "bot-bottle-orchestrator:latest"
 )
 ORCHESTRATOR_DOCKERFILE = "Dockerfile.orchestrator"
-# Baked onto the container as a label so `ensure_running` can tell whether the
-# running process is executing the *current* bind-mounted source — see
-# `source_hash`.
-ORCHESTRATOR_SOURCE_HASH_LABEL = "bot-bottle-orchestrator-source-hash"
 
-# The repo root is bind-mounted into the control-plane container so
-# `python -m bot_bottle.orchestrator` resolves the package (the orchestrator
-# is stdlib-only, so the lean orchestrator image's python is enough).
-_REPO_ROOT = Path(__file__).resolve().parents[2]
-_APP_DIR = "/app"
+# The gateway daemons + orchestrator the infra container runs.
+# BOT_BOTTLE_GATEWAY_DAEMONS listing `orchestrator` opts it in to
+# gateway_init's supervise tree (see gateway_init._OPT_IN_DAEMONS).
+_INFRA_DAEMONS = "egress,git-http,supervise,orchestrator"
+
+# The bind-mount path for the live control-plane source inside the
+# container. Separate from /app so the gateway's baked scripts
+# (egress_addon.py, egress-entrypoint.sh) are not overlaid.
+_SRC_IN_CONTAINER = "/bot-bottle-src"
+# Bot-bottle host-root bind-mount inside the container (DB + state).
 _ROOT_IN_CONTAINER = "/bot-bottle-root"
 
+# The supervise daemon writes proposals into the host DB directory.
+_SUPERVISE_DB_DIR_IN_CONTAINER = os.path.dirname(DB_PATH_IN_CONTAINER)
+
 _HEALTH_POLL_SECONDS = 0.25
-DEFAULT_STARTUP_TIMEOUT_SECONDS = 45.0
 _HEALTH_REQUEST_TIMEOUT_SECONDS = 1.0
 
+_REPO_ROOT = Path(__file__).resolve().parents[2]
+
 
 class OrchestratorStartError(RuntimeError):
-    """The orchestrator container did not become healthy within the timeout."""
+    """The infra container did not become healthy within the timeout."""
 
 
 def source_hash(repo_root: Path) -> str:
     """Content hash of the orchestrator's bind-mounted Python source (the
-    `bot_bottle` package the control-plane process imports). This only
-    changes when the code that would actually run inside the container
-    changes — `ensure_running` recreates the container on a mismatch and
-    otherwise leaves a healthy one alone, so a bottle launch that isn't
-    accompanied by a code change doesn't restart the process and drop every
-    *other* active bottle's in-memory egress tokens (`Orchestrator._tokens`
-    in `service.py`, never persisted to disk by design)."""
+    `bot_bottle` package the control-plane process imports). Changes only
+    when the code that would actually run changes — `ensure_running`
+    recreates the container on a mismatch so a code change takes effect,
+    but leaves a healthy up-to-date container alone to preserve in-memory
+    egress tokens."""
     h = hashlib.sha256()
     for path in sorted((repo_root / "bot_bottle").rglob("*.py")):
         h.update(str(path.relative_to(repo_root)).encode())
@@ -77,57 +94,37 @@ def source_hash(repo_root: Path) -> str:
 
 
 class OrchestratorService:
-    """Manages the orchestrator control-plane container + the shared gateway.
+    """Manages the single per-host infra container (control plane + gateway).
     Callers only need `ensure_running()` + `url`.
 
-    `orchestrator_name` / `orchestrator_label` let backends run independent
-    orchestrators on the same host without name collisions (e.g. the
-    Firecracker backend uses `bot-bottle-fc-orchestrator` alongside the Docker
-    backend's `bot-bottle-orchestrator`); `gateway_name` gives the paired
-    gateway container the same treatment (e.g. isolated integration tests
-    that can't share the production `GATEWAY_NAME` singleton). Subclass and
-    override `_gateway()` for anything `_gateway_image`/`gateway_name` can't
-    express (a genuinely backend-specific gateway variant)."""
+    `infra_name` / `infra_label` let backends run independent infra containers
+    on the same host without name collisions (e.g. isolated integration tests
+    that can't share the production INFRA_NAME singleton)."""
 
     def __init__(
         self,
         *,
         port: int = DEFAULT_PORT,
         network: str = GATEWAY_NETWORK,
-        image: str = ORCHESTRATOR_IMAGE,
-        gateway_image: str = GATEWAY_IMAGE,
-        gateway_name: str = GATEWAY_NAME,
+        image: str = INFRA_IMAGE,
         repo_root: Path = _REPO_ROOT,
         host_root: Path | None = None,
-        orchestrator_name: str = ORCHESTRATOR_NAME,
-        orchestrator_label: str = ORCHESTRATOR_LABEL,
+        infra_name: str = INFRA_NAME,
+        infra_label: str = INFRA_LABEL,
     ) -> None:
         self.port = port
         self.network = network
-        # Two distinct images (#384): `image` is the lean control-plane
-        # runtime this container runs; `_gateway_image` is the heavy egress /
-        # git-gate / supervise data plane the gateway container runs. They
-        # were one conflated image before the split.
         self.image = image
-        self._gateway_image = gateway_image
-        self._gateway_name = gateway_name
         self._repo_root = repo_root
         self._host_root = host_root or bot_bottle_root()
-        self._orchestrator_name = orchestrator_name
-        self._orchestrator_label = orchestrator_label
+        self._infra_name = infra_name
+        self._infra_label = infra_label
 
     @property
     def url(self) -> str:
         """Host-side control-plane URL (published loopback port)."""
         return f"http://127.0.0.1:{self.port}"
 
-    @property
-    def internal_url(self) -> str:
-        """Control-plane URL as the gateway container reaches it — by name over
-        docker DNS on the shared network. This is the gateway's
-        BOT_BOTTLE_ORCHESTRATOR_URL."""
-        return f"http://{self._orchestrator_name}:{self.port}"
-
     def is_healthy(self, *, timeout: float = _HEALTH_REQUEST_TIMEOUT_SECONDS) -> bool:
         try:
             with urllib.request.urlopen(f"{self.url}/health", timeout=timeout) as resp:
@@ -139,139 +136,125 @@ class OrchestratorService:
         proc = run_docker(["docker", "ps", "--filter", f"name=^/{name}$", "--format", "{{.Names}}"])
         return name in proc.stdout.split()
 
-    def _run_orchestrator_container(self, current_hash: str) -> None:
-        """Start the control-plane container (idempotent: clears a stale
-        fixed-name container first). Register-only broker → no docker socket.
-        Labels the container with `current_hash` so a later `ensure_running`
-        can detect a real code change (see `source_hash`)."""
-        run_docker(["docker", "rm", "--force", self._orchestrator_name])
-        proc = run_docker([
-            "docker", "run", "--detach",
-            "--name", self._orchestrator_name,
-            "--label", self._orchestrator_label,
-            "--label", f"{ORCHESTRATOR_SOURCE_HASH_LABEL}={current_hash}",
-            "--network", self.network,
-            # Host CLI reaches the control plane here; bound to loopback so it
-            # is not exposed on the host's external interfaces. NOTE: the
-            # container is still on `self.network` (the shared gateway network),
-            # so agents can reach it by container IP — which is exactly why the
-            # control plane requires the secret below rather than trusting the
-            # network boundary.
-            "--publish", f"127.0.0.1:{self.port}:{self.port}",
-            "--volume", f"{self._repo_root}:{_APP_DIR}:ro",
-            "--workdir", _APP_DIR,
-            # Persist the registry DB on the host (sole-owner: only the
-            # orchestrator opens bot-bottle.db).
-            "--volume", f"{self._host_root}:{_ROOT_IN_CONTAINER}",
-            "--env", f"BOT_BOTTLE_ROOT={_ROOT_IN_CONTAINER}",
-            # The control-plane secret it requires on every route but /health.
-            # Bare `--env NAME` → docker inherits the value from the run env
-            # below, so the secret never lands on argv / `docker inspect`.
-            "--env", CONTROL_PLANE_TOKEN_ENV,
-            "--entrypoint", "python3",
-            self.image,
-            "-m", "bot_bottle.orchestrator",
-            "--host", "0.0.0.0", "--port", str(self.port), "--broker", "stub",
-        ], env={**os.environ, CONTROL_PLANE_TOKEN_ENV: host_control_plane_token()})
-        if proc.returncode != 0:
-            raise OrchestratorStartError(
-                f"orchestrator container failed to start: {proc.stderr.strip()}"
-            )
-
-    def _gateway(self) -> DockerGateway:
-        return DockerGateway(
-            self._gateway_image,
-            name=self._gateway_name,
-            network=self.network,
-            orchestrator_url=self.internal_url,
-        )
-
-    def _ensure_orchestrator_image(self) -> None:
-        """Build the lean control-plane image from `Dockerfile.orchestrator`
-        when it's missing (#384). Cheap — a `FROM python:*-slim` base with no
-        deps to install, so the layer cache makes rebuilds a no-op. Unlike the
-        gateway image this is build-if-missing, not build-every-time: the
-        control plane bind-mounts its source, so a code change is caught by the
-        source-hash recreate (below), not by an image rebuild."""
-        if run_docker(["docker", "image", "inspect", self.image]).returncode == 0:
-            return
-        argv = ["docker", "build", "-t", self.image,
-                "-f", str(self._repo_root / ORCHESTRATOR_DOCKERFILE),
-                str(self._repo_root)]
-        if os.environ.get("BOT_BOTTLE_NO_CACHE"):
-            argv.insert(2, "--no-cache")
-        proc = run_docker(argv)
-        if proc.returncode != 0:
-            raise GatewayError(
-                f"orchestrator image build failed: {proc.stderr.strip()}"
-            )
-
-    def _orchestrator_source_current(self, current_hash: str) -> bool:
-        """True iff the running orchestrator container was created from the
-        *current* bind-mounted source. Mirrors `DockerGateway`'s
-        image-staleness check, but by content hash rather than image id since
-        the orchestrator runs bind-mounted source, not a built image."""
-        if not self._container_running(self._orchestrator_name):
+    def _infra_source_current(self, current_hash: str) -> bool:
+        """True iff the running infra container was started from the current
+        bind-mounted source. Mirrors the macOS backend's `_source_current`."""
+        if not self._container_running(self._infra_name):
             return False
         proc = run_docker([
             "docker", "inspect", "--format",
-            "{{ index .Config.Labels \"" + ORCHESTRATOR_SOURCE_HASH_LABEL + "\" }}",
-            self._orchestrator_name,
+            "{{ index .Config.Labels \"" + INFRA_SOURCE_HASH_LABEL + "\" }}",
+            self._infra_name,
         ])
         if proc.returncode != 0:
-            return True  # can't compare -> don't churn a working container
+            return True  # can't compare → don't churn a working container
         return proc.stdout.strip() == current_hash
 
+    def _ensure_network(self) -> None:
+        if run_docker(["docker", "network", "inspect", self.network]).returncode == 0:
+            return
+        proc = run_docker(["docker", "network", "create", self.network])
+        if proc.returncode != 0 and "already exists" not in proc.stderr:
+            raise GatewayError(
+                f"gateway network {self.network} failed to create: {proc.stderr.strip()}"
+            )
+
+    def _build_images(self) -> None:
+        """Build the orchestrator image (build intermediate), then the infra
+        image. Both are cache-aware: a no-op when nothing changed."""
+        for tag, dockerfile in (
+            (ORCHESTRATOR_IMAGE, ORCHESTRATOR_DOCKERFILE),
+            (self.image, INFRA_DOCKERFILE),
+        ):
+            argv = ["docker", "build", "-t", tag,
+                    "-f", str(self._repo_root / dockerfile),
+                    str(self._repo_root)]
+            if os.environ.get("BOT_BOTTLE_NO_CACHE"):
+                argv.insert(2, "--no-cache")
+            proc = run_docker(argv)
+            if proc.returncode != 0:
+                raise GatewayError(f"{dockerfile} build failed: {proc.stderr.strip()}")
+
+    def _run_infra_container(self, current_hash: str) -> None:
+        """Start the combined infra container (idempotent: clears a stale
+        fixed-name container first). Labels the container with `current_hash`
+        so a later `ensure_running` can detect a real code change."""
+        self._ensure_network()
+        run_docker(["docker", "rm", "--force", self._infra_name])
+        proc = run_docker([
+            "docker", "run", "--detach",
+            "--name", self._infra_name,
+            "--label", self._infra_label,
+            "--label", f"{INFRA_SOURCE_HASH_LABEL}={current_hash}",
+            "--network", self.network,
+            # Host CLI reaches the control plane here (loopback only).
+            "--publish", f"127.0.0.1:{self.port}:{self.port}",
+            # Persist the mitmproxy CA so it survives container recreation.
+            "--volume", f"{GATEWAY_CA_VOLUME}:{MITMPROXY_HOME}",
+            # Shared supervise DB (same file the operator reads over HTTP).
+            "--volume", f"{_host_db_dir()}:{_SUPERVISE_DB_DIR_IN_CONTAINER}",
+            "--env", f"SUPERVISE_DB_PATH={DB_PATH_IN_CONTAINER}",
+            # Live control-plane source, mounted to a path that does not
+            # overlay the gateway's baked /app scripts.
+            "--volume", f"{self._repo_root}:{_SRC_IN_CONTAINER}:ro",
+            # PYTHONPATH lets the orchestrator (and other Python daemons)
+            # import the live source ahead of the installed package.
+            "--env", f"PYTHONPATH={_SRC_IN_CONTAINER}",
+            # Orchestrator registry DB on the host (sole writer: control plane).
+            "--volume", f"{self._host_root}:{_ROOT_IN_CONTAINER}",
+            "--env", f"BOT_BOTTLE_ROOT={_ROOT_IN_CONTAINER}",
+            # Control-plane secret: required by the orchestrator (to enforce)
+            # and by the gateway daemons (to present on /resolve calls).
+            "--env", CONTROL_PLANE_TOKEN_ENV,
+            # Gateway daemons reach the orchestrator over loopback.
+            "--env", f"BOT_BOTTLE_ORCHESTRATOR_URL=http://127.0.0.1:{self.port}",
+            # Opt the orchestrator into gateway_init's supervise tree.
+            "--env", f"BOT_BOTTLE_GATEWAY_DAEMONS={_INFRA_DAEMONS}",
+            self.image,
+        ], env={**os.environ, CONTROL_PLANE_TOKEN_ENV: host_control_plane_token()})
+        if proc.returncode != 0:
+            raise OrchestratorStartError(
+                f"infra container failed to start: {proc.stderr.strip()}"
+            )
+
     def ensure_running(
         self, *, startup_timeout: float = DEFAULT_STARTUP_TIMEOUT_SECONDS,
     ) -> str:
-        """Ensure the control plane + shared gateway are up; return the host
-        control-plane URL. Idempotent — a healthy control plane running
-        current code and a running gateway are left untouched. Raises
-        `OrchestratorStartError` on timeout."""
-        gateway = self._gateway()
-        gateway.ensure_built()  # rebuild the bundle image on a source change
-        gateway.ensure_running()  # creates the shared network + (re)starts gateway
+        """Ensure the infra container (control plane + gateway) is up; return
+        the host control-plane URL. Idempotent — a healthy container on current
+        source is left untouched. Raises `OrchestratorStartError` on timeout."""
+        self._build_images()
 
-        # Recreate the orchestrator container only when its bind-mounted
-        # source has actually changed since it started — its Python process
-        # loaded that code at startup and won't reload, so a stale container
-        # would keep running OLD control-plane code. Recreating on *every*
-        # launch (the prior behaviour) would drop every other active
-        # bottle's in-memory egress tokens each time a new bottle starts,
-        # since the orchestrator process holds them only in memory (#381).
         current_hash = source_hash(self._repo_root)
-        if self.is_healthy() and self._orchestrator_source_current(current_hash):
+        if self.is_healthy() and self._infra_source_current(current_hash):
             return self.url
 
-        self._ensure_orchestrator_image()
-        log.info(
-            "starting orchestrator container",
-            context={"name": self._orchestrator_name},
-        )
-        self._run_orchestrator_container(current_hash)
+        log.info("starting infra container", context={"name": self._infra_name})
+        self._run_infra_container(current_hash)
 
         deadline = time.monotonic() + startup_timeout
         while time.monotonic() < deadline:
             if self.is_healthy():
-                log.info("orchestrator healthy", context={"url": self.url})
+                log.info("infra container healthy", context={"url": self.url})
                 return self.url
             time.sleep(_HEALTH_POLL_SECONDS)
         raise OrchestratorStartError(
-            f"orchestrator at {self.url} did not become healthy within {startup_timeout:g}s"
+            f"infra container at {self.url} did not become healthy within {startup_timeout:g}s"
         )
 
     def stop(self) -> None:
-        """Remove the orchestrator + gateway containers (idempotent)."""
-        run_docker(["docker", "rm", "--force", self._orchestrator_name])
-        self._gateway().stop()
+        """Remove the infra container (idempotent)."""
+        run_docker(["docker", "rm", "--force", self._infra_name])
 
 
 __all__ = [
     "OrchestratorService",
     "OrchestratorStartError",
-    "ORCHESTRATOR_NAME",
+    "INFRA_NAME",
+    "INFRA_IMAGE",
+    "INFRA_SOURCE_HASH_LABEL",
     "ORCHESTRATOR_IMAGE",
     "DEFAULT_PORT",
     "DEFAULT_STARTUP_TIMEOUT_SECONDS",
+    "source_hash",
 ]

bot_bottle/util.py

@@ -7,6 +7,7 @@ from __future__ import annotations
 
 import ipaddress
 import os
+import sys
 
 
 def is_ip_literal(value: str) -> bool:
@@ -17,6 +18,15 @@ def is_ip_literal(value: str) -> bool:
     return True
 
 
+def read_tty_line() -> str:
+    """Mirror `IFS= read -r REPLY </dev/tty`. Falls back to stdin."""
+    try:
+        with open("/dev/tty", "r", encoding="utf-8") as tty:
+            return tty.readline().rstrip("\n")
+    except OSError:
+        return sys.stdin.readline().rstrip("\n")
+
+
 def expand_tilde(path: str) -> str:
     """Expand a leading '~' to $HOME. Leaves paths without a leading
     tilde unchanged. Falls back to the empty string if $HOME is unset

docs/prds/prd-new-consolidate-docker-infra-backend.md

@@ -0,0 +1,155 @@
+# PRD prd-new: Consolidate infra backend for Docker
+
+- **Status:** Active
+- **Author:** Claude
+- **Created:** 2026-07-20
+- **Issue:** #431
+
+## Summary
+
+The Docker backend runs two containers — `bot-bottle-orch-gateway` (gateway
+data plane) and `bot-bottle-orchestrator` (control plane) — where the
+macOS and Firecracker backends already run a single combined infra
+unit. This PRD collapses Docker to the same model: one `bot-bottle-infra`
+container running both processes under the `gateway_init` supervise tree, a
+restructured `Dockerfile.infra` as the shared gateway+orchestrator base,
+and a handful of extracted shared utilities (CA cert polling, teardown
+sequence, launch skeleton) that are currently duplicated across all three
+`consolidated_launch.py` files.
+
+## Goals / success criteria
+
+- Docker backend starts exactly one infra container instead of two.
+- `Dockerfile.infra` is the shared base image (gateway + orchestrator, no
+  buildah); the Firecracker image layers buildah on top of it.
+- The orchestrator process runs under the `gateway_init` supervise tree
+  inside the combined container (one PID-1, one restart/health surface).
+- CA cert polling, the teardown sequence, and the shared launch skeleton
+  (ensure-infra → register → provision → return context) live in a single
+  shared module; all three backends import from it.
+- No functional change to macOS or Firecracker launch paths.
+
+## Non-goals
+
+- Changing per-bottle isolation — agents stay one-VM/container-each.
+- Consolidating transport implementations (`DockerGatewayTransport`,
+  `AppleGatewayTransport`, `SshGatewayTransport`) — these are already the
+  right abstraction boundary.
+- macOS DHCP-inversion of registration order — irreducible backend
+  difference, stays as-is.
+- Any changes to the orchestrator RPC protocol or the attribution model.
+
+## Design
+
+### Dockerfile restructuring
+
+**Current shape:**
+
+- `Dockerfile.gateway` — data plane (mitmproxy, gitleaks, git, openssh,
+  supervise daemons)
+- `Dockerfile.orchestrator` — control plane (python:3.12-slim + bot_bottle
+  package; stdlib-only, no third-party deps)
+- `Dockerfile.infra` — Firecracker only: `FROM bot-bottle-gateway` +
+  buildah + `COPY --from bot-bottle-orchestrator`
+
+**New shape:**
+
+- `Dockerfile.gateway` — unchanged
+- `Dockerfile.orchestrator` — unchanged (single definition of orchestrator
+  content; both Docker infra and Firecracker infra `COPY --from` it)
+- `Dockerfile.infra` — **shared base**: `FROM bot-bottle-gateway` + `COPY
+  --from bot-bottle-orchestrator` (no buildah — Docker infra image)
+- `Dockerfile.infra.fc` — Firecracker only: `FROM bot-bottle-infra` +
+  buildah/crun/netavark/aardvark-dns (layered on the shared base, same net
+  result as today)
+
+The comment in `Dockerfile.infra` that says "the docker backend keeps
+orchestrator + gateway as separate images; this combined image exists only
+for the Firecracker single-VM cut" is removed.
+
+### Orchestrator in the supervise tree
+
+`gateway_init` already supervises the data-plane daemons (egress, git-http,
+supervise-MCP). The orchestrator control plane is added as another supervised
+process: `python3 -m bot_bottle.orchestrator --host 0.0.0.0 --port <port>
+--broker stub`.
+
+The orchestrator source is bind-mounted (`/app` → repo root, as today) so
+dev live-reload still works. `source_hash`-based container recreation in
+`OrchestratorService.ensure_running` continues to apply — a code change
+recreates the combined infra container, which bounces both gateway and
+orchestrator. This is acceptable: the docker backend is a dev/legacy target
+where in-flight egress connections across a code deploy are not a hard
+requirement.
+
+### `OrchestratorService` changes
+
+`OrchestratorService` currently starts two containers in sequence: gateway
+first (`DockerGateway.ensure_running`), then orchestrator. After this PRD:
+
+- Single `docker run` of `bot-bottle-infra:latest`
+- Container name: `bot-bottle-infra` (replaces `bot-bottle-orch-gateway` +
+  `bot-bottle-orchestrator`)
+- Published ports: `127.0.0.1:{port}:{port}` for the control plane (same as
+  today)
+- Bind mounts: repo root + host root (same as today)
+- `DockerGateway` becomes an implementation detail of `OrchestratorService`
+  rather than a separately started container; the gateway image name
+  (`GATEWAY_IMAGE`) is no longer referenced at runtime, only at build time
+  for the `Dockerfile.infra` base
+
+The `_gateway()` / `ensure_running` two-step in `OrchestratorService` is
+replaced by a single `_run_infra_container()`.
+
+### Shared backend utilities
+
+Three items are duplicated across
+`backend/docker/consolidated_launch.py`,
+`backend/macos_container/consolidated_launch.py`, and
+`backend/firecracker/consolidated_launch.py`:
+
+1. **CA cert polling loop** — `deadline = time.monotonic() + timeout; while
+   ...: try fetch CA; sleep` — extracted to
+   `backend/consolidated_util.py:poll_ca_cert(transport, *, timeout)`.
+
+2. **Teardown sequence** — `OrchestratorClient(url).teardown_bottle(id)` +
+   `deprovision_git_gate(transport, id)` — extracted to
+   `backend/consolidated_util.py:teardown_consolidated(url, transport,
+   bottle_id)`.
+
+3. **Launch skeleton** — all three follow: ensure-infra → allocate/register
+   → provision git-gate → fetch CA cert → return launch context. The macOS
+   inversion (agent starts before registration, source IP from DHCP) is the
+   only deviation. Extract a shared `_provision_bottle(transport, bottle_id,
+   plan, orchestrator_url)` helper covering the register → provision →
+   return-token steps; the backends keep their own `launch_consolidated`
+   wrappers for the before/after (infra-ensure + agent-start + IP
+   allocation), calling the shared helper.
+
+The new `backend/consolidated_util.py` module holds only backend-neutral,
+transport-agnostic logic. All three backends import from it.
+
+## Implementation chunks
+
+1. **(this PR)** Dockerfile restructuring: rename current `Dockerfile.infra`
+   content to `Dockerfile.infra.fc`; write new `Dockerfile.infra` as
+   gateway+orchestrator base. Update Firecracker image-build references from
+   `Dockerfile.infra` → `Dockerfile.infra.fc`.
+
+2. Add orchestrator process to `gateway_init` supervise tree.
+
+3. Collapse `OrchestratorService` to a single-container start; rename
+   container from `bot-bottle-orch-gateway`/`bot-bottle-orchestrator` →
+   `bot-bottle-infra`; update image name constant.
+
+4. Extract `backend/consolidated_util.py` with `poll_ca_cert`,
+   `teardown_consolidated`, and `_provision_bottle`; update all three
+   `consolidated_launch.py` files to import from it.
+
+5. Update tests that reference the old container names or two-container
+   startup sequence.
+
+## Open questions
+
+None — the supervise-tree approach and shared Dockerfile layering were
+confirmed in issue #431.

tests/integration/test_orchestrator_docker_control_plane_auth.py

@@ -34,6 +34,7 @@ from tests._docker import skip_unless_docker
 # image instead of leaking a new dangling tag on every invocation.
 _TEST_ORCHESTRATOR_IMAGE = "bot-bottle-orchestrator:itest"
 _TEST_GATEWAY_IMAGE = "bot-bottle-gateway:itest"
+_TEST_INFRA_IMAGE = "bot-bottle-infra:itest"
 
 
 @skip_unless_docker()
@@ -69,20 +70,17 @@ class TestDockerControlPlaneAuthIntegration(unittest.TestCase):
         os.environ["BOT_BOTTLE_ROOT"] = cls._tmp.name
         cls.addClassCleanup(_restore_root)
 
-        orchestrator_name = f"bot-bottle-orch-itest-{suffix}"
-        gateway_name = f"bot-bottle-gw-itest-{suffix}"
+        infra_name = f"bot-bottle-infra-itest-{suffix}"
         network = f"bot-bottle-net-itest-{suffix}"
         host_root = Path(cls._tmp.name)
         cls.addClassCleanup(
-            cls._teardown_docker, orchestrator_name, gateway_name, network, host_root
+            cls._teardown_docker, infra_name, network, host_root
         )
 
         cls.svc = OrchestratorService(
-            orchestrator_name=orchestrator_name,
-            gateway_name=gateway_name,
+            infra_name=infra_name,
             network=network,
-            image=_TEST_ORCHESTRATOR_IMAGE,
-            gateway_image=_TEST_GATEWAY_IMAGE,
+            image=_TEST_INFRA_IMAGE,
             port=20000 + secrets.randbelow(10000),
             host_root=host_root,
         )
@@ -91,23 +89,23 @@ class TestDockerControlPlaneAuthIntegration(unittest.TestCase):
 
     @staticmethod
     def _teardown_docker(
-        orchestrator_name: str, gateway_name: str, network: str, host_root: Path
+        infra_name: str, network: str, host_root: Path
     ) -> None:
         subprocess.run(
-            ["docker", "rm", "--force", orchestrator_name, gateway_name],
+            ["docker", "rm", "--force", infra_name],
             stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
         )
         subprocess.run(
             ["docker", "network", "rm", network],
             stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
         )
-        # The orchestrator container (no USER directive) wrote the registry
+        # The infra container (no USER directive) wrote the registry
         # DB as root into the throwaway host_root; chown it back so the
         # (non-root) tempdir cleanup can remove it. Same workaround
         # test_multitenant_isolation.py uses for the identical bind mount.
         subprocess.run(
             ["docker", "run", "--rm", "-v", f"{host_root}:/r",
-             "--entrypoint", "chown", _TEST_GATEWAY_IMAGE, "-R",
+             "--entrypoint", "chown", _TEST_INFRA_IMAGE, "-R",
              f"{os.getuid()}:{os.getgid()}", "/r"],
             stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
         )

tests/unit/test_backend_selection.py

@@ -57,14 +57,16 @@ class TestGetBottleBackend(unittest.TestCase):
                 return self._available
 
         # No macOS container and the host can't run firecracker (no
-        # KVM / not Linux) → docker is the last resort.
+        # KVM / not Linux) → docker fallback with a prompt. Simulate
+        # the user picking "d" (use docker anyway).
         with patch.dict(os.environ, {}, clear=True), \
              patch.object(backend_mod.FirecrackerBottleBackend,
                           "is_host_capable", classmethod(lambda cls: False)), \
              patch.object(backend_mod, "_backends", {
                  "macos-container": _FakeBackend("macos-container", False),
                  "docker": _FakeBackend("docker", True),
-             }):
+             }), \
+             patch.object(backend_mod, "read_tty_line", return_value="d"):
             b = get_bottle_backend()
         self.assertEqual("docker", b.name)
 
@@ -96,6 +98,145 @@ class TestGetBottleBackend(unittest.TestCase):
             with self.assertRaises(SystemExit):
                 get_bottle_backend("nonexistent")
 
+    def test_no_backend_available_dies(self):
+        # No VM and no docker → print install instructions and die.
+        class _FakeBackend:
+            def __init__(self, name: str, available: bool) -> None:
+                self.name = name
+                self._available = available
+
+            def is_available(self) -> bool:
+                return self._available
+
+        with patch.dict(os.environ, {}, clear=True), \
+             patch.object(backend_mod.FirecrackerBottleBackend,
+                          "is_host_capable", classmethod(lambda cls: False)), \
+             patch.object(backend_mod, "_backends", {
+                 "macos-container": _FakeBackend("macos-container", False),
+                 "docker": _FakeBackend("docker", False),
+             }), \
+             patch.object(backend_mod, "die", side_effect=SystemExit("die")):
+            with self.assertRaises(SystemExit):
+                get_bottle_backend()
+
+    def test_docker_fallback_user_quits(self):
+        # VM unavailable, docker available, user picks "q" → die.
+        class _FakeBackend:
+            def __init__(self, name: str, available: bool) -> None:
+                self.name = name
+                self._available = available
+
+            def is_available(self) -> bool:
+                return self._available
+
+        with patch.dict(os.environ, {}, clear=True), \
+             patch.object(backend_mod.FirecrackerBottleBackend,
+                          "is_host_capable", classmethod(lambda cls: False)), \
+             patch.object(backend_mod, "_backends", {
+                 "macos-container": _FakeBackend("macos-container", False),
+                 "docker": _FakeBackend("docker", True),
+             }), \
+             patch.object(backend_mod, "read_tty_line", return_value="q"), \
+             patch.object(backend_mod, "die", side_effect=SystemExit("die")):
+            with self.assertRaises(SystemExit):
+                get_bottle_backend()
+
+
+    def test_docker_fallback_non_interactive_dies(self):
+        # prompt=False: headless/CI contexts must not block on a TTY read.
+        class _FakeBackend:
+            def __init__(self, name: str, available: bool) -> None:
+                self.name = name
+                self._available = available
+
+            def is_available(self) -> bool:
+                return self._available
+
+        with patch.dict(os.environ, {}, clear=True), \
+             patch.object(backend_mod.FirecrackerBottleBackend,
+                          "is_host_capable", classmethod(lambda cls: False)), \
+             patch.object(backend_mod, "_backends", {
+                 "macos-container": _FakeBackend("macos-container", False),
+                 "docker": _FakeBackend("docker", True),
+             }), \
+             patch.object(backend_mod, "die", side_effect=SystemExit("die")):
+            with self.assertRaises(SystemExit):
+                get_bottle_backend(prompt=False)
+
+    def test_docker_fallback_user_picks_install(self):
+        # User picks [i] → print install instructions then die.
+        class _FakeBackend:
+            def __init__(self, name: str, available: bool) -> None:
+                self.name = name
+                self._available = available
+
+            def is_available(self) -> bool:
+                return self._available
+
+        with patch.dict(os.environ, {}, clear=True), \
+             patch.object(backend_mod.FirecrackerBottleBackend,
+                          "is_host_capable", classmethod(lambda cls: False)), \
+             patch.object(backend_mod, "_backends", {
+                 "macos-container": _FakeBackend("macos-container", False),
+                 "docker": _FakeBackend("docker", True),
+             }), \
+             patch.object(backend_mod, "read_tty_line", return_value="i"), \
+             patch.object(backend_mod, "_print_vm_install_instructions") as mock_inst, \
+             patch.object(backend_mod, "die", side_effect=SystemExit("die")):
+            with self.assertRaises(SystemExit):
+                get_bottle_backend()
+        mock_inst.assert_called_once()
+
+
+class TestReadTtyLine(unittest.TestCase):
+    """Unit tests for the shared read_tty_line helper in bot_bottle.util."""
+
+    def test_reads_from_dev_tty(self):
+        from unittest.mock import mock_open
+        from bot_bottle.util import read_tty_line
+
+        m = mock_open(read_data="hello\n")
+        with patch("builtins.open", m):
+            result = read_tty_line()
+        self.assertEqual("hello", result)
+        m.assert_called_once_with("/dev/tty", "r", encoding="utf-8")
+
+    def test_falls_back_to_stdin_on_oserror(self):
+        import io
+        from bot_bottle.util import read_tty_line
+        import sys as _sys
+
+        with patch("builtins.open", side_effect=OSError("no tty")), \
+             patch.object(_sys, "stdin", io.StringIO("world\n")):
+            result = read_tty_line()
+        self.assertEqual("world", result)
+
+
+class TestPrintVmInstallInstructions(unittest.TestCase):
+    """Unit tests for _print_vm_install_instructions platform branches."""
+
+    def test_linux_prints_firecracker_instructions(self):
+        from bot_bottle.backend import _print_vm_install_instructions
+
+        with patch.object(backend_mod, "_platform_vm_suggestion",
+                          return_value="firecracker"), \
+             patch.object(backend_mod, "info") as mock_info:
+            _print_vm_install_instructions()
+
+        messages = [str(c[0][0]) for c in mock_info.call_args_list]
+        self.assertTrue(any("Firecracker" in m for m in messages))
+
+    def test_macos_prints_apple_container_instructions(self):
+        from bot_bottle.backend import _print_vm_install_instructions
+
+        with patch.object(backend_mod, "_platform_vm_suggestion",
+                          return_value="macos-container"), \
+             patch.object(backend_mod, "info") as mock_info:
+            _print_vm_install_instructions()
+
+        messages = [str(c[0][0]) for c in mock_info.call_args_list]
+        self.assertTrue(any("Apple Container" in m for m in messages))
+
 
 class TestKnownBackendNames(unittest.TestCase):
     def test_returns_backends_sorted(self):

tests/unit/test_cli_cleanup_cross_backend.py

@@ -1,8 +1,10 @@
-"""Unit: `cli.py cleanup` walks every backend (issue follow-up).
+"""Unit: `cli.py cleanup` walks every available backend.
 
-Asserts cmd_cleanup queries each backend's `prepare_cleanup`,
-combines the y/N output, and runs each backend's `cleanup` when
-the operator confirms.  Mocks the backends and stdin."""
+Asserts cmd_cleanup queries each available backend's `prepare_cleanup`,
+combines the y/N output, and runs each backend's `cleanup` when the
+operator confirms. Unavailable backends (e.g. macos-container on Linux)
+are skipped so that `cleanup` never errors on a platform where a backend
+is not installed. Mocks the backends and stdin."""
 
 from __future__ import annotations
 
@@ -21,7 +23,7 @@ def _make_backend(empty: bool = True):
 
 
 class TestCmdCleanup(unittest.TestCase):
-    def test_iterates_every_backend(self):
+    def test_iterates_every_available_backend(self):
         docker, docker_plan = _make_backend(empty=False)
         fc, fc_plan = _make_backend(empty=False)
         backends_by_name = {"docker": docker, "firecracker": fc}
@@ -32,6 +34,8 @@ class TestCmdCleanup(unittest.TestCase):
         ), patch.object(
             cmd, "get_bottle_backend",
             side_effect=lambda name: backends_by_name[name],  # type: ignore
+        ), patch.object(
+            cmd, "has_backend", return_value=True,
         ), patch.object(
             cmd, "_prompt_yes", return_value=True,
         ):
@@ -42,6 +46,32 @@ class TestCmdCleanup(unittest.TestCase):
         docker.cleanup.assert_called_once_with(docker_plan)
         fc.cleanup.assert_called_once_with(fc_plan)
 
+    def test_skips_unavailable_backends(self):
+        # macos-container is not available on Linux — must be silently skipped.
+        docker, docker_plan = _make_backend(empty=False)
+        macos = MagicMock()
+        backends_by_name = {"docker": docker}
+
+        def _has(name: str) -> bool:
+            return name == "docker"
+
+        with patch.object(
+            cmd, "known_backend_names",
+            return_value=("docker", "macos-container"),
+        ), patch.object(
+            cmd, "get_bottle_backend",
+            side_effect=lambda name: backends_by_name[name],  # type: ignore
+        ), patch.object(
+            cmd, "has_backend", side_effect=_has,
+        ), patch.object(
+            cmd, "_prompt_yes", return_value=True,
+        ):
+            self.assertEqual(0, cmd.cmd_cleanup([]))
+
+        docker.prepare_cleanup.assert_called_once()
+        docker.cleanup.assert_called_once_with(docker_plan)
+        macos.prepare_cleanup.assert_not_called()
+
     def test_short_circuits_when_all_empty(self):
         docker, _ = _make_backend(empty=True)
         fc, _ = _make_backend(empty=True)
@@ -53,6 +83,8 @@ class TestCmdCleanup(unittest.TestCase):
         ), patch.object(
             cmd, "get_bottle_backend",
             side_effect=lambda name: backends_by_name[name],  # type: ignore
+        ), patch.object(
+            cmd, "has_backend", return_value=True,
         ), patch.object(
             cmd, "_prompt_yes",
         ) as prompt:
@@ -72,6 +104,8 @@ class TestCmdCleanup(unittest.TestCase):
         ), patch.object(
             cmd, "get_bottle_backend",
             side_effect=lambda name: backends_by_name[name],  # type: ignore
+        ), patch.object(
+            cmd, "has_backend", return_value=True,
         ), patch.object(
             cmd, "_prompt_yes", return_value=False,
         ):
@@ -92,6 +126,8 @@ class TestCmdCleanup(unittest.TestCase):
         ), patch.object(
             cmd, "get_bottle_backend",
             side_effect=lambda name: backends_by_name[name],  # type: ignore
+        ), patch.object(
+            cmd, "has_backend", return_value=True,
         ), patch.object(
             cmd, "_prompt_yes", return_value=True,
         ):

tests/unit/test_cli_start_backend_flag.py

@@ -1,61 +1,29 @@
-"""Unit: `cli.py start --backend=<name>` flag (issue #77).
+"""Unit: backend resolution priority — explicit name > env var.
 
-Asserts that the flag wins over the env var, that the env var is
-the fallback, and that the choices are pulled from the backend
-registry (so adding a backend lights up in argparse without code
-edits)."""
+The `--backend` flag has been removed from `cli.py start`; backend
+selection is driven by BOT_BOTTLE_BACKEND or auto-selection only.
+`get_bottle_backend` still accepts an explicit name so that `resume`
+(which records the backend from a prior session) and the `backend`
+sub-command can pass one directly."""
 
 from __future__ import annotations
 
-import argparse
 import os
 import unittest
 from unittest.mock import patch
 
 
-from bot_bottle.backend import known_backend_names
-
-
-class TestStartBackendFlag(unittest.TestCase):
-    """The flag is wired by `cmd_start`'s argparse and threaded
-    through `prepare_with_preflight(backend_name=...)`. Rather than
-    drive the whole start flow (which builds containers), we test
-    the argparse shape and the resolution function separately."""
-
-    def _build_parser(self):
-        # Mirror the parser definition from `cmd_start` so this
-        # test doesn't have to invoke the full command.
-        parser = argparse.ArgumentParser(prog="cb start")
-        parser.add_argument(
-            "--backend",
-            choices=known_backend_names(),
-            default=None,
-        )
-        parser.add_argument("name")
-        return parser
-
-    def test_flag_recognized(self):
-        args = self._build_parser().parse_args(["--backend=firecracker", "researcher"])
-        self.assertEqual("firecracker", args.backend)
-        self.assertEqual("researcher", args.name)
-
-    def test_flag_default_none_means_env_or_default_backend(self):
-        args = self._build_parser().parse_args(["researcher"])
-        self.assertIsNone(args.backend)
-
-    def test_invalid_backend_rejected_by_argparse(self):
-        parser = self._build_parser()
-        with self.assertRaises(SystemExit):
-            parser.parse_args(["--backend=garbage", "researcher"])
-
-    def test_resolution_priority_explicit_over_env(self):
-        # Independent assertion that get_bottle_backend (where
-        # `--backend` ultimately threads to) prefers the explicit
-        # name over BOT_BOTTLE_BACKEND.
+class TestBackendResolutionPriority(unittest.TestCase):
+    def test_explicit_name_overrides_env_var(self):
         from bot_bottle.backend import get_bottle_backend
         with patch.dict(os.environ, {"BOT_BOTTLE_BACKEND": "firecracker"}):
             self.assertEqual("docker", get_bottle_backend("docker").name)
 
+    def test_env_var_used_when_no_explicit_name(self):
+        from bot_bottle.backend import get_bottle_backend
+        with patch.dict(os.environ, {"BOT_BOTTLE_BACKEND": "firecracker"}):
+            self.assertEqual("firecracker", get_bottle_backend().name)
+
 
 if __name__ == "__main__":
     unittest.main()

tests/unit/test_cli_start_headless.py

@@ -175,14 +175,6 @@ class TestCmdStartHeadless(unittest.TestCase):
             )
         self.assertEqual("researcher-2", self._spec().label)
 
-    # -- backend wiring ------------------------------------------------
-
-    def test_backend_flag_forwarded(self):
-        start_mod.cmd_start(
-            ["--headless", "--backend=docker", "researcher", "--bottle", "claude",
-             "--prompt", "Do it"]
-        )
-        self.assertEqual("docker", self._launch_mock.call_args[1]["backend_name"])
 
 
 class TestPrepareWithPreflight(unittest.TestCase):

tests/unit/test_cli_start_selector.py

@@ -82,7 +82,7 @@ class TestCmdStartSelector(unittest.TestCase):
     # ------------------------------------------------------------------
 
     def test_explicit_agent_skips_agent_picker(self):
-        rc = start_mod.cmd_start(["--backend=docker", "researcher"])
+        rc = start_mod.cmd_start(["researcher"])
         self.assertEqual(0, rc)
         self._agent_picker_mock.assert_not_called()
         self._bottle_picker_mock.assert_called_once()
@@ -100,7 +100,7 @@ class TestCmdStartSelector(unittest.TestCase):
 
     def test_agent_absent_shows_agent_picker(self):
         self._agent_picker_mock.return_value = "researcher"
-        rc = start_mod.cmd_start(["--backend=docker"])
+        rc = start_mod.cmd_start([])
         self.assertEqual(0, rc)
         self._agent_picker_mock.assert_called_once()
         call_kwargs = self._agent_picker_mock.call_args
@@ -111,7 +111,7 @@ class TestCmdStartSelector(unittest.TestCase):
 
     def test_agent_picker_cancel_skips_bottle_picker(self):
         self._agent_picker_mock.return_value = None
-        rc = start_mod.cmd_start(["--backend=docker"])
+        rc = start_mod.cmd_start([])
         self.assertEqual(0, rc)
         self._bottle_picker_mock.assert_not_called()
         self._launch_mock.assert_not_called()
@@ -168,16 +168,6 @@ class TestCmdStartSelector(unittest.TestCase):
     # Backend wiring
     # ------------------------------------------------------------------
 
-    def test_explicit_backend_forwarded(self):
-        start_mod.cmd_start(["--backend=docker", "researcher"])
-        _, kwargs = self._launch_mock.call_args
-        self.assertEqual("docker", kwargs["backend_name"])
-
-    def test_absent_backend_uses_default(self):
-        start_mod.cmd_start(["researcher"])
-        _, kwargs = self._launch_mock.call_args
-        self.assertIsNone(kwargs["backend_name"])
-
     def test_bot_bottle_backend_env_skips_backend_picker(self):
         os.environ["BOT_BOTTLE_BACKEND"] = "docker"
         try:

tests/unit/test_consolidated_launch.py

@@ -15,6 +15,7 @@ from bot_bottle.git_gate import GitGatePlan
 from bot_bottle.orchestrator.client import RegisteredBottle
 
 _MOD = "bot_bottle.backend.docker.consolidated_launch"
+_UTIL = "bot_bottle.backend.consolidated_util"
 
 
 def _egress_plan() -> EgressPlan:
@@ -49,7 +50,7 @@ class TestLaunchConsolidated(unittest.TestCase):
                 patch(f"{_MOD}._container_ip", return_value="172.18.0.2"), \
                 patch(f"{_MOD}._network_container_ips", return_value=list(on_network)), \
                 patch(f"{_MOD}.OrchestratorClient", return_value=client), \
-                patch(f"{_MOD}.provision_git_gate", provision or Mock()):
+                patch(f"{_UTIL}.provision_git_gate", provision or Mock()):
             return launch_consolidated(_egress_plan(), _git_plan(), service=service)
 
     def test_allocates_ip_registers_and_provisions(self) -> None:
@@ -84,8 +85,8 @@ class TestLaunchConsolidated(unittest.TestCase):
 class TestTeardownConsolidated(unittest.TestCase):
     def test_deregisters_and_deprovisions(self) -> None:
         client = Mock()
-        with patch(f"{_MOD}.OrchestratorClient", return_value=client), \
-                patch(f"{_MOD}.deprovision_git_gate") as deprov:
+        with patch(f"{_UTIL}.OrchestratorClient", return_value=client), \
+                patch(f"{_UTIL}.deprovision_git_gate") as deprov:
             teardown_consolidated("b1", orchestrator_url="http://orch:8080")
         client.teardown_bottle.assert_called_once_with("b1")
         deprov.assert_called_once()

tests/unit/test_infra_artifact.py

@@ -96,7 +96,7 @@ class TestVersionInputs(unittest.TestCase):
         (pkg / "app.py").write_text("print('hi')\n")
         (pkg / "egress_entrypoint.sh").write_text("#!/bin/sh\nexec mitmdump\n")
         (pkg / "netpool.defaults.env").write_text("FOO=1\n")
-        for name in ("Dockerfile.orchestrator", "Dockerfile.gateway", "Dockerfile.infra"):
+        for name in ("Dockerfile.orchestrator", "Dockerfile.gateway", "Dockerfile.infra", "Dockerfile.infra.fc"):
             (root / name).write_text(f"FROM scratch  # {name}\n")
         (root / "pyproject.toml").write_text("[project]\nname = 'bot-bottle'\n")
 

tests/unit/test_macos_consolidated_launch.py

@@ -17,6 +17,7 @@ from bot_bottle.git_gate import GitGatePlan
 from bot_bottle.orchestrator.client import RegisteredBottle
 
 _MOD = "bot_bottle.backend.macos_container.consolidated_launch"
+_UTIL = "bot_bottle.backend.consolidated_util"
 
 
 def _egress_plan() -> EgressPlan:
@@ -87,7 +88,7 @@ class TestRegisterAgent(unittest.TestCase):
         *, source_ip: str = "192.168.128.9",
     ):
         with patch(f"{_MOD}.OrchestratorClient", return_value=client), \
-                patch(f"{_MOD}.provision_git_gate", provision or Mock()):
+                patch(f"{_UTIL}.provision_git_gate", provision or Mock()):
             return register_agent(
                 _egress_plan(), _git_plan(),
                 source_ip=source_ip, endpoint=_endpoint(), image_ref="img:1",
@@ -125,8 +126,8 @@ class TestTeardown(unittest.TestCase):
     def test_deregisters_and_deprovisions(self) -> None:
         client = Mock()
         deprovision = Mock()
-        with patch(f"{_MOD}.OrchestratorClient", return_value=client), \
-                patch(f"{_MOD}.deprovision_git_gate", deprovision):
+        with patch(f"{_UTIL}.OrchestratorClient", return_value=client), \
+                patch(f"{_UTIL}.deprovision_git_gate", deprovision):
             teardown_consolidated("b1", orchestrator_url="http://o:8099")
         client.teardown_bottle.assert_called_once_with("b1")
         self.assertEqual("b1", deprovision.call_args.args[1])

tests/unit/test_orchestrator_lifecycle.py

@@ -1,4 +1,4 @@
-"""Unit: orchestrator+gateway container lifecycle — idempotent singleton (PRD 0070)."""
+"""Unit: infra container lifecycle — idempotent singleton (PRD 0070)."""
 
 from __future__ import annotations
 
@@ -8,10 +8,10 @@ import urllib.error
 from pathlib import Path
 from unittest.mock import MagicMock, Mock, patch
 
+from bot_bottle.orchestrator.gateway import GatewayError
 from bot_bottle.orchestrator.lifecycle import (
-    ORCHESTRATOR_IMAGE,
-    ORCHESTRATOR_NAME,
-    ORCHESTRATOR_SOURCE_HASH_LABEL,
+    INFRA_NAME,
+    INFRA_SOURCE_HASH_LABEL,
     OrchestratorService,
     OrchestratorStartError,
     source_hash,
@@ -20,7 +20,6 @@ from tests.unit import use_bottle_root
 
 _URLOPEN = "bot_bottle.orchestrator.lifecycle.urllib.request.urlopen"
 _RUN = "bot_bottle.orchestrator.lifecycle.run_docker"
-_GATEWAY = "bot_bottle.orchestrator.lifecycle.DockerGateway"
 _SLEEP = "bot_bottle.orchestrator.lifecycle.time.sleep"
 _MONOTONIC = "bot_bottle.orchestrator.lifecycle.time.monotonic"
 
@@ -42,10 +41,8 @@ class TestOrchestratorService(unittest.TestCase):
         self.addCleanup(use_bottle_root(Path(self._tmp.name)))
         self.svc = OrchestratorService(port=8099)
 
-    def test_urls(self) -> None:
+    def test_url(self) -> None:
         self.assertEqual("http://127.0.0.1:8099", self.svc.url)
-        # The gateway reaches the control plane by container name over docker DNS.
-        self.assertEqual(f"http://{ORCHESTRATOR_NAME}:8099", self.svc.internal_url)
 
     def test_is_healthy(self) -> None:
         with patch(_URLOPEN, return_value=_health(200)):
@@ -54,126 +51,147 @@ class TestOrchestratorService(unittest.TestCase):
             self.assertFalse(self.svc.is_healthy())
 
     def test_ensure_running_noop_when_healthy_and_source_unchanged(self) -> None:
-        # A healthy control plane already running the *current* bind-mounted
-        # source is left alone — recreating it on every launch would drop
-        # every other active bottle's in-memory egress tokens (#381).
+        # A healthy container on current source is left alone — recreating it
+        # on every launch drops in-memory egress tokens (#381).
         current = source_hash(self.svc._repo_root)
         calls: list[list[str]] = []
 
         def fake(argv: list[str], **_kw: object) -> Mock:
             calls.append(argv)
             if argv[:2] == ["docker", "ps"]:
-                return _proc(stdout=ORCHESTRATOR_NAME)
+                return _proc(stdout=INFRA_NAME)
             if argv[:2] == ["docker", "inspect"]:
                 return _proc(stdout=current)
             return _proc()
 
         with patch(_URLOPEN, return_value=_health(200)), \
-                patch(_GATEWAY) as gw_cls, patch(_RUN, side_effect=fake), patch(_SLEEP):
+                patch(_RUN, side_effect=fake), patch(_SLEEP):
             self.assertEqual(self.svc.url, self.svc.ensure_running())
-        gw_cls.return_value.ensure_running.assert_called()   # gateway kept up
         runs = [c for c in calls if c[:2] == ["docker", "run"]]
-        rms = [c for c in calls if c[:3] == ["docker", "rm", "--force"] and ORCHESTRATOR_NAME in c]
-        self.assertEqual([], runs)   # not recreated
+        rms = [c for c in calls if c[:3] == ["docker", "rm", "--force"] and INFRA_NAME in c]
+        self.assertEqual([], runs)
         self.assertEqual([], rms)
 
     def test_ensure_running_recreates_when_source_changed(self) -> None:
-        # Healthy, but the running container's label doesn't match the
-        # current source hash (a real code change) — recreate so it takes
-        # effect, same as the gateway's image-staleness check.
         calls: list[list[str]] = []
 
         def fake(argv: list[str], **_kw: object) -> Mock:
             calls.append(argv)
             if argv[:2] == ["docker", "ps"]:
-                return _proc(stdout=ORCHESTRATOR_NAME)
+                return _proc(stdout=INFRA_NAME)
             if argv[:2] == ["docker", "inspect"]:
                 return _proc(stdout="stale-hash")
             return _proc()
 
         with patch(_URLOPEN, return_value=_health(200)), \
-                patch(_GATEWAY), patch(_RUN, side_effect=fake), patch(_SLEEP):
+                patch(_RUN, side_effect=fake), patch(_SLEEP):
             self.assertEqual(self.svc.url, self.svc.ensure_running())
         runs = [c for c in calls if c[:2] == ["docker", "run"]]
         self.assertEqual(1, len(runs))
-        self.assertIn(ORCHESTRATOR_NAME, runs[0])
-        # the fresh container is labeled with the current hash, not the stale one
+        self.assertIn(INFRA_NAME, runs[0])
         current = source_hash(self.svc._repo_root)
-        self.assertIn(f"{ORCHESTRATOR_SOURCE_HASH_LABEL}={current}", runs[0])
+        self.assertIn(f"{INFRA_SOURCE_HASH_LABEL}={current}", runs[0])
 
-    def test_ensure_running_starts_orchestrator_container_when_absent(self) -> None:
-        calls: list[list[str]] = []
-
-        def fake(argv: list[str], **_kw: object) -> Mock:
-            calls.append(argv)
-            if argv[:2] == ["docker", "ps"]:
-                return _proc(stdout="")   # not running
-            return _proc()
-
-        with patch(_URLOPEN, side_effect=[urllib.error.URLError("down"), _health(200)]), \
-                patch(_GATEWAY), patch(_RUN, side_effect=fake), patch(_SLEEP):
-            self.assertEqual(self.svc.url, self.svc.ensure_running())
-        runs = [c for c in calls if c[:2] == ["docker", "run"]]
-        self.assertEqual(1, len(runs))
-        argv = runs[0]
-        self.assertIn(ORCHESTRATOR_NAME, argv)
-        self.assertIn("--broker", argv)
-        self.assertEqual("stub", argv[argv.index("--broker") + 1])  # register-only, no socket
-        self.assertIn("bot_bottle.orchestrator", argv)
-        self.assertEqual("127.0.0.1:8099:8099", argv[argv.index("--publish") + 1])
-
-    def test_ensure_running_builds_lean_orchestrator_image_when_missing(self) -> None:
-        # The control plane runs its own lean image (#384), distinct from the
-        # gateway data plane — built from Dockerfile.orchestrator when absent.
-        calls: list[list[str]] = []
-
-        def fake(argv: list[str], **_kw: object) -> Mock:
-            calls.append(argv)
-            if argv[:2] == ["docker", "ps"]:
-                return _proc(stdout="")                 # orchestrator not running
-            if argv[:3] == ["docker", "image", "inspect"]:
-                return _proc(returncode=1)               # image absent -> build
-            return _proc()
-
-        with patch(_URLOPEN, side_effect=[urllib.error.URLError("down"), _health(200)]), \
-                patch(_GATEWAY), patch(_RUN, side_effect=fake), patch(_SLEEP):
-            self.svc.ensure_running()
-        builds = [c for c in calls if c[:2] == ["docker", "build"]]
-        self.assertEqual(1, len(builds))
-        self.assertIn(ORCHESTRATOR_IMAGE, builds[0])
-        self.assertTrue(any(a.endswith("Dockerfile.orchestrator") for a in builds[0]))
-        # It is NOT the gateway image/dockerfile — the split is the point.
-        self.assertFalse(any("Dockerfile.gateway" in a for a in builds[0]))
-
-    def test_ensure_running_skips_orchestrator_image_build_when_present(self) -> None:
+    def test_ensure_running_starts_infra_container_when_absent(self) -> None:
         calls: list[list[str]] = []
 
         def fake(argv: list[str], **_kw: object) -> Mock:
             calls.append(argv)
             if argv[:2] == ["docker", "ps"]:
                 return _proc(stdout="")
-            if argv[:3] == ["docker", "image", "inspect"]:
-                return _proc(returncode=0)               # image present -> no build
             return _proc()
 
         with patch(_URLOPEN, side_effect=[urllib.error.URLError("down"), _health(200)]), \
-                patch(_GATEWAY), patch(_RUN, side_effect=fake), patch(_SLEEP):
+                patch(_RUN, side_effect=fake), patch(_SLEEP):
+            self.assertEqual(self.svc.url, self.svc.ensure_running())
+        runs = [c for c in calls if c[:2] == ["docker", "run"]]
+        self.assertEqual(1, len(runs))
+        argv = runs[0]
+        self.assertIn(INFRA_NAME, argv)
+        # Published on loopback — not exposed on external interfaces.
+        self.assertEqual("127.0.0.1:8099:8099", argv[argv.index("--publish") + 1])
+        # Both processes in one container — no separate entrypoint override.
+        self.assertNotIn("--entrypoint", argv)
+        # Gateway daemons + orchestrator explicitly opted in.
+        daemons_flag = "BOT_BOTTLE_GATEWAY_DAEMONS=egress,git-http,supervise,orchestrator"
+        self.assertIn("orchestrator", argv[argv.index(daemons_flag)])
+
+    def test_ensure_running_builds_both_images(self) -> None:
+        calls: list[list[str]] = []
+
+        def fake(argv: list[str], **_kw: object) -> Mock:
+            calls.append(argv)
+            if argv[:2] == ["docker", "ps"]:
+                return _proc(stdout="")
+            return _proc()
+
+        with patch(_URLOPEN, side_effect=[urllib.error.URLError("down"), _health(200)]), \
+                patch(_RUN, side_effect=fake), patch(_SLEEP):
             self.svc.ensure_running()
-        self.assertEqual([], [c for c in calls if c[:2] == ["docker", "build"]])
+        builds = [c for c in calls if c[:2] == ["docker", "build"]]
+        # Orchestrator (build intermediate) + infra image both built.
+        self.assertEqual(2, len(builds))
+        dockerfiles = [next(a for a in b if "Dockerfile" in a) for b in builds]
+        self.assertIn("Dockerfile.orchestrator", dockerfiles[0])
+        self.assertIn("Dockerfile.infra", dockerfiles[1])
+        # Images are distinct — the point of the split.
+        tags = [b[b.index("-t") + 1] for b in builds]
+        self.assertNotEqual(tags[0], tags[1])
 
     def test_ensure_running_raises_on_timeout(self) -> None:
         with patch(_URLOPEN, side_effect=urllib.error.URLError("down")), \
-                patch(_GATEWAY), patch(_RUN, return_value=Mock(returncode=0, stderr="")), \
+                patch(_RUN, return_value=Mock(returncode=0, stdout="", stderr="")), \
                 patch(_SLEEP), patch(_MONOTONIC, side_effect=[0.0, 0.5, 2.0]):
             with self.assertRaises(OrchestratorStartError):
                 self.svc.ensure_running(startup_timeout=1.0)
 
-    def test_stop_removes_orchestrator_and_gateway(self) -> None:
-        with patch(_RUN) as run, patch(_GATEWAY) as gw_cls:
+    def test_noop_when_healthy_and_inspect_fails(self) -> None:
+        """If docker inspect fails (e.g. docker daemon hiccup), leave the
+        working container alone rather than churning it."""
+        def fake(argv: list[str], **_kw: object) -> Mock:
+            if argv[:2] == ["docker", "ps"]:
+                return _proc(stdout=INFRA_NAME)
+            if argv[:2] == ["docker", "inspect"]:
+                return _proc(returncode=1, stderr="daemon error")
+            return _proc()
+
+        with patch(_URLOPEN, return_value=_health(200)), \
+                patch(_RUN, side_effect=fake), patch(_SLEEP):
+            self.svc.ensure_running()
+        # no docker run — the working container was left alone
+
+    def test_build_failure_raises(self) -> None:
+        with patch(_URLOPEN, side_effect=urllib.error.URLError("down")), \
+                patch(_RUN, return_value=_proc(returncode=1, stderr="no space left on device")):
+            with self.assertRaises(GatewayError):
+                self.svc.ensure_running()
+
+    def test_ensure_network_creates_if_missing(self) -> None:
+        """If the gateway network doesn't exist yet, create it."""
+        calls: list[list[str]] = []
+
+        def fake(argv: list[str], **_kw: object) -> Mock:
+            calls.append(argv)
+            if argv[:3] == ["docker", "network", "inspect"]:
+                return _proc(returncode=1, stderr="not found")
+            if argv[:2] == ["docker", "ps"]:
+                return _proc(stdout="")
+            return _proc()
+
+        with patch(_URLOPEN, side_effect=[urllib.error.URLError("down"), _health(200)]), \
+                patch(_RUN, side_effect=fake), patch(_SLEEP):
+            self.svc.ensure_running()
+        creates = [c for c in calls if c[:3] == ["docker", "network", "create"]]
+        self.assertEqual(1, len(creates))
+
+    def test_stop_removes_infra_container(self) -> None:
+        with patch(_RUN) as run:
             self.svc.stop()
-        rms = [c.args[0] for c in run.call_args_list if c.args[0][:3] == ["docker", "rm", "--force"]]
-        self.assertTrue(any(ORCHESTRATOR_NAME in a for a in rms))
-        gw_cls.return_value.stop.assert_called_once()
+        rms = [
+            c.args[0] for c in run.call_args_list
+            if c.args[0][:3] == ["docker", "rm", "--force"]
+        ]
+        self.assertTrue(any(INFRA_NAME in a for a in rms))
 
 
 if __name__ == "__main__":