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

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

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

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

.coveragerc

@@ -1,10 +1,6 @@
 [run]
 branch = True
 source = .
-# Store paths relative to the project root so .coverage.* files produced on
-# different runners (ubuntu-latest vs self-hosted KVM) can be combined by the
-# coverage job without a [paths] remapping section.
-relative_files = True
 
 [report]
 # Coverage policy: see docs/decisions/0004-coverage-policy.md.

.gitea/workflows/test.yml

@@ -9,12 +9,10 @@
 #   tests/canaries/     — upstream regression canaries; run on a separate
 #                         schedule (see canaries.yml), not here
 #
-# Each test job runs once under coverage and uploads a small .coverage.*
+# Integration tests run once per backend in separate jobs. Each job sets
-# artifact. The `coverage` job combines them — no test reruns, no KVM
+# BOT_BOTTLE_BACKEND explicitly so the test suite uses the right backend.
-# dependency on that job. For main-branch pushes only, the tested rootfs
+# Backends that aren't available on the runner fail the preflight step
-# and matching dropbear are uploaded so `publish-infra` can publish the
+# rather than silently skipping inside the test output.
-# byte-identical artifact that was tested. PRs avoid the ~194 MB rootfs
-# transfer entirely.
 
 name: test
 
@@ -42,6 +40,53 @@ on:
   workflow_dispatch:
 
 jobs:
+  stage-firecracker-inputs:
+    runs-on: [self-hosted, kvm]
+    # Same guard as the other KVM-runner jobs: don't spin the privileged
+    # runner for fork PRs (this only copies a non-secret static binary, but
+    # keep the posture consistent — build-infra/integration/coverage all
+    # depend on it, so gating here gates the whole Firecracker chain).
+    if: >-
+      github.event_name == 'push' ||
+      github.event_name == 'workflow_dispatch' ||
+      (github.event_name == 'pull_request' &&
+       github.event.pull_request.head.repo.full_name == github.repository)
+    steps:
+      - name: Stage the provisioned static dropbear
+        run: |
+          mkdir -p firecracker-inputs
+          cp /var/cache/bot-bottle-fc/dropbear firecracker-inputs/dropbear
+
+      - name: Upload Firecracker build inputs
+        uses: actions/upload-artifact@v3
+        with:
+          name: firecracker-inputs
+          path: firecracker-inputs/
+
+  build-infra:
+    needs: stage-firecracker-inputs
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Download Firecracker build inputs
+        uses: actions/download-artifact@v3
+        with:
+          name: firecracker-inputs
+          path: firecracker-inputs
+
+      - name: Build infra candidate from this checkout
+        env:
+          BOT_BOTTLE_FC_DROPBEAR: ${{ github.workspace }}/firecracker-inputs/dropbear
+        run: python3 -m bot_bottle.backend.firecracker.publish_infra --output infra-candidate
+
+      - name: Upload infra candidate
+        uses: actions/upload-artifact@v3
+        with:
+          name: infra-candidate
+          path: infra-candidate/
+
   unit:
     runs-on: ubuntu-latest
     steps:
@@ -56,17 +101,11 @@ jobs:
       - name: Install dev requirements
         run: python3 -m pip install --break-system-packages -r requirements-dev.txt
 
-      - name: Run unit tests with coverage
+      - name: Run unit tests
-        run: python3 -m coverage run --data-file=.coverage.unit -m unittest discover -t . -s tests/unit -v
+        run: python3 -m coverage run -m unittest discover -t . -s tests/unit -v
 
       - name: Report unit coverage
-        run: python3 -m coverage report --data-file=.coverage.unit -m
+        run: python3 -m coverage report -m
-
-      - name: Upload unit coverage artifact
-        uses: actions/upload-artifact@v3
-        with:
-          name: coverage-unit
-          path: ${{ github.workspace }}/.coverage.unit
 
   integration-docker:
     runs-on: ubuntu-latest
@@ -76,9 +115,6 @@ jobs:
 
       # No actions/setup-python (see the note in the `unit` job); the
       # container's system Python 3.12 runs the stdlib test suite directly.
-      - name: Install coverage
-        run: python3 -m pip install --break-system-packages coverage
-
       - name: Show environment
         run: |
           python3 --version
@@ -88,16 +124,10 @@ jobs:
             echo "docker not on PATH — integration tests will skip"
           fi
 
-      - name: Run integration tests (docker) with coverage
+      - name: Run integration tests (docker)
         env:
           BOT_BOTTLE_BACKEND: docker
-        run: python3 -m coverage run --data-file=.coverage.docker -m unittest discover -t . -s tests/integration -v
+        run: python3 -m unittest discover -t . -s tests/integration -v
-
-      - name: Upload docker coverage artifact
-        uses: actions/upload-artifact@v3
-        with:
-          name: coverage-docker
-          path: ${{ github.workspace }}/.coverage.docker
 
   # Integration tests against the Firecracker backend. Runs on a self-hosted
   # KVM runner (label `kvm`) where /dev/kvm and the TAP/nft pool are available.
@@ -107,16 +137,9 @@ jobs:
   #
   # Runner prerequisites (provision once; see README "Firecracker on Linux"):
   # `firecracker` on PATH, `/dev/kvm` accessible, cached kernel +
-  # static dropbear at /var/cache/bot-bottle-fc/dropbear, and the pool as a
+  # static dropbear, and the pool as a persistent systemd unit.
-  # persistent systemd unit.
-  #
-  # The infra candidate is built here directly (no artifact download) to
-  # eliminate the ~70 s ubuntu-latest upload + ~83 s combined download that
-  # the old build-infra → integration-firecracker + coverage chain incurred.
-  # For main-branch pushes the tested rootfs and matching dropbear are
-  # uploaded so publish-infra can publish the byte-identical artifact; PRs
-  # skip those uploads entirely.
   integration-firecracker:
+    needs: build-infra
     runs-on: [self-hosted, kvm]
     if: >-
       github.event_name == 'push' ||
@@ -136,58 +159,49 @@ jobs:
           # range overlap; it prints the exact `backend setup` fix.
           python3 cli.py backend status --backend=firecracker
 
-      - name: Build infra candidate from this checkout
+      - name: Download the candidate built from this checkout
-        env:
+        uses: actions/download-artifact@v3
-          BOT_BOTTLE_FC_DROPBEAR: /var/cache/bot-bottle-fc/dropbear
+        with:
-        run: python3 -m bot_bottle.backend.firecracker.publish_infra --output infra-candidate
+          name: infra-candidate
+          path: infra-candidate
 
       - name: Replace the persistent infra VM with the candidate
         run: python3 -c 'from bot_bottle.backend.firecracker import infra_vm; infra_vm.stop()'
 
-      # No dev-requirements install: `coverage` is already provided by the
+      # No dev-requirements install: the integration suite runs on stdlib
-      # self-hosted runner's Nix python env, and that env has no `pip`
+      # `unittest` (pylint/pyright are lint.yml's concern, not this job's),
-      # module to install into anyway.
+      # and the self-hosted runner's Nix python env has no `pip` module
-      - name: Run integration tests (firecracker) with coverage
+      # (`python3 -m pip` → "No module named pip"). Nothing to install.
+      - name: Run integration tests (firecracker)
         env:
           BOT_BOTTLE_BACKEND: firecracker
           BOT_BOTTLE_INFRA_ARTIFACT_DIR: ${{ github.workspace }}/infra-candidate
-        run: python3 -m coverage run --data-file=.coverage.firecracker -m unittest discover -t . -s tests/integration -v
+        run: python3 -m unittest discover -t . -s tests/integration -v
 
-      - name: Upload firecracker coverage artifact
+  # Combined unit+integration coverage + the diff-coverage gate (the hard
-        uses: actions/upload-artifact@v3
+  # gate: new/changed lines >= 90%). See docs/decisions/0004-coverage-policy.md.
-        with:
-          name: coverage-firecracker
-          path: ${{ github.workspace }}/.coverage.firecracker
-
-      # Only upload the large rootfs artifact on main-branch pushes;
-      # PRs avoid the ~194 MB transfer. publish-infra only runs on main
-      # and downloads these to publish the byte-identical tested rootfs.
-      - name: Upload tested rootfs (main branch only)
-        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
-        uses: actions/upload-artifact@v3
-        with:
-          name: infra-candidate
-          path: infra-candidate/
-
-      - name: Upload dropbear for publish verification (main branch only)
-        if: github.event_name == 'push' && github.ref == 'refs/heads/main'
-        uses: actions/upload-artifact@v3
-        with:
-          name: firecracker-inputs
-          path: /var/cache/bot-bottle-fc/dropbear
-
-  # Combined coverage gate: aggregates .coverage.* artifacts uploaded by each
-  # test job, then runs the diff-coverage gate (new/changed lines >= 90%).
   #
-  # Runs on ubuntu-latest — no KVM needed, no test reruns. Coverage files use
+  # This runs on a self-hosted KVM runner (label `kvm`), NOT ubuntu-latest,
-  # relative_files = True (.coveragerc) so they combine cleanly across runners.
+  # because the Firecracker backend's subprocess/VM orchestration
+  # (launch/boot/SSH/isolation-probe) is covered by the integration suite,
+  # and that suite needs `/dev/kvm` + the provisioned TAP/nft pool — which a
+  # container-based runner doesn't have. On such a runner the firecracker
+  # integration test skips and its ~230 orchestration lines read as
+  # uncovered, so the gate can't pass there.
   #
-  # Restricted to the same events as integration-firecracker: it depends on
+  # Restricted to the same events as integration-firecracker (same-repo PRs,
-  # that job's coverage artifact and skips for fork PRs alongside it.
+  # push, workflow_dispatch) for the same security reason.
+  #
+  # See #414 for the planned follow-up: artifact-based coverage combination
+  # (run tests once in their respective jobs, combine .coverage files here).
+  #
+  # build-infra creates one candidate from the checkout. This job boots that
+  # same candidate after integration-firecracker has exercised it; the main
+  # push path publishes the identical bytes only after every required job.
   coverage:
-    needs: [unit, integration-docker, integration-firecracker]
+    needs: [build-infra, integration-firecracker]
     timeout-minutes: 15
-    runs-on: ubuntu-latest
+    runs-on: [self-hosted, kvm]
     if: >-
       github.event_name == 'push' ||
       github.event_name == 'workflow_dispatch' ||
@@ -199,29 +213,29 @@ jobs:
         with:
           fetch-depth: 0
 
-      - name: Install coverage
+      - name: Preflight — Firecracker host is ready
-        run: python3 -m pip install --break-system-packages coverage
+        run: |
+          command -v firecracker >/dev/null || {
+            echo "firecracker not on PATH — provision the runner (README: Firecracker on Linux)"; exit 1; }
+          test -e /dev/kvm || { echo "/dev/kvm missing — KVM not available on this runner"; exit 1; }
+          # `backend status` exits non-zero unless the TAP pool is up + no
+          # range overlap; it prints the exact `backend setup` fix.
+          python3 cli.py backend status --backend=firecracker
 
-      - name: Download unit coverage artifact
+      - name: Download the candidate already exercised by integration
         uses: actions/download-artifact@v3
         with:
-          name: coverage-unit
+          name: infra-candidate
-          path: ${{ github.workspace }}
+          path: infra-candidate
-
-      - name: Download docker coverage artifact
-        uses: actions/download-artifact@v3
-        with:
-          name: coverage-docker
-          path: ${{ github.workspace }}
-
-      - name: Download firecracker coverage artifact
-        uses: actions/download-artifact@v3
-        with:
-          name: coverage-firecracker
-          path: ${{ github.workspace }}
 
+      # No dev-requirements install: `coverage` is already provided by the
+      # self-hosted runner's Nix python env, and that env has no `pip`
+      # module to install into anyway. `scripts/coverage.sh` +
+      # `diff_coverage.py` need only `coverage` (not pylint/pyright).
       - name: Combined coverage (unit + integration, incl. firecracker)
-        run: PYTHON=python3 bash scripts/coverage.sh aggregate critical
+        env:
+          BOT_BOTTLE_CI_INFRA_ARTIFACT_DIR: ${{ github.workspace }}/infra-candidate
+        run: PYTHON=python3 bash scripts/coverage.sh critical
 
       - name: Diff-coverage gate (changed lines >= 90%)
         run: |
@@ -229,14 +243,14 @@ jobs:
           python3 scripts/diff_coverage.py --base origin/main --min 90
 
   publish-infra:
-    needs: [unit, integration-docker, integration-firecracker, coverage]
+    needs: [stage-firecracker-inputs, build-infra, unit, integration-docker, integration-firecracker, coverage]
     runs-on: ubuntu-latest
     if: github.event_name == 'push' && github.ref == 'refs/heads/main'
     steps:
       - name: Checkout the tested revision
         uses: actions/checkout@v4
 
-      - name: Download the tested rootfs
+      - name: Download the tested candidate
         uses: actions/download-artifact@v3
         with:
           name: infra-candidate
@@ -244,10 +258,9 @@ jobs:
 
       # publish_infra re-derives the version from the checkout to confirm the
       # bundle matches before uploading, and the version hashes the dropbear
-      # bytes. Download the SAME dropbear integration-firecracker used, or
+      # bytes. Stage the SAME dropbear build-infra used, or the recheck
-      # the recheck computes a "<missing>"-dropbear version and rejects the
+      # computes a "<missing>"-dropbear version and rejects the candidate.
-      # candidate.
+      - name: Download the staged dropbear (matches build-infra's version)
-      - name: Download the staged dropbear (matches build's version)
         uses: actions/download-artifact@v3
         with:
           name: firecracker-inputs

Dockerfile.infra

@@ -1,45 +1,22 @@
-# Firecracker single infra-VM image (PRD 0070 Stage B).
+# Shared infra image: gateway data plane + orchestrator control plane.
 #
-# The per-host infra VM runs the orchestrator control plane, the gateway
+# Used directly by the Docker backend (run as one `bot-bottle-infra`
-# data plane, AND builds agent images (buildah) — all in one microVM (see
+# container, replacing the prior two-container split). The Firecracker
-# backend/firecracker/infra_vm.py). It composes:
+# backend extends this via Dockerfile.infra.fc, adding buildah/crun/
-#   * FROM the gateway image (mitmproxy / git / gitleaks / supervise + the
+# netavark for in-VM agent-image building.
-#     flat daemon modules) — now trixie-based, so buildah 1.39 is available;
+#
-#   * `COPY --from` the orchestrator image's content (the single definition
+# Dockerfile.orchestrator is the single definition of the orchestrator
-#     of the control-plane payload — see Dockerfile.orchestrator), so this
+# content (the lean `bot_bottle` package on python:3.12-slim). Both this
-#     VM and the docker backend share one orchestrator definition; and
+# image and Dockerfile.infra.fc pull it in via `COPY --from`.
-#   * 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 orchestrator content, from its single definition. The gateway image
-# The Firecracker backend builds users' agent Dockerfiles *inside this VM*
+# already has the flat daemon modules under /app; this adds the full
-# with buildah (rootless, daemonless) instead of on the host — no host
+# `bot_bottle` package so `python3 -m bot_bottle.orchestrator` resolves —
-# Docker daemon, no root-equivalent `docker` group. `crun` is the OCI
+# used by gateway_init when BOT_BOTTLE_GATEWAY_DAEMONS includes `orchestrator`.
-# 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.infra.fc

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

bot_bottle/backend/consolidated_util.py

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

bot_bottle/backend/docker/consolidated_launch.py

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

bot_bottle/backend/firecracker/consolidated_launch.py

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

bot_bottle/backend/firecracker/infra_artifact.py

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

bot_bottle/backend/firecracker/infra_vm.py

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

bot_bottle/backend/macos_container/bottle.py

@@ -68,14 +68,9 @@ class MacosContainerBottle(Bottle):
         # 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.
+        # 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
-        # `container exec --env` does NOT override a run-time value — it
+        # supersedes the token-less one baked in at launch.
-        # appends, leaving duplicate entries in the agent's `environ` whose
-        # resolution is runtime-specific (Node last-wins, Rust first-wins). So
-        # nothing here may rely on superseding: the proxy vars are supplied
-        # *only* at exec time and are deliberately absent from the run-time
-        # env. See `launch._agent_env_entries`.
         self._exec_env = dict(exec_env or {})
         self._closed = False
 

bot_bottle/backend/macos_container/consolidated_launch.py

@@ -37,8 +37,7 @@ from dataclasses import dataclass
 from ...egress import EgressPlan
 from ...git_gate import GitGatePlan
 from ...orchestrator.client import OrchestratorClient
-from ...orchestrator.registration import registration_inputs
+from ..consolidated_util import provision_bottle, teardown_consolidated as _teardown_util
-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
@@ -103,17 +102,10 @@ def register_agent(
     container — it is the attribution key the gateway resolves policy by.
     Raises on failure; the caller tears down."""
     client = OrchestratorClient(endpoint.orchestrator_url)
-    inputs = registration_inputs(egress_plan)
+    reg = provision_bottle(
-    reg = client.register_bottle(
+        client, source_ip, egress_plan, git_gate_plan, AppleGatewayTransport(),
-        source_ip, image_ref=image_ref, policy=inputs.policy,
+        image_ref=image_ref, tokens=tokens,
-        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,
@@ -128,8 +120,7 @@ def teardown_consolidated(bottle_id: str, *, orchestrator_url: str) -> None:
     """Deregister the bottle and remove its git-gate state from the gateway.
     Both steps are idempotent so this is safe from a cleanup trap. Does NOT
     stop the gateway — it's a persistent per-host singleton."""
-    OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
+    _teardown_util(bottle_id, AppleGatewayTransport(), orchestrator_url=orchestrator_url)
-    deprovision_git_gate(AppleGatewayTransport(), bottle_id)
 
 
 __all__ = [

bot_bottle/backend/macos_container/enumerate.py

@@ -8,11 +8,7 @@ from ...bottle_state import read_metadata
 from .. import ActiveAgent
 from .infra import INFRA_NAME
 
-# The name every agent container carries: `bot-bottle-<slug>`. Exported
+_PREFIX = "bot-bottle-"
-# because callers that act on a running bottle (gateway-host rewrites,
-# registry reconciliation) have to map an enumerated slug back to a
-# container name.
-CONTAINER_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.
@@ -30,9 +26,9 @@ def enumerate_active() -> list[ActiveAgent]:
         return []
     out: list[ActiveAgent] = []
     for name in sorted(line.strip() for line in result.stdout.splitlines()):
-        if not name.startswith(CONTAINER_NAME_PREFIX) or name in _INFRA_NAMES:
+        if not name.startswith(_PREFIX) or name in _INFRA_NAMES:
             continue
-        slug = name[len(CONTAINER_NAME_PREFIX):]
+        slug = name[len(_PREFIX):]
         metadata = read_metadata(slug)
         out.append(ActiveAgent(
             backend_name="macos-container",

bot_bottle/backend/macos_container/gateway_hosts.py

@@ -1,96 +0,0 @@
-"""Stable gateway name for macOS agents, via each bottle's `/etc/hosts`.
-
-The shared gateway's address is assigned by vmnet's DHCP and changes whenever
-the infra container is recreated — a source-hash bump, an image upgrade, a
-crash. Every agent-facing URL (egress proxy, git-http, supervise) embeds that
-address, and the proxy URL reaches the agent as **process environment** at
-`container exec` time. A running process's `environ` cannot be rewritten from
-outside, so a moved gateway used to strand every running bottle permanently:
-not degraded, unreachable, until the bottle was relaunched and its session
-thrown away.
-
-So the agent never learns the address. It is given a stable *name*
-(`GATEWAY_HOSTNAME`) in every URL, resolved through its own `/etc/hosts`.
-Unlike `environ`, that is a file — it can be rewritten inside a container that
-is already running, so a gateway that comes back at a new address is picked up
-by live bottles instead of orphaning them.
-
-Apple Container 1.0 offers no container-name DNS on a user network (the only
-nameserver an agent sees is vmnet's, which does not know container names) and
-`container run` has no `--add-host`, so the entry is written by exec after the
-container starts.
-
-Writing it needs root, and the agent runs as `node`: the agent therefore
-cannot repoint its own gateway name, while the host (which drives `container
-exec --user root`) can. That asymmetry is deliberate — keep it.
-"""
-
-from __future__ import annotations
-
-from ...log import warn
-from . import util as container_mod
-from .enumerate import CONTAINER_NAME_PREFIX, enumerate_active
-
-# The name every agent-facing gateway URL uses. Must not collide with a real
-# DNS name the agent might resolve; it is bottle-local by construction.
-GATEWAY_HOSTNAME = "bot-bottle-gateway"
-
-# Marker so the rewrite is idempotent and only ever touches our own line —
-# the rest of /etc/hosts (localhost, the container's own name) is preserved.
-_MARKER = "# bot-bottle gateway"
-
-
-def _rewrite_script(gateway_ip: str) -> str:
-    """A shell one-liner that replaces our managed line in `/etc/hosts`.
-
-    Rewrites in place via a temp file + `cat` rather than `mv`, so the file
-    keeps its original inode, ownership, and mode — a bind-mounted or
-    pre-created `/etc/hosts` must not be replaced by a root-owned 0644 copy
-    that the runtime then refuses to update.
-    """
-    return (
-        "set -e; "
-        f"grep -v '{_MARKER}' /etc/hosts > /tmp/.bb-hosts || true; "
-        f"printf '%s %s %s\\n' '{gateway_ip}' '{GATEWAY_HOSTNAME}' "
-        f"'{_MARKER}' >> /tmp/.bb-hosts; "
-        "cat /tmp/.bb-hosts > /etc/hosts; "
-        "rm -f /tmp/.bb-hosts"
-    )
-
-
-def set_gateway_host(container_name: str, gateway_ip: str) -> None:
-    """Point `GATEWAY_HOSTNAME` at `gateway_ip` inside one running container.
-
-    Must run before the agent is exec'd: the agent's proxy URL names the
-    gateway, so the entry has to exist for its first connection. Idempotent —
-    re-running with the same address is a no-op in effect.
-    """
-    container_mod.exec_container_as_root(
-        container_name, ["sh", "-c", _rewrite_script(gateway_ip)],
-    )
-
-
-def refresh_gateway_host(gateway_ip: str) -> list[str]:
-    """Re-point every running bottle at the current gateway address.
-
-    Called once the shared gateway is known to be up, so a bottle stranded by
-    an earlier gateway restart re-attaches instead of needing a relaunch.
-    Returns the containers updated.
-
-    Best-effort per bottle: one container that refuses the write (already
-    exiting, say) must not stop the others from being repaired, and must not
-    fail the launch that triggered the sweep.
-    """
-    updated: list[str] = []
-    for agent in enumerate_active():
-        name = f"{CONTAINER_NAME_PREFIX}{agent.slug}"
-        try:
-            set_gateway_host(name, gateway_ip)
-            updated.append(name)
-        # One bad bottle must not stop the sweep, so this is deliberately broad.
-        except Exception as e:  # noqa: BLE001  # pylint: disable=broad-exception-caught
-            warn(f"could not re-point {name} at the gateway: {e}")
-    return updated
-
-
-__all__ = ["GATEWAY_HOSTNAME", "set_gateway_host", "refresh_gateway_host"]

bot_bottle/backend/macos_container/launch.py

@@ -59,11 +59,6 @@ from ..docker.egress import EGRESS_PORT
 from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
 from . import util as container_mod
 from .bottle import MacosContainerBottle
-from .gateway_hosts import (
-    GATEWAY_HOSTNAME,
-    refresh_gateway_host,
-    set_gateway_host,
-)
 from .bottle_plan import MacosContainerBottlePlan
 from .consolidated_launch import (
     GatewayEndpoint,
@@ -105,11 +100,6 @@ def launch(
         # 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()
-        # The gateway's address may have changed since these bottles launched
-        # (any infra recreate re-runs DHCP). They name the gateway rather than
-        # address it, so re-pointing /etc/hosts re-attaches them in place
-        # instead of leaving them stranded until relaunch.
-        refresh_gateway_host(endpoint.gateway_ip)
 
         # Step 2: mint this bottle's deploy keys, then point it at the SHARED
         # gateway's CA + git-http/supervise ports.
@@ -127,9 +117,6 @@ def launch(
         # 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.
-        # Resolve the gateway name before anything execs: every agent-facing
-        # URL uses it, so the entry must exist for the first connection.
-        set_gateway_host(plan.container_name, endpoint.gateway_ip)
         source_ip = container_mod.wait_container_ipv4_on_network(
             plan.container_name, endpoint.network,
         )
@@ -244,20 +231,13 @@ def _stamp_agent_urls(
 ) -> 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 name).
+    gateway address)."""
-
-    Addressed by `GATEWAY_HOSTNAME`, never by IP: these URLs are baked into
-    the agent's gitconfig and MCP config at provision time, so an address here
-    would strand the bottle the moment the gateway moved. The name is resolved
-    per connection through `/etc/hosts`, which stays rewritable while the
-    bottle runs."""
-    del endpoint  # addressed by name; the address reaches the bottle via /etc/hosts
     git_gate_url = (
-        f"http://{GATEWAY_HOSTNAME}:{_GIT_HTTP_PORT}"
+        f"http://{endpoint.gateway_ip}:{_GIT_HTTP_PORT}"
         if plan.git_gate_plan.upstreams else ""
     )
     supervise_url = (
-        f"http://{GATEWAY_HOSTNAME}:{SUPERVISE_PORT}/"
+        f"http://{endpoint.gateway_ip}:{SUPERVISE_PORT}/"
         if plan.supervise_plan is not None else ""
     )
     return dataclasses.replace(
@@ -267,43 +247,30 @@ def _stamp_agent_urls(
     )
 
 
-def _proxy_url(identity_token: str = "") -> str:
+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).
+    upstream. Without a valid pair `/resolve` denies the request (#366)."""
-
-    Names the gateway rather than addressing it: this URL reaches the agent as
-    process environment, which cannot be rewritten once the agent is running,
-    so an address baked here is unfixable if the gateway moves."""
     cred = f"bottle:{identity_token}@" if identity_token else ""
-    return f"http://{cred}{GATEWAY_HOSTNAME}:{EGRESS_PORT}"
+    return f"http://{cred}{gateway_ip}:{EGRESS_PORT}"
 
 
-def _no_proxy() -> str:
+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 name. Deliberately
+    # egress proxy — the agent reaches them directly by its address.
-    # address-free: NO_PROXY is baked into the run-time env and is therefore
+    return f"localhost,127.0.0.1,{gateway_ip}"
-    # just as unfixable as the proxy URL if the gateway moves.
-    return f"localhost,127.0.0.1,{GATEWAY_HOSTNAME}"
 
 
 def _identity_proxy_env(
     endpoint: GatewayEndpoint, identity_token: str,
 ) -> dict[str, str]:
-    """The token-bearing proxy env applied at `container exec` — the only way
+    """The token-bearing proxy env applied at `container exec`. It supersedes
-    to get the token in, since it does not exist until after the container
+    the token-less run-time value (exec `--env` wins), which is the only way to
-    runs (registration keys on the DHCP-assigned address).
+    get the token in: it does not exist until after the container runs."""
-
-    This is the *sole* source of `*_PROXY` for the agent. It deliberately does
-    not rely on overriding a run-time value: `container exec --env` appends
-    rather than replaces, so a run-time `HTTPS_PROXY` would survive alongside
-    this one and first-wins runtimes would read the wrong entry. See
-    `_agent_env_entries`."""
     if not identity_token:
         return {}
-    del endpoint  # the gateway is named, not addressed
+    url = _proxy_url(endpoint.gateway_ip, identity_token)
-    url = _proxy_url(identity_token)
     return {
         "HTTPS_PROXY": url, "HTTP_PROXY": url,
         "https_proxy": url, "http_proxy": url,
@@ -350,23 +317,16 @@ def _agent_run_argv(
 def _agent_env_entries(
     plan: MacosContainerBottlePlan, endpoint: GatewayEndpoint,
 ) -> tuple[str, ...]:
-    # No `*_PROXY` here on purpose. The token-bearing URL is applied at
+    # Token-less at run time — the token does not exist yet (see
-    # `container exec` (`_identity_proxy_env`), and Apple's `container exec
+    # `_identity_proxy_env`). Anything egressing before the exec-time override
-    # --env` **appends** to the run-time environment rather than replacing it:
+    # is denied by `/resolve`, which is the safe direction.
-    # setting a token-less value here leaves two `HTTPS_PROXY` entries in the
+    proxy_url = _proxy_url(endpoint.gateway_ip)
-    # agent's `environ`, token-less first. Which one a runtime reads is then
+    no_proxy = _no_proxy(endpoint.gateway_ip)
-    # pure luck — Node takes the last (and worked), Rust's `std::env::var`
-    # takes the first, so Codex proxied without its identity token and
-    # `/resolve` fail-closed on every request.
-    #
-    # A token-less proxy URL has no legitimate consumer anyway: the init
-    # process is `sleep` and everything that egresses arrives via exec. Its
-    # only value was a tidy 403 for unattributed callers, which is not worth
-    # silently dropping attribution for. Without it a process that egresses
-    # before the exec-time env still fails closed — the agent network is
-    # host-only, so there is no route off it except the gateway.
-    no_proxy = _no_proxy()
     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}",

bot_bottle/backend/macos_container/util.py

@@ -360,21 +360,6 @@ def exec_container(name: str, argv: list[str]) -> None:
         )
 
 
-def exec_container_as_root(name: str, argv: list[str]) -> None:
-    """`exec_container`, but as uid 0 inside the container.
-
-    For host-driven maintenance the agent itself must not be able to perform —
-    rewriting `/etc/hosts` to point the gateway name at an address. The agent
-    runs as `node`, so it cannot repoint its own gateway; the host can.
-    """
-    result = _run_container_op([_CONTAINER, "exec", "--user", "root", name, *argv])
-    if result.returncode != 0:
-        die(
-            f"container exec (root) in {name} failed: "
-            f"{(result.stderr or '').strip() or '<no stderr>'}"
-        )
-
-
 def _run_container_op(cmd: list[str]) -> subprocess.CompletedProcess[str]:
     result = subprocess.run(
         cmd,

bot_bottle/gateway_init.py

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

bot_bottle/orchestrator/lifecycle.py

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

docs/prds/prd-new-ci-artifact-coverage.md

@@ -1,110 +0,0 @@
-# PRD prd-new: CI artifact-based coverage and local Firecracker candidate flow
-
-- **Status:** Active
-- **Author:** Claude
-- **Created:** 2026-07-21
-- **Issue:** #446
-
-## Summary
-
-Restructure the CI test pipeline to run each test suite exactly once, upload
-small `.coverage.*` artifacts, and combine them in a lightweight aggregation
-job. Move the infra build onto the KVM runner so the ~194 MB rootfs never
-crosses the network for PRs. On main-branch pushes, publish the byte-identical
-rootfs that was tested.
-
-## Motivation
-
-The prior pipeline had two redundant costs:
-
-1. **Duplicate artifact transfers.** `build-infra` (ubuntu-latest) built and
-   uploaded the ~194 MB rootfs; `integration-firecracker` downloaded it; the
-   `coverage` job downloaded it a second time. Combined download overhead: ~83
-   seconds per run, plus the ~70-second upload.
-
-2. **Duplicate test execution.** `integration-firecracker` ran the Firecracker
-   integration suite; `coverage` ran the entire unit + integration suite again
-   on the same KVM runner to collect coverage data. Every line of Firecracker
-   code was tested twice per CI run.
-
-## Goals
-
-- Each test suite (unit, integration-docker, integration-firecracker) executes
-  exactly once per workflow run.
-- PRs incur no large artifact transfers — the rootfs stays on the KVM runner.
-- Main-branch pushes publish a byte-for-byte identical rootfs to the one that
-  passed the integration tests.
-- Concurrent workflow runs cannot cross-publish candidates (naturally enforced
-  by Gitea Actions' per-run artifact scoping).
-- Failed or cancelled runs block publication (enforced by the `needs:` chain on
-  `publish-infra`).
-
-## Non-goals
-
-- Changing test semantics or the coverage policy (ADR 0004).
-- Removing the KVM runner guard on `integration-firecracker` and `coverage`.
-- Changing how `publish_infra.py` builds or uploads the rootfs.
-
-## Design
-
-### Job graph
-
-```
-unit ──────────────────────────────────┐
-integration-docker ────────────────────┤──► coverage ──► publish-infra (main only)
-integration-firecracker (KVM) ─────────┘
-```
-
-### `unit`
-
-Unchanged except: `coverage run` writes `--data-file=.coverage.unit`; the file
-is uploaded as the `coverage-unit` artifact.
-
-### `integration-docker`
-
-Adds a `coverage` install step. `coverage run` writes `--data-file=.coverage.docker`;
-the file is uploaded as `coverage-docker`.
-
-### `integration-firecracker` (KVM runner)
-
-Replaces the old `stage-firecracker-inputs` → `build-infra` → download chain:
-
-1. Builds the infra candidate locally with
-   `BOT_BOTTLE_FC_DROPBEAR=/var/cache/bot-bottle-fc/dropbear`.
-2. Boots the candidate and runs integration tests with coverage, writing
-   `.coverage.firecracker`.
-3. Uploads the small `coverage-firecracker` artifact unconditionally.
-4. On main-branch pushes only, uploads the rootfs as `infra-candidate` and the
-   dropbear as `firecracker-inputs` so `publish-infra` can verify and publish
-   the byte-identical artifact.
-
-### `coverage`
-
-Moves from a KVM runner to `ubuntu-latest`. No tests are re-executed:
-
-1. Downloads `coverage-unit`, `coverage-docker`, and `coverage-firecracker`.
-2. Runs `scripts/coverage.sh aggregate critical`, which calls
-   `coverage combine` then `coverage report`.
-3. Runs the diff-coverage gate (`scripts/diff_coverage.py`).
-
-Coverage files use `relative_files = True` (`.coveragerc`) so they combine
-cleanly across runners with different absolute workspace paths.
-
-### `publish-infra`
-
-Depends on all four predecessor jobs (unchanged gate). Downloads `infra-candidate`
-and `firecracker-inputs` that were uploaded by `integration-firecracker` on
-main — the same byte sequence that passed the integration tests.
-
-### Eliminated jobs
-
-- `stage-firecracker-inputs`: existed only to copy the dropbear to ubuntu-latest
-  for `build-infra`. No longer needed.
-- `build-infra`: the infra candidate is now built on the KVM runner in
-  `integration-firecracker`.
-
-### Script changes
-
-`scripts/coverage.sh` gains an `aggregate` mode (`coverage.sh aggregate [critical]`)
-that combines pre-existing `.coverage.*` files instead of re-running tests.
-The existing run mode (`coverage.sh [critical]`) is preserved for local dev.

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

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

scripts/coverage.sh

@@ -1,19 +1,15 @@
 #!/usr/bin/env bash
 # Combined unit + integration coverage (see docs/decisions/0004-coverage-policy.md).
 #
-# Two modes:
+# Runs the unit suite, then appends the integration suite (which skips
+# cleanly when Docker / the backend CLIs are unavailable), and prints one
+# combined report. The integration suite is what scores the subprocess /
+# backend orchestration modules, so the number here is the policy's
+# yardstick — not the unit-only badge.
 #
-#   scripts/coverage.sh [critical]
+# Usage:
-#     Run mode (default, for local dev): executes the unit suite then the
+#   scripts/coverage.sh            # combined report
-#     integration suite under coverage and prints a combined report.
+#   scripts/coverage.sh critical   # also report just the critical modules
-#
-#   scripts/coverage.sh aggregate [critical]
-#     Aggregate mode (used by CI): combines pre-existing .coverage.* files
-#     produced by individual test jobs and prints a combined report. No tests
-#     are re-executed; no KVM or Docker dependency.
-#
-# Pass "critical" as the last argument in either mode to also report just the
-# critical modules (ADR 0004 target: 90%).
 set -euo pipefail
 
 cd "$(dirname "$0")/.."
@@ -25,22 +21,6 @@ PY="${PYTHON:-python3}"
 # README "core coverage" badge can't drift; comma-join it for --include.
 CRITICAL=$(grep -vE '^[[:space:]]*(#|$)' scripts/critical-modules.txt | paste -sd, -)
 
-if [ "${1:-}" = "aggregate" ]; then
-    # Aggregate mode: combine .coverage.* artifacts already in the workspace.
-    echo "== combining coverage artifacts ==" >&2
-    "$PY" -m coverage combine
-
-    echo "== combined report ==" >&2
-    "$PY" -m coverage report -m
-
-    if [ "${2:-}" = "critical" ]; then
-        echo "== critical modules (ADR 0004 target: 90%) ==" >&2
-        "$PY" -m coverage report --include="$CRITICAL"
-    fi
-    exit 0
-fi
-
-# Run mode (default): execute both suites under coverage in this process.
 rm -f .coverage
 
 echo "== unit ==" >&2

tests/integration/test_orchestrator_docker_control_plane_auth.py

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

tests/unit/test_consolidated_launch.py

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

tests/unit/test_infra_artifact.py

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

tests/unit/test_macos_consolidated_launch.py

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

tests/unit/test_macos_container_launch_wiring.py

@@ -17,10 +17,10 @@ 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.gateway_hosts import GATEWAY_HOSTNAME
 from bot_bottle.backend.macos_container.launch import (
     _agent_run_argv,
     _identity_proxy_env,
+    _proxy_url,
 )
 from bot_bottle.manifest import ManifestIndex
 
@@ -104,38 +104,19 @@ class TestAgentRunArgv(unittest.TestCase):
         read back after start."""
         self.assertNotIn("--ip", self.argv)
 
-    def test_run_time_env_sets_no_proxy_vars_at_all(self) -> None:
+    def test_run_time_proxy_carries_no_identity_token(self) -> None:
-        """Regression: the proxy vars must exist *only* in the exec-time env.
+        """The token is minted by registration, which happens after this run —
-
+        so it cannot be here. `/resolve` denies the token-less pair (#366),
-        `container exec --env` appends rather than replaces, so a token-less
+        which is the safe direction; the real value arrives at exec time."""
-        `HTTPS_PROXY` here would survive next to the token-bearing one and
+        joined = " ".join(self.argv)
-        leave two entries in the agent's `environ`. Resolution is then
+        self.assertIn(f"HTTP_PROXY={_proxy_url('192.168.128.3')}", joined)
-        runtime-specific — Node reads the last, Rust's `std::env::var` reads
+        self.assertNotIn("bottle:", joined)
-        the first — so Codex proxied without its identity token and every
-        request fail-closed at `/resolve`.
-        """
-        for entry in self.argv:
-            self.assertFalse(
-                entry.upper().startswith(("HTTP_PROXY=", "HTTPS_PROXY=")),
-                f"run-time env must not set a proxy var, got {entry!r}",
-            )
-
-    def test_run_time_env_carries_no_identity_token(self) -> None:
-        """The token is minted by registration, which happens after this run,
-        so it cannot be here under any name."""
-        self.assertNotIn("bottle:", " ".join(self.argv))
 
     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(GATEWAY_HOSTNAME, entry)
+        self.assertIn("192.168.128.3", entry)
-
-    def test_no_proxy_names_the_gateway_and_never_addresses_it(self) -> None:
-        """NO_PROXY is baked into the run-time env, so an address here is as
-        unfixable as the proxy URL if the gateway moves."""
-        entry = next(a for a in self.argv if a.startswith("NO_PROXY="))
-        self.assertNotIn("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
@@ -153,7 +134,7 @@ class TestIdentityTokenDelivery(unittest.TestCase):
     def test_exec_env_carries_the_token_as_proxy_credentials(self) -> None:
         env = _identity_proxy_env(_endpoint(), "s3cret")
         self.assertEqual(
-            f"http://bottle:s3cret@{GATEWAY_HOSTNAME}:9099", env["HTTP_PROXY"],
+            "http://bottle:s3cret@192.168.128.3:9099", env["HTTP_PROXY"],
         )
         self.assertEqual(env["HTTP_PROXY"], env["https_proxy"])
 
@@ -221,7 +202,7 @@ class TestPlanIdentityToken(unittest.TestCase):
         self.assertIn("HTTP_PROXY", argv)
         self.assertNotIn("s3cret", " ".join(argv))
         self.assertEqual(
-            f"http://bottle:s3cret@{GATEWAY_HOSTNAME}:9099", kwargs["env"]["HTTP_PROXY"],
+            "http://bottle:s3cret@192.168.128.3:9099", kwargs["env"]["HTTP_PROXY"],
         )
 
 

tests/unit/test_macos_container_util.py

@@ -272,30 +272,6 @@ resolver #2
                 ),
             )
 
-    def test_exec_container_as_root_selects_root_user(self):
-        completed = util.subprocess.CompletedProcess(
-            args=[], returncode=0, stdout="", stderr="",
-        )
-        with patch.object(util, "_run_container_op", return_value=completed) as run:
-            util.exec_container_as_root("bot-bottle-demo", ["true"])
-
-        run.assert_called_once_with([
-            "container", "exec", "--user", "root", "bot-bottle-demo", "true",
-        ])
-
-    def test_exec_container_as_root_reports_failure(self):
-        failed = util.subprocess.CompletedProcess(
-            args=[], returncode=1, stdout="", stderr="permission denied\n",
-        )
-        with patch.object(util, "_run_container_op", return_value=failed), \
-             patch.object(util, "die", side_effect=SystemExit("die")) as die:
-            with self.assertRaises(SystemExit):
-                util.exec_container_as_root("bot-bottle-demo", ["true"])
-
-        die.assert_called_once_with(
-            "container exec (root) in bot-bottle-demo failed: permission denied",
-        )
-
 
 def _completed(stdout: str, returncode: int = 0):
     return util.subprocess.CompletedProcess(args=[], returncode=returncode, stdout=stdout, stderr="")

tests/unit/test_macos_gateway_hosts.py

@@ -1,140 +0,0 @@
-"""Unit: stable gateway name via each bottle's /etc/hosts (issue #443).
-
-The gateway's address moves whenever the infra container is recreated. Agents
-name it instead of addressing it, and the name resolves through `/etc/hosts` —
-a file, so it stays rewritable while the bottle runs, unlike the `environ` the
-proxy URL is delivered in.
-"""
-
-from __future__ import annotations
-
-import unittest
-from types import SimpleNamespace
-from unittest.mock import patch
-
-from bot_bottle.backend.macos_container.gateway_hosts import (
-    GATEWAY_HOSTNAME,
-    refresh_gateway_host,
-    set_gateway_host,
-)
-
-_MOD = "bot_bottle.backend.macos_container.gateway_hosts"
-
-
-class TestSetGatewayHost(unittest.TestCase):
-    def _script(self, exec_root: object) -> str:
-        argv = exec_root.call_args.args[1]  # type: ignore[attr-defined]
-        self.assertEqual(["sh", "-c"], argv[:2])
-        return argv[2]
-
-    def test_writes_the_address_against_the_stable_name(self) -> None:
-        with patch(f"{_MOD}.container_mod.exec_container_as_root") as ex:
-            set_gateway_host("bot-bottle-demo", "192.168.128.19")
-        self.assertEqual("bot-bottle-demo", ex.call_args.args[0])
-        script = self._script(ex)
-        self.assertIn("192.168.128.19", script)
-        self.assertIn(GATEWAY_HOSTNAME, script)
-
-    def test_runs_as_root_so_the_agent_cannot_repoint_itself(self) -> None:
-        """The agent runs as `node`. If it could rewrite /etc/hosts it could
-        aim its own gateway name elsewhere, so the write must go through the
-        root-only helper."""
-        with patch(f"{_MOD}.container_mod.exec_container_as_root") as ex:
-            set_gateway_host("bot-bottle-demo", "10.0.0.1")
-        ex.assert_called_once()
-
-    def test_is_idempotent_by_removing_its_own_line_first(self) -> None:
-        """Re-pointing must replace the managed entry, not append a second one
-        — two entries for the same name would resolve by luck of ordering."""
-        with patch(f"{_MOD}.container_mod.exec_container_as_root") as ex:
-            set_gateway_host("bot-bottle-demo", "10.0.0.1")
-        self.assertIn("grep -v", self._script(ex))
-
-    def test_preserves_the_rest_of_the_hosts_file(self) -> None:
-        """localhost and the container's own name must survive the rewrite."""
-        with patch(f"{_MOD}.container_mod.exec_container_as_root") as ex:
-            set_gateway_host("bot-bottle-demo", "10.0.0.1")
-        script = self._script(ex)
-        # Filter-and-append, never a truncating write of just our line.
-        self.assertIn("/etc/hosts >", script)
-        self.assertIn(">> /tmp/.bb-hosts", script)
-
-    def test_keeps_the_original_inode(self) -> None:
-        """`cat >` rather than `mv`: a pre-created /etc/hosts must keep its
-        ownership and mode, not be replaced by a root-owned copy."""
-        script = None
-        with patch(f"{_MOD}.container_mod.exec_container_as_root") as ex:
-            set_gateway_host("bot-bottle-demo", "10.0.0.1")
-            script = self._script(ex)
-        self.assertIn("cat /tmp/.bb-hosts > /etc/hosts", script)
-        self.assertNotIn("mv ", script)
-
-
-class TestRefreshGatewayHost(unittest.TestCase):
-    """The re-attach sweep: bottles stranded by an earlier gateway restart get
-    re-pointed in place instead of needing a relaunch."""
-
-    def _agents(self, *slugs: str) -> list[SimpleNamespace]:
-        return [SimpleNamespace(slug=s) for s in slugs]
-
-    def test_repoints_every_running_bottle(self) -> None:
-        with patch(f"{_MOD}.enumerate_active", return_value=self._agents("a", "b")), \
-                patch(f"{_MOD}.set_gateway_host") as setter:
-            updated = refresh_gateway_host("192.168.128.19")
-        self.assertEqual(["bot-bottle-a", "bot-bottle-b"], updated)
-        self.assertEqual(
-            [("bot-bottle-a", "192.168.128.19"), ("bot-bottle-b", "192.168.128.19")],
-            [c.args for c in setter.call_args_list],
-        )
-
-    def test_one_failing_bottle_does_not_stop_the_sweep(self) -> None:
-        """A container that is already exiting must not block the repair of
-        its neighbours, nor fail the launch that triggered the sweep."""
-        def _flaky(name: str, _ip: str) -> None:
-            if name == "bot-bottle-a":
-                raise RuntimeError("container is exiting")
-
-        with patch(f"{_MOD}.enumerate_active", return_value=self._agents("a", "b")), \
-                patch(f"{_MOD}.set_gateway_host", side_effect=_flaky), \
-                patch(f"{_MOD}.warn") as warn:
-            updated = refresh_gateway_host("10.0.0.1")
-        self.assertEqual(["bot-bottle-b"], updated)
-        warn.assert_called_once()
-
-    def test_no_running_bottles_is_a_clean_no_op(self) -> None:
-        with patch(f"{_MOD}.enumerate_active", return_value=[]), \
-                patch(f"{_MOD}.set_gateway_host") as setter:
-            self.assertEqual([], refresh_gateway_host("10.0.0.1"))
-        setter.assert_not_called()
-
-
-
-class TestLaunchWiring(unittest.TestCase):
-    """Ordering matters: the name must resolve before anything execs, and the
-    stranded-bottle sweep must run once the gateway is known to be up."""
-
-    def test_launch_sets_the_host_entry_before_reading_the_source_ip(self) -> None:
-        """The agent's every URL names the gateway, so the entry has to exist
-        before the first connection — which means before the agent execs."""
-        import inspect
-
-        from bot_bottle.backend.macos_container import launch
-
-        src = inspect.getsource(launch)
-        set_at = src.index("set_gateway_host(plan.container_name")
-        exec_at = src.index("wait_container_ipv4_on_network")
-        self.assertLess(set_at, exec_at)
-
-    def test_launch_refreshes_stranded_bottles_after_ensure_gateway(self) -> None:
-        import inspect
-
-        from bot_bottle.backend.macos_container import launch
-
-        src = inspect.getsource(launch)
-        ensure_at = src.index("endpoint = ensure_gateway()")
-        refresh_at = src.index("refresh_gateway_host(endpoint.gateway_ip)")
-        self.assertLess(ensure_at, refresh_at)
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_orchestrator_lifecycle.py

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