fix(docker): use run_docker in docker_exec, docker_cp, verify_agent_image

The rebase onto lazy-backend-imports converts existing helpers (image_exists,
container_exists, etc.) to run_docker; the three new functions added in this
branch still called subprocess.run directly. Switch them over for consistency.

Dockerfile.gateway

@@ -34,45 +34,35 @@
 #   9420  git-gate smart HTTP (VM-backend agent-facing transport)
 #   9100  supervise (MCP HTTP)
 
-# Based on `python:3.12-slim` (Debian trixie) rather than the
-# `mitmproxy/mitmproxy` image (Debian bookworm) so the whole stack —
-# gateway here, and the firecracker infra image that builds FROM this —
-# lands on trixie, whose buildah (1.39) can build agent Dockerfiles that
-# use heredocs. mitmproxy is pip-installed to the same effect as the
-# upstream image. (bookworm's buildah is 1.28, which can't parse
-# `RUN ... <<EOF`; see the infra image + PR discussion.)
-FROM python:3.12-slim
+# Stage 1: gitleaks binary. The upstream gitleaks image is alpine
+# with the binary at /usr/bin/gitleaks. Pinned by digest in lockstep
+# with Dockerfile.git-gate's prior base (now deleted at chunk 3).
+FROM zricethezav/gitleaks@sha256:c00b6bd0aeb3071cbcb79009cb16a60dd9e0a7c60e2be9ab65d25e6bc8abbb7f AS gitleaks-src
+
+# Stage 2: assembly. mitmproxy/mitmproxy is debian-slim-based with
+# Python + mitmdump pre-installed — heavier than the others, so
+# this stage starts there and pulls the standalone binaries in.
+FROM mitmproxy/mitmproxy:11.1.3
+
+# Run as root inside the bundle. The bundle is the isolation
+# boundary; per-daemon user separation inside it is not load-bearing
+# and complicates the supervisor's spawn path.
+USER root
 
 # Runtime system deps:
 #   git supplies the `git daemon` subcommand (no separate package)
 #     plus the core `git` binary the pre-receive hook invokes.
 #   openssh-client supplies the upstream SSH transport the
 #     pre-receive hook uses to forward accepted refs.
-#   ca-certificates is needed for mitmdump upstream TLS.
+#   ca-certificates is needed for mitmdump upstream TLS (the
+#     base image already has it; listed for explicitness).
 RUN apt-get update \
  && apt-get install -y --no-install-recommends \
       git openssh-client ca-certificates \
  && rm -rf /var/lib/apt/lists/*
 
-# mitmdump (the egress data plane). The upstream mitmproxy image baked
-# this in; on the plain python base we pip-install the same pinned
-# version. Its CA dir is set explicitly via `--set confdir=` in
-# egress-entrypoint.sh, so it doesn't depend on a `mitmproxy` home user.
-RUN pip install --no-cache-dir mitmproxy==11.1.3
-
-# gitleaks (the pre-receive hook's secret scanner). Installed from its
-# official release, pinned by version + SHA256 and verified — rather than
-# using a third-party image as a build stage (supply-chain surface, and it
-# would pin us to that image's cadence). python (already present) does the
-# download so we add no curl/wget. trixie apt also ships gitleaks, but an
-# older 8.16; the pinned download keeps the verified 8.30.1.
-ARG GITLEAKS_VERSION=8.30.1
-ARG GITLEAKS_SHA256=551f6fc83ea457d62a0d98237cbad105af8d557003051f41f3e7ca7b3f2470eb
-RUN url="https://github.com/gitleaks/gitleaks/releases/download/v${GITLEAKS_VERSION}/gitleaks_${GITLEAKS_VERSION}_linux_x64.tar.gz" \
- && python3 -c "import sys,urllib.request; urllib.request.urlretrieve(sys.argv[1], '/tmp/gitleaks.tar.gz')" "$url" \
- && echo "${GITLEAKS_SHA256}  /tmp/gitleaks.tar.gz" | sha256sum -c - \
- && tar -xzf /tmp/gitleaks.tar.gz -C /usr/bin gitleaks \
- && rm /tmp/gitleaks.tar.gz
+# Pull the standalone binaries into the final image.
+COPY --from=gitleaks-src /usr/bin/gitleaks /usr/bin/gitleaks
 
 # Project Python: addon + server modules + the init supervisor.
 # Kept flat under /app/ so mitmdump's loader resolves them as

Dockerfile.infra

@@ -1,45 +0,0 @@
-# Firecracker single infra-VM image (PRD 0070 Stage B).
-#
-# The per-host infra VM runs the orchestrator control plane, the gateway
-# data plane, AND builds agent images (buildah) — all in one microVM (see
-# backend/firecracker/infra_vm.py). It composes:
-#   * FROM the gateway image (mitmproxy / git / gitleaks / supervise + the
-#     flat daemon modules) — now trixie-based, so buildah 1.39 is available;
-#   * `COPY --from` the orchestrator image's content (the single definition
-#     of the control-plane payload — see Dockerfile.orchestrator), so this
-#     VM and the docker backend share one orchestrator definition; and
-#   * buildah, installed HERE only (the docker orchestrator/gateway images
-#     never carry it).
-#
-# multi-`FROM` can't union two bases (that's multi-stage, not multiple
-# inheritance), so the orchestrator content is pulled in via `COPY --from`
-# rather than a second base. Both images share the trixie `python:3.12-slim`
-# base, so the copy is clean (same python; future installed deps copy too).
-#
-# The docker backend keeps orchestrator + gateway as separate images; this
-# combined image exists only for the Firecracker single-VM cut. Splitting a
-# service back into its own VM later is a routing change, not a repackaging
-# (PRD 0070's "secret concentration"; a disposable builder can boot from
-# this same image on its own TAP).
-FROM bot-bottle-gateway:latest
-
-# --- in-VM agent-image builder (PRD 0069 Stage 3) -------------------
-# The Firecracker backend builds users' agent Dockerfiles *inside this VM*
-# with buildah (rootless, daemonless) instead of on the host — no host
-# Docker daemon, no root-equivalent `docker` group. `crun` is the OCI
-# runtime; `netavark` + `aardvark-dns` are the network backend for `FROM`
-# pulls + `RUN` egress. Requires the trixie base (buildah 1.39: bookworm's
-# 1.28 can't parse Dockerfile heredocs that agent images use).
-RUN apt-get update \
- && apt-get install -y --no-install-recommends \
-      buildah crun netavark aardvark-dns \
- && rm -rf /var/lib/apt/lists/*
-# vfs + chroot: buildah works as root in the bare microVM (no
-# fuse-overlayfs / overlay module / subuid maps). Matches image_builder.
-ENV STORAGE_DRIVER=vfs \
-    BUILDAH_ISOLATION=chroot
-
-# The orchestrator content, pulled from its single definition. The gateway
-# image already has the flat daemon modules under /app; this adds the full
-# `bot_bottle` package so `python3 -m bot_bottle.orchestrator` resolves.
-COPY --from=bot-bottle-orchestrator:latest /app/bot_bottle /app/bot_bottle

Dockerfile.orchestrator

@@ -1,36 +1,27 @@
 # Orchestrator control-plane image (PRD 0070, #384).
 #
-# This is the **single definition of the orchestrator's content** — the
-# `bot_bottle` package baked onto a Python runtime — referenced by BOTH:
-#   * the docker backend, which runs this image directly as the lean
-#     control-plane container; and
-#   * the firecracker infra image (Dockerfile.infra), which `COPY --from`s
-#     this image's `/app/bot_bottle` so the single infra VM runs the same
-#     control plane. Keeping it in one place means future orchestrator deps
-#     (e.g. iroh) are added here once, not duplicated per backend.
+# The per-host orchestrator runs `python3 -m bot_bottle.orchestrator`.
+# The `bot_bottle` package is **stdlib-only** by design, so the control
+# plane needs nothing but a Python runtime — none of the gateway's
+# mitmproxy / git / gitleaks payload (that is the separate
+# `bot-bottle-gateway` image, Dockerfile.gateway). Splitting them keeps
+# the secret-dense control plane (it concentrates every bottle's egress
+# tokens — see PRD 0070's "secret concentration") on a minimal
+# dependency surface.
 #
-# It stays deliberately lean: the control plane is **stdlib-only** today, so
-# no third-party payload — none of the gateway's mitmproxy/git/gitleaks
-# (that's Dockerfile.gateway) and no buildah (that's the firecracker
-# builder, and lives only in Dockerfile.infra). Keeping the secret-dense
-# control plane on a minimal dependency surface is the point (PRD 0070's
-# "secret concentration").
-#
-# Shares the trixie `python:3.12-slim` base with the gateway image, so when
-# the orchestrator grows real deps they can be `COPY --from`'d into the
-# infra image cleanly (same base/python — installed packages copy safely).
+# The repo is bind-mounted read-only into the container at run time (see
+# `orchestrator/lifecycle.py`), so the source is NOT copied in here: the
+# image is just the runtime. `ensure_running` recreates the container
+# only when the bind-mounted source hash changes (#381), which is why
+# the code stays a mount rather than a baked layer.
 
 FROM python:3.12-slim
 
+# No third-party deps to install — stdlib only. Kept as an explicit,
+# self-documenting stage so a future confinement step (baking the
+# package, dropping the bind mount) has an obvious home.
 WORKDIR /app
 
-# The orchestrator content. Baked so the image is self-contained (runs from
-# a built image, no runtime bind-mount); the docker backend may still
-# bind-mount /app for dev live-reload, which simply overlays this copy.
-# `.dockerignore` keeps .git/docs/*.md out of the context. (Future deps like
-# iroh go here too — a shared requirements installed on this same base.)
-COPY bot_bottle /app/bot_bottle
-
 # Documentation only; lifecycle.py overrides the entrypoint to
 # `python3 -m bot_bottle.orchestrator` with the runtime flags.
 ENTRYPOINT ["python3", "-m", "bot_bottle.orchestrator"]

README.md

@@ -5,7 +5,7 @@
 # bot-bottle
 
 [![test](https://gitea.dideric.is/didericis/bot-bottle/actions/workflows/test.yml/badge.svg?branch=main)](https://gitea.dideric.is/didericis/bot-bottle/actions?workflow=test.yml)
-[![coverage](https://img.shields.io/badge/coverage-82%25-brightgreen)](https://coverage.readthedocs.io/)
+[![coverage](https://img.shields.io/badge/coverage-83%25-brightgreen)](https://coverage.readthedocs.io/)
 [![core coverage](https://img.shields.io/badge/core%20coverage-95%25-brightgreen)](https://gitea.dideric.is/didericis/bot-bottle/src/branch/main/docs/decisions/0004-coverage-policy.md)
 
 **Problem:** Developer wants to run a coding agent without supervision, but they don't want a prompt injected or misbehaving agent wrecking their environment or exfiltrating sensitive data.

bot_bottle/agent_provider.py

@@ -266,7 +266,6 @@ class AgentProvider(ABC):
             gate_scheme = getattr(plan, "git_gate_insteadof_scheme", "git")
             content = git_gate_render_gitconfig(
                 manifest_bottle.git, gate_host, scheme=gate_scheme,
-                identity_token=getattr(plan, "identity_token", ""),
             )
             guest_gitconfig = f"{plan.guest_home}/.gitconfig"
             with tempfile.NamedTemporaryFile(

bot_bottle/backend/__init__.py

@@ -511,18 +511,6 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
         del plan
         return ""
 
-    def ensure_orchestrator(self) -> str:
-        """Bring up this backend's per-host orchestrator + shared gateway
-        (idempotent) and return the host-reachable control-plane URL.
-
-        This is the backend-agnostic bring-up entry point: `launch` calls
-        it as part of starting a bottle, and operator tools (`supervise`)
-        call it to start the control plane on demand when none is running
-        yet. Docker starts the orchestrator + gateway containers;
-        firecracker boots the infra VM. Backends with no orchestrator
-        (macos-container) die with a pointer — the default here."""
-        die(f"backend {self.name!r} has no orchestrator control plane")
-
     @abstractmethod
     def prepare_cleanup(self) -> CleanupT:
         """Enumerate orphaned resources from previous bottles. No side

bot_bottle/backend/docker/backend.py

@@ -105,10 +105,6 @@ class DockerBottleBackend(BottleBackend["DockerBottlePlan", "DockerBottleCleanup
         with _launch.launch(plan, provision=self.provision) as bottle:
             yield bottle
 
-    def ensure_orchestrator(self) -> str:
-        from ...orchestrator.lifecycle import OrchestratorService
-        return OrchestratorService().ensure_running()
-
     def supervise_mcp_url(self, plan: DockerBottlePlan) -> str:
         """Docker bottles reach the supervise daemon via the
         compose-network alias `supervise:9100`. No per-bottle URL

bot_bottle/backend/docker/bottle_plan.py

@@ -35,10 +35,6 @@ class DockerBottlePlan(BottlePlan):
     # Likewise the supervise MCP endpoint at the gateway (`http://<gw>:9100/`);
     # empty → the single-tenant `supervise` alias.
     agent_supervise_url: str = ""
-    # Per-bottle identity token the agent presents on every attributed request
-    # (egress proxy credentials, git-gate/supervise headers); set by launch
-    # from the orchestrator registration. Empty pre-registration.
-    identity_token: str = ""
 
     @property
     def container_name(self) -> str:

bot_bottle/backend/docker/consolidated_compose.py

@@ -31,13 +31,7 @@ def consolidated_agent_compose(
 ) -> dict[str, Any]:
     """A compose spec with only the agent service, on the external gateway
     network at `source_ip`, proxying egress through `gateway_ip`."""
-    # Deliver the identity token as egress proxy credentials — the gateway
-    # reads Proxy-Authorization, validates the (source_ip, token) pair, and
-    # strips it before upstream. git-http/supervise get it via their own
-    # headers (git config extraHeader / MCP header).
-    token = getattr(plan, "identity_token", "")
-    cred = f"bottle:{token}@" if token else ""
-    proxy_url = f"http://{cred}{gateway_ip}:{EGRESS_PORT}"
+    proxy_url = f"http://{gateway_ip}:{EGRESS_PORT}"
     # git-http + supervise live on the gateway too and must NOT go through the
     # egress proxy — the agent reaches them directly by the gateway address.
     no_proxy = f"localhost,127.0.0.1,{gateway_ip}"

bot_bottle/backend/docker/consolidated_launch.py

@@ -29,11 +29,7 @@ from ...orchestrator.gateway import GATEWAY_NAME, GATEWAY_NETWORK
 from ...orchestrator.lifecycle import OrchestratorService
 from ...orchestrator.registration import registration_inputs
 from .gateway_net import next_free_ip
-from .gateway_provision import (
-    DockerGatewayTransport,
-    deprovision_git_gate,
-    provision_git_gate,
-)
+from .gateway_provision import deprovision_git_gate, provision_git_gate
 
 
 class ConsolidatedLaunchError(RuntimeError):
@@ -125,8 +121,7 @@ def launch_consolidated(
         metadata=inputs.metadata, tokens=tokens,
     )
     try:
-        provision_git_gate(
-            DockerGatewayTransport(gateway_name), reg.bottle_id, git_gate_plan)
+        provision_git_gate(gateway_name, reg.bottle_id, git_gate_plan)
     except Exception:
         # Roll the registration back so a provisioning failure leaves no orphan.
         client.teardown_bottle(reg.bottle_id)
@@ -147,7 +142,7 @@ def teardown_consolidated(
     """Deregister the bottle and remove its git-gate state from the gateway.
     Both steps are idempotent so this is safe from a cleanup trap."""
     OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
-    deprovision_git_gate(DockerGatewayTransport(gateway_name), bottle_id)
+    deprovision_git_gate(gateway_name, bottle_id)
 
 
 __all__ = [

bot_bottle/backend/docker/gateway_provision.py

@@ -15,15 +15,14 @@ bottle's push credentials out of another's repos on the shared gateway.
 from __future__ import annotations
 
 import re
-from typing import Protocol
 
 from ...docker_cmd import run_docker
 from ...git_gate import GitGatePlan, git_gate_render_provision
 
 # bottle ids index the gateway's per-bottle repo + creds dirs; they land in
-# exec/cp path arguments, so validate before any path is built (a traversal
-# id like "../etc" must never reach the gateway). Registry ids are token_hex —
-# this is defense in depth at the transport boundary.
+# `docker cp`/`rm` path arguments, so validate before any path is built (a
+# traversal id like "../etc" must never reach the container). Registry ids are
+# token_hex — this is defense in depth at the docker boundary.
 _SAFE_BOTTLE_ID = re.compile(r"[A-Za-z0-9_-]+")
 
 
@@ -31,42 +30,6 @@ class GatewayProvisionError(RuntimeError):
     """A git-gate provisioning step against the running gateway failed."""
 
 
-class GatewayTransport(Protocol):
-    """How the launcher stages files + runs commands in the running gateway.
-    Backend-neutral so the same provisioning logic serves the docker gateway
-    (exec/cp over the docker socket) and the firecracker gateway VM (over
-    SSH)."""
-
-    def exec(self, argv: list[str]) -> None:
-        """Run `argv` in the gateway, raising `GatewayProvisionError` on
-        failure."""
-
-    def cp_into(self, src: str, dest: str) -> None:
-        """Copy host file `src` to `dest` in the gateway, raising on
-        failure."""
-
-
-class DockerGatewayTransport:
-    """`GatewayTransport` for the docker gateway container (exec/cp)."""
-
-    def __init__(self, gateway: str) -> None:
-        self.gateway = gateway
-
-    def exec(self, argv: list[str]) -> None:
-        proc = run_docker(["docker", "exec", self.gateway, *argv])
-        if proc.returncode != 0:
-            raise GatewayProvisionError(
-                f"gateway exec {argv!r} failed: {proc.stderr.strip()}"
-            )
-
-    def cp_into(self, src: str, dest: str) -> None:
-        proc = run_docker(["docker", "cp", src, f"{self.gateway}:{dest}"])
-        if proc.returncode != 0:
-            raise GatewayProvisionError(
-                f"gateway cp {src} -> {dest} failed: {proc.stderr.strip()}"
-            )
-
-
 def _require_safe(bottle_id: str) -> None:
     if not _SAFE_BOTTLE_ID.fullmatch(bottle_id):
         raise GatewayProvisionError(f"unsafe bottle id {bottle_id!r}")
@@ -76,11 +39,27 @@ def _creds_dir(bottle_id: str) -> str:
     return f"/git-gate/creds/{bottle_id}"
 
 
-def provision_git_gate(
-    transport: GatewayTransport, bottle_id: str, plan: GitGatePlan,
-) -> None:
-    """Place `bottle_id`'s git-gate credentials into the running gateway and
-    init its bare repos under `/git/<bottle_id>/`.
+def _exec(gateway: str, argv: list[str]) -> None:
+    """`docker exec` a command in the gateway, raising on non-zero exit."""
+    proc = run_docker(["docker", "exec", gateway, *argv])
+    if proc.returncode != 0:
+        raise GatewayProvisionError(
+            f"gateway exec {argv!r} failed: {proc.stderr.strip()}"
+        )
+
+
+def _cp_into(gateway: str, src: str, dest: str) -> None:
+    """`docker cp` a host file into the gateway, raising on non-zero exit."""
+    proc = run_docker(["docker", "cp", src, f"{gateway}:{dest}"])
+    if proc.returncode != 0:
+        raise GatewayProvisionError(
+            f"gateway cp {src} -> {dest} failed: {proc.stderr.strip()}"
+        )
+
+
+def provision_git_gate(gateway: str, bottle_id: str, plan: GitGatePlan) -> None:
+    """Place `bottle_id`'s git-gate credentials into the running `gateway`
+    container and init its bare repos under `/git/<bottle_id>/`.
 
     Copies each upstream's identity key (and known_hosts, when present) into
     `/git-gate/creds/<bottle_id>/`, then runs the namespaced provisioning
@@ -91,36 +70,31 @@ def provision_git_gate(
     # The pre-receive + access hooks are bottle-agnostic and shared by every
     # bottle's repos; install them into the gateway (idempotent — same content
     # each time). The per-bottle model cp'd these into each bundle at start.
-    transport.exec(["mkdir", "-p", "/etc/git-gate"])
-    transport.cp_into(str(plan.hook_script), "/etc/git-gate/pre-receive")
-    transport.cp_into(str(plan.access_hook_script), "/etc/git-gate/access-hook")
+    _exec(gateway, ["mkdir", "-p", "/etc/git-gate"])
+    _cp_into(gateway, str(plan.hook_script), "/etc/git-gate/pre-receive")
+    _cp_into(gateway, str(plan.access_hook_script), "/etc/git-gate/access-hook")
     creds = _creds_dir(bottle_id)
-    transport.exec(["mkdir", "-p", creds])
+    _exec(gateway, ["mkdir", "-p", creds])
     for u in plan.upstreams:
         if u.identity_file:
-            transport.cp_into(u.identity_file, f"{creds}/{u.name}-key")
+            _cp_into(gateway, u.identity_file, f"{creds}/{u.name}-key")
         known_hosts = str(u.known_hosts_file)
         if known_hosts and known_hosts != ".":
-            transport.cp_into(known_hosts, f"{creds}/{u.name}-known_hosts")
+            _cp_into(gateway, known_hosts, f"{creds}/{u.name}-known_hosts")
     # Init the bare repos + per-repo credential config for this namespace.
     script = git_gate_render_provision(bottle_id, plan.upstreams)
-    transport.exec(["sh", "-c", script])
+    _exec(gateway, ["sh", "-c", script])
 
 
-def deprovision_git_gate(transport: GatewayTransport, bottle_id: str) -> None:
+def deprovision_git_gate(gateway: str, bottle_id: str) -> None:
     """Remove a bottle's repos + creds from the gateway on teardown. Idempotent
     — an already-absent namespace is a clean no-op (best effort; a stray dir
     can't leak, since attribution is by source IP and the bottle is gone)."""
     _require_safe(bottle_id)
-    try:
-        transport.exec([
-            "rm", "-rf", f"/git/{bottle_id}", _creds_dir(bottle_id),
-        ])
-    except GatewayProvisionError:
-        pass  # best-effort teardown; absent namespace is success
+    run_docker([
+        "docker", "exec", gateway, "rm", "-rf",
+        f"/git/{bottle_id}", _creds_dir(bottle_id),
+    ])
 
 
-__all__ = [
-    "provision_git_gate", "deprovision_git_gate",
-    "GatewayProvisionError", "GatewayTransport", "DockerGatewayTransport",
-]
+__all__ = ["provision_git_gate", "deprovision_git_gate", "GatewayProvisionError"]

bot_bottle/backend/docker/launch.py

@@ -167,7 +167,6 @@ def launch(
             egress_plan=egress_plan,
             agent_git_gate_url=git_gate_url,
             agent_supervise_url=supervise_url,
-            identity_token=ctx.identity_token,
         )
 
         # Step 5: render + up the agent-only compose, pinned on the shared

bot_bottle/backend/firecracker/backend.py

@@ -110,7 +110,3 @@ class FirecrackerBottleBackend(
 
     def supervise_mcp_url(self, plan: FirecrackerBottlePlan) -> str:
         return plan.agent_supervise_url
-
-    def ensure_orchestrator(self) -> str:
-        from . import infra_vm
-        return infra_vm.ensure_running().control_plane_url

bot_bottle/backend/firecracker/bottle.py

@@ -105,9 +105,10 @@ class FirecrackerBottle(Bottle):
         # root-owned and unreadable by node, which breaks Node's
         # process.cwd(), the shell-snapshot machinery, and `/doctor`.
         # Use `env --chdir` rather than a `sh -c 'cd … && exec "$@"'`
-        # wrapper: it keeps the guest command a flat argv that `agent_argv`
-        # can quote token-by-token for the ssh→guest-shell round trip,
-        # avoiding a fragile nested-quoting `"$@"` script.
+        # wrapper: ssh space-joins everything after the host into one
+        # string for the guest shell, so a quoted script + $@ would be
+        # re-split and mangled (exec'ing the $0 placeholder). All-simple
+        # words survive that join.
         workdir = self.agent_workdir or _HOME_FOR["node"]
         remote = ["runuser", "-u", "node", "--",
                   "env", f"--chdir={workdir}",
@@ -116,15 +117,7 @@ class FirecrackerBottle(Bottle):
         return remote
 
     def agent_argv(self, argv: list[str], *, tty: bool = True) -> list[str]:
-        # ssh space-joins everything after the host into one line the guest
-        # shell re-parses, so pre-quote each remote token for that shell.
-        # Simple words are unchanged (existing behaviour); an arg containing
-        # spaces — e.g. codex's `read_prompt_file` positional "Read and follow
-        # the instructions in <path>." — is quoted so it survives as ONE
-        # argument instead of being re-split (which made codex parse "and" as
-        # a subcommand).
-        remote = self._agent_remote_argv(argv)
-        return [*self._ssh(tty=tty), "--", *(shlex.quote(t) for t in remote)]
+        return [*self._ssh(tty=tty), "--", *self._agent_remote_argv(argv)]
 
     def exec_agent(self, argv: list[str], *, tty: bool = True) -> int:
         agent_argv = self.agent_argv(argv, tty=tty)

bot_bottle/backend/firecracker/bottle_plan.py

@@ -18,10 +18,6 @@ class FirecrackerBottlePlan(BottlePlan):
     agent_proxy_url: str = ""
     agent_git_gate_url: str = ""
     agent_supervise_url: str = ""
-    # Per-bottle identity token the agent presents on every attributed request
-    # (egress proxy credentials, git-gate/supervise headers); set by launch
-    # from the orchestrator registration. Empty pre-registration.
-    identity_token: str = ""
 
     @property
     def container_name(self) -> str:

bot_bottle/backend/firecracker/consolidated_launch.py

@@ -1,23 +1,27 @@
-"""Consolidated bottle launch sequence for the Firecracker backend
-(PRD 0070, Stage B).
+"""Consolidated bottle launch sequence for the Firecracker backend (PRD 0070).
 
-The shared gateway + orchestrator control plane run in a single persistent
-per-host **infra VM** (`infra_vm.py`), not Docker containers. Agent VMs reach
-the gateway's egress / supervise / git-http ports at the infra VM via a
-PREROUTING DNAT on their own host-side TAP IP (see
-`scripts/firecracker-netpool.sh`), and the host CLI reaches the control plane
-over HTTP at the infra VM's guest IP.
+Mirrors bot_bottle.backend.docker.consolidated_launch but wired for
+Firecracker's TAP-based network topology instead of a shared Docker bridge.
 
-Attribution is by the agent VM's guest IP, unspoofable by construction: the
-/31 point-to-point TAP + the `bot_bottle_fc` nft table ensure only the
-expected VM can source-IP that address.
+The per-bottle sidecar bundle (one `docker run` per bottle, published on the
+slot's host-side TAP IP) is replaced by a single persistent gateway that
+every Firecracker VM shares. The gateway runs as a Docker container in the
+dev-harness (a Firecracker VM is stage B per PRD 0070), with its ports
+published on the host (`0.0.0.0:PORT`). VMs reach it at their slot's
+host-side TAP IP because Docker's iptables PREROUTING DNAT redirects
+port 9099/9100/9420 traffic to the gateway container — a path the nft
+isolation table already allows via `ct status dnat accept` in the forward
+chain.
+
+Attribution is by the VM's guest IP, which is unspoofable by construction:
+the /31 point-to-point TAP topology + the `bot_bottle_fc` nft table ensure
+that only the expected VM can source-IP that address.
 
 Sequence:
-  1. ensure the infra VM (control plane + gateway) is up (a singleton — a
-     prior launcher may already have booted it);
+  1. ensure the Firecracker-flavoured orchestrator + gateway are up;
   2. register the bottle by its guest IP (attribution key) → bottle id +
      identity token;
-  3. provision its git-gate repos/creds into the gateway VM (over SSH);
+  3. provision its git-gate repos/creds into the running gateway;
   4. fetch the shared gateway CA for the provisioner to install in the rootfs.
 
 The TAP slot allocation, rootfs build, and VM boot are the caller's job.
@@ -30,12 +34,30 @@ from dataclasses import dataclass
 from ...egress import EgressPlan
 from ...git_gate import GitGatePlan
 from ...orchestrator.client import OrchestratorClient
+from ...orchestrator.gateway import (
+    GATEWAY_NETWORK,
+    DockerGateway,
+)
 from ...orchestrator.lifecycle import (
+    OrchestratorService,
     OrchestratorStartError,  # re-exported so callers can catch it
 )
 from ...orchestrator.registration import registration_inputs
+from ..docker.egress import EGRESS_PORT
 from ..docker.gateway_provision import deprovision_git_gate, provision_git_gate
-from . import infra_vm
+from ...supervise import SUPERVISE_PORT
+
+_GIT_HTTP_PORT = 9420
+
+# Separate names from the Docker gateway so both backends can coexist on one
+# host (and for clarity in `docker ps` output).
+_FC_GATEWAY_NAME = "bot-bottle-fc-gateway"
+_FC_ORCHESTRATOR_NAME = "bot-bottle-fc-orchestrator"
+_FC_ORCHESTRATOR_LABEL = "bot-bottle-fc-orchestrator=1"
+# Ports the gateway publishes on the host so Firecracker VMs can reach it
+# via their TAP link. Docker's PREROUTING DNAT + nft's `ct status dnat
+# accept` in the forward chain route the traffic.
+_FC_GATEWAY_HOST_PORTS = (EGRESS_PORT, SUPERVISE_PORT, _GIT_HTTP_PORT)
 
 
 class ConsolidatedLaunchError(RuntimeError):
@@ -53,6 +75,33 @@ class LaunchContext:
     orchestrator_url: str
 
 
+class _FirecrackerOrchestratorService(OrchestratorService):
+    """Dev-harness orchestrator for the Firecracker backend.
+
+    Uses a gateway that publishes its ports on the host so Firecracker VMs can
+    reach it via their TAP link. The gateway and orchestrator containers use
+    `*-fc-*` names so both backends can run independently on the same host.
+    """
+
+    def __init__(self, **kwargs: object) -> None:
+        super().__init__(
+            orchestrator_name=_FC_ORCHESTRATOR_NAME,
+            orchestrator_label=_FC_ORCHESTRATOR_LABEL,
+            **kwargs,  # type: ignore[arg-type]
+        )
+
+    def _gateway(self) -> DockerGateway:
+        # The heavy data-plane image (#384 split it from the lean control-plane
+        # `image` this service's orchestrator container runs).
+        return DockerGateway(
+            self._gateway_image,
+            name=_FC_GATEWAY_NAME,
+            network=self.network,
+            orchestrator_url=self.internal_url,
+            host_port_bindings=_FC_GATEWAY_HOST_PORTS,
+        )
+
+
 def launch_consolidated(
     egress_plan: EgressPlan,
     git_gate_plan: GitGatePlan,
@@ -60,12 +109,15 @@ def launch_consolidated(
     guest_ip: str,
     image_ref: str = "",
     tokens: dict[str, str] | None = None,
+    service: OrchestratorService | None = None,
+    gateway_name: str = _FC_GATEWAY_NAME,
 ) -> LaunchContext:
-    """Ensure the infra VM is up, register the bottle by its guest IP, and
-    provision its git-gate state into the gateway VM. Returns the context the
-    agent-VM launch needs. Raises on failure — the caller tears down."""
-    infra = infra_vm.ensure_running()
-    url = infra.control_plane_url
+    """Ensure the orchestrator + Firecracker gateway are up, register the
+    bottle by its guest IP, and provision its git-gate state. Returns the
+    context the VM launch needs. Raises `ConsolidatedLaunchError` (or the
+    primitives' own errors) on failure — the caller tears down on failure."""
+    service = service or _FirecrackerOrchestratorService()
+    url = service.ensure_running()
     client = OrchestratorClient(url)
 
     inputs = registration_inputs(egress_plan)
@@ -74,30 +126,33 @@ def launch_consolidated(
         metadata=inputs.metadata, tokens=tokens,
     )
     try:
-        provision_git_gate(
-            infra_vm.gateway_transport(), reg.bottle_id, git_gate_plan)
+        provision_git_gate(gateway_name, reg.bottle_id, git_gate_plan)
     except Exception:
         client.teardown_bottle(reg.bottle_id)
         raise
 
-    # The shared gateway CA every agent on this host trusts for TLS
-    # interception — fetched from the infra VM over SSH.
+    # Fetch the shared gateway CA here so the caller can install it in the
+    # rootfs (the same CA every agent on this host trusts for TLS interception).
+    gateway_ca_pem = DockerGateway(
+        name=gateway_name, network=GATEWAY_NETWORK,
+    ).ca_cert_pem()
+
     return LaunchContext(
         bottle_id=reg.bottle_id,
         identity_token=reg.identity_token,
         source_ip=guest_ip,
-        gateway_ca_pem=infra.gateway_ca_pem(),
+        gateway_ca_pem=gateway_ca_pem,
         orchestrator_url=url,
     )
 
 
-def teardown_consolidated(bottle_id: str, *, orchestrator_url: str) -> None:
-    """Deregister the bottle and remove its git-gate state from the gateway
-    VM. Both steps are idempotent so this is safe from a cleanup trap. Does
-    NOT stop the infra VM — it's a persistent per-host singleton shared by
-    every bottle."""
+def teardown_consolidated(
+    bottle_id: str, *, orchestrator_url: str, gateway_name: str = _FC_GATEWAY_NAME,
+) -> None:
+    """Deregister the bottle and remove its git-gate state from the gateway.
+    Both steps are idempotent so this is safe from a cleanup trap."""
     OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
-    deprovision_git_gate(infra_vm.gateway_transport(), bottle_id)
+    deprovision_git_gate(gateway_name, bottle_id)
 
 
 __all__ = [

bot_bottle/backend/firecracker/firecracker_vm.py

@@ -78,32 +78,20 @@ def _config(
     vcpus: int,
     mem_mib: int,
     guest_mac: str,
-    data_drive: Path | None = None,
 ) -> dict[str, object]:
-    drives: list[dict[str, object]] = [
-        {
-            "drive_id": "rootfs",
-            "path_on_host": str(rootfs),
-            "is_root_device": True,
-            "is_read_only": False,
-        }
-    ]
-    # A second virtio-block device (guest /dev/vdb) — the infra VM's
-    # persistent registry "volume", a host-side ext4 file that outlives the
-    # ephemeral rootfs across VM restarts.
-    if data_drive is not None:
-        drives.append({
-            "drive_id": "data",
-            "path_on_host": str(data_drive),
-            "is_root_device": False,
-            "is_read_only": False,
-        })
     return {
         "boot-source": {
             "kernel_image_path": str(util.kernel_path()),
             "boot_args": _boot_args(guest_ip, host_ip, pubkey),
         },
-        "drives": drives,
+        "drives": [
+            {
+                "drive_id": "rootfs",
+                "path_on_host": str(rootfs),
+                "is_root_device": True,
+                "is_read_only": False,
+            }
+        ],
         "network-interfaces": [
             {
                 "iface_id": "eth0",
@@ -130,16 +118,9 @@ def boot(
     vcpus: int = 2,
     mem_mib: int = 2048,
     guest_mac: str = "06:00:AC:10:00:02",
-    detached: bool = False,
-    data_drive: Path | None = None,
 ) -> VmHandle:
     """Write the config and launch the VMM. Returns once the process is
-    spawned; callers wait for SSH readiness separately.
-
-    `detached` starts the VMM in its own session (`start_new_session`) so it
-    survives the launcher exiting — used for the persistent per-host infra
-    VM, which must outlive the short-lived `start` process (agent VMs stay
-    attached and are torn down with the launcher)."""
+    spawned; callers wait for SSH readiness separately."""
     run_dir.mkdir(parents=True, exist_ok=True)
     config_path = run_dir / "config.json"
     console_log = run_dir / "console.log"
@@ -147,7 +128,6 @@ def boot(
         _config(
             rootfs=rootfs, tap=tap, guest_ip=guest_ip, host_ip=host_ip,
             pubkey=pubkey, vcpus=vcpus, mem_mib=mem_mib, guest_mac=guest_mac,
-            data_drive=data_drive,
         ),
         indent=2,
     ))
@@ -157,7 +137,6 @@ def boot(
     process = subprocess.Popen(
         ["firecracker", "--no-api", "--config-file", str(config_path)],
         stdout=log_fh, stderr=subprocess.STDOUT, stdin=subprocess.DEVNULL,
-        start_new_session=detached,
     )
     return VmHandle(process=process, guest_ip=guest_ip, console_log=console_log)
 

bot_bottle/backend/firecracker/freezer.py

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

bot_bottle/backend/firecracker/image_builder.py

@@ -1,224 +0,0 @@
-"""Docker-free agent-image builds for the Firecracker backend (PRD 0069 Stage 3).
-
-Agent Dockerfiles build **inside the persistent per-host infra VM**
-(`infra_vm.py`), which carries buildah (rootless, daemonless): no host Docker
-daemon, no root-equivalent `docker` group. The build runs over SSH against the
-infra VM and its rootfs streams back to the host, where the existing
-`mke2fs -d` path (`util.build_rootfs_ext4`) turns it into a bootable ext4.
-
-Building in the infra VM — rather than a throwaway builder VM — means there is
-one buildah image (`bot-bottle-infra`) and no contention for the orchestrator
-TAP. Tradeoff: an untrusted Dockerfile's `RUN` steps share the VM with the
-control plane + gateway (buildah `--isolation chroot` isn't a hard boundary) —
-the accepted single-VM blast-radius tradeoff, re-splittable into a disposable
-builder (booted from this same image on its own TAP) later.
-"""
-
-from __future__ import annotations
-
-import fcntl
-import hashlib
-import os
-import shutil
-import subprocess
-from contextlib import contextmanager
-from pathlib import Path
-from typing import Generator
-
-from ...log import die, info
-from . import infra_vm, util
-
-# vfs + chroot: buildah works as root in the microVM (no fuse-overlayfs /
-# overlay module / subuid maps). `--isolation` is a build/run-only flag;
-# `from`/`mount` take just the store.
-_BUILD_FLAGS = "--isolation chroot --storage-driver vfs"
-_STORE_FLAG = "--storage-driver vfs"
-
-_BUILD_TIMEOUT_SECONDS = 900.0
-
-
-def _dockerfile_hash(dockerfile: Path) -> str:
-    """Cache key: the Dockerfile's content. The shipped agent Dockerfiles
-    COPY nothing from the build context (see .dockerignore), so their content
-    fully determines the image; a Dockerfile that adds COPY will want the
-    context folded in here too."""
-    return hashlib.sha256(dockerfile.read_bytes()).hexdigest()[:16]
-
-
-def build_agent_rootfs_dir(
-    dockerfile: Path, *, image_tag: str, smoke_test: tuple[str, ...] = (),
-) -> Path:
-    """Build `dockerfile` in the infra VM (buildah, no host docker), export its
-    rootfs, inject the guest boot bits, and return the cached base dir — the
-    same shape `util.build_rootfs_ext4` consumes. Cached by Dockerfile content,
-    so a repeat launch skips the rebuild.
-
-    `smoke_test` (the provider's declared argv, e.g. `("claude","--version")`)
-    is run in the freshly built image before export, catching an npm
-    silent-failure image at build time rather than at first agent use."""
-    digest = _dockerfile_hash(dockerfile)
-    base = util.cache_dir() / "rootfs" / f"agent-{digest}"
-    if (base / ".bb-ready").is_file():
-        info(f"using cached agent rootfs {base.name}")
-        return base
-
-    # Serialize builds: the infra VM's buildah store + this cache dir are
-    # shared, so concurrent `start`s must not build into them at once. The
-    # lock covers the cache lookup + build + atomic publish; the ready
-    # fast-path above takes no lock.
-    with _build_lock():
-        if (base / ".bb-ready").is_file():  # another build finished while we waited
-            info(f"using cached agent rootfs {base.name}")
-            return base
-        # Build into a temp dir and publish by atomic rename, so a partial
-        # build is never visible as `agent-<digest>`.
-        staging = util.cache_dir() / "rootfs" / f".building-{digest}"
-        shutil.rmtree(staging, ignore_errors=True)
-        staging.mkdir(parents=True)
-        info(f"building agent image {image_tag!r} in the infra VM")
-        _build_in_infra(dockerfile, staging, smoke_test, digest)
-        util.inject_guest_boot(staging)
-        (staging / ".bb-ready").write_text("ok\n")
-        shutil.rmtree(base, ignore_errors=True)
-        os.rename(staging, base)
-    return base
-
-
-@contextmanager
-def _build_lock() -> Generator[None, None, None]:
-    """Host-level exclusive lock serializing agent-image builds (shared infra
-    buildah store + cache dir). flock auto-releases on a crash."""
-    lock_path = util.cache_dir() / "rootfs" / ".build.lock"
-    lock_path.parent.mkdir(parents=True, exist_ok=True)
-    handle = open(lock_path, "w", encoding="utf-8")
-    try:
-        fcntl.flock(handle, fcntl.LOCK_EX)
-        yield
-    finally:
-        handle.close()
-
-
-def _build_in_infra(
-    dockerfile: Path, base: Path, smoke_test: tuple[str, ...], digest: str,
-) -> None:
-    """Ensure the infra VM is up, `buildah build` the Dockerfile in it, smoke
-    test the image, and stream its rootfs into `base`. The infra VM persists;
-    only the per-build container/image/context are cleaned up."""
-    infra = infra_vm.ensure_running()
-    key, ip = infra.private_key, infra.guest_ip
-    tag = f"bot-bottle-agent-build-{digest}"
-    ctx = f"/tmp/agent-build-{digest}"
-    smoke_ctr, export_ctr = f"{tag}-smoke", f"{tag}-export"
-
-    def _cleanup() -> None:
-        # Remove only THIS build's working containers/image/context — never
-        # `buildah rm -a`, which would nuke a concurrent build's container.
-        _ssh(key, ip,
-             f"buildah rm {smoke_ctr} {export_ctr} >/dev/null 2>&1; "
-             f"buildah rmi {_STORE_FLAG} {tag} >/dev/null 2>&1; rm -rf {ctx}",
-             timeout=60)
-
-    _cleanup()  # clear leftovers from a crashed prior build of this digest
-    try:
-        prep = _ssh(key, ip, f"mkdir -p {ctx}/ctx")
-        if prep.returncode != 0:
-            die(f"preparing build dir in the infra VM failed: {prep.stderr.strip()}")
-        _send_dockerfile(key, ip, dockerfile, ctx)
-        _buildah_build(key, ip, ctx, tag)
-        _smoke_test(key, ip, tag, smoke_ctr, smoke_test)
-        _stream_rootfs(key, ip, tag, export_ctr, base)
-    finally:
-        _cleanup()
-
-
-def _ssh(private_key: Path, guest_ip: str, script: str,
-         *, timeout: float = 60.0) -> subprocess.CompletedProcess[str]:
-    return subprocess.run(
-        util.ssh_base_argv(private_key, guest_ip) + [script],
-        capture_output=True, text=True, timeout=timeout, check=False,
-    )
-
-
-def _ssh_streamed(private_key: Path, guest_ip: str, script: str,
-                  *, timeout: float) -> int:
-    """Run an SSH command letting the remote's stdout/stderr flow straight to
-    ours (no capture), for long chatty steps where live progress beats a
-    silent wait. Returns the exit code."""
-    proc = subprocess.run(
-        util.ssh_base_argv(private_key, guest_ip) + [script],
-        timeout=timeout, check=False,
-    )
-    return proc.returncode
-
-
-def _send_dockerfile(private_key: Path, guest_ip: str, dockerfile: Path, ctx: str) -> None:
-    proc = subprocess.run(
-        util.ssh_base_argv(private_key, guest_ip) + [f"cat > {ctx}/Dockerfile"],
-        input=dockerfile.read_bytes(), capture_output=True, timeout=30, check=False,
-    )
-    if proc.returncode != 0:
-        die(f"sending Dockerfile to the infra VM failed: "
-            f"{proc.stderr.decode(errors='replace').strip()}")
-
-
-def _buildah_build(private_key: Path, guest_ip: str, ctx: str, tag: str) -> None:
-    # Stream buildah's step-by-step output straight to our stderr (like the
-    # docker backend's `docker build`), so a long first build (base pull +
-    # apt/npm installs) shows live progress instead of a silent wait. The
-    # remote stderr is where buildah writes its `STEP i/n` lines.
-    info(f"buildah build {tag} in the infra VM (streaming output)")
-    rc = _ssh_streamed(
-        private_key, guest_ip,
-        f"buildah build {_BUILD_FLAGS} -t {tag} -f {ctx}/Dockerfile {ctx}/ctx",
-        timeout=_BUILD_TIMEOUT_SECONDS,
-    )
-    if rc != 0:
-        die(f"buildah build in the infra VM failed (exit {rc}); "
-            "see the build output above.")
-
-
-def _smoke_test(private_key: Path, guest_ip: str, tag: str, ctr: str,
-                argv: tuple[str, ...]) -> None:
-    """Run the provider's smoke argv inside the freshly built image
-    (`buildah run`, which uses the image's own PATH), failing the build
-    loudly if the CLI is a broken stub. No-op without a declared test. Uses a
-    named working container (`ctr`) so cleanup is scoped to this build."""
-    if not argv:
-        return
-    cmd = (
-        f"set -e; buildah from {_STORE_FLAG} --name {ctr} {tag} >/dev/null; "
-        f"buildah run {_BUILD_FLAGS} {ctr} -- {' '.join(argv)}; rc=$?; "
-        f"buildah rm {ctr} >/dev/null 2>&1 || true; exit $rc"
-    )
-    result = _ssh(private_key, guest_ip, cmd, timeout=120)
-    if result.returncode != 0:
-        detail = (result.stdout + result.stderr).strip().splitlines()[-10:]
-        die(f"agent image failed its post-build smoke test "
-            f"({' '.join(argv)}):\n" + "\n".join(detail))
-
-
-def _stream_rootfs(private_key: Path, guest_ip: str, tag: str, ctr: str, base: Path) -> None:
-    """`buildah mount` the built image in the infra VM and pipe its rootfs tar
-    straight into `base` on the host (extracted as the non-root host user, so
-    uid 0 isn't preserved — the guest init restores /root ownership). Uses a
-    named working container so cleanup is scoped to this build."""
-    export = (
-        f"set -e; buildah from {_STORE_FLAG} --name {ctr} {tag} >/dev/null; "
-        f"mnt=$(buildah mount {_STORE_FLAG} {ctr}); "
-        f"tar -C \"$mnt\" -cf - ."
-    )
-    ssh_proc = subprocess.Popen(
-        util.ssh_base_argv(private_key, guest_ip) + [export],
-        stdout=subprocess.PIPE, stderr=subprocess.PIPE,
-    )
-    assert ssh_proc.stdout is not None
-    untar = subprocess.run(
-        ["tar", "-x", "-C", str(base)], stdin=ssh_proc.stdout, check=False,
-    )
-    ssh_proc.stdout.close()
-    ssh_err = (ssh_proc.stderr.read().decode(errors="replace")
-               if ssh_proc.stderr else "")
-    rc = ssh_proc.wait()
-    if rc != 0 or untar.returncode != 0:
-        die(f"exporting the built rootfs from the infra VM failed: "
-            f"{ssh_err.strip() or '<no stderr>'}")

bot_bottle/backend/firecracker/infra_artifact.py

@@ -1,199 +0,0 @@
-"""Prebuilt infra-VM rootfs, pulled as an artifact (PRD 0069 Stage 2).
-
-The Firecracker infra VM boots a fixed rootfs (orchestrator control plane +
-gateway + buildah, control-plane init as PID 1) that does not vary per launch —
-the per-boot bits (authorized_keys, guest IP) ride the kernel cmdline, so one
-rootfs boots on any host. Instead of building that rootfs on the launch host
-with Docker, we build it **off-host** and publish it as a versioned, ready-to-
-boot ext4 (gzip-compressed) to a Gitea **generic package**; the launch host
-downloads + verifies + boots it. No Docker, no image tooling on the launch
-host — just an HTTP fetch and gunzip.
-
-  publish (off-host, see publish_infra.py):
-    docker build -> rootfs dir -> mke2fs -> gzip -> PUT generic package
-  pull (this module, launch host):
-    GET .../rootfs.ext4.gz (+ .sha256) -> verify -> gunzip -> boot
-
-The artifact **version** is a content hash of everything baked into the rootfs
-(the shipped bot_bottle package, the three Dockerfiles, and the init), so a
-launch host always pulls the artifact matching its code and a content change
-can't silently boot a stale rootfs. A checksum mismatch fails closed.
-
-Set `BOT_BOTTLE_INFRA_BUILD=local` to skip the pull and build the rootfs
-locally with Docker (dev iteration on the Dockerfiles) — see `infra_vm`.
-"""
-
-from __future__ import annotations
-
-import gzip
-import hashlib
-import os
-import shutil
-import urllib.error
-import urllib.request
-from pathlib import Path
-
-from ...log import die, info
-from . import util
-
-# Bump if the on-disk artifact *format* changes (compression, layout) so a new
-# scheme can't collide with a cached/published artifact of the old one.
-_ARTIFACT_FORMAT = "1"
-
-_REPO_ROOT = Path(__file__).resolve().parents[3]
-_DOCKERFILES = ("Dockerfile.orchestrator", "Dockerfile.gateway", "Dockerfile.infra")
-
-_DEFAULT_BASE = "https://gitea.dideric.is"
-_DEFAULT_OWNER = "didericis"
-_PACKAGE = "bot-bottle-firecracker-infra"
-
-# Streaming copy chunk for the (hundreds-of-MB) download.
-_CHUNK = 1 << 20
-
-
-def local_build_requested() -> bool:
-    """True when the operator opted into the dev Docker-build path instead of
-    pulling the published artifact (`BOT_BOTTLE_INFRA_BUILD=local`)."""
-    return os.environ.get("BOT_BOTTLE_INFRA_BUILD", "").strip().lower() == "local"
-
-
-def infra_artifact_version(init_script: str, *, repo_root: Path = _REPO_ROOT) -> str:
-    """Content hash (16 hex) of everything baked into the infra rootfs: the
-    whole shipped `bot_bottle` package, the three fixed Dockerfiles, and the
-    guest init. Deterministic across the publish host and the launch host when
-    both run the same checkout, so the tag the launch host pulls is exactly the
-    tag publish produced.
-
-    The package is `COPY bot_bottle /app/bot_bottle`'d wholesale into the image,
-    so hash *every* regular file under it — not just `*.py`. Non-Python inputs
-    (e.g. `egress_entrypoint.sh`, `netpool.defaults.env`) are baked in too, and
-    a change to one must bump the version or a launch host could boot a stale
-    rootfs whose code differs from its checkout. `__pycache__`/`.pyc` are the
-    only exclusions — build artifacts, never copied."""
-    h = hashlib.sha256()
-    h.update(f"format={_ARTIFACT_FORMAT}\n".encode())
-    pkg = repo_root / "bot_bottle"
-    for path in sorted(pkg.rglob("*")):
-        if not path.is_file():
-            continue
-        if "__pycache__" in path.parts or path.suffix == ".pyc":
-            continue
-        h.update(str(path.relative_to(repo_root)).encode())
-        h.update(b"\0")
-        h.update(path.read_bytes())
-    for name in _DOCKERFILES:
-        h.update(name.encode())
-        h.update(b"\0")
-        h.update((repo_root / name).read_bytes())
-    h.update(b"init\0")
-    h.update(init_script.encode())
-    return h.hexdigest()[:16]
-
-
-def _config() -> tuple[str, str, str]:
-    """(base_url, owner, token) for the generic-package endpoint. Base + owner
-    are overridable for other deployments / mirrors; the token comes solely from
-    `BOT_BOTTLE_INFRA_ARTIFACT_TOKEN` (a dedicated package-scoped token, kept
-    separate from the general-purpose Gitea token) and is optional — a public
-    package needs none to pull."""
-    base = os.environ.get("BOT_BOTTLE_INFRA_ARTIFACT_BASE", _DEFAULT_BASE).rstrip("/")
-    owner = os.environ.get("BOT_BOTTLE_INFRA_ARTIFACT_OWNER", _DEFAULT_OWNER)
-    token = os.environ.get("BOT_BOTTLE_INFRA_ARTIFACT_TOKEN", "")
-    return base, owner, token
-
-
-def artifact_url(version: str, filename: str) -> str:
-    """The generic-package download URL for one file of this version's
-    artifact (`rootfs.ext4.gz` / `rootfs.ext4.gz.sha256`)."""
-    base, owner, _ = _config()
-    return f"{base}/api/packages/{owner}/generic/{_PACKAGE}/{version}/{filename}"
-
-
-_GZ_NAME = "rootfs.ext4.gz"
-_SHA_NAME = "rootfs.ext4.gz.sha256"
-
-
-def _cache_root(version: str) -> Path:
-    return util.cache_dir() / "infra-artifact" / version
-
-
-def _open(url: str) -> urllib.request.Request:
-    _, _, token = _config()
-    req = urllib.request.Request(url)
-    if token:
-        req.add_header("Authorization", f"token {token}")
-    return req
-
-
-def _download(url: str, dest: Path) -> None:
-    """Stream `url` to `dest` (atomic via a `.part` sibling)."""
-    tmp = dest.with_suffix(dest.suffix + ".part")
-    try:
-        with urllib.request.urlopen(_open(url)) as resp, open(tmp, "wb") as out:
-            shutil.copyfileobj(resp, out, _CHUNK)
-    except urllib.error.HTTPError as e:
-        tmp.unlink(missing_ok=True)
-        if e.code == 404:
-            die(
-                f"infra artifact not published for this code version.\n"
-                f"    missing: {url}\n"
-                f"    publish it from a build host (Docker):\n"
-                f"        python3 -m bot_bottle.backend.firecracker.publish_infra\n"
-                f"    or build the rootfs locally: BOT_BOTTLE_INFRA_BUILD=local"
-            )
-        die(f"downloading infra artifact failed (HTTP {e.code}): {url}")
-    except urllib.error.URLError as e:
-        tmp.unlink(missing_ok=True)
-        die(f"infra artifact registry unreachable: {url} ({e.reason})")
-    tmp.replace(dest)
-
-
-def _sha256_file(path: Path) -> str:
-    h = hashlib.sha256()
-    with open(path, "rb") as fh:
-        for chunk in iter(lambda: fh.read(_CHUNK), b""):
-            h.update(chunk)
-    return h.hexdigest()
-
-
-def ensure_artifact_gz(version: str) -> Path:
-    """The verified, cached `rootfs.ext4.gz` for `version` — downloading it (and
-    its `.sha256`) once, then reusing it. Fail-closed on a checksum mismatch:
-    the partial is removed and we die rather than boot an unverified rootfs."""
-    root = _cache_root(version)
-    root.mkdir(parents=True, exist_ok=True)
-    gz = root / _GZ_NAME
-    ok = root / ".verified"
-    if gz.is_file() and ok.is_file():
-        return gz
-
-    info(f"pulling infra rootfs artifact {_PACKAGE}/{version}")
-    _download(artifact_url(version, _GZ_NAME), gz)
-    sha = root / _SHA_NAME
-    _download(artifact_url(version, _SHA_NAME), sha)
-
-    expected = sha.read_text().split()[0].strip().lower()
-    actual = _sha256_file(gz)
-    if actual != expected:
-        gz.unlink(missing_ok=True)
-        sha.unlink(missing_ok=True)
-        die(
-            f"infra artifact checksum mismatch for {version}:\n"
-            f"    expected {expected}\n"
-            f"    actual   {actual}\n"
-            f"    refusing to boot an unverified rootfs."
-        )
-    ok.write_text("ok\n")
-    return gz
-
-
-def materialize_ext4(version: str, dest: Path) -> None:
-    """Ensure the verified artifact is cached, then gunzip it to `dest` — a
-    fresh, writable per-boot rootfs (the VM mutates it; the cached `.gz` stays
-    pristine). Atomic via a `.part` sibling."""
-    gz = ensure_artifact_gz(version)
-    tmp = dest.with_suffix(dest.suffix + ".part")
-    info(f"expanding infra rootfs -> {dest}")
-    with gzip.open(gz, "rb") as src, open(tmp, "wb") as out:
-        shutil.copyfileobj(src, out, _CHUNK)
-    tmp.replace(dest)

bot_bottle/backend/firecracker/infra_vm.py

@@ -1,440 +0,0 @@
-"""The per-host infra VM for the Firecracker backend (PRD 0070 Stage B).
-
-A single persistent microVM that runs the orchestrator **control plane** (and,
-in a following step, the gateway **data plane**) — the trusted per-host service
-the docker backend runs as containers. It boots on the NAT'd orchestrator link
-(`netpool.orch_slot()`): the host CLI reaches its control plane over HTTP at the
-guest IP, and agent VMs reach its gateway ports over VM-to-VM routing.
-
-Build-from-source (the default while the design churns): the rootfs is exported
-from the locally built orchestrator image, which bakes the stdlib-only
-control-plane source. A pull-from-registry mode (Gitea's OCI registry) becomes
-the default later.
-
-SSH is left enabled for debugging; the control plane is the load-bearing
-surface.
-"""
-
-from __future__ import annotations
-
-import fcntl
-import hashlib
-import os
-import shlex
-import signal
-import stat
-import subprocess
-import time
-import urllib.error
-import urllib.request
-from contextlib import contextmanager
-from dataclasses import dataclass
-from pathlib import Path
-from typing import Generator
-
-from ...log import die, info
-from ..docker import util as docker_mod
-from ..docker.gateway_provision import GatewayProvisionError
-from . import firecracker_vm, infra_artifact, netpool, util
-
-# The single infra-VM image: gateway data plane + baked control-plane source
-# (Dockerfile.infra FROM the gateway image). Built from source by default;
-# a pull-from-registry mode lands later.
-_INFRA_IMAGE = "bot-bottle-infra:latest"
-_GATEWAY_IMAGE = "bot-bottle-gateway:latest"
-_ORCHESTRATOR_IMAGE = "bot-bottle-orchestrator:latest"
-_REPO_ROOT = Path(__file__).resolve().parents[3]
-
-CONTROL_PLANE_PORT = 8099
-# Gateway data-plane ports (agent-facing): egress proxy, supervise MCP,
-# git-http. Reached by agent VMs over VM-to-VM routing (added next).
-EGRESS_PORT = 9099
-SUPERVISE_PORT = 9100
-GIT_HTTP_PORT = 9420
-# mitmproxy writes its CA here a beat after start; agents install it to trust
-# the gateway's TLS interception.
-_GATEWAY_CA_PATH = "/home/mitmproxy/.mitmproxy/mitmproxy-ca-cert.pem"
-
-# The infra VM makes direct upstream connections (gateway egress, and buildah
-# during builds), and the kernel `ip=` cmdline sets no resolver. Public for
-# now; routing DNS through a filtered path is a later refinement.
-_INFRA_RESOLVER = "1.1.1.1"
-
-_HEALTH_TIMEOUT_SECONDS = 45.0
-_HEALTH_POLL_SECONDS = 0.5
-_CA_TIMEOUT_SECONDS = 30.0
-
-
-@dataclass
-class InfraVm:
-    """A handle to the per-host infra VM: its guest IP and the stable SSH key
-    used to fetch the gateway CA / provision git-gate. `vm` is the live VMM
-    handle when this process booted it, and None when adopting a singleton a
-    prior launcher started (teardown then goes through the PID file)."""
-
-    guest_ip: str
-    private_key: Path
-    vm: firecracker_vm.VmHandle | None = None
-
-    @property
-    def control_plane_url(self) -> str:
-        return f"http://{self.guest_ip}:{CONTROL_PLANE_PORT}"
-
-    def terminate(self) -> None:
-        """Stop the infra VM — via the live handle if we booted it, else the
-        PID file (adopting-process case)."""
-        if self.vm is not None:
-            self.vm.terminate()
-        else:
-            _kill_pidfile()
-        _pid_file().unlink(missing_ok=True)
-
-    def gateway_ca_pem(self, *, timeout: float = _CA_TIMEOUT_SECONDS) -> str:
-        """The gateway's mitmproxy CA (PEM) that agents install to trust its
-        TLS interception. Generated a moment after boot, so this polls over
-        SSH until it appears (mirrors DockerGateway.ca_cert_pem)."""
-        deadline = time.monotonic() + timeout
-        while True:
-            proc = subprocess.run(
-                util.ssh_base_argv(self.private_key, self.guest_ip)
-                + [f"cat {_GATEWAY_CA_PATH}"],
-                capture_output=True, text=True, timeout=15, check=False,
-            )
-            if proc.returncode == 0 and "BEGIN CERTIFICATE" in proc.stdout:
-                return proc.stdout
-            if time.monotonic() >= deadline:
-                die(f"gateway CA not available after {timeout:g}s: "
-                    f"{proc.stderr.strip() or 'empty'}")
-            time.sleep(_HEALTH_POLL_SECONDS)
-
-
-def ensure_built() -> None:
-    """Ensure the infra rootfs is available before boot.
-
-    Default (docker-free, PRD 0069 Stage 2): download + verify the prebuilt
-    rootfs artifact matching this code version (see `infra_artifact`); the
-    launch host needs no Docker. `BOT_BOTTLE_INFRA_BUILD=local` instead builds
-    the three fixed images from source with host Docker — the infra image
-    `COPY --from`s the orchestrator image and is `FROM` the gateway image, so
-    both must exist first — for iterating on the Dockerfiles."""
-    if infra_artifact.local_build_requested():
-        build_infra_images_with_docker()
-        return
-    infra_artifact.ensure_artifact_gz(
-        infra_artifact.infra_artifact_version(_infra_init()))
-
-
-def build_infra_images_with_docker() -> None:
-    """Build the three fixed images from source with host Docker: orchestrator,
-    gateway, then the combined infra image (`COPY --from` orchestrator, `FROM`
-    gateway). The launch host uses this only in `BOT_BOTTLE_INFRA_BUILD=local`
-    mode; `publish_infra` uses it off-host to produce the published artifact."""
-    docker_mod.build_image(
-        _ORCHESTRATOR_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.orchestrator")
-    docker_mod.build_image(
-        _GATEWAY_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.gateway")
-    docker_mod.build_image(
-        _INFRA_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.infra")
-
-
-def build_infra_rootfs_dir() -> Path:
-    """The infra VM's base rootfs: the infra image prepared with the
-    control-plane + gateway init as PID 1. The init's content is folded into
-    the cache key so an init change rebuilds the rootfs (the base image digest
-    alone wouldn't catch it)."""
-    init = _infra_init()
-    tag = hashlib.sha256(init.encode()).hexdigest()[:8]
-    return util.build_base_rootfs_dir(
-        _INFRA_IMAGE, variant=f"-infra-{tag}", init_script=init,
-    )
-
-
-def ensure_running() -> InfraVm:
-    """Idempotent per-host singleton. Adopt the infra VM if its control plane
-    is already healthy (a prior launcher booted it — it outlives short-lived
-    `start` processes); otherwise clear any stale VM and boot a fresh one.
-    Returns a handle usable for CA fetch / git-gate provisioning.
-
-    Concurrency-safe: the cold stop/build/boot path is serialized by a host
-    flock, so two simultaneous first launches don't both boot on the same
-    rootfs/PID. The healthy fast-path takes no lock."""
-    slot = netpool.orch_slot()
-    url = f"http://{slot.guest_ip}:{CONTROL_PLANE_PORT}"
-    key = _infra_dir() / "id_ed25519"
-    if key.exists() and _health_ok(url):
-        info(f"adopting running infra VM at {url}")
-        return InfraVm(guest_ip=slot.guest_ip, private_key=key)
-
-    with _singleton_lock():
-        # Re-check under the lock: another launcher may have booted it while
-        # we waited for the lock (double-checked, so we adopt not re-boot).
-        if key.exists() and _health_ok(url):
-            info(f"adopting running infra VM at {url}")
-            return InfraVm(guest_ip=slot.guest_ip, private_key=key)
-        stop()  # clear a stale/hung VM holding the link before booting fresh
-        ensure_built()
-        infra = boot()
-        wait_for_health(infra)
-        return infra
-
-
-@contextmanager
-def _singleton_lock() -> Generator[None, None, None]:
-    """Host-level exclusive lock serializing the infra VM's cold create path
-    (`stop`/`ensure_built`/`boot`). flock auto-releases if the launcher
-    crashes, so the lock is never leaked."""
-    lock_path = _infra_dir() / "singleton.lock"
-    handle = open(lock_path, "w", encoding="utf-8")
-    try:
-        fcntl.flock(handle, fcntl.LOCK_EX)
-        yield
-    finally:
-        handle.close()
-
-
-def stop() -> None:
-    """Stop the infra VM singleton (idempotent — absent is success)."""
-    _kill_pidfile()
-    _pid_file().unlink(missing_ok=True)
-
-
-def boot() -> InfraVm:
-    """Boot the infra VM (detached, so it outlives the launcher) on the
-    orchestrator link, recording its PID. Prefer `ensure_running`."""
-    slot = netpool.orch_slot()
-    if not netpool.tap_present(slot.iface):
-        die(f"orchestrator link {slot.iface} not present.\n"
-            f"    ./cli.py backend setup --backend=firecracker")
-
-    run_dir = _infra_dir()
-    rootfs = run_dir / "rootfs.ext4"
-    if infra_artifact.local_build_requested():
-        util.build_rootfs_ext4(build_infra_rootfs_dir(), rootfs, slack_mib=8192)
-    else:
-        # Prebuilt artifact already carries the buildah build slack; expand it
-        # to a fresh writable rootfs for this boot.
-        infra_artifact.materialize_ext4(
-            infra_artifact.infra_artifact_version(_infra_init()), rootfs)
-    private_key, pubkey = _stable_keypair()
-
-    info(f"booting infra VM on {slot.iface} (guest {slot.guest_ip})")
-    vm = firecracker_vm.boot(
-        name="bot-bottle-infra", rootfs=rootfs, tap=slot.iface,
-        guest_ip=slot.guest_ip, host_ip=slot.host_ip, pubkey=pubkey,
-        run_dir=run_dir, mem_mib=4096, detached=True,
-        data_drive=_ensure_registry_volume(),
-    )
-    _pid_file().write_text(str(vm.process.pid))
-    return InfraVm(guest_ip=slot.guest_ip, private_key=private_key, vm=vm)
-
-
-def _infra_dir() -> Path:
-    d = util.cache_dir() / "infra"
-    d.mkdir(parents=True, exist_ok=True)
-    return d
-
-
-def _pid_file() -> Path:
-    return _infra_dir() / "vm.pid"
-
-
-# The registry "volume": a host-side ext4 file attached to the infra VM as a
-# second virtio-block device (guest /dev/vdb), mounted at the control plane's
-# DB dir. It outlives the ephemeral rootfs, so the bottle registry survives an
-# infra-VM restart — the firecracker analogue of a docker volume. It is a
-# plain ext4 file: `sudo mount -o loop <path>` on the host (with the VM
-# stopped) to inspect bot-bottle.db directly.
-_REGISTRY_SIZE = "512M"
-
-
-def registry_volume_path() -> Path:
-    return _infra_dir() / "registry.ext4"
-
-
-def _ensure_registry_volume() -> Path:
-    """Create the empty ext4 registry volume on first use; reuse it after."""
-    vol = registry_volume_path()
-    if vol.exists():
-        return vol
-    info(f"creating infra registry volume {vol} ({_REGISTRY_SIZE})")
-    proc = subprocess.run(
-        ["mke2fs", "-q", "-t", "ext4", "-F", str(vol), _REGISTRY_SIZE],
-        capture_output=True, text=True, check=False,
-    )
-    if proc.returncode != 0:
-        vol.unlink(missing_ok=True)
-        die(f"creating registry volume failed: {proc.stderr.strip()}")
-    return vol
-
-
-def _stable_keypair() -> tuple[Path, str]:
-    """The infra VM's SSH keypair — generated once and reused, so any later
-    launcher can SSH in (fetch CA / provision) even though a different process
-    booted the VM. The pubkey is re-injected on every boot via the cmdline."""
-    d = _infra_dir()
-    key, pub = d / "id_ed25519", d / "id_ed25519.pub"
-    if key.exists() and pub.exists():
-        return key, pub.read_text().strip()
-    key.unlink(missing_ok=True)
-    pub.unlink(missing_ok=True)
-    subprocess.run(
-        ["ssh-keygen", "-t", "ed25519", "-N", "", "-q", "-f", str(key),
-         "-C", "bot-bottle-infra"],
-        check=True,
-    )
-    return key, pub.read_text().strip()
-
-
-def _kill_pidfile() -> None:
-    """SIGTERM (then SIGKILL) the recorded infra VMM, if it's still ours.
-    Guards against a recycled PID by checking the process is firecracker."""
-    try:
-        pid = int(_pid_file().read_text().strip())
-    except (OSError, ValueError):
-        return
-    try:
-        comm = Path(f"/proc/{pid}/comm").read_text().strip()
-    except OSError:
-        return  # already gone
-    if comm != "firecracker":
-        return  # PID recycled by an unrelated process
-    try:
-        os.kill(pid, signal.SIGTERM)
-        for _ in range(50):
-            if not Path(f"/proc/{pid}").exists():
-                return
-            time.sleep(0.1)
-        os.kill(pid, signal.SIGKILL)
-    except OSError:
-        pass
-
-
-def _health_ok(url: str) -> bool:
-    try:
-        with urllib.request.urlopen(f"{url}/health", timeout=1.0) as resp:
-            return resp.status == 200
-    except (urllib.error.URLError, TimeoutError, OSError):
-        return False
-
-
-class SshGatewayTransport:
-    """`GatewayTransport` for the gateway running in the infra VM — the docker
-    exec/cp equivalents over SSH (dropbear + the stable infra key)."""
-
-    def __init__(self, private_key: Path, guest_ip: str) -> None:
-        self._key = private_key
-        self._ip = guest_ip
-
-    def exec(self, argv: list[str]) -> None:
-        proc = subprocess.run(
-            util.ssh_base_argv(self._key, self._ip) + [shlex.join(argv)],
-            capture_output=True, text=True, timeout=60, check=False,
-        )
-        if proc.returncode != 0:
-            raise GatewayProvisionError(
-                f"infra gateway exec {argv!r} failed: {proc.stderr.strip()}")
-
-    def cp_into(self, src: str, dest: str) -> None:
-        # Preserve the source mode (docker cp does): the access-hook is staged
-        # 0700 and git-http execs it directly — a plain `cat >` would land it
-        # 0644 and the exec fails with EACCES; keys stay 0600.
-        mode = stat.S_IMODE(os.stat(src).st_mode)
-        q = shlex.quote(dest)
-        proc = subprocess.run(
-            util.ssh_base_argv(self._key, self._ip)
-            + [f"cat > {q} && chmod {mode:o} {q}"],
-            input=Path(src).read_bytes(), capture_output=True, timeout=30, check=False,
-        )
-        if proc.returncode != 0:
-            raise GatewayProvisionError(
-                f"infra gateway cp {src} -> {dest} failed: "
-                f"{proc.stderr.decode(errors='replace').strip()}")
-
-
-def gateway_transport() -> SshGatewayTransport:
-    """git-gate provisioning transport for the gateway in the infra VM, built
-    from the stable key + the orchestrator link's guest IP. Needs no live VM
-    handle, so teardown can use it too."""
-    return SshGatewayTransport(
-        _infra_dir() / "id_ed25519", netpool.orch_slot().guest_ip)
-
-
-def wait_for_health(
-    infra: InfraVm, *, timeout: float = _HEALTH_TIMEOUT_SECONDS,
-) -> None:
-    """Poll the control plane's /health until it answers 200 or the deadline
-    passes. Dies (with the console tail) if the VMM exits early."""
-    url = f"{infra.control_plane_url}/health"
-    deadline = time.monotonic() + timeout
-    while time.monotonic() < deadline:
-        if infra.vm is not None and not infra.vm.is_alive():
-            die(f"infra VM exited during boot (rc={infra.vm.process.returncode}).\n"
-                f"{firecracker_vm._console_tail(infra.vm.console_log)}")
-        try:
-            with urllib.request.urlopen(url, timeout=1.0) as resp:
-                if resp.status == 200:
-                    info(f"infra control plane healthy at {infra.control_plane_url}")
-                    return
-        except (urllib.error.URLError, TimeoutError, OSError):
-            pass
-        time.sleep(_HEALTH_POLL_SECONDS)
-    tail = (firecracker_vm._console_tail(infra.vm.console_log)
-            if infra.vm is not None else "")
-    die(f"infra control plane at {url} did not become healthy within "
-        f"{timeout:.0f}s.\n{tail}")
-
-
-def _infra_init() -> str:
-    """PID-1 init for the infra VM: mount the pseudo-filesystems, wire a
-    resolver, start dropbear (debug SSH), then launch the control plane and
-    the gateway data plane (multi-tenant against the local control plane)."""
-    return f"""#!/bin/sh
-# bot-bottle Firecracker infra VM init (PID 1).
-mount -t proc proc /proc 2>/dev/null
-mount -t sysfs sys /sys 2>/dev/null
-mount -t devtmpfs dev /dev 2>/dev/null
-mkdir -p /dev/pts && mount -t devpts devpts /dev/pts 2>/dev/null
-mount -o remount,rw / 2>/dev/null
-
-# Export a real PATH: a bare-init shell resolves its own execs via a
-# built-in default path, but that isn't in the *environment*, so
-# gateway_init's subprocess daemons (spawned as `python3 ...`) would
-# inherit no PATH and fail to find python3. Export it for all children.
-export PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
-
-# Direct upstream resolver (control-plane / gateway egress + buildah).
-printf 'nameserver {_INFRA_RESOLVER}\\n' > /etc/resolv.conf 2>/dev/null
-
-# Debug SSH: install the per-boot pubkey from the kernel cmdline.
-KEY=$(sed -n 's/.*bb_pubkey=\\([^ ]*\\).*/\\1/p' /proc/cmdline | base64 -d 2>/dev/null)
-if [ -n "$KEY" ]; then
-    mkdir -p /root/.ssh
-    printf '%s\\n' "$KEY" > /root/.ssh/authorized_keys
-    chmod 700 /root/.ssh && chmod 600 /root/.ssh/authorized_keys
-fi
-chown -R 0:0 /root 2>/dev/null || true
-mkdir -p /etc/dropbear /run /var/lib/bot-bottle
-
-# Persistent registry volume (second virtio-block device, /dev/vdb) mounted
-# at the control plane's DB dir, so bot-bottle.db survives infra-VM restarts.
-mount -t ext4 /dev/vdb /var/lib/bot-bottle 2>/dev/null || true
-
-/bb-dropbear -R -E -p 22 &
-
-# Control plane. Source is baked at /app; the package is stdlib-only.
-cd /app
-BOT_BOTTLE_ROOT=/var/lib/bot-bottle python3 -m bot_bottle.orchestrator \\
-    --host 0.0.0.0 --port {CONTROL_PLANE_PORT} --broker stub &
-
-# Gateway data plane, multi-tenant: each request resolves source-IP ->
-# policy against the local control plane. The VM backend reaches git over
-# git-http (9420), so the git:// daemon (git-gate, needs a per-bottle
-# entrypoint the consolidated model doesn't use) is left out.
-BOT_BOTTLE_GATEWAY_DAEMONS=egress,git-http,supervise \\
-BOT_BOTTLE_ORCHESTRATOR_URL=http://127.0.0.1:{CONTROL_PLANE_PORT} \\
-SUPERVISE_DB_PATH=/var/lib/bot-bottle/db/bot-bottle.db \\
-    python3 /app/gateway_init.py &
-
-# Reap as PID 1; children are backgrounded, so `wait` blocks.
-while : ; do wait ; done
-"""

bot_bottle/backend/firecracker/launch.py

@@ -1,8 +1,7 @@
 """Launch flow for the Firecracker backend (PRD 0070, consolidated).
 
 Per bottle:
-  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;
+  1. build the agent image (docker), export it to a cached ext4 rootfs;
   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
@@ -32,7 +31,6 @@ 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,
@@ -47,9 +45,10 @@ 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
+from . import firecracker_vm, isolation_probe, netpool, util
 from .bottle import FirecrackerBottle
 from .bottle_plan import FirecrackerBottlePlan
 from .consolidated_launch import (
@@ -58,6 +57,7 @@ from .consolidated_launch import (
 )
 
 
+_REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
 _GIT_HTTP_PORT = 9420
 
 
@@ -85,10 +85,10 @@ def launch(
             raise teardown_exc
 
     try:
-        # Step 1: agent rootfs. Built from the Dockerfile inside a Firecracker
-        # builder VM (buildah, no host docker); a committed snapshot is reused
-        # when present. Returns the base dir the per-bottle ext4 is made from.
-        plan, agent_base = _build_agent_base(plan)
+        # Step 1: agent image. The sidecar bundle image is built by the
+        # orchestrator service (ensure_running → ensure_built); we only
+        # build the agent image here. Use a committed snapshot when available.
+        plan = _build_agent_image(plan)
 
         # Step 2: mint the git-gate dynamic (gitea) deploy keys, if any.
         git_gate_plan = plan.git_gate_plan
@@ -148,24 +148,17 @@ def launch(
             plan,
             git_gate_plan=git_gate_plan,
             egress_plan=egress_plan,
-            identity_token=ctx.identity_token,
-            # Deliver the identity token as egress proxy credentials — clients
-            # honor `HTTPS_PROXY=http://id:token@gw` without app changes; the
-            # gateway reads Proxy-Authorization, validates the (source_ip,
-            # token) pair, and strips it before upstream.
-            agent_proxy_url=(
-                f"http://bottle:{ctx.identity_token}"
-                f"@{slot.host_ip}:{EGRESS_PORT}"
-            ),
+            agent_proxy_url=f"http://{slot.host_ip}:{EGRESS_PORT}",
             agent_git_gate_url=git_gate_url,
             agent_supervise_url=supervise_url,
         )
 
         # Step 6: build the per-bottle rootfs + SSH key, then boot.
+        base_dir = util.build_base_rootfs_dir(plan.image)
         run_dir = util.cache_dir() / "run" / plan.slug
         run_dir.mkdir(parents=True, exist_ok=True)
         rootfs = run_dir / "rootfs.ext4"
-        util.build_rootfs_ext4(agent_base, rootfs)
+        util.build_rootfs_ext4(base_dir, rootfs)
         private_key, pubkey = util.generate_keypair(run_dir)
 
         vm = firecracker_vm.boot(
@@ -206,24 +199,19 @@ def launch(
         teardown()
 
 
-def _build_agent_base(
-    plan: FirecrackerBottlePlan,
-) -> 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 resumed
-    directly from the rootfs tar the freezer wrote — no host docker either."""
+def _build_agent_image(plan: FirecrackerBottlePlan) -> FirecrackerBottlePlan:
     committed = read_committed_image(plan.slug)
-    committed_tar = committed_rootfs_path(plan.slug)
-    if committed and committed_tar.is_file():
-        info(f"resuming from committed rootfs {committed_tar}")
-        return plan, util.build_committed_rootfs_dir(committed_tar)
-    base = image_builder.build_agent_rootfs_dir(
-        Path(plan.dockerfile_path),
-        image_tag=plan.image,
-        smoke_test=runtime_for(plan.agent_provider_template).smoke_test,
+    if committed and docker_mod.image_exists(committed):
+        info(f"using committed image {committed!r}")
+        return dataclasses.replace(
+            plan,
+            agent_provision=dataclasses.replace(plan.agent_provision, image=committed),
+        )
+    docker_mod.build_image(plan.image, _REPO_DIR, dockerfile=plan.dockerfile_path)
+    docker_mod.verify_agent_image(
+        plan.image, runtime_for(plan.agent_provider_template).smoke_test,
     )
-    return plan, base
+    return plan
 
 
 # --- agent guest env -------------------------------------------------
@@ -232,8 +220,7 @@ def _agent_guest_env(plan: FirecrackerBottlePlan, host_ip: str) -> dict[str, str
     """Env injected into every agent/exec call over SSH. The VM has no
     baked process env (it just runs init), so the proxy/CA/git/supervise
     wiring is applied per-invocation."""
-    # Carries the identity token as proxy credentials (set in `launch`).
-    proxy_url = plan.agent_proxy_url or f"http://{host_ip}:{EGRESS_PORT}"
+    proxy_url = f"http://{host_ip}:{EGRESS_PORT}"
     no_proxy = f"localhost,127.0.0.1,{host_ip}"
     env: dict[str, str] = {
         "HTTPS_PROXY": proxy_url, "HTTP_PROXY": proxy_url,

bot_bottle/backend/firecracker/netpool.defaults.env

@@ -15,11 +15,3 @@ BOT_BOTTLE_FC_POOL_SIZE=8
 BOT_BOTTLE_FC_IP_BASE=10.243.0.0
 BOT_BOTTLE_FC_IFACE_PREFIX=bbfc
 BOT_BOTTLE_FC_NFT_TABLE=bot_bottle_fc
-# The orchestrator/gateway VM's own TAP — a dedicated link OUTSIDE the
-# bbfc* agent pool. Unlike agent VMs (which reach only their gateway),
-# the orchestrator is trusted infra that needs real NAT'd internet
-# egress: to FROM-pull + apt/npm during in-VM agent-image builds
-# (buildah) and to forward agent egress upstream (Stage B gateway). Its
-# /31 is the top of the IP_BASE /16 (host x.y.255.0, guest x.y.255.1),
-# clear of the pool near the bottom of the block.
-BOT_BOTTLE_FC_ORCH_IFACE=bborch0

bot_bottle/backend/firecracker/netpool.py

@@ -79,12 +79,6 @@ def _cfg(key: str) -> str:
 IFACE_PREFIX = _cfg("BOT_BOTTLE_FC_IFACE_PREFIX")
 NFT_TABLE = _cfg("BOT_BOTTLE_FC_NFT_TABLE")
 
-# The orchestrator/gateway VM's dedicated TAP — outside the bbfc* agent
-# pool and, unlike it, NAT'd to the internet (see `orch_slot`). The
-# orchestrator is trusted infra: it builds agent images in-VM (buildah
-# needs to FROM-pull + apt/npm) and forwards agent egress upstream.
-ORCH_IFACE = _cfg("BOT_BOTTLE_FC_ORCH_IFACE")
-
 
 def pool_size() -> int:
     return int(_cfg("BOT_BOTTLE_FC_POOL_SIZE"))
@@ -129,25 +123,6 @@ def all_slots() -> list[Slot]:
     return [slot(i) for i in range(pool_size())]
 
 
-def orch_slot() -> Slot:
-    """The orchestrator/gateway VM's dedicated link — its own TAP
-    (`ORCH_IFACE`) on a /31 at the TOP of the IP_BASE /16 (host
-    x.y.255.0, guest x.y.255.1), well clear of the agent pool near the
-    bottom of the block. Unlike a pool `Slot`, this link is NAT'd out to
-    the internet by the setup (the orchestrator is trusted infra), so it
-    is deliberately *not* one of the isolated `bbfc*` slots.
-
-    `index` is -1 (sentinel: not a pool index)."""
-    base16 = int(ipaddress.IPv4Address(ip_base())) & 0xFFFF0000
-    host = base16 + 0xFF00
-    return Slot(
-        index=-1,
-        iface=ORCH_IFACE,
-        host_ip=str(ipaddress.IPv4Address(host)),
-        guest_ip=str(ipaddress.IPv4Address(host + 1)),
-    )
-
-
 # --- fail-closed verification ---------------------------------------
 
 def _run_ok(argv: list[str]) -> bool:

bot_bottle/backend/firecracker/publish_infra.py

@@ -1,169 +0,0 @@
-"""Build the infra rootfs and publish it as a Gitea generic package.
-
-The off-host (build / CI) half of PRD 0069 Stage 2: this DOES use Docker, but
-never on the launch host. It runs the same pipeline the launch host used to run
-locally — `docker build` the three fixed images, export to a rootfs dir, inject
-the guest boot, `mke2fs` to an ext4 with the buildah build slack — then gzips
-the ext4 and PUTs it (plus a `.sha256`) to
-`…/api/packages/<owner>/generic/bot-bottle-firecracker-infra/<version>/`.
-
-The `<version>` is `infra_artifact.infra_artifact_version(...)`, the content
-hash of the rootfs inputs, so a launch host at the same code checkout resolves
-the exact artifact this produced.
-
-  python3 -m bot_bottle.backend.firecracker.publish_infra [--dry-run] [--force]
-
-Auth: a token with `write:package` on the target owner, from
-`BOT_BOTTLE_INFRA_ARTIFACT_TOKEN`.
-"""
-
-from __future__ import annotations
-
-import argparse
-import gzip
-import hashlib
-import shutil
-import sys
-import tempfile
-import urllib.error
-import urllib.request
-from pathlib import Path
-
-from . import infra_artifact, infra_vm, util
-
-_CHUNK = 1 << 20
-
-# A human-readable description shipped alongside the artifact — generic packages
-# have no description field, so this file *is* the description on the package
-# page. Uploaded on every publish so it never goes stale.
-_ABOUT_NAME = "about.txt"
-_ABOUT_TEXT = (
-    "bot-bottle infra rootfs for the Firecracker backend (PRD 0069 Stage 2, "
-    "#348): the per-host infra VM (orchestrator control plane + gateway + "
-    "buildah). Prebuilt off-host, gzip ext4; the launch host downloads + "
-    "sha256-verifies + boots it, no host Docker. The version tag is a content "
-    "hash of the rootfs inputs. Files: rootfs.ext4.gz + rootfs.ext4.gz.sha256.\n"
-)
-
-
-def _gzip(src: Path, dest: Path) -> None:
-    with open(src, "rb") as fh, gzip.open(dest, "wb") as out:
-        shutil.copyfileobj(fh, out, _CHUNK)
-
-
-def _sha256(path: Path) -> str:
-    h = hashlib.sha256()
-    with open(path, "rb") as fh:
-        for chunk in iter(lambda: fh.read(_CHUNK), b""):
-            h.update(chunk)
-    return h.hexdigest()
-
-
-def _put(url: str, body: "bytes | Path", token: str) -> None:
-    """PUT `body` (raw bytes, or a Path streamed from disk) to `url`. The rootfs
-    is hundreds of MB, so it is passed as a Path and streamed — `urlopen` reads
-    the open file in blocks rather than materializing it in memory (with an
-    explicit Content-Length, which Gitea requires and which also stops urllib
-    from `len()`-ing a non-bytes body)."""
-    handle = None
-    if isinstance(body, Path):
-        length = body.stat().st_size
-        handle = open(body, "rb")
-        data: object = handle
-    else:
-        length = len(body)
-        data = body
-    req = urllib.request.Request(url, data=data, method="PUT")  # type: ignore[arg-type]
-    req.add_header("Content-Length", str(length))
-    if token:
-        req.add_header("Authorization", f"token {token}")
-    req.add_header("Content-Type", "application/octet-stream")
-    try:
-        with urllib.request.urlopen(req) as resp:
-            print(f"  uploaded {url} (HTTP {resp.status})")
-    except urllib.error.HTTPError as e:
-        if e.code == 409:
-            raise SystemExit(
-                f"artifact already published at {url} (HTTP 409); "
-                f"bump the code version or pass --force to overwrite"
-            )
-        raise SystemExit(f"upload failed (HTTP {e.code}): {url}\n{e.read().decode(errors='replace')}")
-    except urllib.error.URLError as e:
-        raise SystemExit(f"registry unreachable: {url} ({e.reason})")
-    finally:
-        if handle is not None:
-            handle.close()
-
-
-def _delete(url: str, token: str) -> None:
-    req = urllib.request.Request(url, method="DELETE")
-    if token:
-        req.add_header("Authorization", f"token {token}")
-    try:
-        with urllib.request.urlopen(req):
-            pass
-    except urllib.error.HTTPError as e:
-        if e.code != 404:
-            raise SystemExit(f"could not overwrite existing artifact (HTTP {e.code}): {url}")
-    except urllib.error.URLError as e:
-        raise SystemExit(f"registry unreachable: {url} ({e.reason})")
-
-
-def build_artifact(out_dir: Path) -> tuple[str, Path, Path]:
-    """Build the infra rootfs ext4, gzip it, and write the checksum. Returns
-    `(version, gz_path, sha_path)`. Uses host Docker (off-host / CI)."""
-    version = infra_artifact.infra_artifact_version(infra_vm._infra_init())
-    print(f"building infra rootfs artifact {version} (docker)")
-    infra_vm.build_infra_images_with_docker()
-    base = infra_vm.build_infra_rootfs_dir()
-
-    ext4 = out_dir / "rootfs.ext4"
-    util.build_rootfs_ext4(base, ext4, slack_mib=8192)
-    gz = out_dir / "rootfs.ext4.gz"
-    print("compressing rootfs")
-    _gzip(ext4, gz)
-    ext4.unlink(missing_ok=True)
-
-    sha = out_dir / "rootfs.ext4.gz.sha256"
-    digest = _sha256(gz)
-    sha.write_text(f"{digest}  rootfs.ext4.gz\n")
-    print(f"  {gz.name}: {gz.stat().st_size / 1e6:.0f} MB  sha256={digest}")
-    return version, gz, sha
-
-
-def main(argv: list[str] | None = None) -> int:
-    parser = argparse.ArgumentParser(
-        prog="publish_infra", description="Build + publish the infra rootfs artifact.")
-    parser.add_argument("--dry-run", action="store_true",
-                        help="build the artifact but do not upload")
-    parser.add_argument("--force", action="store_true",
-                        help="overwrite an already-published artifact of this version")
-    args = parser.parse_args(argv)
-
-    _, _, token = infra_artifact._config()
-    if not args.dry_run and not token:
-        raise SystemExit(
-            "no publish token: set BOT_BOTTLE_INFRA_ARTIFACT_TOKEN to a token "
-            "with write:package")
-
-    with tempfile.TemporaryDirectory(prefix="bb-publish-infra.") as tmp:
-        version, gz, sha = build_artifact(Path(tmp))
-        gz_url = infra_artifact.artifact_url(version, gz.name)
-        sha_url = infra_artifact.artifact_url(version, sha.name)
-        about_url = infra_artifact.artifact_url(version, _ABOUT_NAME)
-        if args.dry_run:
-            print(f"dry-run: would upload -> {gz_url}")
-            return 0
-        if args.force:
-            _delete(gz_url, token)
-            _delete(sha_url, token)
-            _delete(about_url, token)
-        _put(gz_url, gz, token)  # streamed from disk (hundreds of MB)
-        _put(sha_url, sha.read_bytes(), token)  # tiny, in-memory is fine
-        _put(about_url, _ABOUT_TEXT.encode(), token)  # package description
-    print(f"published infra rootfs {version}")
-    return 0
-
-
-if __name__ == "__main__":
-    sys.exit(main())

bot_bottle/backend/firecracker/util.py

@@ -14,7 +14,6 @@ and `./cli.py backend setup --backend=firecracker`.
 
 from __future__ import annotations
 
-import hashlib
 import os
 import platform
 import shutil
@@ -160,22 +159,15 @@ def docker_image_id(ref: str) -> str:
     return result.stdout.strip().replace("sha256:", "")[:16]
 
 
-def build_base_rootfs_dir(
-    image_ref: str, *, variant: str = "", init_script: str | None = None,
-) -> Path:
-    """Export the image's filesystem and inject the guest init + static
-    dropbear. Cached by image digest — the per-bottle bits
+def build_base_rootfs_dir(image_ref: str) -> Path:
+    """Export the agent image's filesystem and inject the guest init +
+    static dropbear. Cached by image digest — the per-bottle bits
     (authorized_keys, IP) are passed at boot via the kernel cmdline, so
     this tree carries nothing bottle-specific and is safely shared.
 
-    `variant` suffixes the cache key so the same image can be prepared
-    with a different `init_script` (e.g. the infra VM boots the same
-    orchestrator image as the builder but runs the control plane as
-    PID 1, not the SSH-only agent init) without a cache collision.
-
     Returns the prepared directory (read as the `mke2fs -d` source)."""
     digest = docker_image_id(image_ref)
-    base = cache_dir() / "rootfs" / f"{digest}{variant}"
+    base = cache_dir() / "rootfs" / digest
     ready = base / ".bb-ready"
     if ready.is_file():
         return base
@@ -208,85 +200,18 @@ def build_base_rootfs_dir(
             stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
         )
 
-    inject_guest_boot(base, init_script=init_script)
+    _inject_guest_boot(base)
     ready.write_text("ok\n")
     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.
-
-    A committed snapshot is guest-controlled, so `bb-dropbear`/`bb-init`
-    may already exist as symlinks aimed at a host file (e.g. bb-init ->
-    ~/.bashrc). Replace whatever is there and create the files with
-    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 _inject_guest_boot(rootfs: Path) -> None:
+    """Drop the static dropbear and the PID-1 init into the rootfs."""
+    shutil.copy2(dropbear_path(), rootfs / "bb-dropbear")
+    os.chmod(rootfs / "bb-dropbear", 0o755)
+    init = rootfs / "bb-init"
+    init.write_text(_GUEST_INIT)
+    os.chmod(init, 0o755)
 
 
 def build_rootfs_ext4(base_dir: Path, out_path: Path, *, slack_mib: int = 1024) -> None:

bot_bottle/backend/macos_container/backend.py

@@ -89,14 +89,6 @@ 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.py

@@ -52,7 +52,6 @@ class MacosContainerBottle(Bottle):
         terminal_title: str = "",
         terminal_color: str = "",
         agent_workdir: str = "/home/node",
-        exec_env: dict[str, str] | None = None,
     ):
         self.name = container
         self._teardown = teardown
@@ -63,15 +62,6 @@ class MacosContainerBottle(Bottle):
         self.terminal_color = terminal_color
         self.agent_provider_template = agent_provider_template
         self.agent_workdir = agent_workdir
-        # Env applied to the agent process at `container exec` time, on top of
-        # what the container was run with. This is how the identity token
-        # reaches the agent (PRD 0070): registration mints it *after* the
-        # container exists — its source IP is the registration key and Apple
-        # Container assigns that by DHCP — so it cannot be in the run-time env
-        # the way docker's compose spec does it. `container exec --env` wins
-        # over the run-time value, so the token-bearing proxy URL set here
-        # supersedes the token-less one baked in at launch.
-        self._exec_env = dict(exec_env or {})
         self._closed = False
 
     def agent_argv(self, argv: list[str], *, tty: bool = True) -> list[str]:
@@ -84,12 +74,6 @@ class MacosContainerBottle(Bottle):
             )
         )
         container_exec = ["container", "exec"]
-        # Bare env names, same rule as the terminal hints below: the value
-        # stays in the child env `exec_agent` builds and never reaches argv —
-        # the proxy URL here carries the identity token, which `ps` would
-        # otherwise expose to every process on the host.
-        for name in sorted(self._exec_env):
-            container_exec.extend(["--env", name])
         if tty:
             container_exec.extend(["--interactive", "--tty"])
             # Forward terminal capability hints so TUIs can enable modified-key
@@ -110,33 +94,21 @@ class MacosContainerBottle(Bottle):
 
     def exec_agent(self, argv: list[str], *, tty: bool = True) -> int:
         agent_argv = self.agent_argv(argv, tty=tty)
-        # The values behind the bare `--env` names in `agent_argv`. `sh -lc`
-        # below is in this process tree, so the child env reaches `container
-        # exec` either way.
-        env = {**os.environ, **self._exec_env} if self._exec_env else None
         script = (
             exec_shell_script(agent_argv, self.terminal_title, self.terminal_color)
             if tty else None
         )
         if script is None:
-            return subprocess.run(agent_argv, env=env, check=False).returncode
-        return subprocess.run(["sh", "-lc", script], env=env, check=False).returncode
+            return subprocess.run(agent_argv, check=False).returncode
+        return subprocess.run(["sh", "-lc", script], check=False).returncode
 
     def exec(self, script: str, *, user: str = "node") -> ExecResult:
-        # Carry the same exec env the agent gets: provisioning steps run
-        # through here, and a provider whose provision step fetches anything
-        # would egress without the identity token and be denied by /resolve.
-        # Bare `--env NAME` again, so the token stays off argv.
-        argv = ["container", "exec", "--user", user, "--interactive"]
-        for name in sorted(self._exec_env):
-            argv.extend(["--env", name])
-        argv.extend([self.name, "sh", "-s"])
         result = subprocess.run(
-            argv,
+            ["container", "exec", "--user", user, "--interactive",
+             self.name, "sh", "-s"],
             input=script,
             capture_output=True,
             text=True,
-            env={**os.environ, **self._exec_env} if self._exec_env else None,
             check=False,
         )
         return ExecResult(

bot_bottle/backend/macos_container/bottle_plan.py

@@ -13,13 +13,9 @@ 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

@@ -1,144 +0,0 @@
-"""Consolidated bottle launch sequence for the macOS backend (PRD 0070).
-
-The docker backend allocates a free address, pins the agent to it with
-`--ip`, registers it, *then* starts the agent — registration precedes launch
-because the pinned address is known up front.
-
-**Apple Container 1.0.0 has no `--ip`.** The `--network` flag takes only
-`<name>[,mac=…][,mtu=…]`; the address is assigned by vmnet's DHCP and is
-knowable only once the container is running. So the macOS order inverts:
-
-    ensure_gateway()  ->  caller starts the agent  ->  register_agent(source_ip)
-
-That is why this module exposes two functions where docker has one — the
-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`
-time instead — see `bottle.MacosContainerBottle`.
-
-That delivery is load-bearing, not a nicety: `/resolve` requires a matching
-`(source_ip, identity_token)` pair and fail-closes with no source-IP-only
-fallback (#366). So egress that does not carry the token is denied — which is
-the safe direction, and is why the agent's init process is a bare `sleep` and
-every real command arrives through `container exec`.
-"""
-
-from __future__ import annotations
-
-from dataclasses import dataclass
-
-from ...egress import EgressPlan
-from ...git_gate import GitGatePlan
-from ...orchestrator.client import OrchestratorClient
-from ...orchestrator.registration import registration_inputs
-from ..docker.gateway_provision import deprovision_git_gate, provision_git_gate
-from .gateway import GATEWAY_NETWORK
-from .gateway_provision import AppleGatewayTransport
-from .infra import MacosInfraService, OrchestratorStartError
-
-
-class ConsolidatedLaunchError(RuntimeError):
-    """The consolidated register/provision sequence could not complete."""
-
-
-@dataclass(frozen=True)
-class GatewayEndpoint:
-    """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
-    gateway_ca_pem: str     # the shared CA the provisioner installs
-    network: str            # the shared host-only network to attach to
-
-
-@dataclass(frozen=True)
-class LaunchContext:
-    """What the running agent needs once it has been registered."""
-
-    bottle_id: str
-    identity_token: str
-    source_ip: str          # the agent's DHCP-assigned address (attribution key)
-    gateway_ip: str
-    network: str
-    orchestrator_url: str
-
-
-def ensure_gateway(
-    *, service: MacosInfraService | None = None,
-) -> GatewayEndpoint:
-    """Ensure the per-host infra container (control plane + gateway) is up and
-    report how to reach it. Idempotent — one singleton, so N bottle launches
-    share it. Call before starting the agent container: the agent's proxy env
-    needs `gateway_ip` at run time."""
-    service = service or MacosInfraService()
-    infra = service.ensure_running()
-    return GatewayEndpoint(
-        orchestrator_url=infra.control_plane_url,
-        gateway_ip=infra.gateway_ip,
-        gateway_ca_pem=service.ca_cert_pem(),
-        network=service.network,
-    )
-
-
-def register_agent(
-    egress_plan: EgressPlan,
-    git_gate_plan: GitGatePlan,
-    *,
-    source_ip: str,
-    endpoint: GatewayEndpoint,
-    image_ref: str = "",
-    tokens: dict[str, str] | None = None,
-) -> LaunchContext:
-    """Register the (already running) agent by its address and provision its
-    git-gate state into the gateway. `source_ip` must be read from the live
-    container — it is the attribution key the gateway resolves policy by.
-    Raises on failure; the caller tears down."""
-    client = OrchestratorClient(endpoint.orchestrator_url)
-    inputs = registration_inputs(egress_plan)
-    reg = client.register_bottle(
-        source_ip, image_ref=image_ref, policy=inputs.policy,
-        metadata=inputs.metadata, tokens=tokens,
-    )
-    try:
-        provision_git_gate(AppleGatewayTransport(), reg.bottle_id, git_gate_plan)
-    except Exception:
-        # Roll the registration back so a provisioning failure leaves no orphan.
-        client.teardown_bottle(reg.bottle_id)
-        raise
-    return LaunchContext(
-        bottle_id=reg.bottle_id,
-        identity_token=reg.identity_token,
-        source_ip=source_ip,
-        gateway_ip=endpoint.gateway_ip,
-        network=endpoint.network,
-        orchestrator_url=endpoint.orchestrator_url,
-    )
-
-
-def teardown_consolidated(bottle_id: str, *, orchestrator_url: str) -> None:
-    """Deregister the bottle and remove its git-gate state from the gateway.
-    Both steps are idempotent so this is safe from a cleanup trap. Does NOT
-    stop the gateway — it's a persistent per-host singleton."""
-    OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
-    deprovision_git_gate(AppleGatewayTransport(), bottle_id)
-
-
-__all__ = [
-    "GatewayEndpoint",
-    "LaunchContext",
-    "ensure_gateway",
-    "register_agent",
-    "teardown_consolidated",
-    "ConsolidatedLaunchError",
-    "OrchestratorStartError",
-    "GATEWAY_NETWORK",
-]

bot_bottle/backend/macos_container/egress_apply.py

@@ -1,11 +1,9 @@
 """Host-side egress route-apply for the macos-container backend.
 
 The per-bottle companion container this used to signal (`container kill
---signal HUP <container>`) was removed in the companion-container removal
-(#385). In the consolidated model the shared gateway resolves egress policy
-per-request against the orchestrator rather than reloading a per-bottle routes
-file, so the live per-bottle reload is not supported here and fails closed
-until the gateway-side apply lands — same posture as the docker backend.
+--signal HUP <container>`) was removed in the companion-container removal (#385),
+along with the disabled macOS launch path. Fails closed until the macOS
+backend grows the consolidated gateway.
 """
 
 from __future__ import annotations
@@ -18,8 +16,8 @@ class MacOSContainerEgressApplicator(EgressApplicator):
         del slug
         raise EgressApplyError(
             "live egress route-apply was removed with the per-bottle "
-            "companion container (#385); route changes will flow through "
-            "the consolidated gateway in a follow-up."
+            "companion container (#385); the macos-container backend is "
+            "disabled until it uses the consolidated gateway."
         )
 
 

bot_bottle/backend/macos_container/enumerate.py

@@ -1,42 +1,14 @@
-"""Active-agent enumeration for the macOS Apple Container backend."""
+"""Active-agent enumeration for the macOS Apple Container backend.
+
+The backend is disabled during the companion-container removal (#385) — it can't
+launch bottles, so there are none to enumerate. Enumeration returns when
+the backend grows the consolidated gateway.
+"""
 
 from __future__ import annotations
 
-import subprocess
-
-from ...bottle_state import read_metadata
 from .. import ActiveAgent
-from .infra import INFRA_NAME
-
-_PREFIX = "bot-bottle-"
-# The shared per-host infra container carries the same prefix as agent
-# containers but is infrastructure, not a bottle — one control plane + gateway
-# serves every agent, so listing it as an agent would invent one per host.
-_INFRA_NAMES = frozenset({INFRA_NAME})
 
 
 def enumerate_active() -> list[ActiveAgent]:
-    result = subprocess.run(
-        ["container", "list", "--quiet"],
-        capture_output=True,
-        text=True,
-        check=False,
-    )
-    if result.returncode != 0:
-        return []
-    out: list[ActiveAgent] = []
-    for name in sorted(line.strip() for line in result.stdout.splitlines()):
-        if not name.startswith(_PREFIX) or name in _INFRA_NAMES:
-            continue
-        slug = name[len(_PREFIX):]
-        metadata = read_metadata(slug)
-        out.append(ActiveAgent(
-            backend_name="macos-container",
-            slug=slug,
-            agent_name=metadata.agent_name if metadata else "?",
-            started_at=metadata.started_at if metadata else "",
-            services=(),
-            label=metadata.label if metadata else "",
-            color=metadata.color if metadata else "",
-        ))
-    return out
+    return []

bot_bottle/backend/macos_container/gateway.py

@@ -1,46 +0,0 @@
-"""Shared network/image constants for the macOS consolidated infra container.
-
-The gateway data plane no longer runs as its own Apple container — it shares a
-single per-host **infra container** with the control plane (see `infra`),
-because two Apple-Container guests writing one `bot-bottle.db` over virtiofs
-would race incoherent `fcntl` locks. This module holds the pieces both the
-infra service and the launch/provision glue need: the network names, the
-gateway image, and the network-creation helper.
-"""
-
-from __future__ import annotations
-
-import os
-
-from ...orchestrator.gateway import GatewayError
-from . import util as container_mod
-
-# The shared host-only network the infra container and every agent bottle sit
-# on. The agent's address here is the attribution key. Distinct from the docker
-# names so both backends can coexist on one host.
-GATEWAY_NETWORK = "bot-bottle-mac-gateway"
-# 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")
-
-DEFAULT_CA_TIMEOUT_SECONDS = 30.0
-
-
-def ensure_networks(
-    network: str = GATEWAY_NETWORK, egress_network: str = GATEWAY_EGRESS_NETWORK,
-) -> None:
-    """Create the shared host-only network + the NAT egress network. Idempotent
-    — `create_network` tolerates 'already exists'."""
-    container_mod.create_network(egress_network)
-    container_mod.create_network(network, internal=True)
-
-
-__all__ = [
-    "GATEWAY_NETWORK",
-    "GATEWAY_EGRESS_NETWORK",
-    "GATEWAY_IMAGE",
-    "GatewayError",
-    "DEFAULT_CA_TIMEOUT_SECONDS",
-    "ensure_networks",
-]

bot_bottle/backend/macos_container/gateway_provision.py

@@ -1,44 +0,0 @@
-"""`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 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 .infra import INFRA_NAME
-
-
-class AppleGatewayTransport:
-    """`GatewayTransport` for the gateway daemons in the Apple infra container."""
-
-    def __init__(self, gateway: str = INFRA_NAME) -> None:
-        self.gateway = gateway
-
-    def exec(self, argv: list[str]) -> None:
-        result = container_mod.run_container_argv(
-            ["container", "exec", self.gateway, *argv]
-        )
-        if result.returncode != 0:
-            raise GatewayProvisionError(
-                f"gateway exec {argv!r} failed: "
-                f"{(result.stderr or '').strip() or '<no stderr>'}"
-            )
-
-    def cp_into(self, src: str, dest: str) -> None:
-        result = container_mod.run_container_argv(
-            ["container", "cp", src, f"{self.gateway}:{dest}"]
-        )
-        if result.returncode != 0:
-            raise GatewayProvisionError(
-                f"gateway cp {src} -> {dest} failed: "
-                f"{(result.stderr or '').strip() or '<no stderr>'}"
-            )
-
-
-__all__ = ["AppleGatewayTransport", "GatewayProvisionError"]

bot_bottle/backend/macos_container/infra.py

@@ -1,305 +0,0 @@
-"""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

@@ -1,74 +1,24 @@
-"""Launch flow for the macOS Apple Container backend (PRD 0070).
+"""Launch flow for the macOS Apple Container backend — disabled (#385).
 
-The agent container attaches to the **shared host-only gateway network** and
-proxies egress through the one per-host gateway, replacing the per-bottle
-companion container removed in #385.
+This backend launched a per-bottle companion container (the egress /
+git-gate / supervise data plane) alongside the agent container, with the
+agent's proxy env pointed at the companion's host-only IP. That
+per-bottle-companion architecture was removed in the companion-container removal;
+the macOS backend will be re-enabled once it grows the consolidated
+per-host gateway the docker backend already uses.
 
-The order differs from docker's, forced by Apple Container 1.0.0 having no
-`--ip` (see `consolidated_launch`): the agent is started *before* it is
-registered, because its DHCP-assigned address — the attribution key — does not
-exist until then.
-
-    gateway up -> run agent -> read its IP -> register it -> provision
-
-Two things follow from that inversion:
-
-- The **identity token** is minted by registration and so cannot be in the
-  agent's run-time env; it rides the proxy URL applied at `container exec`
-  time (`bottle.MacosContainerBottle`). `/resolve` requires it (#366), so
-  egress without it is denied — hence the bare `sleep` init: every real agent
-  command goes through exec and therefore carries the token.
-- The agent is run with `--cap-drop CAP_NET_RAW`. Apple Container grants
-  NET_RAW by default, which would let an agent open a raw socket and forge a
-  neighbour's source address on the shared segment. NET_ADMIN is already
-  absent (the agent cannot change its own address or route), so dropping
-  NET_RAW is what closes the source-address half of PRD 0070's invariant:
-  "a packet's source address, as seen by the orchestrator, provably identifies
-  the originating bottle." The identity token is the other half — an attacker
-  would need to forge the address *and* steal the token — but the invariant is
-  a stated precondition of consolidation, so it is enforced on its own terms
-  rather than left to the token.
+Until then, launching a macOS bottle fails closed. `prepare` / `status`
+/ cleanup still work.
 """
 
 from __future__ import annotations
 
-import dataclasses
-import os
-import subprocess
-from contextlib import ExitStack, contextmanager
-from pathlib import Path
+from contextlib import contextmanager
 from typing import Callable, Generator
 
-from ...bottle_state import (
-    egress_state_dir,
-    git_gate_state_dir,
-    read_committed_image,
-)
-from ...egress import (
-    egress_agent_env_entries,
-    egress_resolve_token_values,
-)
-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
-from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
-from . import util as container_mod
+from ...log import die
 from .bottle import MacosContainerBottle
 from .bottle_plan import MacosContainerBottlePlan
-from .consolidated_launch import (
-    GatewayEndpoint,
-    ensure_gateway,
-    register_agent,
-    teardown_consolidated,
-)
-
-_REPO_DIR = str(Path(__file__).resolve().parent.parent.parent.parent)
-_AGENT_SLEEP_SECONDS = "2147483647"
 
 
 @contextmanager
@@ -77,274 +27,13 @@ def launch(
     *,
     provision: Callable[[MacosContainerBottlePlan, "MacosContainerBottle"], str | None],
 ) -> Generator[MacosContainerBottle, None, None]:
-    """Build, run, register, provision, and yield an Apple Container bottle on
-    the shared per-host gateway."""
-    stack = ExitStack()
-    bottle_for_revoke = plan.manifest.bottle
-    git_gate_dir_for_revoke = git_gate_state_dir(plan.slug)
-
-    def teardown() -> None:
-        teardown_exc: BaseException | None = None
-        try:
-            stack.close()
-        except BaseException as exc:  # noqa: W0718 - teardown must continue
-            teardown_exc = exc
-            warn(f"macos-container teardown failed: {exc!r}")
-        revoke_git_gate_provisioned_keys(bottle_for_revoke, git_gate_dir_for_revoke)
-        if teardown_exc is not None:
-            raise teardown_exc
-
-    try:
-        plan = _build_images(plan)
-
-        # Step 1: the per-host singletons. Must precede the agent run — its
-        # proxy env needs the gateway's address at `container run` time.
-        endpoint = ensure_gateway()
-
-        # Step 2: mint this bottle's deploy keys, then point it at the SHARED
-        # gateway's CA + git-http/supervise ports.
-        plan = _provision_git_gate_keys(plan)
-        plan = _install_gateway_ca(plan, endpoint)
-        plan = _stamp_agent_urls(plan, endpoint)
-
-        # Step 3: run the agent. It has no identity token yet — registration
-        # needs the address this run assigns.
-        container_mod.force_remove_container(plan.container_name)
-        _start_agent(plan, endpoint)
-        stack.callback(container_mod.force_remove_container, plan.container_name)
-
-        # 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. Poll: `container run --detach` can return before vmnet's
-        # 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,
-        )
-        ctx = register_agent(
-            plan.egress_plan,
-            plan.git_gate_plan,
-            source_ip=source_ip,
-            endpoint=endpoint,
-            image_ref=plan.image,
-            tokens=token_values,
-        )
-        stack.callback(
-            teardown_consolidated, ctx.bottle_id,
-            orchestrator_url=ctx.orchestrator_url,
-        )
-        info(
-            f"agent {plan.container_name} registered "
-            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,
-            None,
-            agent_command=plan.agent_command,
-            agent_prompt_mode=plan.agent_prompt_mode,
-            agent_provider_template=plan.agent_provider_template,
-            terminal_title=(
-                f"{plan.spec.label} ({plan.spec.agent_name})"
-                if plan.spec.label else plan.spec.agent_name
-            ),
-            terminal_color=plan.spec.color,
-            agent_workdir=plan.workspace_plan.workdir,
-            exec_env=_identity_proxy_env(endpoint, ctx.identity_token),
-        )
-        bottle.prompt_path = provision(plan, bottle)
-
-        yield bottle
-    finally:
-        teardown()
-
-
-def _build_images(plan: MacosContainerBottlePlan) -> MacosContainerBottlePlan:
-    """Build the agent image. The gateway's own image is built by
-    `ensure_gateway` — it belongs to the shared singleton, not to a bottle."""
-    committed = read_committed_image(plan.slug)
-    if committed and container_mod.image_exists(committed):
-        info(f"using committed image {committed!r}")
-        return dataclasses.replace(
-            plan,
-            agent_provision=dataclasses.replace(
-                plan.agent_provision, image=committed,
-            ),
-        )
-    container_mod.build_image(
-        plan.image, _REPO_DIR, dockerfile=plan.dockerfile_path,
+    """Fail closed: the macOS backend is disabled until it grows the
+    consolidated per-host gateway (the companion-container path it used
+    was removed in #385)."""
+    del plan, provision
+    die(
+        "the macos-container backend is temporarily disabled during the "
+        "companion-container removal (#385); it will return once it uses "
+        "the consolidated gateway. Use --backend=docker for now."
     )
-    return plan
-
-
-def _provision_git_gate_keys(
-    plan: MacosContainerBottlePlan,
-) -> MacosContainerBottlePlan:
-    if not plan.git_gate_plan.upstreams:
-        return plan
-    git_gate_plan = provision_git_gate_dynamic_keys(
-        plan.manifest.bottle,
-        plan.git_gate_plan,
-        git_gate_state_dir(plan.slug),
-    )
-    return dataclasses.replace(plan, git_gate_plan=git_gate_plan)
-
-
-def _install_gateway_ca(
-    plan: MacosContainerBottlePlan, endpoint: GatewayEndpoint,
-) -> MacosContainerBottlePlan:
-    """Stage the SHARED gateway's CA for the provisioner to install, replacing
-    the per-bottle CA the companion container used to mint. Every bottle on
-    this host trusts this one CA."""
-    ca_dir = egress_state_dir(plan.slug) / "gateway-ca"
-    ca_dir.mkdir(parents=True, exist_ok=True)
-    ca_file = ca_dir / "gateway-ca.pem"
-    ca_file.write_text(endpoint.gateway_ca_pem)
-    egress_plan = dataclasses.replace(
-        plan.egress_plan,
-        mitmproxy_ca_host_path=ca_file,
-        mitmproxy_ca_cert_only_host_path=ca_file,
-    )
-    return dataclasses.replace(plan, egress_plan=egress_plan)
-
-
-def _stamp_agent_urls(
-    plan: MacosContainerBottlePlan, endpoint: GatewayEndpoint,
-) -> MacosContainerBottlePlan:
-    """Point the agent's git-gate insteadOf rewrites + supervise MCP at the
-    shared gateway's ports. Both bypass the egress proxy (NO_PROXY covers the
-    gateway address)."""
-    git_gate_url = (
-        f"http://{endpoint.gateway_ip}:{_GIT_HTTP_PORT}"
-        if plan.git_gate_plan.upstreams else ""
-    )
-    supervise_url = (
-        f"http://{endpoint.gateway_ip}:{SUPERVISE_PORT}/"
-        if plan.supervise_plan is not None else ""
-    )
-    return dataclasses.replace(
-        plan,
-        agent_git_gate_url=git_gate_url,
-        agent_supervise_url=supervise_url,
-    )
-
-
-def _proxy_url(gateway_ip: str, identity_token: str = "") -> str:
-    """The agent's egress proxy URL. The identity token rides as proxy
-    credentials — the gateway reads Proxy-Authorization, resolves the
-    (source_ip, token) pair against the control plane, and strips it before
-    upstream. Without a valid pair `/resolve` denies the request (#366)."""
-    cred = f"bottle:{identity_token}@" if identity_token else ""
-    return f"http://{cred}{gateway_ip}:{EGRESS_PORT}"
-
-
-def _no_proxy(gateway_ip: str) -> str:
-    # git-http + supervise live on the gateway and must NOT go through the
-    # egress proxy — the agent reaches them directly by its address.
-    return f"localhost,127.0.0.1,{gateway_ip}"
-
-
-def _identity_proxy_env(
-    endpoint: GatewayEndpoint, identity_token: str,
-) -> dict[str, str]:
-    """The token-bearing proxy env applied at `container exec`. It supersedes
-    the token-less run-time value (exec `--env` wins), which is the only way to
-    get the token in: it does not exist until after the container runs."""
-    if not identity_token:
-        return {}
-    url = _proxy_url(endpoint.gateway_ip, identity_token)
-    return {
-        "HTTPS_PROXY": url, "HTTP_PROXY": url,
-        "https_proxy": url, "http_proxy": url,
-    }
-
-
-def _start_agent(plan: MacosContainerBottlePlan, endpoint: GatewayEndpoint) -> None:
-    argv = _agent_run_argv(plan, endpoint)
-    env = {**os.environ, **plan.forwarded_env}
-    info(f"container run agent {plan.container_name}")
-    result = subprocess.run(
-        argv, capture_output=True, text=True, env=env, check=False,
-    )
-    if result.returncode != 0:
-        die(
-            f"container run for agent {plan.container_name} failed: "
-            f"{(result.stderr or '').strip() or '<no stderr>'}"
-        )
-
-
-def _agent_run_argv(
-    plan: MacosContainerBottlePlan, endpoint: GatewayEndpoint,
-) -> list[str]:
-    argv = [
-        "container", "run",
-        "--name", plan.container_name,
-        "--detach",
-        "--label", "bot-bottle.backend=macos-container",
-        "--network", endpoint.network,
-        # The attribution invariant: without NET_RAW the agent cannot open a
-        # raw socket, so it cannot source-IP-spoof its neighbours on the shared
-        # segment. NET_ADMIN is not granted by default, so its address and
-        # route are already fixed. See the module docstring.
-        "--cap-drop", "CAP_NET_RAW",
-    ]
-    for entry in _agent_env_entries(plan, endpoint):
-        argv += ["--env", entry]
-    # The init process is a no-op: every agent command arrives via
-    # `container exec`, which is also how the identity token gets in.
-    argv += [plan.image, "sleep", _AGENT_SLEEP_SECONDS]
-    return argv
-
-
-def _agent_env_entries(
-    plan: MacosContainerBottlePlan, endpoint: GatewayEndpoint,
-) -> tuple[str, ...]:
-    # Token-less at run time — the token does not exist yet (see
-    # `_identity_proxy_env`). Anything egressing before the exec-time override
-    # is denied by `/resolve`, which is the safe direction.
-    proxy_url = _proxy_url(endpoint.gateway_ip)
-    no_proxy = _no_proxy(endpoint.gateway_ip)
-    env = [
-        f"HTTPS_PROXY={proxy_url}",
-        f"HTTP_PROXY={proxy_url}",
-        f"https_proxy={proxy_url}",
-        f"http_proxy={proxy_url}",
-        f"NO_PROXY={no_proxy}",
-        f"no_proxy={no_proxy}",
-        f"NODE_EXTRA_CA_CERTS={AGENT_CA_PATH}",
-        f"SSL_CERT_FILE={AGENT_CA_BUNDLE}",
-        f"REQUESTS_CA_BUNDLE={AGENT_CA_BUNDLE}",
-    ]
-    if plan.agent_git_gate_url:
-        env.append(f"GIT_GATE_URL={plan.agent_git_gate_url}")
-    if plan.agent_supervise_url:
-        env.append(f"MCP_SUPERVISE_URL={plan.agent_supervise_url}")
-    for name, value in sorted(plan.agent_provision.guest_env.items()):
-        env.append(f"{name}={value}")
-    # Forwarded vars: bare name → inherits from the `container run` process env
-    # so the secret value never lands on argv.
-    for name in sorted(plan.forwarded_env.keys()):
-        env.append(name)
-    env.extend(egress_agent_env_entries(plan.egress_plan))
-    return tuple(env)
-
-
-__all__ = ["launch"]
+    yield  # unreachable — `die` raises; keeps this a generator/contextmanager

bot_bottle/backend/macos_container/util.py

@@ -437,145 +437,22 @@ def inspect_container(name: str) -> dict[str, object]:
 
 
 def container_ipv4_on_network(name: str, network: str) -> str:
-    """The container's IPv4 address on `network`. Fatal if absent — callers
-    that can tolerate "not yet" want `try_container_ipv4_on_network`."""
-    ip = try_container_ipv4_on_network(name, network)
-    if not ip:
-        die(f"container {name} has no IPv4 address on {network}")
-    return ip
-
-
-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.
-
-    `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 _inspect_first(argv: list[str]) -> dict[str, object]:
-    """Run an inspect command and return its first JSON object, or {} on any
-    failure (non-zero exit, malformed JSON, unexpected shape). {} is the shared
-    'don't know' signal all the non-fatal inspect readers below build on — a
-    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 {}
-    try:
-        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 ""
-    descriptor = node.get("descriptor")
-    if isinstance(descriptor, dict) and descriptor.get("digest"):
-        return _normalize_digest(str(descriptor["digest"]))
-    return ""
-
-
-def image_digest(ref: str) -> str:
-    """The digest of image `ref`, or "" if it can't be read. Reads exactly the
-    field `container_image_digest` reads (`configuration.descriptor.digest`) so
-    the two are comparable; "" means 'don't know' → callers don't churn."""
-    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."""
-    config = _inspect_first([_CONTAINER, "inspect", name]).get("configuration")
-    image = config.get("image") if isinstance(config, dict) else None
-    return _descriptor_digest(image)
-
-
-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."""
-    config = _inspect_first([_CONTAINER, "inspect", name]).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):
-        return {}
-    env: dict[str, str] = {}
-    for entry in entries:
-        if isinstance(entry, str) and "=" in entry:
-            key, value = entry.split("=", 1)
-            env[key] = value
-    return env
-
-
-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."""
-    status = _inspect_first([_CONTAINER, "inspect", name]).get("status")
+    data = inspect_container(name)
+    status = data.get("status")
     networks = status.get("networks") if isinstance(status, dict) else None
     if not isinstance(networks, list):
-        return ""
+        die(f"container inspect {name} did not include status.networks")
     for entry in networks:
-        if not isinstance(entry, dict) or entry.get("network") != network:
+        if not isinstance(entry, dict):
+            continue
+        if entry.get("network") != network:
             continue
         raw = entry.get("ipv4Address")
-        if isinstance(raw, str) and raw:
-            return raw.split("/", 1)[0]
-    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)
+        if not isinstance(raw, str) or not raw:
+            die(f"container {name} has no IPv4 address on {network}")
+        return raw.split("/", 1)[0]
+    die(f"container {name} is not attached to network {network}")
+    raise AssertionError("unreachable")
 
 
 def image_id(ref: str) -> str:

bot_bottle/bottle_state.py

@@ -31,7 +31,6 @@ from __future__ import annotations
 import dataclasses
 import json
 import secrets
-import socket
 import string
 from dataclasses import dataclass
 from pathlib import Path
@@ -44,7 +43,6 @@ 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
@@ -89,14 +87,6 @@ def bottle_identity(agent_name: str) -> str:
     return f"{slug}-{suffix}"
 
 
-def globalize_slug(slug: str) -> str:
-    """Return a globally-unique slug qualified with the current hostname.
-
-    Assumes slug is a value returned from mint_slug. Use wherever a slug
-    must be unique across hosts (e.g. deploy-key titles)."""
-    return f"{socket.gethostname()}-{slug}"
-
-
 @dataclass(frozen=True)
 class BottleMetadata:
     """Persistent record of how a bottle was launched, written at
@@ -201,15 +191,6 @@ 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
@@ -359,12 +340,10 @@ __all__ = [
     "BottleMetadata",
     "agent_state_dir",
     "bottle_identity",
-    "globalize_slug",
     "bottle_state_dir",
     "cleanup_state",
     "clear_preserve_marker",
     "committed_image_path",
-    "committed_rootfs_path",
     "egress_state_dir",
     "git_gate_state_dir",
     "is_preserved",

bot_bottle/cli/supervise.py

@@ -20,19 +20,32 @@ from datetime import datetime, timezone
 from pathlib import Path
 
 from ..paths import bot_bottle_root
-from ..log import Die, error, info
-from ..orchestrator.client import (
-    OrchestratorClient,
-    OrchestratorClientError,
-    discover_orchestrator_url,
+from ..bottle_state import read_metadata
+from ..backend.docker.egress_apply import (
+    EgressApplyError,
+    applicator as _docker_applicator,
 )
+from ..backend.macos_container.egress_apply import (
+    applicator as _macos_applicator,
+)
+from ..log import Die, error, info
 
 from ..supervise import (
+    COMPONENT_FOR_TOOL,
+    AuditEntry,
     Proposal,
+    Response,
+    STATUS_APPROVED,
+    STATUS_MODIFIED,
+    STATUS_REJECTED,
     TOOL_EGRESS_ALLOW,
     TOOL_EGRESS_BLOCK,
     TOOL_GITLEAKS_ALLOW,
     TOOL_EGRESS_TOKEN_ALLOW,
+    list_all_pending_proposals,
+    render_diff,
+    write_audit_entry,
+    write_response,
 )
 from ._common import PROG
 
@@ -47,61 +60,30 @@ _REPORT_ONLY_TOOLS: tuple[str, ...] = (TOOL_GITLEAKS_ALLOW, TOOL_EGRESS_TOKEN_AL
 
 @dataclass(frozen=True)
 class QueuedProposal:
-    """A pending proposal from the supervise queue.
-
-    `label` is the operator-facing bottle name (the human slug the
-    orchestrator resolved from the registry); `proposal.bottle_slug` is the
-    opaque bottle_id every operator action is keyed by. Display uses `label`;
-    respond calls use `proposal.bottle_slug`."""
+    """A pending proposal from the supervise queue."""
 
     proposal: Proposal
-    label: str = ""
 
 
-# A failed operator action (orchestrator unreachable, bottle torn down,
-# 409) is caught by the TUI key handlers and surfaced in the status line so
-# the proposal stays pending rather than crashing curses.
-ApplyError = (OrchestratorClientError,)
+# Errors any remediation engine may raise. Caught by the TUI key
+# handlers and surfaced in the status line so a failed apply keeps
+# the proposal pending rather than crashing curses.
+ApplyError = (EgressApplyError,)
 
 
-# The one per-host orchestrator, discovered lazily on first use. Every
-# operator action — list, approve, reject — goes through its HTTP control
-# plane (the orchestrator owns the single DB + live policy); there is no
-# direct-DB path and no backend branching here.
-_client_instance: OrchestratorClient | None = None
-
-
-def _resolve_orchestrator_url() -> str:
-    """URL of the running orchestrator control plane, starting one on demand.
-
-    Supervise is often the first thing an operator runs — before any bottle
-    has booted the control plane. So when discovery finds nothing, bring up
-    the selected backend's orchestrator + gateway (idempotent) rather than
-    failing with "launch a bottle first"."""
-    try:
-        return discover_orchestrator_url()
-    except OrchestratorClientError:
-        from ..backend import get_bottle_backend
-        backend = get_bottle_backend()
-        info(f"no orchestrator control plane running; starting one ({backend.name})…")
-        return backend.ensure_orchestrator()
-
-
-def _client() -> OrchestratorClient:
-    global _client_instance  # noqa: PLW0603 — CLI-session singleton
-    if _client_instance is None:
-        _client_instance = OrchestratorClient(_resolve_orchestrator_url())
-    return _client_instance
+def apply_routes_change(slug: str, content: str) -> tuple[str, str]:
+    meta = read_metadata(slug)
+    backend = meta.backend if meta is not None else ""
+    if backend == "macos-container":
+        return _macos_applicator.apply_routes_change(slug, content)
+    return _docker_applicator.apply_routes_change(slug, content)
 
 
 def discover_pending() -> list[QueuedProposal]:
-    """Collect pending proposals across bottles from the orchestrator."""
+    """Collect pending proposals across bottles."""
     out = [
-        QueuedProposal(
-            proposal=Proposal.from_dict(d),
-            label=str(d.get("bottle_label") or d.get("bottle_slug") or ""),
-        )
-        for d in _client().supervise_pending()
+        QueuedProposal(proposal=proposal)
+        for proposal in list_all_pending_proposals()
     ]
     out.sort(key=lambda q: q.proposal.arrival_timestamp)
     return out
@@ -109,8 +91,8 @@ def discover_pending() -> list[QueuedProposal]:
 
 def _approval_status(qp: QueuedProposal, verb: str) -> str:
     """Status-line text after a successful approval."""
-    base = f"{verb} {qp.proposal.tool} for [{qp.label}]"
-    return f"{base}; resume: ./cli.py resume {qp.label}"
+    base = f"{verb} {qp.proposal.tool} for [{qp.proposal.bottle_slug}]"
+    return f"{base}; resume: ./cli.py resume {qp.proposal.bottle_slug}"
 
 
 def _detail_lines(
@@ -121,7 +103,7 @@ def _detail_lines(
     """Return the detail-view body as (text, curses-attr) tuples."""
     p = qp.proposal
     out: list[tuple[str, int]] = [
-        (f"bottle: {qp.label}", 0),
+        (f"bottle: {p.bottle_slug}", 0),
         (f"tool: {p.tool}", 0),
         (f"id: {p.id}", 0),
         (f"arrived: {p.arrival_timestamp}", 0),
@@ -154,27 +136,39 @@ def approve(
     notes: str = "",
     final_file: str | None = None,
 ) -> None:
-    """Approve (or, with `final_file`, modify-then-approve) via the
-    orchestrator: it applies the route change to the bottle's live policy,
-    writes the response that unblocks the agent, and audits it — one atomic
-    server-side op. Raises `OrchestratorClientError` on failure."""
-    _client().supervise_respond(
-        qp.proposal.id,
-        bottle_slug=qp.proposal.bottle_slug,
-        decision="modify" if final_file is not None else "approve",
+    """Apply the proposal, write the waiting response, and audit it."""
+    status = STATUS_MODIFIED if final_file is not None else STATUS_APPROVED
+    file_to_apply = final_file if final_file is not None else qp.proposal.proposed_file
+
+    diff_before, diff_after = "", ""
+    if qp.proposal.tool in (TOOL_EGRESS_ALLOW, TOOL_EGRESS_BLOCK):
+        diff_before, diff_after = apply_routes_change(
+            qp.proposal.bottle_slug,
+            file_to_apply,
+        )
+
+    response = Response(
+        proposal_id=qp.proposal.id,
+        status=status,
         notes=notes,
         final_file=final_file,
     )
-
+    write_response(qp.proposal.bottle_slug, response)
+    _write_audit(
+        qp, action=status, notes=notes,
+        diff_before=diff_before, diff_after=diff_after,
+    )
 
 def reject(qp: QueuedProposal, *, reason: str) -> None:
-    """Reject via the orchestrator (writes the response + audit)."""
-    _client().supervise_respond(
-        qp.proposal.id,
-        bottle_slug=qp.proposal.bottle_slug,
-        decision="reject",
+    """Write a rejection response and an audit entry."""
+    response = Response(
+        proposal_id=qp.proposal.id,
+        status=STATUS_REJECTED,
         notes=reason,
+        final_file=None,
     )
+    write_response(qp.proposal.bottle_slug, response)
+    _write_audit(qp, action=STATUS_REJECTED, notes=reason, diff_before="", diff_after="")
 
 
 def _approve_from_tui(
@@ -194,6 +188,29 @@ def _approve_from_tui(
     return _approval_status(qp, verb)
 
 
+def _write_audit(
+    qp: QueuedProposal,
+    *,
+    action: str,
+    notes: str,
+    diff_before: str,
+    diff_after: str,
+) -> None:
+    """Audit log for egress tool."""
+    component = COMPONENT_FOR_TOOL.get(qp.proposal.tool)
+    if component is None:
+        return
+    write_audit_entry(AuditEntry(
+        timestamp=datetime.now(timezone.utc).isoformat(),
+        bottle_slug=qp.proposal.bottle_slug,
+        component=component,
+        operator_action=action,
+        operator_notes=notes,
+        justification=qp.proposal.justification,
+        diff=render_diff(diff_before, diff_after, label=component),
+    ))
+
+
 # --- $EDITOR integration --------------------------------------------------
 
 
@@ -228,20 +245,6 @@ def cmd_supervise(argv: list[str]) -> int:
     )
     args = parser.parse_args(argv)
 
-    # Establish the orchestrator connection up front so a missing control
-    # plane is a clean one-line error, not a curses crash mid-loop. This also
-    # starts the orchestrator on demand when none is running (see `_client`).
-    try:
-        _client()
-    except OrchestratorClientError as e:
-        error(str(e))
-        return 1
-    except Die as e:
-        # Backend has no orchestrator to start (e.g. macos-container).
-        if e.message:
-            error(e.message)
-        return e.code if isinstance(e.code, int) else 1
-
     if args.once:
         return _list_once()
     try:
@@ -296,7 +299,7 @@ def _list_once() -> int:
     for qp in pending:
         sys.stdout.write(
             f"{qp.proposal.arrival_timestamp}  "
-            f"[{qp.label}]  "
+            f"[{qp.proposal.bottle_slug}]  "
             f"{qp.proposal.tool}  "
             f"{qp.proposal.id}\n"
         )
@@ -393,7 +396,7 @@ def _main_loop(stdscr: "curses._CursesWindow") -> None:  # type: ignore  # pragm
             reason = _prompt(stdscr, "reject reason: ")
             if reason:
                 reject(qp, reason=reason)
-                status_line = f"rejected {qp.proposal.tool} for [{qp.label}]"
+                status_line = f"rejected {qp.proposal.tool} for [{qp.proposal.bottle_slug}]"
             else:
                 status_line = "reject aborted (empty reason)"
 
@@ -432,7 +435,7 @@ def _render(
             cursor = "> " if i == selected else "  "
             line = (
                 f"{cursor}{ts_short}  "
-                f"[{qp.label}]  {p.tool:<18}  {p.id[:8]}"
+                f"[{p.bottle_slug}]  {p.tool:<18}  {p.id[:8]}"
             )
             attr = curses.A_REVERSE if i == selected else curses.A_NORMAL
             stdscr.addnstr(row, 0, line, w - 1, attr)

bot_bottle/contrib/claude/agent_provider.py

@@ -32,8 +32,6 @@ if TYPE_CHECKING:
 
 
 _SUPERVISE_MCP_NAME = "supervise"
-# App-layer identity token header (mirrors egress_addon / git_http_backend).
-_IDENTITY_HEADER = "x-bot-bottle-identity"
 
 
 def _skills_dir(guest_home: str) -> str:
@@ -303,15 +301,9 @@ class ClaudeAgentProvider(AgentProvider):
         if plan.supervise_plan is None:
             return
         info(f"registering supervise MCP server in agent claude config → {supervise_url}")
-        # Deliver the identity token as an MCP request header — the supervise
-        # daemon requires it (mandatory (source_ip, token) attribution).
-        token = getattr(plan, "identity_token", "")
-        header = (
-            f" --header {shlex.quote(f'{_IDENTITY_HEADER}: {token}')}" if token else ""
-        )
         r = bottle.exec(
             f"claude mcp add --scope user --transport http "
-            f"{_SUPERVISE_MCP_NAME} {supervise_url}{header}",
+            f"{_SUPERVISE_MCP_NAME} {supervise_url}",
             user="node",
         )
         if r.returncode != 0:

bot_bottle/contrib/codex/agent_provider.py

@@ -9,7 +9,6 @@ invocation that registers the supervise daemon in Codex's
 
 from __future__ import annotations
 
-import base64
 import os
 import shlex
 from pathlib import Path
@@ -27,7 +26,7 @@ from ...agent_provider import (
 )
 from .codex_auth import codex_host_access_token, write_codex_dummy_auth_file
 from ...egress import CODEX_HOST_CREDENTIAL_TOKEN_REF, EgressRoute
-from ...log import die, info
+from ...log import die, info, warn
 
 
 if TYPE_CHECKING:
@@ -35,8 +34,6 @@ if TYPE_CHECKING:
 
 
 _SUPERVISE_MCP_NAME = "supervise"
-# App-layer identity token header (mirrors egress_addon / git_http_backend).
-_IDENTITY_HEADER = "x-bot-bottle-identity"
 _CODEX_CLI = "/home/node/.codex/packages/standalone/current/bin/codex"
 _CODEX_CLI_PATH = (
     "/home/node/.local/bin:"
@@ -45,41 +42,6 @@ _CODEX_CLI_PATH = (
 )
 
 
-def _toml_basic_string(value: str) -> str:
-    """Quote `value` as a TOML basic (double-quoted) string."""
-    escaped = (
-        value.replace("\\", "\\\\")
-        .replace('"', '\\"')
-        .replace("\n", "\\n")
-        .replace("\t", "\\t")
-    )
-    return f'"{escaped}"'
-
-
-def _supervise_mcp_config_toml(supervise_url: str, token: str) -> str:
-    """Render the `[mcp_servers.supervise]` streamable-HTTP entry for
-    Codex's `config.toml`.
-
-    The Codex CLI has no `mcp add --header` flag; a static request
-    header on an HTTP MCP server is only expressible via the
-    `http_headers` config key (see `RawMcpServerConfig` /
-    `McpServerTransportConfig::StreamableHttp`). We deliver the
-    mandatory identity token (source_ip, token attribution) that way.
-    Only Codex-supported streamable-HTTP keys (`url`, `http_headers`)
-    are emitted."""
-    lines = [
-        "",
-        f"[mcp_servers.{_SUPERVISE_MCP_NAME}]",
-        f"url = {_toml_basic_string(supervise_url)}",
-    ]
-    if token:
-        key = _toml_basic_string(_IDENTITY_HEADER)
-        val = _toml_basic_string(token)
-        lines.append(f"http_headers = {{ {key} = {val} }}")
-    lines.append("")
-    return "\n".join(lines)
-
-
 def _skills_dir(guest_home: str) -> str:
     # Codex agents still read skills from the claude-code convention
     # (~/.claude/skills/) — the bot-bottle-codex image follows the
@@ -304,39 +266,25 @@ class CodexAgentProvider(AgentProvider):
         bottle: "Bottle",
         supervise_url: str,
     ) -> None:
-        """Register the supervise daemon as a streamable-HTTP MCP
-        server in Codex's user config (`~/.codex/config.toml`).
+        """Run `codex mcp add` inside the agent guest to register the
+        supervise daemon in Codex's user config (~/.codex/config.toml).
 
-        We write the `[mcp_servers.supervise]` entry directly rather
-        than shelling out to `codex mcp add`: the CLI's `add` has no
-        way to attach a static request header, and the identity token
-        (mandatory (source_ip, token) attribution) MUST ride on the
-        MCP request as `http_headers`. Failure is FATAL when supervise
-        is enabled — a silently-unregistered server leaves the agent
-        with no supervise access and, under mandatory attribution, no
-        way to recover from inside the bottle."""
+        Mirrors the Claude provider's `claude mcp add` flow — failure
+        is logged but not fatal."""
         if plan.supervise_plan is None:
             return
         info(f"registering supervise MCP server in agent codex config → {supervise_url}")
-        token = getattr(plan, "identity_token", "")
-        block = _supervise_mcp_config_toml(supervise_url, token)
-        auth_dir = plan.agent_provision.guest_env.get("CODEX_HOME") \
-            or f"{plan.guest_home}/.codex"
-        config_path = f"{auth_dir}/config.toml"
-        # Append via base64 so the TOML payload never has to survive a
-        # shell-quoting round trip. node owns the config file, so append
-        # as node to preserve ownership/mode.
-        payload = base64.b64encode(block.encode()).decode()
-        script = (
-            f"printf %s {shlex.quote(payload)} | base64 -d "
-            f">> {shlex.quote(config_path)}"
+        r = bottle.exec(
+            f"{shlex.quote(_CODEX_CLI)} mcp add {_SUPERVISE_MCP_NAME} --url "
+            f"{shlex.quote(supervise_url)}",
+            user="node",
         )
-        r = bottle.exec(script, user="node")
         if r.returncode != 0:
-            die(
-                "agent provider provisioning: could not register supervise "
-                f"MCP server in {config_path}: "
-                f"{(r.stderr or r.stdout or '').strip()}"
+            warn(
+                f"`codex mcp add supervise` failed (exit {r.returncode}): "
+                f"{(r.stderr or r.stdout or '').strip()}. Inside the bottle, "
+                f"register manually with: "
+                f"codex mcp add supervise --url {shlex.quote(supervise_url)}"
             )
 
     def headless_prompt(self, prompt: str) -> list[str]:

bot_bottle/docker_cmd.py

@@ -14,20 +14,13 @@ from __future__ import annotations
 import subprocess
 
 
-def run_docker(
-    argv: list[str], *, env: dict[str, str] | None = None,
-) -> subprocess.CompletedProcess[str]:
+def run_docker(argv: list[str]) -> 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).
-
-    `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."""
+    already-absent container)."""
     return subprocess.run(
-        argv, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True,
-        check=False, env=env,
+        argv, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, check=False,
     )
 
 

bot_bottle/egress_addon.py

@@ -6,8 +6,6 @@ egress container."""
 from __future__ import annotations
 
 import asyncio
-import base64
-import binascii
 import json
 import os
 import signal
@@ -71,38 +69,10 @@ INTROSPECT_HOST = "_egress.local"
 # → legacy per-bottle single-tenant mode (unchanged).
 ORCHESTRATOR_URL_ENV = "BOT_BOTTLE_ORCHESTRATOR_URL"
 
-# App-layer identity token. Delivered as proxy credentials
-# (`HTTPS_PROXY=http://<bottle_id>:<token>@gw`): clients honor it as part of
-# the proxy protocol without app changes, and the addon reads + strips it so
-# it never leaks upstream. The legacy `x-bot-bottle-identity` request header
-# is still stripped defensively (git-http uses that header on its own port).
+# App-layer identity token (defense-in-depth over the source-IP invariant);
+# the agent injects it, the addon strips it so it never leaks upstream.
 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:
-    Basic base64(<bottle_id>:<token>)` header. Empty on any malformed value —
-    the mandatory `/resolve` then fail-closes on the empty token."""
-    scheme, _, encoded = header.partition(" ")
-    if scheme.lower() != "basic" or not encoded:
-        return ""
-    try:
-        decoded = base64.b64decode(encoded, validate=True).decode("utf-8")
-    except (binascii.Error, ValueError, UnicodeDecodeError):
-        return ""
-    _, _, password = decoded.partition(":")
-    return password
-
 # Seconds the egress proxy holds a token-blocked request open waiting for the
 # operator's supervisor decision (PRD 0062), overridable via env.
 DEFAULT_TOKEN_ALLOW_TIMEOUT_SECONDS = 300.0
@@ -122,10 +92,6 @@ class EgressAddon:
     # Class default so addons built via __new__ (e.g. in tests) default to
     # single-tenant; __init__ sets the instance attribute for real runs.
     _resolver: "PolicyResolver | None" = None
-    # Class default so __new__-built addons have it (real runs get a fresh
-    # per-instance dict in __init__; only http_connect mutates it, which the
-    # request-flow tests don't exercise).
-    _conn_tokens: "dict[str, str]" = {}
 
     def __init__(self) -> None:
         self.routes_path = os.environ.get("EGRESS_ROUTES", DEFAULT_ROUTES_PATH)
@@ -140,10 +106,6 @@ class EgressAddon:
         # scan. In-memory only (a restart re-prompts); mutated only from the
         # asyncio loop that runs the addon hooks, so no lock is needed.
         self._safe_tokens: dict[str, set[str]] = {}
-        # Per-client-connection identity token captured from the CONNECT's
-        # `Proxy-Authorization` (HTTPS tunnels don't repeat it on the bumped
-        # inner requests). Keyed by client_conn.id; cleared on disconnect.
-        self._conn_tokens: dict[str, str] = {}
         self._supervise_slug = os.environ.get("SUPERVISE_BOTTLE_SLUG", "").strip()
         self._token_allow_timeout = _token_allow_timeout_from_env(os.environ)
         self._reload(initial=True)
@@ -233,39 +195,31 @@ class EgressAddon:
             {"Content-Type": "text/plain; charset=utf-8"},
         )
 
-    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.
+    def _log_request(self, flow: http.HTTPFlow) -> None:
         headers = {
-            k: redact_tokens(v, env=env)
+            k: redact_tokens(v, env=os.environ)
             for k, v in flow.request.headers.items()
             if k.lower() != "authorization"
         }
-        body = redact_tokens(flow.request.get_text(strict=False) or "", env=env)
+        body = redact_tokens(flow.request.get_text(strict=False) or "", env=os.environ)
         sys.stderr.write(
             json.dumps({
                 "event": "egress_request",
-                "host": redact_tokens(flow.request.pretty_host, env=env),
+                "host": redact_tokens(flow.request.pretty_host, env=os.environ),
                 "method": flow.request.method,
-                "path": redact_tokens(flow.request.path, env=env),
+                "path": redact_tokens(flow.request.path, env=os.environ),
                 "headers": headers,
                 "body": body,
             })
             + "\n"
         )
 
-    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.
+    def _log_response(self, flow: http.HTTPFlow) -> None:
         headers = {
-            k: redact_tokens(v, env=env)
+            k: redact_tokens(v, env=os.environ)
             for k, v in flow.response.headers.items()
         }
-        body = redact_tokens(flow.response.get_text(strict=False) or "", env=env)
+        body = redact_tokens(flow.response.get_text(strict=False) or "", env=os.environ)
         sys.stderr.write(
             json.dumps({
                 "event": "egress_response",
@@ -293,72 +247,12 @@ class EgressAddon:
             return self.config, self._supervise_slug, os.environ
         conn = flow.client_conn
         client_ip = conn.peername[0] if conn and conn.peername else ""
-        token = self._request_token(flow)
+        token = flow.request.headers.get(IDENTITY_HEADER, "")
+        flow.request.headers.pop(IDENTITY_HEADER, None)
         config, slug, tokens = resolve_client_context(self._resolver, client_ip, token)
         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`)
-        that clients honor without app changes. Plain-HTTP requests carry
-        `Proxy-Authorization` directly; HTTPS bumped requests inherit the token
-        captured from their tunnel's CONNECT. Read then stripped so it never
-        leaks upstream (also strips the legacy header, if present)."""
-        token = _token_from_proxy_auth(
-            flow.request.headers.get("Proxy-Authorization", ""))
-        flow.request.headers.pop("Proxy-Authorization", None)
-        flow.request.headers.pop(IDENTITY_HEADER, None)
-        conn = flow.client_conn
-        if not token and conn is not None:
-            token = self._conn_tokens.get(getattr(conn, "id", ""), "")
-        return token
-
-    def http_connect(self, flow: http.HTTPFlow) -> None:
-        """Capture the identity token from an HTTPS tunnel's CONNECT (the inner
-        bumped requests won't carry `Proxy-Authorization`), keyed by client
-        connection, and strip it so it never reaches upstream."""
-        token = _token_from_proxy_auth(
-            flow.request.headers.get("Proxy-Authorization", ""))
-        flow.request.headers.pop("Proxy-Authorization", None)
-        conn = flow.client_conn
-        if conn is not None and getattr(conn, "id", ""):
-            self._conn_tokens[conn.id] = token
-
-    def client_disconnected(self, client: typing.Any) -> None:
-        """Drop the per-connection token when the client goes away."""
-        self._conn_tokens.pop(getattr(client, "id", ""), None)
-
     async def request(self, flow: http.HTTPFlow) -> None:
         request_path, _, query = flow.request.path.partition("?")
 
@@ -367,9 +261,6 @@ 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.
@@ -428,7 +319,7 @@ class EgressAddon:
             flow.request.headers["authorization"] = decision.inject_authorization
 
         if config.log >= LOG_FULL:
-            self._log_request(flow, env)
+            self._log_request(flow)
 
     def _block_dlp(self, flow: http.HTTPFlow, result: ScanResult) -> None:
         ctx = self._req_ctx(flow)
@@ -637,17 +528,14 @@ 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, against the calling
-        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)
+        """DLP inbound scan on response headers and body."""
+        route = match_route(self.config.routes, flow.request.pretty_host)
         if route is None:
             return
         if flow.response is None:
             return
-        if config.log >= LOG_FULL:
-            self._log_response(flow, env)
+        if self.config.log >= LOG_FULL:
+            self._log_response(flow)
         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)
@@ -664,7 +552,7 @@ 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 config.log >= LOG_BLOCKS:
+        elif result.severity == "warn" and self.config.log >= LOG_BLOCKS:
             sys.stderr.write(
                 json.dumps({
                     "event": "egress_warn",
@@ -675,10 +563,7 @@ class EgressAddon:
             )
 
     def websocket_message(self, flow: http.HTTPFlow) -> None:
-        """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.
+        """DLP scan on WebSocket frames.
 
         Outbound frames (from_client) are scanned for credential leakage;
         inbound frames are scanned for prompt injection.  On a block the
@@ -687,8 +572,10 @@ class EgressAddon:
         """
         if flow.websocket is None:  # type: ignore[union-attr]
             return
-        config, slug, env = self._flow_ctx(flow)
-        route = match_route(config.routes, flow.request.pretty_host)
+        # WebSocket DLP runs against the static config only (single-tenant); in
+        # the consolidated gateway self.config has no routes, so this is inert
+        # 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]
@@ -697,8 +584,8 @@ 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, env,
-                safe_tokens=self._safe_tokens_for(slug), crlf_text="",
+                route, content, os.environ,
+                safe_tokens=self._safe_tokens_for(self._supervise_slug), crlf_text="",
             )
             if result is not None and result.severity == "block":
                 sys.stderr.write(f"egress DLP: {result.reason}\n")

bot_bottle/git_gate_provision.py

@@ -13,7 +13,6 @@ import dataclasses
 from pathlib import Path
 from typing import TYPE_CHECKING
 
-from .bottle_state import globalize_slug
 from .errors import MissingEnvVarError
 from .log import info
 from .manifest import ManifestBottle, ManifestGitEntry
@@ -47,7 +46,7 @@ def _provision_dynamic_key(
     owner_repo = entry.UpstreamPath
     if owner_repo.endswith(".git"):
         owner_repo = owner_repo[:-4]
-    title = f"bot-bottle:{globalize_slug(slug)}:{entry.Name}"
+    title = f"bot-bottle:{slug}:{entry.Name}"
 
     info(f"provisioning deploy key for git-gate.repos[{entry.Name!r}]")
     key_id, private_key_bytes = provisioner.create(owner_repo, title)

bot_bottle/git_gate_render.py

@@ -19,9 +19,6 @@ from .manifest import ManifestBottle, ManifestGitEntry
 # Short network alias for git-gate inside the gateway. The
 # agent's `.gitconfig` insteadOf rewrites resolve through this name.
 GIT_GATE_HOSTNAME = "git-gate"
-# App-layer identity token header the agent's git sends to git-http and the
-# gateway validates (mirrors egress_addon / git_http_backend IDENTITY_HEADER).
-IDENTITY_HEADER = "x-bot-bottle-identity"
 # Shared timeout (seconds) for all git-gate subprocess and CGI calls:
 # git daemon (--timeout/--init-timeout), the access-hook subprocess in
 # git_http_backend, and the git http-backend CGI subprocess.
@@ -78,7 +75,6 @@ def _gitconfig_validate_value(field: str, value: str) -> None:
 
 def git_gate_render_gitconfig(
     entries: tuple[ManifestGitEntry, ...], gate_host: str, *, scheme: str = "git",
-    identity_token: str = "",
 ) -> str:
     """Render the agent's ~/.gitconfig content for git-gate
     `insteadOf` rewrites. Pure host-side, no docker / VM;
@@ -100,15 +96,6 @@ def git_gate_render_gitconfig(
         "# the upstream bidirectionally (gitleaks-scanned push;\n",
         "# fetch-from-upstream-before-every-upload-pack via access-hook).\n",
     ]
-    # Over the smart-HTTP transport (VM backends), attach the per-bottle
-    # identity token as a request header on requests to the gate, scoped to
-    # its URL so it never goes to any other remote. git-http requires it (the
-    # gateway's mandatory (source_ip, token) attribution). git:// (single-tenant
-    # docker) carries no header — attribution there is the network alias.
-    if identity_token and scheme == "http":
-        _gitconfig_validate_value("identity_token", identity_token)
-        out.append(f'[http "http://{gate_host}/"]\n')
-        out.append(f"\textraHeader = {IDENTITY_HEADER}: {identity_token}\n")
     for entry in entries:
         _gitconfig_validate_value(f"repos[{entry.Name!r}].url", entry.Upstream)
         out.append(f'[url "{scheme}://{gate_host}/{entry.Name}.git"]\n')

bot_bottle/orchestrator/__main__.py

@@ -16,7 +16,6 @@ import secrets
 from pathlib import Path
 
 from .. import log
-from ..store_manager import StoreManager
 from .broker import LaunchBroker, StubBroker
 from .control_plane import make_server
 from .docker_broker import DockerBroker
@@ -46,11 +45,6 @@ def main(argv: list[str] | None = None) -> int:
 
     registry = RegistryStore(args.db)
     registry.migrate()
-    # One DB per host: the supervise queue + audit tables live in the SAME
-    # SQLite file the registry owns, so the control plane is the single
-    # source of truth. The in-VM supervise daemon writes here; the host
-    # operator reaches it over HTTP (never a second, disconnected DB).
-    StoreManager(registry.db_path).migrate()
 
     # An ephemeral signing secret ties the orchestrator (signer) to its
     # broker (verifier). 'stub' records launches instead of starting

bot_bottle/orchestrator/client.py

@@ -17,22 +17,9 @@ 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)."""
 
@@ -47,24 +34,11 @@ class RegisteredBottle:
 
 
 class OrchestratorClient:
-    """Trusted host-side client for the orchestrator control plane.
+    """Trusted host-side client for the orchestrator control plane."""
 
-    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:
+    def __init__(self, base_url: str, *, timeout: float = DEFAULT_TIMEOUT_SECONDS) -> 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,
@@ -75,8 +49,6 @@ 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,
         )
@@ -163,78 +135,10 @@ class OrchestratorClient:
         bottles = payload.get("bottles")
         return bottles if isinstance(bottles, list) else []
 
-    # --- supervise queue (operator TUI) ------------------------------------
-
-    def supervise_pending(self) -> list[dict[str, object]]:
-        """Pending supervise proposals across all bottles
-        (`GET /supervise/proposals`)."""
-        payload = self._ok("GET", "/supervise/proposals")
-        proposals = payload.get("proposals")
-        return proposals if isinstance(proposals, list) else []
-
-    def supervise_respond(
-        self,
-        proposal_id: str,
-        *,
-        bottle_slug: str,
-        decision: str,
-        notes: str = "",
-        final_file: str | None = None,
-    ) -> None:
-        """Record an operator decision (`POST /supervise/respond`). `decision`
-        is approve/modify/reject. Raises `OrchestratorClientError` if the
-        proposal is gone or the bottle can no longer be applied to (409)."""
-        body: dict[str, object] = {
-            "proposal_id": proposal_id,
-            "bottle_slug": bottle_slug,
-            "decision": decision,
-            "notes": notes,
-        }
-        if final_file is not None:
-            body["final_file"] = final_file
-        self._ok("POST", "/supervise/respond", body)
-
-
-def discover_orchestrator_url(*, timeout: float = 2.0) -> str:
-    """The URL of the one running per-host orchestrator control plane, probing
-    the backends' well-known control-plane addresses (both on port 8099):
-    docker publishes it on loopback; the firecracker infra VM serves it on the
-    orchestrator TAP. Returns the first that answers `/health`; raises if none
-    do (no orchestrator up — launch a bottle first)."""
-    candidates: list[str] = []
-    try:  # docker: loopback-published control plane
-        from .lifecycle import DEFAULT_PORT as _DOCKER_PORT
-        candidates.append(f"http://127.0.0.1:{_DOCKER_PORT}")
-    except Exception:  # noqa: BLE001 — backend optional
-        candidates.append("http://127.0.0.1:8099")
-    try:  # firecracker: infra VM control plane on the orchestrator TAP
-        from ..backend.firecracker import netpool
-        from ..backend.firecracker.infra_vm import CONTROL_PLANE_PORT
-        candidates.append(
-            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
-    raise OrchestratorClientError(
-        "no running orchestrator control plane found (tried "
-        + ", ".join(candidates)
-        + "); launch a bottle first"
-    )
-
 
 __all__ = [
     "OrchestratorClient",
     "OrchestratorClientError",
     "RegisteredBottle",
     "DEFAULT_TIMEOUT_SECONDS",
-    "discover_orchestrator_url",
 ]

bot_bottle/orchestrator/control_plane.py

@@ -16,10 +16,6 @@ vsock / unix-socket portability caveats):
     POST   /attribute                 -> 200 {"bottle_id"} | 403
     POST   /resolve                   -> 200 {"bottle_id","policy"} | 403
                                          body: {"source_ip","identity_token"}
-    GET    /supervise/proposals       -> 200 {"proposals": [ <proposal>, ...]}
-    POST   /supervise/respond         -> 200 {"responded": true} | 409  (operator)
-                                         body: {"proposal_id","bottle_slug",
-                                                "decision", ["notes"],["final_file"]}
 
 `POST /bottles` / `DELETE` drive the full launch lifecycle: they mint (or
 tear down) the bottle in the registry AND broker the backend-native launch
@@ -34,7 +30,6 @@ returned only once, to the caller that launches the bottle.
 
 from __future__ import annotations
 
-import hmac
 import http.server
 import json
 import os
@@ -43,20 +38,11 @@ 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."""
@@ -69,29 +55,15 @@ 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, *, authorized: bool = True,
+    orch: Orchestrator, method: str, path: str, body: bytes
 ) -> 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.
-
-    `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."""
+    no I/O beyond the orchestrator — so it is fully testable without a socket."""
     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()
 
@@ -155,44 +127,10 @@ def dispatch(  # pylint: disable=too-many-return-statements,too-many-branches
             return 403, {"error": "unattributed"}
         return 200, {"bottle_id": rec.bottle_id}
 
-    if method == "GET" and route == "/supervise/proposals":
-        # Operator TUI: pending supervise proposals across all bottles.
-        return 200, {"proposals": orch.supervise_pending()}
-
-    if method == "POST" and route == "/supervise/respond":
-        # Operator decision: apply (approve/modify rewrites egress policy),
-        # write the queued response, audit — all server-side on the one DB.
-        try:
-            data = _parse_json_object(body)
-        except ValueError as e:
-            return 400, {"error": f"invalid JSON: {e}"}
-        proposal_id = data.get("proposal_id")
-        bottle_slug = data.get("bottle_slug")
-        decision = data.get("decision")
-        if not (isinstance(proposal_id, str) and proposal_id):
-            return 400, {"error": "proposal_id (string) is required"}
-        if not (isinstance(bottle_slug, str) and bottle_slug):
-            return 400, {"error": "bottle_slug (string) is required"}
-        if not (isinstance(decision, str) and decision):
-            return 400, {"error": "decision (string) is required"}
-        notes = data.get("notes")
-        final_file = data.get("final_file")
-        ok, err = orch.supervise_respond(
-            proposal_id,
-            bottle_slug=bottle_slug,
-            decision=decision,
-            notes=notes if isinstance(notes, str) else "",
-            final_file=final_file if isinstance(final_file, str) else None,
-        )
-        if ok:
-            return 200, {"responded": True}
-        return 409, {"error": err}
-
     if method == "POST" and route == "/resolve":
         # The per-request lookup the multi-tenant gateway makes: returns the
-        # bottle's policy. Requires a matching (source_ip, identity_token)
-        # pair — a missing/empty/mismatched token fail-closes (403), no
-        # source-IP-only fallback.
+        # bottle's policy. identity_token is OPTIONAL — absent means resolve
+        # by source IP alone (network-layer attribution).
         try:
             data = _parse_json_object(body)
         except ValueError as e:
@@ -233,10 +171,8 @@ 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, authorized=authorized)
+            status, payload = dispatch(server.orchestrator, method, self.path, body)
         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()
@@ -262,40 +198,15 @@ class Handler(http.server.BaseHTTPRequestHandler):
 
 
 class ControlPlaneServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
-    """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)."""
+    """Threading HTTP server that carries the orchestrator for its handlers."""
 
     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
@@ -305,7 +216,4 @@ def make_server(
     return ControlPlaneServer((host, port), orchestrator)
 
 
-__all__ = [
-    "dispatch", "Handler", "ControlPlaneServer", "make_server", "Json",
-    "CONTROL_AUTH_HEADER",
-]
+__all__ = ["dispatch", "Handler", "ControlPlaneServer", "make_server", "Json"]

bot_bottle/orchestrator/gateway.py

@@ -23,17 +23,6 @@ import time
 from pathlib import Path
 
 from ..docker_cmd import run_docker
-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
-# writes its queued proposals into the ONE host DB (the same file the
-# orchestrator container opens and the operator reaches over HTTP).
-_SUPERVISE_DB_DIR_IN_CONTAINER = os.path.dirname(DB_PATH_IN_CONTAINER)
 
 # The gateway's mitmproxy writes its CA a beat after the container starts, so
 # reads poll for it rather than assuming it's there on a fresh launch.
@@ -65,14 +54,6 @@ GATEWAY_DOCKERFILE = "Dockerfile.gateway"
 _REPO_ROOT = Path(__file__).resolve().parents[2]
 
 
-def _host_db_dir() -> str:
-    """The host DB directory (created if missing), for the gateway's
-    supervise-DB bind-mount."""
-    db_dir = host_db_path().parent
-    db_dir.mkdir(parents=True, exist_ok=True)
-    return str(db_dir)
-
-
 class GatewayError(Exception):
     """The shared gateway failed to build/start/stop (non-zero `docker` exit)."""
 
@@ -211,27 +192,15 @@ class DockerGateway(Gateway):
             # Persist the self-generated CA so it survives restarts (agents
             # trust it) — see GATEWAY_CA_VOLUME.
             "--volume", f"{GATEWAY_CA_VOLUME}:{MITMPROXY_HOME}",
-            # Share the one host DB: the supervise daemon queues proposals
-            # into the same file the orchestrator (and the operator, over
-            # HTTP) reads — no second, disconnected DB in the container.
-            "--volume", f"{_host_db_dir()}:{_SUPERVISE_DB_DIR_IN_CONTAINER}",
-            "--env", f"SUPERVISE_DB_PATH={DB_PATH_IN_CONTAINER}",
         ]
         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, env=run_env)
+        proc = run_docker(argv)
         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 CONTROL_PLANE_TOKEN_ENV, bot_bottle_root, host_control_plane_token
-from .gateway import GATEWAY_IMAGE, GATEWAY_NAME, GATEWAY_NETWORK, DockerGateway, GatewayError
+from ..paths import bot_bottle_root
+from .gateway import GATEWAY_IMAGE, GATEWAY_NETWORK, DockerGateway, GatewayError
 
 DEFAULT_PORT = 8099
 ORCHESTRATOR_NAME = "bot-bottle-orchestrator"
@@ -41,7 +41,7 @@ ORCHESTRATOR_IMAGE = os.environ.get(
 ORCHESTRATOR_DOCKERFILE = "Dockerfile.orchestrator"
 # Baked onto the container as a label so `ensure_running` can tell whether the
 # running process is executing the *current* bind-mounted source — see
-# `source_hash`.
+# `_source_hash`.
 ORCHESTRATOR_SOURCE_HASH_LABEL = "bot-bottle-orchestrator-source-hash"
 
 # The repo root is bind-mounted into the control-plane container so
@@ -60,7 +60,7 @@ class OrchestratorStartError(RuntimeError):
     """The orchestrator container did not become healthy within the timeout."""
 
 
-def source_hash(repo_root: Path) -> str:
+def _source_hash(repo_root: Path) -> str:
     """Content hash of the orchestrator's bind-mounted Python source (the
     `bot_bottle` package the control-plane process imports). This only
     changes when the code that would actually run inside the container
@@ -83,11 +83,8 @@ 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`); `gateway_name` gives the paired
-    gateway container the same treatment (e.g. isolated integration tests
-    that can't share the production `GATEWAY_NAME` singleton). Subclass and
-    override `_gateway()` for anything `_gateway_image`/`gateway_name` can't
-    express (a genuinely backend-specific gateway variant)."""
+    backend's `bot-bottle-orchestrator`). Subclass and override `_gateway()`
+    to supply a backend-specific gateway variant."""
 
     def __init__(
         self,
@@ -96,7 +93,6 @@ 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,
@@ -110,7 +106,6 @@ 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
@@ -139,24 +134,20 @@ class OrchestratorService:
         proc = run_docker(["docker", "ps", "--filter", f"name=^/{name}$", "--format", "{{.Names}}"])
         return name in proc.stdout.split()
 
-    def _run_orchestrator_container(self, current_hash: str) -> None:
+    def _run_orchestrator_container(self, source_hash: str) -> None:
         """Start the control-plane container (idempotent: clears a stale
         fixed-name container first). Register-only broker → no docker socket.
-        Labels the container with `current_hash` so a later `ensure_running`
-        can detect a real code change (see `source_hash`)."""
+        Labels the container with `source_hash` so a later `ensure_running`
+        can detect a real code change (see `_source_hash`)."""
         run_docker(["docker", "rm", "--force", self._orchestrator_name])
         proc = run_docker([
             "docker", "run", "--detach",
             "--name", self._orchestrator_name,
             "--label", self._orchestrator_label,
-            "--label", f"{ORCHESTRATOR_SOURCE_HASH_LABEL}={current_hash}",
+            "--label", f"{ORCHESTRATOR_SOURCE_HASH_LABEL}={source_hash}",
             "--network", self.network,
             # Host CLI reaches the control plane here; bound to loopback so it
-            # is not exposed on the host's external interfaces. NOTE: the
-            # container is still on `self.network` (the shared gateway network),
-            # so agents can reach it by container IP — which is exactly why the
-            # control plane requires the secret below rather than trusting the
-            # network boundary.
+            # is not exposed on the host's external interfaces.
             "--publish", f"127.0.0.1:{self.port}:{self.port}",
             "--volume", f"{self._repo_root}:{_APP_DIR}:ro",
             "--workdir", _APP_DIR,
@@ -164,15 +155,11 @@ 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()}"
@@ -180,10 +167,7 @@ class OrchestratorService:
 
     def _gateway(self) -> DockerGateway:
         return DockerGateway(
-            self._gateway_image,
-            name=self._gateway_name,
-            network=self.network,
-            orchestrator_url=self.internal_url,
+            self._gateway_image, network=self.network, orchestrator_url=self.internal_url
         )
 
     def _ensure_orchestrator_image(self) -> None:
@@ -240,7 +224,7 @@ class OrchestratorService:
         # launch (the prior behaviour) would drop every other active
         # bottle's in-memory egress tokens each time a new bottle starts,
         # since the orchestrator process holds them only in memory (#381).
-        current_hash = source_hash(self._repo_root)
+        current_hash = _source_hash(self._repo_root)
         if self.is_healthy() and self._orchestrator_source_current(current_hash):
             return self.url
 

bot_bottle/orchestrator/service.py

@@ -17,37 +17,9 @@ Launch lifecycle:
 
 from __future__ import annotations
 
-import json
-from datetime import datetime, timezone
-
 from .broker import LaunchBroker, LaunchRequest, sign_request
 from .registry import BottleRecord, RegistryStore
 from .gateway import Gateway
-from ..supervise import (
-    AuditEntry,
-    COMPONENT_FOR_TOOL,
-    Response,
-    STATUS_APPROVED,
-    STATUS_MODIFIED,
-    STATUS_REJECTED,
-    TOOL_EGRESS_ALLOW,
-    TOOL_EGRESS_BLOCK,
-    list_all_pending_proposals,
-    read_proposal,
-    render_diff,
-    write_audit_entry,
-    write_response,
-)
-
-
-# Operator decision → Response.status. The apply half (egress tools) runs
-# for approve/modify only.
-_RESPOND_STATUS = {
-    "approve": STATUS_APPROVED,
-    "modify": STATUS_MODIFIED,
-    "reject": STATUS_REJECTED,
-}
-_APPLY_TOOLS = (TOOL_EGRESS_ALLOW, TOOL_EGRESS_BLOCK)
 
 
 class Orchestrator:
@@ -127,134 +99,22 @@ class Orchestrator:
         """Fail-closed attribution (delegates to the registry)."""
         return self.registry.attribute(source_ip, identity_token)
 
-    def resolve(self, source_ip: str, identity_token: str) -> BottleRecord | None:
-        """Resolve the bottle behind a request — the per-request lookup the
-        multi-tenant gateway makes; the returned record carries its `policy`.
-
-        **Mandatory pair**: requires a matching `(source_ip, identity_token)`
-        (constant-time). There is no source-IP-only fallback — the app-layer
-        token is delivered on every attributed data plane (egress proxy
-        credentials, git-gate/supervise headers), so a missing or mismatched
-        token fail-closes. This keeps a spoofed source IP (which the /31 TAP
-        alone does not prevent) from selecting another bottle's policy/tokens
-        without also holding that bottle's unguessable token."""
-        return self.registry.attribute(source_ip, identity_token)
+    def resolve(self, source_ip: str, identity_token: str = "") -> BottleRecord | None:
+        """Resolve the bottle behind a request — the source-IP-keyed lookup
+        the multi-tenant gateway makes per request; the returned record
+        carries its `policy`. With a token, full attribution (source IP +
+        token); without, network-layer attribution by source IP alone
+        (valid where the IP is unspoofable and the control plane is
+        gateway-only)."""
+        if identity_token:
+            return self.registry.attribute(source_ip, identity_token)
+        return self.registry.by_source_ip(source_ip)
 
     def set_policy(self, bottle_id: str, policy: str) -> bool:
         """Update a bottle's gateway policy in place (live reload). False if
         the bottle is unknown."""
         return self.registry.set_policy(bottle_id, policy)
 
-    # --- supervise queue (operator approvals) ------------------------------
-    #
-    # The orchestrator owns the single DB *and* the live policy, so operator
-    # decisions are applied here, server-side, and reached over HTTP by the
-    # host TUI (no direct-DB access, one path for every backend).
-
-    def supervise_pending(self) -> list[dict[str, object]]:
-        """All pending proposals across bottles, FIFO, as JSON dicts
-        (`Proposal.to_dict`, round-trippable via `Proposal.from_dict`).
-
-        Each dict carries an extra `bottle_label`: the bottle's human slug
-        resolved from the registry (the proposal itself is keyed by the
-        orchestrator-assigned bottle_id, which is opaque to an operator). The
-        CLI renders the label but still responds against `bottle_slug`."""
-        out: list[dict[str, object]] = []
-        for p in list_all_pending_proposals():
-            d = p.to_dict()
-            d["bottle_label"] = self._label_for(p.bottle_slug)
-            out.append(d)
-        return out
-
-    def _label_for(self, bottle_slug: str) -> str:
-        """The human slug recorded in registry metadata for a proposal's
-        bottle, or the bottle_slug unchanged when the bottle is gone or has no
-        recorded slug — so the label is always non-empty."""
-        rec = self.registry.get(bottle_slug)
-        if rec is None:
-            return bottle_slug
-        try:
-            meta = json.loads(rec.metadata) if rec.metadata else {}
-        except ValueError:
-            meta = {}
-        slug = meta.get("slug") if isinstance(meta, dict) else None
-        return slug if isinstance(slug, str) and slug else bottle_slug
-
-    def _record_for_slug(self, slug: str) -> BottleRecord | None:
-        """The live registry record for a proposal's bottle, or None (e.g. the
-        bottle was torn down before the operator responded).
-
-        In consolidated mode the supervise server attributes each proposal to
-        the orchestrator-assigned bottle_id and stores that as the proposal's
-        `bottle_slug` (see supervise_server `_attributed_config`), so the fast
-        path is a direct bottle_id lookup. The metadata-slug scan is the
-        fallback for legacy single-tenant proposals keyed by the human slug."""
-        rec = self.registry.get(slug)
-        if rec is not None:
-            return rec
-        for rec in self.registry.all():
-            try:
-                meta = json.loads(rec.metadata) if rec.metadata else {}
-            except ValueError:
-                meta = {}
-            if isinstance(meta, dict) and meta.get("slug") == slug:
-                return rec
-        return None
-
-    def supervise_respond(
-        self,
-        proposal_id: str,
-        *,
-        bottle_slug: str,
-        decision: str,
-        notes: str = "",
-        final_file: str | None = None,
-    ) -> tuple[bool, str]:
-        """Record an operator decision on a queued proposal, applying it
-        server-side. `decision` is approve/modify/reject.
-
-        Approve/modify on an egress tool rewrites the bottle's policy so the
-        gateway serves the new routes on its next `/resolve` (the live apply);
-        then the queued Response is written (unblocking the agent's MCP call)
-        and an audit entry recorded — all against the one DB. Returns
-        (ok, error): ok=False with a message when the proposal or decision is
-        unknown, or the bottle is gone so an approval can't be applied."""
-        status = _RESPOND_STATUS.get(decision)
-        if status is None:
-            return False, f"unknown decision {decision!r}"
-        try:
-            proposal = read_proposal(bottle_slug, proposal_id)
-        except FileNotFoundError:
-            return False, "no such proposal"
-
-        diff_before, diff_after = "", ""
-        if status in (STATUS_APPROVED, STATUS_MODIFIED) and proposal.tool in _APPLY_TOOLS:
-            new_policy = final_file if final_file is not None else proposal.proposed_file
-            rec = self._record_for_slug(bottle_slug)
-            if rec is None:
-                return False, (
-                    f"bottle {bottle_slug!r} is no longer registered; "
-                    "cannot apply the route change"
-                )
-            diff_before, diff_after = rec.policy, new_policy
-            self.set_policy(rec.bottle_id, new_policy)
-
-        write_response(bottle_slug, Response(
-            proposal_id=proposal_id, status=status, notes=notes, final_file=final_file,
-        ))
-        component = COMPONENT_FOR_TOOL.get(proposal.tool)
-        if component is not None:
-            write_audit_entry(AuditEntry(
-                timestamp=datetime.now(timezone.utc).isoformat(),
-                bottle_slug=bottle_slug,
-                component=component,
-                operator_action=status,
-                operator_notes=notes,
-                justification=proposal.justification,
-                diff=render_diff(diff_before, diff_after, label=component),
-            ))
-        return True, ""
-
     # --- consolidated gateway ----------------------------------------------
 
     def ensure_gateway(self) -> None:

bot_bottle/paths.py

@@ -16,8 +16,6 @@ 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
@@ -25,14 +23,6 @@ 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`."""
@@ -50,52 +40,4 @@ def host_db_path() -> Path:
     return bot_bottle_root() / "db" / HOST_DB_FILENAME
 
 
-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",
-]
+__all__ = ["HOST_DB_FILENAME", "bot_bottle_root", "host_db_path"]

bot_bottle/policy_resolver.py

@@ -29,29 +29,11 @@ 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 —
@@ -75,7 +57,7 @@ class PolicyResolver:
         ).encode()
         req = urllib.request.Request(
             f"{self._base}/resolve", data=body, method="POST",
-            headers={"Content-Type": "application/json", **_control_auth_headers()},
+            headers={"Content-Type": "application/json"},
         )
         try:
             with urllib.request.urlopen(req, timeout=self._timeout) as resp:

bot_bottle/supervise_server.py

@@ -51,16 +51,12 @@ from dataclasses import dataclass, replace
 try:
     # Same-directory imports inside the bundle container; these files are
     # COPYed flat under /app by Dockerfile.gateway.
-    from egress_addon_core import (
-        LOG_OFF, load_config, resolve_client_context, route_to_yaml_dict,
-    )
+    from egress_addon_core import LOG_OFF, load_config
     from policy_resolver import PolicyResolveError, PolicyResolver
     import supervise as _sv
 except ModuleNotFoundError:
     # Package imports for host-side tests and tooling.
-    from .egress_addon_core import (
-        LOG_OFF, load_config, resolve_client_context, route_to_yaml_dict,
-    )
+    from .egress_addon_core import LOG_OFF, load_config
     from .policy_resolver import PolicyResolveError, PolicyResolver
     from . import supervise as _sv
 
@@ -69,8 +65,6 @@ except ModuleNotFoundError:
 
 
 MCP_PROTOCOL_VERSION = "2024-11-05"
-# App-layer identity token header (mirrors egress_addon / git_http_backend).
-IDENTITY_HEADER = "x-bot-bottle-identity"
 SERVER_NAME = "bot-bottle-supervise"
 SERVER_VERSION = "0.1.0"
 
@@ -531,17 +525,6 @@ class MCPHandler(http.server.BaseHTTPRequestHandler):
         if method == "tools/list":
             return handle_tools_list(req.params)
         if method == "tools/call":
-            # `list-egress-routes` is read-only introspection. In consolidated
-            # mode the gateway's *static* route table is empty (routes are
-            # resolved per request by source IP), so answer it from the calling
-            # bottle's resolved policy. Otherwise the agent sees an empty
-            # allowlist and composes an egress proposal that *replaces* the live
-            # routes instead of extending them — silently dropping base routes
-            # like api.anthropic.com when the operator approves it.
-            if req.params.get("name") == _sv.TOOL_LIST_EGRESS_ROUTES:
-                resolved = self._resolved_routes_payload()
-                if resolved is not None:
-                    return resolved
             # Attribute the proposal to the calling bottle. Single-tenant → the
             # env slug on `config`; consolidated → the source-IP-resolved
             # bottle id, so one shared server queues each bottle's proposal
@@ -549,28 +532,6 @@ class MCPHandler(http.server.BaseHTTPRequestHandler):
             return handle_tools_call(req.params, self._attributed_config(config))
         raise _RpcClientError(ERR_METHOD_NOT_FOUND, f"method not found: {method}")
 
-    def _resolved_routes_payload(self) -> dict[str, object] | None:
-        """The calling bottle's live egress routes as the `list-egress-routes`
-        JSON payload, resolved by (source_ip, identity token) — the same shape
-        the single-tenant introspection endpoint returns. None when there is no
-        resolver (single-tenant), so the caller falls back to that endpoint.
-
-        Fail-closed like `_attributed_config`: an unattributed source or an
-        unreachable orchestrator yields an empty route list (never another
-        bottle's), courtesy of `resolve_client_context`."""
-        resolver = getattr(self.server, "policy_resolver", None)
-        if resolver is None:
-            return None
-        headers = getattr(self, "headers", None)
-        token = headers.get(IDENTITY_HEADER, "") if headers is not None else ""
-        conf, _slug, _tokens = resolve_client_context(
-            resolver, self.client_address[0], token,
-        )
-        body = json.dumps(
-            {"routes": [route_to_yaml_dict(r) for r in conf.routes]}, indent=2,
-        )
-        return {"content": [{"type": "text", "text": body}], "isError": False}
-
     def _attributed_config(self, config: ServerConfig) -> ServerConfig:
         """The ServerConfig with `bottle_slug` bound to *this request's* bottle.
         Single-tenant (no resolver): unchanged. Consolidated: the bottle id
@@ -580,13 +541,8 @@ class MCPHandler(http.server.BaseHTTPRequestHandler):
         resolver = getattr(self.server, "policy_resolver", None)
         if resolver is None:
             return config
-        # The agent's MCP client sends the identity token as a request header
-        # (provisioned via `mcp add --header`); the orchestrator requires the
-        # (source_ip, token) pair, so a missing/wrong token fail-closes below.
-        headers = getattr(self, "headers", None)
-        token = headers.get(IDENTITY_HEADER, "") if headers is not None else ""
         try:
-            bottle_id = resolver.resolve_bottle_id(self.client_address[0], token)
+            bottle_id = resolver.resolve_bottle_id(self.client_address[0])
         except PolicyResolveError as e:
             raise _RpcInternalError(f"orchestrator unreachable, cannot attribute: {e}") from e
         if not bottle_id:

docs/prds/0069-firecracker-native-docker-free.md

@@ -8,20 +8,16 @@
 > **Superseded in part by [PRD 0070](0070-per-host-orchestrator.md) (#351):**
 > the sidecar-consolidation framing here (Stage 1, per-host sidecar; Stage 4,
 > sidecar-as-VM) is taken over by 0070's per-host orchestrator. This PRD still
-> owns the docker-free **image-provisioning** work — Stage 2 (pull the fixed
-> images from an OCI registry instead of building them with host Docker, a
-> dependency of 0070) and Stage 3 (in-VM Dockerfile builder).
+> owns the docker-free **image-building** work — Stage 2 (nix-built fixed
+> images, a dependency of 0070) and Stage 3 (in-VM Dockerfile builder).
 
 ## Summary
 
 Make the Firecracker backend depend on **firecracker + KVM only**, removing
 Docker from the host. Two moves get us there: run the **sidecar bundle as a
 persistent, per-host service** (eventually a Firecracker VM) instead of a
-per-bottle container, and **provision rootfs images without a host Docker
-daemon** — pull the fixed images (orchestrator/gateway/infra) from an OCI
-registry and unpack them daemonlessly, and build user Dockerfiles in an in-VM
-builder. The images are still *built* with Docker, but off the launch host
-(CI / a publish step) and pushed to the registry; the launch host only pulls.
+per-bottle container, and **build agent rootfs images without a host Docker
+daemon** (nix for the fixed images; an in-VM builder for user Dockerfiles).
 
 ## Motivation
 
@@ -97,51 +93,13 @@ torn down at exit."
 Can ship as a container first (quick resource/ops win) and become a VM in
 Stage 4.
 
-### Stage 2 — Fixed rootfs prebuilt + pulled as an artifact (no host Docker)
+### Stage 2 — Fixed images built with nix (no Docker)
 
-The one fixed image the Firecracker backend needs at launch — the combined
-**infra** rootfs the infra VM boots (orchestrator control plane + gateway +
-buildah, with the control-plane init as PID 1) — is **prebuilt end-to-end off
-the launch host and published as a versioned, ready-to-boot ext4 artifact**.
-The launch host **downloads the `.ext4` and boots it directly** — no
-`docker build`, no `docker export`, no `mke2fs`, no image tooling at all.
-
-This is possible because the infra rootfs is already **host- and
-bottle-agnostic**: the per-boot bits (authorized_keys, guest IP) arrive on the
-**kernel cmdline**, not in the rootfs (see `build_base_rootfs_dir`). So one
-published ext4 boots on any launch host.
-
-- **Artifact.** `rootfs.ext4` + a `rootfs.ext4.sha256`, published as a Gitea
-  **generic package** (`bot-bottle-firecracker-infra/<tag>`) — generic packages take
-  arbitrary large binaries (no attachment size cap / file-type allowlist that
-  release attachments impose). The matching `vmlinux` kernel can ship the same
-  way, so the whole VM is fetchable.
-- **Pull.** The launch host `GET`s
-  `…/api/packages/<owner>/generic/bot-bottle-firecracker-infra/<tag>/rootfs.ext4` (+
-  `.sha256`) for its pinned tag, verifies the checksum, caches it under the
-  tag, and attaches it as the infra VM's root disk. Host prerequisite is an
-  HTTP client — nothing else. Public packages need no auth to pull; a token
-  with `read:package` covers a private instance.
-- **Registry.** The artifact base URL + owner are configurable, defaulting to
-  this deployment's Gitea (`https://gitea.dideric.is` / `didericis`);
-  overridable via env for other deployments / air-gapped mirrors.
-- **Versioning.** A pinned tag bumped when the infra rootfs contents change
-  (bot_bottle's shipped files, the base deps, or the init), so a launch host
-  pulls the artifact matching its code and a content change can't silently
-  boot a stale rootfs. A checksum mismatch fails closed.
-- **Publish.** A `publish` step (CLI subcommand / CI job) runs the full
-  pipeline **on a build/CI host** — `docker build` the three Dockerfiles →
-  export → inject guest boot → `mke2fs` → upload the `.ext4` + `.sha256`.
-  Building still uses Docker, but never on the launch/runner host, which is
-  the one #348 needs unprivileged.
-- **Dev escape hatch.** An explicit opt-in still builds the rootfs locally
-  with Docker (for iterating on the Dockerfiles without a publish
-  round-trip); it is never the default path.
-
-Removes Docker from the launch host entirely for the fixed image, and the
-launch host needs no OCI/rootfs tooling — just fetch + boot. The build-time
-cache / build-time-egress open problems a from-scratch build would face don't
-arise: the launch host never builds, it downloads a finished disk.
+The images bot-bottle *ships* — the sidecar, the agent base, and the builder
+(Stage 3) — are built declaratively with nix (`nixos-generators` /
+`make-ext4-fs` / `pkgs.dockerTools` for the rootfs), producing an ext4 or
+tar with correct ownership. Removes Docker for everything we own and gives
+the rootless-rootfs correctness (#347) for free on these images.
 
 ### Stage 3 — User Dockerfiles built in a builder VM (the unlock)
 

docs/research/apple-container-networking-spike.md

@@ -358,111 +358,3 @@ the Apple Container-specific constraints directly:
 
 Do not implement the backend as a direct clone of Docker Compose
 service aliases. That assumption failed in this run.
-
-## Addendum: consolidated-gateway findings (2026-07-17, PRD 0070)
-
-Re-tested on Apple Container 1.0.0 while porting the backend to the
-per-host consolidated gateway (#351). The two-network shape above still
-holds; these are the additional constraints that shaped the port, each
-verified against the live CLI on this host.
-
-### No static IP for a container
-
-`container run --network` accepts only
-`<name>[,mac=XX:XX:XX:XX:XX:XX][,mtu=VALUE]`. There is no `--ip`. The
-address comes from vmnet's DHCP and is knowable only after the container
-is running:
-
-```console
-$ container run --name a --network bb-net --detach alpine sleep 900
-$ container inspect a | jq -r '.[0].status.networks[0].ipv4Address'
-192.168.128.3/24
-```
-
-Consequence: the docker backend's "allocate a free IP -> pin it with
-`--ip` -> register -> launch" order cannot be reproduced. macOS inverts
-it to "launch -> read the assigned address -> register". The identity
-token therefore cannot be in the agent's run-time env (registration mints
-it after the container exists) and is delivered at `container exec` time.
-
-### Networks are fixed at run time
-
-There is no `container network connect`; `container network` exposes only
-`create`, `delete`, `list`, `inspect`, `prune`. A network cannot be
-attached to a running container, so a *persistent* shared gateway rules
-out per-bottle networks — they would force a gateway restart per launch.
-One shared host-only network, created up front, is the only shape that
-keeps the gateway a singleton.
-
-### No container DNS
-
-Containers cannot resolve each other by name; the host-only network's
-resolver refuses the query:
-
-```console
-$ container exec agent nslookup gw
-;; connection timed out; no servers could be reached
-$ container exec agent cat /etc/resolv.conf
-nameserver 192.168.128.1
-```
-
-Consequence: the gateway is handed the control plane's **IP**, not a
-container name as on docker. That forces the startup order
-orchestrator -> read its address -> gateway.
-
-### The host can reach the host-only network directly
-
-```console
-$ container inspect c | jq -r '.[0].status.networks[0].ipv4Address'
-192.168.128.2/24
-$ curl -s http://192.168.128.2:8099/i
-ok
-```
-
-So no `--publish` hop is needed: the host CLI and the gateway use the
-same control-plane URL. Docker needs `--publish 127.0.0.1:...` plus a
-separate internal URL for the same job.
-
-### CAP_NET_RAW is granted by default — and matters for attribution
-
-Apple grants NET_RAW but not NET_ADMIN. The agent therefore cannot change
-its own address or route:
-
-```console
-$ container exec agent ip addr add 192.168.128.99/24 dev eth0
-ip: RTNETLINK answers: Operation not permitted
-$ container exec agent ip route replace default via 192.168.128.2 dev eth0
-ip: RTNETLINK answers: Operation not permitted
-$ container exec agent grep CapEff /proc/self/status
-CapEff:	00000000a80425fb        # bit 13 (NET_RAW) set, bit 12 (NET_ADMIN) clear
-```
-
-But NET_RAW permits raw sockets, i.e. source-address forgery against
-neighbours on the shared segment — directly against PRD 0070's invariant
-("a packet's source address, as seen by the orchestrator, provably
-identifies the originating bottle"). `--cap-drop CAP_NET_RAW` closes it:
-
-```console
-$ container run --cap-drop CAP_NET_RAW ... alpine
-$ container exec nr grep CapEff /proc/self/status
-CapEff:	00000000a80405fb        # bit 13 cleared
-$ container exec nr ping -c1 192.168.128.2
-ping: permission denied (are you root?)
-```
-
-The agent is run with `--cap-drop CAP_NET_RAW` for this reason.
-
-### `container exec` inherits run-time env, and `--env` overrides it
-
-```console
-$ container run --name e --env FOO=from_run --detach alpine sleep 120
-$ container exec e sh -c 'echo $FOO'
-from_run
-$ container exec --env FOO=from_exec e sh -c 'echo $FOO'
-from_exec
-```
-
-This is what makes exec-time identity-token delivery work: the token-less
-proxy URL baked in at launch is superseded by the token-bearing one at
-exec. Bare `--env NAME` (inherit from the parent process) keeps the token
-value off argv.

nix/firecracker-netpool.nix

@@ -49,12 +49,10 @@ let
   # /31 alignment == an even final octet (only bit 0 matters for base+2i).
   lastOctet = lib.toInt (lib.last (lib.splitString "." cfg.ipBase));
 
-  # The script needs ip/nft/sysctl + the usual coreutils, plus iptables
-  # for the orchestrator link's DOCKER-USER accept (best-effort; skipped
-  # when Docker is absent). It gets every pool value via the unit's
-  # Environment=, so it never reads the shared defaults file (which isn't
-  # beside it once copied to the store).
-  runtimePath = with pkgs; [ iproute2 nftables iptables procps coreutils gnused ];
+  # The script needs ip/nft/sysctl + the usual coreutils. It gets every
+  # pool value via the unit's Environment=, so it never reads the shared
+  # defaults file (which isn't beside it once copied to the store).
+  runtimePath = with pkgs; [ iproute2 nftables procps coreutils gnused ];
 
   ownEnv =
     if cfg.group != null
@@ -66,7 +64,6 @@ let
     BOT_BOTTLE_FC_IP_BASE = cfg.ipBase;
     BOT_BOTTLE_FC_IFACE_PREFIX = cfg.ifacePrefix;
     BOT_BOTTLE_FC_NFT_TABLE = cfg.tableName;
-    BOT_BOTTLE_FC_ORCH_IFACE = cfg.orchIface;
   } // ownEnv;
 in
 {
@@ -130,19 +127,6 @@ in
       description = "nftables table name for the isolation boundary. Must match netpool.NFT_TABLE.";
     };
 
-    orchIface = lib.mkOption {
-      type = lib.types.str;
-      default = defaults.BOT_BOTTLE_FC_ORCH_IFACE;
-      defaultText = lib.literalMD "the shared `netpool.defaults.env` value";
-      description = ''
-        TAP name for the orchestrator/gateway VM's dedicated link. Unlike
-        the isolated bbfc* agent pool, this link is NAT'd to the internet
-        (the orchestrator is trusted infra that builds agent images in-VM
-        and forwards agent egress upstream). Must match
-        BOT_BOTTLE_FC_ORCH_IFACE / netpool.ORCH_IFACE.
-      '';
-    };
-
     writeEnvFile = lib.mkOption {
       type = lib.types.bool;
       default = false;
@@ -192,7 +176,6 @@ in
         BOT_BOTTLE_FC_IP_BASE=${cfg.ipBase}
         BOT_BOTTLE_FC_IFACE_PREFIX=${cfg.ifacePrefix}
         BOT_BOTTLE_FC_NFT_TABLE=${cfg.tableName}
-        BOT_BOTTLE_FC_ORCH_IFACE=${cfg.orchIface}
       '';
     };
   };

scripts/firecracker-netpool.sh

@@ -63,13 +63,12 @@ POOL_SIZE="${BOT_BOTTLE_FC_POOL_SIZE:-$(_default BOT_BOTTLE_FC_POOL_SIZE)}"
 IP_BASE="${BOT_BOTTLE_FC_IP_BASE:-$(_default BOT_BOTTLE_FC_IP_BASE)}"
 PREFIX="${BOT_BOTTLE_FC_IFACE_PREFIX:-$(_default BOT_BOTTLE_FC_IFACE_PREFIX)}"
 TABLE="${BOT_BOTTLE_FC_NFT_TABLE:-$(_default BOT_BOTTLE_FC_NFT_TABLE)}"
-ORCH_IFACE="${BOT_BOTTLE_FC_ORCH_IFACE:-$(_default BOT_BOTTLE_FC_ORCH_IFACE)}"
 OWNER="${BOT_BOTTLE_FC_OWNER:-${SUDO_USER:-$USER}}"
 GROUP="${BOT_BOTTLE_FC_GROUP:-}"
 
 # Fail loudly rather than provisioning a half/empty range if a value
 # resolved to nothing (env unset AND the shared file unreadable).
-for _v in POOL_SIZE IP_BASE PREFIX TABLE ORCH_IFACE; do
+for _v in POOL_SIZE IP_BASE PREFIX TABLE; do
     [ -n "${!_v}" ] || { echo "error: $_v unresolved (set BOT_BOTTLE_FC_* or fix $_DEFAULTS)" >&2; exit 1; }
 done
 
@@ -90,13 +89,6 @@ host_ip() { _int_to_ip $(( $(_ip_to_int "$IP_BASE") + 2*$1 )); }
 guest_ip() { _int_to_ip $(( $(_ip_to_int "$IP_BASE") + 2*$1 + 1 )); }
 iface()   { echo "${PREFIX}$1"; }
 
-# Orchestrator/gateway VM link: a /31 at the TOP of the IP_BASE /16
-# (host x.y.255.0, guest x.y.255.1), well clear of the agent pool near
-# the bottom of the block. Must match netpool.py:orch_slot().
-_orch_base() { echo $(( ($(_ip_to_int "$IP_BASE") & 0xFFFF0000) + 0xFF00 )); }
-orch_host()  { _int_to_ip "$(_orch_base)"; }
-orch_guest() { _int_to_ip $(( $(_orch_base) + 1 )); }
-
 require_root() {
     if [ "$(id -u)" -ne 0 ]; then
         echo "error: '$1' needs root (run under sudo)" >&2
@@ -133,21 +125,8 @@ cmd_up() {
         echo "  $dev  host=$host  guest=$(guest_ip "$i")  $own_desc"
     done
 
-    # The orchestrator/gateway VM's dedicated link. Same rootless-open
-    # ownership as the pool, but NAT'd to the internet (below) — it is
-    # trusted infra, not an isolated agent slot.
-    ip link show "$ORCH_IFACE" >/dev/null 2>&1 \
-        || ip tuntap add dev "$ORCH_IFACE" mode tap "${own_args[@]}"
-    ip addr replace "$(orch_host)/31" dev "$ORCH_IFACE"
-    ip link set "$ORCH_IFACE" up
-    echo "  $ORCH_IFACE  host=$(orch_host)  guest=$(orch_guest)  (NAT'd egress)  $own_desc"
-
     _install_nft
     echo "nftables table inet $TABLE installed (fail-closed boundary)"
-    _install_orch_egress
-    echo "orchestrator egress installed ($ORCH_IFACE -> NAT out)"
-    _install_gateway_route
-    echo "agent->gateway route installed (${PREFIX}* :$GATEWAY_PORTS -> $(orch_guest))"
     echo "done."
 }
 
@@ -163,30 +142,12 @@ _install_nft() {
     #   input: a VM never needs host-local delivery (its gateway is
     #     reached via DNAT->forward), so drop all direct input from VMs
     #     -> host services bound on 0.0.0.0 are unreachable from the VM.
-    # Delete-first (create empty, delete, recreate) so a re-applied `up`
-    # lands identical state instead of appending rules / erroring on the
-    # existing base chains — the setup is idempotent regardless of history.
-
-    # Anti-spoof: bind each TAP to its assigned guest IP. The /31 alone
-    # does NOT make the source address unspoofable — root in an agent VM
-    # can source another bottle's guest IP on its own bbfc TAP, and the
-    # gateway attributes egress/policy/tokens by source IP. So drop any
-    # packet whose source isn't the guest address assigned to the exact
-    # TAP it arrived on, before it can be attributed. One rule per slot.
-    local antispoof="" i
-    for i in $(seq 0 $((POOL_SIZE-1))); do
-        antispoof="${antispoof}        iifname \"$(iface "$i")\" ip saddr != $(guest_ip "$i") drop
-"
-    done
-
     nft -f - <<EOF
-table inet $TABLE {}
-delete table inet $TABLE
 table inet $TABLE {
     chain forward {
         type filter hook forward priority -10; policy accept;
         iifname != "${PREFIX}*" return
-${antispoof}        ct state established,related accept
+        ct state established,related accept
         ct status dnat accept
         drop
     }
@@ -200,87 +161,8 @@ ${antispoof}        ct state established,related accept
 EOF
 }
 
-# Give the orchestrator/gateway VM real internet egress (agent VMs get
-# none — that's the isolation table above). Three parts, because the
-# path must work both during bootstrap (Docker still present) and after
-# Docker is removed:
-#   * masquerade   — SNAT the orch guest /31 out the host uplink so its
-#                    RFC-1918 address can reach the internet.
-#   * nft forward  — accept the orch link's forward path (load-bearing
-#                    on a pure-nft host whose FORWARD policy drops; a
-#                    harmless no-op where forwarding is already open).
-#                    It never drops, so it can't weaken the isolation
-#                    table's agent drops.
-#   * DOCKER-USER  — during bootstrap Docker's FORWARD chain policy is
-#                    DROP; its sanctioned DOCKER-USER hook is the only
-#                    place a user ACCEPT survives. Best-effort + guarded
-#                    (skipped once Docker is gone).
-_install_orch_egress() {
-    nft -f - <<EOF
-table inet ${TABLE}_nat {}
-delete table inet ${TABLE}_nat
-table inet ${TABLE}_nat {
-    chain forward {
-        type filter hook forward priority -10; policy accept;
-        iifname "$ORCH_IFACE" accept
-        oifname "$ORCH_IFACE" ct state established,related accept
-    }
-    chain postrouting {
-        type nat hook postrouting priority 100; policy accept;
-        ip saddr $(orch_guest) oifname != "$ORCH_IFACE" masquerade
-    }
-}
-EOF
-    _docker_user_orch add
-}
-
-# Insert (add) or delete (del) the DOCKER-USER ACCEPT rules for the
-# orchestrator link, idempotently, only when the chain exists.
-_docker_user_orch() {
-    local op="$1" flag
-    command -v iptables >/dev/null 2>&1 || return 0
-    iptables -t filter -L DOCKER-USER >/dev/null 2>&1 || return 0
-    for flag in "-i" "-o"; do
-        if [ "$op" = add ]; then
-            iptables -C DOCKER-USER "$flag" "$ORCH_IFACE" -j ACCEPT 2>/dev/null \
-                || iptables -I DOCKER-USER "$flag" "$ORCH_IFACE" -j ACCEPT
-        else
-            iptables -D DOCKER-USER "$flag" "$ORCH_IFACE" -j ACCEPT 2>/dev/null || true
-        fi
-    done
-}
-
-# Agent -> gateway VM routing. The shared gateway (egress / supervise /
-# git-http) runs in the orchestrator/infra VM at $(orch_guest). Agents keep
-# addressing their own host-side TAP IP on the gateway ports; a PREROUTING
-# DNAT redirects that to the infra VM, and the isolation table's
-# `ct status dnat accept` forward rule lets it through — every other agent
-# egress stays dropped. Source IP is deliberately NOT masqueraded: the
-# gateway attributes each request to the originating bottle by its (nft +
-# /31 unspoofable) guest IP.
-_install_gateway_route() {
-    nft -f - <<EOF
-table ip ${TABLE}_gw {}
-delete table ip ${TABLE}_gw
-table ip ${TABLE}_gw {
-    chain prerouting {
-        type nat hook prerouting priority -100; policy accept;
-        iifname "${PREFIX}*" tcp dport { $GATEWAY_PORTS } dnat to $(orch_guest)
-    }
-}
-EOF
-}
-
 cmd_down() {
     require_root down
-    _docker_user_orch del
-    nft delete table ip "${TABLE}_gw" 2>/dev/null || true
-    nft delete table inet "${TABLE}_nat" 2>/dev/null || true
-    if ip link show "$ORCH_IFACE" >/dev/null 2>&1; then
-        ip link set "$ORCH_IFACE" down 2>/dev/null || true
-        ip tuntap del dev "$ORCH_IFACE" mode tap 2>/dev/null || true
-        echo "  removed $ORCH_IFACE"
-    fi
     nft delete table inet "$TABLE" 2>/dev/null || true
     for i in $(seq 0 $((POOL_SIZE-1))); do
         local dev ; dev="$(iface "$i")"
@@ -296,10 +178,6 @@ cmd_down() {
 cmd_status() {
     echo "table inet $TABLE:"
     nft list table inet "$TABLE" 2>/dev/null || echo "  (absent)"
-    echo "table inet ${TABLE}_nat (orchestrator egress):"
-    nft list table inet "${TABLE}_nat" 2>/dev/null || echo "  (absent)"
-    echo "table ip ${TABLE}_gw (agent->gateway route):"
-    nft list table ip "${TABLE}_gw" 2>/dev/null || echo "  (absent)"
     echo "taps:"
     for i in $(seq 0 $((POOL_SIZE-1))); do
         local dev ; dev="$(iface "$i")"
@@ -307,9 +185,6 @@ cmd_status() {
             ip -brief addr show "$dev" | sed 's/^/  /'
         fi
     done
-    if ip -brief addr show "$ORCH_IFACE" >/dev/null 2>&1; then
-        ip -brief addr show "$ORCH_IFACE" | sed 's/^/  /'
-    fi
 }
 
 case "${1:-}" in

tests/integration/test_orchestrator_docker_control_plane_auth.py

@@ -1,155 +0,0 @@
-"""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

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

tests/unit/test_backend_selection.py

@@ -244,45 +244,5 @@ class TestHasBackend(unittest.TestCase):
         self.assertFalse(has_backend("nonexistent"))
 
 
-class TestEnsureOrchestrator(unittest.TestCase):
-    """The backend-agnostic orchestrator bring-up entry point. Docker starts
-    the orchestrator + gateway containers; firecracker boots the infra VM;
-    macos-container starts the infra container."""
-
-    def test_docker_delegates_to_orchestrator_service(self):
-        b = get_bottle_backend("docker")
-        with patch(
-            "bot_bottle.orchestrator.lifecycle.OrchestratorService"
-        ) as service_cls:
-            service_cls.return_value.ensure_running.return_value = (
-                "http://127.0.0.1:8099"
-            )
-            url = b.ensure_orchestrator()
-        self.assertEqual(url, "http://127.0.0.1:8099")
-        service_cls.return_value.ensure_running.assert_called_once_with()
-
-    def test_firecracker_delegates_to_infra_vm(self):
-        b = get_bottle_backend("firecracker")
-        with patch(
-            "bot_bottle.backend.firecracker.infra_vm.ensure_running"
-        ) as ensure_running:
-            ensure_running.return_value.control_plane_url = (
-                "http://10.243.255.1:8099"
-            )
-            url = b.ensure_orchestrator()
-        self.assertEqual(url, "http://10.243.255.1:8099")
-
-    def test_macos_delegates_to_infra_container(self):
-        b = get_bottle_backend("macos-container")
-        with patch(
-            "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__":
     unittest.main()

tests/unit/test_contrib_codex_provider.py

@@ -54,7 +54,6 @@ def _plan(
     skills: list[str] | None = None,
     agent_provision: AgentProvisionPlan | None = None,
     supervise: bool = False,
-    identity_token: str = "",
 ) -> DockerBottlePlan:
     bottle_json: dict = {"agent_provider": {"template": "codex"}}  # type: ignore
     if supervise:
@@ -101,7 +100,6 @@ def _plan(
         ),
         supervise_plan=supervise_plan,
         use_runsc=False,
-        identity_token=identity_token,
         agent_provision=agent_provision or AgentProvisionPlan(
             template="codex", command="codex", prompt_mode="read_prompt_file",
             image="bot-bottle-codex:latest", dockerfile="",
@@ -316,31 +314,6 @@ class TestCodexDockerfile(unittest.TestCase):
         self.assertIn("procps", dockerfile)
 
 
-# Codex-supported streamable-HTTP MCP config keys (RawMcpServerConfig in
-# codex-rs/config/src/mcp_types.rs). config.toml uses deny_unknown_fields,
-# so an entry that names anything outside this set is rejected by the CLI.
-_CODEX_HTTP_MCP_KEYS = frozenset({
-    "url", "http_headers", "env_http_headers", "bearer_token_env_var",
-    # shared (transport-agnostic) keys
-    "environment_id", "auth", "startup_timeout_sec", "startup_timeout_ms",
-    "tool_timeout_sec", "enabled", "required", "supports_parallel_tool_calls",
-    "default_tools_approval_mode", "enabled_tools", "disabled_tools",
-    "scopes", "oauth", "oauth_resource", "name", "tools",
-})
-
-
-def _append_target(bottle: MagicMock) -> tuple[str, str]:
-    """Reconstruct (config_path, appended_toml) from the base64 append
-    script the provider ran."""
-    import base64 as _b64
-
-    script = bottle.exec.call_args.args[0]
-    # printf %s '<b64>' | base64 -d >> '<path>'
-    b64 = script.split("printf %s ", 1)[1].split(" |", 1)[0].strip("'")
-    path = script.rsplit(">> ", 1)[1].strip().strip("'")
-    return path, _b64.b64decode(b64).decode()
-
-
 class TestCodexSuperviseMcp(unittest.TestCase):
     def test_noop_when_supervise_disabled(self):
         bottle = _make_bottle()
@@ -349,68 +322,27 @@ class TestCodexSuperviseMcp(unittest.TestCase):
         )
         bottle.exec.assert_not_called()
 
-    def test_appends_streamable_http_entry_as_node(self):
-        import tomllib
-
-        bottle = _make_bottle()
-        plan = _plan(supervise=True, identity_token="tok-abc123")
-        CodexAgentProvider().provision_supervise_mcp(plan, bottle, _URL)
-        bottle.exec.assert_called_once()
-        self.assertEqual("node", bottle.exec.call_args.kwargs.get("user"))
-
-        config_path, appended = _append_target(bottle)
-        self.assertEqual("/home/node/.codex/config.toml", config_path)
-        # The appended block must be valid TOML and parse to a streamable
-        # HTTP server carrying the identity token as a static http header.
-        parsed = tomllib.loads(appended)
-        server = parsed["mcp_servers"]["supervise"]
-        self.assertEqual(_URL, server["url"])
-        self.assertEqual(
-            "tok-abc123", server["http_headers"]["x-bot-bottle-identity"],
-        )
-        # Never emit an unsupported key (config.toml is deny_unknown_fields);
-        # in particular there is no `--header` / `header` surface.
-        self.assertTrue(
-            set(server).issubset(_CODEX_HTTP_MCP_KEYS),
-            f"unsupported codex mcp keys: {set(server) - _CODEX_HTTP_MCP_KEYS}",
-        )
-        self.assertNotIn("mcp add", bottle.exec.call_args.args[0])
-
-    def test_appends_to_custom_codex_home(self):
-        bottle = _make_bottle()
-        provision = AgentProvisionPlan(
-            template="codex", command="codex", prompt_mode="read_prompt_file",
-            image="", dockerfile="", guest_home="/home/node",
-            instance_name="bot-bottle-demo-abc12",
-            prompt_file=Path("/tmp/prompt.txt"),
-            guest_env={"CODEX_HOME": "/home/node/alt-codex"},
-        )
-        plan = _plan(
-            supervise=True, agent_provision=provision, identity_token="tok",
-        )
-        CodexAgentProvider().provision_supervise_mcp(plan, bottle, _URL)
-        config_path, _ = _append_target(bottle)
-        self.assertEqual("/home/node/alt-codex/config.toml", config_path)
-
-    def test_omits_http_headers_when_no_token(self):
-        import tomllib
-
+    def test_runs_codex_mcp_add_as_node(self):
         bottle = _make_bottle()
         CodexAgentProvider().provision_supervise_mcp(
             _plan(supervise=True), bottle, _URL,
         )
-        _, appended = _append_target(bottle)
-        server = tomllib.loads(appended)["mcp_servers"]["supervise"]
-        self.assertNotIn("http_headers", server)
+        bottle.exec.assert_called_once()
+        script = bottle.exec.call_args.args[0]
+        self.assertEqual("node", bottle.exec.call_args.kwargs.get("user"))
+        self.assertEqual(
+            "/home/node/.codex/packages/standalone/current/bin/codex "
+            f"mcp add supervise --url {_URL}",
+            script,
+        )
 
-    def test_registration_failure_is_fatal(self):
+    def test_logs_warning_on_failure_but_does_not_raise(self):
         bottle = _make_bottle(
             exec_result=ExecResult(returncode=1, stdout="", stderr="boom"),
         )
-        with self.assertRaises(SystemExit):
-            CodexAgentProvider().provision_supervise_mcp(
-                _plan(supervise=True), bottle, _URL,
-            )
+        CodexAgentProvider().provision_supervise_mcp(
+            _plan(supervise=True), bottle, _URL,
+        )
 
 
 class TestCodexHeadlessPrompt(unittest.TestCase):

tests/unit/test_egress_addon_log_redaction.py

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

tests/unit/test_egress_addon_request_flow.py

@@ -141,10 +141,6 @@ 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
@@ -863,91 +859,5 @@ 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_backend.py

@@ -255,30 +255,6 @@ class TestBottleAgentArgv(unittest.TestCase):
             argv[idx:],
         )
 
-    def test_codex_multiword_prompt_survives_ssh_reparse(self):
-        # codex's read_prompt_file mode passes a single positional with
-        # spaces ("Read and follow the instructions in <path>."). ssh
-        # space-joins the remote argv and the guest shell re-splits it, so
-        # the token MUST be quoted or codex sees "and" as a subcommand
-        # (regression). Each remote token is shlex.quote'd; round-tripping
-        # the joined remote command back through shlex.split must recover
-        # the prompt as ONE argument.
-        import shlex
-
-        argv = _bottle(
-            agent_command="codex",
-            agent_prompt_mode="read_prompt_file",
-            agent_provider_template="codex",
-            prompt_path_in_guest="/home/node/.bot-bottle-prompt.txt",
-        ).agent_argv([], tty=False)
-        idx = argv.index("--")
-        remote_line = " ".join(argv[idx + 1:])  # what ssh sends to the guest
-        reparsed = shlex.split(remote_line)  # what the guest shell sees
-        prompt = "Read and follow the instructions in /home/node/.bot-bottle-prompt.txt."
-        self.assertIn(prompt, reparsed)
-        # codex is the last simple token before the (single) prompt arg.
-        self.assertEqual([*reparsed[reparsed.index("codex"):]], ["codex", prompt])
-
     def test_workdir_sets_chdir(self):
         # The agent runs from its workdir via `env --chdir` (ssh-safe;
         # not a `sh -c 'cd …'` wrapper, which the ssh arg-join mangles).
@@ -358,18 +334,6 @@ class TestBootArgs(unittest.TestCase):
         self.assertEqual("/run/rootfs.ext4", cfg["drives"][0]["path_on_host"])
         self.assertFalse(cfg["drives"][0]["is_read_only"])
         self.assertEqual("bbfc0", cfg["network-interfaces"][0]["host_dev_name"])
-        self.assertEqual(1, len(cfg["drives"]))  # no data drive by default
-
-    def test_config_adds_data_drive(self):
-        cfg = cast(Any, firecracker_vm._config(
-            rootfs=Path("/run/rootfs.ext4"), tap="bbfc0",
-            guest_ip="100.64.0.1", host_ip="100.64.0.0", pubkey="k",
-            vcpus=2, mem_mib=2048, guest_mac="06:00:AC:10:00:02",
-            data_drive=Path("/run/registry.ext4"),
-        ))
-        self.assertEqual(2, len(cfg["drives"]))
-        self.assertFalse(cfg["drives"][1]["is_root_device"])
-        self.assertEqual("/run/registry.ext4", cfg["drives"][1]["path_on_host"])
 
 
 class TestBottleExecClose(unittest.TestCase):

tests/unit/test_firecracker_helpers.py

@@ -6,13 +6,10 @@ 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
@@ -67,21 +64,6 @@ class TestNetpoolProbes(unittest.TestCase):
              patch.object(netpool, "tap_present", side_effect=[True, False]):
             self.assertEqual(["bbfc1"], netpool.missing_taps())
 
-    def test_orch_slot_is_top_of_ip_base_16(self):
-        # Dedicated orchestrator link: /31 at the top of the IP_BASE /16,
-        # clear of the pool (bottom of the block). Must match the shell
-        # script's orch_host()/orch_guest() and be a non-pool index.
-        with patch.dict("os.environ", {"BOT_BOTTLE_FC_IP_BASE": "10.243.0.0"}):
-            s = netpool.orch_slot()
-        self.assertEqual(netpool.ORCH_IFACE, s.iface)
-        self.assertEqual("10.243.255.0", s.host_ip)
-        self.assertEqual("10.243.255.1", s.guest_ip)
-        self.assertEqual(-1, s.index)
-        # Never collides with a pool slot's guest address.
-        with patch.dict("os.environ", {"BOT_BOTTLE_FC_IP_BASE": "10.243.0.0"}):
-            pool_guests = {sl.guest_ip for sl in netpool.all_slots()}
-        self.assertNotIn(s.guest_ip, pool_guests)
-
 
 class TestConsoleTail(unittest.TestCase):
     def test_reads_tail(self):
@@ -131,172 +113,5 @@ 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_firecracker_image_builder.py

@@ -1,74 +0,0 @@
-"""Unit tests for the docker-free Firecracker agent-image builder.
-
-The VM boot / SSH / buildah plumbing (`_build_in_infra`) is integration-tested
-on a KVM host; here we cover the cache decision, the boot-bit injection, and
-the smoke-test no-op — the logic that must hold without a VM.
-"""
-
-from __future__ import annotations
-
-import tempfile
-import unittest
-from pathlib import Path
-from unittest.mock import patch
-
-from bot_bottle.backend.firecracker import image_builder
-
-
-class TestBuildAgentRootfsDir(unittest.TestCase):
-    def setUp(self):
-        self._tmp = tempfile.TemporaryDirectory()
-        self.cache = Path(self._tmp.name)
-        self.dockerfile = self.cache / "Dockerfile"
-        self.dockerfile.write_text("FROM node:22-slim\n")
-        self.addCleanup(self._tmp.cleanup)
-
-    def test_cache_hit_skips_rebuild(self):
-        digest = image_builder._dockerfile_hash(self.dockerfile)
-        base = self.cache / "rootfs" / f"agent-{digest}"
-        base.mkdir(parents=True)
-        (base / ".bb-ready").write_text("ok\n")
-        with patch.object(image_builder.util, "cache_dir", return_value=self.cache), \
-             patch.object(image_builder, "_build_in_infra") as build:
-            out = image_builder.build_agent_rootfs_dir(
-                self.dockerfile, image_tag="t:latest")
-        build.assert_not_called()
-        self.assertEqual(base, out)
-
-    def test_cache_miss_builds_injects_and_marks_ready(self):
-        with patch.object(image_builder.util, "cache_dir", return_value=self.cache), \
-             patch.object(image_builder, "_build_in_infra") as build, \
-             patch.object(image_builder.util, "inject_guest_boot") as inject:
-            out = image_builder.build_agent_rootfs_dir(
-                self.dockerfile, image_tag="t:latest", smoke_test=("claude", "--version"))
-        build.assert_called_once()
-        # smoke_test threads through to the VM build.
-        self.assertEqual(("claude", "--version"), build.call_args.args[2])
-        inject.assert_called_once()
-        self.assertTrue((out / ".bb-ready").is_file())
-
-    def test_content_addressed_cache_key(self):
-        other = self.cache / "Dockerfile2"
-        other.write_text("FROM python:3.12-slim\n")
-        self.assertNotEqual(
-            image_builder._dockerfile_hash(self.dockerfile),
-            image_builder._dockerfile_hash(other),
-        )
-
-
-class TestSmokeTest(unittest.TestCase):
-    def test_empty_argv_is_noop(self):
-        with patch.object(image_builder, "_ssh") as ssh:
-            image_builder._smoke_test(Path("/k"), "10.0.0.1", "tag", "ctr", ())
-        ssh.assert_not_called()
-
-    def test_failed_smoke_dies(self):
-        import subprocess
-        result = subprocess.CompletedProcess([], 1, stdout="broken", stderr="")
-        with patch.object(image_builder, "_ssh", return_value=result), \
-             self.assertRaises(SystemExit):
-            image_builder._smoke_test(Path("/k"), "10.0.0.1", "tag", "ctr", ("claude", "--version"))
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_firecracker_infra_vm.py

@@ -1,189 +0,0 @@
-"""Unit tests for the Firecracker infra VM (control-plane VM boot).
-
-The KVM boot / HTTP reachability is integration-tested on a KVM host; here
-we cover the URL shape, the rootfs-variant wiring, and the health-poll
-decisions that must hold without a VM.
-"""
-
-from __future__ import annotations
-
-import os
-import unittest
-from pathlib import Path
-from unittest.mock import MagicMock, patch
-
-from bot_bottle.backend.firecracker import infra_vm
-
-
-class TestControlPlaneUrl(unittest.TestCase):
-    def test_url_uses_guest_ip_and_port(self):
-        infra = infra_vm.InfraVm(
-            vm=MagicMock(), guest_ip="10.243.255.1", private_key=Path("/k"))
-        self.assertEqual(
-            f"http://10.243.255.1:{infra_vm.CONTROL_PLANE_PORT}",
-            infra.control_plane_url,
-        )
-
-
-class TestBuildInfraRootfs(unittest.TestCase):
-    def test_uses_infra_variant_and_init(self):
-        with patch.object(infra_vm.util, "build_base_rootfs_dir") as build:
-            build.return_value = Path("/cache/rootfs/x-infra")
-            infra_vm.build_infra_rootfs_dir()
-        build.assert_called_once()
-        self.assertEqual(infra_vm._INFRA_IMAGE, build.call_args.args[0])
-        # variant is "-infra-<init-hash>" so an init change rebuilds the rootfs.
-        self.assertTrue(build.call_args.kwargs["variant"].startswith("-infra-"))
-        # The init runs BOTH the control plane and the gateway data plane,
-        # and exports PATH so gateway_init's subprocess daemons find python3.
-        init = build.call_args.kwargs["init_script"]
-        self.assertIn("bot_bottle.orchestrator", init)
-        self.assertIn("gateway_init.py", init)
-        self.assertIn("export PATH=", init)
-        # Persistent registry volume mounted at the DB dir before the CP starts.
-        self.assertIn("/dev/vdb", init)
-        # VM backend uses git-http (9420); the git:// daemon is left out.
-        self.assertIn("BOT_BOTTLE_GATEWAY_DAEMONS=egress,git-http,supervise", init)
-
-
-class TestSshGatewayTransport(unittest.TestCase):
-    def test_cp_into_preserves_source_mode(self):
-        import os
-        import tempfile
-        from subprocess import CompletedProcess
-        with tempfile.NamedTemporaryFile() as f:
-            os.chmod(f.name, 0o700)  # like the staged access-hook
-            t = infra_vm.SshGatewayTransport(Path("/k"), "10.0.0.1")
-            with patch.object(infra_vm.subprocess, "run",
-                              return_value=CompletedProcess([], 0)) as run:
-                t.cp_into(f.name, "/etc/git-gate/access-hook")
-        remote_cmd = run.call_args.args[0][-1]
-        self.assertIn("chmod 700", remote_cmd)  # exec bit preserved over SSH
-
-    def test_exec_raises_on_failure(self):
-        from subprocess import CompletedProcess
-        t = infra_vm.SshGatewayTransport(Path("/k"), "10.0.0.1")
-        with patch.object(infra_vm.subprocess, "run",
-                          return_value=CompletedProcess([], 1, stderr="nope")), \
-             self.assertRaises(infra_vm.GatewayProvisionError):
-            t.exec(["mkdir", "-p", "/git-gate"])
-
-
-class TestRegistryVolume(unittest.TestCase):
-    def test_reuses_existing_volume(self):
-        import tempfile
-        with tempfile.TemporaryDirectory() as td:
-            vol = Path(td) / "registry.ext4"
-            vol.write_bytes(b"")  # already present
-            with patch.object(infra_vm, "registry_volume_path", return_value=vol), \
-                 patch.object(infra_vm.subprocess, "run") as run:
-                out = infra_vm._ensure_registry_volume()
-            run.assert_not_called()  # no mke2fs when it exists
-            self.assertEqual(vol, out)
-
-    def test_creates_volume_when_missing(self):
-        import tempfile
-        from subprocess import CompletedProcess
-        with tempfile.TemporaryDirectory() as td:
-            vol = Path(td) / "registry.ext4"
-            with patch.object(infra_vm, "registry_volume_path", return_value=vol), \
-                 patch.object(infra_vm.subprocess, "run",
-                              return_value=CompletedProcess([], 0)) as run:
-                infra_vm._ensure_registry_volume()
-            argv = run.call_args.args[0]
-            self.assertIn("mke2fs", argv)
-            self.assertIn(str(vol), argv)
-
-
-class TestEnsureBuilt(unittest.TestCase):
-    def test_default_pulls_artifact_without_docker(self):
-        # PRD 0069 Stage 2: the launch host pulls the prebuilt rootfs; no Docker.
-        with patch.object(infra_vm.docker_mod, "build_image") as build, \
-                patch.object(infra_vm.infra_artifact, "ensure_artifact_gz") as pull:
-            infra_vm.ensure_built()
-        build.assert_not_called()
-        pull.assert_called_once()
-
-    def test_local_mode_builds_deps_before_infra(self):
-        with patch.dict(os.environ, {"BOT_BOTTLE_INFRA_BUILD": "local"}), \
-                patch.object(infra_vm.docker_mod, "build_image") as build:
-            infra_vm.ensure_built()
-        tags = [c.args[0] for c in build.call_args_list]
-        # infra is FROM gateway and COPY --from orchestrator, so both first.
-        self.assertEqual(infra_vm._INFRA_IMAGE, tags[-1])
-        self.assertIn(infra_vm._ORCHESTRATOR_IMAGE, tags[:-1])
-        self.assertIn(infra_vm._GATEWAY_IMAGE, tags[:-1])
-
-
-class TestWaitForHealth(unittest.TestCase):
-    def _infra(self, alive: bool = True) -> infra_vm.InfraVm:
-        vm = MagicMock()
-        vm.is_alive.return_value = alive
-        return infra_vm.InfraVm(vm=vm, guest_ip="10.0.0.1", private_key=Path("/k"))
-
-    def test_returns_on_200(self):
-        infra = self._infra()
-        cm = MagicMock()
-        cm.__enter__.return_value.status = 200
-        with patch.object(infra_vm.urllib.request, "urlopen", return_value=cm):
-            infra_vm.wait_for_health(infra, timeout=5)  # must not raise
-
-    def test_dies_when_vm_exits(self):
-        infra = self._infra(alive=False)
-        assert infra.vm is not None  # narrow for the type checker (it's a mock)
-        infra.vm.process.returncode = 1
-        with patch.object(infra_vm.firecracker_vm, "_console_tail", return_value=""), \
-             self.assertRaises(SystemExit):
-            infra_vm.wait_for_health(infra, timeout=5)
-
-
-class TestEnsureRunningSingleton(unittest.TestCase):
-    def test_adopts_when_healthy(self):
-        # A healthy control plane + existing key -> adopt (no boot), vm=None.
-        with patch.object(infra_vm, "_health_ok", return_value=True), \
-             patch.object(infra_vm, "_infra_dir") as d, \
-             patch.object(infra_vm, "boot") as boot:
-            keydir = MagicMock()
-            (keydir / "id_ed25519").exists.return_value = True
-            d.return_value = keydir
-            infra = infra_vm.ensure_running()
-        boot.assert_not_called()
-        self.assertIsNone(infra.vm)
-
-    def test_boots_when_unhealthy(self):
-        with patch.object(infra_vm, "_health_ok", return_value=False), \
-             patch.object(infra_vm, "stop") as stop, \
-             patch.object(infra_vm, "ensure_built") as built, \
-             patch.object(infra_vm, "boot") as boot, \
-             patch.object(infra_vm, "wait_for_health") as wait:
-            boot.return_value = infra_vm.InfraVm(
-                guest_ip="10.243.255.1", private_key=Path("/k"), vm=MagicMock())
-            infra_vm.ensure_running()
-        stop.assert_called_once()      # clear a stale VM first
-        built.assert_called_once()
-        boot.assert_called_once()
-        wait.assert_called_once()
-
-
-class TestKillPidfile(unittest.TestCase):
-    def test_noop_when_no_pidfile(self):
-        import tempfile
-        with tempfile.TemporaryDirectory() as td:
-            with patch.object(infra_vm, "_pid_file", return_value=Path(td) / "vm.pid"), \
-                 patch.object(infra_vm.os, "kill") as kill:
-                infra_vm._kill_pidfile()  # must not raise
-            kill.assert_not_called()
-
-    def test_skips_dead_or_recycled_pid(self):
-        import tempfile
-        with tempfile.TemporaryDirectory() as td:
-            pidf = Path(td) / "vm.pid"
-            pidf.write_text("999999")  # a PID that isn't a live firecracker
-            with patch.object(infra_vm, "_pid_file", return_value=pidf), \
-                 patch.object(infra_vm.os, "kill") as kill:
-                infra_vm._kill_pidfile()
-            kill.assert_not_called()
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_gateway_provision.py

@@ -8,7 +8,6 @@ from unittest.mock import Mock, patch
 
 from bot_bottle.backend.docker.gateway_provision import (
     GatewayProvisionError,
-    DockerGatewayTransport,
     deprovision_git_gate,
     provision_git_gate,
 )
@@ -55,7 +54,7 @@ class TestProvisionGitGate(unittest.TestCase):
     def test_copies_creds_and_runs_namespaced_init(self) -> None:
         calls: list[list[str]] = []
         with patch(_RUN, side_effect=_recorder(calls)):
-            provision_git_gate(DockerGatewayTransport("gw"), "bottle1", _plan(_up("foo", known_hosts="/host/kh")))
+            provision_git_gate("gw", "bottle1", _plan(_up("foo", known_hosts="/host/kh")))
 
         cps = [c for c in calls if c[:2] == ["docker", "cp"]]
         self.assertIn(["docker", "cp", "/host/keys/id", "gw:/git-gate/creds/bottle1/foo-key"], cps)
@@ -72,32 +71,32 @@ class TestProvisionGitGate(unittest.TestCase):
     def test_omits_known_hosts_copy_when_absent(self) -> None:
         calls: list[list[str]] = []
         with patch(_RUN, side_effect=_recorder(calls)):
-            provision_git_gate(DockerGatewayTransport("gw"), "b1", _plan(_up("foo")))  # no known_hosts
+            provision_git_gate("gw", "b1", _plan(_up("foo")))  # no known_hosts
         creds_cps = [c for c in calls if c[:2] == ["docker", "cp"] and "/git-gate/creds/" in c[3]]
         self.assertEqual(1, len(creds_cps))  # only the key, not known_hosts
         self.assertTrue(creds_cps[0][3].endswith("/foo-key"))
 
     def test_no_upstreams_is_noop(self) -> None:
         with patch(_RUN) as m:
-            provision_git_gate(DockerGatewayTransport("gw"), "b1", _plan())
+            provision_git_gate("gw", "b1", _plan())
         m.assert_not_called()
 
     def test_raises_on_docker_failure(self) -> None:
         with patch(_RUN, return_value=_proc(returncode=1, stderr="boom")):
             with self.assertRaises(GatewayProvisionError):
-                provision_git_gate(DockerGatewayTransport("gw"), "b1", _plan(_up("foo")))
+                provision_git_gate("gw", "b1", _plan(_up("foo")))
 
     def test_rejects_unsafe_bottle_id_before_any_docker(self) -> None:
         with patch(_RUN) as m:
             with self.assertRaises(GatewayProvisionError):
-                provision_git_gate(DockerGatewayTransport("gw"), "../etc", _plan(_up("foo")))
+                provision_git_gate("gw", "../etc", _plan(_up("foo")))
         m.assert_not_called()  # rejected before a single docker call
 
 
 class TestDeprovision(unittest.TestCase):
     def test_removes_repo_and_creds(self) -> None:
         with patch(_RUN, return_value=_proc()) as m:
-            deprovision_git_gate(DockerGatewayTransport("gw"), "b1")
+            deprovision_git_gate("gw", "b1")
         argv = m.call_args.args[0]
         self.assertEqual(["docker", "exec", "gw", "rm", "-rf"], argv[:5])
         self.assertIn("/git/b1", argv)
@@ -106,7 +105,7 @@ class TestDeprovision(unittest.TestCase):
     def test_rejects_unsafe_bottle_id(self) -> None:
         with patch(_RUN) as m:
             with self.assertRaises(GatewayProvisionError):
-                deprovision_git_gate(DockerGatewayTransport("gw"), "a/b")
+                deprovision_git_gate("gw", "a/b")
         m.assert_not_called()
 
 

tests/unit/test_git_gate_render_provision.py

@@ -6,7 +6,6 @@ Covers the pure `git_gate_render_gitconfig` renderer and the dynamic
 
 from __future__ import annotations
 
-import socket
 import tempfile
 import types
 import unittest
@@ -75,19 +74,6 @@ class TestRenderGitconfig(unittest.TestCase):
         out = git_gate_render_gitconfig((_entry(),), "1.2.3.4:9418", scheme="http")
         self.assertIn('[url "http://1.2.3.4:9418/repo.git"]', out)
 
-    def test_identity_token_extraheader_over_http(self) -> None:
-        # Delivered as a URL-scoped http.extraHeader so git-http can enforce
-        # the mandatory (source_ip, token) pair; only over the http transport.
-        out = git_gate_render_gitconfig(
-            (_entry(),), "1.2.3.4:9420", scheme="http", identity_token="TOK123")
-        self.assertIn('[http "http://1.2.3.4:9420/"]', out)
-        self.assertIn("extraHeader = x-bot-bottle-identity: TOK123", out)
-
-    def test_identity_token_omitted_over_git_scheme(self) -> None:
-        out = git_gate_render_gitconfig(
-            (_entry(),), "git-gate", scheme="git", identity_token="TOK123")
-        self.assertNotIn("extraHeader", out)
-
     def test_remote_key_alias_with_nondefault_port(self) -> None:
         out = git_gate_render_gitconfig(
             (_entry(RemoteKey="10.0.0.5", UpstreamPort="2222"),), "git-gate",
@@ -127,9 +113,8 @@ class TestProvisionDynamicKey(unittest.TestCase):
             self.assertEqual(b"PRIVATE-KEY-BYTES", key_file.read_bytes())
             id_file = Path(d) / "repo-deploy-key-id"
             self.assertEqual("kid123", id_file.read_text())
-        # owner_repo had .git stripped; title carries globalize_slug(slug) + name
-        hostname = socket.gethostname()
-        self.assertEqual([("o/r", f"bot-bottle:{hostname}-myslug:repo")], fake.created)
+        # owner_repo had .git stripped; title carries slug + name
+        self.assertEqual([("o/r", "bot-bottle:myslug:repo")], fake.created)
 
     def test_missing_token_raises(self) -> None:
         with tempfile.TemporaryDirectory() as d, \

tests/unit/test_infra_artifact.py

@@ -1,182 +0,0 @@
-"""Unit: the prebuilt infra-rootfs artifact pull (PRD 0069 Stage 2).
-
-The launch-host half — version hashing and download/verify/decompress — is
-what keeps a docker-free host from booting a stale or corrupted rootfs, so the
-checksum + fail-closed paths are locked here. Network is mocked; no Docker.
-"""
-
-from __future__ import annotations
-
-import gzip
-import hashlib
-import io
-import os
-import tempfile
-import unittest
-import urllib.error
-import urllib.request
-from pathlib import Path
-from unittest import mock
-
-from bot_bottle.backend.firecracker import infra_artifact as ia
-from bot_bottle.log import Die
-
-
-def _gz(data: bytes) -> bytes:
-    return gzip.compress(data)
-
-
-class _FakeNet:
-    """Map artifact URLs to bytes (or an HTTPError) for urlopen."""
-
-    def __init__(self, responses: "dict[str, bytes | Exception]") -> None:
-        self._responses = responses
-        self.calls: list[str] = []
-
-    def urlopen(self, req: urllib.request.Request, *a: object, **k: object) -> io.BytesIO:
-        url = req.full_url
-        self.calls.append(url)
-        val = self._responses.get(url)
-        if isinstance(val, Exception):
-            raise val
-        if val is None:
-            raise urllib.error.HTTPError(url, 404, "not found", {}, None)  # type: ignore[arg-type]
-        return io.BytesIO(val)
-
-
-class _CacheMixin(unittest.TestCase):
-    def setUp(self) -> None:
-        self._tmp = tempfile.TemporaryDirectory()
-        self._env = mock.patch.dict(
-            os.environ,
-            {"BOT_BOTTLE_FC_CACHE": self._tmp.name,
-             "BOT_BOTTLE_INFRA_ARTIFACT_TOKEN": ""},
-            clear=False,
-        )
-        self._env.start()
-        self.addCleanup(self._env.stop)
-        self.addCleanup(self._tmp.cleanup)
-
-    def _serve(self, version: str, gz_bytes: bytes, sha_text: str | None = None):
-        if sha_text is None:
-            sha_text = f"{hashlib.sha256(gz_bytes).hexdigest()}  rootfs.ext4.gz\n"
-        net = _FakeNet({
-            ia.artifact_url(version, "rootfs.ext4.gz"): gz_bytes,
-            ia.artifact_url(version, "rootfs.ext4.gz.sha256"): sha_text.encode(),
-        })
-        return mock.patch.object(ia.urllib.request, "urlopen", net.urlopen), net
-
-
-class TestVersion(unittest.TestCase):
-    def test_deterministic_16_hex(self) -> None:
-        v = ia.infra_artifact_version("#!/bin/sh\ntrue\n")
-        self.assertEqual(v, ia.infra_artifact_version("#!/bin/sh\ntrue\n"))
-        self.assertEqual(16, len(v))
-        int(v, 16)  # hex
-
-    def test_init_change_bumps_version(self) -> None:
-        self.assertNotEqual(
-            ia.infra_artifact_version("a"), ia.infra_artifact_version("b"))
-
-
-class TestVersionInputs(unittest.TestCase):
-    """The hash must cover *every* file baked into the rootfs, not just `*.py`
-    (`COPY bot_bottle` is wholesale) — else a non-Python change (e.g. the egress
-    entrypoint shell script) leaves the version unchanged and a launch host
-    boots a rootfs whose code differs from its checkout."""
-
-    def _fake_repo(self, root: Path) -> None:
-        pkg = root / "bot_bottle"
-        pkg.mkdir()
-        (pkg / "app.py").write_text("print('hi')\n")
-        (pkg / "egress_entrypoint.sh").write_text("#!/bin/sh\nexec mitmdump\n")
-        (pkg / "netpool.defaults.env").write_text("FOO=1\n")
-        for name in ("Dockerfile.orchestrator", "Dockerfile.gateway", "Dockerfile.infra"):
-            (root / name).write_text(f"FROM scratch  # {name}\n")
-
-    def test_non_python_file_change_bumps_version(self) -> None:
-        with tempfile.TemporaryDirectory() as d:
-            root = Path(d)
-            self._fake_repo(root)
-            before = ia.infra_artifact_version("init", repo_root=root)
-            (root / "bot_bottle" / "egress_entrypoint.sh").write_text(
-                "#!/bin/sh\nexec mitmdump --different\n")
-            after = ia.infra_artifact_version("init", repo_root=root)
-        self.assertNotEqual(before, after)
-
-    def test_pyc_and_pycache_ignored(self) -> None:
-        with tempfile.TemporaryDirectory() as d:
-            root = Path(d)
-            self._fake_repo(root)
-            before = ia.infra_artifact_version("init", repo_root=root)
-            cache = root / "bot_bottle" / "__pycache__"
-            cache.mkdir()
-            (cache / "app.cpython-312.pyc").write_bytes(b"\x00bytecode")
-            (root / "bot_bottle" / "app.pyc").write_bytes(b"\x00bytecode")
-            after = ia.infra_artifact_version("init", repo_root=root)
-        self.assertEqual(before, after)
-
-
-class TestEnsureArtifact(_CacheMixin):
-    def test_downloads_verifies_and_caches(self) -> None:
-        version = "deadbeef00000000"
-        gz = _gz(b"fake ext4 bytes")
-        patcher, net = self._serve(version, gz)
-        with patcher:
-            path = ia.ensure_artifact_gz(version)
-            self.assertTrue(path.is_file())
-            self.assertEqual(gz, path.read_bytes())
-            first_calls = len(net.calls)
-            # Second call is a cache hit — no further network.
-            ia.ensure_artifact_gz(version)
-            self.assertEqual(first_calls, len(net.calls))
-
-    def test_checksum_mismatch_fails_closed(self) -> None:
-        version = "beefbeefbeefbeef"
-        gz = _gz(b"payload")
-        patcher, _ = self._serve(version, gz, sha_text="0" * 64 + "  rootfs.ext4.gz\n")
-        with patcher:
-            with self.assertRaises(Die) as ctx:
-                ia.ensure_artifact_gz(version)
-        self.assertIn("checksum mismatch", str(ctx.exception.message))
-        # nothing left cached to accidentally boot
-        self.assertFalse((ia._cache_root(version) / "rootfs.ext4.gz").exists())
-
-    def test_missing_artifact_points_at_publish(self) -> None:
-        version = "0000000000000000"
-        net = _FakeNet({})  # everything 404s
-        with mock.patch.object(ia.urllib.request, "urlopen", net.urlopen):
-            with self.assertRaises(Die) as ctx:
-                ia.ensure_artifact_gz(version)
-        self.assertIn("publish_infra", str(ctx.exception.message))
-
-    def test_materialize_gunzips_to_dest(self) -> None:
-        version = "1234123412341234"
-        raw = b"the real rootfs contents" * 100
-        patcher, _ = self._serve(version, _gz(raw))
-        with patcher, tempfile.TemporaryDirectory() as d:
-            dest = Path(d) / "rootfs.ext4"
-            ia.materialize_ext4(version, dest)
-            self.assertEqual(raw, dest.read_bytes())
-
-
-class TestConfig(unittest.TestCase):
-    def test_base_and_owner_overridable(self) -> None:
-        with mock.patch.dict(os.environ, {
-            "BOT_BOTTLE_INFRA_ARTIFACT_BASE": "https://mirror.example/",
-            "BOT_BOTTLE_INFRA_ARTIFACT_OWNER": "acme",
-        }):
-            url = ia.artifact_url("v1", "rootfs.ext4.gz")
-        self.assertEqual(
-            "https://mirror.example/api/packages/acme/generic/"
-            "bot-bottle-firecracker-infra/v1/rootfs.ext4.gz", url)
-
-    def test_local_build_flag(self) -> None:
-        with mock.patch.dict(os.environ, {"BOT_BOTTLE_INFRA_BUILD": "local"}):
-            self.assertTrue(ia.local_build_requested())
-        with mock.patch.dict(os.environ, {"BOT_BOTTLE_INFRA_BUILD": ""}):
-            self.assertFalse(ia.local_build_requested())
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_macos_consolidated_launch.py

@@ -1,136 +0,0 @@
-"""Unit: macOS consolidated launch — register-after-start (PRD 0070)."""
-
-from __future__ import annotations
-
-import unittest
-from pathlib import Path
-from unittest.mock import MagicMock, Mock, patch
-
-from bot_bottle.backend.macos_container.consolidated_launch import (
-    GatewayEndpoint,
-    ensure_gateway,
-    register_agent,
-    teardown_consolidated,
-)
-from bot_bottle.egress import EgressPlan, EgressRoute
-from bot_bottle.git_gate import GitGatePlan
-from bot_bottle.orchestrator.client import RegisteredBottle
-
-_MOD = "bot_bottle.backend.macos_container.consolidated_launch"
-
-
-def _egress_plan() -> EgressPlan:
-    return EgressPlan(
-        slug="demo", routes_path=Path("/x"),
-        routes=(EgressRoute(host="api.example.com"),), token_env_map={},
-    )
-
-
-def _git_plan() -> GitGatePlan:
-    return GitGatePlan(
-        slug="demo", entrypoint_script=Path(), hook_script=Path(),
-        access_hook_script=Path(), upstreams=(),
-    )
-
-
-def _endpoint() -> GatewayEndpoint:
-    return GatewayEndpoint(
-        orchestrator_url="http://192.168.128.2:8099",
-        gateway_ip="192.168.128.3",
-        gateway_ca_pem="-----BEGIN CERTIFICATE-----\n",
-        network="bot-bottle-mac-gateway",
-    )
-
-
-def _client() -> Mock:
-    c = Mock()
-    c.register_bottle.return_value = RegisteredBottle("b1", "tok")
-    return c
-
-
-class TestEnsureGateway(unittest.TestCase):
-    def _run(self, service: MagicMock) -> GatewayEndpoint:
-        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 = InfraEndpoint(
-            control_plane_url="http://192.168.128.2:8099",
-            gateway_ip="192.168.128.2",
-        )
-        service.network = "bot-bottle-mac-gateway"
-        service.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("192.168.128.2", endpoint.gateway_ip)
-        self.assertEqual("PEM", endpoint.gateway_ca_pem)
-        self.assertEqual("bot-bottle-mac-gateway", endpoint.network)
-
-    def test_control_plane_and_gateway_share_one_address(self) -> None:
-        """One infra container hosts both, so the gateway IP and the
-        control-plane host are the same."""
-        endpoint = self._run(self._service())
-        self.assertEqual(
-            endpoint.gateway_ip,
-            endpoint.orchestrator_url.split("://")[1].split(":")[0],
-        )
-
-
-class TestRegisterAgent(unittest.TestCase):
-    def _run(
-        self, client: Mock, provision: Mock | None = None,
-        *, source_ip: str = "192.168.128.9",
-    ):
-        with patch(f"{_MOD}.OrchestratorClient", return_value=client), \
-                patch(f"{_MOD}.provision_git_gate", provision or Mock()):
-            return register_agent(
-                _egress_plan(), _git_plan(),
-                source_ip=source_ip, endpoint=_endpoint(), image_ref="img:1",
-            )
-
-    def test_registers_by_the_address_read_from_the_live_container(self) -> None:
-        """The attribution key is the DHCP-assigned address the caller read
-        back — there is no --ip to pin it up front."""
-        client = _client()
-        ctx = self._run(client, source_ip="192.168.128.9")
-        self.assertEqual("192.168.128.9", ctx.source_ip)
-        self.assertEqual("192.168.128.9", client.register_bottle.call_args.args[0])
-
-    def test_returns_identity_token_and_bottle_id(self) -> None:
-        ctx = self._run(_client())
-        self.assertEqual("b1", ctx.bottle_id)
-        self.assertEqual("tok", ctx.identity_token)
-
-    def test_provisions_git_gate_for_the_registered_bottle(self) -> None:
-        provision = Mock()
-        self._run(_client(), provision)
-        self.assertEqual("b1", provision.call_args.args[1])
-
-    def test_rolls_registration_back_when_provisioning_fails(self) -> None:
-        """A provisioning failure must not leave an orphan registration
-        holding the source IP."""
-        client = _client()
-        provision = Mock(side_effect=RuntimeError("boom"))
-        with self.assertRaises(RuntimeError):
-            self._run(client, provision)
-        client.teardown_bottle.assert_called_once_with("b1")
-
-
-class TestTeardown(unittest.TestCase):
-    def test_deregisters_and_deprovisions(self) -> None:
-        client = Mock()
-        deprovision = Mock()
-        with patch(f"{_MOD}.OrchestratorClient", return_value=client), \
-                patch(f"{_MOD}.deprovision_git_gate", deprovision):
-            teardown_consolidated("b1", orchestrator_url="http://o:8099")
-        client.teardown_bottle.assert_called_once_with("b1")
-        self.assertEqual("b1", deprovision.call_args.args[1])
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_macos_container_cleanup.py

@@ -43,31 +43,10 @@ class TestMacosContainerCleanup(unittest.TestCase):
 
 
 class TestMacosContainerEnumerate(unittest.TestCase):
-    """The backend launches bottles again (PRD 0070), so enumeration is real
-    rather than the disabled-era stub. These must not shell out: `container`
-    does not exist on the Linux CI host."""
-
-    def _enumerate(self, stdout: str, returncode: int = 0):
-        completed = enum_mod.subprocess.CompletedProcess(
-            args=[], returncode=returncode, stdout=stdout, stderr="",
-        )
-        with patch.object(enum_mod.subprocess, "run", return_value=completed), \
-                patch.object(enum_mod, "read_metadata", return_value=None):
-            return enum_mod.enumerate_active()
-
-    def test_lists_agent_containers_by_slug(self):
-        agents = self._enumerate("bot-bottle-dev-abc\nunrelated\n")
-        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_infra_singleton(self):
-        """The infra container shares the bot-bottle- prefix but is
-        infrastructure — listing it would invent an agent per host."""
-        agents = self._enumerate("bot-bottle-mac-infra\nbot-bottle-dev-abc\n")
-        self.assertEqual(["dev-abc"], [a.slug for a in agents])
-
-    def test_empty_when_the_cli_fails(self):
-        self.assertEqual([], self._enumerate("", returncode=1))
+    def test_enumerate_active_is_empty_while_disabled(self):
+        # The macOS backend is disabled during the companion-container removal cleanup
+        # (#385); it launches nothing, so there is nothing to enumerate.
+        self.assertEqual([], enum_mod.enumerate_active())
 
 
 if __name__ == "__main__":

tests/unit/test_macos_container_launch_wiring.py

@@ -1,210 +0,0 @@
-"""Unit: macOS agent run wiring — the attribution invariant + token delivery
-(PRD 0070).
-
-Replaces the argv coverage from the per-bottle companion-container era
-(`test_macos_container_launch.py`, removed with that architecture in #385).
-"""
-
-from __future__ import annotations
-
-import tempfile
-import unittest
-from pathlib import Path
-from types import SimpleNamespace
-from typing import cast
-from unittest.mock import patch
-
-from bot_bottle.backend.macos_container.bottle import MacosContainerBottle
-from bot_bottle.backend.macos_container.bottle_plan import MacosContainerBottlePlan
-from bot_bottle.backend.macos_container.consolidated_launch import GatewayEndpoint
-from bot_bottle.backend.macos_container.launch import (
-    _agent_run_argv,
-    _identity_proxy_env,
-    _proxy_url,
-)
-from bot_bottle.manifest import ManifestIndex
-
-_BOTTLE = "bot_bottle.backend.macos_container.bottle"
-
-_MANIFEST = ManifestIndex.from_json_obj({
-    "bottles": {"dev": {}},
-    "agents": {"demo": {"skills": [], "prompt": "", "bottle": "dev"}},
-}).load_for_agent("demo")
-
-
-def _endpoint() -> GatewayEndpoint:
-    return GatewayEndpoint(
-        orchestrator_url="http://192.168.128.2:8099",
-        gateway_ip="192.168.128.3",
-        gateway_ca_pem="PEM",
-        network="bot-bottle-mac-gateway",
-    )
-
-
-def _plan(
-    stage_dir: Path,
-    *,
-    agent_git_gate_url: str = "",
-    agent_supervise_url: str = "",
-) -> MacosContainerBottlePlan:
-    routes_path = stage_dir / "routes.yaml"
-    routes_path.write_text("routes: []\n", encoding="utf-8")
-    ca_path = stage_dir / "gateway-ca.pem"
-    ca_path.write_text("ca\n", encoding="utf-8")
-    egress_plan = SimpleNamespace(
-        mitmproxy_ca_host_path=ca_path,
-        routes_path=routes_path,
-        routes=("route",),
-        token_env_map={"EGRESS_TOKEN_0": "HOST_TOKEN"},
-        canary="",
-        canary_env="",
-    )
-    return cast(MacosContainerBottlePlan, SimpleNamespace(
-        spec=SimpleNamespace(),
-        manifest=_MANIFEST,
-        stage_dir=stage_dir,
-        slug="dev-abc",
-        container_name="bot-bottle-dev-abc",
-        image="bot-bottle-agent:latest",
-        forwarded_env={"OAUTH_TOKEN": "host-value"},
-        egress_plan=egress_plan,
-        git_gate_plan=SimpleNamespace(upstreams=()),
-        supervise_plan=None,
-        agent_provision=SimpleNamespace(
-            guest_env={"LITERAL": "value"},
-            provisioned_env={},
-        ),
-        agent_git_gate_url=agent_git_gate_url,
-        agent_supervise_url=agent_supervise_url,
-    ))
-
-
-class TestAgentRunArgv(unittest.TestCase):
-    def setUp(self) -> None:
-        self._tmp = tempfile.TemporaryDirectory()
-        self.argv = _agent_run_argv(_plan(Path(self._tmp.name)), _endpoint())
-
-    def tearDown(self) -> None:
-        self._tmp.cleanup()
-
-    def test_drops_net_raw(self) -> None:
-        """The attribution invariant: Apple grants CAP_NET_RAW by default,
-        which would let an agent forge a neighbour's source address with a raw
-        socket and be attributed as that bottle."""
-        self.assertIn("--cap-drop", self.argv)
-        self.assertEqual("CAP_NET_RAW", self.argv[self.argv.index("--cap-drop") + 1])
-
-    def test_attaches_to_the_shared_gateway_network(self) -> None:
-        self.assertEqual(
-            "bot-bottle-mac-gateway", self.argv[self.argv.index("--network") + 1],
-        )
-
-    def test_never_pins_an_ip(self) -> None:
-        """Apple Container 1.0.0 has no --ip: the address is DHCP-assigned and
-        read back after start."""
-        self.assertNotIn("--ip", self.argv)
-
-    def test_run_time_proxy_carries_no_identity_token(self) -> None:
-        """The token is minted by registration, which happens after this run —
-        so it cannot be here. `/resolve` denies the token-less pair (#366),
-        which is the safe direction; the real value arrives at exec time."""
-        joined = " ".join(self.argv)
-        self.assertIn(f"HTTP_PROXY={_proxy_url('192.168.128.3')}", joined)
-        self.assertNotIn("bottle:", joined)
-
-    def test_gateway_bypasses_the_proxy(self) -> None:
-        """git-http + supervise live on the gateway and must be reached
-        directly, not through its own egress proxy."""
-        entry = next(a for a in self.argv if a.startswith("NO_PROXY="))
-        self.assertIn("192.168.128.3", entry)
-
-    def test_forwarded_secrets_stay_off_argv(self) -> None:
-        """Bare name → inherited from the run process env, so the value never
-        lands on the command line."""
-        self.assertIn("OAUTH_TOKEN", self.argv)
-        self.assertNotIn("host-value", " ".join(self.argv))
-
-    def test_agent_init_is_a_no_op(self) -> None:
-        """Every agent command arrives via `container exec`; the init process
-        just holds the container open."""
-        self.assertEqual("sleep", self.argv[-2])
-
-
-class TestIdentityTokenDelivery(unittest.TestCase):
-    def test_exec_env_carries_the_token_as_proxy_credentials(self) -> None:
-        env = _identity_proxy_env(_endpoint(), "s3cret")
-        self.assertEqual(
-            "http://bottle:s3cret@192.168.128.3:9099", env["HTTP_PROXY"],
-        )
-        self.assertEqual(env["HTTP_PROXY"], env["https_proxy"])
-
-    def test_no_token_means_no_override(self) -> None:
-        self.assertEqual({}, _identity_proxy_env(_endpoint(), ""))
-
-    def test_token_value_never_reaches_argv(self) -> None:
-        """`ps` is world-readable: the token rides the child env behind a bare
-        `--env` name, never the command line."""
-        bottle = MacosContainerBottle(
-            "bot-bottle-demo", lambda: None, None,
-            exec_env=_identity_proxy_env(_endpoint(), "s3cret"),
-        )
-        argv = bottle.agent_argv(["--help"], tty=False)
-        self.assertNotIn("s3cret", " ".join(argv))
-        self.assertIn("HTTP_PROXY", argv)
-        self.assertEqual("--env", argv[argv.index("HTTP_PROXY") - 1])
-
-    def test_bottle_without_exec_env_is_unchanged(self) -> None:
-        bottle = MacosContainerBottle("bot-bottle-demo", lambda: None, None)
-        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."""
-        bottle = MacosContainerBottle(
-            "bot-bottle-demo", lambda: None, None,
-            exec_env=_identity_proxy_env(_endpoint(), "s3cret"),
-        )
-        with patch(f"{_BOTTLE}.subprocess.run") as run:
-            run.return_value = SimpleNamespace(returncode=0, stdout="", stderr="")
-            bottle.exec("echo hi")
-        argv, kwargs = run.call_args.args[0], run.call_args.kwargs
-        self.assertIn("HTTP_PROXY", argv)
-        self.assertNotIn("s3cret", " ".join(argv))
-        self.assertEqual(
-            "http://bottle:s3cret@192.168.128.3:9099", kwargs["env"]["HTTP_PROXY"],
-        )
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_macos_container_util.py

@@ -273,55 +273,5 @@ 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_infra.py

@@ -1,168 +0,0 @@
-"""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

@@ -11,22 +11,13 @@ import secrets
 import tempfile
 import threading
 import unittest
-import urllib.error
 import urllib.request
 from pathlib import Path
-from unittest.mock import patch
 
 from bot_bottle.orchestrator.broker import StubBroker
 from bot_bottle.orchestrator.control_plane import dispatch, make_server
 from bot_bottle.orchestrator.registry import RegistryStore
 from bot_bottle.orchestrator.service import Orchestrator
-from bot_bottle.store_manager import StoreManager
-from bot_bottle.supervise import (
-    Proposal,
-    TOOL_EGRESS_ALLOW,
-    sha256_hex,
-    write_proposal,
-)
 
 
 def _body(obj: object) -> bytes:
@@ -180,25 +171,13 @@ class TestDispatch(unittest.TestCase):
         )
         self.assertEqual(400, status)
 
-    def test_resolve_without_token_denies(self) -> None:
-        # Mandatory token: source-IP alone no longer resolves (fail-closed 403).
-        dispatch(
+    def test_resolve_without_token_by_source_ip(self) -> None:
+        _, reg = dispatch(
             self.orch, "POST", "/bottles",
             _body({"source_ip": "10.243.0.5", "policy": "P"}),
         )
-        status, _ = dispatch(
-            self.orch, "POST", "/resolve", _body({"source_ip": "10.243.0.5"})
-        )
-        self.assertEqual(403, status)
-
-    def test_resolve_with_matching_token(self) -> None:
-        _, reg = dispatch(
-            self.orch, "POST", "/bottles",
-            _body({"source_ip": "10.243.0.6", "policy": "P"}),
-        )
         status, payload = dispatch(
-            self.orch, "POST", "/resolve",
-            _body({"source_ip": "10.243.0.6", "identity_token": reg["identity_token"]}),
+            self.orch, "POST", "/resolve", _body({"source_ip": "10.243.0.5"})
         )
         self.assertEqual(200, status)
         self.assertEqual(reg["bottle_id"], payload["bottle_id"])
@@ -244,146 +223,5 @@ 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()."""
-
-    def setUp(self) -> None:
-        self._tmp = tempfile.TemporaryDirectory()
-        root = Path(self._tmp.name)
-        db = root / "db" / "bot-bottle.db"
-        db.parent.mkdir(parents=True)
-        self._env = patch.dict("os.environ", {
-            "BOT_BOTTLE_ROOT": str(root),
-            "SUPERVISE_DB_PATH": str(db),
-        })
-        self._env.start()
-        self.store = RegistryStore(db)
-        self.store.migrate()
-        StoreManager(db).migrate()
-        secret = secrets.token_bytes(16)
-        self.orch = Orchestrator(self.store, StubBroker(secret), secret)
-
-    def tearDown(self) -> None:
-        self._env.stop()
-        self._tmp.cleanup()
-
-    def _queue(self, slug: str, proposed: str) -> str:
-        self.store.register(
-            "10.243.0.1", metadata=json.dumps({"slug": slug}), policy="routes: []\n")
-        p = Proposal.new(
-            bottle_slug=slug, tool=TOOL_EGRESS_ALLOW, proposed_file=proposed,
-            justification="need it", current_file_hash=sha256_hex(proposed))
-        write_proposal(p)
-        return p.id
-
-    def test_list_pending(self) -> None:
-        pid = self._queue("demo", "routes:\n  - host: google.com\n")
-        status, payload = dispatch(self.orch, "GET", "/supervise/proposals", b"")
-        self.assertEqual(200, status)
-        proposals = payload["proposals"]
-        assert isinstance(proposals, list)
-        self.assertEqual(pid, proposals[0]["id"])
-
-    def test_respond_approve_applies_and_clears(self) -> None:
-        pid = self._queue("demo", "routes:\n  - host: google.com\n")
-        status, payload = dispatch(
-            self.orch, "POST", "/supervise/respond",
-            _body({"proposal_id": pid, "bottle_slug": "demo", "decision": "approve"}),
-        )
-        self.assertEqual(200, status)
-        self.assertTrue(payload["responded"])
-        _, listing = dispatch(self.orch, "GET", "/supervise/proposals", b"")
-        self.assertEqual([], listing["proposals"])
-
-    def test_respond_requires_fields(self) -> None:
-        status, _ = dispatch(
-            self.orch, "POST", "/supervise/respond", _body({"decision": "approve"}))
-        self.assertEqual(400, status)
-
-    def test_respond_unknown_proposal_conflicts(self) -> None:
-        status, payload = dispatch(
-            self.orch, "POST", "/supervise/respond",
-            _body({"proposal_id": "ghost", "bottle_slug": "demo", "decision": "approve"}),
-        )
-        self.assertEqual(409, status)
-        self.assertIn("no such proposal", str(payload["error"]))
-
-
 if __name__ == "__main__":
     unittest.main()

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], **_kw: object) -> Mock:
+        def fake(argv: list[str]) -> 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], **_kw: object) -> Mock:
+        def fake(argv: list[str]) -> 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], **_kw: object) -> Mock:
+        def fake(argv: list[str]) -> Mock:
             calls.append(argv)
             return _proc(stdout="") if argv[:2] == ["docker", "ps"] else _proc()
 
@@ -91,18 +91,11 @@ class TestDockerGateway(unittest.TestCase):
         self.assertEqual(self.sc.network, runs[0][runs[0].index("--network") + 1])
         # Persists its CA on a named volume so agents keep trusting it.
         self.assertTrue(any("mitmproxy" in a for a in runs[0]))
-        # Shares the ONE host DB: the supervise daemon queues into the same
-        # file the orchestrator + operator (over HTTP) use.
-        self.assertTrue(any(
-            a.startswith("SUPERVISE_DB_PATH=") and a.endswith("/run/supervise/bot-bottle.db")
-            for a in runs[0]))
-        self.assertTrue(any(
-            a.endswith(":/run/supervise") for a in runs[0]))
 
     def test_ensure_running_creates_network_when_missing(self) -> None:
         calls: list[list[str]] = []
 
-        def fake(argv: list[str], **_kw: object) -> Mock:
+        def fake(argv: list[str]) -> Mock:
             calls.append(argv)
             if argv[:3] == ["docker", "network", "inspect"]:
                 return _proc(returncode=1, stderr="No such network")
@@ -135,7 +128,7 @@ class TestDockerGateway(unittest.TestCase):
     def test_ensure_running_reuses_existing_network(self) -> None:
         calls: list[list[str]] = []
 
-        def fake(argv: list[str], **_kw: object) -> Mock:
+        def fake(argv: list[str]) -> Mock:
             calls.append(argv)
             return _proc(stdout="") if argv[:2] == ["docker", "ps"] else _proc()
 
@@ -144,7 +137,7 @@ 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], **_kw: object) -> Mock:
+        def fake(argv: list[str]) -> Mock:
             if argv[:2] == ["docker", "ps"]:
                 return _proc(stdout="")
             if argv[:2] == ["docker", "run"]:
@@ -181,7 +174,7 @@ class TestDockerGatewayBuild(unittest.TestCase):
         # build-if-missing silently ran a stale single-tenant image.
         calls: list[list[str]] = []
 
-        def rec(argv: list[str], **_kw: object) -> Mock:
+        def rec(argv: list[str]) -> Mock:
             calls.append(argv)
             return _proc()  # image present, build succeeds
 
@@ -196,7 +189,7 @@ 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], **_kw: object) -> Mock:
+        def rec(argv: list[str]) -> Mock:
             calls.append(argv)
             return _proc()
 

tests/unit/test_orchestrator_lifecycle.py

@@ -14,7 +14,7 @@ from bot_bottle.orchestrator.lifecycle import (
     ORCHESTRATOR_SOURCE_HASH_LABEL,
     OrchestratorService,
     OrchestratorStartError,
-    source_hash,
+    _source_hash,
 )
 from tests.unit import use_bottle_root
 
@@ -57,10 +57,10 @@ class TestOrchestratorService(unittest.TestCase):
         # A healthy control plane already running the *current* bind-mounted
         # source is left alone — recreating it on every launch would drop
         # every other active bottle's in-memory egress tokens (#381).
-        current = source_hash(self.svc._repo_root)
+        current = _source_hash(self.svc._repo_root)
         calls: list[list[str]] = []
 
-        def fake(argv: list[str], **_kw: object) -> Mock:
+        def fake(argv: list[str]) -> 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], **_kw: object) -> Mock:
+        def fake(argv: list[str]) -> Mock:
             calls.append(argv)
             if argv[:2] == ["docker", "ps"]:
                 return _proc(stdout=ORCHESTRATOR_NAME)
@@ -98,13 +98,13 @@ class TestOrchestratorService(unittest.TestCase):
         self.assertEqual(1, len(runs))
         self.assertIn(ORCHESTRATOR_NAME, runs[0])
         # the fresh container is labeled with the current hash, not the stale one
-        current = source_hash(self.svc._repo_root)
+        current = _source_hash(self.svc._repo_root)
         self.assertIn(f"{ORCHESTRATOR_SOURCE_HASH_LABEL}={current}", runs[0])
 
     def test_ensure_running_starts_orchestrator_container_when_absent(self) -> None:
         calls: list[list[str]] = []
 
-        def fake(argv: list[str], **_kw: object) -> Mock:
+        def fake(argv: list[str]) -> 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], **_kw: object) -> Mock:
+        def fake(argv: list[str]) -> 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], **_kw: object) -> Mock:
+        def fake(argv: list[str]) -> Mock:
             calls.append(argv)
             if argv[:2] == ["docker", "ps"]:
                 return _proc(stdout="")

tests/unit/test_orchestrator_service.py

@@ -2,26 +2,15 @@
 
 from __future__ import annotations
 
-import json
 import secrets
 import tempfile
 import unittest
 from pathlib import Path
-from unittest.mock import patch
 
 from bot_bottle.orchestrator.broker import LaunchBroker, LaunchRequest, StubBroker
 from bot_bottle.orchestrator.registry import RegistryStore
 from bot_bottle.orchestrator.service import Orchestrator
 from bot_bottle.orchestrator.gateway import Gateway
-from bot_bottle.store_manager import StoreManager
-from bot_bottle.supervise import (
-    Proposal,
-    STATUS_APPROVED,
-    TOOL_EGRESS_ALLOW,
-    read_response,
-    sha256_hex,
-    write_proposal,
-)
 
 
 class _FailingBroker(LaunchBroker):
@@ -125,12 +114,9 @@ class TestOrchestrator(unittest.TestCase):
     def test_set_policy_unknown_is_false(self) -> None:
         self.assertFalse(self.orch.set_policy("ghost", "{}"))
 
-    def test_resolve_requires_matching_token(self) -> None:
-        # Mandatory (source_ip, token) pair — no source-IP-only fallback.
+    def test_resolve_by_source_ip_without_token(self) -> None:
         rec = self.orch.launch_bottle("10.243.0.1", policy="P")
-        self.assertIsNone(self.orch.resolve("10.243.0.1", ""))  # empty token denies
-        self.assertIsNone(self.orch.resolve("10.243.0.1", "wrong"))  # mismatch denies
-        got = self.orch.resolve("10.243.0.1", rec.identity_token)  # exact pair
+        got = self.orch.resolve("10.243.0.1")  # network-layer, no token
         assert got is not None
         self.assertEqual(rec.bottle_id, got.bottle_id)
         self.assertEqual("P", got.policy)
@@ -166,141 +152,5 @@ class TestOrchestrator(unittest.TestCase):
         )
 
 
-class TestOrchestratorSupervise(unittest.TestCase):
-    """Operator-approval flow: the orchestrator applies the decision
-    server-side against the single DB (queue + policy + audit)."""
-
-    def setUp(self) -> None:
-        self._tmp = tempfile.TemporaryDirectory()
-        root = Path(self._tmp.name)
-        db = root / "db" / "bot-bottle.db"
-        db.parent.mkdir(parents=True)
-        # One DB for registry + supervise queue + audit (as in the VM).
-        self._env = patch.dict("os.environ", {
-            "BOT_BOTTLE_ROOT": str(root),
-            "SUPERVISE_DB_PATH": str(db),
-        })
-        self._env.start()
-        self.store = RegistryStore(db)
-        self.store.migrate()
-        StoreManager(db).migrate()
-        secret = secrets.token_bytes(16)
-        self.orch = Orchestrator(self.store, StubBroker(secret), secret)
-
-    def tearDown(self) -> None:
-        self._env.stop()
-        self._tmp.cleanup()
-
-    def _register(self, slug: str, policy: str) -> str:
-        rec = self.store.register(
-            "10.243.0.1", metadata=json.dumps({"slug": slug}), policy=policy)
-        return rec.bottle_id
-
-    def _queue(self, slug: str, proposed: str) -> str:
-        p = Proposal.new(
-            bottle_slug=slug, tool=TOOL_EGRESS_ALLOW, proposed_file=proposed,
-            justification="need it", current_file_hash=sha256_hex(proposed))
-        write_proposal(p)
-        return p.id
-
-    def test_pending_lists_queued_proposal(self) -> None:
-        self._register("demo", "routes: []\n")
-        pid = self._queue("demo", "routes:\n  - host: google.com\n")
-        pending = self.orch.supervise_pending()
-        self.assertEqual(1, len(pending))
-        self.assertEqual(pid, pending[0]["id"])
-        self.assertEqual("demo", pending[0]["bottle_slug"])
-
-    def test_approve_applies_policy_writes_response_and_clears_pending(self) -> None:
-        bottle_id = self._register("demo", "routes:\n  - host: existing.com\n")
-        new_routes = "routes:\n  - host: google.com\n"
-        pid = self._queue("demo", new_routes)
-        ok, err = self.orch.supervise_respond(
-            pid, bottle_slug="demo", decision="approve")
-        self.assertTrue(ok, err)
-        # policy live-applied so /resolve serves the new routes
-        rec = self.store.get(bottle_id)
-        assert rec is not None
-        self.assertEqual(new_routes, rec.policy)
-        # response written -> agent unblocks, proposal no longer pending
-        self.assertEqual(STATUS_APPROVED, read_response("demo", pid).status)
-        self.assertEqual([], self.orch.supervise_pending())
-
-    def test_pending_carries_human_label(self) -> None:
-        # The proposal is keyed by bottle_id, but pending dicts also expose the
-        # bottle's human slug so the operator sees a name, not a hex id.
-        bottle_id = self._register("codex-dev-a1b2c", "routes: []\n")
-        self._queue(bottle_id, "routes:\n  - host: google.com\n")
-        pending = self.orch.supervise_pending()
-        self.assertEqual(bottle_id, pending[0]["bottle_slug"])
-        self.assertEqual("codex-dev-a1b2c", pending[0]["bottle_label"])
-
-    def test_pending_label_falls_back_to_slug_when_bottle_gone(self) -> None:
-        # No registry record (torn down): label is the id, never empty.
-        self._queue("ghost-id", "routes:\n  - host: google.com\n")
-        pending = self.orch.supervise_pending()
-        self.assertEqual("ghost-id", pending[0]["bottle_label"])
-
-    def test_approve_by_bottle_id_applies_policy(self) -> None:
-        # Consolidated reality: the supervise server keys each proposal by the
-        # orchestrator-assigned bottle_id, not the human slug. Approval must
-        # resolve the record by that id and apply the policy (regression for
-        # the "bottle <id> is no longer registered" 409).
-        bottle_id = self._register("codex-dev-a1b2c", "routes: []\n")
-        new_routes = "routes:\n  - host: google.com\n"
-        pid = self._queue(bottle_id, new_routes)
-        ok, err = self.orch.supervise_respond(
-            pid, bottle_slug=bottle_id, decision="approve")
-        self.assertTrue(ok, err)
-        rec = self.store.get(bottle_id)
-        assert rec is not None
-        self.assertEqual(new_routes, rec.policy)
-
-    def test_modify_applies_final_file_not_proposed(self) -> None:
-        bottle_id = self._register("demo", "routes: []\n")
-        pid = self._queue("demo", "routes:\n  - host: google.com\n")
-        edited = "routes:\n  - host: example.com\n"
-        ok, _ = self.orch.supervise_respond(
-            pid, bottle_slug="demo", decision="modify", final_file=edited)
-        self.assertTrue(ok)
-        rec = self.store.get(bottle_id)
-        assert rec is not None
-        self.assertEqual(edited, rec.policy)
-
-    def test_reject_leaves_policy_unchanged(self) -> None:
-        bottle_id = self._register("demo", "routes:\n  - host: existing.com\n")
-        pid = self._queue("demo", "routes:\n  - host: google.com\n")
-        ok, _ = self.orch.supervise_respond(
-            pid, bottle_slug="demo", decision="reject", notes="no")
-        self.assertTrue(ok)
-        rec = self.store.get(bottle_id)
-        assert rec is not None
-        self.assertEqual("routes:\n  - host: existing.com\n", rec.policy)
-        self.assertEqual("rejected", read_response("demo", pid).status)
-
-    def test_unknown_proposal_is_error(self) -> None:
-        ok, err = self.orch.supervise_respond(
-            "ghost", bottle_slug="demo", decision="approve")
-        self.assertFalse(ok)
-        self.assertIn("no such proposal", err)
-
-    def test_unknown_decision_is_error(self) -> None:
-        self._register("demo", "routes: []\n")
-        pid = self._queue("demo", "routes:\n  - host: google.com\n")
-        ok, err = self.orch.supervise_respond(
-            pid, bottle_slug="demo", decision="bogus")
-        self.assertFalse(ok)
-        self.assertIn("unknown decision", err)
-
-    def test_approve_when_bottle_gone_cannot_apply(self) -> None:
-        # Proposal queued but the bottle was torn down before the operator
-        # acted: an egress apply has no target, so respond fails closed.
-        pid = self._queue("ghost-bottle", "routes:\n  - host: google.com\n")
-        ok, err = self.orch.supervise_respond(
-            pid, bottle_slug="ghost-bottle", decision="approve")
-        self.assertFalse(ok)
-        self.assertIn("no longer registered", err)
-
-
 if __name__ == "__main__":
     unittest.main()

tests/unit/test_publish_infra.py

@@ -1,62 +0,0 @@
-"""Unit: the infra-artifact publisher's upload path (PRD 0069 Stage 2).
-
-The rootfs is hundreds of MB, so `_put` must stream it from disk rather than
-read it into memory. Network is mocked; no Docker, no real build.
-"""
-
-from __future__ import annotations
-
-import tempfile
-import unittest
-import urllib.request
-from pathlib import Path
-from unittest import mock
-
-from bot_bottle.backend.firecracker import publish_infra as pub
-
-
-class _Resp:
-    status = 201
-
-    def __enter__(self) -> "_Resp":
-        return self
-
-    def __exit__(self, *a: object) -> bool:
-        return False
-
-
-class TestPut(unittest.TestCase):
-    def test_streams_file_body_with_content_length(self) -> None:
-        captured: list[urllib.request.Request] = []
-
-        def fake_urlopen(req: urllib.request.Request, *a: object, **k: object) -> _Resp:
-            captured.append(req)
-            return _Resp()
-
-        with tempfile.TemporaryDirectory() as d:
-            f = Path(d) / "rootfs.ext4.gz"
-            payload = b"x" * 4096
-            f.write_bytes(payload)
-            with mock.patch.object(pub.urllib.request, "urlopen", fake_urlopen):
-                pub._put("https://reg/pkg", f, token="t")
-
-        req = captured[0]
-        # Body is the open file object (streamed), never the bytes in memory.
-        self.assertTrue(hasattr(req.data, "read"))
-        self.assertNotIsInstance(req.data, (bytes, bytearray))
-        self.assertEqual(str(len(payload)), req.get_header("Content-length"))
-
-    def test_small_bytes_body_still_works(self) -> None:
-        captured: list[urllib.request.Request] = []
-
-        def fake_urlopen(req: urllib.request.Request, *a: object, **k: object) -> _Resp:
-            captured.append(req)
-            return _Resp()
-
-        with mock.patch.object(pub.urllib.request, "urlopen", fake_urlopen):
-            pub._put("https://reg/sha", b"abc123  rootfs\n", token="")
-        self.assertEqual(b"abc123  rootfs\n", captured[0].data)
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_supervise_cli.py

@@ -1,24 +1,31 @@
-"""Unit: supervise headless paths — the discovery + approve/reject that the
-TUI key handlers call into.
+"""Unit: supervise headless paths (PRD 0013 phase 4, PRD 0016).
 
-These go through the orchestrator HTTP client now (the operator never
-touches the DB directly), so the client is mocked here; the server-side
-apply / response / audit is covered in test_orchestrator_service.
+The curses TUI itself isn't exercised here — these tests cover the
+discovery + approve/reject paths that the TUI's key handlers call into.
 """
 
 import os
 import tempfile
 import unittest
 from datetime import datetime, timezone
-from unittest.mock import MagicMock, patch
+from pathlib import Path
+from unittest.mock import patch
 
+from bot_bottle import supervise
+from tests.unit import use_bottle_root
+from bot_bottle.audit_store import AuditStore
 from bot_bottle.cli import supervise as supervise_cli
+from bot_bottle.queue_store import QueueStore
 from bot_bottle.supervise import (
     Proposal,
+    STATUS_APPROVED,
+    STATUS_MODIFIED,
+    STATUS_REJECTED,
     TOOL_EGRESS_ALLOW,
-    TOOL_EGRESS_BLOCK,
     TOOL_GITLEAKS_ALLOW,
     TOOL_EGRESS_TOKEN_ALLOW,
+    read_audit_entries,
+    read_response,
     sha256_hex,
 )
 
@@ -26,131 +33,198 @@ from bot_bottle.supervise import (
 FIXED = datetime(2026, 5, 25, 12, 0, 0, tzinfo=timezone.utc)
 
 
-def _proposal(slug: str = "dev", tool: str = TOOL_EGRESS_ALLOW,
-              *, now: datetime = FIXED) -> Proposal:
+def _proposal(slug: str = "dev", tool: str = TOOL_EGRESS_ALLOW) -> Proposal:
     payloads = {
-        TOOL_EGRESS_ALLOW: "routes:\n  - host: example.com\n",
-        TOOL_EGRESS_BLOCK: "routes:\n  - host: example.com\n",
+        supervise.TOOL_EGRESS_ALLOW: "routes:\n  - host: example.com\n",
+        supervise.TOOL_EGRESS_BLOCK: "routes:\n  - host: example.com\n",
         TOOL_GITLEAKS_ALLOW: "file: tests/test_fixture.py\nline: 3\n",
         TOOL_EGRESS_TOKEN_ALLOW: "host: api.example.com\ndetector: token\n",
     }
     payload = payloads.get(tool, "")
     return Proposal.new(
-        bottle_slug=slug, tool=tool, proposed_file=payload,
-        justification=f"needed for {slug}", current_file_hash=sha256_hex(payload),
-        now=now,
+        bottle_slug=slug, tool=tool,
+        proposed_file=payload,
+        justification=f"needed for {slug}",
+        current_file_hash=sha256_hex(payload),
+        now=FIXED,
     )
 
 
-class _ClientMixin:
-    """Install a mock orchestrator client as the CLI-session singleton."""
+class _FakeHomeMixin:
+    """Point bot_bottle_root at a temp dir (via BOT_BOTTLE_ROOT) for the test."""
 
-    def _install_client(self, pending: "list[Proposal] | None" = None) -> MagicMock:
-        client = MagicMock()
-        client.supervise_pending.return_value = [
-            p.to_dict() for p in (pending or [])
-        ]
-        patcher = patch.object(supervise_cli, "_client", return_value=client)
-        patcher.start()
-        self.addCleanup(patcher.stop)  # type: ignore[attr-defined]
-        self.addCleanup(  # type: ignore[attr-defined]
-            lambda: setattr(supervise_cli, "_client_instance", None))
-        return client
+    def _setup_fake_home(self):
+        self._tmp = tempfile.TemporaryDirectory(prefix="supervise-test.")
+        self._restore_home = use_bottle_root(Path(self._tmp.name) / ".bot-bottle")
+        QueueStore("").migrate()
+        AuditStore().migrate()
+
+    def _teardown_fake_home(self):
+        self._restore_home()
+        self._tmp.cleanup()
 
 
-class TestDiscoverPending(_ClientMixin, unittest.TestCase):
-    def test_empty(self) -> None:
-        self._install_client([])
+class TestDiscoverPending(_FakeHomeMixin, unittest.TestCase):
+    def setUp(self):
+        self._setup_fake_home()
+
+    def tearDown(self):
+        self._teardown_fake_home()
+
+    def test_empty_when_no_queues(self):
         self.assertEqual([], supervise_cli.discover_pending())
 
-    def test_lists_all_bottles(self) -> None:
-        self._install_client([_proposal("dev"), _proposal("api")])
+    def test_walks_all_slug_subdirs(self):
+        for slug in ("dev", "api"):
+            supervise.write_proposal(_proposal(slug=slug))
         pending = supervise_cli.discover_pending()
-        self.assertEqual(
-            {"dev", "api"}, {qp.proposal.bottle_slug for qp in pending})
+        self.assertEqual({"dev", "api"}, {qp.proposal.bottle_slug for qp in pending})
 
-    def test_sorted_by_arrival(self) -> None:
-        early = _proposal(
-            "api", now=datetime(2026, 5, 25, 10, 0, 0, tzinfo=timezone.utc))
-        late = _proposal(
-            "dev", now=datetime(2026, 5, 25, 14, 0, 0, tzinfo=timezone.utc))
-        self._install_client([late, early])
+    def test_sorted_by_arrival_across_bottles(self):
+        early = Proposal.new(
+            bottle_slug="api", tool=TOOL_EGRESS_ALLOW,
+            proposed_file="routes:\n  - host: early.example.com\n", justification="early",
+            current_file_hash="h",
+            now=datetime(2026, 5, 25, 10, 0, 0, tzinfo=timezone.utc),
+        )
+        late = Proposal.new(
+            bottle_slug="dev", tool=TOOL_EGRESS_ALLOW,
+            proposed_file="routes:\n  - host: late.example.com\n", justification="late",
+            current_file_hash="h",
+            now=datetime(2026, 5, 25, 14, 0, 0, tzinfo=timezone.utc),
+        )
+        for p in (late, early):
+            supervise.write_proposal(p)
         pending = supervise_cli.discover_pending()
         self.assertEqual([early.id, late.id], [qp.proposal.id for qp in pending])
 
-    def test_label_comes_from_bottle_label(self) -> None:
-        # The server tags each dict with the human slug; the CLI displays it
-        # while the proposal stays keyed by the opaque bottle_id.
-        client = MagicMock()
-        d = _proposal("3601cbe883c2786d").to_dict()
-        d["bottle_label"] = "codex-dev-a1b2c"
-        client.supervise_pending.return_value = [d]
-        with patch.object(supervise_cli, "_client", return_value=client):
-            pending = supervise_cli.discover_pending()
-        self.assertEqual("codex-dev-a1b2c", pending[0].label)
-        self.assertEqual("3601cbe883c2786d", pending[0].proposal.bottle_slug)
-
-    def test_label_falls_back_to_slug_when_absent(self) -> None:
-        # Legacy dicts without bottle_label (e.g. an older orchestrator).
-        self._install_client([_proposal("dev")])
-        self.assertEqual("dev", supervise_cli.discover_pending()[0].label)
+    def test_excludes_already_responded(self):
+        p = _proposal()
+        supervise.write_proposal(p)
+        supervise.write_response("dev", supervise.Response(
+            proposal_id=p.id, status=STATUS_APPROVED, notes="",
+        ))
+        self.assertEqual([], supervise_cli.discover_pending())
 
 
-class TestApproveReject(_ClientMixin, unittest.TestCase):
-    def _qp(self, tool: str = TOOL_EGRESS_ALLOW) -> "supervise_cli.QueuedProposal":
-        return supervise_cli.QueuedProposal(proposal=_proposal(tool=tool))
+class TestApproveReject(_FakeHomeMixin, unittest.TestCase):
+    def setUp(self):
+        self._setup_fake_home()
 
-    def test_approve_calls_respond(self) -> None:
-        client = self._install_client()
-        qp = self._qp()
-        supervise_cli.approve(qp)
-        client.supervise_respond.assert_called_once_with(
-            qp.proposal.id, bottle_slug="dev", decision="approve",
-            notes="", final_file=None,
-        )
+    def tearDown(self):
+        self._teardown_fake_home()
 
-    def test_modify_sets_decision_and_final_file(self) -> None:
-        client = self._install_client()
-        qp = self._qp()
-        edited = "routes:\n  - host: edited.example.com\n"
-        supervise_cli.approve(qp, final_file=edited, notes="tweaked")
-        client.supervise_respond.assert_called_once_with(
-            qp.proposal.id, bottle_slug="dev", decision="modify",
-            notes="tweaked", final_file=edited,
-        )
+    def _enqueue(self, tool: str = TOOL_EGRESS_ALLOW):
+        p = _proposal(tool=tool)
+        supervise.write_proposal(p)
+        return supervise_cli.QueuedProposal(proposal=p)
 
-    def test_reject_calls_respond(self) -> None:
-        client = self._install_client()
-        qp = self._qp()
+    def test_approve_writes_response(self):
+        qp = self._enqueue()
+        with patch(
+            "bot_bottle.cli.supervise.apply_routes_change",
+            return_value=("routes: []\n", "routes:\n  - host: example.com\n"),
+        ):
+            supervise_cli.approve(qp)
+        resp = read_response(qp.proposal.bottle_slug, qp.proposal.id)
+        self.assertEqual(STATUS_APPROVED, resp.status)
+        self.assertIsNone(resp.final_file)
+
+    def test_approve_with_final_file_marks_modified(self):
+        qp = self._enqueue()
+        with patch(
+            "bot_bottle.cli.supervise.apply_routes_change",
+            return_value=("routes: []\n", "routes:\n  - host: edited.example.com\n"),
+        ):
+            supervise_cli.approve(
+                qp,
+                final_file="routes:\n  - host: edited.example.com\n",
+                notes="tweaked",
+            )
+        resp = read_response(qp.proposal.bottle_slug, qp.proposal.id)
+        self.assertEqual(STATUS_MODIFIED, resp.status)
+        self.assertEqual("routes:\n  - host: edited.example.com\n", resp.final_file)
+        self.assertEqual("tweaked", resp.notes)
+
+    def test_reject_writes_rejection(self):
+        qp = self._enqueue()
         supervise_cli.reject(qp, reason="nope")
-        client.supervise_respond.assert_called_once_with(
-            qp.proposal.id, bottle_slug="dev", decision="reject", notes="nope",
-        )
+        resp = read_response(qp.proposal.bottle_slug, qp.proposal.id)
+        self.assertEqual(STATUS_REJECTED, resp.status)
+        self.assertEqual("nope", resp.notes)
 
-    def test_tui_report_only_requires_reason(self) -> None:
-        self._install_client()
-        qp = self._qp(tool=TOOL_GITLEAKS_ALLOW)
+    def test_approve_egress_block_writes_audit_log(self):
+        qp = self._enqueue(tool=supervise.TOOL_EGRESS_BLOCK)
+        with patch(
+            "bot_bottle.cli.supervise.apply_routes_change",
+            return_value=("routes: []\n", "routes:\n  - host: example.com\n"),
+        ) as apply_routes_change:
+            supervise_cli.approve(qp)
+        apply_routes_change.assert_called_once_with(
+            "dev",
+            "routes:\n  - host: example.com\n",
+        )
+        entries = read_audit_entries("egress", "dev")
+        self.assertEqual(1, len(entries))
+        self.assertEqual(STATUS_APPROVED, entries[0].operator_action)
+        self.assertEqual("needed for dev", entries[0].justification)
+
+    def test_approve_gitleaks_allow_leaves_response_for_gate(self):
+        qp = self._enqueue(tool=TOOL_GITLEAKS_ALLOW)
+        supervise_cli.approve(qp, notes="dummy fixture")
+        # Gate polls the DB for the response; TUI must not archive it.
+        resp = read_response(qp.proposal.bottle_slug, qp.proposal.id)
+        self.assertEqual(STATUS_APPROVED, resp.status)
+        self.assertEqual("dummy fixture", resp.notes)
+
+    def test_tui_gitleaks_allow_requires_reason(self):
+        qp = self._enqueue(tool=TOOL_GITLEAKS_ALLOW)
         with patch.object(supervise_cli, "_prompt", return_value=""):
             status = supervise_cli._approve_from_tui(None, qp)  # type: ignore[arg-type]
         self.assertEqual("approve aborted (empty reason)", status)
 
-    def test_tui_report_only_writes_reason(self) -> None:
-        client = self._install_client()
-        qp = self._qp(tool=TOOL_GITLEAKS_ALLOW)
+    def test_tui_gitleaks_allow_writes_reason(self):
+        qp = self._enqueue(tool=TOOL_GITLEAKS_ALLOW)
         with patch.object(supervise_cli, "_prompt", return_value="test fixture"):
             status = supervise_cli._approve_from_tui(None, qp)  # type: ignore[arg-type]
         self.assertIn("approved gitleaks-allow", status)
-        client.supervise_respond.assert_called_once()
-        self.assertEqual(
-            "test fixture", client.supervise_respond.call_args.kwargs["notes"])
+        resp = read_response(qp.proposal.bottle_slug, qp.proposal.id)
+        self.assertEqual("test fixture", resp.notes)
 
-    def test_suffix_for_token_allow_is_txt(self) -> None:
-        self.assertEqual(
-            ".txt", supervise_cli._suffix_for_tool(TOOL_EGRESS_TOKEN_ALLOW))
+    def test_approve_token_allow_leaves_response_for_egress(self):
+        qp = self._enqueue(tool=TOOL_EGRESS_TOKEN_ALLOW)
+        supervise_cli.approve(qp, notes="false positive")
+        # The egress addon polls the DB for the response; the TUI must
+        # not archive it (the addon archives after reading).
+        resp = read_response(qp.proposal.bottle_slug, qp.proposal.id)
+        self.assertEqual(STATUS_APPROVED, resp.status)
+        self.assertEqual("false positive", resp.notes)
+
+    def test_token_allow_writes_no_audit_log(self):
+        qp = self._enqueue(tool=TOOL_EGRESS_TOKEN_ALLOW)
+        supervise_cli.approve(qp, notes="false positive")
+        self.assertEqual([], read_audit_entries("egress", "dev"))
+
+    def test_tui_token_allow_requires_reason(self):
+        qp = self._enqueue(tool=TOOL_EGRESS_TOKEN_ALLOW)
+        with patch.object(supervise_cli, "_prompt", return_value=""):
+            status = supervise_cli._approve_from_tui(None, qp)  # type: ignore[arg-type]
+        self.assertEqual("approve aborted (empty reason)", status)
+
+    def test_tui_token_allow_writes_reason(self):
+        qp = self._enqueue(tool=TOOL_EGRESS_TOKEN_ALLOW)
+        with patch.object(supervise_cli, "_prompt", return_value="legit"):
+            status = supervise_cli._approve_from_tui(None, qp)  # type: ignore[arg-type]
+        self.assertIn("approved egress-token-allow", status)
+        resp = read_response(qp.proposal.bottle_slug, qp.proposal.id)
+        self.assertEqual("legit", resp.notes)
+
+    def test_suffix_for_token_allow_is_txt(self):
+        self.assertEqual(".txt", supervise_cli._suffix_for_tool(TOOL_EGRESS_TOKEN_ALLOW))
 
 
 class TestEditInEditor(unittest.TestCase):
-    def test_runs_editor_returns_edited_content(self) -> None:
+    def test_runs_editor_returns_edited_content(self):
         original_editor = os.environ.get("EDITOR")
         try:
             with tempfile.NamedTemporaryFile(
@@ -171,7 +245,7 @@ class TestEditInEditor(unittest.TestCase):
             else:
                 os.environ["EDITOR"] = original_editor
 
-    def test_returns_none_when_unchanged(self) -> None:
+    def test_returns_none_when_unchanged(self):
         original_editor = os.environ.get("EDITOR")
         try:
             with tempfile.NamedTemporaryFile(
@@ -193,31 +267,5 @@ class TestEditInEditor(unittest.TestCase):
                 os.environ["EDITOR"] = original_editor
 
 
-class TestResolveOrchestratorUrl(unittest.TestCase):
-    """`_resolve_orchestrator_url` starts the backend orchestrator on demand
-    when discovery finds nothing — supervise is often the first thing run."""
-
-    def test_returns_discovered_url_without_starting(self) -> None:
-        with patch.object(
-            supervise_cli, "discover_orchestrator_url",
-            return_value="http://127.0.0.1:8099",
-        ), patch("bot_bottle.backend.get_bottle_backend") as get_backend:
-            url = supervise_cli._resolve_orchestrator_url()
-        self.assertEqual(url, "http://127.0.0.1:8099")
-        get_backend.assert_not_called()  # nothing to start; discovery won
-
-    def test_starts_backend_orchestrator_when_none_running(self) -> None:
-        backend = MagicMock()
-        backend.name = "firecracker"
-        backend.ensure_orchestrator.return_value = "http://10.243.255.1:8099"
-        with patch.object(
-            supervise_cli, "discover_orchestrator_url",
-            side_effect=supervise_cli.OrchestratorClientError("none"),
-        ), patch("bot_bottle.backend.get_bottle_backend", return_value=backend):
-            url = supervise_cli._resolve_orchestrator_url()
-        self.assertEqual(url, "http://10.243.255.1:8099")
-        backend.ensure_orchestrator.assert_called_once_with()
-
-
 if __name__ == "__main__":
     unittest.main()

tests/unit/test_supervise_cli_crash_logging.py

@@ -56,15 +56,6 @@ class _FakeHomeMixin:
 class TestCmdSuperviseErrorPaths(_FakeHomeMixin, unittest.TestCase):
     def setUp(self):
         self._setup_fake_home()
-        # `cmd_supervise` establishes the orchestrator client up front; these
-        # tests exercise the curses / crash-logging paths that run *after*
-        # that, so stub the client. Otherwise the outcome depends on whether a
-        # live orchestrator happens to be reachable (CI has none, so the
-        # up-front connect would error and short-circuit before curses).
-        client_patch = mock.patch.object(
-            supervise_cli, "_client", return_value=mock.MagicMock())
-        client_patch.start()
-        self.addCleanup(client_patch.stop)
 
     def tearDown(self):
         self._teardown_fake_home()

tests/unit/test_supervise_server.py

@@ -631,15 +631,9 @@ class TestHttpEndToEnd(unittest.TestCase):
 
 
 class _FakeResolver:
-    def __init__(
-        self,
-        bottle_id: str | None = None,
-        raises: bool = False,
-        policy: str = "",
-    ) -> None:
+    def __init__(self, bottle_id: str | None = None, raises: bool = False) -> None:
         self._bottle_id = bottle_id
         self._raises = raises
-        self._policy = policy
         self.calls: list[str] = []
 
     def resolve_bottle_id(self, source_ip: str, identity_token: str = "") -> str | None:
@@ -651,15 +645,6 @@ class _FakeResolver:
             raise supervise_server.PolicyResolveError("orchestrator down")
         return self._bottle_id
 
-    def resolve_policy_and_bottle_id(
-        self, source_ip: str, identity_token: str = "",
-    ) -> "tuple[str, str | None, dict[str, str]]":
-        del identity_token
-        self.calls.append(source_ip)
-        if self._raises:
-            raise supervise_server.PolicyResolveError("orchestrator down")
-        return self._policy, self._bottle_id, {}
-
 
 def _handler(resolver: object) -> MCPHandler:
     """A bare MCPHandler wired with a server (carrying the resolver) and a
@@ -697,41 +682,5 @@ class TestAttributedConfig(unittest.TestCase):
             )
 
 
-class TestResolvedRoutesPayload(unittest.TestCase):
-    """`list-egress-routes` answers from the calling bottle's resolved policy in
-    consolidated mode — not the gateway's empty static table. Regression: an
-    empty list led agents to propose replace-all route files that dropped base
-    hosts like api.anthropic.com on approval."""
-
-    def test_returns_resolved_bottle_routes(self) -> None:
-        policy = (
-            "routes:\n"
-            "  - host: api.anthropic.com\n"
-            "  - host: www.google.com\n"
-        )
-        payload = _handler(
-            _FakeResolver(bottle_id="b1", policy=policy)
-        )._resolved_routes_payload()
-        assert payload is not None
-        self.assertFalse(payload["isError"])  # type: ignore[index]
-        data = json.loads(payload["content"][0]["text"])  # type: ignore[index]
-        hosts = {r["host"] for r in data["routes"]}
-        self.assertEqual({"api.anthropic.com", "www.google.com"}, hosts)
-
-    def test_orchestrator_error_fails_closed_to_empty(self) -> None:
-        # resolve_client_context swallows resolver errors → deny-all (empty),
-        # never another bottle's routes.
-        payload = _handler(
-            _FakeResolver(raises=True)
-        )._resolved_routes_payload()
-        assert payload is not None
-        data = json.loads(payload["content"][0]["text"])  # type: ignore[index]
-        self.assertEqual([], data["routes"])
-
-    def test_single_tenant_returns_none(self) -> None:
-        # No resolver → caller falls back to the static introspection endpoint.
-        self.assertIsNone(_handler(None)._resolved_routes_payload())
-
-
 if __name__ == "__main__":
     unittest.main()