fix(egress): redact the per-bottle token in the now-active multi-tenant response log

Self-review of this PR: making `response()` run in the consolidated gateway
also activates its `LOG_FULL` `_log_response` call there — previously
unreachable, since the empty static config made `response()` return early. That
logger redacted with `os.environ`, which in multi-tenant mode does NOT hold the
bottle's per-request `/resolve` tokens (only the resolved `env` overlay does),
so a non-token-shaped provisioned secret appearing in a response could be logged
in the clear.

Thread the resolved per-flow `env` into `_log_request` / `_log_response` so the
LOG_FULL redaction scrubs the calling bottle's secrets. Adds a regression test
(a non-token-shaped `/resolve` secret, absent from os.environ, must not appear
in the response log) and updates the redaction-test helpers for the new arg.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UoEZHDjv84ChoZbozQERhJ

bot_bottle/backend/firecracker/freezer.py

@@ -1,9 +1,12 @@
-"""FirecrackerFreezer — snapshot a running microVM to a Docker image.
+"""FirecrackerFreezer — snapshot a running microVM to a rootfs tar.
 
 The VM is live and can't be block-copied safely, so — like the macOS
 backend — we stream the guest root filesystem out over the control
-channel (SSH here) and rebuild an image from it. The bottle keeps
+channel (SSH here). Unlike the other backends this needs no Docker: the
-running after the snapshot.
+tar *is* the resumable artifact. `resume` extracts it and rebuilds a
+fresh per-bottle ext4 with `mke2fs -d` (see `util.build_committed_rootfs_dir`
+and `launch._build_agent_base`). The bottle keeps running after the
+snapshot.
 """
 
 from __future__ import annotations
@@ -11,9 +14,9 @@ from __future__ import annotations
 import json
 import os
 import subprocess
-import tempfile
 from pathlib import Path
 
+from ...bottle_state import committed_rootfs_path
 from ...log import die, info
 from .. import ActiveAgent
 from ..freeze import Freezer
@@ -30,14 +33,13 @@ class FirecrackerFreezer(Freezer):
         if not private_key.is_file() or not guest_ip:
             die(f"cannot freeze {agent.slug}: run dir {run_dir} is missing the "
                 f"SSH key or VM config (is the bottle still running?)")
-        image_tag = f"bot-bottle-committed-{agent.slug}:latest"
+        tar_path = committed_rootfs_path(agent.slug)
-        _commit_via_ssh(private_key, guest_ip, image_tag)
+        _commit_rootfs_via_ssh(private_key, guest_ip, tar_path)
-        info(f"committed {agent.slug} -> {image_tag!r}")
+        info(f"committed {agent.slug} -> {tar_path}")
-        return image_tag
+        return str(tar_path)
 
     def _export_hint(self, slug: str, image_ref: str) -> None:
-        info(f"to export for migration:      docker image save {image_ref} "
+        info(f"to export for migration:      cp {image_ref} {slug}.tar")
-             f"-o {slug}.tar")
 
 
 def _guest_ip_from_config(config_path: Path) -> str:
@@ -53,24 +55,36 @@ def _guest_ip_from_config(config_path: Path) -> str:
     return ""
 
 
-def _commit_via_ssh(private_key: Path, guest_ip: str, image_tag: str) -> None:
+def _commit_rootfs_via_ssh(private_key: Path, guest_ip: str, tar_path: Path) -> None:
-    with tempfile.TemporaryDirectory(prefix="bot-bottle-fc-commit.") as tmp:
+    """Stream the guest rootfs out over SSH into `tar_path`. Excludes the
-        rootfs_tar = os.path.join(tmp, "rootfs.tar")
+    virtual/live mounts (proc/sys/dev/run) — resume recreates those empty
-        ssh = util.ssh_base_argv(private_key, guest_ip)
+    mount points. Written to a `.partial` sibling and renamed on success so
-        with open(rootfs_tar, "wb") as tar_out:
+    a failed freeze never leaves a truncated artifact in its place."""
-            result = subprocess.run(
+    tar_path.parent.mkdir(parents=True, exist_ok=True)
-                [*ssh, "--", "tar", "--create", "--one-file-system",
+    partial = tar_path.with_name(tar_path.name + ".partial")
-                 "--exclude=./proc", "--exclude=./sys", "--exclude=./dev",
+    ssh = util.ssh_base_argv(private_key, guest_ip)
-                 "--exclude=./run", "--file=-", "--directory=/", "."],
+    # The snapshot can contain the bottle's private workspace, so keep it
-                stdout=tar_out, stderr=subprocess.PIPE, check=False,
+    # owner-only (0600) for the whole stream. The `os.open` mode only applies
-            )
+    # on *creation*, so unlink any leftover partial (a prior interrupted run
-        if result.returncode != 0:
+    # could have left it world-readable, or something could swap in a symlink
-            die(f"ssh tar for {guest_ip} failed: "
+    # at this predictable name) and exclusively recreate it — O_EXCL|O_NOFOLLOW
-                f"{(result.stderr or b'').decode().strip() or '<no stderr>'}")
+    # — then fchmod immediately so umask can't loosen it. Re-assert after the
-        with open(os.path.join(tmp, "Dockerfile"), "w", encoding="utf-8") as f:
+    # rename too (os.replace carries the source mode, but be explicit).
-            f.write("FROM scratch\nADD rootfs.tar /\nUSER node\nWORKDIR /home/node\n")
+    partial.unlink(missing_ok=True)
-        build = subprocess.run(
+    fd = os.open(
-            ["docker", "build", "-t", image_tag, tmp], check=False,
+        partial, os.O_WRONLY | os.O_CREAT | os.O_EXCL | os.O_NOFOLLOW, 0o600
+    )
+    os.fchmod(fd, 0o600)
+    with os.fdopen(fd, "wb") as tar_out:
+        result = subprocess.run(
+            [*ssh, "--", "tar", "--create", "--one-file-system",
+             "--exclude=./proc", "--exclude=./sys", "--exclude=./dev",
+             "--exclude=./run", "--file=-", "--directory=/", "."],
+            stdout=tar_out, stderr=subprocess.PIPE, check=False,
         )
-        if build.returncode != 0:
+    if result.returncode != 0:
-            die(f"docker build for {image_tag!r} failed")
+        partial.unlink(missing_ok=True)
+        die(f"ssh tar for {guest_ip} failed: "
+            f"{(result.stderr or b'').decode().strip() or '<no stderr>'}")
+    os.replace(partial, tar_path)
+    os.chmod(tar_path, 0o600)

bot_bottle/backend/firecracker/launch.py

@@ -1,7 +1,8 @@
 """Launch flow for the Firecracker backend (PRD 0070, consolidated).
 
 Per bottle:
-  1. build the agent image (docker), export it to a cached ext4 rootfs;
+  1. build the agent rootfs in a builder VM (buildah, no host docker), or
+     resume a frozen bottle from its committed rootfs tar; cache the ext4;
   2. ensure the per-host orchestrator + shared gateway are up;
   3. claim a free TAP pool slot (rootless flock);
   4. register the bottle on the orchestrator by the VM's guest IP (the
@@ -31,6 +32,7 @@ from typing import Callable, Generator
 
 from ...agent_provider import runtime_for
 from ...bottle_state import (
+    committed_rootfs_path,
     egress_state_dir,
     git_gate_state_dir,
     read_committed_image,
@@ -45,7 +47,6 @@ from ...git_gate import (
 )
 from ...log import info, warn
 from ...supervise import SUPERVISE_PORT
-from ..docker import util as docker_mod
 from ..docker.egress import EGRESS_PORT
 from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
 from . import firecracker_vm, image_builder, isolation_probe, netpool, util
@@ -210,16 +211,13 @@ def _build_agent_base(
 ) -> tuple[FirecrackerBottlePlan, Path]:
     """Produce the agent's base rootfs dir. Primary path: build the Dockerfile
     inside a Firecracker builder VM (buildah, no host docker), smoke-testing
-    the image before export. A committed snapshot (freeze/migrate) is still
+    the image before export. A committed snapshot (freeze/migrate) is resumed
-    exported via the host docker path until that is ported too."""
+    directly from the rootfs tar the freezer wrote — no host docker either."""
     committed = read_committed_image(plan.slug)
-    if committed and docker_mod.image_exists(committed):
+    committed_tar = committed_rootfs_path(plan.slug)
-        info(f"using committed image {committed!r}")
+    if committed and committed_tar.is_file():
-        plan = dataclasses.replace(
+        info(f"resuming from committed rootfs {committed_tar}")
-            plan,
+        return plan, util.build_committed_rootfs_dir(committed_tar)
-            agent_provision=dataclasses.replace(plan.agent_provision, image=committed),
-        )
-        return plan, util.build_base_rootfs_dir(committed)
     base = image_builder.build_agent_rootfs_dir(
         Path(plan.dockerfile_path),
         image_tag=plan.image,

bot_bottle/backend/firecracker/util.py

@@ -14,6 +14,7 @@ and `./cli.py backend setup --backend=firecracker`.
 
 from __future__ import annotations
 
+import hashlib
 import os
 import platform
 import shutil
@@ -212,15 +213,80 @@ def build_base_rootfs_dir(
     return base
 
 
+def build_committed_rootfs_dir(tar_path: Path) -> Path:
+    """Prepare a base rootfs dir from a frozen-bottle snapshot tar (the
+    freeze/resume path — no Docker). Extracts the snapshot, recreates the
+    virtual mount points the freezer excluded, and injects the guest init +
+    static dropbear, mirroring `build_base_rootfs_dir` but sourced from a tar
+    we control rather than a Docker image.
+
+    Cached under the rootfs cache, keyed by the tar's size+mtime so a
+    re-freeze re-extracts but repeated resumes of the same snapshot don't.
+    Returns the prepared directory (read as the `mke2fs -d` source)."""
+    st = tar_path.stat()
+    fingerprint = hashlib.sha256(
+        f"{tar_path}:{st.st_size}:{st.st_mtime_ns}".encode()
+    ).hexdigest()[:16]
+    base = cache_dir() / "rootfs" / f"committed-{fingerprint}"
+    ready = base / ".bb-ready"
+    if ready.is_file():
+        return base
+
+    if base.exists():
+        shutil.rmtree(base, ignore_errors=True)
+    base.mkdir(parents=True)
+
+    info(f"extracting committed rootfs {tar_path} -> {base}")
+    result = subprocess.run(
+        ["tar", "-x", "-f", str(tar_path), "-C", str(base)],
+        capture_output=True, text=True, check=False,
+    )
+    if result.returncode != 0:
+        die(f"extracting committed rootfs {tar_path} failed: "
+            f"{result.stderr.strip() or '<no stderr>'}")
+
+    # The freezer excludes the live/virtual filesystems from the snapshot;
+    # recreate them as empty mount points so the guest init can mount
+    # proc/sys/dev and dropbear has a writable /run.
+    for mount_point in ("proc", "sys", "dev", "run"):
+        (base / mount_point).mkdir(mode=0o755, exist_ok=True)
+
+    inject_guest_boot(base)
+    ready.write_text("ok\n")
+    return base
+
+
 def inject_guest_boot(rootfs: Path, init_script: str | None = None) -> None:
     """Drop the static dropbear and the PID-1 init into the rootfs.
     `init_script` defaults to the SSH-only agent init; the infra VM
-    passes its own (control plane + gateway) init."""
+    passes its own (control plane + gateway) init.
-    shutil.copy2(dropbear_path(), rootfs / "bb-dropbear")
+
-    os.chmod(rootfs / "bb-dropbear", 0o755)
+    A committed snapshot is guest-controlled, so `bb-dropbear`/`bb-init`
-    init = rootfs / "bb-init"
+    may already exist as symlinks aimed at a host file (e.g. bb-init ->
-    init.write_text(init_script or _GUEST_INIT)
+    ~/.bashrc). Replace whatever is there and create the files with
-    os.chmod(init, 0o755)
+    O_EXCL|O_NOFOLLOW so the write always lands a fresh regular file in
+    the staging tree and never follows a planted symlink out of it."""
+    _write_staged_file(rootfs / "bb-dropbear", dropbear_path().read_bytes())
+    _write_staged_file(rootfs / "bb-init", (init_script or _GUEST_INIT).encode())
+
+
+def _write_staged_file(path: Path, data: bytes) -> None:
+    """Write `data` to `path` (mode 0755) as a fresh regular file inside a
+    staging rootfs, replacing any pre-existing entry without following a
+    symlink at `path`. Fails closed on anything unexpected there."""
+    if path.is_symlink() or path.exists():
+        if path.is_dir() and not path.is_symlink():
+            shutil.rmtree(path)
+        else:
+            path.unlink()
+    fd = os.open(
+        path, os.O_WRONLY | os.O_CREAT | os.O_EXCL | os.O_NOFOLLOW, 0o755
+    )
+    try:
+        os.write(fd, data)
+    finally:
+        os.close(fd)
+    os.chmod(path, 0o755)
 
 
 def build_rootfs_ext4(base_dir: Path, out_path: Path, *, slack_mib: int = 1024) -> None:

bot_bottle/backend/macos_container/backend.py

@@ -89,6 +89,14 @@ class MacosContainerBottleBackend(
         with _launch.launch(plan, provision=self.provision) as bottle:
             yield bottle
 
+    def ensure_orchestrator(self) -> str:
+        """Bring up the per-host infra container (control plane + gateway) and
+        return its control-plane URL — the on-demand entry point operator tools
+        (`supervise`) call when no control plane is running yet. Mirrors
+        firecracker's infra-VM bring-up."""
+        from .infra import MacosInfraService
+        return MacosInfraService().ensure_running().control_plane_url
+
     def prepare_cleanup(self) -> MacosContainerBottleCleanupPlan:
         return _cleanup.prepare_cleanup()
 

bot_bottle/backend/macos_container/bottle_plan.py

@@ -13,9 +13,13 @@ from .. import BottlePlan
 class MacosContainerBottlePlan(BottlePlan):
     slug: str
     forwarded_env: dict[str, str] = field(repr=False)
-    agent_proxy_url: str = ""
     agent_git_gate_url: str = ""
     agent_supervise_url: str = ""
+    # Read by provision-time consumers (git extraHeader, supervise MCP header)
+    # via getattr(plan, "identity_token", ""); stamped in launch after the
+    # bottle is registered. See launch.py's stamp for why it lives here and not
+    # only in the exec-time proxy env.
+    identity_token: str = ""
 
     @property
     def container_name(self) -> str:

bot_bottle/backend/macos_container/consolidated_launch.py

@@ -15,6 +15,9 @@ caller has to start the agent in between. `ensure_gateway` runs first because
 the agent's proxy env needs the gateway's address at `container run` time; the
 agent's *own* address (the attribution key) only exists afterwards.
 
+The control plane and the gateway are one **infra container** here (see
+`infra`), so `gateway_ip` and the control-plane host are the same address.
+
 The consequence for the identity token: it is minted by registration, i.e.
 *after* the agent container exists, so it cannot be baked into the run-time
 env the way docker's compose spec does. It is delivered at `container exec`
@@ -38,7 +41,7 @@ from ...orchestrator.registration import registration_inputs
 from ..docker.gateway_provision import deprovision_git_gate, provision_git_gate
 from .gateway import GATEWAY_NETWORK
 from .gateway_provision import AppleGatewayTransport
-from .orchestrator_service import MacosOrchestratorService, OrchestratorStartError
+from .infra import MacosInfraService, OrchestratorStartError
 
 
 class ConsolidatedLaunchError(RuntimeError):
@@ -47,7 +50,9 @@ class ConsolidatedLaunchError(RuntimeError):
 
 @dataclass(frozen=True)
 class GatewayEndpoint:
-    """What the agent `container run` needs to reach the shared gateway."""
+    """What the agent `container run` needs to reach the shared gateway (the
+    infra container). `gateway_ip` is that container's host-only address, the
+    same host the control-plane URL points at."""
 
     orchestrator_url: str
     gateway_ip: str         # the gateway's address — the agent's proxy target
@@ -68,19 +73,18 @@ class LaunchContext:
 
 
 def ensure_gateway(
-    *, service: MacosOrchestratorService | None = None,
+    *, service: MacosInfraService | None = None,
 ) -> GatewayEndpoint:
-    """Ensure the orchestrator control plane + shared gateway are up, and
+    """Ensure the per-host infra container (control plane + gateway) is up and
-    report how to reach them. Idempotent — both are per-host singletons, so N
+    report how to reach it. Idempotent — one singleton, so N bottle launches
-    bottle launches share the one pair. Call before starting the agent
+    share it. Call before starting the agent container: the agent's proxy env
-    container: the agent's proxy env needs `gateway_ip` at run time."""
+    needs `gateway_ip` at run time."""
-    service = service or MacosOrchestratorService()
+    service = service or MacosInfraService()
-    url = service.ensure_running()
+    infra = service.ensure_running()
-    gateway = service.gateway(url)
     return GatewayEndpoint(
-        orchestrator_url=url,
+        orchestrator_url=infra.control_plane_url,
-        gateway_ip=gateway.ip_on_shared_network(),
+        gateway_ip=infra.gateway_ip,
-        gateway_ca_pem=gateway.ca_cert_pem(),
+        gateway_ca_pem=service.ca_cert_pem(),
         network=service.network,
     )
 

bot_bottle/backend/macos_container/enumerate.py

@@ -6,14 +6,13 @@ import subprocess
 
 from ...bottle_state import read_metadata
 from .. import ActiveAgent
-from .gateway import GATEWAY_NAME
+from .infra import INFRA_NAME
-from .orchestrator_service import ORCHESTRATOR_NAME
 
 _PREFIX = "bot-bottle-"
-# The shared per-host singletons carry the same prefix as agent containers but
+# The shared per-host infra container carries the same prefix as agent
-# are infrastructure, not bottles — one gateway and one control plane serve
+# containers but is infrastructure, not a bottle — one control plane + gateway
-# every agent, so listing them as agents would invent one per host.
+# serves every agent, so listing it as an agent would invent one per host.
-_INFRA_NAMES = frozenset({GATEWAY_NAME, ORCHESTRATOR_NAME})
+_INFRA_NAMES = frozenset({INFRA_NAME})
 
 
 def enumerate_active() -> list[ActiveAgent]:

bot_bottle/backend/macos_container/gateway.py

@@ -1,241 +1,46 @@
-"""The consolidated per-host gateway as an Apple container (PRD 0070).
+"""Shared network/image constants for the macOS consolidated infra container.
 
-The macOS counterpart of `orchestrator.gateway.DockerGateway`: one persistent
+The gateway data plane no longer runs as its own Apple container — it shares a
-gateway per host, shared by every bottle, attributing each request to a bottle
+single per-host **infra container** with the control plane (see `infra`),
-by its source IP on the shared host-only network.
+because two Apple-Container guests writing one `bot-bottle.db` over virtiofs
-
+would race incoherent `fcntl` locks. This module holds the pieces both the
-Two Apple Container 1.0.0 constraints shape this and make it *not* a
+infra service and the launch/provision glue need: the network names, the
-transliteration of the docker gateway:
+gateway image, and the network-creation helper.
-
-- **No container DNS.** Containers cannot resolve each other by name (the
-  host-only network's resolver refuses the query), so the gateway reaches the
-  control plane by **IP**, not by name as the docker gateway does. The
-  orchestrator must therefore be started *before* the gateway — see
-  `orchestrator_service`.
-- **Networks are fixed at `container run`.** There is no `network connect`,
-  so a network cannot be attached to a running container. The gateway must sit
-  on one shared, up-front network for the lifetime of the process; per-bottle
-  networks would mean restarting the gateway on every launch, which defeats the
-  consolidation.
-
-The gateway is dual-homed, **NAT network first**: Apple Container makes the
-first `--network` the default route, so the egress network must lead or the
-gateway has no route to the internet.
 """
 
 from __future__ import annotations
 
 import os
-import time
-from pathlib import Path
 
-from ...orchestrator.gateway import (
+from ...orchestrator.gateway import GatewayError
-    GATEWAY_CA_CERT,
-    GATEWAY_DOCKERFILE,
-    MITMPROXY_HOME,
-    Gateway,
-    GatewayError,
-)
-from ...paths import host_db_path
-from ...supervise import DB_PATH_IN_CONTAINER
 from . import util as container_mod
 
-# Distinct from the docker gateway's names so both backends' gateways can
+# The shared host-only network the infra container and every agent bottle sit
-# coexist on one host (a macOS host can run the docker backend too).
+# on. The agent's address here is the attribution key. Distinct from the docker
-GATEWAY_NAME = "bot-bottle-mac-gateway"
+# names so both backends can coexist on one host.
-# The shared host-only network the gateway and every agent bottle sit on. The
-# agent's address here is the attribution key.
 GATEWAY_NETWORK = "bot-bottle-mac-gateway"
-# The NAT network that gives the gateway (and only the gateway) a route out.
+# The NAT network that gives the infra container (and only it) a route out.
 GATEWAY_EGRESS_NETWORK = "bot-bottle-mac-egress"
 
 GATEWAY_IMAGE = os.environ.get("BOT_BOTTLE_GATEWAY_IMAGE", "bot-bottle-gateway:latest")
 
-_REPO_ROOT = Path(__file__).resolve().parents[3]
-
-_SUPERVISE_DB_DIR_IN_CONTAINER = os.path.dirname(DB_PATH_IN_CONTAINER)
-
-# mitmproxy writes its CA a beat after start; reads poll rather than assume.
-_CA_POLL_SECONDS = 0.5
 DEFAULT_CA_TIMEOUT_SECONDS = 30.0
 
 
-def gateway_ca_dir() -> Path:
-    """Host dir bind-mounted as mitmproxy's home, keeping the gateway's
-    self-generated CA **stable across container recreation** — every agent
-    installs this one CA to trust the shared gateway's TLS interception, so it
-    must not rotate when the gateway restarts.
-
-    The docker gateway uses a named volume for this; a plain host dir is the
-    same guarantee with fewer moving parts, and it lets `ca_cert_pem` read the
-    PEM straight off the host instead of shelling into the container."""
-    path = host_db_path().parent / "mac-gateway-ca"
-    path.mkdir(parents=True, exist_ok=True)
-    return path
-
-
 def ensure_networks(
     network: str = GATEWAY_NETWORK, egress_network: str = GATEWAY_EGRESS_NETWORK,
 ) -> None:
-    """Create the shared host-only network + the gateway's NAT network.
+    """Create the shared host-only network + the NAT egress network. Idempotent
-    Idempotent — `create_network` tolerates 'already exists'.
+    — `create_network` tolerates 'already exists'."""
-
-    Module-level rather than a gateway method because the **orchestrator**
-    needs the shared network too, and it starts first (Apple has no container
-    DNS, so the gateway must be handed the control plane's IP). Both callers
-    ensure the networks; whoever runs first wins."""
     container_mod.create_network(egress_network)
     container_mod.create_network(network, internal=True)
 
 
-def _host_db_dir() -> str:
-    db_dir = host_db_path().parent
-    db_dir.mkdir(parents=True, exist_ok=True)
-    return str(db_dir)
-
-
-def _mount(source: str, target: str, *, readonly: bool = False) -> str:
-    spec = f"type=bind,source={source},target={target}"
-    if readonly:
-        spec += ",readonly"
-    return spec
-
-
-class AppleGateway(Gateway):
-    """The consolidated gateway as a single, fixed-name Apple container."""
-
-    def __init__(
-        self,
-        image_ref: str = GATEWAY_IMAGE,
-        *,
-        name: str = GATEWAY_NAME,
-        network: str = GATEWAY_NETWORK,
-        egress_network: str = GATEWAY_EGRESS_NETWORK,
-        orchestrator_url: str = "",
-        build_context: Path | None = None,
-        dockerfile: str | None = GATEWAY_DOCKERFILE,
-    ) -> None:
-        self.image_ref = image_ref
-        self.name = name
-        self.network = network
-        self.egress_network = egress_network
-        # Reached by IP (no container DNS on Apple) — the caller resolves the
-        # orchestrator's address before constructing this. Empty → single-tenant.
-        self._orchestrator_url = orchestrator_url
-        self._build_context = build_context or _REPO_ROOT
-        self._dockerfile = dockerfile
-
-    def ensure_built(self) -> None:
-        """Build the gateway data-plane image from its Dockerfile. Builds every
-        time (cache-aware, so it's cheap when nothing changed): a stale image
-        silently runs the OLD single-tenant daemons. Mirrors `DockerGateway`."""
-        if self._dockerfile is None:
-            return
-        container_mod.build_image(
-            self.image_ref, str(self._build_context), dockerfile=self._dockerfile,
-        )
-
-    def is_running(self) -> bool:
-        return container_mod.container_is_running(self.name)
-
-    def _running_image_is_current(self) -> bool:
-        """True iff the running gateway was created from the *current*
-        `image_ref`. `ensure_built` rebuilding the image is not enough on its
-        own — the running container still holds the OLD image, so this
-        mismatch check is what makes a rebuild take effect."""
-        running = container_mod.container_image_digest(self.name)
-        current = container_mod.image_digest(self.image_ref)
-        if not running or not current:
-            return True  # can't compare → don't churn a working container
-        return running == current
-
-    def _running_control_plane_is_current(self) -> bool:
-        """True iff the running gateway points at the control plane we would
-        pass today.
-
-        Docker gets this for free — it hands the gateway a container *name*,
-        which survives the orchestrator being recreated. Apple has no container
-        DNS, so the URL is an **IP baked into the gateway's env at run time**,
-        and a recreated orchestrator can come back on a different DHCP address.
-        Without this check the gateway would keep pointing at the old address
-        and every `/resolve` would fail — denying egress for *every* bottle on
-        the host until something else happened to recreate the gateway."""
-        if not self._orchestrator_url:
-            return True
-        env = container_mod.container_env(self.name)
-        if not env:
-            return True  # can't compare → don't churn a working container
-        return env.get("BOT_BOTTLE_ORCHESTRATOR_URL") == self._orchestrator_url
-
-    def ensure_running(self) -> None:
-        if (self.is_running()
-                and self._running_image_is_current()
-                and self._running_control_plane_is_current()):
-            return
-        ensure_networks(self.network, self.egress_network)
-        container_mod.force_remove_container(self.name)
-        argv = [
-            "container", "run", "--detach",
-            "--name", self.name,
-            "--label", "bot-bottle.backend=macos-container",
-            "--label", "bot-bottle-mac-gateway=1",
-            # NAT network FIRST: Apple Container takes the first --network as
-            # the default route, so this ordering is what gives the gateway a
-            # route out. Reversing it silently blackholes egress.
-            "--network", self.egress_network,
-            "--network", self.network,
-            # The NAT gateway routes but does not resolve, so DNS is explicit.
-            "--dns", container_mod.dns_server(),
-            "--mount", _mount(str(gateway_ca_dir()), MITMPROXY_HOME),
-            "--mount", _mount(_host_db_dir(), _SUPERVISE_DB_DIR_IN_CONTAINER),
-            "--env", f"SUPERVISE_DB_PATH={DB_PATH_IN_CONTAINER}",
-        ]
-        if self._orchestrator_url:
-            # Makes the data plane multi-tenant: each request resolves
-            # source-IP → policy against the control plane.
-            argv += ["--env", f"BOT_BOTTLE_ORCHESTRATOR_URL={self._orchestrator_url}"]
-        argv.append(self.image_ref)
-        result = container_mod.run_container_argv(argv)
-        if result.returncode != 0:
-            raise GatewayError(
-                f"gateway failed to start: "
-                f"{(result.stderr or '').strip() or '<no stderr>'}"
-            )
-
-    def ip_on_shared_network(self) -> str:
-        """The gateway's address on the shared host-only network — what agents
-        point their proxy / git-http / supervise URLs at."""
-        return container_mod.container_ipv4_on_network(self.name, self.network)
-
-    def ca_cert_pem(self, *, timeout: float = DEFAULT_CA_TIMEOUT_SECONDS) -> str:
-        """The gateway's CA certificate (PEM) that agents install to trust its
-        TLS interception. Polls: mitmproxy generates it a moment after start.
-        Read from the host bind-mount, so no exec into the container."""
-        ca_path = gateway_ca_dir() / os.path.basename(GATEWAY_CA_CERT)
-        deadline = time.monotonic() + timeout
-        while True:
-            try:
-                pem = ca_path.read_text()
-                if pem.strip():
-                    return pem
-            except OSError:
-                pass
-            if time.monotonic() >= deadline:
-                raise GatewayError(
-                    f"gateway CA cert not available at {ca_path} after {timeout:g}s"
-                )
-            time.sleep(_CA_POLL_SECONDS)
-
-    def stop(self) -> None:
-        container_mod.force_remove_container(self.name)
-
-
 __all__ = [
-    "AppleGateway",
-    "GatewayError",
-    "GATEWAY_NAME",
     "GATEWAY_NETWORK",
     "GATEWAY_EGRESS_NETWORK",
     "GATEWAY_IMAGE",
-    "gateway_ca_dir",
+    "GatewayError",
+    "DEFAULT_CA_TIMEOUT_SECONDS",
+    "ensure_networks",
 ]

bot_bottle/backend/macos_container/gateway_provision.py

@@ -1,23 +1,23 @@
-"""`GatewayTransport` for the Apple gateway container (PRD 0070).
+"""`GatewayTransport` for the Apple infra container (PRD 0070).
 
 The provisioning *logic* (per-bottle creds dirs, namespaced repo init) is
 backend-neutral and lives in `backend.docker.gateway_provision`; this is only
 the transport — how files and commands reach the running gateway. Docker uses
 `docker exec`/`docker cp` and Firecracker uses SSH; Apple uses the `container`
-CLI's equivalents.
+CLI's equivalents against the infra container that hosts the gateway daemons.
 """
 
 from __future__ import annotations
 
 from ..docker.gateway_provision import GatewayProvisionError
 from . import util as container_mod
-from .gateway import GATEWAY_NAME
+from .infra import INFRA_NAME
 
 
 class AppleGatewayTransport:
-    """`GatewayTransport` for the gateway as an Apple container."""
+    """`GatewayTransport` for the gateway daemons in the Apple infra container."""
 
-    def __init__(self, gateway: str = GATEWAY_NAME) -> None:
+    def __init__(self, gateway: str = INFRA_NAME) -> None:
         self.gateway = gateway
 
     def exec(self, argv: list[str]) -> None:

bot_bottle/backend/macos_container/infra.py

@@ -0,0 +1,305 @@
+"""The per-host infra container for the macOS backend (PRD 0070).
+
+A single persistent Apple container that runs BOTH the orchestrator control
+plane and the gateway data plane — the macOS analogue of the Firecracker infra
+VM (`backend/firecracker/infra_vm.py`), not the docker backend's two separate
+containers.
+
+Why one container, not two: Apple Containers are lightweight VMs, each with its
+own kernel. The docker backend runs the orchestrator and gateway as two
+containers safely because they share the host kernel, so their concurrent
+writes to the one `bot-bottle.db` (the orchestrator's registry + the gateway
+supervise daemon's queue) are serialized by coherent `fcntl` locks. Across two
+*guest* kernels sharing a virtiofs-mounted DB those locks are not coherent, and
+concurrent writers can corrupt the file. Firecracker solved this by putting
+both services in one guest with the DB on a device only that guest mounts; this
+does the same with Apple primitives.
+
+Two consequences fall out of the single container, both simplifications:
+
+- **No DNS dance.** The control plane and the gateway daemons reach each other
+  over `127.0.0.1`, so nothing depends on Apple's (absent) container DNS and
+  there is no orchestrator-before-gateway ordering to get right.
+- **The DB is never host-shared.** It lives on a container-only volume, so no
+  host process opens the live file. The host CLI reaches registry + supervise
+  state through the control-plane HTTP surface (`cli/supervise.py` already uses
+  `OrchestratorClient`), exactly as it does for firecracker.
+
+The control-plane source is bind-mounted (like the docker orchestrator), so a
+code change takes effect on the next launch without an image rebuild; the
+gateway daemons are baked in the gateway image and rebuild through its own
+digest check.
+"""
+
+from __future__ import annotations
+
+import os
+import time
+import urllib.error
+import urllib.request
+from dataclasses import dataclass
+from pathlib import Path
+
+from ... import log
+from ...orchestrator.gateway import GATEWAY_CA_CERT
+from ...orchestrator.lifecycle import (
+    DEFAULT_PORT,
+    DEFAULT_STARTUP_TIMEOUT_SECONDS,
+    OrchestratorStartError,
+    source_hash,
+)
+from ...paths import (
+    CONTROL_PLANE_TOKEN_ENV,
+    HOST_DB_FILENAME,
+    host_control_plane_token,
+)
+from . import util as container_mod
+from .gateway import (
+    DEFAULT_CA_TIMEOUT_SECONDS,
+    GATEWAY_EGRESS_NETWORK,
+    GATEWAY_IMAGE,
+    GATEWAY_NETWORK,
+    GatewayError,
+    ensure_networks,
+)
+
+# The one per-host infra container: control plane + gateway data plane.
+INFRA_NAME = "bot-bottle-mac-infra"
+INFRA_LABEL = "bot-bottle-mac-infra=1"
+# Container-only volume holding bot-bottle.db. No host bind-mount, so the DB is
+# written by exactly one kernel (this container's). Survives recreation.
+INFRA_DB_VOLUME = "bot-bottle-mac-db"
+
+# BOT_BOTTLE_ROOT inside the container; host_db_path() resolves the DB to
+# <root>/db/<filename> and the supervise daemon writes the same file.
+_DB_ROOT_IN_CONTAINER = "/var/lib/bot-bottle"
+_DB_PATH_IN_CONTAINER = f"{_DB_ROOT_IN_CONTAINER}/db/{HOST_DB_FILENAME}"
+_SRC_IN_CONTAINER = "/bot-bottle-src"
+
+_REPO_ROOT = Path(__file__).resolve().parents[3]
+
+_HEALTH_POLL_SECONDS = 0.25
+_HEALTH_REQUEST_TIMEOUT_SECONDS = 1.0
+_CA_POLL_SECONDS = 0.5
+
+# The gateway subset the consolidated model runs (no per-bottle git:// daemon).
+_GATEWAY_DAEMONS = "egress,git-http,supervise"
+
+
+def _init_script(port: int) -> str:
+    """PID-1 init: start the control plane and the gateway daemons, both in
+    this container, reaching each other over loopback. Backgrounded so `wait`
+    reaps as PID 1. No `set -e` — a transient daemon failure must not kill the
+    whole container (gateway_init applies the same 'stay up' policy)."""
+    return (
+        "export PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin\n"
+        f"mkdir -p $(dirname {_DB_PATH_IN_CONTAINER})\n"
+        # Control plane, from the bind-mounted source (stdlib-only package).
+        f"( cd {_SRC_IN_CONTAINER} && BOT_BOTTLE_ROOT={_DB_ROOT_IN_CONTAINER} "
+        f"python3 -m bot_bottle.orchestrator --host 0.0.0.0 --port {port} "
+        "--broker stub ) &\n"
+        # Gateway data plane, multi-tenant against the local control plane.
+        f"( cd /app && BOT_BOTTLE_GATEWAY_DAEMONS={_GATEWAY_DAEMONS} "
+        f"BOT_BOTTLE_ORCHESTRATOR_URL=http://127.0.0.1:{port} "
+        f"SUPERVISE_DB_PATH={_DB_PATH_IN_CONTAINER} python3 /app/gateway_init.py ) &\n"
+        "while : ; do wait ; done\n"
+    )
+
+
+@dataclass(frozen=True)
+class InfraEndpoint:
+    """How to reach the running infra container. The control plane and the
+    gateway are the same container, so one address serves both."""
+
+    control_plane_url: str   # http://<infra ip>:8099 — host CLI + registration
+    gateway_ip: str          # same container; agents' proxy / git-http / MCP target
+
+
+class MacosInfraService:
+    """Manages the single per-host infra container. Callers use
+    `ensure_running()` (returns the endpoint) and `ca_cert_pem()`."""
+
+    def __init__(
+        self,
+        *,
+        port: int = DEFAULT_PORT,
+        network: str = GATEWAY_NETWORK,
+        egress_network: str = GATEWAY_EGRESS_NETWORK,
+        image: str = GATEWAY_IMAGE,
+        repo_root: Path = _REPO_ROOT,
+        name: str = INFRA_NAME,
+        db_volume: str = INFRA_DB_VOLUME,
+    ) -> None:
+        self.port = port
+        self.network = network
+        self.egress_network = egress_network
+        self.image = image
+        self._repo_root = repo_root
+        self._name = name
+        self._db_volume = db_volume
+
+    def _resolve_url(self) -> str:
+        """The control-plane URL, or "" while the container has no address."""
+        ip = container_mod.try_container_ipv4_on_network(self._name, self.network)
+        return f"http://{ip}:{self.port}" if ip else ""
+
+    def is_healthy(
+        self, url: str, *, timeout: float = _HEALTH_REQUEST_TIMEOUT_SECONDS,
+    ) -> bool:
+        if not url:
+            return False
+        try:
+            with urllib.request.urlopen(f"{url}/health", timeout=timeout) as resp:
+                return resp.status == 200
+        except (urllib.error.URLError, TimeoutError, OSError):
+            return False
+
+    def _source_current(self, current_hash: str) -> bool:
+        """True iff the running infra container was created from the current
+        bind-mounted control-plane source. The control-plane process loads that
+        code at startup and won't reload it, so a stale container keeps serving
+        OLD code."""
+        if not container_mod.container_is_running(self._name):
+            return False
+        env = container_mod.container_env(self._name)
+        if not env:
+            return True  # can't compare → don't churn a working container
+        return env.get("BOT_BOTTLE_SOURCE_HASH") == current_hash
+
+    def _running_healthy_endpoint(self, current_hash: str) -> InfraEndpoint | None:
+        """The endpoint if the running container is BOTH source-current and
+        answering /health, else None (→ recreate). Health, not just the source
+        label, is what lets a wedged-but-current container self-heal instead of
+        being polled to death forever."""
+        if not self._source_current(current_hash):
+            return None
+        url = self._resolve_url()
+        if url and self.is_healthy(url):
+            return InfraEndpoint(control_plane_url=url, gateway_ip=_ip_of(url))
+        return None
+
+    def ensure_built(self) -> None:
+        """Ensure the gateway data-plane image exists. The control-plane source
+        is bind-mounted, not baked, so only the gateway image needs building."""
+        container_mod.build_image(
+            self.image, str(self._repo_root), dockerfile="Dockerfile.gateway",
+        )
+
+    def ensure_running(
+        self, *, startup_timeout: float = DEFAULT_STARTUP_TIMEOUT_SECONDS,
+    ) -> InfraEndpoint:
+        """Ensure the single infra container is up; return how to reach it.
+        Idempotent per-host singleton — a healthy container on current source
+        is left untouched, so N launches share the one control plane + gateway.
+        Raises `OrchestratorStartError` on startup timeout."""
+        current_hash = source_hash(self._repo_root)
+        endpoint = self._running_healthy_endpoint(current_hash)
+        if endpoint is not None:
+            return endpoint
+        self.ensure_built()
+        log.info("starting infra container", context={"name": self._name})
+        self._run_container(current_hash)
+        return self._wait_healthy(startup_timeout)
+
+    def _run_container(self, current_hash: str) -> None:
+        ensure_networks(self.network, self.egress_network)
+        container_mod.force_remove_container(self._name)
+        argv = [
+            "container", "run", "--detach",
+            "--name", self._name,
+            "--label", "bot-bottle.backend=macos-container",
+            "--label", INFRA_LABEL,
+            # NAT network FIRST so the gateway's egress has a default route;
+            # the host-only network is where agents (and the host CLI) reach it.
+            "--network", self.egress_network,
+            "--network", self.network,
+            "--dns", container_mod.dns_server(),
+            # Container-only DB volume: one kernel writes bot-bottle.db, never
+            # shared with the host or another guest.
+            "--volume", f"{self._db_volume}:{_DB_ROOT_IN_CONTAINER}",
+            # Bind-mount the control-plane source (read-only); a code change
+            # takes effect on relaunch with no image rebuild.
+            "--mount",
+            container_mod.bind_mount_spec(
+                str(self._repo_root), _SRC_IN_CONTAINER, readonly=True),
+            # Baked onto the container so `_source_current` can detect a real
+            # control-plane code change and recreate.
+            "--env", f"BOT_BOTTLE_SOURCE_HASH={current_hash}",
+            # The control-plane secret, for BOTH the control plane (to require
+            # it) and the gateway's PolicyResolver (to present it) — they share
+            # this one container. Bare `--env NAME` inherits the value from the
+            # run process below, so the secret never lands on argv or in
+            # `container inspect`'s command line. The agent runs in a SEPARATE
+            # container that is never given this var, which is the whole point.
+            "--env", CONTROL_PLANE_TOKEN_ENV,
+            "--entrypoint", "sh",
+            self.image,
+            "-c", _init_script(self.port),
+        ]
+        run_env = {**os.environ, CONTROL_PLANE_TOKEN_ENV: host_control_plane_token()}
+        result = container_mod.run_container_argv(argv, env=run_env)
+        if result.returncode != 0:
+            raise OrchestratorStartError(
+                f"infra container failed to start: "
+                f"{(result.stderr or '').strip() or '<no stderr>'}"
+            )
+
+    def _wait_healthy(self, startup_timeout: float) -> InfraEndpoint:
+        deadline = time.monotonic() + startup_timeout
+        while True:
+            url = self._resolve_url()
+            if url and self.is_healthy(url):
+                log.info("infra container healthy", context={"url": url})
+                return InfraEndpoint(control_plane_url=url, gateway_ip=_ip_of(url))
+            if time.monotonic() >= deadline:
+                raise OrchestratorStartError(
+                    f"infra container did not become healthy within "
+                    f"{startup_timeout:g}s"
+                )
+            time.sleep(_HEALTH_POLL_SECONDS)
+
+    def ca_cert_pem(self, *, timeout: float = DEFAULT_CA_TIMEOUT_SECONDS) -> str:
+        """The gateway's mitmproxy CA (PEM) agents install to trust its TLS
+        interception. Read out of the container (the CA lives on a
+        container-internal path, not a host mount); polls because mitmproxy
+        writes it a beat after start."""
+        deadline = time.monotonic() + timeout
+        while True:
+            result = container_mod.run_container_argv(
+                ["container", "exec", self._name, "cat", GATEWAY_CA_CERT])
+            if result.returncode == 0 and result.stdout.strip():
+                return result.stdout
+            if time.monotonic() >= deadline:
+                raise GatewayError(
+                    f"gateway CA not available in {self._name} after {timeout:g}s: "
+                    f"{(result.stderr or '').strip() or 'empty'}"
+                )
+            time.sleep(_CA_POLL_SECONDS)
+
+    def stop(self) -> None:
+        """Remove the infra container (idempotent). The DB volume persists."""
+        container_mod.force_remove_container(self._name)
+
+
+def _ip_of(url: str) -> str:
+    """The host from an http://host:port URL."""
+    return url.split("://", 1)[-1].rsplit(":", 1)[0]
+
+
+def probe_control_plane_url(port: int = DEFAULT_PORT) -> str:
+    """The running infra container's control-plane URL, or "" if it isn't up.
+    Used by host-side control-plane discovery (`discover_orchestrator_url`);
+    safe to call on any host — returns "" when the container or the `container`
+    CLI isn't present."""
+    ip = container_mod.try_container_ipv4_on_network(INFRA_NAME, GATEWAY_NETWORK)
+    return f"http://{ip}:{port}" if ip else ""
+
+
+__all__ = [
+    "MacosInfraService",
+    "InfraEndpoint",
+    "OrchestratorStartError",
+    "GatewayError",
+    "INFRA_NAME",
+    "INFRA_DB_VOLUME",
+]

bot_bottle/backend/macos_container/launch.py

@@ -52,6 +52,7 @@ from ...git_gate import (
     provision_git_gate_dynamic_keys,
     revoke_git_gate_provisioned_keys,
 )
+from ...git_http_backend import DEFAULT_PORT as _GIT_HTTP_PORT
 from ...log import die, info, warn
 from ...supervise import SUPERVISE_PORT
 from ..docker.egress import EGRESS_PORT
@@ -68,7 +69,6 @@ from .consolidated_launch import (
 
 _REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
 _AGENT_SLEEP_SECONDS = "2147483647"
-_GIT_HTTP_PORT = 9420
 
 
 @contextmanager
@@ -115,10 +115,16 @@ def launch(
 
         # Step 4: read the assigned address and register by it. This is the
         # attribution key; `--cap-drop CAP_NET_RAW` at run is what makes it
-        # unforgeable.
+        # unforgeable. Poll: `container run --detach` can return before vmnet's
-        source_ip = container_mod.container_ipv4_on_network(
+        # DHCP has assigned the address.
+        source_ip = container_mod.wait_container_ipv4_on_network(
             plan.container_name, endpoint.network,
         )
+        if not source_ip:
+            die(
+                f"agent {plan.container_name} never got an address on "
+                f"{endpoint.network}"
+            )
         effective_env = {**os.environ, **plan.agent_provision.provisioned_env}
         token_values = egress_resolve_token_values(
             plan.egress_plan.token_env_map, effective_env,
@@ -140,6 +146,15 @@ def launch(
             f"(gateway {endpoint.gateway_ip}, ip {source_ip})"
         )
 
+        # Stamp the token onto the plan so provision-time consumers can read it,
+        # not only the exec-time egress proxy. git-gate's gitconfig extraHeader
+        # and the supervise MCP --header both reach the gateway on NO_PROXY (they
+        # bypass the egress proxy that carries the token), so without this the
+        # gateway's /resolve fail-closes and every git fetch/push and supervise
+        # call from the bottle is denied. Registration already produced the
+        # token above, so — unlike the run-time env — the plan CAN carry it.
+        plan = dataclasses.replace(plan, identity_token=ctx.identity_token)
+
         bottle = MacosContainerBottle(
             plan.container_name,
             teardown,
@@ -227,7 +242,6 @@ def _stamp_agent_urls(
     )
     return dataclasses.replace(
         plan,
-        agent_proxy_url=f"http://{endpoint.gateway_ip}:{EGRESS_PORT}",
         agent_git_gate_url=git_gate_url,
         agent_supervise_url=supervise_url,
     )

bot_bottle/backend/macos_container/orchestrator_service.py

@@ -1,241 +0,0 @@
-"""Orchestrator + gateway lifecycle for the macOS backend (PRD 0070).
-
-The macOS counterpart of `orchestrator.lifecycle.OrchestratorService`. Same
-shape — an idempotent singleton that brings up the control plane and the shared
-gateway and hands back the control-plane URL — but the startup **order is
-reversed**, and the reason is a real Apple Container constraint rather than a
-stylistic choice:
-
-- Docker starts the gateway first and lets it find the control plane by
-  *container name* over docker DNS.
-- Apple Container 1.0.0 has **no container DNS** (see `gateway`), so the
-  gateway can only be handed an **IP**. That IP does not exist until the
-  orchestrator container is running — hence: orchestrator first, read its
-  address, then start the gateway pointed at it.
-
-The second difference: no published port. Apple Container puts every container
-on a host-reachable address, and the host can reach the host-only network
-directly, so the host CLI and the gateway use the **same** URL — the
-orchestrator's address on the shared network. Docker needs a
-`--publish 127.0.0.1:…` hop plus a separate `internal_url` for the same job.
-
-Like the docker service this runs the **register-only broker**: the backend
-launches agent containers, so the control plane needs no privileged socket.
-"""
-
-from __future__ import annotations
-
-import time
-import urllib.error
-import urllib.request
-from pathlib import Path
-
-from ... import log
-from ...orchestrator.lifecycle import (
-    DEFAULT_PORT,
-    DEFAULT_STARTUP_TIMEOUT_SECONDS,
-    ORCHESTRATOR_DOCKERFILE,
-    ORCHESTRATOR_IMAGE,
-    ORCHESTRATOR_SOURCE_HASH_LABEL,
-    OrchestratorStartError,
-    source_hash,
-)
-from ...paths import bot_bottle_root
-from . import util as container_mod
-from .gateway import (
-    GATEWAY_EGRESS_NETWORK,
-    GATEWAY_IMAGE,
-    GATEWAY_NETWORK,
-    AppleGateway,
-    ensure_networks,
-)
-
-# Distinct from the docker backend's container name so both can run on one host.
-ORCHESTRATOR_NAME = "bot-bottle-mac-orchestrator"
-
-_REPO_ROOT = Path(__file__).resolve().parents[3]
-_APP_DIR = "/app"
-_ROOT_IN_CONTAINER = "/bot-bottle-root"
-
-_HEALTH_POLL_SECONDS = 0.25
-_HEALTH_REQUEST_TIMEOUT_SECONDS = 1.0
-
-
-def _mount(source: str, target: str, *, readonly: bool = False) -> str:
-    spec = f"type=bind,source={source},target={target}"
-    if readonly:
-        spec += ",readonly"
-    return spec
-
-
-class MacosOrchestratorService:
-    """Manages the orchestrator control-plane container + the shared Apple
-    gateway. Callers only need `ensure_running()`, which returns the URL."""
-
-    def __init__(
-        self,
-        *,
-        port: int = DEFAULT_PORT,
-        network: str = GATEWAY_NETWORK,
-        egress_network: str = GATEWAY_EGRESS_NETWORK,
-        image: str = ORCHESTRATOR_IMAGE,
-        gateway_image: str = GATEWAY_IMAGE,
-        repo_root: Path = _REPO_ROOT,
-        host_root: Path | None = None,
-        orchestrator_name: str = ORCHESTRATOR_NAME,
-    ) -> None:
-        self.port = port
-        self.network = network
-        self.egress_network = egress_network
-        self.image = image
-        self._gateway_image = gateway_image
-        self._repo_root = repo_root
-        self._host_root = host_root or bot_bottle_root()
-        self._orchestrator_name = orchestrator_name
-        # Resolved once the container is up — there is no name to fall back on.
-        self._url = ""
-
-    @property
-    def url(self) -> str:
-        """The control-plane URL, or "" before the container is up. One URL for
-        both the host CLI and the gateway (see the module docstring)."""
-        return self._url
-
-    def _resolve_url(self) -> str:
-        """The control-plane URL, or "" while the container has no address."""
-        ip = container_mod.try_container_ipv4_on_network(
-            self._orchestrator_name, self.network,
-        )
-        return f"http://{ip}:{self.port}" if ip else ""
-
-    def is_healthy(
-        self, url: str = "", *, timeout: float = _HEALTH_REQUEST_TIMEOUT_SECONDS,
-    ) -> bool:
-        target = url or self._url
-        if not target:
-            return False
-        try:
-            with urllib.request.urlopen(f"{target}/health", timeout=timeout) as resp:
-                return resp.status == 200
-        except (urllib.error.URLError, TimeoutError, OSError):
-            return False
-
-    def _ensure_orchestrator_image(self) -> None:
-        """Build the lean control-plane image when missing. 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, not a rebuild."""
-        if container_mod.image_exists(self.image):
-            return
-        container_mod.build_image(
-            self.image, str(self._repo_root), dockerfile=ORCHESTRATOR_DOCKERFILE,
-        )
-
-    def _orchestrator_source_current(self, current_hash: str) -> bool:
-        """True iff the running orchestrator was created from the *current*
-        bind-mounted source. The process loaded that code at startup and won't
-        reload it, so a stale container would keep serving OLD control-plane
-        code."""
-        if not container_mod.container_is_running(self._orchestrator_name):
-            return False
-        data = container_mod.inspect_container(self._orchestrator_name)
-        config = data.get("configuration")
-        labels = config.get("labels") if isinstance(config, dict) else None
-        if not isinstance(labels, dict):
-            return True  # can't compare → don't churn a working container
-        return labels.get(ORCHESTRATOR_SOURCE_HASH_LABEL) == current_hash
-
-    def _run_orchestrator_container(self, current_hash: str) -> None:
-        # The orchestrator is the first thing on the shared network, so it —
-        # not the gateway — is what has to bring the network into existence.
-        ensure_networks(self.network, self.egress_network)
-        container_mod.force_remove_container(self._orchestrator_name)
-        argv = [
-            "container", "run", "--detach",
-            "--name", self._orchestrator_name,
-            "--label", "bot-bottle.backend=macos-container",
-            "--label", f"{ORCHESTRATOR_SOURCE_HASH_LABEL}={current_hash}",
-            # Host-only network only: the control plane needs no route out, and
-            # the host reaches it here directly (no --publish needed).
-            "--network", self.network,
-            "--mount", _mount(str(self._repo_root), _APP_DIR, readonly=True),
-            "--workdir", _APP_DIR,
-            # Persist the registry DB on the host (sole-owner: only the
-            # orchestrator opens bot-bottle.db).
-            "--mount", _mount(str(self._host_root), _ROOT_IN_CONTAINER),
-            "--env", f"BOT_BOTTLE_ROOT={_ROOT_IN_CONTAINER}",
-            "--entrypoint", "python3",
-            self.image,
-            "-m", "bot_bottle.orchestrator",
-            "--host", "0.0.0.0", "--port", str(self.port), "--broker", "stub",
-        ]
-        result = container_mod.run_container_argv(argv)
-        if result.returncode != 0:
-            raise OrchestratorStartError(
-                f"orchestrator container failed to start: "
-                f"{(result.stderr or '').strip() or '<no stderr>'}"
-            )
-
-    def gateway(self, orchestrator_url: str) -> AppleGateway:
-        """The shared gateway, pointed at the control plane at
-        `orchestrator_url` (by IP — Apple has no container DNS)."""
-        return AppleGateway(
-            self._gateway_image,
-            network=self.network,
-            egress_network=self.egress_network,
-            orchestrator_url=orchestrator_url,
-        )
-
-    def ensure_running(
-        self, *, startup_timeout: float = DEFAULT_STARTUP_TIMEOUT_SECONDS,
-    ) -> str:
-        """Ensure the control plane + shared gateway are up; return the
-        control-plane URL. Idempotent — a healthy control plane running current
-        code and a running gateway are left untouched."""
-        current_hash = source_hash(self._repo_root)
-        if not self._orchestrator_source_current(current_hash):
-            self._ensure_orchestrator_image()
-            log.info(
-                "starting orchestrator container",
-                context={"name": self._orchestrator_name},
-            )
-            self._run_orchestrator_container(current_hash)
-
-        url = self._wait_healthy(startup_timeout)
-        self._url = url
-
-        # Gateway second: it can only reach the control plane by IP, which does
-        # not exist until the orchestrator container is up (see the docstring).
-        gateway = self.gateway(url)
-        gateway.ensure_built()
-        gateway.ensure_running()
-        return url
-
-    def _wait_healthy(self, startup_timeout: float) -> str:
-        """Poll until the control plane answers /health, resolving its address
-        each time: the container is up before it has an IP, and it has an IP
-        before the server binds."""
-        deadline = time.monotonic() + startup_timeout
-        while True:
-            url = self._resolve_url()
-            if url and self.is_healthy(url):
-                log.info("orchestrator healthy", context={"url": url})
-                return url
-            if time.monotonic() >= deadline:
-                raise OrchestratorStartError(
-                    f"orchestrator did not become healthy within "
-                    f"{startup_timeout:g}s"
-                )
-            time.sleep(_HEALTH_POLL_SECONDS)
-
-    def stop(self) -> None:
-        """Remove the orchestrator + gateway containers (idempotent)."""
-        container_mod.force_remove_container(self._orchestrator_name)
-        self.gateway("").stop()
-        self._url = ""
-
-
-__all__ = [
-    "MacosOrchestratorService",
-    "OrchestratorStartError",
-    "ORCHESTRATOR_NAME",
-]

bot_bottle/backend/macos_container/util.py

@@ -445,85 +445,89 @@ def container_ipv4_on_network(name: str, network: str) -> str:
     return ip
 
 
-def run_container_argv(argv: list[str]) -> subprocess.CompletedProcess[str]:
+def run_container_argv(
+    argv: list[str], *, env: dict[str, str] | None = None,
+) -> subprocess.CompletedProcess[str]:
     """Run a `container` command, returning the result for the caller to
     interpret. Unlike the `die`-on-failure helpers above, this lets callers
     that raise their own typed errors (the gateway / orchestrator lifecycle)
-    keep control of the failure path."""
+    keep control of the failure path.
-    return subprocess.run(argv, capture_output=True, text=True, check=False)
+
+    `env` sets the child process environment — used to hand a secret to a bare
+    `--env NAME` flag (Apple's "just key → inherit from host" form) so the
+    value is inherited from this process, never written onto argv or into
+    `container inspect`'s recorded command line."""
+    return subprocess.run(
+        argv, capture_output=True, text=True, check=False, env=env)
+
+
+def bind_mount_spec(source: str, target: str, *, readonly: bool = False) -> str:
+    """A `container run --mount` bind spec. One definition so the gateway and
+    orchestrator emit an identical string — a divergence here would silently
+    break one backend's mounts while the other kept working."""
+    spec = f"type=bind,source={source},target={target}"
+    if readonly:
+        spec += ",readonly"
+    return spec
 
 
 def _normalize_digest(value: str) -> str:
     return value.split(":", 1)[1] if ":" in value else value
 
 
-def image_digest(ref: str) -> str:
+def _inspect_first(argv: list[str]) -> dict[str, object]:
-    """The digest of image `ref`, or "" if it can't be read. Empty is a
+    """Run an inspect command and return its first JSON object, or {} on any
-    'don't know' signal — callers treat it as "don't churn a working
+    failure (non-zero exit, malformed JSON, unexpected shape). {} is the shared
-    container" rather than as a mismatch."""
+    'don't know' signal all the non-fatal inspect readers below build on — a
-    result = run_container_argv([_CONTAINER, "image", "inspect", ref])
+    caller comparing against it treats it as 'leave the working container
+    alone', never as a mismatch."""
+    result = run_container_argv(argv)
     if result.returncode != 0:
-        return ""
+        return {}
     try:
-        data = json.loads(result.stdout or "{}")
+        data = json.loads(result.stdout or "[]")
     except json.JSONDecodeError:
+        return {}
+    if isinstance(data, list):
+        data = data[0] if data else {}
+    return data if isinstance(data, dict) else {}
+
+
+def _descriptor_digest(node: object) -> str:
+    """The normalized digest under a `{... "descriptor": {"digest": ...}}`
+    node, or "". Both the image and container inspect shapes nest the image's
+    identity this way, so the digest readers stay symmetric — a difference
+    between them is what would spuriously recreate a container."""
+    if not isinstance(node, dict):
         return ""
-    if isinstance(data, list) and data:
+    descriptor = node.get("descriptor")
-        data = data[0]
+    if isinstance(descriptor, dict) and descriptor.get("digest"):
-    if not isinstance(data, dict):
+        return _normalize_digest(str(descriptor["digest"]))
-        return ""
+    return ""
-    config = data.get("configuration")
+
-    if isinstance(config, dict):
+
-        descriptor = config.get("descriptor")
+def image_digest(ref: str) -> str:
-        if isinstance(descriptor, dict) and descriptor.get("digest"):
+    """The digest of image `ref`, or "" if it can't be read. Reads exactly the
-            return _normalize_digest(str(descriptor["digest"]))
+    field `container_image_digest` reads (`configuration.descriptor.digest`) so
-    value = data.get("id")
+    the two are comparable; "" means 'don't know' → callers don't churn."""
-    return _normalize_digest(str(value)) if value else ""
+    data = _inspect_first([_CONTAINER, "image", "inspect", ref])
+    return _descriptor_digest(data.get("configuration"))
 
 
 def container_image_digest(name: str) -> str:
     """The digest of the image container `name` was created from, or "" if it
     can't be read. Compare with `image_digest(ref)` to tell whether a running
     container predates an image rebuild."""
-    result = run_container_argv([_CONTAINER, "inspect", name])
+    config = _inspect_first([_CONTAINER, "inspect", name]).get("configuration")
-    if result.returncode != 0:
+    image = config.get("image") if isinstance(config, dict) else None
-        return ""
+    return _descriptor_digest(image)
-    try:
-        data = json.loads(result.stdout or "[]")
-    except json.JSONDecodeError:
-        return ""
-    if isinstance(data, list) and data:
-        data = data[0]
-    if not isinstance(data, dict):
-        return ""
-    config = data.get("configuration")
-    if not isinstance(config, dict):
-        return ""
-    image = config.get("image")
-    if not isinstance(image, dict):
-        return ""
-    descriptor = image.get("descriptor")
-    if isinstance(descriptor, dict) and descriptor.get("digest"):
-        return _normalize_digest(str(descriptor["digest"]))
-    return ""
 
 
 def container_env(name: str) -> dict[str, str]:
     """The env container `name` was started with, or {} if unreadable. Lets a
     caller tell whether a running container's baked-in configuration still
     matches what it would pass today."""
-    result = run_container_argv([_CONTAINER, "inspect", name])
+    config = _inspect_first([_CONTAINER, "inspect", name]).get("configuration")
-    if result.returncode != 0:
-        return {}
-    try:
-        data = json.loads(result.stdout or "[]")
-    except json.JSONDecodeError:
-        return {}
-    if isinstance(data, list) and data:
-        data = data[0]
-    if not isinstance(data, dict):
-        return {}
-    config = data.get("configuration")
     init = config.get("initProcess") if isinstance(config, dict) else None
     entries = init.get("environment") if isinstance(init, dict) else None
     if not isinstance(entries, list):
@@ -540,18 +544,7 @@ def try_container_ipv4_on_network(name: str, network: str) -> str:
     """`container_ipv4_on_network` without the fatal exit: "" when the address
     isn't readable yet. For pollers — a container is created before it has an
     address, so "not yet" is an expected state there, not an error."""
-    result = run_container_argv([_CONTAINER, "inspect", name])
+    status = _inspect_first([_CONTAINER, "inspect", name]).get("status")
-    if result.returncode != 0:
-        return ""
-    try:
-        data = json.loads(result.stdout or "[]")
-    except json.JSONDecodeError:
-        return ""
-    if isinstance(data, list) and data:
-        data = data[0]
-    if not isinstance(data, dict):
-        return ""
-    status = data.get("status")
     networks = status.get("networks") if isinstance(status, dict) else None
     if not isinstance(networks, list):
         return ""
@@ -564,6 +557,27 @@ def try_container_ipv4_on_network(name: str, network: str) -> str:
     return ""
 
 
+def wait_container_ipv4_on_network(
+    name: str, network: str, *, timeout: float = 15.0, poll: float = 0.25,
+) -> str:
+    """Poll for the container's DHCP-assigned address on `network`, returning
+    it once available or "" on timeout.
+
+    Apple Container has no `--ip`: `container run --detach` can return before
+    vmnet's DHCP has populated `status.networks[].ipv4Address`, so a bare read
+    right after start races the assignment. Callers that need the address (the
+    attribution key, the gateway's proxy target) poll through here instead of
+    the fatal `container_ipv4_on_network`."""
+    deadline = time.monotonic() + timeout
+    while True:
+        ip = try_container_ipv4_on_network(name, network)
+        if ip:
+            return ip
+        if time.monotonic() >= deadline:
+            return ""
+        time.sleep(poll)
+
+
 def image_id(ref: str) -> str:
     """Return the image digest/ID from `container image inspect`.
 

bot_bottle/bottle_state.py

@@ -44,6 +44,7 @@ from .paths import bot_bottle_root
 _STATE_SUBDIR = "state"
 _PER_BOTTLE_DOCKERFILE_NAME = "Dockerfile"
 _COMMITTED_IMAGE_NAME = "committed-image"
+_COMMITTED_ROOTFS_NAME = "committed-rootfs.tar"
 _TRANSCRIPT_SUBDIR = "transcript"
 # Per-daemon scratch subdirs. PRD 0018 chunk 2: bind-mount sources
 # live here so chunk 3's `docker compose up` can find them at stable
@@ -200,6 +201,15 @@ def committed_image_path(identity: str) -> Path:
     return bottle_state_dir(identity) / _COMMITTED_IMAGE_NAME
 
 
+def committed_rootfs_path(identity: str) -> Path:
+    """Where the Firecracker freezer stores a snapshot of the bottle's
+    guest rootfs (a plain tar). This is the resumable/migratable artifact
+    the Firecracker backend boots from — no Docker image involved. The
+    matching `committed-image` state file records that a snapshot exists
+    (and its path); `resume` boots from this tar when both are present."""
+    return bottle_state_dir(identity) / _COMMITTED_ROOTFS_NAME
+
+
 def write_committed_image(identity: str, image_tag: str) -> Path:
     """Persist the committed image tag for `identity`. The next
     `cli.py resume <identity>` will boot from this image instead of
@@ -354,6 +364,7 @@ __all__ = [
     "cleanup_state",
     "clear_preserve_marker",
     "committed_image_path",
+    "committed_rootfs_path",
     "egress_state_dir",
     "git_gate_state_dir",
     "is_preserved",

bot_bottle/docker_cmd.py

@@ -14,13 +14,20 @@ from __future__ import annotations
 import subprocess
 
 
-def run_docker(argv: list[str]) -> subprocess.CompletedProcess[str]:
+def run_docker(
+    argv: list[str], *, env: dict[str, str] | None = None,
+) -> subprocess.CompletedProcess[str]:
     """Run a `docker` command, capturing stdout/stderr as text. Never raises
     on a non-zero exit — callers inspect `returncode` / `stderr` so they can
     stay fail-closed or tolerate idempotent no-ops (e.g. removing an
-    already-absent container)."""
+    already-absent container).
+
+    `env` sets the child process environment — used to hand a secret to a bare
+    `--env NAME` flag (docker inherits its value from this process) so the
+    value never lands on argv or in `docker inspect`'s recorded command line."""
     return subprocess.run(
-        argv, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, check=False,
+        argv, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True,
+        check=False, env=env,
     )
 
 

bot_bottle/egress_addon.py

@@ -78,6 +78,16 @@ ORCHESTRATOR_URL_ENV = "BOT_BOTTLE_ORCHESTRATOR_URL"
 # is still stripped defensively (git-http uses that header on its own port).
 IDENTITY_HEADER = "x-bot-bottle-identity"
 
+# Per-flow key under which `request()` stashes the resolved (Config, supervise
+# slug, env) so the later `response()` and `websocket_message()` hooks scan
+# against the *calling bottle's* policy. In the consolidated (multi-tenant)
+# gateway the static `self.config` is empty — every request's real policy comes
+# from the per-request `/resolve` — so a hook that fell back to `self.config`
+# would find no route and silently skip its DLP scan (fail-open). Resolving once
+# at the request and reusing it also avoids a `/resolve` round-trip per response
+# and per WebSocket frame.
+_FLOW_CTX_KEY = "bot_bottle_egress_ctx"
+
 
 def _token_from_proxy_auth(header: str) -> str:
     """Extract the identity token (the password) from a `Proxy-Authorization:
@@ -223,31 +233,39 @@ class EgressAddon:
             {"Content-Type": "text/plain; charset=utf-8"},
         )
 
-    def _log_request(self, flow: http.HTTPFlow) -> None:
+    def _log_request(
+        self, flow: http.HTTPFlow, env: "typing.Mapping[str, str]",
+    ) -> None:
+        # `env` is the per-flow resolved overlay (process env + this bottle's
+        # /resolve tokens), so the log redaction scrubs the calling bottle's
+        # provisioned secrets — not just the process-level ones in os.environ.
         headers = {
-            k: redact_tokens(v, env=os.environ)
+            k: redact_tokens(v, env=env)
             for k, v in flow.request.headers.items()
             if k.lower() != "authorization"
         }
-        body = redact_tokens(flow.request.get_text(strict=False) or "", env=os.environ)
+        body = redact_tokens(flow.request.get_text(strict=False) or "", env=env)
         sys.stderr.write(
             json.dumps({
                 "event": "egress_request",
-                "host": redact_tokens(flow.request.pretty_host, env=os.environ),
+                "host": redact_tokens(flow.request.pretty_host, env=env),
                 "method": flow.request.method,
-                "path": redact_tokens(flow.request.path, env=os.environ),
+                "path": redact_tokens(flow.request.path, env=env),
                 "headers": headers,
                 "body": body,
             })
             + "\n"
         )
 
-    def _log_response(self, flow: http.HTTPFlow) -> None:
+    def _log_response(
+        self, flow: http.HTTPFlow, env: "typing.Mapping[str, str]",
+    ) -> None:
+        # Per-flow env overlay (see _log_request): redact this bottle's tokens.
         headers = {
-            k: redact_tokens(v, env=os.environ)
+            k: redact_tokens(v, env=env)
             for k, v in flow.response.headers.items()
         }
-        body = redact_tokens(flow.response.get_text(strict=False) or "", env=os.environ)
+        body = redact_tokens(flow.response.get_text(strict=False) or "", env=env)
         sys.stderr.write(
             json.dumps({
                 "event": "egress_response",
@@ -280,6 +298,36 @@ class EgressAddon:
         env = {**os.environ, **tokens} if tokens else os.environ
         return config, slug, env
 
+    def _stash_flow_ctx(
+        self,
+        flow: http.HTTPFlow,
+        config: Config,
+        slug: str,
+        env: "typing.Mapping[str, str]",
+    ) -> None:
+        """Remember the per-flow context `request()` resolved, so the later
+        `response()` / `websocket_message()` hooks reuse it — scanning against
+        the same bottle's policy the request was decided on, with one `/resolve`
+        per flow rather than one per frame."""
+        meta = getattr(flow, "metadata", None)
+        if isinstance(meta, dict):
+            meta[_FLOW_CTX_KEY] = (config, slug, env)
+
+    def _flow_ctx(
+        self, flow: http.HTTPFlow,
+    ) -> "tuple[Config, str, typing.Mapping[str, str]]":
+        """The `(Config, supervise slug, env)` `request()` resolved for this
+        flow, so a later hook scans against the calling bottle's policy — not the
+        empty static config the consolidated gateway carries. Falls back to the
+        single-tenant static values for a flow that never passed through
+        `request()` (or a flow object without metadata)."""
+        meta = getattr(flow, "metadata", None)
+        if isinstance(meta, dict):
+            ctx = meta.get(_FLOW_CTX_KEY)
+            if ctx is not None:
+                return ctx
+        return self.config, self._supervise_slug, os.environ
+
     def _request_token(self, flow: http.HTTPFlow) -> str:
         """The per-bottle identity token for this request, from the proxy
         credentials — the delivery mechanism (`HTTPS_PROXY=http://id:token@gw`)
@@ -319,6 +367,9 @@ class EgressAddon:
             return
 
         config, slug, env = self._resolve_flow(flow)
+        # Stash for the response / websocket hooks so their DLP scans use this
+        # bottle's resolved policy, not the empty static config (see _flow_ctx).
+        self._stash_flow_ctx(flow, config, slug, env)
 
         # DLP outbound scan BEFORE stripping auth — catches tokens the
         # agent tried to smuggle in any header, path, query param, or body.
@@ -377,7 +428,7 @@ class EgressAddon:
             flow.request.headers["authorization"] = decision.inject_authorization
 
         if config.log >= LOG_FULL:
-            self._log_request(flow)
+            self._log_request(flow, env)
 
     def _block_dlp(self, flow: http.HTTPFlow, result: ScanResult) -> None:
         ctx = self._req_ctx(flow)
@@ -586,14 +637,17 @@ class EgressAddon:
             await asyncio.sleep(TOKEN_ALLOW_POLL_INTERVAL_SECONDS)
 
     def response(self, flow: http.HTTPFlow) -> None:
-        """DLP inbound scan on response headers and body."""
+        """DLP inbound scan on response headers and body, against the calling
-        route = match_route(self.config.routes, flow.request.pretty_host)
+        bottle's resolved config (multi-tenant) or the static config
+        (single-tenant) — see `_flow_ctx`."""
+        config, _slug, env = self._flow_ctx(flow)
+        route = match_route(config.routes, flow.request.pretty_host)
         if route is None:
             return
         if flow.response is None:
             return
-        if self.config.log >= LOG_FULL:
+        if config.log >= LOG_FULL:
-            self._log_response(flow)
+            self._log_response(flow, env)
         resp_headers = {k.lower(): v for k, v in flow.response.headers.items()}
         body = flow.response.get_text(strict=False) or ""
         scan_text = build_inbound_scan_text(resp_headers, body)
@@ -610,7 +664,7 @@ class EgressAddon:
             resp_ctx = {**resp_ctx, "context": result.context}
         if result.severity == "block":
             self._block(flow, f"egress DLP: {result.reason}", ctx=resp_ctx)
-        elif result.severity == "warn" and self.config.log >= LOG_BLOCKS:
+        elif result.severity == "warn" and config.log >= LOG_BLOCKS:
             sys.stderr.write(
                 json.dumps({
                     "event": "egress_warn",
@@ -621,7 +675,10 @@ class EgressAddon:
             )
 
     def websocket_message(self, flow: http.HTTPFlow) -> None:
-        """DLP scan on WebSocket frames.
+        """DLP scan on WebSocket frames, against the calling bottle's resolved
+        config (see `_flow_ctx`). `request()` resolves and stashes the per-flow
+        (config, slug, env) at the upgrade, so both the multi-tenant and
+        single-tenant gateways scan here.
 
         Outbound frames (from_client) are scanned for credential leakage;
         inbound frames are scanned for prompt injection.  On a block the
@@ -630,10 +687,8 @@ class EgressAddon:
         """
         if flow.websocket is None:  # type: ignore[union-attr]
             return
-        # WebSocket DLP runs against the static config only (single-tenant); in
+        config, slug, env = self._flow_ctx(flow)
-        # the consolidated gateway self.config has no routes, so this is inert
+        route = match_route(config.routes, flow.request.pretty_host)
-        # until websocket routing is made source-IP-aware (a separate slice).
-        route = match_route(self.config.routes, flow.request.pretty_host)
         if route is None:
             return
         message = flow.websocket.messages[-1]  # type: ignore[union-attr]
@@ -642,8 +697,8 @@ class EgressAddon:
             # A WebSocket data frame is not an HTTP request line, so CRLF is
             # not an injection vector here — scan only for credential leakage.
             result = scan_outbound(
-                route, content, os.environ,
+                route, content, env,
-                safe_tokens=self._safe_tokens_for(self._supervise_slug), crlf_text="",
+                safe_tokens=self._safe_tokens_for(slug), crlf_text="",
             )
             if result is not None and result.severity == "block":
                 sys.stderr.write(f"egress DLP: {result.reason}\n")

bot_bottle/orchestrator/client.py

@@ -17,9 +17,22 @@ import urllib.error
 import urllib.request
 from dataclasses import dataclass
 
+from ..paths import host_control_plane_token
+from .control_plane import CONTROL_AUTH_HEADER
+
 DEFAULT_TIMEOUT_SECONDS = 5.0
 
 
+def _host_auth_token() -> str:
+    """The per-host control-plane secret, or "" if it can't be read. "" means
+    'send no auth header' — correct against an open (unconfigured) control
+    plane, and harmlessly rejected by a secured one."""
+    try:
+        return host_control_plane_token()
+    except OSError:
+        return ""
+
+
 class OrchestratorClientError(RuntimeError):
     """A control-plane call failed (unreachable, or an unexpected status)."""
 
@@ -34,11 +47,24 @@ class RegisteredBottle:
 
 
 class OrchestratorClient:
-    """Trusted host-side client for the orchestrator control plane."""
+    """Trusted host-side client for the orchestrator control plane.
 
-    def __init__(self, base_url: str, *, timeout: float = DEFAULT_TIMEOUT_SECONDS) -> None:
+    Presents the per-host control-plane secret on every call (the header the
+    control plane requires on all routes but `/health`). The secret is read
+    from the host file — this client only ever runs host-side (CLI, launcher,
+    discovery), so it can read what an agent can't. `auth_token` is overridable
+    for tests; the default reads the host file, minting it on first use."""
+
+    def __init__(
+        self,
+        base_url: str,
+        *,
+        timeout: float = DEFAULT_TIMEOUT_SECONDS,
+        auth_token: str | None = None,
+    ) -> None:
         self._base = base_url.rstrip("/")
         self._timeout = timeout
+        self._auth_token = auth_token if auth_token is not None else _host_auth_token()
 
     def _request(
         self, method: str, path: str, body: dict[str, object] | None = None,
@@ -49,6 +75,8 @@ class OrchestratorClient:
         callers can treat 404 as a meaningful "no such bottle"."""
         data = json.dumps(body).encode() if body is not None else None
         headers = {"Content-Type": "application/json"} if data is not None else {}
+        if self._auth_token:
+            headers[CONTROL_AUTH_HEADER] = self._auth_token
         req = urllib.request.Request(
             f"{self._base}{path}", data=data, method=method, headers=headers,
         )
@@ -186,6 +214,13 @@ def discover_orchestrator_url(*, timeout: float = 2.0) -> str:
             f"http://{netpool.orch_slot().guest_ip}:{CONTROL_PLANE_PORT}")
     except Exception:  # noqa: BLE001 — backend optional / not firecracker
         pass
+    try:  # macOS: infra container control plane on its host-only address
+        from ..backend.macos_container.infra import probe_control_plane_url
+        url = probe_control_plane_url()
+        if url:
+            candidates.append(url)
+    except Exception:  # noqa: BLE001 — backend optional / not macOS
+        pass
     for url in candidates:
         if OrchestratorClient(url, timeout=timeout).health():
             return url

bot_bottle/orchestrator/control_plane.py

@@ -34,6 +34,7 @@ returned only once, to the caller that launches the bottle.
 
 from __future__ import annotations
 
+import hmac
 import http.server
 import json
 import os
@@ -42,11 +43,20 @@ import sys
 import typing
 from urllib.parse import urlsplit
 
+from ..paths import CONTROL_PLANE_TOKEN_ENV
 from .service import Orchestrator
 
 # JSON body payload type (parsed request / rendered response).
 Json = dict[str, object]
 
+# The request header carrying the per-host control-plane secret. Every route
+# except `GET /health` requires it (see `dispatch`). The trusted callers hold
+# the secret (the gateway's PolicyResolver, the host CLI's OrchestratorClient);
+# an agent that can merely *reach* the port cannot present it, so it can't
+# enumerate bottles, rewrite policy, read injected upstream tokens, or approve
+# its own supervise proposals.
+CONTROL_AUTH_HEADER = "x-bot-bottle-control-auth"
+
 
 def _parse_json_object(body: bytes) -> Json:
     """Parse a JSON object body. Raises ValueError for non-objects / bad JSON."""
@@ -59,15 +69,29 @@ def _parse_json_object(body: bytes) -> Json:
 
 
 def dispatch(  # pylint: disable=too-many-return-statements,too-many-branches
-    orch: Orchestrator, method: str, path: str, body: bytes
+    orch: Orchestrator, method: str, path: str, body: bytes, *, authorized: bool = True,
 ) -> tuple[int, Json]:
     """Route one control-plane request to a (status, payload) pair. Pure —
-    no I/O beyond the orchestrator — so it is fully testable without a socket."""
+    no I/O beyond the orchestrator — so it is fully testable without a socket.
+
+    `authorized` is whether the request presented the control-plane secret (or
+    no secret is configured — see `ControlPlaneServer`). Every route except
+    `GET /health` requires it: the source-IP + identity-token checks inside
+    `/resolve` and `/attribute` authenticate the *bottle* a request is about,
+    not the *caller*, so without this gate any agent that can reach the port
+    could rewrite another bottle's policy, read the injected upstream tokens,
+    or approve its own supervise proposals. Defaults True so unit tests of the
+    routing logic don't have to thread it through."""
     route = urlsplit(path).path.rstrip("/") or "/"
 
     if method == "GET" and route == "/health":
         return 200, {"status": "ok"}
 
+    if not authorized:
+        # Everything below is a trusted-caller operation. Deny before touching
+        # the registry / broker / supervise store.
+        return 401, {"error": "control-plane authentication required"}
+
     if method == "GET" and route == "/gateway":
         return 200, orch.gateway_status()
 
@@ -209,8 +233,10 @@ class Handler(http.server.BaseHTTPRequestHandler):
         assert isinstance(server, ControlPlaneServer)
         length = int(self.headers.get("Content-Length") or 0)
         body = self.rfile.read(length) if length > 0 else b""
+        authorized = server.is_authorized(self.headers.get(CONTROL_AUTH_HEADER, ""))
         try:
-            status, payload = dispatch(server.orchestrator, method, self.path, body)
+            status, payload = dispatch(
+                server.orchestrator, method, self.path, body, authorized=authorized)
         except Exception as e:  # noqa: BLE001 — the control plane must stay up
             sys.stderr.write(f"orchestrator: {method} {self.path} failed: {e!r}\n")
             sys.stderr.flush()
@@ -236,15 +262,40 @@ class Handler(http.server.BaseHTTPRequestHandler):
 
 
 class ControlPlaneServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
-    """Threading HTTP server that carries the orchestrator for its handlers."""
+    """Threading HTTP server that carries the orchestrator for its handlers.
+
+    Holds the per-host control-plane secret (from `$BOT_BOTTLE_CONTROL_PLANE_TOKEN`,
+    injected by the launcher into this container only). When a secret is set,
+    every route but `/health` requires it; when it is unset the server runs
+    **open** and says so loudly at startup — a fail-visible fallback for tests
+    and any backend that hasn't wired the secret yet (e.g. Firecracker, whose
+    nft boundary already blocks agents from the control-plane port)."""
 
     daemon_threads = True
     allow_reuse_address = True
 
     def __init__(self, address: tuple[str, int], orchestrator: Orchestrator) -> None:
         self.orchestrator = orchestrator
+        self._auth_token = os.environ.get(CONTROL_PLANE_TOKEN_ENV, "").strip()
+        if not self._auth_token:
+            sys.stderr.write(
+                "orchestrator: WARNING — no control-plane secret "
+                f"(${CONTROL_PLANE_TOKEN_ENV}); running WITHOUT caller "
+                "authentication. Any client that can reach this port can drive "
+                "it. Backends that put the control plane on an agent-reachable "
+                "network MUST set this.\n"
+            )
+            sys.stderr.flush()
         super().__init__(address, Handler)
 
+    def is_authorized(self, presented: str) -> bool:
+        """True iff the request may proceed past `/health`: either no secret is
+        configured (open mode) or the presented header matches it. Constant-time
+        compare so a wrong token leaks nothing timing-wise."""
+        if not self._auth_token:
+            return True
+        return hmac.compare_digest(presented, self._auth_token)
+
 
 def make_server(
     orchestrator: Orchestrator, host: str = "127.0.0.1", port: int = 0
@@ -254,4 +305,7 @@ def make_server(
     return ControlPlaneServer((host, port), orchestrator)
 
 
-__all__ = ["dispatch", "Handler", "ControlPlaneServer", "make_server", "Json"]
+__all__ = [
+    "dispatch", "Handler", "ControlPlaneServer", "make_server", "Json",
+    "CONTROL_AUTH_HEADER",
+]

bot_bottle/orchestrator/gateway.py

@@ -23,7 +23,11 @@ import time
 from pathlib import Path
 
 from ..docker_cmd import run_docker
-from ..paths import host_db_path
+from ..paths import (
+    CONTROL_PLANE_TOKEN_ENV,
+    host_control_plane_token,
+    host_db_path,
+)
 from ..supervise import DB_PATH_IN_CONTAINER
 
 # The host DB dir is bind-mounted here so the gateway's supervise daemon
@@ -215,12 +219,19 @@ class DockerGateway(Gateway):
         ]
         for port in self._host_port_bindings:
             argv += ["--publish", f"0.0.0.0:{port}:{port}"]
+        run_env = dict(os.environ)
         if self._orchestrator_url:
             # Makes the gateway's egress / git / supervise daemons multi-tenant:
             # each request resolves source-IP -> policy against the control plane.
             argv += ["--env", f"BOT_BOTTLE_ORCHESTRATOR_URL={self._orchestrator_url}"]
+            # ...and presents the control-plane secret on those /resolve calls
+            # (the control plane requires it). Bare `--env NAME` keeps the value
+            # off argv / `docker inspect`; only the gateway (not the agent) is
+            # given it. Only needed in multi-tenant mode, where /resolve is used.
+            argv += ["--env", CONTROL_PLANE_TOKEN_ENV]
+            run_env[CONTROL_PLANE_TOKEN_ENV] = host_control_plane_token()
         argv.append(self.image_ref)
-        proc = run_docker(argv)
+        proc = run_docker(argv, env=run_env)
         if proc.returncode != 0:
             raise GatewayError(f"gateway failed to start: {proc.stderr.strip()}")
 

bot_bottle/orchestrator/lifecycle.py

@@ -25,8 +25,8 @@ from pathlib import Path
 
 from .. import log
 from ..docker_cmd import run_docker
-from ..paths import bot_bottle_root
+from ..paths import CONTROL_PLANE_TOKEN_ENV, bot_bottle_root, host_control_plane_token
-from .gateway import GATEWAY_IMAGE, GATEWAY_NETWORK, DockerGateway, GatewayError
+from .gateway import GATEWAY_IMAGE, GATEWAY_NAME, GATEWAY_NETWORK, DockerGateway, GatewayError
 
 DEFAULT_PORT = 8099
 ORCHESTRATOR_NAME = "bot-bottle-orchestrator"
@@ -83,8 +83,11 @@ class OrchestratorService:
     `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`). Subclass and override `_gateway()`
+    backend's `bot-bottle-orchestrator`); `gateway_name` gives the paired
-    to supply a backend-specific gateway variant."""
+    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)."""
 
     def __init__(
         self,
@@ -93,6 +96,7 @@ class OrchestratorService:
         network: str = GATEWAY_NETWORK,
         image: str = ORCHESTRATOR_IMAGE,
         gateway_image: str = GATEWAY_IMAGE,
+        gateway_name: str = GATEWAY_NAME,
         repo_root: Path = _REPO_ROOT,
         host_root: Path | None = None,
         orchestrator_name: str = ORCHESTRATOR_NAME,
@@ -106,6 +110,7 @@ class OrchestratorService:
         # 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
@@ -147,7 +152,11 @@ class OrchestratorService:
             "--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.
+            # 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,
@@ -155,11 +164,15 @@ class OrchestratorService:
             # 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()}"
@@ -167,7 +180,10 @@ class OrchestratorService:
 
     def _gateway(self) -> DockerGateway:
         return DockerGateway(
-            self._gateway_image, network=self.network, orchestrator_url=self.internal_url
+            self._gateway_image,
+            name=self._gateway_name,
+            network=self.network,
+            orchestrator_url=self.internal_url,
         )
 
     def _ensure_orchestrator_image(self) -> None:

bot_bottle/paths.py

@@ -16,6 +16,8 @@ layer (and to COPY flat into the gateway).
 from __future__ import annotations
 
 import os
+import secrets
+import stat
 from pathlib import Path
 
 # The single shared host state DB. All bot-bottle SQLite stores (supervise
@@ -23,6 +25,14 @@ from pathlib import Path
 # TableMigrations schema_key namespaces each store's tables.
 HOST_DB_FILENAME = "bot-bottle.db"
 
+# The per-host control-plane secret file, and the env var the launchers inject
+# its value into. The control plane requires this secret on every mutating /
+# reading route (see orchestrator/control_plane.py); it is held only by the
+# trusted callers (control plane, gateway, host CLI) and never handed to an
+# agent, so an agent that can reach the control-plane port still can't drive it.
+CONTROL_PLANE_TOKEN_FILENAME = "control-plane-token"
+CONTROL_PLANE_TOKEN_ENV = "BOT_BOTTLE_CONTROL_PLANE_TOKEN"
+
 
 def bot_bottle_root() -> Path:
     """The app data root — `$BOT_BOTTLE_ROOT` if set, else `~/.bot-bottle`."""
@@ -40,4 +50,52 @@ def host_db_path() -> Path:
     return bot_bottle_root() / "db" / HOST_DB_FILENAME
 
 
-__all__ = ["HOST_DB_FILENAME", "bot_bottle_root", "host_db_path"]
+def host_db_dir() -> Path:
+    """The directory holding the shared host state DB, created if missing.
+    Backends bind-mount this into their gateway so the supervise daemon writes
+    to the one DB the orchestrator (and the operator over HTTP) reads."""
+    db_dir = host_db_path().parent
+    db_dir.mkdir(parents=True, exist_ok=True)
+    return db_dir
+
+
+def host_control_plane_token() -> str:
+    """The per-host control-plane secret, minted (256-bit, url-safe) and
+    persisted 0600 on first use, then reused.
+
+    This is the shared secret the launchers inject into the control-plane and
+    gateway containers and that the host CLI presents on every call. It is a
+    *host* artifact — the file lives under the root the agent never mounts, and
+    the env var is set only on the trusted containers — so reading it here is
+    safe on the host launch path but the value never reaches a bottle."""
+    path = bot_bottle_root() / CONTROL_PLANE_TOKEN_FILENAME
+    try:
+        existing = path.read_text().strip()
+        if existing:
+            return existing
+    except OSError:
+        pass
+    path.parent.mkdir(parents=True, exist_ok=True)
+    token = secrets.token_urlsafe(32)
+    # Create 0600 up front (O_EXCL loses a concurrent race harmlessly — we
+    # re-read the winner's token below) so the secret is never briefly world-
+    # readable between write and chmod.
+    try:
+        fd = os.open(path, os.O_WRONLY | os.O_CREAT | os.O_EXCL, 0o600)
+    except FileExistsError:
+        return path.read_text().strip()
+    with os.fdopen(fd, "w") as f:
+        f.write(token)
+    os.chmod(path, stat.S_IRUSR | stat.S_IWUSR)
+    return token
+
+
+__all__ = [
+    "HOST_DB_FILENAME",
+    "CONTROL_PLANE_TOKEN_FILENAME",
+    "CONTROL_PLANE_TOKEN_ENV",
+    "bot_bottle_root",
+    "host_db_path",
+    "host_db_dir",
+    "host_control_plane_token",
+]

bot_bottle/policy_resolver.py

@@ -29,11 +29,29 @@ the gateway.
 from __future__ import annotations
 
 import json
+import os
 import urllib.error
 import urllib.request
 
 DEFAULT_TIMEOUT_SECONDS = 2.0
 
+# The control-plane secret this gateway presents on every /resolve call, read
+# from the env the launcher injects into the gateway container. The control
+# plane requires it (orchestrator/control_plane.py). Constant + env-var name are
+# duplicated here rather than imported because this module is COPYed flat into
+# the gateway image, free of bot-bottle imports — same rationale as
+# IDENTITY_HEADER in egress_addon / git_http_backend.
+CONTROL_AUTH_HEADER = "x-bot-bottle-control-auth"
+CONTROL_PLANE_TOKEN_ENV = "BOT_BOTTLE_CONTROL_PLANE_TOKEN"
+
+
+def _control_auth_headers() -> dict[str, str]:
+    """The auth header to send, or {} when no secret is configured (an open
+    control plane, e.g. Firecracker behind its nft boundary — sending nothing
+    is correct there and harmlessly ignored)."""
+    token = os.environ.get(CONTROL_PLANE_TOKEN_ENV, "").strip()
+    return {CONTROL_AUTH_HEADER: token} if token else {}
+
 
 class PolicyResolveError(RuntimeError):
     """The orchestrator was unreachable or returned an unexpected status —
@@ -57,7 +75,7 @@ class PolicyResolver:
         ).encode()
         req = urllib.request.Request(
             f"{self._base}/resolve", data=body, method="POST",
-            headers={"Content-Type": "application/json"},
+            headers={"Content-Type": "application/json", **_control_auth_headers()},
         )
         try:
             with urllib.request.urlopen(req, timeout=self._timeout) as resp:

tests/integration/test_orchestrator_docker_control_plane_auth.py

@@ -0,0 +1,155 @@
+"""Integration: the Docker orchestrator's control plane enforces the
+per-host auth secret against a real container (issue #400).
+
+Unit tests exercise `dispatch()` in-process, socket-free. This starts the
+actual orchestrator + gateway as Docker containers and drives the real HTTP
+server over its published loopback port, the same path an agent sharing the
+gateway network — or the trusted host CLI — would use.
+
+Gated on a reachable Docker daemon. Uses unique container/network names,
+test-only image tags (never the production `:latest` ones, so a rebuild
+here can't make `_running_image_is_current()` see a real host's running
+gateway as stale and force-recreate it), and a throwaway `BOT_BOTTLE_ROOT`
+so a run never touches or collides with a real per-host orchestrator or
+gateway. The whole stack is brought up once for the class (`setUpClass`),
+not per test method — every test here is a read-only check against the
+same running control plane.
+"""
+
+from __future__ import annotations
+
+import os
+import secrets
+import subprocess
+import tempfile
+import unittest
+from pathlib import Path
+
+from bot_bottle.orchestrator.client import OrchestratorClient
+from bot_bottle.orchestrator.lifecycle import OrchestratorService
+from bot_bottle.paths import host_control_plane_token
+from tests._docker import skip_unless_docker
+
+# Fixed (not per-run-suffixed) so repeated runs reuse the same layer-cached
+# 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"
+
+
+@skip_unless_docker()
+@unittest.skipIf(
+    os.environ.get("GITEA_ACTIONS") == "true",
+    "skipped under act_runner: the orchestrator container bind-mounts the repo "
+    "path into a container on the socket-shared host daemon, which can't see the "
+    "runner's /workspace — same host-bind-mount constraint as the other "
+    "bottle-bringup integration tests",
+)
+class TestDockerControlPlaneAuthIntegration(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls) -> None:
+        suffix = secrets.token_hex(4)
+        cls._tmp = tempfile.TemporaryDirectory()  # pylint: disable=consider-using-with
+        cls.addClassCleanup(cls._tmp.cleanup)
+
+        # host_control_plane_token() — both the token read below and the one
+        # OrchestratorService injects into the container's env — resolves its
+        # path via the *ambient* BOT_BOTTLE_ROOT env var, not the host_root
+        # kwarg passed to the constructor (that kwarg only controls the DB
+        # bind-mount destination). Without pointing the env var at the same
+        # throwaway dir, this "isolated" test would read/write the developer's
+        # real ~/.bot-bottle/control-plane-token.
+        previous_root = os.environ.get("BOT_BOTTLE_ROOT")
+
+        def _restore_root() -> None:
+            if previous_root is None:
+                os.environ.pop("BOT_BOTTLE_ROOT", None)
+            else:
+                os.environ["BOT_BOTTLE_ROOT"] = previous_root
+
+        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}"
+        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.svc = OrchestratorService(
+            orchestrator_name=orchestrator_name,
+            gateway_name=gateway_name,
+            network=network,
+            image=_TEST_ORCHESTRATOR_IMAGE,
+            gateway_image=_TEST_GATEWAY_IMAGE,
+            port=20000 + secrets.randbelow(10000),
+            host_root=host_root,
+        )
+        cls.svc.ensure_running()
+        cls.token = host_control_plane_token()
+
+    @staticmethod
+    def _teardown_docker(
+        orchestrator_name: str, gateway_name: str, network: str, host_root: Path
+    ) -> None:
+        subprocess.run(
+            ["docker", "rm", "--force", orchestrator_name, gateway_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
+        # 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",
+             f"{os.getuid()}:{os.getgid()}", "/r"],
+            stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
+        )
+
+    def _request(
+        self, method: str, path: str, *, token: str = ""
+    ) -> tuple[int, dict[str, object]]:
+        # Reuses the real host-side client's request/response handling rather
+        # than hand-rolling urllib here; _request (not one of the named
+        # wrapper methods) is what exposes raw status codes for arbitrary
+        # paths/tokens, which is exactly what these auth-boundary tests need.
+        client = OrchestratorClient(self.svc.url, auth_token=token)
+        return client._request(method, path)  # pylint: disable=protected-access
+
+    def test_health_is_open_without_a_token(self) -> None:
+        status, payload = self._request("GET", "/health")
+        self.assertEqual(200, status)
+        self.assertEqual("ok", payload["status"])
+
+    def test_bottles_rejects_a_caller_with_no_token(self) -> None:
+        """The enumeration attack from issue #400: an agent sharing the
+        gateway network could list every bottle + its policy with no
+        credential at all."""
+        status, _ = self._request("GET", "/bottles")
+        self.assertEqual(401, status)
+
+    def test_bottles_rejects_a_wrong_token(self) -> None:
+        status, _ = self._request("GET", "/bottles", token="not-the-real-secret")
+        self.assertEqual(401, status)
+
+    def test_bottles_accepts_the_real_token(self) -> None:
+        status, payload = self._request("GET", "/bottles", token=self.token)
+        self.assertEqual(200, status)
+        self.assertEqual([], payload["bottles"])
+
+    def test_resolve_rejects_a_caller_with_no_token(self) -> None:
+        """The credential-lift attack from issue #400: an agent could POST
+        /resolve directly and read back the upstream tokens it's never meant
+        to see."""
+        status, _ = self._request("POST", "/resolve")
+        self.assertEqual(401, status)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/test_backend_freezer.py

@@ -205,25 +205,29 @@ class TestFirecrackerFreezer(_FakeHomeMixin, unittest.TestCase):
         )
 
     def test_snapshots_running_vm_without_stopping(self):
-        """Commit should tar the running guest rootfs over SSH, not stop it."""
+        """Commit should tar the running guest rootfs over SSH into the
+        committed-rootfs artifact (no Docker), not stop the VM."""
         slug = "dev-abc12"
         self._write_meta(slug)
         self._stage_run_dir(slug)
         freezer = FirecrackerFreezer()
         agent = _make_agent(slug, "firecracker")
 
-        with patch("bot_bottle.backend.firecracker.freezer._commit_via_ssh") as mock_commit, \
+        commit_fn = "bot_bottle.backend.firecracker.freezer._commit_rootfs_via_ssh"
+        with patch(commit_fn) as mock_commit, \
              patch("bot_bottle.backend.freeze.info"), \
              patch("bot_bottle.backend.firecracker.freezer.info"):
             freezer.commit(agent)
 
-        image_tag = f"bot-bottle-committed-{slug}:latest"
+        tar_path = bottle_state.committed_rootfs_path(slug)
         self.assertEqual(1, mock_commit.call_count)
-        # (private_key, guest_ip, image_tag) — guest_ip parsed from config.
+        # (private_key, guest_ip, tar_path) — guest_ip parsed from config.
         args = mock_commit.call_args.args
         self.assertEqual("100.64.0.1", args[1])
-        self.assertEqual(image_tag, args[2])
+        self.assertEqual(tar_path, args[2])
-        self.assertEqual(image_tag, bottle_state.read_committed_image(slug))
+        # The committed-image state records the artifact path; resume boots
+        # from the tar rather than a Docker image.
+        self.assertEqual(str(tar_path), bottle_state.read_committed_image(slug))
         self.assertTrue(bottle_state.is_preserved(slug))
 
 

tests/unit/test_backend_selection.py

@@ -247,7 +247,7 @@ class TestHasBackend(unittest.TestCase):
 class TestEnsureOrchestrator(unittest.TestCase):
     """The backend-agnostic orchestrator bring-up entry point. Docker starts
     the orchestrator + gateway containers; firecracker boots the infra VM;
-    backends without one (macos-container) die with a pointer."""
+    macos-container starts the infra container."""
 
     def test_docker_delegates_to_orchestrator_service(self):
         b = get_bottle_backend("docker")
@@ -272,11 +272,16 @@ class TestEnsureOrchestrator(unittest.TestCase):
             url = b.ensure_orchestrator()
         self.assertEqual(url, "http://10.243.255.1:8099")
 
-    def test_macos_default_dies(self):
+    def test_macos_delegates_to_infra_container(self):
-        from bot_bottle.log import Die
         b = get_bottle_backend("macos-container")
-        with self.assertRaises(Die):
+        with patch(
-            b.ensure_orchestrator()
+            "bot_bottle.backend.macos_container.infra.MacosInfraService"
+        ) as service_cls:
+            service_cls.return_value.ensure_running.return_value.control_plane_url = (
+                "http://192.168.128.2:8099"
+            )
+            url = b.ensure_orchestrator()
+        self.assertEqual(url, "http://192.168.128.2:8099")
 
 
 if __name__ == "__main__":

tests/unit/test_egress_addon_log_redaction.py

@@ -8,6 +8,7 @@ real mitmproxy package."""
 from __future__ import annotations
 
 import json
+import os
 import sys
 import types
 import unittest
@@ -107,14 +108,14 @@ class _Flow:
 def _log_request(addon: EgressAddon, flow: _Flow) -> dict[str, Any]:
     buf = StringIO()
     with patch("sys.stderr", buf):
-        addon._log_request(flow)  # type: ignore[arg-type]
+        addon._log_request(flow, os.environ)  # type: ignore[arg-type]
     return json.loads(buf.getvalue())
 
 
 def _log_response(addon: EgressAddon, flow: _Flow) -> dict[str, Any]:
     buf = StringIO()
     with patch("sys.stderr", buf):
-        addon._log_response(flow)  # type: ignore[arg-type]
+        addon._log_response(flow, os.environ)  # type: ignore[arg-type]
     return json.loads(buf.getvalue())
 
 

tests/unit/test_egress_addon_request_flow.py

@@ -141,6 +141,10 @@ class _Flow:
         self.response = response
         self.websocket: Any = None
         self.killed = False
+        # mitmproxy flows carry a per-flow `metadata` dict for addon use; the
+        # egress addon stashes the resolved (config, slug, env) there in
+        # request() so the response/websocket hooks reuse it.
+        self.metadata: dict[str, Any] = {}
 
     def kill(self) -> None:
         self.killed = True
@@ -859,5 +863,91 @@ class TestSuperviseMultiTenant(unittest.TestCase):
         self.assertNotIn(_OPENAI_KEY, addon._safe_tokens_for(""))
 
 
+class TestMultiTenantInboundDlp(unittest.TestCase):
+    """Consolidated gateway: the response + websocket DLP hooks must scan
+    against the *calling bottle's* config, resolved by source IP in request()
+    and reused here. The static `self.config` is empty in this mode, so before
+    the flow-context stash these hooks silently skipped every scan (fail-open).
+    """
+
+    def _consolidated_addon(self) -> EgressAddon:
+        addon = _addon(Config(routes=()))  # empty static config, as in prod
+        addon._resolver = cast(Any, _CtxResolver({"10.0.0.1": "bottle-a"}))
+        return addon
+
+    def test_response_injection_blocked_after_request_resolves(self) -> None:
+        addon = self._consolidated_addon()
+        flow = _with_client_ip(_Flow(_Request(host="api.example.com")), "10.0.0.1")
+        _run_request(addon, flow)  # resolves + stashes bottle-a's allowlist
+        self.assertIsNone(flow.response)  # request forwarded
+        flow.response = _Response(200, content=_INJECTION_BLOCK)
+        addon.response(flow)  # type: ignore[arg-type]
+        assert flow.response is not None
+        # Empty static config would have found no route and left this 200.
+        self.assertEqual(403, flow.response.status_code)
+
+    def test_websocket_outbound_token_killed_after_request_resolves(self) -> None:
+        addon = self._consolidated_addon()
+        flow = _with_client_ip(_Flow(_Request(host="api.example.com")), "10.0.0.1")
+        _run_request(addon, flow)  # the ws upgrade resolves + stashes the config
+        flow.websocket = _WebSocketData(
+            [_Message(f"k={_OPENAI_KEY}".encode(), from_client=True)]
+        )
+        addon.websocket_message(flow)  # type: ignore[arg-type]
+        self.assertTrue(flow.killed)  # scanned against bottle-a's route now
+
+    def test_websocket_inbound_injection_killed_after_request_resolves(self) -> None:
+        addon = self._consolidated_addon()
+        flow = _with_client_ip(_Flow(_Request(host="api.example.com")), "10.0.0.1")
+        _run_request(addon, flow)
+        flow.websocket = _WebSocketData(
+            [_Message(_INJECTION_BLOCK.encode(), from_client=False)]
+        )
+        addon.websocket_message(flow)  # type: ignore[arg-type]
+        self.assertTrue(flow.killed)
+
+    def test_response_log_redacts_per_bottle_resolve_token(self) -> None:
+        # LOG_FULL response logging now runs in multi-tenant mode, so it must
+        # scrub the calling bottle's /resolve token — which lives only in the
+        # resolved env overlay, never in the gateway's os.environ. A
+        # non-token-shaped secret is caught only via that env, so os.environ
+        # redaction (the pre-fix behaviour) would leak it into the log.
+        secret = "bottle-a-provisioned-secret-value"
+        policy = "log: 2\nroutes:\n  - host: api.example.com\n"
+
+        class _TokenResolver:
+            def resolve_policy_and_bottle_id(
+                self, ip: str, identity_token: str = "",
+            ) -> tuple[str | None, str | None, dict[str, str]]:
+                del ip, identity_token
+                return policy, "bottle-a", {"EGRESS_TOKEN_0": secret}
+
+        addon = _addon(Config(routes=()))
+        addon._resolver = cast(Any, _TokenResolver())
+        flow = _with_client_ip(_Flow(_Request(host="api.example.com")), "10.0.0.1")
+        _run_request(addon, flow)
+        flow.response = _Response(200, content=f"echo {secret} back")
+        buf = StringIO()
+        with patch("sys.stderr", buf):
+            addon.response(flow)  # type: ignore[arg-type]
+        logged = buf.getvalue()
+        self.assertIn("egress_response", logged)  # LOG_FULL logged the response
+        self.assertNotIn(secret, logged)  # redacted via the resolved env overlay
+
+    def test_unattributed_flow_has_no_route_so_frame_passes(self) -> None:
+        # An unattributed source resolves to a deny-all (empty) config, so the
+        # request is blocked at the upgrade and any later frame has no route to
+        # scan against — it passes rather than being attributed to a bottle.
+        addon = self._consolidated_addon()
+        flow = _with_client_ip(_Flow(_Request(host="api.example.com")), "10.9.9.9")
+        _run_request(addon, flow)
+        self.assertIsNotNone(flow.response)  # blocked at the upgrade
+        flow.websocket = _WebSocketData(
+            [_Message(f"k={_OPENAI_KEY}".encode(), from_client=True)]
+        )
+        addon.websocket_message(flow)  # type: ignore[arg-type]
+        self.assertFalse(flow.killed)
+
+
 if __name__ == "__main__":
     unittest.main()

tests/unit/test_firecracker_helpers.py

@@ -6,10 +6,13 @@ branches. Mock subprocess/os so nothing needs KVM or a live VM.
 from __future__ import annotations
 
 import json
+import os
+import stat
 import subprocess
 import tempfile
 import unittest
 from pathlib import Path
+from typing import Any
 from unittest.mock import patch
 
 from bot_bottle.backend.firecracker import firecracker_vm, freezer, netpool, util
@@ -128,5 +131,172 @@ class TestRequireFirecracker(unittest.TestCase):
                 util.require_firecracker()
 
 
+class TestBuildCommittedRootfsDir(unittest.TestCase):
+    """Resume prepares the base rootfs dir from the freezer's snapshot tar
+    with no Docker: extract, recreate the excluded mount points, inject the
+    guest boot bits."""
+
+    def _make_tar(self, tmp: Path) -> Path:
+        import tarfile
+
+        src = tmp / "src"
+        (src / "home" / "node").mkdir(parents=True)
+        (src / "home" / "node" / "hello").write_text("hi")
+        tar_path = tmp / "rootfs.tar"
+        with tarfile.open(tar_path, "w") as tar:
+            tar.add(src, arcname=".")
+        return tar_path
+
+    def test_extracts_recreates_mountpoints_and_injects_boot(self):
+        with tempfile.TemporaryDirectory(prefix="fc-committed.") as d:
+            tmp = Path(d)
+            tar_path = self._make_tar(tmp)
+            # Stand in for the static dropbear that inject_guest_boot copies.
+            dropbear = tmp / "dropbear"
+            dropbear.write_text("#!/bin/true\n")
+            cache = tmp / "cache"
+            cache.mkdir()
+
+            with patch.object(util, "cache_dir", return_value=cache), \
+                 patch.object(util, "dropbear_path", return_value=dropbear), \
+                 patch.object(util, "info"):
+                base = util.build_committed_rootfs_dir(tar_path)
+
+            self.assertEqual("hi", (base / "home" / "node" / "hello").read_text())
+            for mount_point in ("proc", "sys", "dev", "run"):
+                self.assertTrue((base / mount_point).is_dir(),
+                                f"missing recreated mount point /{mount_point}")
+            self.assertTrue((base / "bb-dropbear").is_file())
+            self.assertTrue((base / "bb-init").is_file())
+            self.assertTrue((base / ".bb-ready").is_file())
+
+    def test_caches_on_repeat_and_reextracts_after_refreeze(self):
+        with tempfile.TemporaryDirectory(prefix="fc-committed.") as d:
+            tmp = Path(d)
+            tar_path = self._make_tar(tmp)
+            dropbear = tmp / "dropbear"
+            dropbear.write_text("#!/bin/true\n")
+            cache = tmp / "cache"
+            cache.mkdir()
+
+            ctx = [
+                patch.object(util, "cache_dir", return_value=cache),
+                patch.object(util, "dropbear_path", return_value=dropbear),
+                patch.object(util, "info"),
+            ]
+            for c in ctx:
+                c.start()
+            self.addCleanup(lambda: [c.stop() for c in ctx])
+
+            real_run = subprocess.run
+            calls = {"n": 0}
+
+            def counting_run(argv: list[str], *a: Any, **k: Any) -> Any:
+                if argv and argv[0] == "tar":
+                    calls["n"] += 1
+                return real_run(argv, *a, **k)
+
+            with patch.object(util.subprocess, "run", side_effect=counting_run):
+                first = util.build_committed_rootfs_dir(tar_path)
+                second = util.build_committed_rootfs_dir(tar_path)
+                self.assertEqual(first, second)
+                self.assertEqual(1, calls["n"])  # cached — no re-extract
+
+                # A re-freeze rewrites the tar; a new size/mtime -> new cache
+                # key -> re-extract. Force a distinct mtime so the test isn't
+                # at the mercy of filesystem timestamp granularity.
+                import tarfile
+                extra = tmp / "extra"
+                extra.mkdir()
+                (extra / "note").write_text("v2")
+                with tarfile.open(tar_path, "w") as tar:
+                    tar.add(extra, arcname=".")
+                st = tar_path.stat()
+                os.utime(tar_path, ns=(st.st_atime_ns, st.st_mtime_ns + 1_000_000_000))
+
+                third = util.build_committed_rootfs_dir(tar_path)
+                self.assertNotEqual(first, third)
+                self.assertEqual(2, calls["n"])
+
+
+class TestInjectGuestBootSymlinkSafe(unittest.TestCase):
+    """A committed snapshot is guest-controlled: inject_guest_boot must not
+    follow a planted symlink and overwrite a host file during resume."""
+
+    def test_planted_symlink_does_not_escape_staging_tree(self):
+        with tempfile.TemporaryDirectory(prefix="fc-inject.") as d:
+            tmp = Path(d)
+            dropbear = tmp / "dropbear"
+            dropbear.write_bytes(b"DROPBEAR")
+            # A host file the malicious snapshot tries to clobber.
+            victim = tmp / "victim"
+            victim.write_text("original")
+
+            rootfs = tmp / "rootfs"
+            rootfs.mkdir()
+            # The snapshot planted bb-init/bb-dropbear as symlinks to it.
+            (rootfs / "bb-init").symlink_to(victim)
+            (rootfs / "bb-dropbear").symlink_to(victim)
+
+            with patch.object(util, "dropbear_path", return_value=dropbear):
+                util.inject_guest_boot(rootfs, init_script="#!/bin/sh\nreal\n")
+
+            # Host file untouched; the staged paths are fresh regular files.
+            self.assertEqual("original", victim.read_text())
+            self.assertFalse((rootfs / "bb-init").is_symlink())
+            self.assertFalse((rootfs / "bb-dropbear").is_symlink())
+            self.assertEqual("#!/bin/sh\nreal\n", (rootfs / "bb-init").read_text())
+            self.assertEqual(b"DROPBEAR", (rootfs / "bb-dropbear").read_bytes())
+
+
+class TestCommitRootfsPermissions(unittest.TestCase):
+    """The snapshot tar can hold the bottle's private workspace, so the
+    freezer must write it owner-only (0600)."""
+
+    def _commit(self, tar_path: Path) -> int:
+        """Run _commit_rootfs_via_ssh with a stubbed ssh|tar pipe; return the
+        mode of the open partial observed mid-stream (from subprocess.run)."""
+        key = tar_path.parent.parent / "key"
+        key.write_text("K")
+        seen: dict[str, int] = {}
+
+        def fake_run(argv: list[str], *a: Any, **k: Any) -> Any:
+            out = k["stdout"]
+            seen["mode"] = stat.S_IMODE(os.fstat(out.fileno()).st_mode)
+            out.write(b"TARDATA")
+            return subprocess.CompletedProcess(argv, 0, b"", b"")
+
+        with patch.object(freezer.util, "ssh_base_argv", return_value=["ssh"]), \
+             patch.object(freezer.subprocess, "run", side_effect=fake_run):
+            freezer._commit_rootfs_via_ssh(key, "10.0.0.1", tar_path)
+        return seen["mode"]
+
+    def test_snapshot_created_owner_only(self):
+        with tempfile.TemporaryDirectory(prefix="fc-freeze.") as d:
+            tar_path = Path(d) / "state" / "committed-rootfs.tar"
+            tar_path.parent.mkdir()
+            stream_mode = self._commit(tar_path)
+
+            self.assertEqual(0o600, stream_mode)  # private during the stream
+            self.assertEqual(b"TARDATA", tar_path.read_bytes())
+            self.assertEqual(0o600, stat.S_IMODE(tar_path.stat().st_mode))
+
+    def test_leftover_world_readable_partial_is_recreated_private(self):
+        """A partial left 0644 by an interrupted prior run must not keep the
+        new snapshot world-readable while it streams."""
+        with tempfile.TemporaryDirectory(prefix="fc-freeze.") as d:
+            tar_path = Path(d) / "state" / "committed-rootfs.tar"
+            tar_path.parent.mkdir()
+            partial = tar_path.with_name(tar_path.name + ".partial")
+            partial.write_bytes(b"stale")
+            os.chmod(partial, 0o644)
+
+            stream_mode = self._commit(tar_path)
+
+            self.assertEqual(0o600, stream_mode)
+            self.assertEqual(b"TARDATA", tar_path.read_bytes())
+            self.assertEqual(0o600, stat.S_IMODE(tar_path.stat().st_mode))
+
+
 if __name__ == "__main__":
     unittest.main()

tests/unit/test_macos_consolidated_launch.py

@@ -50,30 +50,35 @@ def _client() -> Mock:
 
 class TestEnsureGateway(unittest.TestCase):
     def _run(self, service: MagicMock) -> GatewayEndpoint:
-        with patch(f"{_MOD}.MacosOrchestratorService", return_value=service):
+        with patch(f"{_MOD}.MacosInfraService", return_value=service):
             return ensure_gateway()
 
     def _service(self) -> MagicMock:
+        from bot_bottle.backend.macos_container.infra import InfraEndpoint
         service = MagicMock()
-        service.ensure_running.return_value = "http://192.168.128.2:8099"
+        service.ensure_running.return_value = InfraEndpoint(
+            control_plane_url="http://192.168.128.2:8099",
+            gateway_ip="192.168.128.2",
+        )
         service.network = "bot-bottle-mac-gateway"
-        service.gateway.return_value.ip_on_shared_network.return_value = "192.168.128.3"
+        service.ca_cert_pem.return_value = "PEM"
-        service.gateway.return_value.ca_cert_pem.return_value = "PEM"
         return service
 
     def test_reports_gateway_endpoint(self) -> None:
         endpoint = self._run(self._service())
         self.assertEqual("http://192.168.128.2:8099", endpoint.orchestrator_url)
-        self.assertEqual("192.168.128.3", endpoint.gateway_ip)
+        self.assertEqual("192.168.128.2", endpoint.gateway_ip)
         self.assertEqual("PEM", endpoint.gateway_ca_pem)
         self.assertEqual("bot-bottle-mac-gateway", endpoint.network)
 
-    def test_gateway_is_pointed_at_the_resolved_control_plane(self) -> None:
+    def test_control_plane_and_gateway_share_one_address(self) -> None:
-        """Apple has no container DNS, so the gateway must be handed the
+        """One infra container hosts both, so the gateway IP and the
-        control plane's *resolved URL* rather than a container name."""
+        control-plane host are the same."""
-        service = self._service()
+        endpoint = self._run(self._service())
-        self._run(service)
+        self.assertEqual(
-        service.gateway.assert_called_with("http://192.168.128.2:8099")
+            endpoint.gateway_ip,
+            endpoint.orchestrator_url.split("://")[1].split(":")[0],
+        )
 
 
 class TestRegisterAgent(unittest.TestCase):

tests/unit/test_macos_container_cleanup.py

@@ -60,13 +60,10 @@ class TestMacosContainerEnumerate(unittest.TestCase):
         self.assertEqual(["dev-abc"], [a.slug for a in agents])
         self.assertEqual(["macos-container"], [a.backend_name for a in agents])
 
-    def test_excludes_the_shared_singletons(self):
+    def test_excludes_the_infra_singleton(self):
-        """The gateway and control plane share the bot-bottle- prefix but are
+        """The infra container shares the bot-bottle- prefix but is
-        infrastructure — listing them would invent an agent per host."""
+        infrastructure — listing it would invent an agent per host."""
-        agents = self._enumerate(
+        agents = self._enumerate("bot-bottle-mac-infra\nbot-bottle-dev-abc\n")
-            "bot-bottle-mac-gateway\nbot-bottle-mac-orchestrator\n"
-            "bot-bottle-dev-abc\n"
-        )
         self.assertEqual(["dev-abc"], [a.slug for a in agents])
 
     def test_empty_when_the_cli_fails(self):

tests/unit/test_macos_container_launch_wiring.py

@@ -158,6 +158,36 @@ class TestIdentityTokenDelivery(unittest.TestCase):
         argv = bottle.agent_argv(["--help"], tty=False)
         self.assertNotIn("--env", argv)
 
+
+class TestPlanIdentityToken(unittest.TestCase):
+    """git-gate's gitconfig extraHeader and the supervise MCP --header read
+    `getattr(plan, "identity_token", "")` at provision time and both bypass the
+    egress proxy (NO_PROXY), so the exec-time proxy token never reaches them —
+    the plan must carry the token or /resolve fail-closes and git + supervise
+    are denied on macOS."""
+
+    def test_macos_plan_has_the_identity_token_field(self) -> None:
+        from dataclasses import fields
+
+        from bot_bottle.backend.macos_container.bottle_plan import (
+            MacosContainerBottlePlan,
+        )
+        names = {f.name for f in fields(MacosContainerBottlePlan)}
+        self.assertIn("identity_token", names)
+
+    def test_matches_the_docker_plan(self) -> None:
+        """Both consolidated backends must expose identity_token so a shared
+        provision-time consumer degrades to neither backend silently."""
+        from dataclasses import fields
+
+        from bot_bottle.backend.docker.bottle_plan import DockerBottlePlan
+        from bot_bottle.backend.macos_container.bottle_plan import (
+            MacosContainerBottlePlan,
+        )
+        docker = {f.name for f in fields(DockerBottlePlan)}
+        macos = {f.name for f in fields(MacosContainerBottlePlan)}
+        self.assertIn("identity_token", docker & macos)
+
     def test_provisioning_exec_also_carries_the_token(self) -> None:
         """`provision` runs through `exec`; a provider whose provision step
         fetches anything would otherwise egress token-less and be denied."""

tests/unit/test_macos_container_util.py

@@ -273,5 +273,55 @@ resolver #2
             )
 
 
+def _completed(stdout: str, returncode: int = 0):
+    return util.subprocess.CompletedProcess(args=[], returncode=returncode, stdout=stdout, stderr="")
+
+
+class TestInspectDigests(unittest.TestCase):
+    """image_digest and container_image_digest must read the SAME field shape
+    (a `descriptor.digest`) so a running container and its image are
+    comparable. An asymmetry recreates the gateway on every launch."""
+
+    _IMAGE = '{"configuration": {"descriptor": {"digest": "sha256:abc123"}}, "id": "abc123"}'
+    _CONTAINER = '[{"configuration": {"image": {"descriptor": {"digest": "sha256:abc123"}}}}]'
+
+    def test_image_and_container_digests_agree_for_the_same_image(self):
+        with patch.object(util, "run_container_argv") as run:
+            run.return_value = _completed(self._IMAGE)
+            img = util.image_digest("bot-bottle-gateway:latest")
+            run.return_value = _completed(self._CONTAINER)
+            ctr = util.container_image_digest("bot-bottle-mac-gateway")
+        self.assertEqual("abc123", img)
+        self.assertEqual(img, ctr)
+
+    def test_image_digest_never_falls_back_to_a_tag_or_id(self):
+        """The old `id` fallback could yield a value container_image_digest
+        can't produce, permanently mismatching. Missing descriptor → '' (don't
+        churn), never a stray id/tag."""
+        with patch.object(util, "run_container_argv") as run:
+            run.return_value = _completed('{"id": "bot-bottle-gateway:latest"}')
+            self.assertEqual("", util.image_digest("bot-bottle-gateway:latest"))
+
+    def test_unreadable_inspect_returns_empty(self):
+        with patch.object(util, "run_container_argv") as run:
+            run.return_value = _completed("", returncode=1)
+            self.assertEqual("", util.image_digest("x"))
+            self.assertEqual("", util.container_image_digest("x"))
+            self.assertEqual({}, util.container_env("x"))
+
+
+class TestWaitContainerIpv4(unittest.TestCase):
+    def test_returns_address_once_dhcp_assigns_it(self):
+        with patch.object(util, "try_container_ipv4_on_network", side_effect=["", "", "192.168.128.4"]), \
+                patch.object(util.time, "sleep"):
+            ip = util.wait_container_ipv4_on_network("c", "net", timeout=5, poll=0)
+        self.assertEqual("192.168.128.4", ip)
+
+    def test_returns_empty_on_timeout(self):
+        with patch.object(util, "try_container_ipv4_on_network", return_value=""), \
+                patch.object(util.time, "sleep"):
+            self.assertEqual("", util.wait_container_ipv4_on_network("c", "net", timeout=-1))
+
+
 if __name__ == "__main__":
     unittest.main()

tests/unit/test_macos_gateway.py

@@ -1,275 +0,0 @@
-"""Unit: the Apple gateway + orchestrator lifecycle (PRD 0070)."""
-
-from __future__ import annotations
-
-import unittest
-from pathlib import Path
-from unittest.mock import Mock, patch
-
-from bot_bottle.backend.macos_container.gateway import AppleGateway, GatewayError
-from bot_bottle.backend.macos_container.orchestrator_service import (
-    MacosOrchestratorService,
-    OrchestratorStartError,
-)
-
-_GW = "bot_bottle.backend.macos_container.gateway"
-_ORCH = "bot_bottle.backend.macos_container.orchestrator_service"
-
-
-def _ok(stdout: str = "") -> Mock:
-    return Mock(returncode=0, stdout=stdout, stderr="")
-
-
-def _fail(stderr: str = "boom") -> Mock:
-    return Mock(returncode=1, stdout="", stderr=stderr)
-
-
-class TestAppleGatewayRun(unittest.TestCase):
-    def _argv(self, run: Mock) -> list[str]:
-        return run.call_args.args[0]
-
-    def _start(self, run: Mock) -> None:
-        with patch(f"{_GW}.container_mod") as mod:
-            mod.container_is_running.return_value = False
-            mod.dns_server.return_value = "1.1.1.1"
-            mod.run_container_argv = run
-            AppleGateway(orchestrator_url="http://192.168.128.2:8099").ensure_running()
-
-    def test_nat_network_precedes_the_host_only_network(self) -> None:
-        """Apple Container makes the FIRST --network the default route, so the
-        NAT network must lead or the gateway has no route out."""
-        run = Mock(return_value=_ok())
-        self._start(run)
-        argv = self._argv(run)
-        networks = [argv[i + 1] for i, a in enumerate(argv) if a == "--network"]
-        self.assertEqual(["bot-bottle-mac-egress", "bot-bottle-mac-gateway"], networks)
-
-    def test_control_plane_url_is_passed_for_multi_tenancy(self) -> None:
-        run = Mock(return_value=_ok())
-        self._start(run)
-        self.assertIn(
-            "BOT_BOTTLE_ORCHESTRATOR_URL=http://192.168.128.2:8099", self._argv(run),
-        )
-
-    def test_dns_is_explicit(self) -> None:
-        """The NAT gateway routes but does not resolve."""
-        run = Mock(return_value=_ok())
-        self._start(run)
-        argv = self._argv(run)
-        self.assertEqual("1.1.1.1", argv[argv.index("--dns") + 1])
-
-    def test_start_failure_raises(self) -> None:
-        with self.assertRaises(GatewayError):
-            self._start(Mock(return_value=_fail()))
-
-    def test_running_current_gateway_is_left_alone(self) -> None:
-        """Idempotent singleton: N launches must not restart the gateway and
-        drop every other bottle's data plane."""
-        run = Mock(return_value=_ok())
-        with patch(f"{_GW}.container_mod") as mod:
-            mod.container_is_running.return_value = True
-            mod.container_image_digest.return_value = "abc"
-            mod.image_digest.return_value = "abc"
-            mod.run_container_argv = run
-            AppleGateway().ensure_running()
-        run.assert_not_called()
-
-    def test_stale_image_forces_a_recreate(self) -> None:
-        """A rebuilt image only takes effect if the running container is
-        replaced — otherwise it keeps serving the OLD daemons."""
-        run = Mock(return_value=_ok())
-        with patch(f"{_GW}.container_mod") as mod:
-            mod.container_is_running.return_value = True
-            mod.container_image_digest.return_value = "old"
-            mod.image_digest.return_value = "new"
-            mod.dns_server.return_value = "1.1.1.1"
-            mod.run_container_argv = run
-            AppleGateway().ensure_running()
-        run.assert_called_once()
-
-    def test_unreadable_digest_does_not_churn(self) -> None:
-        run = Mock(return_value=_ok())
-        with patch(f"{_GW}.container_mod") as mod:
-            mod.container_is_running.return_value = True
-            mod.container_image_digest.return_value = ""
-            mod.image_digest.return_value = ""
-            mod.run_container_argv = run
-            AppleGateway().ensure_running()
-        run.assert_not_called()
-
-    def _start_with_running_env(self, env: dict[str, str], url: str) -> Mock:
-        run = Mock(return_value=_ok())
-        with patch(f"{_GW}.container_mod") as mod:
-            mod.container_is_running.return_value = True
-            mod.container_image_digest.return_value = "abc"
-            mod.image_digest.return_value = "abc"
-            mod.container_env.return_value = env
-            mod.dns_server.return_value = "1.1.1.1"
-            mod.run_container_argv = run
-            AppleGateway(orchestrator_url=url).ensure_running()
-        return run
-
-    def test_moved_control_plane_forces_a_recreate(self) -> None:
-        """Docker hands the gateway a container *name*, stable across an
-        orchestrator recreate. Apple has no DNS, so the URL is an IP baked into
-        the gateway's env — if the orchestrator comes back on a new address and
-        the gateway isn't recreated, every /resolve fails and every bottle on
-        the host loses egress."""
-        run = self._start_with_running_env(
-            {"BOT_BOTTLE_ORCHESTRATOR_URL": "http://192.168.128.2:8099"},
-            "http://192.168.128.7:8099",
-        )
-        run.assert_called_once()
-        self.assertIn(
-            "BOT_BOTTLE_ORCHESTRATOR_URL=http://192.168.128.7:8099",
-            run.call_args.args[0],
-        )
-
-    def test_unmoved_control_plane_does_not_churn(self) -> None:
-        run = self._start_with_running_env(
-            {"BOT_BOTTLE_ORCHESTRATOR_URL": "http://192.168.128.2:8099"},
-            "http://192.168.128.2:8099",
-        )
-        run.assert_not_called()
-
-    def test_unreadable_env_does_not_churn(self) -> None:
-        run = self._start_with_running_env({}, "http://192.168.128.2:8099")
-        run.assert_not_called()
-
-
-class TestMacosOrchestratorService(unittest.TestCase):
-    def test_orchestrator_starts_before_the_gateway(self) -> None:
-        """Apple has no container DNS, so the gateway can only be handed the
-        control plane's IP — which does not exist until it is running. This
-        ordering is the whole reason the macOS service diverges from docker's."""
-        order: list[str] = []
-        svc = MacosOrchestratorService(repo_root=Path("/r"), host_root=Path("/h"))
-        gateway = Mock()
-        gateway.ensure_running.side_effect = lambda: order.append("gateway")
-
-        def _record_orchestrator(_hash: str) -> None:
-            order.append("orchestrator")
-
-        with patch(f"{_ORCH}.container_mod") as mod, \
-                patch(f"{_ORCH}.source_hash", return_value="h1"), \
-                patch.object(svc, "_run_orchestrator_container",
-                             side_effect=_record_orchestrator), \
-                patch.object(svc, "gateway", return_value=gateway), \
-                patch.object(svc, "is_healthy", return_value=True):
-            mod.container_is_running.return_value = False
-            mod.image_exists.return_value = True
-            mod.try_container_ipv4_on_network.return_value = "192.168.128.2"
-            url = svc.ensure_running()
-        self.assertEqual(["orchestrator", "gateway"], order)
-        self.assertEqual("http://192.168.128.2:8099", url)
-
-    def test_gateway_is_handed_the_resolved_url(self) -> None:
-        svc = MacosOrchestratorService(repo_root=Path("/r"), host_root=Path("/h"))
-        with patch(f"{_ORCH}.container_mod") as mod, \
-                patch(f"{_ORCH}.source_hash", return_value="h1"), \
-                patch.object(svc, "_run_orchestrator_container"), \
-                patch.object(svc, "gateway") as gw, \
-                patch.object(svc, "is_healthy", return_value=True):
-            mod.container_is_running.return_value = False
-            mod.image_exists.return_value = True
-            mod.try_container_ipv4_on_network.return_value = "192.168.128.2"
-            svc.ensure_running()
-        gw.assert_called_with("http://192.168.128.2:8099")
-
-    def test_current_source_leaves_a_healthy_orchestrator_alone(self) -> None:
-        """Recreating on every launch would drop every other live bottle's
-        in-memory egress tokens (#381)."""
-        svc = MacosOrchestratorService(repo_root=Path("/r"), host_root=Path("/h"))
-        run = Mock()
-        with patch(f"{_ORCH}.container_mod") as mod, \
-                patch(f"{_ORCH}.source_hash", return_value="h1"), \
-                patch.object(svc, "_run_orchestrator_container", run), \
-                patch.object(svc, "gateway"), \
-                patch.object(svc, "is_healthy", return_value=True):
-            mod.container_is_running.return_value = True
-            mod.inspect_container.return_value = {
-                "configuration": {"labels": {"bot-bottle-orchestrator-source-hash": "h1"}}
-            }
-            mod.try_container_ipv4_on_network.return_value = "192.168.128.2"
-            svc.ensure_running()
-        run.assert_not_called()
-
-    def test_changed_source_recreates_the_orchestrator(self) -> None:
-        """The control-plane process loaded its bind-mounted source at startup
-        and won't reload it."""
-        svc = MacosOrchestratorService(repo_root=Path("/r"), host_root=Path("/h"))
-        run = Mock()
-        with patch(f"{_ORCH}.container_mod") as mod, \
-                patch(f"{_ORCH}.source_hash", return_value="h2"), \
-                patch.object(svc, "_run_orchestrator_container", run), \
-                patch.object(svc, "gateway"), \
-                patch.object(svc, "is_healthy", return_value=True):
-            mod.container_is_running.return_value = True
-            mod.inspect_container.return_value = {
-                "configuration": {"labels": {"bot-bottle-orchestrator-source-hash": "h1"}}
-            }
-            mod.image_exists.return_value = True
-            mod.try_container_ipv4_on_network.return_value = "192.168.128.2"
-            svc.ensure_running()
-        run.assert_called_once()
-
-    def test_never_healthy_raises(self) -> None:
-        svc = MacosOrchestratorService(repo_root=Path("/r"), host_root=Path("/h"))
-        with patch(f"{_ORCH}.container_mod") as mod, \
-                patch(f"{_ORCH}.source_hash", return_value="h1"), \
-                patch.object(svc, "_run_orchestrator_container"), \
-                patch.object(svc, "is_healthy", return_value=False):
-            mod.container_is_running.return_value = False
-            mod.image_exists.return_value = True
-            mod.try_container_ipv4_on_network.return_value = "192.168.128.2"
-            with self.assertRaises(OrchestratorStartError):
-                svc.ensure_running(startup_timeout=0.01)
-
-    def test_control_plane_needs_no_route_out(self) -> None:
-        """The orchestrator sits only on the host-only network: the host
-        reaches it there directly, so there is no --publish and no NAT leg."""
-        svc = MacosOrchestratorService(repo_root=Path("/r"), host_root=Path("/h"))
-        run = Mock(return_value=_ok())
-        # `ensure_networks` lives in the gateway module and shells out to the
-        # `container` CLI, which does not exist on the Linux CI host — patch it
-        # here, not gateway.container_mod, since it is called through this
-        # module's imported name.
-        with patch(f"{_ORCH}.container_mod") as mod, \
-                patch(f"{_ORCH}.ensure_networks"):
-            mod.run_container_argv = run
-            svc._run_orchestrator_container("h1")
-        argv = run.call_args.args[0]
-        networks = [argv[i + 1] for i, a in enumerate(argv) if a == "--network"]
-        self.assertEqual(["bot-bottle-mac-gateway"], networks)
-        self.assertNotIn("--publish", argv)
-
-    def test_networks_exist_before_the_orchestrator_runs(self) -> None:
-        """The orchestrator is the first container on the shared network, so it
-        has to create it — the gateway that used to do so now starts second."""
-        svc = MacosOrchestratorService(repo_root=Path("/r"), host_root=Path("/h"))
-        order: list[str] = []
-
-        def _networks(*_args: str) -> None:
-            order.append("networks")
-
-        def _run(*_args: list[str]) -> Mock:
-            order.append("run")
-            return _ok()
-
-        with patch(f"{_ORCH}.container_mod") as mod, \
-                patch(f"{_ORCH}.ensure_networks", side_effect=_networks):
-            mod.run_container_argv = Mock(side_effect=_run)
-            svc._run_orchestrator_container("h1")
-        self.assertEqual(["networks", "run"], order)
-
-    def test_orchestrator_start_failure_raises(self) -> None:
-        svc = MacosOrchestratorService(repo_root=Path("/r"), host_root=Path("/h"))
-        with patch(f"{_ORCH}.container_mod") as mod, \
-                patch(f"{_ORCH}.ensure_networks"):
-            mod.run_container_argv = Mock(return_value=_fail())
-            with self.assertRaises(OrchestratorStartError):
-                svc._run_orchestrator_container("h1")
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_macos_infra.py

@@ -0,0 +1,168 @@
+"""Unit: the single macOS infra container (control plane + gateway, PRD 0070)."""
+
+from __future__ import annotations
+
+import unittest
+from pathlib import Path
+from unittest.mock import Mock, patch
+
+from bot_bottle.backend.macos_container.infra import (
+    INFRA_DB_VOLUME,
+    MacosInfraService,
+    OrchestratorStartError,
+    probe_control_plane_url,
+)
+
+_INFRA = "bot_bottle.backend.macos_container.infra"
+
+
+def _ok(stdout: str = "") -> Mock:
+    return Mock(returncode=0, stdout=stdout, stderr="")
+
+
+def _fail(stderr: str = "boom") -> Mock:
+    return Mock(returncode=1, stdout="", stderr=stderr)
+
+
+class TestInfraRun(unittest.TestCase):
+    def _run_container(self, svc: MacosInfraService) -> list[str]:
+        run = Mock(return_value=_ok())
+
+        def _spec(src: str, tgt: str, readonly: bool = False) -> str:
+            return f"type=bind,source={src},target={tgt}" + (
+                ",readonly" if readonly else "")
+
+        with patch(f"{_INFRA}.container_mod") as mod, \
+                patch(f"{_INFRA}.ensure_networks"):
+            mod.dns_server.return_value = "1.1.1.1"
+            mod.bind_mount_spec.side_effect = _spec
+            mod.run_container_argv = run
+            svc._run_container("h1")
+        return run.call_args.args[0]
+
+    def test_single_container_runs_both_processes(self) -> None:
+        """The whole point: one container starts the control plane AND the
+        gateway daemons, so one kernel owns the DB."""
+        argv = self._run_container(MacosInfraService(repo_root=Path("/r")))
+        script = argv[-1]
+        self.assertIn("bot_bottle.orchestrator", script)
+        self.assertIn("gateway_init.py", script)
+        self.assertIn("127.0.0.1", script)  # they reach each other on loopback
+
+    def test_db_is_a_container_only_volume(self) -> None:
+        """No host bind-mount of the DB — a named volume only this container
+        mounts, so the DB is never written by two kernels."""
+        argv = self._run_container(MacosInfraService(repo_root=Path("/r")))
+        vols = [argv[i + 1] for i, a in enumerate(argv) if a == "--volume"]
+        self.assertTrue(any(v.startswith(f"{INFRA_DB_VOLUME}:") for v in vols))
+        # The repo source is bind-mounted read-only; the DB is not a bind mount.
+        mounts = [argv[i + 1] for i, a in enumerate(argv) if a == "--mount"]
+        self.assertTrue(all("bot-bottle.db" not in m for m in mounts))
+
+    def test_nat_network_precedes_the_host_only_network(self) -> None:
+        argv = self._run_container(MacosInfraService(repo_root=Path("/r")))
+        nets = [argv[i + 1] for i, a in enumerate(argv) if a == "--network"]
+        self.assertEqual(["bot-bottle-mac-egress", "bot-bottle-mac-gateway"], nets)
+
+    def test_source_hash_is_labelled_for_recreate(self) -> None:
+        argv = self._run_container(MacosInfraService(repo_root=Path("/r")))
+        self.assertIn("BOT_BOTTLE_SOURCE_HASH=h1", argv)
+
+    def test_start_failure_raises(self) -> None:
+        svc = MacosInfraService(repo_root=Path("/r"))
+        with patch(f"{_INFRA}.container_mod") as mod, \
+                patch(f"{_INFRA}.ensure_networks"):
+            mod.dns_server.return_value = "1.1.1.1"
+            mod.bind_mount_spec.return_value = "m"
+            mod.run_container_argv = Mock(return_value=_fail())
+            with self.assertRaises(OrchestratorStartError):
+                svc._run_container("h1")
+
+
+class TestInfraEnsureRunning(unittest.TestCase):
+    def test_current_healthy_container_is_left_alone(self) -> None:
+        """Idempotent singleton: N launches must not churn the infra container
+        and drop every live bottle's control plane."""
+        svc = MacosInfraService(repo_root=Path("/r"))
+        run = Mock()
+        with patch(f"{_INFRA}.container_mod") as mod, \
+                patch(f"{_INFRA}.source_hash", return_value="h1"), \
+                patch.object(svc, "_run_container", run), \
+                patch.object(svc, "is_healthy", return_value=True):
+            mod.container_is_running.return_value = True
+            mod.container_env.return_value = {"BOT_BOTTLE_SOURCE_HASH": "h1"}
+            mod.try_container_ipv4_on_network.return_value = "192.168.128.2"
+            endpoint = svc.ensure_running()
+        run.assert_not_called()
+        self.assertEqual("http://192.168.128.2:8099", endpoint.control_plane_url)
+        self.assertEqual("192.168.128.2", endpoint.gateway_ip)
+
+    def test_changed_source_recreates(self) -> None:
+        svc = MacosInfraService(repo_root=Path("/r"))
+        run = Mock()
+        with patch(f"{_INFRA}.container_mod") as mod, \
+                patch(f"{_INFRA}.source_hash", return_value="h2"), \
+                patch.object(svc, "ensure_built"), \
+                patch.object(svc, "_run_container", run), \
+                patch.object(svc, "is_healthy", return_value=True):
+            mod.container_is_running.return_value = True
+            mod.container_env.return_value = {"BOT_BOTTLE_SOURCE_HASH": "h1"}
+            mod.try_container_ipv4_on_network.return_value = "192.168.128.2"
+            svc.ensure_running()
+        run.assert_called_once()
+
+    def test_wedged_but_current_container_is_recreated(self) -> None:
+        """Current source but a dead HTTP server must be recreated, not polled
+        to death forever — health, not just the source label, gates reuse."""
+        svc = MacosInfraService(repo_root=Path("/r"))
+        run = Mock()
+        health = Mock(side_effect=[False, True])
+        with patch(f"{_INFRA}.container_mod") as mod, \
+                patch(f"{_INFRA}.source_hash", return_value="h1"), \
+                patch.object(svc, "ensure_built"), \
+                patch.object(svc, "_run_container", run), \
+                patch.object(svc, "is_healthy", health):
+            mod.container_is_running.return_value = True
+            mod.container_env.return_value = {"BOT_BOTTLE_SOURCE_HASH": "h1"}
+            mod.try_container_ipv4_on_network.return_value = "192.168.128.2"
+            svc.ensure_running()
+        run.assert_called_once()
+
+    def test_never_healthy_raises(self) -> None:
+        svc = MacosInfraService(repo_root=Path("/r"))
+        with patch(f"{_INFRA}.container_mod") as mod, \
+                patch(f"{_INFRA}.source_hash", return_value="h1"), \
+                patch.object(svc, "ensure_built"), \
+                patch.object(svc, "_run_container"), \
+                patch.object(svc, "is_healthy", return_value=False):
+            mod.container_is_running.return_value = False
+            mod.try_container_ipv4_on_network.return_value = "192.168.128.2"
+            with self.assertRaises(OrchestratorStartError):
+                svc.ensure_running(startup_timeout=0.01)
+
+
+class TestCaCertPem(unittest.TestCase):
+    def test_reads_ca_out_of_the_container(self) -> None:
+        svc = MacosInfraService(repo_root=Path("/r"))
+        with patch(f"{_INFRA}.container_mod") as mod:
+            mod.run_container_argv.return_value = _ok("-----BEGIN CERTIFICATE-----\n")
+            pem = svc.ca_cert_pem()
+        self.assertTrue(pem.startswith("-----BEGIN CERTIFICATE-----"))
+        argv = mod.run_container_argv.call_args.args[0]
+        self.assertEqual(["container", "exec", "bot-bottle-mac-infra", "cat"], argv[:4])
+
+
+class TestProbeControlPlane(unittest.TestCase):
+    def test_returns_url_when_running(self) -> None:
+        with patch(f"{_INFRA}.container_mod") as mod:
+            mod.try_container_ipv4_on_network.return_value = "192.168.128.2"
+            self.assertEqual("http://192.168.128.2:8099", probe_control_plane_url())
+
+    def test_empty_when_absent(self) -> None:
+        with patch(f"{_INFRA}.container_mod") as mod:
+            mod.try_container_ipv4_on_network.return_value = ""
+            self.assertEqual("", probe_control_plane_url())
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/test_orchestrator_control_plane.py

@@ -11,6 +11,7 @@ import secrets
 import tempfile
 import threading
 import unittest
+import urllib.error
 import urllib.request
 from pathlib import Path
 from unittest.mock import patch
@@ -243,6 +244,82 @@ class TestServerRoundTrip(unittest.TestCase):
         self.assertEqual(reg["bottle_id"], attr["bottle_id"])
 
 
+class TestControlPlaneAuth(unittest.TestCase):
+    """The per-host control-plane secret (issue #400): every route but /health
+    is a trusted-caller op an agent must not be able to drive just because it
+    can reach the port."""
+
+    def setUp(self) -> None:
+        self._tmp = tempfile.TemporaryDirectory()
+        self.addCleanup(self._tmp.cleanup)
+        self.orch = _orchestrator(Path(self._tmp.name) / "r.db")
+
+    def test_health_is_public_even_unauthorized(self) -> None:
+        status, _ = dispatch(self.orch, "GET", "/health", b"", authorized=False)
+        self.assertEqual(200, status)
+
+    def test_unauthorized_denies_every_other_route(self) -> None:
+        for method, path, body in [
+            ("GET", "/bottles", b""),
+            ("POST", "/bottles", _body({"source_ip": "10.0.0.1"})),
+            ("PUT", "/bottles/x/policy", _body({"policy": "routes: []"})),
+            ("DELETE", "/bottles/x", b""),
+            ("POST", "/resolve", _body({"source_ip": "10.0.0.1", "identity_token": "t"})),
+            ("POST", "/attribute", _body({"source_ip": "10.0.0.1", "identity_token": "t"})),
+            ("GET", "/supervise/proposals", b""),
+            ("POST", "/supervise/respond", _body({"proposal_id": "p", "bottle_slug": "s", "decision": "approve"})),
+        ]:
+            status, _ = dispatch(self.orch, method, path, body, authorized=False)
+            self.assertEqual(401, status, f"{method} {path} should be 401 unauthorized")
+
+    def test_deny_happens_before_the_registry_is_touched(self) -> None:
+        """An unauthorized DELETE must not tear a bottle down. 401, and the
+        bottle is still there."""
+        rec = self.orch.registry.register("10.0.0.9", policy="", metadata="")
+        status, _ = dispatch(
+            self.orch, "DELETE", f"/bottles/{rec.bottle_id}", b"", authorized=False)
+        self.assertEqual(401, status)
+        self.assertIsNotNone(self.orch.registry.get(rec.bottle_id))
+
+    def _server_with_secret(self, secret: str):
+        with patch.dict("os.environ", {"BOT_BOTTLE_CONTROL_PLANE_TOKEN": secret}):
+            server = make_server(self.orch, "127.0.0.1", 0)
+        self.addCleanup(server.server_close)
+        threading.Thread(target=server.serve_forever, daemon=True).start()
+        self.addCleanup(server.shutdown)
+        host, port = server.server_address[0], server.server_address[1]
+        return f"http://{host}:{port}"
+
+    def _status(self, url: str, *, header: str | None = None) -> int:
+        req = urllib.request.Request(url)
+        if header is not None:
+            req.add_header("x-bot-bottle-control-auth", header)
+        try:
+            return urllib.request.urlopen(req, timeout=5).status
+        except urllib.error.HTTPError as e:
+            return e.code
+
+    def test_configured_server_enforces_the_header_over_http(self) -> None:
+        base = self._server_with_secret("s3cret-admin")
+        # /health is public — no header needed.
+        self.assertEqual(200, self._status(f"{base}/health"))
+        # /bottles requires the secret.
+        self.assertEqual(401, self._status(f"{base}/bottles"))
+        self.assertEqual(401, self._status(f"{base}/bottles", header="wrong"))
+        self.assertEqual(200, self._status(f"{base}/bottles", header="s3cret-admin"))
+
+    def test_unconfigured_server_runs_open(self) -> None:
+        """No secret set (tests / nft-protected Firecracker): open mode, so the
+        existing round-trip and unit behavior are unchanged."""
+        with patch.dict("os.environ", {}, clear=False):
+            import os
+            os.environ.pop("BOT_BOTTLE_CONTROL_PLANE_TOKEN", None)
+            server = make_server(self.orch, "127.0.0.1", 0)
+        self.addCleanup(server.server_close)
+        self.assertTrue(server.is_authorized(""))
+        self.assertTrue(server.is_authorized("anything"))
+
+
 class TestDispatchSupervise(unittest.TestCase):
     """The /supervise/* routes over the pure dispatch()."""
 

tests/unit/test_orchestrator_gateway.py

@@ -38,7 +38,7 @@ class TestDockerGateway(unittest.TestCase):
     def test_ensure_running_noop_when_up_and_image_current(self) -> None:
         calls: list[list[str]] = []
 
-        def fake(argv: list[str]) -> Mock:
+        def fake(argv: list[str], **_kw: object) -> Mock:
             calls.append(argv)
             if argv[:2] == ["docker", "ps"]:
                 return _proc(stdout=self.sc.name)          # running
@@ -58,7 +58,7 @@ class TestDockerGateway(unittest.TestCase):
         # a rebuild's new flat daemons take effect.
         calls: list[list[str]] = []
 
-        def fake(argv: list[str]) -> Mock:
+        def fake(argv: list[str], **_kw: object) -> Mock:
             calls.append(argv)
             if argv[:2] == ["docker", "ps"]:
                 return _proc(stdout=self.sc.name)
@@ -76,7 +76,7 @@ class TestDockerGateway(unittest.TestCase):
     def test_ensure_running_starts_the_singleton_when_absent(self) -> None:
         calls: list[list[str]] = []
 
-        def fake(argv: list[str]) -> Mock:
+        def fake(argv: list[str], **_kw: object) -> Mock:
             calls.append(argv)
             return _proc(stdout="") if argv[:2] == ["docker", "ps"] else _proc()
 
@@ -102,7 +102,7 @@ class TestDockerGateway(unittest.TestCase):
     def test_ensure_running_creates_network_when_missing(self) -> None:
         calls: list[list[str]] = []
 
-        def fake(argv: list[str]) -> Mock:
+        def fake(argv: list[str], **_kw: object) -> Mock:
             calls.append(argv)
             if argv[:3] == ["docker", "network", "inspect"]:
                 return _proc(returncode=1, stderr="No such network")
@@ -135,7 +135,7 @@ class TestDockerGateway(unittest.TestCase):
     def test_ensure_running_reuses_existing_network(self) -> None:
         calls: list[list[str]] = []
 
-        def fake(argv: list[str]) -> Mock:
+        def fake(argv: list[str], **_kw: object) -> Mock:
             calls.append(argv)
             return _proc(stdout="") if argv[:2] == ["docker", "ps"] else _proc()
 
@@ -144,7 +144,7 @@ class TestDockerGateway(unittest.TestCase):
         self.assertEqual([], [c for c in calls if c[:3] == ["docker", "network", "create"]])
 
     def test_ensure_running_raises_on_docker_failure(self) -> None:
-        def fake(argv: list[str]) -> Mock:
+        def fake(argv: list[str], **_kw: object) -> Mock:
             if argv[:2] == ["docker", "ps"]:
                 return _proc(stdout="")
             if argv[:2] == ["docker", "run"]:
@@ -181,7 +181,7 @@ class TestDockerGatewayBuild(unittest.TestCase):
         # build-if-missing silently ran a stale single-tenant image.
         calls: list[list[str]] = []
 
-        def rec(argv: list[str]) -> Mock:
+        def rec(argv: list[str], **_kw: object) -> Mock:
             calls.append(argv)
             return _proc()  # image present, build succeeds
 
@@ -196,7 +196,7 @@ class TestDockerGatewayBuild(unittest.TestCase):
     def test_ensure_built_no_cache_env_forces_full_rebuild(self) -> None:
         calls: list[list[str]] = []
 
-        def rec(argv: list[str]) -> Mock:
+        def rec(argv: list[str], **_kw: object) -> Mock:
             calls.append(argv)
             return _proc()
 

tests/unit/test_orchestrator_lifecycle.py

@@ -60,7 +60,7 @@ class TestOrchestratorService(unittest.TestCase):
         current = source_hash(self.svc._repo_root)
         calls: list[list[str]] = []
 
-        def fake(argv: list[str]) -> Mock:
+        def fake(argv: list[str], **_kw: object) -> Mock:
             calls.append(argv)
             if argv[:2] == ["docker", "ps"]:
                 return _proc(stdout=ORCHESTRATOR_NAME)
@@ -83,7 +83,7 @@ class TestOrchestratorService(unittest.TestCase):
         # effect, same as the gateway's image-staleness check.
         calls: list[list[str]] = []
 
-        def fake(argv: list[str]) -> Mock:
+        def fake(argv: list[str], **_kw: object) -> Mock:
             calls.append(argv)
             if argv[:2] == ["docker", "ps"]:
                 return _proc(stdout=ORCHESTRATOR_NAME)
@@ -104,7 +104,7 @@ class TestOrchestratorService(unittest.TestCase):
     def test_ensure_running_starts_orchestrator_container_when_absent(self) -> None:
         calls: list[list[str]] = []
 
-        def fake(argv: list[str]) -> Mock:
+        def fake(argv: list[str], **_kw: object) -> Mock:
             calls.append(argv)
             if argv[:2] == ["docker", "ps"]:
                 return _proc(stdout="")   # not running
@@ -127,7 +127,7 @@ class TestOrchestratorService(unittest.TestCase):
         # gateway data plane — built from Dockerfile.orchestrator when absent.
         calls: list[list[str]] = []
 
-        def fake(argv: list[str]) -> Mock:
+        def fake(argv: list[str], **_kw: object) -> Mock:
             calls.append(argv)
             if argv[:2] == ["docker", "ps"]:
                 return _proc(stdout="")                 # orchestrator not running
@@ -148,7 +148,7 @@ class TestOrchestratorService(unittest.TestCase):
     def test_ensure_running_skips_orchestrator_image_build_when_present(self) -> None:
         calls: list[list[str]] = []
 
-        def fake(argv: list[str]) -> Mock:
+        def fake(argv: list[str], **_kw: object) -> Mock:
             calls.append(argv)
             if argv[:2] == ["docker", "ps"]:
                 return _proc(stdout="")