fix(ci): use absolute github.workspace paths for coverage artifact upload/download

The delphi-ci runner resolves relative paths in upload-artifact and
download-artifact from a different CWD than run: shell steps, so
'.coverage.unit' etc. were never found. Using ${{ github.workspace }}
gives an absolute path that does not depend on the JS action's CWD.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

.coveragerc

@@ -1,6 +1,10 @@
 [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

@@ -9,10 +9,12 @@
 #   tests/canaries/     — upstream regression canaries; run on a separate
 #                         schedule (see canaries.yml), not here
 #
-# Integration tests run once per backend in separate jobs. Each job sets
-# BOT_BOTTLE_BACKEND explicitly so the test suite uses the right backend.
-# Backends that aren't available on the runner fail the preflight step
-# rather than silently skipping inside the test output.
+# Each test job runs once under coverage and uploads a small .coverage.*
+# artifact. The `coverage` job combines them — no test reruns, no KVM
+# dependency on that job. For main-branch pushes only, the tested rootfs
+# and matching dropbear are uploaded so `publish-infra` can publish the
+# byte-identical artifact that was tested. PRs avoid the ~194 MB rootfs
+# transfer entirely.
 
 name: test
 
@@ -40,53 +42,6 @@ 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:
@@ -101,11 +56,17 @@ jobs:
       - name: Install dev requirements
         run: python3 -m pip install --break-system-packages -r requirements-dev.txt
 
-      - name: Run unit tests
-        run: python3 -m coverage run -m unittest discover -t . -s tests/unit -v
+      - name: Run unit tests with coverage
+        run: python3 -m coverage run --data-file=.coverage.unit -m unittest discover -t . -s tests/unit -v
 
       - name: Report unit coverage
-        run: python3 -m coverage report -m
+        run: python3 -m coverage report --data-file=.coverage.unit -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
@@ -115,6 +76,9 @@ 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
@@ -124,10 +88,16 @@ jobs:
             echo "docker not on PATH — integration tests will skip"
           fi
 
-      - name: Run integration tests (docker)
+      - name: Run integration tests (docker) with coverage
         env:
           BOT_BOTTLE_BACKEND: docker
-        run: python3 -m unittest discover -t . -s tests/integration -v
+        run: python3 -m coverage run --data-file=.coverage.docker -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.
@@ -137,9 +107,16 @@ jobs:
   #
   # Runner prerequisites (provision once; see README "Firecracker on Linux"):
   # `firecracker` on PATH, `/dev/kvm` accessible, cached kernel +
-  # static dropbear, and the pool as a persistent systemd unit.
+  # static dropbear at /var/cache/bot-bottle-fc/dropbear, and the pool as a
+  # 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' ||
@@ -159,49 +136,58 @@ jobs:
           # range overlap; it prints the exact `backend setup` fix.
           python3 cli.py backend status --backend=firecracker
 
-      - name: Download the candidate built from this checkout
-        uses: actions/download-artifact@v3
-        with:
-          name: infra-candidate
-          path: infra-candidate
+      - name: Build infra candidate from this checkout
+        env:
+          BOT_BOTTLE_FC_DROPBEAR: /var/cache/bot-bottle-fc/dropbear
+        run: python3 -m bot_bottle.backend.firecracker.publish_infra --output 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: the integration suite runs on stdlib
-      # `unittest` (pylint/pyright are lint.yml's concern, not this job's),
-      # and the self-hosted runner's Nix python env has no `pip` module
-      # (`python3 -m pip` → "No module named pip"). Nothing to install.
-      - name: Run integration tests (firecracker)
+      # 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.
+      - name: Run integration tests (firecracker) with coverage
         env:
           BOT_BOTTLE_BACKEND: firecracker
           BOT_BOTTLE_INFRA_ARTIFACT_DIR: ${{ github.workspace }}/infra-candidate
-        run: python3 -m unittest discover -t . -s tests/integration -v
+        run: python3 -m coverage run --data-file=.coverage.firecracker -m unittest discover -t . -s tests/integration -v
 
-  # Combined unit+integration coverage + the diff-coverage gate (the hard
-  # gate: new/changed lines >= 90%). See docs/decisions/0004-coverage-policy.md.
+      - name: Upload firecracker coverage artifact
+        uses: actions/upload-artifact@v3
+        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%).
   #
-  # This runs on a self-hosted KVM runner (label `kvm`), NOT ubuntu-latest,
-  # 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.
+  # Runs on ubuntu-latest — no KVM needed, no test reruns. Coverage files use
+  # relative_files = True (.coveragerc) so they combine cleanly across runners.
   #
-  # Restricted to the same events as integration-firecracker (same-repo PRs,
-  # 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.
+  # Restricted to the same events as integration-firecracker: it depends on
+  # that job's coverage artifact and skips for fork PRs alongside it.
   coverage:
-    needs: [build-infra, integration-firecracker]
+    needs: [unit, integration-docker, integration-firecracker]
     timeout-minutes: 15
-    runs-on: [self-hosted, kvm]
+    runs-on: ubuntu-latest
     if: >-
       github.event_name == 'push' ||
       github.event_name == 'workflow_dispatch' ||
@@ -213,29 +199,29 @@ jobs:
         with:
           fetch-depth: 0
 
-      - name: Preflight — Firecracker host is ready
-        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: Install coverage
+        run: python3 -m pip install --break-system-packages coverage
 
-      - name: Download the candidate already exercised by integration
+      - name: Download unit coverage artifact
         uses: actions/download-artifact@v3
         with:
-          name: infra-candidate
-          path: infra-candidate
+          name: coverage-unit
+          path: ${{ github.workspace }}
+
+      - 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)
-        env:
-          BOT_BOTTLE_CI_INFRA_ARTIFACT_DIR: ${{ github.workspace }}/infra-candidate
-        run: PYTHON=python3 bash scripts/coverage.sh critical
+        run: PYTHON=python3 bash scripts/coverage.sh aggregate critical
 
       - name: Diff-coverage gate (changed lines >= 90%)
         run: |
@@ -243,14 +229,14 @@ jobs:
           python3 scripts/diff_coverage.py --base origin/main --min 90
 
   publish-infra:
-    needs: [stage-firecracker-inputs, build-infra, unit, integration-docker, integration-firecracker, coverage]
+    needs: [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 candidate
+      - name: Download the tested rootfs
         uses: actions/download-artifact@v3
         with:
           name: infra-candidate
@@ -258,9 +244,10 @@ jobs:
 
       # publish_infra re-derives the version from the checkout to confirm the
       # bundle matches before uploading, and the version hashes the dropbear
-      # bytes. Stage the SAME dropbear build-infra used, or the recheck
-      # computes a "<missing>"-dropbear version and rejects the candidate.
-      - name: Download the staged dropbear (matches build-infra's version)
+      # bytes. Download the SAME dropbear integration-firecracker used, or
+      # the recheck computes a "<missing>"-dropbear version and rejects the
+      # candidate.
+      - name: Download the staged dropbear (matches build's version)
         uses: actions/download-artifact@v3
         with:
           name: firecracker-inputs

bot_bottle/backend/__init__.py

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

bot_bottle/backend/firecracker/util.py

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

bot_bottle/backend/macos_container/bottle.py

@@ -68,9 +68,14 @@ 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. `container exec --env` wins
-        # over the run-time value, so the token-bearing proxy URL set here
-        # supersedes the token-less one baked in at launch.
+        # the way docker's compose spec does it.
+        #
+        # `container exec --env` does NOT override a run-time value — it
+        # 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/enumerate.py

@@ -8,7 +8,11 @@ from ...bottle_state import read_metadata
 from .. import ActiveAgent
 from .infra import INFRA_NAME
 
-_PREFIX = "bot-bottle-"
+# The name every agent container carries: `bot-bottle-<slug>`. Exported
+# 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.
@@ -26,9 +30,9 @@ 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(_PREFIX) or name in _INFRA_NAMES:
+        if not name.startswith(CONTAINER_NAME_PREFIX) or name in _INFRA_NAMES:
             continue
-        slug = name[len(_PREFIX):]
+        slug = name[len(CONTAINER_NAME_PREFIX):]
         metadata = read_metadata(slug)
         out.append(ActiveAgent(
             backend_name="macos-container",

bot_bottle/backend/macos_container/gateway_hosts.py

@@ -0,0 +1,96 @@
+"""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

@@ -59,6 +59,11 @@ 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,
@@ -100,6 +105,11 @@ 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.
@@ -117,6 +127,9 @@ 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,
         )
@@ -231,13 +244,20 @@ 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 address)."""
+    gateway name).
+
+    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://{endpoint.gateway_ip}:{_GIT_HTTP_PORT}"
+        f"http://{GATEWAY_HOSTNAME}:{_GIT_HTTP_PORT}"
         if plan.git_gate_plan.upstreams else ""
     )
     supervise_url = (
-        f"http://{endpoint.gateway_ip}:{SUPERVISE_PORT}/"
+        f"http://{GATEWAY_HOSTNAME}:{SUPERVISE_PORT}/"
         if plan.supervise_plan is not None else ""
     )
     return dataclasses.replace(
@@ -247,30 +267,43 @@ def _stamp_agent_urls(
     )
 
 
-def _proxy_url(gateway_ip: str, identity_token: str = "") -> str:
+def _proxy_url(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_ip}:{EGRESS_PORT}"
+    return f"http://{cred}{GATEWAY_HOSTNAME}:{EGRESS_PORT}"
 
 
-def _no_proxy(gateway_ip: str) -> str:
+def _no_proxy() -> str:
     # git-http + supervise live on the gateway and must NOT go through the
-    # egress proxy — the agent reaches them directly by its address.
-    return f"localhost,127.0.0.1,{gateway_ip}"
+    # egress proxy — the agent reaches them directly by name. Deliberately
+    # address-free: NO_PROXY is baked into the run-time env and is therefore
+    # 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`. It supersedes
-    the token-less run-time value (exec `--env` wins), which is the only way to
-    get the token in: it does not exist until after the container runs."""
+    """The token-bearing proxy env applied at `container exec` — the only way
+    to get the token in, since it does not exist until after the container
+    runs (registration keys on the DHCP-assigned address).
+
+    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 {}
-    url = _proxy_url(endpoint.gateway_ip, identity_token)
+    del endpoint  # the gateway is named, not addressed
+    url = _proxy_url(identity_token)
     return {
         "HTTPS_PROXY": url, "HTTP_PROXY": url,
         "https_proxy": url, "http_proxy": url,
@@ -317,16 +350,23 @@ def _agent_run_argv(
 def _agent_env_entries(
     plan: MacosContainerBottlePlan, endpoint: GatewayEndpoint,
 ) -> tuple[str, ...]:
-    # Token-less at run time — the token does not exist yet (see
-    # `_identity_proxy_env`). Anything egressing before the exec-time override
-    # is denied by `/resolve`, which is the safe direction.
-    proxy_url = _proxy_url(endpoint.gateway_ip)
-    no_proxy = _no_proxy(endpoint.gateway_ip)
+    # No `*_PROXY` here on purpose. The token-bearing URL is applied at
+    # `container exec` (`_identity_proxy_env`), and Apple's `container exec
+    # --env` **appends** to the run-time environment rather than replacing it:
+    # setting a token-less value here leaves two `HTTPS_PROXY` entries in the
+    # agent's `environ`, token-less first. Which one a runtime reads is then
+    # 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

@@ -360,6 +360,21 @@ 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/cli/_common.py

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

bot_bottle/cli/cleanup.py

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

bot_bottle/cli/start.py

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

bot_bottle/util.py

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

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

@@ -0,0 +1,110 @@
+# 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.

scripts/coverage.sh

@@ -1,15 +1,19 @@
 #!/usr/bin/env bash
 # Combined unit + integration coverage (see docs/decisions/0004-coverage-policy.md).
 #
-# 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.
+# Two modes:
 #
-# Usage:
-#   scripts/coverage.sh            # combined report
-#   scripts/coverage.sh critical   # also report just the critical modules
+#   scripts/coverage.sh [critical]
+#     Run mode (default, for local dev): executes the unit suite then the
+#     integration suite under coverage and prints a combined report.
+#
+#   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 "$0")/.."
@@ -21,6 +25,22 @@ PY="${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/unit/test_backend_selection.py

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

tests/unit/test_cli_cleanup_cross_backend.py

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

tests/unit/test_cli_start_backend_flag.py

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

tests/unit/test_cli_start_headless.py

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

tests/unit/test_cli_start_selector.py

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

tests/unit/test_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
 
@@ -104,19 +104,38 @@ class TestAgentRunArgv(unittest.TestCase):
         read back after start."""
         self.assertNotIn("--ip", self.argv)
 
-    def test_run_time_proxy_carries_no_identity_token(self) -> None:
-        """The token is minted by registration, which happens after this run —
-        so it cannot be here. `/resolve` denies the token-less pair (#366),
-        which is the safe direction; the real value arrives at exec time."""
-        joined = " ".join(self.argv)
-        self.assertIn(f"HTTP_PROXY={_proxy_url('192.168.128.3')}", joined)
-        self.assertNotIn("bottle:", joined)
+    def test_run_time_env_sets_no_proxy_vars_at_all(self) -> None:
+        """Regression: the proxy vars must exist *only* in the exec-time env.
+
+        `container exec --env` appends rather than replaces, so a token-less
+        `HTTPS_PROXY` here would survive next to the token-bearing one and
+        leave two entries in the agent's `environ`. Resolution is then
+        runtime-specific — Node reads the last, Rust's `std::env::var` reads
+        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("192.168.128.3", entry)
+        self.assertIn(GATEWAY_HOSTNAME, 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
@@ -134,7 +153,7 @@ class TestIdentityTokenDelivery(unittest.TestCase):
     def test_exec_env_carries_the_token_as_proxy_credentials(self) -> None:
         env = _identity_proxy_env(_endpoint(), "s3cret")
         self.assertEqual(
-            "http://bottle:s3cret@192.168.128.3:9099", env["HTTP_PROXY"],
+            f"http://bottle:s3cret@{GATEWAY_HOSTNAME}:9099", env["HTTP_PROXY"],
         )
         self.assertEqual(env["HTTP_PROXY"], env["https_proxy"])
 
@@ -202,7 +221,7 @@ class TestPlanIdentityToken(unittest.TestCase):
         self.assertIn("HTTP_PROXY", argv)
         self.assertNotIn("s3cret", " ".join(argv))
         self.assertEqual(
-            "http://bottle:s3cret@192.168.128.3:9099", kwargs["env"]["HTTP_PROXY"],
+            f"http://bottle:s3cret@{GATEWAY_HOSTNAME}:9099", kwargs["env"]["HTTP_PROXY"],
         )
 
 

tests/unit/test_macos_container_util.py

@@ -272,6 +272,30 @@ 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

@@ -0,0 +1,140 @@
+"""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()