feat(orchestrator): list_live broker op + reconcile via broker (#468)

Chunk 3 of the host-control-server stack: grow the broker op vocabulary
(PRD gap 3), starting with `list_live`, and invert `reconcile` onto it.

- broker: split the closed op vocabulary into mutation (`launch`/`teardown`,
  carry a bottle id + static flags) and query (`list_live`, carries nothing
  but its op name) kinds. `verify_request` now enforces a **strict schema**
  (open question 1, resolved yes): unknown claim keys are rejected, a mutation
  must name its bottle, and a query that smuggles any id/flag is refused.
- broker verb: `LaunchBroker.list_live` / `SubmitBroker.list_live` return the
  backend's live source IPs; a backend enumeration failure is converted to the
  single `BrokerUnavailableError` "live set unknown" signal. `DockerBroker`
  enumerates its labelled containers; `StubBroker` derives from launches (or a
  test override).
- host controller: `POST /broker/live` verifies a signed `list_live` token and
  returns `{source_ips}`; `BrokerClient.list_live` is its drop-in client.
- reconcile: `OrchestratorCore.reconcile()` drops the `live_source_ips`
  parameter and pulls the live set from the broker itself — the tell that the
  orchestrator couldn't see the backend goes away. **Fail-safe**: if the broker
  can't return an authoritative set the sweep is skipped, never run against an
  empty/partial set (which would reap healthy rows). The `/reconcile` HTTP
  contract + `OrchestratorClient.reconcile` become a bare trigger.

The macOS launcher's Apple-container enumeration stays for now; it becomes the
host controller's `list_live` when launch itself moves behind the broker (the
pulled-forward chunk 5, next in the stack).

Tests + pyright clean; pylint 10.0 on broker.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

.gitea/workflows/test.yml

@@ -102,20 +102,6 @@ jobs:
           python3 --version
           python3 cli.py backend status --backend=docker
 
-      - name: Preflight — clear any leftover poisoned gateway network
-        run: |
-          # The gateway network has a fixed name and persists across jobs on
-          # this shared runner. A pre-fix or concurrent launch can leave it with
-          # a malformed IPv6 subnet that trips docker's own ParseAddr in
-          # `network inspect` (see PR #515); the code now self-heals it, but the
-          # heal can't run if `network inspect` is what's broken on some daemon
-          # versions. Drop the network here so this run recreates it IPv4-only.
-          # Remove the attached gateway container first (else `network rm` fails
-          # on active endpoints); both are recreated by ensure_running. Harmless
-          # when absent.
-          docker rm --force bot-bottle-orch-gateway 2>/dev/null || true
-          docker network rm bot-bottle-gateway 2>/dev/null || true
-
       - name: Run integration tests (docker) with coverage
         env:
           BOT_BOTTLE_BACKEND: docker
@@ -298,7 +284,7 @@ jobs:
       - name: Combined coverage (unit + docker integration)
         run: PYTHON=python3 bash scripts/coverage.sh aggregate critical
 
-      - name: Diff-coverage gate (changed lines >= 80%)
+      - name: Diff-coverage gate (changed lines >= 90%)
         run: |
           git fetch --no-tags origin main:refs/remotes/origin/main
-          python3 scripts/diff_coverage.py --base origin/main --min 80
+          python3 scripts/diff_coverage.py --base origin/main --min 90

Dockerfile.orchestrator

@@ -9,9 +9,12 @@
 #     Keeping the content in one place means future orchestrator deps (e.g.
 #     iroh) are added here once, not duplicated per backend.
 #
-# It stays deliberately lean: only the pinned FastAPI/Uvicorn control-plane
-# stack is installed here — none of the gateway's mitmproxy/git/gitleaks
-# (that's Dockerfile.gateway) and no buildah (that's firecracker-only).
+# It stays deliberately lean: the control plane is **stdlib-only** today, so
+# no third-party payload — none of the gateway's mitmproxy/git/gitleaks
+# (that's Dockerfile.gateway) and no buildah (that's the firecracker
+# builder, and lives only in Dockerfile.orchestrator.fc). Keeping the
+# secret-dense control plane on a minimal dependency surface is the point
+# (PRD 0070's "secret concentration").
 #
 # Shares an exact multi-architecture Python/trixie manifest with the gateway
 # image. The version-qualified tag keeps the human-readable upstream version;
@@ -22,11 +25,6 @@ FROM ${PYTHON_BASE_IMAGE}
 
 WORKDIR /app
 
-COPY requirements.orchestrator.lock /tmp/requirements.orchestrator.lock
-RUN pip install --no-cache-dir --require-hashes \
-        -r /tmp/requirements.orchestrator.lock \
-    && rm /tmp/requirements.orchestrator.lock
-
 # The orchestrator content. Baked so the image is self-contained (runs from
 # a built image, no runtime bind-mount); the docker backend may still
 # bind-mount /app for dev live-reload, which simply overlays this copy.

bot_bottle/backend/__init__.py

@@ -30,7 +30,6 @@ if TYPE_CHECKING:
         BottleImages,
         BottlePlan,
         BottleSpec,
-        EnumerationError,
         ExecResult,
     )
     from .selection import (
@@ -60,7 +59,6 @@ _LAZY_MODULES: dict[str, str] = {
     "BottleImages": "base",
     "BottleBackend": "base",
     "BackendStatus": "base",
-    "EnumerationError": "base",
     "get_bottle_backend": "selection",
     "known_backend_names": "selection",
     "has_backend": "selection",
@@ -102,7 +100,6 @@ __all__ = [
     "BottlePlan",
     "BottleSpec",
     "ExecResult",
-    "EnumerationError",
     "CommitCancelled",
     "Freezer",
     "get_freezer",

bot_bottle/backend/base.py

@@ -42,10 +42,6 @@ class BackendStatus(enum.IntEnum):
     READY = 0
 
 
-class EnumerationError(RuntimeError):
-    """A backend could not produce an authoritative live-resource snapshot."""
-
-
 @dataclass(frozen=True)
 class BottleSpec:
     """CLI-supplied intent. Backend-agnostic — each backend's prepare

bot_bottle/backend/docker/compose.py

@@ -16,7 +16,6 @@ from pathlib import Path
 from typing import Any
 
 from ...log import die, warn
-from ..base import EnumerationError
 
 
 # --- Lifecycle helpers (PRD 0018 chunk 3) ----------------------------------
@@ -53,20 +52,19 @@ def slug_from_compose_project(project: str) -> str:
 
 
 def list_compose_projects(
-    *,
-    include_stopped: bool = True,
-    warn_on_error: bool = True,
-    raise_on_error: bool = False,
+    *, include_stopped: bool = True, warn_on_error: bool = True,
 ) -> list[str]:
     """All compose project names starting with `bot-bottle-`.
     `include_stopped=True` (default) runs `docker compose ls --all`
     so exited projects appear too; pass False to get only projects
     with at least one running container.
 
-    Best-effort callers get ``[]`` on Docker errors or malformed output.
-    Enumeration callers pass ``raise_on_error=True`` so a failed query is not
-    reported as an authoritative empty result.
-    """
+    Returns [] on docker daemon errors or malformed output rather
+    than raising — callers should treat the empty list as "no
+    projects discoverable", not "no projects exist". `warn_on_error`
+    stays true for explicit operator commands like cleanup, but active
+    discovery paths set it false so dashboard refreshes don't spam
+    stderr while Docker Desktop is stopped."""
     argv = ["docker", "compose", "ls", "--format", "json"]
     if include_stopped:
         argv.insert(3, "--all")
@@ -74,27 +72,19 @@ def list_compose_projects(
         result = subprocess.run(
             argv, capture_output=True, text=True, check=False,
         )
-    except FileNotFoundError as exc:
-        if raise_on_error:
-            raise EnumerationError(
-                "docker compose ls failed: docker not found"
-            ) from exc
+    except FileNotFoundError:
+        # docker binary not on PATH — same shape as a daemon-down
+        # error from the caller's POV: no projects discoverable.
         return []
     if result.returncode != 0:
-        message = f"docker compose ls failed: {result.stderr.strip()}"
-        if raise_on_error:
-            raise EnumerationError(message)
         if warn_on_error:
-            warn(message)
+            warn(f"docker compose ls failed: {result.stderr.strip()}")
         return []
     try:
         projects = json.loads(result.stdout or "[]")
     except json.JSONDecodeError as e:
-        message = f"docker compose ls returned malformed JSON: {e}"
-        if raise_on_error:
-            raise EnumerationError(message) from e
         if warn_on_error:
-            warn(message)
+            warn(f"docker compose ls returned malformed JSON: {e}")
         return []
     names: list[str] = []
     for p in projects:
@@ -107,10 +97,7 @@ def list_compose_projects(
 
 
 def list_active_slugs(
-    *,
-    include_stopped: bool = False,
-    warn_on_error: bool = True,
-    raise_on_error: bool = False,
+    *, include_stopped: bool = False, warn_on_error: bool = True,
 ) -> list[str]:
     """Slugs (project name minus prefix) of currently-running
     bottles. Used by the dashboard's operator-edit verbs to choose
@@ -121,7 +108,6 @@ def list_active_slugs(
             for p in list_compose_projects(
                 include_stopped=include_stopped,
                 warn_on_error=warn_on_error,
-                raise_on_error=raise_on_error,
             )
         ) if slug
     )

bot_bottle/backend/docker/consolidated_launch.py

@@ -68,11 +68,6 @@ def _network_container_ips(network: str) -> list[str]:
         "docker", "network", "inspect", "--format",
         "{{range .Containers}}{{.IPv4Address}} {{end}}", network,
     ])
-    if proc.returncode != 0:
-        detail = proc.stderr.strip() or f"exit {proc.returncode}"
-        raise ConsolidatedLaunchError(
-            f"could not inspect addresses on gateway network {network}: {detail}"
-        )
     ips: list[str] = []
     for entry in proc.stdout.split():
         ips.append(entry.split("/", 1)[0])

bot_bottle/backend/docker/enumerate.py

@@ -1,8 +1,9 @@
 """Active-agent enumeration for the docker backend.
 
 Returns `ActiveAgent` records the CLI `active` command and the
-dashboard agents pane consume. Docker query failures raise rather
-than masquerading as an authoritative empty result.
+dashboard agents pane consume. Empty when docker isn't reachable
+— gated by `has_backend('docker')` at the cross-backend caller
+so this module trusts that docker is available when called.
 
 The parser (`_parse_services_by_project`) is exposed for direct
 unit testing; the docker `docker ps` invocation is in
@@ -12,18 +13,17 @@ from __future__ import annotations
 
 import subprocess
 
-from .. import ActiveAgent, EnumerationError
+from .. import ActiveAgent
 from ...bottle_state import read_metadata
 from .compose import compose_project_name, list_active_slugs
 
 
 def enumerate_active() -> list[ActiveAgent]:
-    """All currently-running docker-backed agents."""
-    slugs = list_active_slugs(
-        include_stopped=False,
-        warn_on_error=False,
-        raise_on_error=True,
-    )
+    """All currently-running docker-backed agents. Caller is
+    responsible for gating on `has_backend('docker')` if it
+    matters; if docker is missing the `docker ps` call below
+    returns an empty list silently."""
+    slugs = list_active_slugs(include_stopped=False, warn_on_error=False)
     if not slugs:
         return []
     services_by_project = _query_services_by_project()
@@ -74,8 +74,8 @@ def _query_services_by_project() -> dict[str, set[str]]:
             ],
             capture_output=True, text=True, check=False,
         )
-    except FileNotFoundError as exc:
-        raise EnumerationError("docker ps failed: docker not found") from exc
+    except FileNotFoundError:
+        return {}
     if r.returncode != 0:
-        raise EnumerationError(f"docker ps failed: {r.stderr.strip()}")
+        return {}
     return _parse_services_by_project(r.stdout or "")

bot_bottle/backend/docker/gateway.py

@@ -140,43 +140,12 @@ class DockerGateway(Gateway):
             marker = inspected.stdout.strip()
             if marker in {"", self._subnet}:
                 return
-            # Inspectable but mislabelled: the stale auto-IPAM network created
-            # by older releases. Replace it below.
-            stale = True
-        else:
-            # inspect failed. Classify by stderr — do NOT assume "not absent"
-            # implies "poisoned": a transient daemon/API error, permission
-            # failure, timeout, or bad context also fails here, and destroying
-            # the shared gateway on that guess would tear the network out from
-            # under every live bottle.
-            err = inspected.stderr.lower()
-            if "no such network" in err or "not found" in err:
-                # Absent: nothing to replace — create it below.
-                stale = False
-            elif "parseaddr" in err:
-                # Present but poisoned. A daemon that default-enables IPv6
-                # attaches an fdd0::/64 subnet whose `::1/64` gateway trips
-                # docker's own netip.ParseAddr in `network inspect`/`ls`, so the
-                # command exits non-zero with that signature. A fixed release
-                # never *creates* such a network, but one can survive on a
-                # shared host from an older or concurrent launch — and
-                # `--ipv6=false` alone can't heal it, since the create below only
-                # no-ops on "already exists". Force-replace it so later reads
-                # (e.g. `_network_cidr` pinning a source IP) stop failing.
-                stale = True
-            else:
-                # Unrecognized failure: no evidence the network is malformed.
-                # Surface it rather than mutate shared state on a guess.
-                raise GatewayError(
-                    f"gateway network {self.network} could not be inspected: "
-                    f"{inspected.stderr.strip()}"
-                )
-        if stale:
-            # Migrate the stale/poisoned network. Removing the fixed gateway is
-            # safe here: this launch recreates it.
+        if inspected.returncode == 0:
+            # Migrate the stale auto-IPAM network created by older releases.
+            # Removing the fixed gateway is safe here: this launch recreates it.
             run_docker(["docker", "rm", "--force", self.name])
             removed = run_docker(["docker", "network", "rm", self.network])
-            if removed.returncode != 0 and "no such network" not in removed.stderr.lower():
+            if removed.returncode != 0:
                 raise GatewayError(
                     f"gateway network {self.network} needs explicit subnet "
                     f"{self._subnet} but could not be replaced: "

bot_bottle/backend/firecracker/cleanup.py

@@ -29,8 +29,7 @@ import subprocess
 from pathlib import Path
 
 from ...log import info
-from .. import EnumerationError
-from . import lifecycle_lock, util
+from . import util
 from .bottle_cleanup_plan import FirecrackerBottleCleanupPlan
 
 
@@ -63,23 +62,12 @@ def _scan_processes(run_root: Path) -> tuple[set[str], list[int]]:
       * ``orphan_pids`` — firecracker pids whose run dir no longer exists
         (a lingering VMM to kill).
     """
-    try:
-        result = subprocess.run(
-            ["pgrep", "-a", "firecracker"],
-            capture_output=True, text=True, check=False,
-        )
-    except OSError as exc:
-        raise EnumerationError(
-            f"could not enumerate Firecracker processes: {exc}"
-        ) from exc
-    if result.returncode == 1:
-        # pgrep's documented "no processes matched" result.
-        return set(), []
+    result = subprocess.run(
+        ["pgrep", "-a", "firecracker"],
+        capture_output=True, text=True, check=False,
+    )
     if result.returncode != 0:
-        detail = (result.stderr or "").strip() or f"exit {result.returncode}"
-        raise EnumerationError(
-            f"could not enumerate Firecracker processes: {detail}"
-        )
+        return set(), []
     live: set[str] = set()
     orphan_pids: list[int] = []
     for line in result.stdout.splitlines():
@@ -126,42 +114,12 @@ def prepare_cleanup() -> FirecrackerBottleCleanupPlan:
 
 
 def cleanup(plan: FirecrackerBottleCleanupPlan) -> None:
-    """Revalidate the preview under the launch lock, then remove its survivors."""
-    with lifecycle_lock.hold():
-        fresh = prepare_cleanup()
-        approved_pids = set(plan.vm_pids).intersection(fresh.vm_pids)
-        approved_dirs = set(plan.run_dirs).intersection(fresh.run_dirs)
-        for pid in sorted(approved_pids):
-            _terminate_orphan(pid, _run_root())
-        for path in sorted(approved_dirs):
-            info(f"rm -rf {path}")
-            shutil.rmtree(path, ignore_errors=True)
-
-
-def _terminate_orphan(pid: int, run_root: Path) -> None:
-    """Signal exactly the process identity that still owns an orphan config."""
-    try:
-        pidfd = os.pidfd_open(pid)
-    except ProcessLookupError:
-        return
-    except OSError as exc:
-        raise EnumerationError(
-            f"could not pin Firecracker pid {pid} for cleanup: {exc}"
-        ) from exc
-    try:
-        try:
-            raw = Path(f"/proc/{pid}/cmdline").read_bytes()
-        except FileNotFoundError:
-            return
-        except OSError as exc:
-            raise EnumerationError(
-                f"could not revalidate Firecracker pid {pid}: {exc}"
-            ) from exc
-        command = raw.replace(b"\0", b" ").decode(errors="replace")
-        run_dir = _run_dir_of(command, run_root)
-        if run_dir is None or run_dir.is_dir():
-            return
+    for pid in plan.vm_pids:
         info(f"kill firecracker VM pid {pid}")
-        signal.pidfd_send_signal(pidfd, signal.SIGTERM)
-    finally:
-        os.close(pidfd)
+        try:
+            os.kill(pid, signal.SIGTERM)
+        except ProcessLookupError:
+            pass
+    for path in plan.run_dirs:
+        info(f"rm -rf {path}")
+        shutil.rmtree(path, ignore_errors=True)

bot_bottle/backend/firecracker/enumerate.py

@@ -1,32 +1,14 @@
 """Active-agent enumeration for the Firecracker backend.
 
-Running bottles are the Firecracker processes whose ``--config-file`` points
-at an existing per-bottle run directory. The same authoritative process scan
-protects cleanup from deleting live VMs; operational scan failures propagate
-as ``EnumerationError`` instead of masquerading as an empty host.
+The backend is disabled during the companion-container removal (#385) — it can't
+launch bottles, so there are none to enumerate. Real enumeration returns
+with the backend's consolidated relaunch (#354).
 """
 
 from __future__ import annotations
 
-from ...bottle_state import read_metadata
 from .. import ActiveAgent
-from .cleanup import live_run_dirs
 
 
 def enumerate_active() -> list[ActiveAgent]:
-    out: list[ActiveAgent] = []
-    for run_dir in live_run_dirs():
-        slug = run_dir.name
-        metadata = read_metadata(slug)
-        out.append(ActiveAgent(
-            backend_name="firecracker",
-            slug=slug,
-            agent_name=metadata.agent_name if metadata else "?",
-            started_at=metadata.started_at if metadata else "",
-            # Firecracker uses the shared gateway, so there are no
-            # per-bottle gateway service containers to report.
-            services=(),
-            label=metadata.label if metadata else "",
-            color=metadata.color if metadata else "",
-        ))
-    return out
+    return []

bot_bottle/backend/firecracker/infra_artifact.py

@@ -54,7 +54,6 @@ _BUILD_INPUTS = {
         "image-build-args.json",
         "Dockerfile.orchestrator",
         "Dockerfile.orchestrator.fc",
-        "requirements.orchestrator.lock",
     ),
     "gateway": (
         "image-build-args.json",

bot_bottle/backend/firecracker/launch.py

@@ -46,7 +46,7 @@ from ...log import die, info, warn
 from ...supervisor.types import SUPERVISE_PORT
 from ..docker.egress import EGRESS_PORT
 from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
-from . import firecracker_vm, image_builder, isolation_probe, lifecycle_lock, netpool, util
+from . import firecracker_vm, image_builder, isolation_probe, netpool, util
 from .bottle import FirecrackerBottle
 from .bottle_plan import FirecrackerBottlePlan
 from ...orchestrator.store.config_store import resolve_teardown_timeout
@@ -164,29 +164,25 @@ def launch(
         )
 
         # Step 6: build the per-bottle rootfs + SSH key, then boot.
-        # Cleanup takes the same lock while refreshing its process snapshot.
-        # Hold it until the VMM exists so a newly-created run dir can never be
-        # mistaken for an orphan in the build-before-boot window.
-        with lifecycle_lock.hold():
-            run_dir = util.cache_dir() / "run" / plan.slug
-            run_dir.mkdir(parents=True, exist_ok=True)
-            # Remove the run dir on teardown so the per-bottle rootfs.ext4 (~1G)
-            # doesn't leak. Registered before vm.terminate below so it runs
-            # *after* it (ExitStack is LIFO).
-            stack.callback(lambda: shutil.rmtree(run_dir, ignore_errors=True))
-            rootfs = run_dir / "rootfs.ext4"
-            util.build_rootfs_ext4(agent_base, rootfs)
-            private_key, pubkey = util.generate_keypair(run_dir)
+        run_dir = util.cache_dir() / "run" / plan.slug
+        run_dir.mkdir(parents=True, exist_ok=True)
+        # Remove the run dir on teardown so the per-bottle rootfs.ext4 (~1G)
+        # doesn't leak. Registered before vm.terminate below so it runs *after*
+        # it (ExitStack is LIFO): the VM is gone before we rm its rootfs.
+        stack.callback(lambda: shutil.rmtree(run_dir, ignore_errors=True))
+        rootfs = run_dir / "rootfs.ext4"
+        util.build_rootfs_ext4(agent_base, rootfs)
+        private_key, pubkey = util.generate_keypair(run_dir)
 
-            vm = firecracker_vm.boot(
-                name=plan.container_name,
-                rootfs=rootfs,
-                tap=slot.iface,
-                guest_ip=slot.guest_ip,
-                host_ip=slot.host_ip,
-                pubkey=pubkey,
-                run_dir=run_dir,
-            )
+        vm = firecracker_vm.boot(
+            name=plan.container_name,
+            rootfs=rootfs,
+            tap=slot.iface,
+            guest_ip=slot.guest_ip,
+            host_ip=slot.host_ip,
+            pubkey=pubkey,
+            run_dir=run_dir,
+        )
         stack.callback(vm.terminate)
         firecracker_vm.wait_for_ssh(vm, private_key)
         persist_env_var_secret(private_key, slot.guest_ip, ctx.env_var_secret)

bot_bottle/backend/firecracker/lifecycle_lock.py

@@ -1,30 +0,0 @@
-"""Serialize Firecracker run-directory creation with orphan cleanup."""
-
-from __future__ import annotations
-
-import fcntl
-from contextlib import contextmanager
-from pathlib import Path
-from typing import Generator
-
-from . import util
-
-
-def _lock_path() -> Path:
-    return util.cache_dir() / "run.lifecycle.lock"
-
-
-@contextmanager
-def hold() -> Generator[None]:
-    """Exclude cleanup while a launch directory lacks a visible VMM."""
-    path = _lock_path()
-    path.parent.mkdir(parents=True, exist_ok=True)
-    with path.open("a", encoding="utf-8") as handle:
-        fcntl.flock(handle, fcntl.LOCK_EX)
-        try:
-            yield
-        finally:
-            fcntl.flock(handle, fcntl.LOCK_UN)
-
-
-__all__ = ["hold"]

bot_bottle/backend/macos_container/cleanup.py

@@ -4,8 +4,7 @@ from __future__ import annotations
 
 import subprocess
 
-from .. import EnumerationError
-from ...log import info
+from ...log import info, warn
 from . import util as container_mod
 from .bottle_cleanup_plan import MacosContainerBottleCleanupPlan
 
@@ -20,8 +19,8 @@ def _list_prefixed_containers() -> list[str]:
         check=False,
     )
     if result.returncode != 0:
-        detail = result.stderr.strip() or f"exit {result.returncode}"
-        raise EnumerationError(f"container list failed: {detail}")
+        warn(f"container list failed: {result.stderr.strip()}")
+        return []
     return sorted(
         name for name in (line.strip() for line in result.stdout.splitlines())
         if name.startswith(_PREFIX)
@@ -36,8 +35,7 @@ def _list_prefixed_networks() -> list[str]:
         check=False,
     )
     if result.returncode != 0:
-        detail = result.stderr.strip() or f"exit {result.returncode}"
-        raise EnumerationError(f"container network list failed: {detail}")
+        return []
     return sorted(
         name for name in (line.strip() for line in result.stdout.splitlines())
         if name.startswith(_PREFIX)

bot_bottle/backend/macos_container/consolidated_launch.py

@@ -166,9 +166,17 @@ def register_agent(
     # collide with this bottle's — and `by_source_ip` fail-closes on ambiguity,
     # which would resolve no policy at all and deny every host. Best-effort: a
     # reconciliation failure must not block an otherwise-fine launch.
+    #
+    # The orchestrator now pulls the live set from the broker itself, so this is
+    # a bare trigger. Until macOS moves onto the host controller (the follow-up
+    # that routes launch through the broker), the orchestrator's broker is the
+    # stub, whose live set is the bottles it recorded launches for — so the sweep
+    # only under-reaps (leaves an orphan a cycle longer), never reaps a healthy
+    # bottle. The Apple-container enumeration below (`live_source_ips`) becomes
+    # that host controller's `list_live` there.
     try:
-        client.reconcile(live_source_ips(endpoint.network))
-    except (OrchestratorClientError, EnumerationError) as e:
+        client.reconcile()
+    except OrchestratorClientError as e:
         info(f"registry reconciliation skipped: {e}")
     reg = provision_bottle(
         client, source_ip, egress_plan, git_gate_plan, MacosGatewayTransport(),

bot_bottle/backend/macos_container/enumerate.py

@@ -5,7 +5,7 @@ from __future__ import annotations
 import subprocess
 
 from ...bottle_state import read_metadata
-from .. import ActiveAgent, EnumerationError
+from .. import ActiveAgent
 from .infra import INFRA_NAME, ORCHESTRATOR_NAME
 
 # The name every agent container carries: `bot-bottle-<slug>`. Exported
@@ -20,18 +20,17 @@ CONTAINER_NAME_PREFIX = "bot-bottle-"
 _INFRA_NAMES = frozenset({INFRA_NAME, ORCHESTRATOR_NAME})
 
 
+class EnumerationError(RuntimeError):
+    """container list failed; the resulting live set is not authoritative."""
+
+
 def enumerate_active() -> list[ActiveAgent]:
-    try:
-        result = subprocess.run(
-            ["container", "list", "--quiet"],
-            capture_output=True,
-            text=True,
-            check=False,
-        )
-    except FileNotFoundError as exc:
-        raise EnumerationError(
-            "container list failed: container CLI not found"
-        ) from exc
+    result = subprocess.run(
+        ["container", "list", "--quiet"],
+        capture_output=True,
+        text=True,
+        check=False,
+    )
     if result.returncode != 0:
         raise EnumerationError(
             f"container list failed: "

bot_bottle/cli/commands/cleanup.py

@@ -52,11 +52,7 @@ def cmd_cleanup(_argv: list[str]) -> int:
         info("cleanup: skipped")
         return 0
 
-    # Confirmation authorizes a fresh authoritative snapshot, not blind use of
-    # identities that may have changed while the operator reviewed the preview.
-    refreshed = [(name, backend, backend.prepare_cleanup())
-                 for name, backend, _plan in prepared]
-    for name, backend, plan in refreshed:
+    for name, backend, plan in prepared:
         if plan.empty:
             continue
         backend.cleanup(plan)

bot_bottle/gateway/bounded_http.py

@@ -1,109 +0,0 @@
-"""Shared resource boundaries for gateway stdlib HTTP services."""
-
-from __future__ import annotations
-
-import http.server
-import socket
-import threading
-import time
-from dataclasses import dataclass
-from typing import Any, Protocol
-
-
-class Readable(Protocol):
-    def read(self, size: int = -1, /) -> bytes: ...
-
-
-@dataclass(frozen=True)
-class BodyReadError(Exception):
-    status: int
-    message: str
-
-
-def read_declared_body(
-    stream: Readable,
-    connection: socket.socket,
-    raw_length: str | None,
-    *,
-    maximum: int,
-    timeout_seconds: float,
-    require_length: bool,
-) -> bytes:
-    """Validate and read exactly one declared body under a read deadline."""
-    if raw_length is None:
-        if require_length:
-            raise BodyReadError(411, "Content-Length required")
-        raw_length = "0"
-    try:
-        length = int(raw_length)
-    except ValueError as exc:
-        raise BodyReadError(400, "invalid Content-Length") from exc
-    if length < 0:
-        raise BodyReadError(400, "invalid Content-Length")
-    if length > maximum:
-        raise BodyReadError(413, "request body too large")
-    previous_timeout = connection.gettimeout()
-    deadline = time.monotonic() + timeout_seconds
-    chunks: list[bytes] = []
-    remaining = length
-    try:
-        while remaining:
-            timeout = deadline - time.monotonic()
-            if timeout <= 0:
-                raise BodyReadError(408, "request body read timed out")
-            connection.settimeout(timeout)
-            chunk = stream.read(min(remaining, 64 * 1024))
-            if not chunk:
-                raise BodyReadError(400, "incomplete request body")
-            chunks.append(chunk)
-            remaining -= len(chunk)
-    except TimeoutError as exc:
-        raise BodyReadError(408, "request body read timed out") from exc
-    finally:
-        connection.settimeout(previous_timeout)
-    return b"".join(chunks)
-
-
-class BoundedThreadingHTTPServer(http.server.ThreadingHTTPServer):
-    """ThreadingHTTPServer with a hard cap on in-flight request threads."""
-
-    daemon_threads = True
-
-    def __init__(  # pylint: disable=consider-using-with
-        self, *args, max_workers: int = 32, **kwargs,  # type: ignore[no-untyped-def]
-    ):
-        if max_workers < 1:
-            raise ValueError("max_workers must be positive")
-        self._request_slots = threading.BoundedSemaphore(max_workers)
-        super().__init__(*args, **kwargs)
-
-    def process_request(
-        self, request: Any, client_address: Any,
-    ) -> None:
-        if not self._request_slots.acquire(  # pylint: disable=consider-using-with
-            blocking=False,
-        ):
-            try:
-                request.sendall(
-                    b"HTTP/1.1 503 Service Unavailable\r\n"
-                    b"Content-Length: 0\r\nConnection: close\r\n\r\n"
-                )
-            finally:
-                self.shutdown_request(request)
-            return
-        try:
-            super().process_request(request, client_address)
-        except BaseException:
-            self._request_slots.release()
-            raise
-
-    def process_request_thread(
-        self, request: Any, client_address: Any,
-    ) -> None:
-        try:
-            super().process_request_thread(request, client_address)
-        finally:
-            self._request_slots.release()
-
-
-__all__ = ["BodyReadError", "BoundedThreadingHTTPServer", "read_declared_body"]

bot_bottle/gateway/egress/addon.py

@@ -16,7 +16,7 @@ import typing
 from mitmproxy import http  # type: ignore[import-not-found]  # pylint: disable=import-error
 
 from bot_bottle.constants import IDENTITY_HEADER
-from bot_bottle.gateway.egress.dlp_detectors import redact_tokens
+from bot_bottle.gateway.egress.dlp_detectors import redact_tokens, strip_crlf
 from bot_bottle.gateway.egress.dlp_config import (
     DEFAULT_OUTBOUND_ON_MATCH,
     ON_MATCH_BLOCK,
@@ -25,19 +25,19 @@ from bot_bottle.gateway.egress.dlp_config import (
 from bot_bottle.gateway.egress.context import resolve_client_context
 from bot_bottle.gateway.egress.dlp import (
     build_inbound_scan_text,
+    build_outbound_scan_text,
     build_token_allow_payload,
+    outbound_scan_headers,
     scan_inbound,
     scan_outbound,
 )
-from bot_bottle.gateway.egress.outbound_pipeline import redact_request, scan_request
 from bot_bottle.gateway.egress.matching import (
     decide,
+    decide_git_fetch,
+    is_git_fetch_request,
+    is_git_push_request,
     match_route,
 )
-from bot_bottle.gateway.egress.request_pipeline import (
-    evaluate_route_policy,
-    git_block_reason,
-)
 from bot_bottle.gateway.egress.schema import route_to_yaml_dict
 from bot_bottle.gateway.egress.types import (
     LOG_BLOCKS,
@@ -389,9 +389,19 @@ class EgressAddon:
         self._passthrough_conns.discard(conn_id)
 
     async def request(self, flow: http.HTTPFlow) -> None:
-        config, slug, env = self._request_context(flow)
         request_path, _, query = flow.request.path.partition("?")
 
+        # Reuse the context stashed by http_connect for HTTPS flows (one
+        # orchestrator round-trip per connection). Plain-HTTP flows have no
+        # prior CONNECT stash, so resolve now and stash for response/websocket.
+        meta = getattr(flow, "metadata", None)
+        if isinstance(meta, dict) and _FLOW_CTX_KEY in meta:
+            config, slug, env = meta[_FLOW_CTX_KEY]
+            self._request_token(flow)  # strip identity headers; token already resolved
+        else:
+            config, slug, env = self._resolve_flow(flow)
+            self._stash_flow_ctx(flow, config, slug, env)
+
         # Introspection ("_egress.local/allowlist") reports the calling bottle's
         # own resolved routes — served after resolution so it reflects this
         # bottle's policy, not a stale global.
@@ -412,66 +422,56 @@ class EgressAddon:
             # the path/query the git checks below rely on.
             request_path, _, query = flow.request.path.partition("?")
 
-        if not self._allow_git_request(flow, config, request_path, query):
+        if is_git_push_request(request_path, query):
+            self._block(
+                flow,
+                "egress: git push over HTTPS is not supported; "
+                "use the bottle.git SSH path (gitleaks-scanned by "
+                "git-gate's pre-receive hook).",
+                ctx=self._req_ctx(flow),
+            )
             return
 
-        self._apply_route_policy(flow, config, route, request_path, env)
+        if is_git_fetch_request(request_path, query):
+            git_decision = decide_git_fetch(
+                config.routes, flow.request.pretty_host,
+            )
+            if git_decision.action == "block":
+                self._block(
+                    flow,
+                    git_decision.reason,
+                    ctx=self._req_ctx(flow),
+                )
+                return
 
-    def _request_context(
-        self, flow: http.HTTPFlow,
-    ) -> tuple[Config, str, "typing.Mapping[str, str]"]:
-        """Resolve one bottle context, reusing the HTTPS CONNECT snapshot."""
-        meta = getattr(flow, "metadata", None)
-        if isinstance(meta, dict) and _FLOW_CTX_KEY in meta:
-            config, slug, env = meta[_FLOW_CTX_KEY]
-            self._request_token(flow)
-            return config, slug, env
-        config, slug, env = self._resolve_flow(flow)
-        self._stash_flow_ctx(flow, config, slug, env)
-        return config, slug, env
-
-    def _allow_git_request(
-        self, flow: http.HTTPFlow, config: Config,
-        request_path: str, query: str,
-    ) -> bool:
-        """Apply the HTTPS Git push/fetch boundary before general routing."""
-        reason = git_block_reason(
-            config.routes, flow.request.pretty_host, request_path, query,
-        )
-        if not reason:
-            return True
-        self._block(flow, reason, ctx=self._req_ctx(flow))
-        return False
-
-    def _apply_route_policy(
-        self, flow: http.HTTPFlow, config: Config, route: Route | None,
-        request_path: str, env: "typing.Mapping[str, str]",
-    ) -> None:
-        """Strip agent auth, evaluate the route, then inject gateway auth."""
         # Strip agent-set Authorization after DLP scan so smuggled tokens
         # are caught above; the route may inject gateway-owned auth below.
         # Routes with preserve_auth=True pass the header through as-is so the
         # agent's own credentials (e.g. registry bearer tokens) reach the upstream.
-        result = evaluate_route_policy(
-            config,
-            route,
-            host=flow.request.pretty_host,
-            request_path=request_path,
-            method=flow.request.method,
-            headers=dict(flow.request.headers),
-            env=env,
-        )
-        if result.strip_authorization:
+        if route is None or not route.preserve_auth:
             flow.request.headers.pop("authorization", None)
 
-        if result.block_reason:
-            self._block(flow, result.block_reason, ctx=self._req_ctx(flow))
+        # Build headers mapping for match evaluation
+        req_headers = {k.lower(): v for k, v in flow.request.headers.items()}
+
+        decision = decide(
+            config.routes,
+            flow.request.pretty_host,
+            request_path,
+            env,
+            request_method=flow.request.method,
+            request_headers=req_headers,
+            deny_reason=config.deny_reason,
+        )
+
+        if decision.action == "block":
+            self._block(flow, decision.reason, ctx=self._req_ctx(flow))
             return
 
-        if result.inject_authorization is not None:
-            flow.request.headers["authorization"] = result.inject_authorization
+        if decision.inject_authorization is not None:
+            flow.request.headers["authorization"] = decision.inject_authorization
 
-        if result.log_request:
+        if config.log >= LOG_FULL:
             self._log_request(flow, env)
 
     def _block_dlp(self, flow: http.HTTPFlow, result: ScanResult) -> None:
@@ -495,12 +495,20 @@ class EgressAddon:
         Loops so the supervise policy can re-scan after each approval — a
         second, un-approved token in the same request is still caught."""
         while True:
-            request_path, _, _ = flow.request.path.partition("?")
-            result = scan_request(
-                flow.request,
-                route,
-                env,
-                safe_tokens=self._safe_tokens_for(slug),
+            request_path, _, query = flow.request.path.partition("?")
+            body = flow.request.get_text(strict=False) or ""
+            headers = outbound_scan_headers(route, dict(flow.request.headers))
+            scan_text = build_outbound_scan_text(
+                flow.request.pretty_host, request_path, query, headers, body,
+            )
+            # CRLF is scanned only over the request line + headers, never the
+            # body (see scan_outbound) — a body is not an injection vector.
+            crlf_text = build_outbound_scan_text(
+                flow.request.pretty_host, request_path, query, headers, "",
+            )
+            result = scan_outbound(
+                route, scan_text, env,
+                safe_tokens=self._safe_tokens_for(slug), crlf_text=crlf_text,
             )
             if result is None or result.severity != "block":
                 return True
@@ -510,7 +518,7 @@ class EgressAddon:
             # redact scrubs every detection (tokens and structural CRLF) and
             # forwards; it fails closed only if a match survives the scrub.
             if policy == ON_MATCH_REDACT:
-                if redact_request(flow.request, route, env):
+                if self._redact_outbound(flow, route, env):
                     if self._flow_log(flow) >= LOG_BLOCKS:
                         sys.stderr.write(json.dumps({
                             "event": "egress_redacted",
@@ -543,6 +551,41 @@ class EgressAddon:
                 return False  # _supervise_token_block wrote the 403 response
             # loop: the approved value is now in safe_tokens; re-scan.
 
+    def _redact_outbound(
+        self, flow: http.HTTPFlow, route: Route, env: "typing.Mapping[str, str]",
+    ) -> bool:
+        """Scrub detected tokens (and CRLF injection sequences) from the mutable
+        request surfaces (body, headers, path/query) and re-scan. `env` is the
+        per-bottle env overlay. Returns True if the request is now clean; False
+        if a block-severity match remains on a surface redaction cannot rewrite
+        (the hostname) so the caller fails closed."""
+        body = flow.request.get_text(strict=False)
+        if body:
+            redacted_body = redact_tokens(body, env=env)
+            if redacted_body != body:
+                flow.request.text = redacted_body
+        for name, value in list(flow.request.headers.items()):
+            if name.lower() == "host":
+                continue  # routing-critical; never a legitimate token
+            redacted = strip_crlf(redact_tokens(value, env=env))
+            if redacted != value:
+                flow.request.headers[name] = redacted
+        redacted_path = strip_crlf(redact_tokens(flow.request.path, env=env))
+        if redacted_path != flow.request.path:
+            flow.request.path = redacted_path
+
+        request_path, _, query = flow.request.path.partition("?")
+        new_body = flow.request.get_text(strict=False) or ""
+        headers = outbound_scan_headers(route, dict(flow.request.headers))
+        scan_text = build_outbound_scan_text(
+            flow.request.pretty_host, request_path, query, headers, new_body,
+        )
+        crlf_text = build_outbound_scan_text(
+            flow.request.pretty_host, request_path, query, headers, "",
+        )
+        result = scan_outbound(route, scan_text, env, crlf_text=crlf_text)
+        return result is None or result.severity != "block"
+
     async def _supervise_token_block(
         self,
         flow: http.HTTPFlow,

bot_bottle/gateway/egress/outbound_pipeline.py

@@ -1,83 +0,0 @@
-"""Outbound DLP request scanning and redaction for the egress pipeline."""
-
-from __future__ import annotations
-
-from typing import ItemsView, Mapping, Protocol
-
-from .dlp import (
-    build_outbound_scan_text,
-    outbound_scan_headers,
-    scan_outbound,
-)
-from .dlp_detectors import redact_tokens, strip_crlf
-from .types import Route, ScanResult
-
-
-class MutableHeaders(Protocol):
-    def items(self) -> ItemsView[str, str]: ...
-    def __getitem__(self, name: str, /) -> str: ...
-    def __setitem__(self, name: str, value: str, /) -> None: ...
-
-
-class MutableRequest(Protocol):
-    pretty_host: str
-    path: str
-    headers: MutableHeaders
-    text: str
-
-    def get_text(self, strict: bool = False) -> str | None: ...
-
-
-def scan_request(
-    request: MutableRequest,
-    route: Route,
-    env: Mapping[str, str],
-    *,
-    safe_tokens: set[str] | None = None,
-) -> ScanResult | None:
-    """Scan all mutable outbound request surfaces in their canonical order."""
-    request_path, _, query = request.path.partition("?")
-    headers = outbound_scan_headers(route, dict(request.headers.items()))
-    body = request.get_text(strict=False) or ""
-    scan_text = build_outbound_scan_text(
-        request.pretty_host, request_path, query, headers, body,
-    )
-    # Bodies cannot alter HTTP framing, so CRLF detection is deliberately
-    # restricted to the request line and headers.
-    crlf_text = build_outbound_scan_text(
-        request.pretty_host, request_path, query, headers, "",
-    )
-    return scan_outbound(
-        route,
-        scan_text,
-        env,
-        safe_tokens=safe_tokens,
-        crlf_text=crlf_text,
-    )
-
-
-def redact_request(
-    request: MutableRequest,
-    route: Route,
-    env: Mapping[str, str],
-) -> bool:
-    """Redact mutable request surfaces and return whether the result is clean."""
-    body = request.get_text(strict=False)
-    if body:
-        redacted_body = redact_tokens(body, env=env)
-        if redacted_body != body:
-            request.text = redacted_body
-    for name, value in list(request.headers.items()):
-        if name.lower() == "host":
-            continue
-        redacted = strip_crlf(redact_tokens(value, env=env))
-        if redacted != value:
-            request.headers[name] = redacted
-    redacted_path = strip_crlf(redact_tokens(request.path, env=env))
-    if redacted_path != request.path:
-        request.path = redacted_path
-    result = scan_request(request, route, env)
-    return result is None or result.severity != "block"
-
-
-__all__ = ["MutableRequest", "redact_request", "scan_request"]

bot_bottle/gateway/egress/request_pipeline.py

@@ -1,92 +0,0 @@
-"""Framework-neutral request policy stages for the egress adapter.
-
-The mitmproxy addon owns flow mutation and response construction. This module
-owns the ordered Git and route-policy decisions so those rules remain directly
-testable without a live proxy flow.
-"""
-
-from __future__ import annotations
-
-from dataclasses import dataclass
-from typing import Mapping, Sequence
-
-from .matching import (
-    decide,
-    decide_git_fetch,
-    is_git_fetch_request,
-    is_git_push_request,
-)
-from .types import LOG_FULL, Config, Route
-
-GIT_PUSH_BLOCK_REASON = (
-    "egress: git push over HTTPS is not supported; "
-    "use the bottle.git SSH path (gitleaks-scanned by "
-    "git-gate's pre-receive hook)."
-)
-
-
-@dataclass(frozen=True)
-class RoutePolicyResult:
-    """The flow mutations and outcome produced by general route policy."""
-
-    block_reason: str = ""
-    strip_authorization: bool = False
-    inject_authorization: str | None = None
-    log_request: bool = False
-
-
-def git_block_reason(
-    routes: Sequence[Route],
-    host: str,
-    request_path: str,
-    query: str,
-) -> str:
-    """Return the HTTPS Git policy denial, or ``""`` when allowed."""
-    if is_git_push_request(request_path, query):
-        return GIT_PUSH_BLOCK_REASON
-    if not is_git_fetch_request(request_path, query):
-        return ""
-    decision = decide_git_fetch(routes, host)
-    return decision.reason if decision.action == "block" else ""
-
-
-def evaluate_route_policy(
-    config: Config,
-    route: Route | None,
-    *,
-    host: str,
-    request_path: str,
-    method: str,
-    headers: Mapping[str, str],
-    env: Mapping[str, str],
-) -> RoutePolicyResult:
-    """Evaluate authorization stripping, matching, injection, and logging."""
-    strip_authorization = route is None or not route.preserve_auth
-    effective_headers = {
-        name.lower(): value
-        for name, value in headers.items()
-        if not (strip_authorization and name.lower() == "authorization")
-    }
-    decision = decide(
-        config.routes,
-        host,
-        request_path,
-        env,
-        request_method=method,
-        request_headers=effective_headers,
-        deny_reason=config.deny_reason,
-    )
-    return RoutePolicyResult(
-        block_reason=decision.reason if decision.action == "block" else "",
-        strip_authorization=strip_authorization,
-        inject_authorization=decision.inject_authorization,
-        log_request=config.log >= LOG_FULL,
-    )
-
-
-__all__ = [
-    "GIT_PUSH_BLOCK_REASON",
-    "RoutePolicyResult",
-    "evaluate_route_policy",
-    "git_block_reason",
-]

bot_bottle/gateway/git_gate/http_backend.py

@@ -22,16 +22,11 @@ import os
 import subprocess
 import sys
 import typing
-from http.server import BaseHTTPRequestHandler
+from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
 from pathlib import Path
 from urllib.parse import urlsplit
 
 from bot_bottle.constants import GIT_GATE_TIMEOUT_SECS, IDENTITY_HEADER
-from bot_bottle.gateway.bounded_http import (
-    BodyReadError,
-    BoundedThreadingHTTPServer,
-    read_declared_body,
-)
 from bot_bottle.gateway.policy_resolver import PolicyResolveError, PolicyResolver
 
 
@@ -82,8 +77,6 @@ def resolve_sandbox_root(
 
 # Bound memory use while still allowing ordinary git push packfiles.
 MAX_BODY_BYTES = 100 * 1024 * 1024
-REQUEST_BODY_TIMEOUT_SECONDS = 30.0
-MAX_REQUEST_WORKERS = 16
 
 
 class GitHttpHandler(BaseHTTPRequestHandler):
@@ -191,18 +184,19 @@ class GitHttpHandler(BaseHTTPRequestHandler):
             value = self.headers.get(header)
             if value:
                 env[variable] = value
+        raw_length = self.headers.get("content-length", "0") or "0"
         try:
-            body = read_declared_body(
-                self.rfile,
-                self.connection,
-                self.headers.get("content-length"),
-                maximum=MAX_BODY_BYTES,
-                timeout_seconds=REQUEST_BODY_TIMEOUT_SECONDS,
-                require_length=False,
-            )
-        except BodyReadError as exc:
-            self.send_error(exc.status, exc.message)
+            length = int(raw_length)
+        except ValueError:
+            self.send_error(400, "Bad Content-Length")
             return
+        if length < 0:
+            self.send_error(400, "Negative Content-Length")
+            return
+        if length > MAX_BODY_BYTES:
+            self.send_error(413, "Request body too large")
+            return
+        body = self.rfile.read(length) if length else b""
         proc = subprocess.run(
             ["git", "http-backend"],
             input=body,
@@ -279,9 +273,7 @@ def main() -> int:
             "(no single-tenant flat-root fallback)\n"
         )
         return 1
-    server = BoundedThreadingHTTPServer(
-        ("0.0.0.0", port), GitHttpHandler, max_workers=MAX_REQUEST_WORKERS,
-    )
+    server = ThreadingHTTPServer(("0.0.0.0", port), GitHttpHandler)
     # Resolve each request's sandbox namespace by source IP against the
     # orchestrator control plane.
     server.policy_resolver = PolicyResolver(orch_url)  # type: ignore[attr-defined]

bot_bottle/gateway/supervisor/mcp_dispatch.py

@@ -1,92 +0,0 @@
-"""Framework-neutral MCP method and tool dispatch."""
-
-from __future__ import annotations
-
-import json
-from dataclasses import dataclass
-from typing import Callable, Protocol
-
-from bot_bottle.gateway.egress.schema import load_config, route_to_yaml_dict
-from bot_bottle.gateway.policy_resolver import PolicyResolveError, PolicyResolver
-from bot_bottle.supervisor import types as _sv
-
-
-class Request(Protocol):
-    @property
-    def method(self) -> str: ...
-
-    @property
-    def params(self) -> dict[str, object]: ...
-
-
-class MethodNotFoundError(Exception):
-    """Raised when a JSON-RPC method has no MCP handler."""
-
-
-class RouteResolutionError(Exception):
-    """The caller's live route table could not be resolved authoritatively."""
-
-
-Handler = Callable[[dict[str, object]], object]
-
-
-@dataclass(frozen=True)
-class Handlers:
-    initialize: Handler
-    tools_list: Handler
-    list_routes: Handler
-    check_proposal: Handler
-    propose: Handler
-
-
-def dispatch(request: Request, handlers: Handlers) -> object:
-    """Route one parsed request without depending on the HTTP server."""
-    if request.method == "initialize":
-        return handlers.initialize(request.params)
-    if request.method == "notifications/initialized":
-        return None
-    if request.method == "tools/list":
-        return handlers.tools_list(request.params)
-    if request.method != "tools/call":
-        raise MethodNotFoundError(request.method)
-
-    tool = request.params.get("name")
-    if tool == _sv.TOOL_LIST_EGRESS_ROUTES:
-        return handlers.list_routes(request.params)
-    if tool == _sv.TOOL_CHECK_PROPOSAL:
-        return handlers.check_proposal(request.params)
-    return handlers.propose(request.params)
-
-
-def resolved_routes_payload(
-    resolver: PolicyResolver,
-    source_ip: str,
-    identity_token: str,
-) -> dict[str, object]:
-    """Render an authoritatively resolved route table for the calling bottle."""
-    try:
-        policy, bottle_id, _tokens = resolver.resolve_policy_and_bottle_id(
-            source_ip, identity_token,
-        )
-    except PolicyResolveError as exc:
-        raise RouteResolutionError("orchestrator unavailable") from exc
-    if not bottle_id:
-        raise RouteResolutionError("request source is not attributed to a bottle")
-    try:
-        config = load_config(policy or "")
-    except ValueError as exc:
-        raise RouteResolutionError("resolved policy is invalid") from exc
-    body = json.dumps(
-        {"routes": [route_to_yaml_dict(route) for route in config.routes]},
-        indent=2,
-    )
-    return {"content": [{"type": "text", "text": body}], "isError": False}
-
-
-__all__ = [
-    "Handlers",
-    "MethodNotFoundError",
-    "RouteResolutionError",
-    "dispatch",
-    "resolved_routes_payload",
-]

bot_bottle/gateway/supervisor/server.py

@@ -51,27 +51,17 @@ from __future__ import annotations
 import http.server
 import json
 import os
+import socketserver
 import sys
 import time
 import typing
 from dataclasses import dataclass
 
 from bot_bottle.constants import IDENTITY_HEADER
-from bot_bottle.gateway.bounded_http import (
-    BodyReadError,
-    BoundedThreadingHTTPServer,
-    read_declared_body,
-)
-from bot_bottle.gateway.egress.schema import load_config
+from bot_bottle.gateway.egress.context import resolve_client_context
+from bot_bottle.gateway.egress.schema import load_config, route_to_yaml_dict
 from bot_bottle.gateway.egress.types import LOG_OFF
 from bot_bottle.gateway.policy_resolver import PolicyResolveError, PolicyResolver
-from bot_bottle.gateway.supervisor.mcp_dispatch import (
-    Handlers as DispatchHandlers,
-    MethodNotFoundError,
-    RouteResolutionError,
-    dispatch,
-    resolved_routes_payload,
-)
 from bot_bottle.supervisor import types as _sv
 
 
@@ -575,8 +565,6 @@ def format_unknown_proposal_text(proposal_id: str) -> str:
 # Max request body the server accepts. 1 MB is well above any realistic
 # routes.yaml proposal.
 MAX_BODY_BYTES = 1 * 1024 * 1024
-REQUEST_BODY_TIMEOUT_SECONDS = 10.0
-MAX_REQUEST_WORKERS = 32
 
 
 class MCPHandler(http.server.BaseHTTPRequestHandler):
@@ -599,18 +587,19 @@ class MCPHandler(http.server.BaseHTTPRequestHandler):
         self._write_text(405, "use POST for MCP requests\n")
 
     def do_POST(self) -> None:
-        try:
-            body = read_declared_body(
-                self.rfile,
-                self.connection,
-                self.headers.get("Content-Length"),
-                maximum=MAX_BODY_BYTES,
-                timeout_seconds=REQUEST_BODY_TIMEOUT_SECONDS,
-                require_length=True,
-            )
-        except BodyReadError as exc:
-            self._write_text(exc.status, exc.message + "\n")
+        length_header = self.headers.get("Content-Length")
+        if length_header is None:
+            self._write_text(411, "Content-Length required\n")
             return
+        try:
+            length = int(length_header)
+        except ValueError:
+            self._write_text(400, "invalid Content-Length\n")
+            return
+        if length < 0 or length > MAX_BODY_BYTES:
+            self._write_text(413, "request body too large\n")
+            return
+        body = self.rfile.read(length)
 
         try:
             req = parse_jsonrpc(body)
@@ -622,11 +611,6 @@ class MCPHandler(http.server.BaseHTTPRequestHandler):
 
         try:
             result = self._dispatch(req, config)
-        except MethodNotFoundError as e:
-            self._write_jsonrpc(
-                jsonrpc_error(req.id, ERR_METHOD_NOT_FOUND, f"method not found: {e}"),
-            )
-            return
         except _RpcClientError as e:
             self._write_jsonrpc(jsonrpc_error(req.id, e.code, e.message))
             return
@@ -649,42 +633,41 @@ class MCPHandler(http.server.BaseHTTPRequestHandler):
         self._write_jsonrpc(jsonrpc_result(req.id, result))
 
     def _dispatch(self, req: JsonRpcRequest, config: ServerConfig) -> object:
-        def check(params: dict[str, object]) -> object:
-            return handle_check_proposal(
-                params,
-                resolver=self._resolver_or_fail(),
-                source_ip=self.client_address[0],
-                identity_token=self._identity_token(),
-            )
-
-        def propose(params: dict[str, object]) -> object:
-            return handle_tools_call(
-                params,
-                config,
-                resolver=self._resolver_or_fail(),
-                source_ip=self.client_address[0],
-                identity_token=self._identity_token(),
-            )
-
-        def list_routes(_params: dict[str, object]) -> object:
-            try:
-                return resolved_routes_payload(
-                    self._resolver_or_fail(),
-                    self.client_address[0],
-                    self._identity_token(),
+        method = req.method
+        if method == "initialize":
+            return handle_initialize(req.params)
+        if method == "notifications/initialized":
+            return None  # ack-only
+        if method == "tools/list":
+            return handle_tools_list(req.params)
+        if method == "tools/call":
+            # `list-egress-routes` is read-only introspection. The shared gateway
+            # has no static route table (routes are resolved per request by
+            # source IP), so answer it from the calling bottle's resolved policy.
+            # Otherwise the agent sees an empty allowlist and composes an egress
+            # proposal that *replaces* the live routes instead of extending them
+            # — silently dropping base routes like api.anthropic.com on approval.
+            if req.params.get("name") == _sv.TOOL_LIST_EGRESS_ROUTES:
+                return self._resolved_routes_payload()
+            resolver = self._resolver_or_fail()
+            source_ip = self.client_address[0]
+            token = self._identity_token()
+            # `check-proposal` is a non-blocking read of the calling bottle's
+            # own queue — attributed by (source_ip, identity_token) like a
+            # proposal, but it never queues or blocks.
+            if req.params.get("name") == _sv.TOOL_CHECK_PROPOSAL:
+                return handle_check_proposal(
+                    req.params, resolver=resolver,
+                    source_ip=source_ip, identity_token=token,
                 )
-            except RouteResolutionError as exc:
-                raise _RpcInternalError(
-                    f"could not resolve live egress routes: {exc}"
-                ) from exc
-
-        return dispatch(req, DispatchHandlers(
-            initialize=handle_initialize,
-            tools_list=handle_tools_list,
-            list_routes=list_routes,
-            check_proposal=check,
-            propose=propose,
-        ))
+            # The control plane attributes the proposal to the source-IP + token
+            # resolved bottle, so the one shared queue holds each bottle's
+            # proposal under its own id — no slug is asserted by this daemon.
+            return handle_tools_call(
+                req.params, config, resolver=resolver,
+                source_ip=source_ip, identity_token=token,
+            )
+        raise _RpcClientError(ERR_METHOD_NOT_FOUND, f"method not found: {method}")
 
     def _identity_token(self) -> str:
         """The agent's per-bottle identity token from the request header (the
@@ -703,6 +686,20 @@ class MCPHandler(http.server.BaseHTTPRequestHandler):
             raise _RpcInternalError("supervise server has no policy resolver")
         return resolver
 
+    def _resolved_routes_payload(self) -> dict[str, object]:
+        """The calling bottle's live egress routes as the `list-egress-routes`
+        JSON payload, resolved by (source_ip, identity token). Fail-closed: an
+        unattributed source or an unreachable orchestrator yields an empty route
+        list (never another bottle's), courtesy of `resolve_client_context`."""
+        resolver = self._resolver_or_fail()
+        conf, _slug, _tokens = resolve_client_context(
+            resolver, self.client_address[0], self._identity_token(),
+        )
+        body = json.dumps(
+            {"routes": [route_to_yaml_dict(r) for r in conf.routes]}, indent=2,
+        )
+        return {"content": [{"type": "text", "text": body}], "isError": False}
+
     def _write_jsonrpc(self, body: bytes) -> None:
         self.send_response(200)
         self.send_header("Content-Type", "application/json")
@@ -722,7 +719,7 @@ class MCPHandler(http.server.BaseHTTPRequestHandler):
             self.wfile.write(encoded)
 
 
-class MCPServer(BoundedThreadingHTTPServer):
+class MCPServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
     allow_reuse_address = True
     daemon_threads = True
     config: ServerConfig = ServerConfig()
@@ -731,9 +728,6 @@ class MCPServer(BoundedThreadingHTTPServer):
     # closed per request (see `_resolver_or_fail`).
     policy_resolver: "PolicyResolver | None" = None
 
-    def __init__(self, *args, **kwargs):  # type: ignore[no-untyped-def]
-        super().__init__(*args, max_workers=MAX_REQUEST_WORKERS, **kwargs)
-
 
 # --- Entry point -----------------------------------------------------------
 

bot_bottle/orchestrator/__init__.py

@@ -44,7 +44,7 @@ if TYPE_CHECKING:
     from ..gateway import Gateway, GatewayError
     from .lifecycle import Orchestrator
     from .service import OrchestratorCore
-    from .server import OrchestratorServer, create_app, make_server
+    from .server import OrchestratorServer, dispatch, make_server
 
 
 # Facade name -> submodule that defines it. Lazy so importing a leaf (or the
@@ -67,8 +67,8 @@ _LAZY: dict[str, str] = {
     "GatewayError": "..gateway",
     "Orchestrator": ".lifecycle",
     "OrchestratorCore": ".service",
-    "create_app": ".server",
     "OrchestratorServer": ".server",
+    "dispatch": ".server",
     "make_server": ".server",
 }
 
@@ -100,7 +100,7 @@ __all__ = [
     "GatewayError",
     "Orchestrator",
     "OrchestratorCore",
-    "create_app",
     "OrchestratorServer",
+    "dispatch",
     "make_server",
 ]

bot_bottle/orchestrator/__main__.py

@@ -1,7 +1,6 @@
 """Run the orchestrator control plane as a plain process (PRD 0070 dev-harness).
 
-    BOT_BOTTLE_ORCHESTRATOR_TOKEN=<signing-key> \
-        python -m bot_bottle.orchestrator [--host H] [--port P] [--db PATH]
+    python -m bot_bottle.orchestrator [--host H] [--port P] [--db PATH]
 
 The PRD sequences the orchestrator as a plain-process dev-harness first, so
 the consolidation core (registry + attribution + HTTP control plane + live
@@ -17,13 +16,15 @@ import secrets
 from pathlib import Path
 
 from .. import log
-from ..trust_domain import CONTROL_PLANE
-from .broker import LaunchBroker, StubBroker
-from .docker_broker import DockerBroker
-from .server import make_server
-from .service import OrchestratorCore
 from .store.store_manager import StoreManager
+from ..paths import LAUNCH_BROKER_KEY_ENV
+from .broker import StubBroker, SubmitBroker
+from .broker_client import BrokerClient
+from .host_server import DEFAULT_PORT, broker_secret
+from .server import make_server
+from .docker_broker import DockerBroker
 from .store.registry_store import RegistryStore, default_db_path
+from .service import OrchestratorCore
 
 
 def main(argv: list[str] | None = None) -> int:
@@ -36,15 +37,15 @@ def main(argv: list[str] | None = None) -> int:
         help=f"registry DB path (default: {default_db_path()})",
     )
     parser.add_argument(
-        "--broker", choices=("stub", "docker"), default="stub",
-        help="launch broker: 'stub' records requests; 'docker' runs containers",
+        "--broker", choices=("stub", "docker", "http"), default="stub",
+        help="launch broker: 'stub' records requests; 'docker' runs containers "
+             "in-process; 'http' relays signed requests to a host control server",
+    )
+    parser.add_argument(
+        "--host-controller-url", default=f"http://127.0.0.1:{DEFAULT_PORT}",
+        help="host control server URL (used only with --broker http)",
     )
     args = parser.parse_args(argv)
-    if not CONTROL_PLANE.key_from_env():
-        log.die(
-            f"{CONTROL_PLANE.key_env} is required; refusing to start the "
-            "orchestrator without caller authentication"
-        )
 
     registry = RegistryStore(args.db)
     registry.migrate()
@@ -54,22 +55,41 @@ def main(argv: list[str] | None = None) -> int:
     # operator reaches it over HTTP (never a second, disconnected DB).
     StoreManager(registry.db_path).migrate()
 
-    # An ephemeral signing secret ties the orchestrator (signer) to its
-    # broker (verifier). 'stub' records launches instead of starting
-    # anything; 'docker' runs real containers (firecracker drops in later).
-    secret = secrets.token_bytes(32)
-    broker: LaunchBroker = DockerBroker(secret) if args.broker == "docker" else StubBroker(secret)
+    # A signing secret ties the orchestrator (signer) to its broker (verifier).
+    # 'stub' records launches instead of starting anything; 'docker' runs real
+    # containers in-process; 'http' relays signed requests to a separate host
+    # control server, which verifies and launches. For 'stub'/'docker' the secret
+    # is ephemeral (signer and verifier share this process). For 'http' it must be
+    # the SAME key the host controller holds — and this process is the *guest*
+    # (signer), so it must be given that key by injection, NOT mint its own
+    # process-local one (which would diverge from the host's and 401 every launch).
+    broker: SubmitBroker
+    if args.broker == "http":
+        secret = broker_secret()  # env-injected only; no host-file fallback here
+        if secret is None:
+            parser.error(
+                f"--broker http requires the launch-broker key injected as "
+                f"${LAUNCH_BROKER_KEY_ENV} (the host controller owns/mints it); the "
+                "orchestrator must not mint its own or it would diverge from the host's"
+            )
+        broker = BrokerClient(args.host_controller_url)
+    else:
+        secret = secrets.token_bytes(32)
+        broker = DockerBroker(secret) if args.broker == "docker" else StubBroker(secret)
     orchestrator = OrchestratorCore(registry, broker, secret)
 
     server = make_server(orchestrator, host=args.host, port=args.port)
+    bound_host, bound_port = server.server_address[0], server.server_address[1]
     log.info(
         "orchestrator control plane listening",
-        context={"host": args.host, "port": args.port, "db": str(registry.db_path)},
+        context={"host": bound_host, "port": bound_port, "db": str(registry.db_path)},
     )
     try:
-        server.run()
+        server.serve_forever()
     except KeyboardInterrupt:
         log.info("orchestrator shutting down")
+    finally:
+        server.server_close()
     return 0
 
 

bot_bottle/orchestrator/api.py

@@ -1,339 +0,0 @@
-"""FastAPI control-plane routes for the orchestrator."""
-# pyright: reportUnusedFunction=false
-
-from __future__ import annotations
-
-import asyncio
-import math
-import sys
-from fastapi import FastAPI, HTTPException
-from fastapi.responses import JSONResponse
-from pydantic import BaseModel, ConfigDict, StrictStr
-from starlette.types import ASGIApp, Message, Receive, Scope, Send
-
-from ..orchestrator_auth import ROLE_CLI, ROLES
-from ..supervisor.types import TOOLS
-from ..trust_domain import CONTROL_PLANE
-from .http_contract import (
-    MAX_BODY_BYTES,
-    ORCHESTRATOR_AUTH_HEADER,
-    REQUEST_BODY_TIMEOUT_SECONDS,
-)
-from .service import OrchestratorCore
-
-_GATEWAY_ROUTES = frozenset({
-    ("POST", "/resolve"),
-    ("POST", "/supervise/propose"),
-    ("POST", "/supervise/poll"),
-})
-
-
-class _StrictModel(BaseModel):
-    model_config = ConfigDict(extra="ignore", strict=True)
-
-
-class LaunchBody(_StrictModel):
-    source_ip: StrictStr
-    image_ref: StrictStr = ""
-    metadata: StrictStr = ""
-    policy: StrictStr = ""
-    tokens: dict[StrictStr, StrictStr] = {}
-    env_var_secret: StrictStr = ""
-
-
-class PolicyBody(_StrictModel):
-    policy: StrictStr
-
-
-class ReprovisionBody(_StrictModel):
-    env_var_secret: StrictStr
-
-
-class ReconcileBody(_StrictModel):
-    live_source_ips: list[StrictStr]
-    grace_seconds: float | None = None
-
-
-class IdentityBody(_StrictModel):
-    source_ip: StrictStr
-    identity_token: StrictStr = ""
-
-
-class AttributeBody(_StrictModel):
-    source_ip: StrictStr
-    identity_token: StrictStr
-
-
-class RespondBody(_StrictModel):
-    proposal_id: StrictStr
-    bottle_slug: StrictStr
-    decision: StrictStr
-    notes: StrictStr = ""
-    final_file: StrictStr | None = None
-
-
-class ProposeBody(IdentityBody):
-    tool: StrictStr
-    proposed_file: StrictStr
-    justification: StrictStr
-
-
-class PollBody(IdentityBody):
-    proposal_id: StrictStr
-
-
-class ControlPlaneBoundary:
-    """Reject unauthenticated and oversized requests before reading a body."""
-
-    def __init__(self, app: ASGIApp, signing_key: str) -> None:
-        self.app = app
-        self.signing_key = signing_key
-
-    async def __call__(self, scope: Scope, receive: Receive, send: Send) -> None:
-        if scope["type"] != "http":
-            await self.app(scope, receive, send)
-            return
-        method = scope["method"]
-        route = scope["path"].rstrip("/") or "/"
-        if not (method == "GET" and route == "/health"):
-            headers = dict(scope["headers"])
-            presented = headers.get(
-                ORCHESTRATOR_AUTH_HEADER.encode(), b"",
-            ).decode(errors="ignore")
-            role = CONTROL_PLANE.verify(presented, self.signing_key)
-            if role is None:
-                await self._reject(
-                    scope, send, 401, "control-plane authentication required",
-                )
-                return
-            allowed = ROLES if (method, route) in _GATEWAY_ROUTES else {ROLE_CLI}
-            if role not in allowed:
-                await self._reject(scope, send, 403, "insufficient role for this route")
-                return
-            scope.setdefault("state", {})["role"] = role
-        raw_length = dict(scope["headers"]).get(b"content-length")
-        if raw_length is not None:
-            try:
-                length = int(raw_length)
-            except ValueError:
-                await self._reject(scope, send, 400, "invalid Content-Length")
-                return
-            if length < 0:
-                await self._reject(scope, send, 400, "invalid Content-Length")
-                return
-            if length > MAX_BODY_BYTES:
-                await self._reject(scope, send, 413, "request body too large")
-                return
-        try:
-            body = await self._read_body(receive)
-        except _BodyTooLarge:
-            await self._reject(scope, send, 413, "request body too large")
-            return
-        except TimeoutError:
-            await self._reject(scope, send, 408, "request body read timed out")
-            return
-        try:
-            await self.app(scope, self._replay_body(body), send)
-        except Exception as exc:  # noqa: BLE001 - redact control-plane failures
-            sys.stderr.write(
-                f"orchestrator: {method} {route} failed "
-                f"[error_type={type(exc).__name__}]\n"
-            )
-            sys.stderr.flush()
-            await self._reject(scope, send, 500, "internal error")
-
-    @staticmethod
-    async def _reject(
-        scope: Scope, send: Send, status: int, error: str,
-    ) -> None:
-        response = JSONResponse({"error": error}, status_code=status)
-        await response(scope, ControlPlaneBoundary._empty_receive, send)
-
-    @staticmethod
-    async def _empty_receive() -> Message:
-        return {"type": "http.disconnect"}
-
-    @staticmethod
-    async def _read_body(receive: Receive) -> bytes:
-        body = bytearray()
-        async with asyncio.timeout(REQUEST_BODY_TIMEOUT_SECONDS):
-            while True:
-                message = await receive()
-                if message["type"] != "http.request":
-                    break
-                body.extend(message.get("body", b""))
-                if len(body) > MAX_BODY_BYTES:
-                    raise _BodyTooLarge
-                if not message.get("more_body", False):
-                    break
-        return bytes(body)
-
-    @staticmethod
-    def _replay_body(body: bytes) -> Receive:
-        sent = False
-
-        async def replay() -> Message:
-            nonlocal sent
-            if sent:
-                return {"type": "http.disconnect"}
-            sent = True
-            return {"type": "http.request", "body": body, "more_body": False}
-
-        return replay
-
-
-class _BodyTooLarge(Exception):
-    """The streamed request exceeded the control-plane body limit."""
-
-
-def _required(value: str, name: str) -> str:
-    if not value:
-        raise HTTPException(400, f"{name} (string) is required")
-    return value
-
-
-def create_app(orch: OrchestratorCore, *, signing_key: str) -> FastAPI:
-    """Build the authenticated orchestrator ASGI application."""
-    key = signing_key.strip()
-    if not key:
-        raise ValueError(
-            "orchestrator control-plane signing key is required; "
-            "refusing to start without caller authentication"
-        )
-    app = FastAPI(
-        title="bot-bottle orchestrator",
-        docs_url=None,
-        redoc_url=None,
-        openapi_url=None,
-    )
-    app.add_middleware(ControlPlaneBoundary, signing_key=key)
-
-    @app.get("/health")
-    def health() -> dict[str, str]:
-        return {"status": "ok"}
-
-    @app.get("/gateway")
-    def gateway() -> dict[str, object]:
-        return orch.gateway_status()
-
-    @app.get("/bottles")
-    def bottles() -> dict[str, object]:
-        return {"bottles": [record.redacted() for record in orch.registry.all()]}
-
-    @app.post("/bottles", status_code=201)
-    def launch(body: LaunchBody) -> dict[str, str]:
-        rec = orch.launch_bottle(
-            _required(body.source_ip, "source_ip"),
-            image_ref=body.image_ref,
-            metadata=body.metadata,
-            policy=body.policy,
-            tokens=dict(body.tokens),
-            env_var_secret=body.env_var_secret,
-        )
-        return {"bottle_id": rec.bottle_id, "identity_token": rec.identity_token}
-
-    @app.put("/bottles/{bottle_id}/policy")
-    def set_policy(bottle_id: str, body: PolicyBody) -> dict[str, object]:
-        if orch.set_policy(bottle_id, body.policy):
-            return {"updated": True}
-        raise HTTPException(404, "no such bottle")
-
-    @app.post("/bottles/{bottle_id}/reprovision_gateway")
-    def reprovision(bottle_id: str, body: ReprovisionBody) -> dict[str, object]:
-        secret = _required(body.env_var_secret, "env_var_secret")
-        if orch.reprovision_from_secret(bottle_id, secret):
-            return {"reprovisioned": True}
-        raise HTTPException(404, "no stored secrets for this bottle")
-
-    @app.delete("/bottles/{bottle_id}")
-    def teardown(bottle_id: str) -> dict[str, object]:
-        if orch.teardown_bottle(bottle_id):
-            return {"torn_down": True}
-        raise HTTPException(404, "no such bottle")
-
-    @app.post("/reconcile")
-    def reconcile(body: ReconcileBody) -> dict[str, object]:
-        if any(not ip for ip in body.live_source_ips):
-            raise HTTPException(400, "live_source_ips must contain non-empty strings")
-        kwargs: dict[str, float] = {}
-        if body.grace_seconds is not None:
-            if not math.isfinite(body.grace_seconds) or body.grace_seconds < 0:
-                raise HTTPException(
-                    400, "grace_seconds must be a non-negative finite number",
-                )
-            kwargs["grace_seconds"] = body.grace_seconds
-        return {"reaped": orch.reconcile(body.live_source_ips, **kwargs)}
-
-    @app.post("/attribute")
-    def attribute(body: AttributeBody) -> dict[str, str]:
-        rec = orch.attribute(body.source_ip, body.identity_token)
-        if rec is None:
-            raise HTTPException(403, "unattributed")
-        return {"bottle_id": rec.bottle_id}
-
-    @app.get("/supervise/proposals")
-    def proposals() -> dict[str, object]:
-        return {"proposals": orch.supervise_pending()}
-
-    @app.post("/supervise/respond")
-    def respond(body: RespondBody) -> dict[str, object]:
-        ok, error = orch.supervise_respond(
-            _required(body.proposal_id, "proposal_id"),
-            bottle_slug=_required(body.bottle_slug, "bottle_slug"),
-            decision=_required(body.decision, "decision"),
-            notes=body.notes,
-            final_file=body.final_file,
-        )
-        if not ok:
-            raise HTTPException(409, error)
-        return {"responded": True}
-
-    @app.post("/supervise/propose", status_code=201)
-    def propose(body: ProposeBody) -> dict[str, str]:
-        source_ip = _required(body.source_ip, "source_ip")
-        if body.tool not in TOOLS:
-            raise HTTPException(400, f"tool (string) must be one of {TOOLS}")
-        rec = orch.resolve(source_ip, body.identity_token)
-        if rec is None:
-            raise HTTPException(403, "unattributed")
-        proposal_id = orch.supervise_queue_proposal(
-            rec.bottle_id,
-            tool=body.tool,
-            proposed_file=_required(body.proposed_file, "proposed_file"),
-            justification=_required(body.justification, "justification"),
-        )
-        return {"proposal_id": proposal_id}
-
-    @app.post("/supervise/poll")
-    def poll(body: PollBody) -> dict[str, object]:
-        rec = orch.resolve(
-            _required(body.source_ip, "source_ip"), body.identity_token,
-        )
-        if rec is None:
-            raise HTTPException(403, "unattributed")
-        return orch.supervise_poll_response(
-            rec.bottle_id, _required(body.proposal_id, "proposal_id"),
-        )
-
-    @app.post("/resolve")
-    def resolve(body: IdentityBody) -> dict[str, object]:
-        rec = orch.resolve(
-            _required(body.source_ip, "source_ip"), body.identity_token,
-        )
-        if rec is None:
-            raise HTTPException(403, "unattributed")
-        return {
-            "bottle_id": rec.bottle_id,
-            "policy": rec.policy,
-            "tokens": orch.tokens_for(rec.bottle_id),
-        }
-
-    return app
-
-
-__all__ = [
-    "ControlPlaneBoundary",
-    "MAX_BODY_BYTES",
-    "ORCHESTRATOR_AUTH_HEADER",
-    "create_app",
-]

bot_bottle/orchestrator/broker.py

@@ -29,29 +29,71 @@ import json
 import secrets
 import time
 from dataclasses import dataclass
+from typing import Protocol
 
 _JWT_HEADER = {"alg": "HS256", "typ": "JWT"}
-_ALLOWED_OPS = ("launch", "teardown")
+
+# The closed op vocabulary, split by kind (PRD "ids + static flags" rule):
+#   * mutation ops act on ONE bottle — they carry its id (+ static launch flags);
+#   * query ops enumerate host state — they carry NO ids or flags at all.
+# Each new host-privileged op is added here deliberately; `verify_request`
+# enforces the per-kind shape so the privileged surface can't drift.
+_MUTATION_OPS = ("launch", "teardown")
+_QUERY_OPS = ("list_live",)
+_ALLOWED_OPS = _MUTATION_OPS + _QUERY_OPS
+
+# Every claim key a signed request may carry — the request fields plus the two
+# per-signature envelope claims. A strict allow-list (open question 1, resolved
+# "yes"): an unknown key is rejected outright, so the schema can't silently widen
+# as ops are added.
+_ALLOWED_CLAIMS = frozenset(
+    {"op", "bottle_id", "source_ip", "image_ref", "slot", "jti", "iat"}
+)
 
 
 class BrokerAuthError(Exception):
     """A broker request failed provenance or schema verification —
     bad/absent signature, malformed token, or a payload that doesn't match
-    the fixed launch-request shape. Fail-closed: the broker must not act."""
+    the fixed launch-request shape. Fail-closed: the broker must not act.
+
+    A **definite** negative: nothing was launched, so a caller may safely roll
+    back as if the op never happened."""
+
+
+class BrokerUnavailableError(Exception):
+    """A brokered request could not be carried to a verdict: the broker (or the
+    wire to it) was unreachable, timed out, or dropped the response.
+
+    Crucially **ambiguous** — unlike `BrokerAuthError`, the op MAY already have
+    taken effect on the backend before the response was lost, so a caller must
+    NOT assume it did nothing (e.g. must not roll a registry row back as if no
+    launch happened, which would orphan a running container). Only the in-process
+    brokers never raise this; the out-of-process `BrokerClient` does."""
 
 
 @dataclass(frozen=True)
-class LaunchRequest:
-    """The structured, un-coercible launch/teardown request. Ids + flags
-    only — `image_ref` is a content-addressed id, never a path/argv."""
+class BrokerRequest:
+    """A structured, un-coercible broker request. Ids + static flags only —
+    `image_ref` is a content-addressed id, never a path/argv.
+
+    A **mutation** op (`launch`/`teardown`) names the bottle it acts on in
+    `bottle_id` (plus launch's static flags). A **query** op (`list_live`) acts
+    on no single bottle, so it carries nothing but its `op` name — `bottle_id`
+    and every flag stay empty, and `verify_request` rejects a query that smuggles
+    any in. `LaunchRequest` is kept as an alias for the launch/teardown callers."""
 
     op: str  # one of _ALLOWED_OPS
-    bottle_id: str
+    bottle_id: str = ""
     source_ip: str = ""
     image_ref: str = ""
     slot: int | None = None
 
 
+# Historical name — the request type predates the query ops. Kept so the launch
+# path (`OrchestratorCore`, `DockerBroker`) reads unchanged.
+LaunchRequest = BrokerRequest
+
+
 # --- minimal JWS/JWT (HS256), stdlib only ----------------------------------
 
 def _b64url(data: bytes) -> str:
@@ -103,26 +145,55 @@ def verify_request(token: str, secret: bytes) -> LaunchRequest:
         raise BrokerAuthError("unexpected header/alg")
     if not isinstance(claims, dict):
         raise BrokerAuthError("claims are not an object")
+    # Strict schema (open question 1): a signed request may carry ONLY the known
+    # claim keys, so the privileged surface can't widen by smuggling an extra
+    # claim past the fixed field checks below.
+    unknown = set(claims) - _ALLOWED_CLAIMS
+    if unknown:
+        raise BrokerAuthError(f"unknown claim(s): {', '.join(sorted(unknown))}")
 
     op = claims.get("op")
-    bottle_id = claims.get("bottle_id")
+    if not isinstance(op, str) or op not in _ALLOWED_OPS:
+        raise BrokerAuthError("request does not match the broker-request schema")
+    bottle_id = claims.get("bottle_id", "")
     source_ip = claims.get("source_ip", "")
     image_ref = claims.get("image_ref", "")
     slot = claims.get("slot")
     if (
-        not isinstance(op, str) or op not in _ALLOWED_OPS
-        or not isinstance(bottle_id, str) or not bottle_id
+        not isinstance(bottle_id, str)
         or not isinstance(source_ip, str) or not isinstance(image_ref, str)
         or not (slot is None or isinstance(slot, int))
     ):
-        raise BrokerAuthError("request does not match the launch-request schema")
-    return LaunchRequest(
+        raise BrokerAuthError("request does not match the broker-request schema")
+    # Per-kind shape: a mutation names exactly one bottle; a query names none and
+    # carries no flags (the "no arguments" rule for `list_live`). Enforcing both
+    # halves keeps `bottle_id`/flags from being a coercible field on a query op.
+    if op in _MUTATION_OPS:
+        if not bottle_id:
+            raise BrokerAuthError(f"{op} requires a bottle_id")
+    elif bottle_id or source_ip or image_ref or slot is not None:
+        raise BrokerAuthError(f"{op} is a query op and takes no ids or flags")
+    return BrokerRequest(
         op=op, bottle_id=bottle_id, source_ip=source_ip, image_ref=image_ref, slot=slot
     )
 
 
 # --- the broker itself ------------------------------------------------------
 
+class SubmitBroker(Protocol):
+    """The broker surface `OrchestratorCore` depends on. `submit` verifies a
+    signed *mutation* token and performs its op, returning the verified request;
+    `list_live` verifies a signed `list_live` token and returns the source IPs of
+    the bottles the backend currently has running (reconcile's live set). Both the
+    in-process `LaunchBroker` and the out-of-process `BrokerClient` (which relays
+    the token to the host control server) satisfy it structurally, so the core is
+    unchanged whether the backend is local or a real host service."""
+
+    def submit(self, token: str) -> LaunchRequest: ...
+
+    def list_live(self, token: str) -> list[str]: ...
+
+
 class LaunchBroker(abc.ABC):
     """Verifies a signed request came from the orchestrator, then performs
     the backend-native launch/teardown. Subclasses implement `_launch` /
@@ -132,15 +203,35 @@ class LaunchBroker(abc.ABC):
         self._secret = secret
 
     def submit(self, token: str) -> LaunchRequest:
-        """Verify `token` and perform its op. Returns the verified request;
-        raises `BrokerAuthError` if provenance/shape fails."""
+        """Verify `token` and perform its mutation op. Returns the verified
+        request; raises `BrokerAuthError` if provenance/shape fails, or if the
+        token is a non-mutation op (a `list_live` token routed here by mistake)."""
         req = verify_request(token, self._secret)
         if req.op == "launch":
             self._launch(req)
-        else:
+        elif req.op == "teardown":
             self._teardown(req)
+        else:
+            raise BrokerAuthError(f"{req.op} is not a submit op")
         return req
 
+    def list_live(self, token: str) -> list[str]:
+        """Verify a `list_live` `token` and return the source IPs of the bottles
+        the backend currently has running. Raises `BrokerAuthError` on bad
+        provenance/shape or a non-`list_live` op; a backend enumeration failure
+        is converted to `BrokerUnavailableError` — the single "live set could not
+        be determined" signal reconcile catches to skip the sweep rather than
+        reaping healthy rows against a partial set (the out-of-process
+        `BrokerClient` raises the same on an enumeration 502 / no response)."""
+        req = verify_request(token, self._secret)
+        if req.op != "list_live":
+            raise BrokerAuthError(f"{req.op} is not a list_live op")
+        try:
+            return list(self._list_live())
+        except Exception as e:  # noqa: BLE001 — any enumeration failure means the
+            # live set is unknown; reconcile must skip, never reap against it.
+            raise BrokerUnavailableError(f"list_live enumeration failed: {e}") from e
+
     @abc.abstractmethod
     def _launch(self, req: LaunchRequest) -> None:
         ...
@@ -149,15 +240,31 @@ class LaunchBroker(abc.ABC):
     def _teardown(self, req: LaunchRequest) -> None:
         ...
 
+    @abc.abstractmethod
+    def _list_live(self) -> list[str]:
+        """Every running bottle's source IP, backend-native. Must raise (not
+        return a partial list) if the live set can't be determined
+        authoritatively, so reconcile skips rather than reaping healthy rows."""
+        ...
+
 
 class StubBroker(LaunchBroker):
     """Dev-harness broker: records verified requests without launching
-    anything. Exercises the full sign -> verify -> act contract in-process."""
+    anything. Exercises the full sign -> verify -> act contract in-process.
+
+    Its live set (`_list_live`) is, by default, every bottle it recorded a
+    launch for and no teardown since — the in-process analogue of enumerating
+    the backend. Tests that need to simulate a bottle dying out from under the
+    registry (the case reconcile exists for) set `live_source_ips` explicitly to
+    override that derived set."""
 
     def __init__(self, secret: bytes) -> None:
         super().__init__(secret)
         self.launched: list[LaunchRequest] = []
         self.torn_down: list[LaunchRequest] = []
+        # When not None, the exact live set `_list_live` reports — lets a test
+        # say "only these IPs are still up" regardless of what was launched.
+        self.live_source_ips: list[str] | None = None
 
     def _launch(self, req: LaunchRequest) -> None:
         self.launched.append(req)
@@ -165,10 +272,20 @@ class StubBroker(LaunchBroker):
     def _teardown(self, req: LaunchRequest) -> None:
         self.torn_down.append(req)
 
+    def _list_live(self) -> list[str]:
+        if self.live_source_ips is not None:
+            return list(self.live_source_ips)
+        torn = {r.bottle_id for r in self.torn_down}
+        return [r.source_ip for r in self.launched
+                if r.bottle_id not in torn and r.source_ip]
+
 
 __all__ = [
     "BrokerAuthError",
+    "BrokerUnavailableError",
+    "BrokerRequest",
     "LaunchRequest",
+    "SubmitBroker",
     "LaunchBroker",
     "StubBroker",
     "sign_request",

bot_bottle/orchestrator/broker_client.py

@@ -0,0 +1,168 @@
+"""Orchestrator-side broker transport (issue #468, chunk 1).
+
+The signer's half of the launch-broker transport gap. `BrokerClient` satisfies
+the exact `submit(token)` contract `OrchestratorCore` already depends on (see
+`broker.SubmitBroker`), but instead of verifying and launching in-process it POSTs
+the signed token to the host control server over HTTP (stdlib `urllib`, like
+`orchestrator/client.py`). Because it is drop-in for that interface, wiring a real
+out-of-process backend does not change the core: it still signs a request and
+calls `submit()`; only the wire is new.
+
+A provenance/schema rejection from the host controller (HTTP 401) is re-raised as
+the same `BrokerAuthError` the in-process broker raises, so the launch path's
+rollback-on-failure (`OrchestratorCore.launch_bottle`) behaves identically whether
+the broker is local or remote.
+"""
+
+from __future__ import annotations
+
+import json
+import urllib.error
+import urllib.request
+
+from .broker import BrokerAuthError, BrokerUnavailableError, LaunchRequest
+
+DEFAULT_TIMEOUT_SECONDS = 5.0
+
+
+class BrokerClientError(RuntimeError):
+    """The host control server *responded*, but with an unexpected status other
+    than the fail-closed 401 (which surfaces as `BrokerAuthError`) — e.g. a 502
+    backend failure or a malformed body. A definite negative: the host processed
+    the request and it did not launch. (A *no-response* failure — unreachable /
+    timeout / dropped — is the ambiguous `BrokerUnavailableError` instead.)"""
+
+
+class BrokerClient:
+    """Drop-in `submit(token)` that relays a signed request to the host control
+    server. Holds no secret — provenance rides entirely in the signed token, so a
+    caller that can reach this client still cannot forge a launch."""
+
+    def __init__(self, base_url: str, *, timeout: float = DEFAULT_TIMEOUT_SECONDS) -> None:
+        self._base = base_url.rstrip("/")
+        self._timeout = timeout
+
+    def submit(self, token: str) -> LaunchRequest:
+        """POST the signed token to the host controller and return the request it
+        verified and acted on.
+
+        Raises `BrokerAuthError` on a fail-closed 401 (bad provenance/schema —
+        the same exception the in-process broker raises); `BrokerClientError` if
+        the host *responds* with any other non-success status or a malformed
+        body (a definite negative); or `BrokerUnavailableError` if no response is
+        obtained (unreachable / timeout / dropped) — the **ambiguous** case, where
+        the host may already have acted, so the caller must not roll back."""
+        data = json.dumps({"token": token}).encode()
+        req = urllib.request.Request(
+            f"{self._base}/broker", data=data, method="POST",
+            headers={"Content-Type": "application/json"},
+        )
+        try:
+            with urllib.request.urlopen(req, timeout=self._timeout) as resp:
+                return _request_from(_json_object(resp.read()))
+        except urllib.error.HTTPError as e:
+            detail = _error_detail(e)
+            if e.code == 401:
+                raise BrokerAuthError(
+                    detail or "host controller rejected the request"
+                ) from e
+            raise BrokerClientError(
+                f"POST /broker: HTTP {e.code} {detail}".rstrip()
+            ) from e
+        except (urllib.error.URLError, TimeoutError, OSError) as e:
+            # No usable response — unreachable, timed out, or the connection
+            # dropped mid-exchange. Ambiguous: the request may already have
+            # launched the bottle, so this is NOT a definite failure.
+            raise BrokerUnavailableError(f"POST /broker: {e}") from e
+
+    def list_live(self, token: str) -> list[str]:
+        """POST the signed `list_live` token to the host controller and return
+        the source IPs of the bottles it enumerated as running.
+
+        Raises `BrokerAuthError` on a fail-closed 401 (bad provenance/schema);
+        `BrokerClientError` on any other non-success status or a malformed body
+        (a backend-enumeration 502 included); or `BrokerUnavailableError` if no
+        response is obtained. A query has no backend side effect, so — unlike
+        `submit` — every one of these is a *definite* "no live set"; reconcile
+        catches all three and skips the sweep rather than reaping against an
+        unknown or partial set."""
+        data = json.dumps({"token": token}).encode()
+        req = urllib.request.Request(
+            f"{self._base}/broker/live", data=data, method="POST",
+            headers={"Content-Type": "application/json"},
+        )
+        try:
+            with urllib.request.urlopen(req, timeout=self._timeout) as resp:
+                return _source_ips_from(_json_object(resp.read()))
+        except urllib.error.HTTPError as e:
+            detail = _error_detail(e)
+            if e.code == 401:
+                raise BrokerAuthError(
+                    detail or "host controller rejected the request"
+                ) from e
+            raise BrokerClientError(
+                f"POST /broker/live: HTTP {e.code} {detail}".rstrip()
+            ) from e
+        except (urllib.error.URLError, TimeoutError, OSError) as e:
+            raise BrokerUnavailableError(f"POST /broker/live: {e}") from e
+
+
+def _json_object(raw: bytes) -> dict[str, object]:
+    """Parse a JSON object, tolerating an empty or malformed body (→ {}), like
+    the orchestrator client — a bad body becomes a clean 'missing field' error
+    downstream rather than an opaque JSON crash."""
+    if not raw:
+        return {}
+    try:
+        obj = json.loads(raw)
+    except ValueError:
+        return {}
+    return obj if isinstance(obj, dict) else {}
+
+
+def _error_detail(e: urllib.error.HTTPError) -> str:
+    """The `error` string from a structured error response, best-effort — an
+    error body may be absent or unreadable, in which case there is no detail."""
+    try:
+        detail = _json_object(e.read()).get("error", "")
+    except Exception:  # noqa: BLE001 — the error body is advisory only
+        return ""
+    return detail if isinstance(detail, str) else ""
+
+
+def _source_ips_from(payload: dict[str, object]) -> list[str]:
+    """The `source_ips` list from a `/broker/live` response — every string
+    entry, ignoring any non-string the host controller should never send. A
+    missing/!list field is a malformed response (the query is meaningless
+    without it), so it fails rather than silently reconciling against []."""
+    raw = payload.get("source_ips")
+    if not isinstance(raw, list):
+        raise BrokerClientError("host controller response missing source_ips")
+    return [ip for ip in raw if isinstance(ip, str) and ip]
+
+
+def _request_from(payload: dict[str, object]) -> LaunchRequest:
+    """Reconstruct the verified `LaunchRequest` the controller echoed, so the
+    returned value matches the in-process broker's (which returns the request it
+    acted on). A missing op/bottle_id means a malformed response."""
+    op = payload.get("op")
+    bottle_id = payload.get("bottle_id")
+    if not isinstance(op, str) or not isinstance(bottle_id, str) or not bottle_id:
+        raise BrokerClientError("host controller response missing op/bottle_id")
+    source_ip = payload.get("source_ip")
+    image_ref = payload.get("image_ref")
+    slot = payload.get("slot")
+    return LaunchRequest(
+        op=op,
+        bottle_id=bottle_id,
+        source_ip=source_ip if isinstance(source_ip, str) else "",
+        image_ref=image_ref if isinstance(image_ref, str) else "",
+        slot=slot if isinstance(slot, int) and not isinstance(slot, bool) else None,
+    )
+
+
+__all__ = [
+    "BrokerClient",
+    "BrokerClientError",
+    "DEFAULT_TIMEOUT_SECONDS",
+]

bot_bottle/orchestrator/client.py

@@ -15,13 +15,12 @@ from __future__ import annotations
 import json
 import urllib.error
 import urllib.request
-from collections.abc import Iterable
 from dataclasses import dataclass
 
 from ..log import debug
 from ..orchestrator_auth import ROLE_CLI
 from ..trust_domain import CONTROL_PLANE
-from .http_contract import ORCHESTRATOR_AUTH_HEADER
+from .server import ORCHESTRATOR_AUTH_HEADER
 
 DEFAULT_TIMEOUT_SECONDS = 5.0
 
@@ -194,14 +193,13 @@ class OrchestratorClient:
             raise OrchestratorClientError(f"teardown {bottle_id}: HTTP {status}")
         return True
 
-    def reconcile(
-        self, live_source_ips: Iterable[str], *, grace_seconds: float | None = None,
-    ) -> list[str]:
-        """Drop registry rows for bottles that are no longer running
-        (`POST /reconcile`), returning the reaped bottle ids. `live_source_ips`
-        is the caller's enumeration of its live bottles — the orchestrator
-        can't see the backend from inside the orchestrator container/VM."""
-        body: dict[str, object] = {"live_source_ips": list(live_source_ips)}
+    def reconcile(self, *, grace_seconds: float | None = None) -> list[str]:
+        """Trigger the orchestrator's self-heal sweep (`POST /reconcile`),
+        returning the reaped bottle ids. The caller no longer enumerates the
+        live set: the orchestrator pulls it from the host controller
+        (`list_live`) itself, so this is a bare trigger with an optional
+        `grace_seconds`."""
+        body: dict[str, object] = {}
         if grace_seconds is not None:
             body["grace_seconds"] = grace_seconds
         payload = self._ok("POST", "/reconcile", body)

bot_bottle/orchestrator/docker_broker.py

@@ -71,6 +71,31 @@ class DockerBroker(LaunchBroker):
                 f"docker rm failed for {req.bottle_id}: {proc.stderr.strip()}"
             )
 
+    def _list_live(self) -> list[str]:
+        """Every running bottle container's network IP, from `docker ps` filtered
+        to this broker's label. Raises `DockerBrokerError` if the listing or any
+        inspect fails, so reconcile treats the live set as unknown and skips the
+        sweep rather than reaping healthy rows against a partial enumeration."""
+        listing = self._docker([
+            "docker", "ps", "--filter", f"label={BOTTLE_ID_LABEL}",
+            "--format", "{{.ID}}",
+        ])
+        if listing.returncode != 0:
+            raise DockerBrokerError(f"docker ps failed: {listing.stderr.strip()}")
+        ips: list[str] = []
+        for cid in (line for line in listing.stdout.splitlines() if line):
+            inspected = self._docker([
+                "docker", "inspect", "--format",
+                "{{range .NetworkSettings.Networks}}{{.IPAddress}} {{end}}", cid,
+            ])
+            if inspected.returncode != 0:
+                raise DockerBrokerError(
+                    f"docker inspect {cid} failed; live set is not authoritative: "
+                    f"{inspected.stderr.strip()}"
+                )
+            ips.extend(ip for ip in inspected.stdout.split() if ip)
+        return ips
+
 
 __all__ = [
     "DockerBroker",

bot_bottle/orchestrator/host_server.py

@@ -0,0 +1,316 @@
+"""Host control server (issue #468) — the launch broker as a real host service.
+
+Chunk 1 of the host-control-server stack closes the **transport** gap the PRD
+opens with: today `LaunchBroker.submit(token)` is an in-process method call from
+`OrchestratorCore`, and a real host service needs it reachable over the wire.
+This module is that service — the single privileged host component — reached over
+**HTTP** (the universal transport 0070 chose), mirroring the orchestrator control
+plane's shape (`orchestrator/server.py`): a pure `dispatch()` for socket-free
+testing, wrapped by a thin stdlib `http.server` adapter.
+
+    GET  /health       -> 200 {"status": "ok"}
+    POST /broker       -> 200 {"op", "bottle_id", "source_ip", "image_ref", "slot"}
+                          400 (bad body) | 401 (bad provenance/schema) | 502 (backend)
+                          body: {"token": "<signed launch/teardown JWT>"}
+    POST /broker/live  -> 200 {"source_ips": [...]}
+                          400 (bad body) | 401 (bad provenance/schema) | 502 (backend)
+                          body: {"token": "<signed list_live JWT>"}
+
+The op vocabulary grows one signed op at a time (PRD gap 3); each verb reaches
+the backend only through `verify_request`, so nothing free-form ever crosses the
+wire. `/broker/live` is the first query op — reconcile's live-bottle enumeration,
+which the orchestrator (blind to the backend from inside its container) now pulls
+from the host controller instead of being handed by the CLI.
+
+Only the **signed token** crosses the wire; the server holds the shared HS256
+secret and a real `LaunchBroker` (e.g. `DockerBroker`) and runs the existing
+`verify_request` + `_launch`/`_teardown` path behind the endpoint, so nothing
+free-form ever reaches it. Provenance/schema failures are fail-closed 401s that
+never touch the backend (`LaunchBroker.submit` verifies before acting), and a
+backend launch failure is a 502 the caller must surface — neither takes the
+controller down.
+
+The signed launch token *is* the endpoint's authentication (its provenance is the
+whole point of the JWS), so `/broker` needs no separate caller credential; the
+host controller's own lifecycle endpoints, which do, arrive with the `host`-role
+tokens of the separate `HOST_CONTROLLER` trust domain in a later chunk.
+
+The shared signing secret is the durable **launch-broker `TrustDomain` key**
+(#468/#476): a host-canonical key file minted 0600 on first use, provisioned to
+the orchestrator (signer) and this server (verifier). A backend launcher injects
+it via `$BOT_BOTTLE_LAUNCH_BROKER_KEY`; a host-side dev-harness process reads the
+key file directly. Durability is the point — a restarted orchestrator re-verifies
+against the same key, so re-adoption works.
+"""
+
+from __future__ import annotations
+
+import argparse
+import http.server
+import json
+import os
+import socketserver
+import sys
+import typing
+from urllib.parse import urlsplit
+
+from .. import log
+from ..paths import LAUNCH_BROKER_KEY_ENV
+from ..trust_domain import LAUNCH_BROKER
+from .broker import BrokerAuthError, LaunchBroker
+from .docker_broker import DockerBroker
+
+# JSON body payload type (parsed request / rendered response).
+Json = dict[str, object]
+
+# Default host-controller port. Distinct from the orchestrator control plane
+# (8099) — a separate privileged component listening on its own socket.
+DEFAULT_PORT = 8091
+
+# Cap on the request body. A signed broker request is tiny, so rejecting anything
+# larger *before reading it* keeps a caller that can merely reach the socket (no
+# signed token needed) from exhausting memory or a handler thread with a huge
+# Content-Length — the signed token, not mere reachability, is the authority.
+MAX_BODY_BYTES = 64 * 1024
+
+# Per-request socket timeout, bounding how long a stalled / slow-loris caller can
+# hold a handler thread on this privileged listener.
+REQUEST_TIMEOUT_SECONDS = 15
+
+
+def _parse_json_object(body: bytes) -> Json:
+    """Parse a JSON object body. Raises ValueError for non-objects / bad JSON."""
+    if not body:
+        return {}
+    obj = json.loads(body)  # raises json.JSONDecodeError (a ValueError)
+    if not isinstance(obj, dict):
+        raise ValueError("request body must be a JSON object")
+    return obj
+
+
+def broker_secret(
+    environ: typing.Mapping[str, str] | None = None, *, allow_host_file: bool = False,
+) -> bytes | None:
+    """The shared launch-broker HS256 secret, as this process should use it.
+
+    Always prefers the key injected into this process's env
+    (`$BOT_BOTTLE_LAUNCH_BROKER_KEY`). `allow_host_file` decides the fallback when
+    it is absent, and the distinction is a security boundary:
+
+    - **Host-side** processes — the host controller and the host dev-harness — pass
+      ``allow_host_file=True`` to read (minting on first use) the durable host key
+      file (``bot_bottle_root()/launch-broker-key``) they legitimately own.
+    - The **guest orchestrator** (``--broker http``) keeps the default ``False``.
+      It runs inside a container/VM whose ``bot_bottle_root()`` is process-local,
+      so minting a file there would silently create a key UNRELATED to the host
+      controller's — startup would succeed but every launch would be rejected 401.
+      It must instead be *given* the key by its launcher, and fail closed (None)
+      if it wasn't, rather than diverge.
+
+    None when no key is available (a guest with no injection, or an unwritable
+    host root)."""
+    key = LAUNCH_BROKER.key_from_env(environ)
+    if not key and allow_host_file:
+        try:
+            key = LAUNCH_BROKER.signing_key()  # host-canonical, minted on first use
+        except OSError:
+            return None
+    return key.encode("utf-8") if key else None
+
+
+def dispatch(  # pylint: disable=too-many-return-statements
+    broker: LaunchBroker, method: str, path: str, body: bytes,
+) -> tuple[int, Json]:
+    """Route one host-control request to a (status, payload) pair. Pure — the
+    only side effect is the broker's own backend launch — so routing is testable
+    without a socket.
+
+    Total by design: a provenance/schema failure becomes 401 and a backend launch
+    failure becomes 502 rather than raising, so one bad request can neither act
+    on the backend nor take the controller down for the next caller."""
+    route = urlsplit(path).path.rstrip("/") or "/"
+
+    if method == "GET" and route == "/health":
+        return 200, {"status": "ok"}
+
+    if method == "POST" and route == "/broker":
+        try:
+            data = _parse_json_object(body)
+        except ValueError as e:
+            return 400, {"error": f"invalid JSON: {e}"}
+        token = data.get("token")
+        if not isinstance(token, str) or not token:
+            return 400, {"error": "token (string) is required"}
+        try:
+            req = broker.submit(token)
+        except BrokerAuthError as e:
+            # Fail-closed: bad signature, malformed token, or off-schema payload.
+            # `submit` verifies before acting, so nothing was launched.
+            return 401, {"error": f"broker auth failed: {e}"}
+        except Exception as e:  # noqa: BLE001 — a backend launch failure (docker
+            # down, image gone) is operational, not a control-plane bug; the
+            # caller must see it as a distinct 502, and the server must stay up.
+            return 502, {"error": f"backend launch failed: {e}"}
+        return 200, {
+            "op": req.op,
+            "bottle_id": req.bottle_id,
+            "source_ip": req.source_ip,
+            "image_ref": req.image_ref,
+            "slot": req.slot,
+        }
+
+    if method == "POST" and route == "/broker/live":
+        try:
+            data = _parse_json_object(body)
+        except ValueError as e:
+            return 400, {"error": f"invalid JSON: {e}"}
+        token = data.get("token")
+        if not isinstance(token, str) or not token:
+            return 400, {"error": "token (string) is required"}
+        try:
+            source_ips = broker.list_live(token)
+        except BrokerAuthError as e:
+            # Fail-closed: bad signature, malformed token, or a non-list_live op.
+            return 401, {"error": f"broker auth failed: {e}"}
+        except Exception as e:  # noqa: BLE001 — a backend enumeration failure
+            # (docker down, inspect failed) is operational, not a control-plane
+            # bug; surface it as a 502 so the caller skips reconcile rather than
+            # reaping against a partial set, and keep the controller up.
+            return 502, {"error": f"backend enumeration failed: {e}"}
+        return 200, {"source_ips": source_ips}
+
+    return 404, {"error": "not found"}
+
+
+class Handler(http.server.BaseHTTPRequestHandler):
+    """Thin stdlib adapter: read the body, call `dispatch`, write JSON."""
+
+    # Socket timeout per request (applied by StreamRequestHandler.setup) so a
+    # stalled caller can't pin a handler thread on this privileged listener.
+    timeout = REQUEST_TIMEOUT_SECONDS
+
+    # Quiet by default; opt back into stdlib access logging with
+    # BOT_BOTTLE_HOST_CONTROLLER_DEBUG (the controller has its own logging).
+    def log_message(self, format: str, *args: typing.Any) -> None:  # noqa: A002
+        if os.environ.get("BOT_BOTTLE_HOST_CONTROLLER_DEBUG"):
+            super().log_message(format, *args)
+
+    def _serve(self, method: str) -> None:
+        """Read the request body (bounded), dispatch it, and write the JSON
+        reply. A dispatch that raises (it shouldn't — dispatch is total) still
+        returns a 500 rather than dropping the connection."""
+        server = self.server
+        assert isinstance(server, HostControlServer)
+        try:
+            length = int(self.headers.get("Content-Length") or 0)
+        except ValueError:
+            self._reply(400, {"error": "invalid Content-Length"})
+            return
+        if length < 0 or length > MAX_BODY_BYTES:
+            # Reject before reading: nothing legitimate is this big, so an
+            # oversized declared length is a bug or a resource-exhaustion attempt.
+            self._reply(413, {"error": "request body too large"})
+            return
+        body = self.rfile.read(length) if length > 0 else b""
+        try:
+            status, payload = dispatch(server.broker, method, self.path, body)
+        except Exception as e:  # noqa: BLE001 — the controller must stay up
+            sys.stderr.write(f"host controller: {method} {self.path} failed: {e!r}\n")
+            sys.stderr.flush()
+            status, payload = 500, {"error": f"internal error: {e}"}
+        self._reply(status, payload)
+
+    def _reply(self, status: int, payload: typing.Mapping[str, object]) -> None:
+        """Write one JSON response with an explicit Content-Length."""
+        data = json.dumps(payload).encode()
+        self.send_response(status)
+        self.send_header("Content-Type", "application/json")
+        self.send_header("Content-Length", str(len(data)))
+        self.end_headers()
+        self.wfile.write(data)
+
+    def do_GET(self) -> None:
+        self._serve("GET")
+
+    def do_POST(self) -> None:
+        self._serve("POST")
+
+
+class HostControlServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
+    """Threading HTTP server that carries the launch broker for its handlers.
+
+    The broker holds the shared signing secret and performs the backend-native
+    launch/teardown; the server itself keeps no secret of its own — provenance
+    rides entirely in each request's signed token."""
+
+    daemon_threads = True
+    allow_reuse_address = True
+
+    def __init__(self, address: tuple[str, int], broker: LaunchBroker) -> None:
+        self.broker = broker
+        super().__init__(address, Handler)
+
+
+def make_host_server(
+    broker: LaunchBroker, host: str = "127.0.0.1", port: int = DEFAULT_PORT
+) -> HostControlServer:
+    """Build (but do not start) a host control server. `port=0` binds an
+    ephemeral port — read `server.server_address` for the actual one."""
+    return HostControlServer((host, port), broker)
+
+
+def main(argv: list[str] | None = None) -> int:
+    """Run the host control server as a plain process (dev-harness).
+
+        python -m bot_bottle.orchestrator.host_server [--host H] [--port P]
+
+    Fail-closed: without the launch-broker key the server can verify no request's
+    provenance, so it refuses to start rather than run a launcher that accepts
+    unsigned input. As the host-side owner of the key, it may mint/read the host
+    key file (`allow_host_file=True`)."""
+    parser = argparse.ArgumentParser(prog="bot_bottle.orchestrator.host_server")
+    parser.add_argument("--host", default="127.0.0.1", help="bind address")
+    parser.add_argument("--port", type=int, default=DEFAULT_PORT, help="bind port (0 = ephemeral)")
+    args = parser.parse_args(argv)
+
+    secret = broker_secret(allow_host_file=True)
+    if secret is None:
+        sys.stderr.write(
+            f"host controller: refusing to start without the launch-broker key "
+            f"(${LAUNCH_BROKER_KEY_ENV}, or a writable host root to mint it) — it "
+            "could verify no request's provenance and would relay unsigned "
+            "launches to the backend\n"
+        )
+        sys.stderr.flush()
+        return 2
+
+    broker = DockerBroker(secret)
+    server = make_host_server(broker, host=args.host, port=args.port)
+    bound_host, bound_port = server.server_address[0], server.server_address[1]
+    log.info(
+        "host control server listening",
+        context={"host": bound_host, "port": bound_port},
+    )
+    try:
+        server.serve_forever()
+    except KeyboardInterrupt:
+        log.info("host controller shutting down")
+    finally:
+        server.server_close()
+    return 0
+
+
+__all__ = [
+    "dispatch",
+    "Handler",
+    "HostControlServer",
+    "make_host_server",
+    "broker_secret",
+    "main",
+    "Json",
+    "DEFAULT_PORT",
+]
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

bot_bottle/orchestrator/http_contract.py

@@ -1,11 +0,0 @@
-"""Dependency-free constants shared by orchestrator HTTP clients and server."""
-
-ORCHESTRATOR_AUTH_HEADER = "x-bot-bottle-orchestrator-auth"
-MAX_BODY_BYTES = 1 * 1024 * 1024
-REQUEST_BODY_TIMEOUT_SECONDS = 10.0
-
-__all__ = [
-    "MAX_BODY_BYTES",
-    "ORCHESTRATOR_AUTH_HEADER",
-    "REQUEST_BODY_TIMEOUT_SECONDS",
-]

bot_bottle/orchestrator/server.py

@@ -1,80 +1,459 @@
-"""Uvicorn transport for the FastAPI orchestrator control plane."""
+"""Orchestrator HTTP control plane (PRD 0070).
+
+The backend-agnostic control-plane RPC (CLI / console -> orchestrator) over
+**HTTP** — the universal transport chosen in 0070 (works on every host; no
+vsock / unix-socket portability caveats):
+
+    GET    /health                    -> 200 {"status": "ok"}
+    GET    /gateway                   -> 200 {"configured", ["name","running"]}
+    GET    /bottles                   -> 200 {"bottles": [ <redacted record>, ...]}
+    POST   /bottles                   -> 201 {"bottle_id","identity_token"}  (launch)
+                                         body: {"source_ip", ["image_ref"],
+                                                ["metadata"], ["policy"],
+                                                ["tokens"], ["env_var_secret"]}
+    PUT    /bottles/<bottle_id>/policy -> 200 {"updated": true} | 404  (live reload)
+                                         body: {"policy"}
+    POST   /bottles/<bottle_id>/reprovision_gateway
+                                      -> 200 {"reprovisioned": true} | 404
+                                         body: {"env_var_secret"}
+    DELETE /bottles/<bottle_id>        -> 200 {"torn_down": true} | 404  (teardown)
+    POST   /reconcile                 -> 200 {"reaped": [bottle_id, ...]}
+                                         body: {["grace_seconds"]}  (live set is
+                                         pulled from the host controller, not sent)
+    POST   /attribute                 -> 200 {"bottle_id"} | 403
+    POST   /resolve                   -> 200 {"bottle_id","policy"} | 403
+                                         body: {"source_ip","identity_token"}
+    GET    /supervise/proposals       -> 200 {"proposals": [ <proposal>, ...]}
+    POST   /supervise/respond         -> 200 {"responded": true} | 409  (operator)
+                                         body: {"proposal_id","bottle_slug",
+                                                "decision", ["notes"],["final_file"]}
+    POST   /supervise/propose         -> 201 {"proposal_id"} | 403  (agent)
+                                         body: {"source_ip","identity_token",
+                                                "tool","proposed_file","justification"}
+    POST   /supervise/poll            -> 200 {"status", ["notes"],["final_file"]} | 403
+                                         body: {"source_ip","identity_token",
+                                                "proposal_id"}
+
+The `/supervise/propose` + `/supervise/poll` pair is the **agent** half of the
+supervise flow: the data plane (supervise / egress / git-gate) queues a proposal
+and polls for its response over RPC instead of opening `bot-bottle.db` directly.
+`poll` is idempotent — it never archives, so a dropped connection can't lose an
+operator decision (the row is reaped when the bottle is torn down / reconciled).
+Both attribute the caller by `(source_ip, identity_token)` exactly like
+`/resolve`, so a bottle can only ever queue or read its own proposals.
+
+`POST /bottles` / `DELETE` drive the full launch lifecycle: they mint (or
+tear down) the bottle in the registry AND broker the backend-native launch
+via the orchestrator. Register/deregister without a launch are internal to
+`OrchestratorCore`, not exposed here.
+
+Routing/handling is the pure function `dispatch()` so it is unit-testable
+without a socket; `Handler` / `OrchestratorServer` / `make_server` are a
+thin stdlib adapter around it. Listing redacts identity tokens — they are
+returned only once, to the caller that launches the bottle.
+"""
 
 from __future__ import annotations
 
+import http.server
+import json
+import math
 import os
-import socket
-import threading
-
-import uvicorn
+import socketserver
+import sys
+import typing
+from urllib.parse import urlsplit
 
+from ..orchestrator_auth import ROLE_CLI, ROLES
 from ..trust_domain import CONTROL_PLANE
-from .api import create_app
-from .http_contract import MAX_BODY_BYTES, ORCHESTRATOR_AUTH_HEADER
+from ..supervisor.types import TOOLS
 from .service import OrchestratorCore
 
-MAX_REQUESTS = 32
-KEEP_ALIVE_TIMEOUT_SECONDS = 10
+# JSON body payload type (parsed request / rendered response).
+Json = dict[str, object]
+
+# The request header carrying the caller's role-scoped control-plane token (a
+# signed JWT naming the caller's role — see orchestrator_auth). The role gates which
+# routes the caller may reach: the data plane holds a `gateway` token good only
+# for the agent-facing lookups; the host CLI holds a `cli` token for the
+# operator/mutating routes. An agent that can merely *reach* the port holds no
+# token at all, and a compromised gateway holds only `gateway` — neither can
+# drive the operator routes (approve proposals, rewrite policy, read tokens).
+ORCHESTRATOR_AUTH_HEADER = "x-bot-bottle-orchestrator-auth"
+
+# The routes the data plane (role `gateway`) is allowed to reach — exactly the
+# per-request lookups PolicyResolver makes. Every other authenticated route is
+# operator-only. `cli` is a superset role: it may reach any route.
+_GATEWAY_ROUTES: frozenset[tuple[str, str]] = frozenset({
+    ("POST", "/resolve"),
+    ("POST", "/supervise/propose"),
+    ("POST", "/supervise/poll"),
+})
 
 
-class OrchestratorServer:
-    """Small lifecycle wrapper around Uvicorn with an eagerly bound socket."""
+def _allowed_roles(method: str, route: str) -> frozenset[str]:
+    """The roles permitted on `(method, route)`: `gateway` or `cli` on the
+    data-plane routes, `cli`-only everywhere else."""
+    if (method, route) in _GATEWAY_ROUTES:
+        return ROLES
+    return frozenset({ROLE_CLI})
 
-    def __init__(self, config: uvicorn.Config) -> None:
-        self._server = uvicorn.Server(config)
-        self._stopped = threading.Event()
-        self._socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
-        self._socket.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
-        self._socket.bind((config.host, config.port))
-        self._socket.listen(config.backlog)
-        self.server_address = self._socket.getsockname()
 
-    def run(self) -> None:
+def _parse_json_object(body: bytes) -> Json:
+    """Parse a JSON object body. Raises ValueError for non-objects / bad JSON."""
+    if not body:
+        return {}
+    obj = json.loads(body)  # raises json.JSONDecodeError (a ValueError)
+    if not isinstance(obj, dict):
+        raise ValueError("request body must be a JSON object")
+    return obj
+
+
+def dispatch(  # pylint: disable=too-many-return-statements,too-many-branches
+    orch: OrchestratorCore, method: str, path: str, body: bytes, *, role: str | None = ROLE_CLI,
+) -> tuple[int, Json]:
+    """Route one control-plane request to a (status, payload) pair. Pure —
+    no I/O beyond the orchestrator — so it is fully testable without a socket.
+
+    `role` is the caller's verified control-plane role (`gateway` or `cli`), or
+    None for an unauthenticated request; an open-mode server (no signing key
+    configured — see `OrchestratorServer`) passes `cli`. Every route except
+    `GET /health` requires a role: a missing role is 401, and a role that
+    doesn't cover the route is 403 — so a `gateway` data-plane token can reach
+    `/resolve` + `/supervise/{propose,poll}` but not the operator routes
+    (rewrite policy, read injected tokens, approve its own supervise proposals).
+    The source-IP + identity-token checks inside `/resolve` and `/attribute`
+    authenticate the *bottle* a request is about, not the *caller*, so this role
+    gate is what protects the caller-privileged routes. Defaults `cli` so unit
+    tests of the routing logic don't have to thread it through."""
+    route = urlsplit(path).path.rstrip("/") or "/"
+
+    if method == "GET" and route == "/health":
+        return 200, {"status": "ok"}
+
+    # Role gate — every route below is a trusted-caller operation. Deny before
+    # touching the registry / broker / supervise store.
+    if role is None:
+        return 401, {"error": "control-plane authentication required"}
+    if role not in _allowed_roles(method, route):
+        return 403, {"error": "insufficient role for this route"}
+
+    if method == "GET" and route == "/gateway":
+        return 200, orch.gateway_status()
+
+    if method == "GET" and route == "/bottles":
+        return 200, {"bottles": [r.redacted() for r in orch.registry.all()]}
+
+    if method == "POST" and route == "/bottles":
         try:
-            self._server.run(sockets=[self._socket])
-        finally:
-            self._stopped.set()
+            data = _parse_json_object(body)
+        except ValueError as e:
+            return 400, {"error": f"invalid JSON: {e}"}
+        source_ip = data.get("source_ip")
+        if not isinstance(source_ip, str) or not source_ip:
+            return 400, {"error": "source_ip (string) is required"}
+        image_ref = data.get("image_ref")
+        metadata = data.get("metadata")
+        policy = data.get("policy")
+        raw_tokens = data.get("tokens")
+        tokens = {
+            k: v for k, v in raw_tokens.items() if isinstance(k, str) and isinstance(v, str)
+        } if isinstance(raw_tokens, dict) else {}
+        env_var_secret = data.get("env_var_secret", "")
+        rec = orch.launch_bottle(
+            source_ip,
+            image_ref=image_ref if isinstance(image_ref, str) else "",
+            metadata=metadata if isinstance(metadata, str) else "",
+            policy=policy if isinstance(policy, str) else "",
+            tokens=tokens,
+            env_var_secret=env_var_secret if isinstance(env_var_secret, str) else "",
+        )
+        return 201, {"bottle_id": rec.bottle_id, "identity_token": rec.identity_token}
 
-    def serve_forever(self) -> None:
-        self.run()
+    if method == "PUT" and route.startswith("/bottles/") and route.endswith("/policy"):
+        bottle_id = route[len("/bottles/"):-len("/policy")]
+        try:
+            data = _parse_json_object(body)
+        except ValueError as e:
+            return 400, {"error": f"invalid JSON: {e}"}
+        policy = data.get("policy")
+        if not isinstance(policy, str):
+            return 400, {"error": "policy (string) is required"}
+        if orch.set_policy(bottle_id, policy):
+            return 200, {"updated": True}
+        return 404, {"error": "no such bottle"}
 
-    def shutdown(self) -> None:
-        self._server.should_exit = True
-        self._stopped.wait(timeout=5)
+    if (
+        method == "POST"
+        and route.startswith("/bottles/")
+        and route.endswith("/reprovision_gateway")
+    ):
+        bottle_id = route[len("/bottles/") : -len("/reprovision_gateway")]
+        try:
+            data = _parse_json_object(body)
+        except ValueError as e:
+            return 400, {"error": f"invalid JSON: {e}"}
+        env_var_secret = data.get("env_var_secret")
+        if not isinstance(env_var_secret, str) or not env_var_secret:
+            return 400, {"error": "env_var_secret (string) is required"}
+        if orch.reprovision_from_secret(bottle_id, env_var_secret):
+            return 200, {"reprovisioned": True}
+        return 404, {"error": "no stored secrets for this bottle"}
 
-    def server_close(self) -> None:
-        self._socket.close()
+    if method == "DELETE" and route.startswith("/bottles/"):
+        bottle_id = route[len("/bottles/"):]
+        if orch.teardown_bottle(bottle_id):
+            return 200, {"torn_down": True}
+        return 404, {"error": "no such bottle"}
+
+    if method == "POST" and route == "/reconcile":
+        # Host-driven self-heal trigger: the orchestrator pulls its own live set
+        # from the host controller (`list_live`) and drops rows for every other
+        # active bottle — the caller no longer supplies the live IPs. Trusted-
+        # caller only: an agent that could reach this would trigger a sweep that
+        # unregisters its neighbours. Body is optional (just `grace_seconds`).
+        try:
+            data = _parse_json_object(body)
+        except ValueError as e:
+            return 400, {"error": f"invalid JSON: {e}"}
+        grace = data.get("grace_seconds")
+        kwargs: dict[str, float] = {}
+        if grace is not None:
+            if isinstance(grace, bool) or not isinstance(grace, (int, float)):
+                return 400, {"error": "grace_seconds must be a non-negative finite number"}
+            parsed_grace = float(grace)
+            if not math.isfinite(parsed_grace) or parsed_grace < 0:
+                return 400, {"error": "grace_seconds must be a non-negative finite number"}
+            kwargs["grace_seconds"] = parsed_grace
+        return 200, {"reaped": orch.reconcile(**kwargs)}
+
+    if method == "POST" and route == "/attribute":
+        try:
+            data = _parse_json_object(body)
+        except ValueError as e:
+            return 400, {"error": f"invalid JSON: {e}"}
+        source_ip = data.get("source_ip")
+        token = data.get("identity_token")
+        if not isinstance(source_ip, str) or not isinstance(token, str):
+            return 400, {"error": "source_ip and identity_token (strings) required"}
+        rec = orch.attribute(source_ip, token)
+        if rec is None:
+            return 403, {"error": "unattributed"}
+        return 200, {"bottle_id": rec.bottle_id}
+
+    if method == "GET" and route == "/supervise/proposals":
+        # Operator TUI: pending supervise proposals across all bottles.
+        return 200, {"proposals": orch.supervise_pending()}
+
+    if method == "POST" and route == "/supervise/respond":
+        # Operator decision: apply (approve/modify rewrites egress policy),
+        # write the queued response, audit — all server-side on the one DB.
+        try:
+            data = _parse_json_object(body)
+        except ValueError as e:
+            return 400, {"error": f"invalid JSON: {e}"}
+        proposal_id = data.get("proposal_id")
+        bottle_slug = data.get("bottle_slug")
+        decision = data.get("decision")
+        if not (isinstance(proposal_id, str) and proposal_id):
+            return 400, {"error": "proposal_id (string) is required"}
+        if not (isinstance(bottle_slug, str) and bottle_slug):
+            return 400, {"error": "bottle_slug (string) is required"}
+        if not (isinstance(decision, str) and decision):
+            return 400, {"error": "decision (string) is required"}
+        notes = data.get("notes")
+        final_file = data.get("final_file")
+        ok, err = orch.supervise_respond(
+            proposal_id,
+            bottle_slug=bottle_slug,
+            decision=decision,
+            notes=notes if isinstance(notes, str) else "",
+            final_file=final_file if isinstance(final_file, str) else None,
+        )
+        if ok:
+            return 200, {"responded": True}
+        return 409, {"error": err}
+
+    if method == "POST" and route == "/supervise/propose":
+        # Agent half: queue a proposal, attributed to the caller resolved from
+        # (source_ip, identity_token) — never a caller-supplied slug — so the
+        # data plane can't forge attribution. Fail-closed 403 when unattributed.
+        try:
+            data = _parse_json_object(body)
+        except ValueError as e:
+            return 400, {"error": f"invalid JSON: {e}"}
+        source_ip = data.get("source_ip")
+        token = data.get("identity_token")
+        tool = data.get("tool")
+        proposed_file = data.get("proposed_file")
+        justification = data.get("justification")
+        if not isinstance(source_ip, str) or not source_ip:
+            return 400, {"error": "source_ip (string) is required"}
+        if not isinstance(tool, str) or tool not in TOOLS:
+            return 400, {"error": f"tool (string) must be one of {TOOLS}"}
+        if not isinstance(proposed_file, str) or not proposed_file:
+            return 400, {"error": "proposed_file (string) is required"}
+        if not isinstance(justification, str) or not justification:
+            return 400, {"error": "justification (string) is required"}
+        rec = orch.resolve(source_ip, token if isinstance(token, str) else "")
+        if rec is None:
+            return 403, {"error": "unattributed"}
+        proposal_id = orch.supervise_queue_proposal(
+            rec.bottle_id, tool=tool, proposed_file=proposed_file,
+            justification=justification,
+        )
+        return 201, {"proposal_id": proposal_id}
+
+    if method == "POST" and route == "/supervise/poll":
+        # Agent half: non-blocking read of the caller's own proposal decision.
+        # Attributed like /propose, and scoped to the resolved bottle id, so a
+        # guessed proposal_id can never read another bottle's response.
+        try:
+            data = _parse_json_object(body)
+        except ValueError as e:
+            return 400, {"error": f"invalid JSON: {e}"}
+        source_ip = data.get("source_ip")
+        token = data.get("identity_token")
+        proposal_id = data.get("proposal_id")
+        if not isinstance(source_ip, str) or not source_ip:
+            return 400, {"error": "source_ip (string) is required"}
+        if not isinstance(proposal_id, str) or not proposal_id:
+            return 400, {"error": "proposal_id (string) is required"}
+        rec = orch.resolve(source_ip, token if isinstance(token, str) else "")
+        if rec is None:
+            return 403, {"error": "unattributed"}
+        return 200, orch.supervise_poll_response(rec.bottle_id, proposal_id)
+
+    if method == "POST" and route == "/resolve":
+        # The per-request lookup the multi-tenant gateway makes: returns the
+        # bottle's policy. Requires a matching (source_ip, identity_token)
+        # pair — a missing/empty/mismatched token fail-closes (403), no
+        # source-IP-only fallback.
+        try:
+            data = _parse_json_object(body)
+        except ValueError as e:
+            return 400, {"error": f"invalid JSON: {e}"}
+        source_ip = data.get("source_ip")
+        token = data.get("identity_token")
+        if not isinstance(source_ip, str) or not source_ip:
+            return 400, {"error": "source_ip (string) is required"}
+        rec = orch.resolve(source_ip, token if isinstance(token, str) else "")
+        if rec is None:
+            return 403, {"error": "unattributed"}
+        # tokens are the in-memory per-bottle egress auth values the gateway
+        # injects; served here, never persisted.
+        return 200, {
+            "bottle_id": rec.bottle_id,
+            "policy": rec.policy,
+            "tokens": orch.tokens_for(rec.bottle_id),
+        }
+
+    return 404, {"error": "not found"}
+
+
+class Handler(http.server.BaseHTTPRequestHandler):
+    """Thin stdlib adapter: read the body, call `dispatch`, write JSON."""
+
+    # Quiet by default (the orchestrator has its own logging); opt back into
+    # stdlib access logging with BOT_BOTTLE_ORCHESTRATOR_DEBUG.
+    def log_message(self, format: str, *args: typing.Any) -> None:  # noqa: A002
+        if os.environ.get("BOT_BOTTLE_ORCHESTRATOR_DEBUG"):
+            super().log_message(format, *args)
+
+    def _serve(self, method: str) -> None:
+        """Read the request body, dispatch it, and write the JSON reply. A
+        dispatch failure (e.g. a broker error) returns a 500 rather than
+        crashing the connection, so one bad request can't take the control
+        plane down for the caller."""
+        server = self.server
+        assert isinstance(server, OrchestratorServer)
+        length = int(self.headers.get("Content-Length") or 0)
+        body = self.rfile.read(length) if length > 0 else b""
+        role = server.role_for(self.headers.get(ORCHESTRATOR_AUTH_HEADER, ""))
+        try:
+            status, payload = dispatch(
+                server.orchestrator, method, self.path, body, role=role)
+        except Exception as e:  # noqa: BLE001 — the control plane must stay up
+            # Do not echo exception messages to the caller or logs: broker and
+            # persistence exceptions can contain request data. The operation,
+            # route, and exception type are enough to correlate a traceback.
+            sys.stderr.write(
+                f"orchestrator: {method} {self.path} failed "
+                f"[error_type={type(e).__name__}]\n"
+            )
+            sys.stderr.flush()
+            status, payload = 500, {"error": "internal error"}
+        data = json.dumps(payload).encode()
+        self.send_response(status)
+        self.send_header("Content-Type", "application/json")
+        self.send_header("Content-Length", str(len(data)))
+        self.end_headers()
+        self.wfile.write(data)
+
+    def do_GET(self) -> None:
+        self._serve("GET")
+
+    def do_POST(self) -> None:
+        self._serve("POST")
+
+    def do_PUT(self) -> None:
+        self._serve("PUT")
+
+    def do_DELETE(self) -> None:
+        self._serve("DELETE")
+
+
+class OrchestratorServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
+    """Threading HTTP server that carries the orchestrator for its handlers.
+
+    Holds the per-host control-plane *signing key* (from
+    `$BOT_BOTTLE_ORCHESTRATOR_TOKEN`, injected by the launcher into the
+    orchestrator process only) and verifies each request's role-scoped token
+    against it. When a key is set, every route but `/health` requires a valid
+    token whose role covers the route; when it is unset the server runs **open**
+    (full `cli` access) and says so loudly at startup — a fail-visible fallback
+    for tests and any backend that hasn't wired the key yet (e.g. Firecracker,
+    whose nft boundary already blocks agents from the control-plane port)."""
+
+    daemon_threads = True
+    allow_reuse_address = True
+
+    def __init__(self, address: tuple[str, int], orchestrator: OrchestratorCore) -> None:
+        self.orchestrator = orchestrator
+        # The control-plane trust domain's signing key, as injected into THIS
+        # (the owning) process by the launcher (#476). Unset → open mode below.
+        self._signing_key = CONTROL_PLANE.key_from_env()
+        if not self._signing_key:
+            sys.stderr.write(
+                "orchestrator: WARNING — no control-plane signing key "
+                f"(${CONTROL_PLANE.key_env}); running WITHOUT caller "
+                "authentication. Any client that can reach this port can drive "
+                "it. Backends that put the control plane on an agent-reachable "
+                "network MUST set this.\n"
+            )
+            sys.stderr.flush()
+        super().__init__(address, Handler)
+
+    def role_for(self, presented: str) -> str | None:
+        """The role the request is authorized as, or None if unauthenticated.
+        Open mode (no signing key) grants full `cli` access — the fail-visible
+        fallback. Otherwise verify the presented signed token; a missing/invalid
+        token yields None (→ 401), a valid one yields its `gateway`/`cli`
+        role (→ per-route 401/403 in `dispatch`)."""
+        if not self._signing_key:
+            return ROLE_CLI
+        return CONTROL_PLANE.verify(presented, self._signing_key)
 
 
 def make_server(
-    orchestrator: OrchestratorCore,
-    host: str = "127.0.0.1",
-    port: int = 0,
-    *,
-    signing_key: str | None = None,
+    orchestrator: OrchestratorCore, host: str = "127.0.0.1", port: int = 0
 ) -> OrchestratorServer:
-    """Build a bounded Uvicorn server around the orchestrator application."""
-    key = CONTROL_PLANE.key_from_env() if signing_key is None else signing_key
-    app = create_app(orchestrator, signing_key=key)
-    config = uvicorn.Config(
-        app,
-        host=host,
-        port=port,
-        access_log=bool(os.environ.get("BOT_BOTTLE_ORCHESTRATOR_DEBUG")),
-        log_level="info",
-        limit_concurrency=MAX_REQUESTS,
-        timeout_keep_alive=KEEP_ALIVE_TIMEOUT_SECONDS,
-        server_header=False,
-    )
-    return OrchestratorServer(config)
+    """Build (but do not start) a control-plane server. `port=0` binds an
+    ephemeral port — read `server.server_address` for the actual one."""
+    return OrchestratorServer((host, port), orchestrator)
 
 
 __all__ = [
-    "KEEP_ALIVE_TIMEOUT_SECONDS",
-    "MAX_BODY_BYTES",
-    "MAX_REQUESTS",
+    "dispatch", "Handler", "OrchestratorServer", "make_server", "Json",
     "ORCHESTRATOR_AUTH_HEADER",
-    "OrchestratorServer",
-    "create_app",
-    "make_server",
 ]

bot_bottle/orchestrator/service.py

@@ -22,10 +22,17 @@ Launch lifecycle:
 from __future__ import annotations
 
 import json
-from collections.abc import Iterable
 from datetime import datetime, timezone
 
-from .broker import LaunchBroker, LaunchRequest, sign_request
+from .. import log
+from .broker import (
+    BrokerAuthError,
+    BrokerUnavailableError,
+    LaunchRequest,
+    SubmitBroker,
+    sign_request,
+)
+from .broker_client import BrokerClientError
 from .store.registry_store import DEFAULT_REAP_GRACE_SECONDS, BottleRecord, RegistryStore
 from .supervisor import (
     AuditEntry,
@@ -62,7 +69,7 @@ class OrchestratorCore:
     def __init__(
         self,
         registry: RegistryStore,
-        broker: LaunchBroker,
+        broker: SubmitBroker,
         sign_secret: bytes,
         supervisor: Supervisor | None = None,
     ) -> None:
@@ -111,14 +118,23 @@ class OrchestratorCore:
             image_ref=image_ref,
             slot=slot,
         )
-        launched = False
         try:
             self._broker.submit(sign_request(req, self._secret))
-            launched = True
-        finally:
-            if not launched:
-                self.registry.deregister(rec.bottle_id)
-                self._tokens.pop(rec.bottle_id, None)
+        except BrokerUnavailableError:
+            # Ambiguous delivery failure (timeout / dropped response): the broker
+            # may already have launched the bottle before the response was lost.
+            # Do NOT deregister — that would orphan a running container with no
+            # registry row (reconcile reaps rows, never containers). Keep the row
+            # so reconcile reaps it iff the bottle is not actually live; surface
+            # the error so the caller knows the launch is unconfirmed.
+            raise
+        except Exception:
+            # A definite failure — a fail-closed rejection, a backend launch
+            # error, or the host reporting it did not launch: nothing is running,
+            # so roll the registry entry back to leave no orphan.
+            self.registry.deregister(rec.bottle_id)
+            self._tokens.pop(rec.bottle_id, None)
+            raise
         return rec
 
     def teardown_bottle(self, bottle_id: str) -> bool:
@@ -136,22 +152,36 @@ class OrchestratorCore:
 
     def reconcile(
         self,
-        live_source_ips: Iterable[str],
         *,
         grace_seconds: float = DEFAULT_REAP_GRACE_SECONDS,
     ) -> list[str]:
         """Drop registry rows for bottles that are no longer running, and
         forget their in-memory egress tokens. Returns the reaped bottle ids.
 
-        The caller supplies the live set because only the host can enumerate
-        its own containers — the orchestrator runs *inside* the infra
-        container and has no view of the backend. Deliberately does not
-        broker a teardown: the container is already gone, so there is nothing
-        to stop, and a broker error must not stop the sweep from clearing
-        the row that would otherwise brick the next bottle at that address.
+        The live set is pulled from the **broker** (`list_live`), not passed in:
+        only the host can enumerate its own containers, and the host controller
+        is now that host component, so the orchestrator — blind to the backend
+        from inside its container — asks it over the same signed seam it launches
+        through. (Before the host control server this was a `live_source_ips`
+        argument the CLI handed in; the tell that the orchestrator couldn't see
+        the backend goes away with it — PRD gap 3.)
+
+        Fail-safe: if the broker can't return an authoritative live set
+        (unreachable, timed out, enumeration failed), the sweep is **skipped**,
+        never run against an empty/partial set — reaping a healthy bottle is far
+        worse than leaving an orphan one more cycle. Deliberately does not broker
+        a teardown: a reaped container is already gone, so there is nothing to
+        stop.
 
         See `RegistryStore.reap_absent` for why orphans accumulate and why
         they are harmful rather than merely untidy."""
+        token = sign_request(LaunchRequest(op="list_live"), self._secret)
+        try:
+            live_source_ips = self._broker.list_live(token)
+        except (BrokerUnavailableError, BrokerAuthError, BrokerClientError) as e:
+            log.info("reconcile skipped: live set unavailable",
+                     context={"error": str(e)})
+            return []
         reaped = self.registry.reap_absent(
             live_source_ips, grace_seconds=grace_seconds)
         for rec in reaped:
@@ -366,23 +396,15 @@ class OrchestratorCore:
         value with *env_var_secret*, and restores ``_tokens[bottle_id]``.
         Returns True on success, False when no stored secrets exist for this
         bottle or decryption fails (wrong key / corrupt data)."""
-        from .store.secret_store import decrypt_value, encrypt_value, is_legacy_blob
+        from .store.secret_store import decrypt_value
         encrypted = self.registry.get_agent_secrets(bottle_id)
         if not encrypted:
             return False
         try:
-            decrypted = {
-                k: decrypt_value(env_var_secret, v) for k, v in encrypted.items()
-            }
+            self._tokens[bottle_id] = {k: decrypt_value(env_var_secret, v)
+                                       for k, v in encrypted.items()}
         except ValueError:
             return False
-        self._tokens[bottle_id] = decrypted
-        if any(is_legacy_blob(value) for value in encrypted.values()):
-            migrated = {
-                key: encrypt_value(env_var_secret, value)
-                for key, value in decrypted.items()
-            }
-            self.registry.store_agent_secrets(bottle_id, migrated)
         return True
 
     # --- consolidated gateway ----------------------------------------------

bot_bottle/orchestrator/store/secret_store.py

@@ -12,18 +12,22 @@ reattachment path reads ENV_VAR_SECRET from the running agent container via
 ``POST /bottles/<id>/reprovision_gateway``; the orchestrator decrypts the
 stored rows and re-populates ``_tokens``.
 
-Encryption scheme: encrypt-then-MAC using independent HMAC-SHA256-derived
-encryption and authentication subkeys (stdlib-only, no external deps). Each
-value is encrypted independently. New output blobs are:
-
-``version || nonce (16 bytes) || ciphertext || tag (32 bytes)``
-
-encoded as URL-safe base64 (no padding). The version marker lets the reader
-accept legacy ``nonce || ciphertext`` rows long enough to rewrite them in the
-authenticated format after a successful reprovision.
+Encryption scheme: HMAC-SHA256 used as a PRF in CTR mode, **authenticated**
+encrypt-then-MAC (stdlib-only, no external deps). Each value is encrypted
+independently. The output blob is ``nonce (16 bytes) || ciphertext || tag
+(32 bytes)`` encoded as URL-safe base64 (no padding).
 
     keystream_block_i = HMAC-SHA256(key, nonce || i.to_bytes(4, "big"))
     ciphertext_i      = plaintext_i XOR keystream_block_i[:len(plaintext_i)]
+    mac_key           = HMAC-SHA256(key, "bottled-secret-mac-v1")
+    tag               = HMAC-SHA256(mac_key, nonce || ciphertext)
+
+The tag is what makes a **wrong key deterministically detectable**: without it,
+CTR decryption with the wrong key yields garbage that only fails when it isn't
+valid UTF-8 (so ``reprovision`` would sometimes "succeed" with a wrong
+ENV_VAR_SECRET and inject garbage egress tokens). The MAC key is derived from
+the ENV_VAR_SECRET by a domain-separated HMAC so the same key never both
+generates the keystream and signs the tag with the same message shape.
 """
 
 from __future__ import annotations
@@ -35,9 +39,8 @@ import secrets
 
 _KEY_BYTES = 32    # 256-bit key from ENV_VAR_SECRET
 _NONCE_BYTES = 16  # 128-bit random nonce per encrypt call
+_TAG_BYTES = 32    # HMAC-SHA256 authentication tag
 _BLOCK = 32        # HMAC-SHA256 output width == one keystream block
-_TAG_BYTES = 32
-_VERSION = b"BBSE1"
 
 # Env-var name the agent container receives at startup.
 ENV_VAR_SECRET_NAME = "ENV_VAR_SECRET"
@@ -49,13 +52,7 @@ def new_env_var_secret() -> str:
 
 
 def _b64dec(s: str) -> bytes:
-    return base64.b64decode(
-        s + "=" * (-len(s) % 4), altchars=b"-_", validate=True,
-    )
-
-
-def _subkey(key: bytes, purpose: bytes) -> bytes:
-    return hmac.new(key, b"bot-bottle-secret-store:" + purpose, hashlib.sha256).digest()
+    return base64.urlsafe_b64decode(s + "=" * (-len(s) % 4))
 
 
 def _keystream(key: bytes, nonce: bytes, block_index: int) -> bytes:
@@ -64,93 +61,58 @@ def _keystream(key: bytes, nonce: bytes, block_index: int) -> bytes:
     ).digest()
 
 
+def _tag(key: bytes, nonce: bytes, ciphertext: bytes) -> bytes:
+    """The authentication tag over ``nonce || ciphertext``, keyed by a MAC
+    subkey domain-separated from the keystream key."""
+    mac_key = hmac.new(key, b"bottled-secret-mac-v1", hashlib.sha256).digest()
+    return hmac.new(mac_key, nonce + ciphertext, hashlib.sha256).digest()
+
+
+def _ctr(key: bytes, nonce: bytes, data: bytes) -> bytes:
+    """CTR keystream XOR — its own inverse, so it both encrypts and decrypts."""
+    out = bytearray()
+    for i in range(0, len(data), _BLOCK):
+        chunk = data[i : i + _BLOCK]
+        ks = _keystream(key, nonce, i)[: len(chunk)]
+        out.extend(b ^ k for b, k in zip(chunk, ks))
+    return bytes(out)
+
+
 def encrypt_value(secret_b64: str, plaintext: str) -> str:
     """Encrypt a single string value with *secret_b64* (the ENV_VAR_SECRET).
 
-    Returns a URL-safe base64 authenticated blob suitable for
+    Returns a URL-safe base64 blob ``nonce || ciphertext || tag`` suitable for
     the ``bottled_agent_secrets.value`` column."""
     key = _b64dec(secret_b64)
-    encryption_key = _subkey(key, b"encryption")
-    authentication_key = _subkey(key, b"authentication")
-    pt = plaintext.encode()
     nonce = secrets.token_bytes(_NONCE_BYTES)
-    ct = bytearray()
-    for i in range(0, len(pt), _BLOCK):
-        chunk = pt[i : i + _BLOCK]
-        ks = _keystream(encryption_key, nonce, i // _BLOCK)[: len(chunk)]
-        ct.extend(p ^ k for p, k in zip(chunk, ks))
-    authenticated = _VERSION + nonce + bytes(ct)
-    tag = hmac.new(authentication_key, authenticated, hashlib.sha256).digest()
-    return base64.urlsafe_b64encode(authenticated + tag).rstrip(b"=").decode()
-
-
-def is_legacy_blob(blob_b64: str) -> bool:
-    """Whether *blob_b64* uses the pre-authentication storage format."""
-    try:
-        return not _b64dec(blob_b64).startswith(_VERSION)
-    except (ValueError, TypeError):
-        return False
-
-
-def _decrypt_legacy(key: bytes, blob: bytes) -> str:
-    """Read the original ``nonce || ciphertext`` format for migration only."""
-    if len(blob) < _NONCE_BYTES:
-        raise ValueError("ciphertext blob too short")
-    nonce, ciphertext = blob[:_NONCE_BYTES], blob[_NONCE_BYTES:]
-    pt = bytearray()
-    # The legacy format used the byte offset as the PRF counter.
-    for i in range(0, len(ciphertext), _BLOCK):
-        chunk = ciphertext[i : i + _BLOCK]
-        ks = _keystream(key, nonce, i)[: len(chunk)]
-        pt.extend(c ^ k for c, k in zip(chunk, ks))
-    try:
-        return bytes(pt).decode()
-    except UnicodeDecodeError as exc:
-        raise ValueError(f"decryption produced non-UTF-8 output: {exc}") from exc
+    ct = _ctr(key, nonce, plaintext.encode())
+    tag = _tag(key, nonce, ct)
+    return base64.urlsafe_b64encode(nonce + ct + tag).rstrip(b"=").decode()
 
 
 def decrypt_value(secret_b64: str, blob_b64: str) -> str:
     """Decrypt a blob produced by :func:`encrypt_value`.
 
     Returns the original plaintext string. Raises ``ValueError`` for malformed
-    input, authentication failure, or a key mismatch. Legacy unauthenticated
-    rows remain readable so callers can migrate them immediately."""
+    input, a **wrong key**, or a tampered ciphertext — all caught by the
+    authentication tag before any plaintext is returned, so a wrong
+    ENV_VAR_SECRET is rejected deterministically (never a garbage token)."""
     key = _b64dec(secret_b64)
     try:
         blob = _b64dec(blob_b64)
-    except (ValueError, TypeError) as exc:
+    except Exception as exc:
         raise ValueError(f"invalid ciphertext blob: {exc}") from exc
-    if not blob.startswith(_VERSION):
-        return _decrypt_legacy(key, blob)
-    minimum = len(_VERSION) + _NONCE_BYTES + _TAG_BYTES
-    if len(blob) < minimum:
+    if len(blob) < _NONCE_BYTES + _TAG_BYTES:
         raise ValueError("ciphertext blob too short")
-    authenticated, supplied_tag = blob[:-_TAG_BYTES], blob[-_TAG_BYTES:]
-    authentication_key = _subkey(key, b"authentication")
-    expected_tag = hmac.new(
-        authentication_key, authenticated, hashlib.sha256,
-    ).digest()
-    if not hmac.compare_digest(supplied_tag, expected_tag):
-        raise ValueError("ciphertext authentication failed")
-    nonce_start = len(_VERSION)
-    nonce = blob[nonce_start : nonce_start + _NONCE_BYTES]
-    ciphertext = blob[nonce_start + _NONCE_BYTES : -_TAG_BYTES]
-    encryption_key = _subkey(key, b"encryption")
-    pt = bytearray()
-    for i in range(0, len(ciphertext), _BLOCK):
-        chunk = ciphertext[i : i + _BLOCK]
-        ks = _keystream(encryption_key, nonce, i // _BLOCK)[: len(chunk)]
-        pt.extend(c ^ k for c, k in zip(chunk, ks))
+    nonce = blob[:_NONCE_BYTES]
+    tag = blob[-_TAG_BYTES:]
+    ciphertext = blob[_NONCE_BYTES:-_TAG_BYTES]
+    if not hmac.compare_digest(tag, _tag(key, nonce, ciphertext)):
+        raise ValueError("ciphertext failed authentication (wrong key or tampered)")
     try:
-        return bytes(pt).decode()
-    except UnicodeDecodeError as exc:
-        raise ValueError(f"decryption produced non-UTF-8 output (wrong key?): {exc}") from exc
+        return _ctr(key, nonce, ciphertext).decode()
+    except UnicodeDecodeError as exc:  # pragma: no cover - authenticated, so unreachable
+        raise ValueError(f"decryption produced non-UTF-8 output: {exc}") from exc
 
 
-__all__ = [
-    "ENV_VAR_SECRET_NAME",
-    "new_env_var_secret",
-    "encrypt_value",
-    "decrypt_value",
-    "is_legacy_blob",
-]
+__all__ = ["ENV_VAR_SECRET_NAME", "new_env_var_secret", "encrypt_value", "decrypt_value"]

bot_bottle/orchestrator_auth.py

@@ -36,6 +36,13 @@ ROLE_GATEWAY = "gateway"
 ROLE_CLI = "cli"
 ROLES: frozenset[str] = frozenset({ROLE_GATEWAY, ROLE_CLI})
 
+# The host controller's own lifecycle role (#468). Deliberately OUTSIDE `ROLES`:
+# it belongs to a separate trust domain (`HOST_CONTROLLER`) signed by a key the
+# orchestrator never holds, so the orchestrator's control-plane key can neither
+# mint nor accept it — the orchestrator must not be able to forge the credential
+# used to start and stop it.
+ROLE_HOST = "host"
+
 _ALG = "HS256"
 
 
@@ -103,4 +110,4 @@ def verify(token: str, secret: str, *, roles: frozenset[str] = ROLES) -> str | N
     return role if isinstance(role, str) and role in roles else None
 
 
-__all__ = ["ROLE_GATEWAY", "ROLE_CLI", "ROLES", "mint", "verify"]
+__all__ = ["ROLE_GATEWAY", "ROLE_CLI", "ROLE_HOST", "ROLES", "mint", "verify"]

bot_bottle/paths.py

@@ -47,6 +47,22 @@ ORCHESTRATOR_TOKEN_ENV = "BOT_BOTTLE_ORCHESTRATOR_TOKEN"
 # cannot forge a higher-privilege `cli` token (issue #469 review).
 ORCHESTRATOR_AUTH_JWT_ENV = "BOT_BOTTLE_ORCHESTRATOR_AUTH_JWT"
 
+# The durable launch-broker signing key: the HS256 secret the orchestrator
+# (signer) and the host control server (verifier) share to sign/verify launch
+# requests (#468). A host-canonical key file (minted 0600 on first use) so it
+# survives orchestrator restarts — re-adoption re-verifies against the same key —
+# instead of the ephemeral per-process secret of the in-process broker.
+LAUNCH_BROKER_KEY_FILENAME = "launch-broker-key"
+LAUNCH_BROKER_KEY_ENV = "BOT_BOTTLE_LAUNCH_BROKER_KEY"
+# The host controller's OWN key, for its lifecycle endpoints (the direct
+# cli -> host controller path that starts/stops the orchestrator). Separate from
+# the launch-broker key and never held by the orchestrator: the controller starts
+# and stops the orchestrator, so the orchestrator must not be able to mint the
+# credentials used to drive it (#468/#476).
+HOST_CONTROLLER_KEY_FILENAME = "host-controller-key"
+HOST_CONTROLLER_KEY_ENV = "BOT_BOTTLE_HOST_CONTROLLER_KEY"
+HOST_CONTROLLER_AUTH_JWT_ENV = "BOT_BOTTLE_HOST_CONTROLLER_AUTH_JWT"
+
 # The host directory holding the gateway's persistent mitmproxy CA. Bind-mounted
 # into the infra/gateway container at mitmproxy's confdir so the self-generated
 # CA survives container recreation — every agent installs this one CA to trust
@@ -142,6 +158,11 @@ __all__ = [
     "ORCHESTRATOR_TOKEN_FILENAME",
     "ORCHESTRATOR_TOKEN_ENV",
     "ORCHESTRATOR_AUTH_JWT_ENV",
+    "LAUNCH_BROKER_KEY_FILENAME",
+    "LAUNCH_BROKER_KEY_ENV",
+    "HOST_CONTROLLER_KEY_FILENAME",
+    "HOST_CONTROLLER_KEY_ENV",
+    "HOST_CONTROLLER_AUTH_JWT_ENV",
     "GATEWAY_CA_DIRNAME",
     "bot_bottle_root",
     "host_db_path",

bot_bottle/resources.py

@@ -44,7 +44,6 @@ BUNDLED_RESOURCES: tuple[str, ...] = (
     "Dockerfile.orchestrator",
     "Dockerfile.orchestrator.fc",
     "requirements.gateway.lock",
-    "requirements.orchestrator.lock",
     "nix/firecracker-netpool.nix",
     "scripts/firecracker-netpool.sh",
 )

bot_bottle/trust_domain.py

@@ -29,8 +29,13 @@ from collections.abc import Mapping
 from dataclasses import dataclass
 
 from . import orchestrator_auth
-from .orchestrator_auth import ROLE_GATEWAY
+from .orchestrator_auth import ROLE_GATEWAY, ROLE_HOST
 from .paths import (
+    HOST_CONTROLLER_AUTH_JWT_ENV,
+    HOST_CONTROLLER_KEY_ENV,
+    HOST_CONTROLLER_KEY_FILENAME,
+    LAUNCH_BROKER_KEY_ENV,
+    LAUNCH_BROKER_KEY_FILENAME,
     ORCHESTRATOR_AUTH_JWT_ENV,
     ORCHESTRATOR_TOKEN_ENV,
     ORCHESTRATOR_TOKEN_FILENAME,
@@ -40,7 +45,7 @@ from .paths import (
 
 class ProvisioningError(RuntimeError):
     """A control-plane auth invariant would be violated (e.g. starting the
-    orchestrator without its signing key)."""
+    orchestrator without its signing key — which would run OPEN)."""
 
 
 @dataclass(frozen=True)
@@ -67,8 +72,9 @@ class TrustDomain:
 
     def key_from_env(self, environ: Mapping[str, str] | None = None) -> str:
         """The signing key as the owning process sees it — read from `key_env`
-        (default `os.environ`). ``""`` when unset; owning services reject that
-        value rather than start without authentication."""
+        (default `os.environ`). "" when unset; the caller decides whether that is
+        fatal (`ControlPlaneProvisioning`) or the open-mode fallback
+        (`OrchestratorServer`)."""
         env = os.environ if environ is None else environ
         return env.get(self.key_env, "").strip()
 
@@ -98,6 +104,40 @@ CONTROL_PLANE = TrustDomain(
 )
 
 
+# The launch-broker domain (#468): durable key material for the broker's own
+# signed launch requests (`broker.py`'s HS256 launch JWT), shared by the
+# orchestrator (signer) and the host control server (verifier). Unlike
+# `CONTROL_PLANE` it mints no role tokens — the broker's provenance is the launch
+# JWT, not a role token — so its `roles` set is empty and it is used only as a
+# provider of durable, host-canonical key material (`signing_key` / `key_from_env`).
+# The durability is the point: the key survives orchestrator restarts, so a
+# restarted orchestrator re-verifies against the same key instead of the
+# ephemeral per-process secret the in-process broker used.
+LAUNCH_BROKER = TrustDomain(
+    name="launch-broker",
+    key_filename=LAUNCH_BROKER_KEY_FILENAME,
+    roles=frozenset(),
+    key_env=LAUNCH_BROKER_KEY_ENV,
+    token_env="",
+)
+
+# The host controller's own domain (#468) — the SECOND domain #476 reserves. Its
+# key, which the orchestrator never holds, signs the `host`-role tokens the CLI
+# presents on the host controller's lifecycle endpoints (start / restart / status
+# of the orchestrator itself). Keeping it separate from `CONTROL_PLANE` is the
+# whole point: the host controller starts and stops the orchestrator, so the
+# orchestrator must not be able to mint the credentials used to drive it. (The
+# lifecycle endpoints themselves arrive in a later chunk; the domain is
+# established here alongside the durable launch-broker key.)
+HOST_CONTROLLER = TrustDomain(
+    name="host-controller",
+    key_filename=HOST_CONTROLLER_KEY_FILENAME,
+    roles=frozenset({ROLE_HOST}),
+    key_env=HOST_CONTROLLER_KEY_ENV,
+    token_env=HOST_CONTROLLER_AUTH_JWT_ENV,
+)
+
+
 @dataclass(frozen=True)
 class ControlPlaneProvisioning:
     """The one seam every backend launcher uses to provision control-plane auth,
@@ -131,9 +171,56 @@ class ControlPlaneProvisioning:
         return self.domain.mint(ROLE_GATEWAY)
 
 
+@dataclass(frozen=True)
+class LaunchBrokerProvisioning:
+    """The seam that provisions the host-side launch broker's durable keys (#468),
+    the counterpart to `ControlPlaneProvisioning`. Both the orchestrator (signer)
+    and the host control server (verifier) receive the SAME launch-broker key
+    (carry it in `broker_domain.key_env`); the host controller ALSO receives its
+    own lifecycle key (`controller_domain.key_env`) the orchestrator never holds.
+
+    Fail-closed like the control-plane seam: minting returns "" only if the host
+    root is unwritable, and an empty launch-broker key would leave the verifier
+    unable to authenticate any launch — so we raise rather than hand back a key
+    that would make the host controller reject (or, if a caller defaulted it,
+    accept) unsigned input."""
+
+    broker_domain: TrustDomain = LAUNCH_BROKER
+    controller_domain: TrustDomain = HOST_CONTROLLER
+
+    def broker_key(self) -> str:
+        """The durable launch-broker key both the orchestrator and the host
+        control server must receive (in `broker_domain.key_env`). Raises rather
+        than return ""."""
+        key = self.broker_domain.signing_key()
+        if not key:
+            raise ProvisioningError(
+                f"refusing to provision the {self.broker_domain.name} broker "
+                "without a signing key: the host controller could then verify no "
+                "launch request's provenance"
+            )
+        return key
+
+    def controller_key(self) -> str:
+        """The host controller's own lifecycle key — provisioned ONLY to the host
+        controller (in `controller_domain.key_env`), never to the orchestrator, so
+        the orchestrator cannot mint the `host`-role tokens that start and stop
+        it. Raises rather than return ""."""
+        key = self.controller_domain.signing_key()
+        if not key:
+            raise ProvisioningError(
+                f"refusing to provision the {self.controller_domain.name} without "
+                "a signing key: its lifecycle endpoints would authenticate no one"
+            )
+        return key
+
+
 __all__ = [
     "ProvisioningError",
     "TrustDomain",
     "CONTROL_PLANE",
+    "LAUNCH_BROKER",
+    "HOST_CONTROLLER",
     "ControlPlaneProvisioning",
+    "LaunchBrokerProvisioning",
 ]

docs/decisions/0004-coverage-policy.md

@@ -3,10 +3,6 @@
 - **Status:** Accepted
 - **Date:** 2026-06-25
 - **Deciders:** didericis
-- **Revised:** 2026-07-27 — thresholds relaxed (critical minimum 90→85%,
-  diff-coverage gate 90→80%) to cut low-value test churn on changed lines.
-  The risk-weighting structure and the "global is informational" rule are
-  unchanged.
 
 ## Context
 
@@ -38,7 +34,7 @@ a regression (Goodhart's law).
 Coverage is **risk-weighted**, measured over the **combined unit +
 integration** suites, with three rules:
 
-1. **Critical modules must remain ≥ 85%.** The curated security/logic core
+1. **Critical modules must remain ≥ 90%.** The curated security/logic core
    covers the host and gateway egress policy, manifest trust boundary,
    git-gate enforcement, supervise protocol/server, YAML parser, and bottle
    state. The concrete module list lives in `scripts/critical-modules.txt`;
@@ -59,7 +55,7 @@ integration** suites, with three rules:
 
 The forward-looking guard is a **diff-coverage gate**
 (`scripts/diff_coverage.py`): new/changed executable lines on a branch
-must be ≥ 80% covered. This catches regressions where they are
+must be ≥ 90% covered. This catches regressions where they are
 introduced without forcing a back-fill crusade through legacy glue. The
 gate skips lines in omitted files (there is no coverage data for them),
 so the omit list cannot launder *new* logic into the dark: anything that

docs/prds/0079-control-plane-auth-provisioning.md

@@ -56,7 +56,8 @@ key.
 - Rewriting the HMAC primitive: `orchestrator_auth.mint/verify` gain an optional
   `roles=` arg (default unchanged) so a key can carry a different role set;
   nothing else changes.
-- Network topology or the plane split (#469).
+- Network topology, the plane split (#469), or the server's open-mode fallback
+  for tests.
 
 ## Design
 

docs/prds/0082-authoritative-failure-boundaries.md

@@ -1,197 +0,0 @@
-# PRD 0082: Authoritative failure boundaries
-
-- **Status:** Draft
-- **Author:** codex
-- **Created:** 2026-07-27
-- **Issue:** #444
-
-## Summary
-
-Make every security- or lifecycle-sensitive snapshot distinguish authoritative
-empty state from unavailable state, and make every destructive or
-resource-consuming boundary revalidate the assumptions it acts on. This
-finishes the focused quality work begun under #444 without broad rewrites:
-cleanup cannot act on stale identities, policy introspection cannot publish a
-fabricated empty policy, gateway servers bound untrusted work, and daemon
-shutdown does not emit uncaught background-thread failures. Shared
-control-plane storage and gateway credential provisioning also enforce their
-filesystem security contract before sensitive data is written.
-
-## Problem
-
-Several paths are individually fail-closed but compose into unsafe or
-misleading behavior:
-
-1. `cleanup` prepares a plan, waits indefinitely for operator confirmation,
-   then kills stored PIDs and removes stored paths without checking that those
-   identities still describe the same orphan. A PID may be reused or a run
-   directory may become active during the prompt.
-2. The supervisor reuses egress's deny-all fallback for
-   `list-egress-routes`. Deny-all is correct for enforcement, but presenting it
-   as a successful empty route table can cause a later replace-all proposal to
-   discard live routes.
-3. The supervisor and Git HTTP services accept bounded declared body sizes but
-   use blocking reads and unbounded request threads. An untrusted bottle can
-   exhaust the shared gateway with slow or parallel requests.
-4. macOS cleanup enumerates containers and networks independently and treats a
-   failed query as an empty class, so a partial snapshot can still become a
-   destructive plan.
-5. Gateway log-pump threads race stream closure during shutdown and emit
-   uncaught exceptions even when shutdown otherwise succeeds.
-6. Firecracker discovers VMs through whitespace-split `pgrep -a` output.
-   A configured cache path containing spaces can hide a live VM from the
-   snapshot and make its run directory appear orphaned.
-7. Docker cleanup asks compose for its project snapshot in best-effort mode.
-   A transient query failure can therefore become an empty stopped-project
-   set and authorize deletion of associated state directories.
-8. Firecracker artifact downloads and registry publication have no network
-   deadline, so an unresponsive registry can hold setup or release work
-   indefinitely.
-9. Authenticated secret blobs select the unauthenticated legacy decoder when
-   their in-band version prefix is changed, allowing storage tampering to
-   bypass tag verification.
-10. Cleanup executes the entire post-confirmation snapshot rather than the
-    intersection with what the operator saw, and mutation failures are not
-    reflected in the command result.
-11. Git smart-HTTP can retain sixteen 100 MiB request bodies concurrently,
-    cleanup mutations have no subprocess deadline, and Firecracker signalling
-    failures bypass shared mutation accounting.
-12. SQLite creates the shared control-plane database before its mode is
-    restricted, then suppresses permission-repair failures. Gateway transports
-    also differ in whether copied deploy-key modes are preserved.
-
-These are one design problem: state used to authorize deletion, replacement,
-or resource allocation must be authoritative at the point of use.
-
-## Goals / Success Criteria
-
-- Cleanup never signals a PID or recursively deletes a path solely because it
-  appeared in a pre-confirmation snapshot.
-- Firecracker cleanup proves immediately before action that a PID is still the
-  same Firecracker process and that a run directory is still orphaned.
-- Firecracker process discovery reads NUL-delimited argv from `/proc`; paths
-  are never reconstructed from whitespace-delimited process listings.
-- All backend cleanup discovery primitives raise a typed enumeration error on
-  operational failure. No backend may independently continue from a partial
-  snapshot.
-- Shared cleanup control flow lives in the backend layer; concrete backends
-  override resource-specific discovery and validation primitives rather than
-  each implementing a bespoke failure policy.
-- `list-egress-routes` returns an MCP error when attribution or policy
-  resolution is unavailable. A genuine, authoritatively resolved empty policy
-  remains a successful empty list.
-- Supervisor and Git HTTP request bodies have total read deadlines, and each
-  service bounds concurrent request work. Limits apply to authenticated
-  callers because bottles themselves are untrusted.
-- Gateway child-output pumping treats expected stream closure during shutdown
-  as completion while preserving diagnostics for unexpected failures.
-- Artifact pull, existence-check, and publication requests use explicit
-  network deadlines.
-- Persisted secrets accept only the authenticated format. The schema migration
-  intentionally clears legacy rows; local agents are reprovisioned rather
-  than retaining a ciphertext-controlled downgrade path.
-- Cleanup executes only resources present in both the displayed and current
-  authoritative plans, attempts every approved mutation, and returns failure
-  when any mutation does not complete.
-- Git request bodies spool to disk behind a separate heavy-work semaphore;
-  cleanup commands have configurable deadlines; Firecracker signalling
-  failures aggregate while identity-verification uncertainty still aborts.
-- The shared database directory and file are private before SQLite writes any
-  control-plane state; an inability to enforce those modes aborts startup.
-- Gateway credential directories and files receive explicit private modes
-  inside the gateway, independent of Docker, Apple Container, or SSH copy
-  semantics.
-- Unit tests cover PID/path reuse, partial backend enumeration, transient
-  policy resolution failure, slow bodies, concurrency saturation, and stream
-  closure races.
-
-## Non-goals
-
-- Further decomposition solely to reduce module line counts.
-- Replacing gateway stdlib HTTP services with a web framework.
-- Changing egress matching, DLP decisions, proposal semantics, or backend
-  launch behavior beyond the synchronization required for safe cleanup.
-- Making cleanup silently skip uncertain resources. Uncertainty is an
-  operator-visible failure.
-
-## Design
-
-### Shared backend control flow
-
-Follow the backend architecture rule used by gateway attachment: shared
-behavior lives above concrete backends; subclasses provide primitives, not
-control flow.
-
-Cleanup remains previewable, but confirmation authorizes a *new authoritative
-evaluation*, not blind execution of the displayed object. The shared flow:
-
-1. asks each available backend for a preview;
-2. displays the union and asks for confirmation;
-3. refreshes each non-empty backend plan;
-4. validates destructive identities immediately before action;
-5. aborts loudly if the refreshed plan or any identity cannot be proven safe.
-
-Backend-specific primitives define how to identify a resource. Firecracker
-uses process start identity plus canonical config/run paths; container
-backends use authoritative CLI queries and stable resource names/labels.
-
-Container engines expose destructive name-based commands without a portable
-compare-and-delete operation. Cleanup therefore refreshes after confirmation
-and requires every discovery query to succeed, minimizing but not claiming to
-eliminate the final name-reuse race. A future engine-specific stable-ID
-primitive may close that residual window without moving control flow back
-into each backend.
-
-### Enforcement state versus introspection state
-
-Egress enforcement retains its deny-all fallback because uncertainty must not
-grant network access. Supervisor introspection uses a strict resolver path:
-unattributed callers and resolver failures become typed MCP errors, while a
-successfully resolved policy containing zero routes returns `routes: []`.
-
-### Gateway resource boundaries
-
-Both stdlib servers set a per-connection body deadline before reading and use a
-bounded request executor or semaphore. Saturated capacity fails quickly with a
-service-unavailable response. Existing size caps remain independent:
-supervisor proposals retain the 1 MiB cap and Git pack requests retain their
-larger protocol-appropriate cap.
-
-### Shutdown diagnostics
-
-The gateway output pump catches only stream-closure exceptions expected after
-the supervisor closes child pipes. Other I/O failures remain visible and are
-reported through the supervisor's normal diagnostic channel.
-
-### Shared filesystem security
-
-The common SQLite store owns database creation for every backend. It creates
-the parent directory and an empty database with private modes before opening
-SQLite, repairs existing modes, verifies the resulting state, and propagates
-every enforcement failure. Backend launchers do not duplicate this policy.
-
-The backend-neutral gateway provisioner likewise applies directory and file
-modes after transport copies complete. This avoids relying on copy behavior
-that differs among Docker, Apple Container, and Firecracker's SSH transport.
-
-## Implementation chunks
-
-1. Existing fail-closed security and backend enumeration fixes.
-2. FastAPI orchestrator transport and bounded control-plane bodies.
-3. Egress request-policy and outbound-DLP pipeline extraction.
-4. Supervisor MCP dispatch extraction.
-5. Shared cleanup refresh/revalidation plus authoritative macOS discovery.
-6. Strict supervisor introspection and bounded supervisor/Git HTTP work.
-7. Gateway shutdown log-pump closure handling.
-8. Lossless Firecracker process identities, authoritative Docker cleanup
-   queries, and bounded Firecracker artifact transfers.
-9. Mandatory authenticated secret storage, shared cleanup-plan intersection
-   and mutation accounting, and contained Git backend process failures.
-10. Disk-spooled and separately bounded Git bodies, cleanup command deadlines,
-    and classified Firecracker signalling failures.
-11. Fail-closed shared database creation and backend-neutral gateway credential
-    permissions.
-
-## Open questions
-
-None.

docs/prds/prd-new-host-control-server.md

@@ -0,0 +1,273 @@
+# PRD prd-new: Host control server
+
+- **Status:** Draft
+- **Author:** Claude
+- **Created:** 2026-07-26
+- **Issue:** #468
+
+## Summary
+
+Promote the in-process launch broker into a standalone **host control
+server**: the single privileged component on the host. Both the CLI and the
+orchestrator drive it over HTTP; it brokers agent launches, owns the
+orchestrator's own lifecycle, and is the sole writer of host-durable state (the
+tamper-evident audit record). This closes the three gaps between today's
+well-formed broker *contract* ([`orchestrator/broker.py`](../../bot_bottle/orchestrator/broker.py))
+and a real out-of-process service — transport, durable provisioned secret,
+and a disciplined op vocabulary — and splits host state by
+owner and lifetime. The prize: **the CLI no longer needs the Docker socket**,
+which is what finally lets a dedicated Gitea runner user drop the
+root-equivalent `docker` group (PRD 0070, "Relationship to other work").
+
+## Problem
+
+Container launches run directly from a short-lived CLI process against the
+Docker socket. That socket is root-equivalent, so every host that launches
+bottles hands root to whoever invokes the CLI — including a CI runner user we
+want to keep unprivileged. PRD 0070 already argues for replacing the fat socket
+with a **thin, structured, auditable** launch broker, and the contract for that
+broker exists and is tested in-process. But it is *only* in-process:
+`LaunchBroker.submit(token)` is a method call from
+`OrchestratorCore.launch_bottle` ([`service.py:116`](../../bot_bottle/orchestrator/service.py)),
+and `DockerBroker` is on no production path — every backend starts the
+orchestrator with `--broker stub` ([`__main__.py:54`](../../bot_bottle/orchestrator/__main__.py)).
+
+Three gaps stand between that scaffold and a host service:
+
+1. **No transport.** `submit` is an in-process call. A real service needs a
+   `BrokerClient` that POSTs the signed token and a host-side HTTP server that
+   verifies and acts.
+2. **The signing secret is ephemeral and self-generated.**
+   [`__main__.py:53`](../../bot_bottle/orchestrator/__main__.py) does
+   `secrets.token_bytes(32)` and hands the *same value* to signer and verifier —
+   viable only because they share a process. A separate daemon needs the secret
+   provisioned out of band and durable across orchestrator restarts.
+3. **The op vocabulary is `launch` / `teardown` only.** Everything else
+   host-privileged still lives in the CLI, so the schema has to grow — carefully,
+   since PRD 0070's security argument rests on "structured requests only, static
+   flags + ids."
+
+Separately, host state has no clear owner. `OrchestratorCore.reconcile` takes
+`live_source_ips` as a parameter *only because the orchestrator cannot see the
+backend* ([`service.py:137`](../../bot_bottle/orchestrator/service.py)); the
+egress traffic log is written to the container's stderr; and there is no durable,
+tamper-evident home for the audit record that survives orchestrator destruction.
+
+## Goals / Success Criteria
+
+- A standalone host control server that the CLI and orchestrator reach over
+  **HTTP**, with three entry paths working end to end:
+  - `web console -(iroh)-> orchestrator -(http)-> host controller -> launch`
+  - `cli -(http)-> orchestrator -(http)-> host controller -> launch`
+  - `cli -(http)-> host controller` — start / restart / status of the
+    orchestrator **itself** (the bootstrap/recovery path #391 targets).
+- The launch op is expressed as a **signed JWT of static flags + ids only**,
+  verified against a closed schema.
+- The signing secret is **provisioned out of band and durable** across
+  orchestrator restarts (a `TrustDomain` per #476, with a key the orchestrator
+  never holds for the host controller's *own* endpoints).
+- Host-privileged operations move off the CLI to the control server; **the CLI
+  no longer opens the Docker socket** for bottle operations.
+- `Orchestrator.reconcile` no longer takes `live_source_ips` — live-bottle
+  enumeration becomes an internal control-server call.
+- Host-durable state lands as an **append-only, hash-chained JSONL** audit log
+  owned solely by the host controller; operational state stays SQLite owned
+  solely by the orchestrator.
+
+## Non-goals
+
+- **Removing standing privilege.** This converts on-demand privilege (a CLI the
+  user invokes) into standing privilege (a daemon under launchd/systemd). The
+  win is that the privilege is *narrower* (structured requests vs. a raw socket),
+  not that it disappears. "Always running" is an accepted new property.
+- **Asymmetric signing.** We stay HS256 — see Design / "Signing stays
+  symmetric."
+- **Integrity against a live compromised orchestrator.** Host-location of the
+  audit log does not buy this: the orchestrator makes the decisions being audited
+  and can forge or omit entries wherever the file lives. An off-box copy is the
+  answer, tracked separately.
+- **A single unified DB for all state.** Impossible over a guest-kernel share
+  (SQLite locking is not coherent); state is split by owner and lifetime instead.
+- **The generic `SecretProvider` (#355)** and **remote terminal design (#478)** —
+  both ride the same door but are their own work.
+
+## Design
+
+### Topology
+
+The host controller is the sole privileged component. The orchestrator becomes a
+client of it for launches, and the CLI becomes a client of it for *both* bottle
+operations (indirectly, through the orchestrator) and orchestrator lifecycle
+(directly, for bootstrap/recovery — startup can't route through the thing being
+started).
+
+```
+web console ─(iroh)─▶ orchestrator ─┐
+                                    ├─(http, signed JWT)─▶ host controller ─▶ launch
+cli ────────(http)──▶ orchestrator ─┘
+cli ────────(http, bearer)──────────────────────────────▶ host controller   (orchestrator lifecycle)
+```
+
+### Transport: `BrokerClient` + host server
+
+`LaunchBroker.submit(token)` keeps its exact signature and semantics; only the
+*wire* changes. A new `BrokerClient` implements the same submit contract by
+POSTing the signed token to the host controller (stdlib `urllib`, like the
+existing [`orchestrator/client.py`](../../bot_bottle/orchestrator/client.py)),
+and the host controller's launch handler is the existing `verify_request` +
+`_launch`/`_teardown` path, now reached over HTTP instead of a method call. The
+in-process `StubBroker` stays for the dev-harness and tests; `DockerBroker`'s
+`_launch`/`_teardown` bodies move behind the server unchanged. Because the client
+satisfies the same interface `OrchestratorCore` already depends on, the core does
+not change to gain a real backend.
+
+### Signing stays symmetric (HS256)
+
+PRD 0070 nominally specifies asymmetric; the code is HS256 and we keep it.
+Asymmetric matters when the verifier is *less* privileged than the signer — here
+it is the reverse: the host controller (verifier) is strictly more privileged
+than the orchestrator (signer), and a controller that could forge orchestrator
+requests gains nothing, since it is already the component that launches. Staying
+symmetric also honors the no-runtime-deps policy (stdlib has no Ed25519). This
+matches the reasoning already inlined in `broker.py`'s module docstring.
+
+### Replay protection is out of scope (tracked in #494)
+
+Once the launch token travels over a wire, a captured token could be replayed —
+`sign_request` already emits `jti`/`iat` but `verify_request` reads neither, so
+there is no expiry window or `jti` cache today. Enforcing that (an `iat` window +
+a self-trimming `jti` cache) is a pure in-process change that lands independently
+of this work, and it is deferred to **#494** rather than gating the MVP of the
+host control server. Nothing here depends on it; it can merge before or after.
+
+### Op vocabulary and the "ids + static flags" rule (gap 3)
+
+Each op moved off the CLI widens the privileged surface, so growth is governed by
+one explicit rule, enforced in `verify_request`'s schema check:
+
+> A broker op carries **only ids and enumerated static flags** — a bottle id, a
+> pool slot, a **content-addressed** image ref chosen from a fixed set, an op
+> name from a closed vocabulary. Never a free-form path, argv, command, or
+> caller-supplied filesystem location. If an operation cannot be expressed that
+> way, it does not become a broker op.
+
+Operations that fit and move off the CLI (all today in
+`backend/*/consolidated_launch.py`, driven by a short-lived CLI process):
+
+| Op | What it does | Fits the rule because |
+|---|---|---|
+| `launch` / `teardown` | existing | ids + slot + image ref |
+| `orchestrator.ensure_running` | start the infra container | no arguments |
+| `orchestrator.{start,restart,status}` | lifecycle (the #391 path) | no arguments |
+| `list_live` | enumerate running bottles for reconcile | no arguments; returns ids/IPs |
+| `allocate_ip` | `next_free_ip` over `_network_container_ips` | no arguments; returns an IP |
+| `provision_git_gate` | `cp`/`exec` a per-bottle deploy key into the gateway | bottle id + key handle, no path |
+| `reprovision` | `docker exec printenv <ENV_VAR_SECRET>` on a live agent | bottle id + secret *name* |
+
+Image **builds** stay with the orchestrator for v1 (PRD 0070 §Memory: builds run
+control-plane-side; a dedicated slim build unit is later, #468-adjacent), so no
+`build` broker op is added here.
+
+With `list_live` as an internal control-server call, `Orchestrator.reconcile`'s
+`live_source_ips` parameter goes away — the tell PRD 0070 called out that the
+orchestrator couldn't see the backend disappears with it.
+
+### Secret provisioning (gap 2)
+
+The shared HS256 secret becomes a durable, out-of-band artifact via the
+**`TrustDomain`** seam (#476,
+[`trust_domain.py`](../../bot_bottle/trust_domain.py)):
+
+- The **launch-broker secret** is a `TrustDomain` whose key
+  (`host_signing_key(<file>)`, minted 0600 on first use, durable under
+  `bot_bottle_root()`) is provisioned to the orchestrator (signer) and the host
+  controller (verifier). Durability across orchestrator restarts is what makes
+  re-adoption work — a restart re-verifies against the same key.
+- The **host controller's own lifecycle endpoints** (the direct `cli -> host
+  controller` path) get a **separate** `TrustDomain` key the orchestrator never
+  holds — exactly the second domain #476's PRD reserves. The orchestrator must
+  not be able to mint the credentials used to start and stop it.
+
+This reuses the seam #476 landed rather than re-deriving provisioning per
+backend (the PR #471 bug class).
+
+### One daemon, structurally separate handlers (open decision 1)
+
+The audit writer and the broker live in **one daemon** for install simplicity,
+but with **no shared parsing** and **different credentials per handler**:
+
+- the **launch** handler requires the signed launch **JWT** (provenance +
+  un-coercible schema);
+- the **audit-append** handler takes a plain **bearer token** and writes to the
+  JSONL log.
+
+This does not defend against orchestrator compromise (it holds both creds) — it
+stops a bug in the boring audit path from reaching the privileged launch path.
+The launcher stays small enough to audit line-by-line, per PRD 0070.
+
+### State ownership: split by owner and lifetime
+
+A single mounted DB is impossible — SQLite locking is not coherent across guest
+kernels over a share, which is why the macOS backend already uses a container-only
+volume (`INFRA_DB_VOLUME`). So state splits three ways (depends on #469, which
+gets `bot-bottle.db` off the data plane first):
+
+| Owner | State | Home | Shape |
+|---|---|---|---|
+| **Orchestrator** | `orchestrator_bottles` registry; `bottled_agent_secrets` (encrypted egress tokens); `supervise_proposals` / `supervise_responses` | volume nothing else mounts (generalizing the macOS design) | **SQLite** — mutable, transactional, queried |
+| **Host controller** | supervise audit entries; egress traffic log (today → container stderr); host-side config | host filesystem, survives orchestrator/volume destruction | **JSONL** — append-only |
+| **Gateway** | none | — | after #469 the data plane holds no DB state |
+
+The historical record is **JSONL, not SQLite**, because it is append-only, never
+updated, never transactionally queried: `O_APPEND` writes are atomic, there is no
+locking protocol to get wrong, hash-chaining for tamper-evidence is cheap, and it
+survives container-runtime volume pruning (the #450 lesson) and stays readable
+without the orchestrator running. Both halves of "the audit record" — supervise
+decisions and the egress traffic log — land in the one place.
+
+The orchestrator is **sole mounter and sole writer** of its SQLite volume; the
+host controller is **sole writer** of the JSONL log, over the authenticated
+audit-append channel.
+
+## Implementation chunks
+
+Ordered, each independently mergeable:
+
+1. **`BrokerClient` + host launch server** over HTTP, reusing `verify_request`
+   and the existing `DockerBroker` bodies. Wire `OrchestratorCore` to a
+   `BrokerClient` behind a flag; keep `StubBroker` for the dev-harness. Closes
+   gap 1.
+2. **Durable secret via `TrustDomain`** — provision the launch-broker key to
+   signer + verifier; add the host controller's own lifecycle `TrustDomain`.
+   Closes gap 2.
+3. **Grow the op vocabulary** one op at a time (`list_live` first — it also
+   removes `reconcile`'s `live_source_ips`), each behind the ids + static-flags
+   rule. Closes gap 3.
+4. **JSONL audit log** — the host-controller-owned, hash-chained historical
+   record with the plain-bearer audit-append handler; redirect the egress traffic
+   log into it.
+5. **Drop the Docker socket from the CLI** once every host-privileged op it used
+   is a broker op — the payoff that unblocks the unprivileged Gitea runner user.
+
+## Open questions
+
+1. **Schema-width rule enforcement.** The "ids + static flags" rule is stated;
+   should `verify_request` reject unknown claim keys outright (strict schema) to
+   keep the surface from drifting? Leaning yes.
+2. **Audit-append back-pressure.** What the audit handler does if the JSONL sink
+   is unavailable (fail-closed vs. buffer) — resolve before shipping chunk 5.
+
+## References
+
+- **PRD 0070** — the contract, the launch broker, and the state tiers this
+  implements.
+- **#469** — get `bot-bottle.db` off the data plane (lands underneath this).
+- **#476** ([`prd-new-control-plane-auth-provisioning`](prd-new-control-plane-auth-provisioning.md))
+  — the `TrustDomain` seam this plugs the host controller's key into.
+- **#391** — backend-agnostic orchestrator restart (the bootstrap path).
+- **#494** — enforce broker replay protection (`iat` window + `jti` cache); split
+  out of this PRD as an independent in-process change.
+- **#386** — prebuilt images from the Gitea OCI registry (the fixed image set the
+  broker validates against).
+- **#355** — generic `SecretProvider`.
+- **#478** — remote terminal design.

requirements-dev.txt

@@ -2,12 +2,9 @@
 # The bot-bottle project itself has no runtime dependencies.
 # These tools are used for code quality checks in CI/CD.
 
--r requirements.orchestrator.in
 pylint>=3.0.0
 pyright>=1.1.411
 coverage>=7.0.0
 # PEP 517 build front-end used by tests/unit/test_wheel_install.py to build and
 # install a real wheel (proves the installed distribution is self-contained).
 build>=1.0.0
-# FastAPI's in-process TestClient transport.
-httpx>=0.28.0

requirements.orchestrator.in

@@ -1,3 +0,0 @@
-# Runtime dependencies baked only into the orchestrator images.
-fastapi==0.140.0
-uvicorn==0.51.0

requirements.orchestrator.lock

@@ -1,182 +0,0 @@
-#
-# This file is autogenerated by pip-compile with Python 3.13
-# by the following command:
-#
-#    pip-compile --generate-hashes --output-file=requirements.orchestrator.lock requirements.orchestrator.in
-#
-annotated-doc==0.0.4 \
-    --hash=sha256:571ac1dc6991c450b25a9c2d84a3705e2ae7a53467b5d111c24fa8baabbed320 \
-    --hash=sha256:fbcda96e87e9c92ad167c2e53839e57503ecfda18804ea28102353485033faa4
-    # via fastapi
-annotated-types==0.8.0 \
-    --hash=sha256:13b2beaad985e05e2d6407ee4c4f35590b11f8d693a258a561055cac8f64cab7 \
-    --hash=sha256:f072f4d804ea359e4eaf198b1af7a8b0943881a87f31bb764f8bf219bb9419e0
-    # via pydantic
-anyio==4.14.2 \
-    --hash=sha256:9f505dda5ac9f0c8309b5e8bd445a8c2bf7246f3ce950121e45ea15bc41d1494 \
-    --hash=sha256:cfa139f3ed1a23ee8f88a145ddb5ac7605b8bbfd8592baacd7ce3d8bb4313c7f
-    # via starlette
-click==8.4.2 \
-    --hash=sha256:9a6cea6e60b17ebe0a44c5cc636d94f09bd66142c1cd7d8b4cd731c4917a15f6 \
-    --hash=sha256:e6f9f66136c816745b9d65817da91d61d957fb16e02e4dcd0552553c5a197b76
-    # via uvicorn
-fastapi==0.140.0 \
-    --hash=sha256:e951c0a0d9540bf5d9a2a9e078fd415da2ab7e312d435139e7d9e2e7fe9f0b23 \
-    --hash=sha256:f338951b82fd74ca8f843163aec43ea1a1ce84d515415a50fa98fa25572a5544
-    # via -r requirements.orchestrator.in
-h11==0.16.0 \
-    --hash=sha256:4e35b956cf45792e4caa5885e69fba00bdbc6ffafbfa020300e549b208ee5ff1 \
-    --hash=sha256:63cf8bbe7522de3bf65932fda1d9c2772064ffb3dae62d55932da54b31cb6c86
-    # via uvicorn
-idna==3.18 \
-    --hash=sha256:7f952cbe720b688055e3f87de14f5c3e5fdaa8bc3928985c4077ca689de849a2 \
-    --hash=sha256:ffb385a7e039654cef1ab9ef32c6fafe283c0c0467bba1d9029738ce4a14a848
-    # via anyio
-pydantic==2.13.4 \
-    --hash=sha256:45a282cde31d808236fd7ea9d919b128653c8b38b393d1c4ab335c62924d9aba \
-    --hash=sha256:c40756b57adaa8b1efeeced5c196f3f3b7c435f90e84ea7f443901bec8099ef6
-    # via fastapi
-pydantic-core==2.46.4 \
-    --hash=sha256:00c603d540afdd6b80eb39f078f33ebd46211f02f33e34a32d9f053bba711de0 \
-    --hash=sha256:0186750b482eefa11d7f435892b09c5c606193ef3375bcf94aa00ae6bfb66262 \
-    --hash=sha256:041bde0a48fd37cf71cab1c9d56d3e8625a3793fef1f7dd232b3ff37e978ecda \
-    --hash=sha256:0c563b08bca408dc7f65f700633d8442fffb2421fc47b8101377e9fd65051ff0 \
-    --hash=sha256:0cbe8b01f948de4286c74cdd6c667aceb38f5c1e26f0693b3983d9d74887c65e \
-    --hash=sha256:0ce40cd7b21210e99342afafbd4d0f76d784eb5b1d60f3bdc566be4983c6c73b \
-    --hash=sha256:0e96592440881c74a213e5ad528e2b24d3d4f940de2766bed9010ab1d9e51594 \
-    --hash=sha256:10e17cbb10a330363733efc4d7c4d0dd827ac0909b8f6a6542298fed1ea62f29 \
-    --hash=sha256:133878133d271ade3d41d1bfb2a45ec38dbdbda40bc065921c6b04e4630127e2 \
-    --hash=sha256:14d4edf427bdcf950a8a02d7cb44a08614388dd6e1bdcbf4f67504fa7887da9c \
-    --hash=sha256:14f4c5d6db102bd796a627bbb3a17b4cf4574b9ae861d8b7c9a9661c6dd3362d \
-    --hash=sha256:17299feefe090f2caa5b8e37222bb5f663e4935a8bfa6931d4102e5df1a9f398 \
-    --hash=sha256:184c081504d17f1c1066e430e117142b2c77d9448a97f7b65c6ac9fd9aee238d \
-    --hash=sha256:18e5ceec2ab67e6d5f1a9085e5a24c9c4e2ac4545730bfe668680bca05e555f3 \
-    --hash=sha256:19e51f073cd3df251856a8a4189fbdf1de4012c3ebacfb1884f94f1eb406079f \
-    --hash=sha256:1a7dd0b3ee80d90150e3495a3a13ac34dbcbfd4f012996a6a1d8900e91b5c0fb \
-    --hash=sha256:1d8ba486450b14f3b1d63bc521d410ec7565e52f887b9fb671791886436a42f7 \
-    --hash=sha256:2108ba5c1c1eca18030634489dc544844144ee36357f2f9f780b93e7ddbb44b5 \
-    --hash=sha256:228ee9bae8bef5b1e97ec58302f80357c37199e0d0a99174e138d28e6957b9d9 \
-    --hash=sha256:23ace664830ee0bfe014a0c7bc248b1f7f25ed7ad103852c317624a1083af462 \
-    --hash=sha256:2412e734dcb48da14d4e4006b82b46b74f2518b8a26ee7e58c6844a6cd6d03c4 \
-    --hash=sha256:29c61fc04a3d840155ff08e475a04809278972fe6aef51e2720554e96367e34b \
-    --hash=sha256:2f84c03c8607173d16b5a854ec68a2f9079ae03237a54fb506d13af47e1d018d \
-    --hash=sha256:3009f12e4e90b7f88b4f9adb1b0c4a3d58fe7820f3238c190047209d148026df \
-    --hash=sha256:3245406455a5d98187ec35530fd772b1d799b26667980872c8d4614991e2c4a2 \
-    --hash=sha256:3447661d99f75a3683a4cf5c87da72f2161964611864dbbeac7fbb118bb4bfc0 \
-    --hash=sha256:372429a130e469c9cd698925ce5fc50940b7a1336b0d82038e63d5bbc4edc519 \
-    --hash=sha256:395aebd9183f9d112f569aeb5b2214d1a10a33bec8456447f7fbdfa51d38d4cd \
-    --hash=sha256:3a233125ac121aa3ffba9a2b59edfc4a985a76092dc8279586ab4b71390875e7 \
-    --hash=sha256:3be77f45df024d789a672ae34f8b06fb346c4f9f46ea714956660ea4862e89ac \
-    --hash=sha256:3bf92c5d0e00fefaab325a4d27828fe6b6e2a21848686b5b60d2d9eeb09d76c6 \
-    --hash=sha256:3ecbc122d18468d06ca279dc26a8c2e2d5acb10943bb35e36ae92096dc3b5565 \
-    --hash=sha256:3fb702cd90b0446a3a1c5e470bfa0dd23c0233b676a9099ddcc964fa6ca13898 \
-    --hash=sha256:428e04521a40150c85216fc8b85e8d39fece235a9cf5e383761238c7fa9b96fb \
-    --hash=sha256:432c179df7874eeb73307aad2df0755e1ae0efa61ff0ea89b93e194411ae3928 \
-    --hash=sha256:4a05d69cba51d852c5c3e92758653245a50c0b646ced0cf05bd793ed592839d6 \
-    --hash=sha256:4c63ebc82684aa89d9a3bcbd13d515b3be44250dc68dd3bd81526c1cb31286c3 \
-    --hash=sha256:4fc73cb559bdb54b1134a706a2802a4cddd27a0633f5abb7e53056268751ac6a \
-    --hash=sha256:4fcbe087dbc2068af7eda3aa87634eba216dbda64d1ae73c8684b621d33f6596 \
-    --hash=sha256:56cb4851bcaf3d117eddcef4fe66afd750a50274b0da8e22be256d10e5611987 \
-    --hash=sha256:5855698a4856556d86e8e6cd8434bc3ac0314ee8e12089ae0e143f64c6256e4e \
-    --hash=sha256:5a4330cdbc57162e4b3aa303f588ba752257694c9c9be3e7ebb11b4aca659b5d \
-    --hash=sha256:5b712b53160b79a5850310b912a5ef8e57e56947c8ad690c227f5c9d7e561712 \
-    --hash=sha256:5d5902252db0d3cedf8d4a1bc68f70eeb430f7e4c7104c8c476753519b423008 \
-    --hash=sha256:617d7e2ca7dcb8c5cf6bcb8c59b8832c94b36196bbf1cbd1bfb56ed341905edd \
-    --hash=sha256:62f875393d7f270851f20523dd2e29f082bcc82292d66db2b64ea71f64b6e1c1 \
-    --hash=sha256:633147d34cf4550417f12e2b1a0383973bdf5cdfde212cb09e9a581cf10820be \
-    --hash=sha256:66ce7632c22d837c95301830e111ad0128a32b8207533b60896a96c4915192ea \
-    --hash=sha256:6b3ace8194b0e5204818c92802dcdca7fc6d88aabbb799d7c795540d9cd6d292 \
-    --hash=sha256:6f2eeda33a839975441c86a4119e1383c50b47faf0cbb5176985565c6bb02c33 \
-    --hash=sha256:7027560ee92211647d0d34e3f7cd6f50da56399d26a9c8ad0da286d3869a53f3 \
-    --hash=sha256:7283d57845ecf5a163403eb0702dfc220cc4fbdd18919cb5ccea4f95ee1cdab4 \
-    --hash=sha256:7a5f930472650a82629163023e630d160863fce524c616f4e5186e5de9d9a49b \
-    --hash=sha256:7bfb192b3f4b9e8a89b6277b6ce787564f62cfd272055f6e685726b111dc7826 \
-    --hash=sha256:811ff8e9c313ab425368bcbb36e5c4ebd7108c2bbf4e4089cfbb0b01eff63fac \
-    --hash=sha256:8233f2947cf85404441fd7e0085f53b10c93e0ee78611099b5c7237e36aacbf7 \
-    --hash=sha256:82cf5301172168103724d49a1444d3378cb20cdee30b116a1bd6031236298a5d \
-    --hash=sha256:8358a950c8909158e3df31538a7e4edc2d7265a7c54b47f0864d9e5bae9dcebf \
-    --hash=sha256:85bb3611ff1802f3ee7fdd7dbff26b56f343fb432d57a4728fdd49b6ef35e2f4 \
-    --hash=sha256:86e1a4418c6cd97d60c95c71164158eaf7324fae7b0923264016baa993eba6fc \
-    --hash=sha256:8b9bab013d1c7a79d3501ff86d0bc9c31bf587db4551677b96bec07df78c6b15 \
-    --hash=sha256:8c5dac79fa1614d1e06ca695109c6105923bd9c7d1d6c918d4e637b7e6b32fd3 \
-    --hash=sha256:8d0820e8192167f80d88d64038e609c31452eeca865b4e1d9950a27a4609b00b \
-    --hash=sha256:8daafc69c93ee8a0204506a3b6b30f586ef54028f52aeeeb5c4cfc5184fd5914 \
-    --hash=sha256:9037063db01f09b09e237c282b6792bd4da634b5402c4e7f0c61effed7701a04 \
-    --hash=sha256:905a0ed8ea6f2d61c1738835f99b699348d7857379083e5fc497fa0c967a407c \
-    --hash=sha256:90884113d8b48f760e9587002789ddd741e76ab9f89518cd1e43b1f1a52ec44b \
-    --hash=sha256:91a06d2e259ecfbd8c901d70c3c507900458498142b3026a296b7de4d1322cc9 \
-    --hash=sha256:926c9541b14b12b1681dca8a0b75feb510b06c6341b70a8e500c2fdcff837cce \
-    --hash=sha256:9401557acd873c3a7f3eb9383edef8ac4968f9510e340f4808d427e75667e7b4 \
-    --hash=sha256:9551187363ffc0de2a00b2e47c25aeaeb1020b69b668762966df15fc5659dd5a \
-    --hash=sha256:962ccbab7b642487b1d8b7df90ef677e03134cf1fd8880bf698649b22a69371f \
-    --hash=sha256:97e7cf2be5c77b7d1a9713a05605d49460d02c6078d38d8bef3cbe323c548424 \
-    --hash=sha256:9aa768456404a8bf48a4406685ac2bec8e72b62c69313734fa3b73cf33b3a894 \
-    --hash=sha256:9bc519fbf2b7578398853d815009ae5e4d4603d12f4e3f91da8c06852d3da3e9 \
-    --hash=sha256:9d56801be94b86a9da183e5f3766e6310752b99ff647e38b09a9500d88e46e76 \
-    --hash=sha256:9f444c499b3eefd3a92e348059471ea0c3a6e303d9c1cec09fa748fd9f895201 \
-    --hash=sha256:9fa8ae11da9e2b3126c6426f147e0fba88d96d65921799bb30c6abd1cb2c97fb \
-    --hash=sha256:a0f62d0a58f4e7da165457e995725421e0064f2255d8eccebc49f41bbc23b109 \
-    --hash=sha256:a396dcc17e5a0b164dbe026896245a4fa9ff402edca1dff0be3d53a517f74de4 \
-    --hash=sha256:aaa2a54443eff1950ba5ddc6b6ccda0d9c84a364276a62f969bdf2a390650848 \
-    --hash=sha256:ad785e92e6dc634c21555edc8bd6b64957ab844541bcb96a1366c202951ae526 \
-    --hash=sha256:af8244b2bef6aaad6d92cda81372de7f8c8d36c9f0c3ea36e827c60e7d9467a0 \
-    --hash=sha256:b078afbc25f3a1436c7a1d2cd3e322497ee99615ba97c563566fdf46aff1ee01 \
-    --hash=sha256:b2f69dec1725e79a012d920df1707de5caf7ed5e08f3be4435e25803efc47458 \
-    --hash=sha256:b8458003118a712e66286df6a707db01c52c0f52f7db8e4a38f0da1d3b94fc4e \
-    --hash=sha256:bb63e0198ca18aad131c089b9204c23079c3afa95487e561f4c522d519e55aba \
-    --hash=sha256:bfec22eab3c8cc2ceec0248aec886624116dc079afa027ecc8ad4a7e62010f8a \
-    --hash=sha256:c1747f85cee84c26985853c6f3d9bd3e75da5212912443fa111c113b9c246f39 \
-    --hash=sha256:c1b3f518abeca3aa13c712fd202306e145abf59a18b094a6bafb2d2bbf59192c \
-    --hash=sha256:c50f2528cf200c5eed56faf3f4e22fcd5f38c157a8b78576e6ba3168ec35f000 \
-    --hash=sha256:c68fcd102d71ea85c5b2dfac3f4f8476eff42a9e078fd5faefff6d145063536b \
-    --hash=sha256:c7a7bd4e39e8e4c12c39cd480356842b6a8a06e41b23a55a5e3e191718838ddf \
-    --hash=sha256:c94f0688e7b8d0a67abf40e57a7eaaecd17cc9586706a31b76c031f63df052b4 \
-    --hash=sha256:cbaf13819775b7f769bf4a1f066cb6df7a28d4480081a589828ef190226881cd \
-    --hash=sha256:cd2213145bcc2ba85884d0ac63d222fece9209678f77b9b4d76f054c561adb28 \
-    --hash=sha256:ce5c1d2a8b27468f433ca974829c44060b8097eedc39933e3c206a90ee49c4a9 \
-    --hash=sha256:d396ec2b979760aaf3218e76c24e65bd0aca24983298653b3a9d7a45f9e47b30 \
-    --hash=sha256:d51026d73fcfd93610abc7b27789c26b313920fcfb20e27462d74a7f8b06e983 \
-    --hash=sha256:d80ee3d731373b24cebbc10d689ca4ee1875caf0d5703a245db18efd4dd37fc1 \
-    --hash=sha256:d995260fdf4e1db774581b4900e0f832abe3c7c84996726bbc161b19c8f29e76 \
-    --hash=sha256:da4b951fe36dc7c3a1ccb4e3cd1747c3542b8c9ceede8fc86cae054e764485f5 \
-    --hash=sha256:daa27d92c36f24388fe3ad306b174781c747627f134452e4f128ea00ce1fe8c4 \
-    --hash=sha256:db06ffe51636ffe9ca531fe9023dd64bdd794be8754cb5df57c5498ae5b518a7 \
-    --hash=sha256:e0d65b8c354be7fb5f720c3caa8bc940bc2d20ce749c8e06135f07f8ed95dd7c \
-    --hash=sha256:e68b7a074f65a2fd746c52a7ce6142ab7006074ac269ace0c25cd8ba171f8066 \
-    --hash=sha256:e739fee756ba1010f8bcccb534252e85a35fe45ae92c295a06059ce58b74ccd3 \
-    --hash=sha256:e846ae7835bf0703ae43f534ab79a867146dadd59dc9ca5c8b53d5c8f7c9ef02 \
-    --hash=sha256:e9c26f834c65f5752f3f06cb08cb86a913ceb7274d0db6e267808a708b46bc89 \
-    --hash=sha256:ea793e075b70290d89d8142074262885d3f7da19634845135751bd6344f73b50 \
-    --hash=sha256:f027324c56cd5406ca49c124b0db10e56c69064fec039acc571c29020cc87c76 \
-    --hash=sha256:f13a646d65d09fbf1bc6b3a9635d30095c8e7e5cc419ff35ecc563c5fd04cd49 \
-    --hash=sha256:f47286a97f0bc9b8859519809077b91b2cefe4ae47fcbf5e466a009c1c5d742b \
-    --hash=sha256:f747929cf940cddb5b3668a390056ddd5ba2e5010615ea2dcf4f9c4f3ab8791d \
-    --hash=sha256:f99626688942fb746e545232e7726926f3be91b5975f8b55327665fafda991c7 \
-    --hash=sha256:f9fa868638bf362d3d138ea55829cefb3d5f4b0d7f142234382a15e2485dbec4 \
-    --hash=sha256:fbdb89b3e1c94a30cc5edfce477c6e6a5dc4d8f84665b455c27582f211a1c72c \
-    --hash=sha256:fc010ab034c8c7452522748bf937df58020d256ccae0874463d1f4d01758af8e \
-    --hash=sha256:fc3e9034a63de20e15e8ade85358bc6efc614008cab72898b4b4952bea0509ff \
-    --hash=sha256:fd8b3d9fd264be37976686c7f65cd52a83f5e84f4bfd2adf9c1d469676bbb6ae
-    # via pydantic
-starlette==1.3.1 \
-    --hash=sha256:05d0213193f2fbaae60e2ecb593b4add4262ad4e46536b54abe36f11a71724e0 \
-    --hash=sha256:c7372aae11c3c3f26a42df7bd626cec2f47d03483d261d369516a615a53714c6
-    # via fastapi
-typing-extensions==4.16.0 \
-    --hash=sha256:481caa481374e813c1b176ada14e97f1f67a4539ce9cfeb3f350d78d6370c2e8 \
-    --hash=sha256:dc983d19a509c94dba722ee6abd33940f7c05a89e243c47e907eb4db6f1a43e5
-    # via
-    #   fastapi
-    #   pydantic
-    #   pydantic-core
-    #   typing-inspection
-typing-inspection==0.4.2 \
-    --hash=sha256:4ed1cacbdc298c220f1bd249ed5287caa16f34d44ef4e9c3d0cbad5b521545e7 \
-    --hash=sha256:ba561c48a67c5958007083d386c3295464928b01faa735ab8547c5692e87f464
-    # via
-    #   fastapi
-    #   pydantic
-uvicorn==0.51.0 \
-    --hash=sha256:5d38af6cd620f2ae3849fb44fd4879e0890aa1febe8d47eb355fb45d93fe6a5b \
-    --hash=sha256:f6f4b69b657c312f516dd2d268ab9ae6f254b11e4bac504f37b2ab58b24dd0b0
-    # via -r requirements.orchestrator.in

scripts/coverage.sh

@@ -13,7 +13,7 @@
 #     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: 85%).
+# critical modules (ADR 0004 target: 90%).
 set -euo pipefail
 
 cd "$(dirname "$0")/.."
@@ -34,8 +34,8 @@ if [ "${1:-}" = "aggregate" ]; then
     "$PY" -m coverage report -m
 
     if [ "${2:-}" = "critical" ]; then
-        echo "== critical modules (ADR 0004 minimum: 85%) ==" >&2
-        "$PY" -m coverage report --include="$CRITICAL" --fail-under=85
+        echo "== critical modules (ADR 0004 minimum: 90%) ==" >&2
+        "$PY" -m coverage report --include="$CRITICAL" --fail-under=90
     fi
     exit 0
 fi
@@ -55,6 +55,6 @@ echo "== combined report ==" >&2
 "$PY" -m coverage report -m
 
 if [ "${1:-}" = "critical" ]; then
-    echo "== critical modules (ADR 0004 minimum: 85%) ==" >&2
-    "$PY" -m coverage report --include="$CRITICAL" --fail-under=85
+    echo "== critical modules (ADR 0004 minimum: 90%) ==" >&2
+    "$PY" -m coverage report --include="$CRITICAL" --fail-under=90
 fi

scripts/critical-modules.txt

@@ -1,4 +1,4 @@
-# Critical security/logic core held to the >=85% coverage bar by
+# Critical security/logic core held to the >=90% coverage bar by
 # docs/decisions/0004-coverage-policy.md.
 #
 # SINGLE SOURCE OF TRUTH: scripts/coverage.sh (the `critical` report) and

scripts/diff_coverage.py

@@ -13,8 +13,8 @@ policy.
 
 Usage:
     scripts/coverage.sh                 # produce .coverage first
-    python3 scripts/diff_coverage.py    # gate against origin/main, min 80%
-    python3 scripts/diff_coverage.py --base main --min 75
+    python3 scripts/diff_coverage.py    # gate against origin/main, min 90%
+    python3 scripts/diff_coverage.py --base main --min 85
 """
 
 from __future__ import annotations
@@ -74,7 +74,7 @@ def main() -> int:
     ap = argparse.ArgumentParser()
     ap.add_argument("--base", default="origin/main",
                     help="git ref to diff against (default: origin/main)")
-    ap.add_argument("--min", type=float, default=80.0,
+    ap.add_argument("--min", type=float, default=90.0,
                     help="minimum %% of changed executable lines covered")
     args = ap.parse_args()
 

setup.py

@@ -26,7 +26,6 @@ _BUNDLED_RESOURCES = (
     "Dockerfile.orchestrator",
     "Dockerfile.orchestrator.fc",
     "requirements.gateway.lock",
-    "requirements.orchestrator.lock",
     "nix/firecracker-netpool.nix",
     "scripts/firecracker-netpool.sh",
 )

tests/unit/test_cli_cleanup_cross_backend.py

@@ -41,8 +41,8 @@ class TestCmdCleanup(unittest.TestCase):
         ):
             self.assertEqual(0, cmd.cmd_cleanup([]))
 
-        self.assertEqual(2, docker.prepare_cleanup.call_count)
-        self.assertEqual(2, fc.prepare_cleanup.call_count)
+        docker.prepare_cleanup.assert_called_once()
+        fc.prepare_cleanup.assert_called_once()
         docker.cleanup.assert_called_once_with(docker_plan)
         fc.cleanup.assert_called_once_with(fc_plan)
 
@@ -68,7 +68,7 @@ class TestCmdCleanup(unittest.TestCase):
         ):
             self.assertEqual(0, cmd.cmd_cleanup([]))
 
-        self.assertEqual(2, docker.prepare_cleanup.call_count)
+        docker.prepare_cleanup.assert_called_once()
         docker.cleanup.assert_called_once_with(docker_plan)
         macos.prepare_cleanup.assert_not_called()
 
@@ -135,25 +135,6 @@ class TestCmdCleanup(unittest.TestCase):
         docker.cleanup.assert_called_once_with(docker_plan)
         fc.cleanup.assert_not_called()
 
-    def test_executes_refreshed_plan_after_confirmation(self):
-        backend = MagicMock()
-        preview = MagicMock(empty=False)
-        refreshed = MagicMock(empty=False)
-        backend.prepare_cleanup.side_effect = [preview, refreshed]
-
-        with patch.object(
-            cmd, "known_backend_names", return_value=("firecracker",),
-        ), patch.object(
-            cmd, "get_bottle_backend", return_value=backend,
-        ), patch.object(
-            cmd, "has_backend", return_value=True,
-        ), patch.object(
-            cmd, "_prompt_yes", return_value=True,
-        ):
-            self.assertEqual(0, cmd.cmd_cleanup([]))
-
-        backend.cleanup.assert_called_once_with(refreshed)
-
 
 if __name__ == "__main__":
     unittest.main()

tests/unit/test_compose.py

@@ -18,7 +18,6 @@ from bot_bottle.backend.docker.compose import (
     list_compose_projects,
     slug_from_compose_project,
 )
-from bot_bottle.backend import EnumerationError
 
 
 class TestProjectNaming(unittest.TestCase):
@@ -70,19 +69,6 @@ class TestComposeProjectListing(unittest.TestCase):
             self.assertEqual([], list_active_slugs(warn_on_error=False))
         warn.assert_not_called()
 
-    def test_compose_ls_error_can_be_raised_for_enumeration(self):
-        with mock.patch(
-            "bot_bottle.backend.docker.compose.subprocess.run",
-            return_value=subprocess.CompletedProcess(
-                args=["docker"], returncode=1, stdout="", stderr="no daemon",
-            ),
-        ):
-            with self.assertRaisesRegex(EnumerationError, "no daemon"):
-                list_active_slugs(
-                    warn_on_error=False,
-                    raise_on_error=True,
-                )
-
 
 if __name__ == "__main__":
     unittest.main()

tests/unit/test_consolidated_launch.py

@@ -7,8 +7,6 @@ from pathlib import Path
 from unittest.mock import MagicMock, Mock, patch
 
 from bot_bottle.backend.docker.consolidated_launch import (
-    ConsolidatedLaunchError,
-    _network_container_ips,
     launch_consolidated,
     deprovision_consolidated,
 )
@@ -88,16 +86,6 @@ class TestLaunchConsolidated(unittest.TestCase):
         client.teardown_bottle.assert_called_once_with("b1")  # no orphan left
 
 
-class TestNetworkContainerIps(unittest.TestCase):
-    def test_fails_closed_when_network_inspection_fails(self) -> None:
-        result = Mock(returncode=1, stdout="", stderr="daemon unavailable")
-        with (
-            patch(f"{_MOD}.run_docker", return_value=result),
-            self.assertRaisesRegex(ConsolidatedLaunchError, "daemon unavailable"),
-        ):
-            _network_container_ips("bot-bottle-gateway")
-
-
 class TestTeardownConsolidated(unittest.TestCase):
     def test_deregisters_and_deprovisions(self) -> None:
         client = Mock()

tests/unit/test_docker_enumerate_active.py

@@ -19,16 +19,13 @@ of issue #77 — the dashboard now delegates to this layer.
 
 from __future__ import annotations
 
-import subprocess
 import tempfile
 import unittest
 from pathlib import Path
-from unittest.mock import patch
 
 from tests.unit import use_bottle_root
 from bot_bottle import bottle_state
 from bot_bottle.backend.docker import enumerate as _enumerate
-from bot_bottle.backend import EnumerationError
 
 
 class TestParseServicesByProject(unittest.TestCase):
@@ -75,18 +72,6 @@ class TestParseServicesByProject(unittest.TestCase):
         self.assertEqual({"bot-bottle-dev-abc": {"egress"}}, out)
 
 
-class TestQueryServicesByProject(unittest.TestCase):
-    def test_docker_ps_failure_is_not_an_empty_result(self):
-        with patch(
-            "bot_bottle.backend.docker.enumerate.subprocess.run",
-            return_value=subprocess.CompletedProcess(
-                args=["docker"], returncode=1, stdout="", stderr="daemon down",
-            ),
-        ):
-            with self.assertRaisesRegex(EnumerationError, "daemon down"):
-                _enumerate._query_services_by_project()
-
-
 class _FakeHomeMixin:
     def _setup_fake_home(self) -> None:
         self._tmp = tempfile.TemporaryDirectory(prefix="enum-active.")

tests/unit/test_egress_outbound_pipeline.py

@@ -1,81 +0,0 @@
-"""Unit tests for framework-neutral outbound DLP request stages."""
-
-from __future__ import annotations
-
-import unittest
-
-from bot_bottle.gateway.egress.outbound_pipeline import (
-    MutableHeaders,
-    redact_request,
-    scan_request,
-)
-from bot_bottle.gateway.egress.types import Route
-
-
-class _Headers(dict[str, str]):
-    pass
-
-
-class _Request:
-    def __init__(
-        self,
-        *,
-        host: str = "api.example.com",
-        path: str = "/v1/messages",
-        headers: dict[str, str] | None = None,
-        body: str = "",
-    ) -> None:
-        self.pretty_host = host
-        self.path = path
-        self.headers: MutableHeaders = _Headers(headers or {})
-        self.text = body
-
-    def get_text(self, strict: bool = False) -> str | None:
-        del strict
-        return self.text
-
-
-class TestOutboundScan(unittest.TestCase):
-    def test_detects_secret_in_body(self) -> None:
-        request = _Request(body="token=sk-" + "a" * 48)
-
-        result = scan_request(request, Route(host="api.example.com"), {})
-
-        self.assertIsNotNone(result)
-        self.assertEqual("block", result.severity if result else None)
-
-    def test_safe_token_is_ignored(self) -> None:
-        token = "sk-" + "a" * 48
-        request = _Request(body=f"token={token}")
-
-        result = scan_request(
-            request,
-            Route(host="api.example.com"),
-            {},
-            safe_tokens={token},
-        )
-
-        self.assertIsNone(result)
-
-
-class TestOutboundRedaction(unittest.TestCase):
-    def test_redacts_body_header_and_path_but_preserves_host(self) -> None:
-        token = "sk-" + "a" * 48
-        request = _Request(
-            path=f"/v1/messages?key={token}",
-            headers={"Host": "api.example.com", "X-Token": token + "\r\nInjected: yes"},
-            body=f"token={token}",
-        )
-
-        clean = redact_request(request, Route(host="api.example.com"), {})
-
-        self.assertTrue(clean)
-        self.assertNotIn(token, request.path)
-        self.assertNotIn(token, request.headers["X-Token"])
-        self.assertNotIn("\r", request.headers["X-Token"])
-        self.assertNotIn(token, request.text)
-        self.assertEqual("api.example.com", request.headers["Host"])
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_egress_request_pipeline.py

@@ -1,89 +0,0 @@
-"""Unit tests for framework-neutral egress request policy stages."""
-
-from __future__ import annotations
-
-import unittest
-
-from bot_bottle.gateway.egress.request_pipeline import (
-    GIT_PUSH_BLOCK_REASON,
-    evaluate_route_policy,
-    git_block_reason,
-)
-from bot_bottle.gateway.egress.types import Config, LOG_FULL, Route
-
-
-class TestGitPolicy(unittest.TestCase):
-    def test_push_is_always_blocked(self) -> None:
-        reason = git_block_reason(
-            (), "git.example.com", "/repo.git/git-receive-pack", "",
-        )
-        self.assertEqual(GIT_PUSH_BLOCK_REASON, reason)
-
-    def test_fetch_requires_route_opt_in(self) -> None:
-        path = "/repo.git/git-upload-pack"
-        blocked = git_block_reason((), "git.example.com", path, "")
-        allowed = git_block_reason(
-            (Route(host="git.example.com", git_fetch=True),),
-            "git.example.com",
-            path,
-            "",
-        )
-        self.assertTrue(blocked)
-        self.assertEqual("", allowed)
-
-    def test_non_git_request_is_not_decided_here(self) -> None:
-        self.assertEqual(
-            "",
-            git_block_reason((), "api.example.com", "/v1/messages", ""),
-        )
-
-
-class TestRoutePolicy(unittest.TestCase):
-    def test_strips_agent_auth_and_injects_gateway_auth(self) -> None:
-        route = Route(
-            host="api.example.com",
-            auth_scheme="Bearer",
-            token_env="API_TOKEN",
-        )
-        result = evaluate_route_policy(
-            Config(routes=(route,)),
-            route,
-            host="api.example.com",
-            request_path="/v1/messages",
-            method="POST",
-            headers={"Authorization": "agent-secret"},
-            env={"API_TOKEN": "gateway-secret"},
-        )
-        self.assertTrue(result.strip_authorization)
-        self.assertEqual("Bearer gateway-secret", result.inject_authorization)
-        self.assertFalse(result.block_reason)
-
-    def test_preserved_auth_participates_in_matching(self) -> None:
-        route = Route(host="registry.example.com", preserve_auth=True)
-        result = evaluate_route_policy(
-            Config(routes=(route,), log=LOG_FULL),
-            route,
-            host="registry.example.com",
-            request_path="/v2/",
-            method="GET",
-            headers={"Authorization": "Bearer agent-token"},
-            env={},
-        )
-        self.assertFalse(result.strip_authorization)
-        self.assertTrue(result.log_request)
-
-    def test_missing_route_fails_closed(self) -> None:
-        result = evaluate_route_policy(
-            Config(routes=(), deny_reason="not allowed"),
-            None,
-            host="blocked.example.com",
-            request_path="/",
-            method="GET",
-            headers={},
-            env={},
-        )
-        self.assertEqual("not allowed", result.block_reason)
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_firecracker_cleanup.py

@@ -15,7 +15,6 @@ import unittest
 from pathlib import Path
 from unittest.mock import patch
 
-from bot_bottle.backend import EnumerationError
 from bot_bottle.backend.firecracker import cleanup as fc_cleanup
 from bot_bottle.backend.firecracker.bottle_cleanup_plan import (
     FirecrackerBottleCleanupPlan,
@@ -59,37 +58,10 @@ class TestProcessScan(unittest.TestCase):
         self.assertEqual({str(run_root / "live-a")}, live)
         self.assertEqual([222], orphan_pids)
 
-    def test_scan_empty_when_pgrep_finds_no_processes(self):
+    def test_scan_empty_when_pgrep_fails(self):
         with patch.object(fc_cleanup.subprocess, "run", return_value=_proc(returncode=1)):
             self.assertEqual((set(), []), fc_cleanup._scan_processes(Path("/x")))
 
-    def test_scan_raises_when_pgrep_errors(self):
-        proc = subprocess.CompletedProcess(
-            [], 2, stdout="", stderr="invalid process expression",
-        )
-        with (
-            patch.object(fc_cleanup.subprocess, "run", return_value=proc),
-            self.assertRaisesRegex(EnumerationError, "invalid process expression"),
-        ):
-            fc_cleanup._scan_processes(Path("/x"))
-
-    def test_prepare_cleanup_does_not_plan_deletions_when_scan_errors(self):
-        with tempfile.TemporaryDirectory() as tmp:
-            run_root = Path(tmp)
-            live = run_root / "live-a"
-            live.mkdir()
-            with (
-                patch.object(fc_cleanup, "_run_root", return_value=run_root),
-                patch.object(
-                    fc_cleanup.subprocess,
-                    "run",
-                    return_value=_proc(returncode=2),
-                ),
-                self.assertRaises(EnumerationError),
-            ):
-                fc_cleanup.prepare_cleanup()
-            self.assertTrue(live.is_dir())
-
     def test_live_run_dirs_returns_paths_in_stable_order(self):
         with patch.object(fc_cleanup, "_run_root", return_value=Path("/run")), \
              patch.object(fc_cleanup, "_scan_processes",
@@ -132,46 +104,18 @@ class TestCleanupRemoval(unittest.TestCase):
             vm_pids=(101,),
             run_dirs=("/run/dev-x",),
         )
-        with patch.object(fc_cleanup, "prepare_cleanup", return_value=plan), \
-             patch.object(fc_cleanup, "_run_root", return_value=Path("/run")), \
-             patch.object(fc_cleanup, "_terminate_orphan") as terminate, \
+        with patch.object(fc_cleanup.os, "kill") as kill, \
              patch.object(fc_cleanup.shutil, "rmtree") as rmtree, \
              patch.object(fc_cleanup, "info"):
             fc_cleanup.cleanup(plan)
-        terminate.assert_called_once_with(101, Path("/run"))
+        kill.assert_called_once()
         rmtree.assert_called_once_with("/run/dev-x", ignore_errors=True)
 
-    def test_cleanup_skips_resources_no_longer_in_refreshed_plan(self):
-        preview = FirecrackerBottleCleanupPlan(
-            vm_pids=(999,), run_dirs=("/run/reused",),
-        )
-        with patch.object(
-            fc_cleanup, "prepare_cleanup",
-            return_value=FirecrackerBottleCleanupPlan(),
-        ), patch.object(fc_cleanup, "_terminate_orphan") as terminate, \
-             patch.object(fc_cleanup.shutil, "rmtree") as rmtree:
-            fc_cleanup.cleanup(preview)
-        terminate.assert_not_called()
-        rmtree.assert_not_called()
-
-    def test_pidfd_prevents_pid_reuse_from_signalling_unrelated_process(self):
-        with patch.object(fc_cleanup.os, "pidfd_open", return_value=7), \
-             patch.object(
-                 fc_cleanup.Path, "read_bytes",
-                 return_value=b"/usr/bin/python\0worker.py\0",
-             ), patch.object(fc_cleanup.signal, "pidfd_send_signal") as send, \
-             patch.object(fc_cleanup.os, "close"):
-            fc_cleanup._terminate_orphan(101, Path("/run"))
-        send.assert_not_called()
-
-    def test_pidfd_signals_revalidated_orphan(self):
-        command = b"firecracker\0--config-file\0/run/gone/config.json\0"
-        with patch.object(fc_cleanup.os, "pidfd_open", return_value=7), \
-             patch.object(fc_cleanup.Path, "read_bytes", return_value=command), \
-             patch.object(fc_cleanup.signal, "pidfd_send_signal") as send, \
-             patch.object(fc_cleanup.os, "close"), patch.object(fc_cleanup, "info"):
-            fc_cleanup._terminate_orphan(101, Path("/run"))
-        send.assert_called_once_with(7, fc_cleanup.signal.SIGTERM)
+    def test_cleanup_tolerates_dead_pid(self):
+        plan = FirecrackerBottleCleanupPlan(vm_pids=(999,))
+        with patch.object(fc_cleanup.os, "kill", side_effect=ProcessLookupError), \
+             patch.object(fc_cleanup, "info"):
+            fc_cleanup.cleanup(plan)  # must not raise
 
 
 class TestCleanupPlan(unittest.TestCase):

tests/unit/test_firecracker_enumerate.py

@@ -1,64 +0,0 @@
-"""Unit tests for Firecracker active-agent enumeration."""
-
-from __future__ import annotations
-
-import unittest
-from pathlib import Path
-from unittest.mock import patch
-
-from bot_bottle.backend import EnumerationError
-from bot_bottle.backend.firecracker import enumerate as fc_enumerate
-from bot_bottle.bottle_state import BottleMetadata
-
-
-class TestEnumerateActive(unittest.TestCase):
-    def test_maps_live_run_dirs_to_active_agents(self) -> None:
-        metadata = BottleMetadata(
-            identity="dev-a",
-            agent_name="claude",
-            cwd="",
-            copy_cwd=False,
-            started_at="2026-07-26T12:00:00Z",
-            label="review",
-            color="blue",
-        )
-        with (
-            patch.object(
-                fc_enumerate, "live_run_dirs",
-                return_value=(Path("/cache/run/dev-a"),),
-            ),
-            patch.object(fc_enumerate, "read_metadata", return_value=metadata),
-        ):
-            agents = fc_enumerate.enumerate_active()
-        self.assertEqual(1, len(agents))
-        self.assertEqual("firecracker", agents[0].backend_name)
-        self.assertEqual("dev-a", agents[0].slug)
-        self.assertEqual("claude", agents[0].agent_name)
-        self.assertEqual("review", agents[0].label)
-        self.assertEqual((), agents[0].services)
-
-    def test_missing_metadata_uses_safe_defaults(self) -> None:
-        with (
-            patch.object(
-                fc_enumerate, "live_run_dirs",
-                return_value=(Path("/cache/run/dev-a"),),
-            ),
-            patch.object(fc_enumerate, "read_metadata", return_value=None),
-        ):
-            agent = fc_enumerate.enumerate_active()[0]
-        self.assertEqual("?", agent.agent_name)
-        self.assertEqual("", agent.started_at)
-
-    def test_process_scan_failure_propagates(self) -> None:
-        with (
-            patch.object(
-                fc_enumerate, "live_run_dirs",
-                side_effect=EnumerationError("pgrep failed"),
-            ),
-            self.assertRaisesRegex(EnumerationError, "pgrep failed"),
-        ):
-            fc_enumerate.enumerate_active()
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_gateway_bounded_http.py

@@ -1,79 +0,0 @@
-"""Unit tests for shared gateway stdlib HTTP resource boundaries."""
-# pylint: disable=protected-access
-
-from __future__ import annotations
-
-import io
-import socket
-import unittest
-
-from bot_bottle.gateway.bounded_http import (
-    BodyReadError,
-    BoundedThreadingHTTPServer,
-    read_declared_body,
-)
-
-
-class _Handler:
-    pass
-
-
-class _TimeoutStream:
-    def read(self, _size: int = -1, /) -> bytes:
-        raise TimeoutError
-
-
-class TestDeclaredBody(unittest.TestCase):
-    def setUp(self) -> None:
-        self.left, self.right = socket.socketpair()
-
-    def tearDown(self) -> None:
-        self.left.close()
-        self.right.close()
-
-    def test_rejects_incomplete_body(self) -> None:
-        with self.assertRaisesRegex(BodyReadError, "incomplete"):
-            read_declared_body(
-                io.BytesIO(b"short"),
-                self.left,
-                "10",
-                maximum=100,
-                timeout_seconds=1,
-                require_length=True,
-            )
-
-    def test_maps_read_timeout(self) -> None:
-        with self.assertRaises(BodyReadError) as caught:
-            read_declared_body(
-                _TimeoutStream(),
-                self.left,
-                "1",
-                maximum=100,
-                timeout_seconds=1,
-                require_length=True,
-            )
-        self.assertEqual(408, caught.exception.status)
-
-
-class TestBoundedServer(unittest.TestCase):
-    def test_saturated_server_rejects_without_spawning_thread(self) -> None:
-        client, peer = socket.socketpair()
-        with BoundedThreadingHTTPServer(
-            ("127.0.0.1", 0), _Handler, max_workers=1,  # type: ignore[arg-type]
-        ) as server:
-            with client, peer:
-                # Directly reserve the only slot to model an in-flight handler.
-                self.assertTrue(
-                    server._request_slots.acquire(  # pylint: disable=consider-using-with
-                        blocking=False,
-                    ),
-                )
-                try:
-                    server.process_request(client, ("127.0.0.1", 1))
-                    self.assertIn(b"503 Service Unavailable", peer.recv(1024))
-                finally:
-                    server._request_slots.release()
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_infra_artifact.py

@@ -114,7 +114,6 @@ class TestVersionInputs(unittest.TestCase):
             '{"PYTHON_BASE_IMAGE": "python:pinned"}\n',
         )
         (root / "requirements.gateway.lock").write_text("mitmproxy==11.1.3\n")
-        (root / "requirements.orchestrator.lock").write_text("fastapi==0.140.0\n")
         (root / "pyproject.toml").write_text("[project]\nname = 'bot-bottle'\n")
 
     def test_pyproject_toml_change_bumps_version(self) -> None:
@@ -166,21 +165,6 @@ class TestVersionInputs(unittest.TestCase):
             )
         self.assertNotEqual(before, after)
 
-    def test_orchestrator_lock_change_bumps_orchestrator_version(self) -> None:
-        with tempfile.TemporaryDirectory() as d:
-            root = Path(d)
-            self._fake_repo(root)
-            before = ia.infra_artifact_version(
-                "init", "orchestrator", repo_root=root,
-            )
-            (root / "requirements.orchestrator.lock").write_text(
-                "fastapi==0.140.0 --hash=sha256:changed\n",
-            )
-            after = ia.infra_artifact_version(
-                "init", "orchestrator", repo_root=root,
-            )
-        self.assertNotEqual(before, after)
-
     def test_base_image_argument_change_bumps_both_role_versions(self) -> None:
         with tempfile.TemporaryDirectory() as d:
             root = Path(d)

tests/unit/test_macos_consolidated_launch.py

@@ -190,8 +190,7 @@ class TestRegisterAgentReconciles(unittest.TestCase):
 
     def _register(self, client: Mock) -> None:
         with patch(f"{_MOD}.OrchestratorClient", return_value=client), \
-                patch(f"{_UTIL}.provision_git_gate"), \
-                patch(f"{_MOD}.live_source_ips", return_value=["10.0.0.7"]):
+                patch(f"{_UTIL}.provision_git_gate"):
             register_agent(
                 _egress_plan(), _git_plan(),
                 source_ip="10.0.0.7", endpoint=_endpoint(),
@@ -213,7 +212,9 @@ class TestRegisterAgentReconciles(unittest.TestCase):
         client.register_bottle.side_effect = _register_bottle
         self._register(client)
         self.assertEqual(["reconcile", "register"], calls)
-        client.reconcile.assert_called_once_with(["10.0.0.7"])
+        # A bare trigger now — the orchestrator enumerates the live set itself
+        # (from the host controller), so the CLI passes no IPs.
+        client.reconcile.assert_called_once_with()
 
     def test_a_reconcile_failure_does_not_block_the_launch(self) -> None:
         from bot_bottle.orchestrator.client import OrchestratorClientError
@@ -221,18 +222,3 @@ class TestRegisterAgentReconciles(unittest.TestCase):
         client.reconcile.side_effect = OrchestratorClientError("unreachable")
         self._register(client)
         client.register_bottle.assert_called_once()
-
-    def test_enumeration_error_does_not_block_the_launch(self) -> None:
-        """A partial container listing must not abort the launch — skip
-        reconciliation and proceed, just as with an unreachable orchestrator."""
-        from bot_bottle.backend.macos_container.enumerate import EnumerationError
-        client = _client()
-        with patch(f"{_MOD}.OrchestratorClient", return_value=client), \
-                patch(f"{_UTIL}.provision_git_gate"), \
-                patch(f"{_MOD}.live_source_ips",
-                      side_effect=EnumerationError("container list failed")):
-            register_agent(
-                _egress_plan(), _git_plan(),
-                source_ip="10.0.0.7", endpoint=_endpoint(),
-            )
-        client.register_bottle.assert_called_once()

tests/unit/test_macos_container_cleanup.py

@@ -5,7 +5,6 @@ from __future__ import annotations
 import unittest
 from unittest.mock import patch
 
-from bot_bottle.backend import EnumerationError
 from bot_bottle.backend.macos_container import cleanup, enumerate as enum_mod
 from bot_bottle.backend.macos_container.bottle_cleanup_plan import (
     MacosContainerBottleCleanupPlan,
@@ -42,22 +41,6 @@ class TestMacosContainerCleanup(unittest.TestCase):
             run.call_args_list[1].args[0],
         )
 
-    def test_container_enumeration_failure_aborts(self):
-        completed = cleanup.subprocess.CompletedProcess(
-            args=[], returncode=1, stdout="", stderr="service unavailable",
-        )
-        with patch.object(cleanup.subprocess, "run", return_value=completed), \
-                self.assertRaisesRegex(EnumerationError, "service unavailable"):
-            cleanup._list_prefixed_containers()
-
-    def test_network_enumeration_failure_aborts(self):
-        completed = cleanup.subprocess.CompletedProcess(
-            args=[], returncode=1, stdout="", stderr="service unavailable",
-        )
-        with patch.object(cleanup.subprocess, "run", return_value=completed), \
-                self.assertRaisesRegex(EnumerationError, "service unavailable"):
-            cleanup._list_prefixed_networks()
-
 
 class TestMacosContainerEnumerate(unittest.TestCase):
     """The backend launches bottles again (PRD 0070), so enumeration is real
@@ -86,18 +69,10 @@ class TestMacosContainerEnumerate(unittest.TestCase):
         self.assertEqual(["dev-abc"], [a.slug for a in agents])
 
     def test_raises_when_the_cli_fails(self):
+        from bot_bottle.backend.macos_container.enumerate import EnumerationError
         with self.assertRaises(EnumerationError):
             self._enumerate("", returncode=1)
 
-    def test_raises_typed_error_when_cli_is_missing(self):
-        with (
-            patch.object(
-                enum_mod.subprocess, "run", side_effect=FileNotFoundError,
-            ),
-            self.assertRaisesRegex(EnumerationError, "CLI not found"),
-        ):
-            enum_mod.enumerate_active()
-
 
 if __name__ == "__main__":
     unittest.main()

tests/unit/test_orchestrator_broker.py

@@ -2,6 +2,10 @@
 
 from __future__ import annotations
 
+import base64
+import hashlib
+import hmac
+import json
 import secrets
 import unittest
 
@@ -14,6 +18,21 @@ from bot_bottle.orchestrator.broker import (
 )
 
 
+def _sign_claims(claims: dict[str, object], secret: bytes) -> str:
+    """Sign an arbitrary claims dict (bypassing `sign_request`'s fixed fields)
+    so a test can craft off-schema payloads — e.g. an extra claim key, or a
+    query op carrying ids — with a *valid* signature, isolating the schema check
+    from the provenance check."""
+    def b64(data: bytes) -> str:
+        return base64.urlsafe_b64encode(data).rstrip(b"=").decode("ascii")
+    header = b64(json.dumps({"alg": "HS256", "typ": "JWT"}, sort_keys=True,
+                            separators=(",", ":")).encode())
+    payload = b64(json.dumps(claims, sort_keys=True, separators=(",", ":")).encode())
+    signing_input = f"{header}.{payload}"
+    sig = b64(hmac.new(secret, signing_input.encode("ascii"), hashlib.sha256).digest())
+    return f"{signing_input}.{sig}"
+
+
 class TestSignVerify(unittest.TestCase):
     def setUp(self) -> None:
         self.secret = secrets.token_bytes(16)
@@ -54,6 +73,41 @@ class TestSignVerify(unittest.TestCase):
         with self.assertRaises(BrokerAuthError):
             verify_request(token, self.secret)
 
+    def test_list_live_round_trip(self) -> None:
+        req = LaunchRequest(op="list_live")
+        got = verify_request(sign_request(req, self.secret), self.secret)
+        self.assertEqual("list_live", got.op)
+        self.assertEqual("", got.bottle_id)
+
+    def test_mutation_without_bottle_id_rejected(self) -> None:
+        # A launch/teardown must name its bottle even with a valid signature.
+        for op in ("launch", "teardown"):
+            token = _sign_claims(
+                {"op": op, "bottle_id": "", "jti": "x", "iat": 1}, self.secret)
+            with self.assertRaises(BrokerAuthError):
+                verify_request(token, self.secret)
+
+    def test_query_op_carrying_ids_or_flags_rejected(self) -> None:
+        # list_live is "no arguments" — a signed one that smuggles a bottle_id /
+        # source_ip / image_ref / slot is off-schema and refused.
+        for extra in (
+            {"bottle_id": "b1"}, {"source_ip": "10.0.0.1"},
+            {"image_ref": "img"}, {"slot": 2},
+        ):
+            claims: dict[str, object] = {"op": "list_live", "jti": "x", "iat": 1, **extra}
+            with self.assertRaises(BrokerAuthError):
+                verify_request(_sign_claims(claims, self.secret), self.secret)
+
+    def test_unknown_claim_key_rejected(self) -> None:
+        # Strict schema (open question 1): a well-signed token with an extra claim
+        # key is refused, so the surface can't widen past the fixed fields.
+        token = _sign_claims(
+            {"op": "launch", "bottle_id": "b1", "cmd": "rm -rf /", "jti": "x", "iat": 1},
+            self.secret,
+        )
+        with self.assertRaises(BrokerAuthError):
+            verify_request(token, self.secret)
+
 
 class TestStubBroker(unittest.TestCase):
     def setUp(self) -> None:
@@ -81,6 +135,37 @@ class TestStubBroker(unittest.TestCase):
             self.broker.submit(forged)
         self.assertEqual([], self.broker.launched)  # nothing acted on
 
+    def test_list_live_derives_from_launches(self) -> None:
+        # Default live set: launched, minus torn-down, by source IP.
+        self.broker.submit(
+            sign_request(LaunchRequest(op="launch", bottle_id="b1", source_ip="10.0.0.1"),
+                         self.secret))
+        self.broker.submit(
+            sign_request(LaunchRequest(op="launch", bottle_id="b2", source_ip="10.0.0.2"),
+                         self.secret))
+        self.broker.submit(
+            sign_request(LaunchRequest(op="teardown", bottle_id="b1", source_ip="10.0.0.1"),
+                         self.secret))
+        live = self.broker.list_live(
+            sign_request(LaunchRequest(op="list_live"), self.secret))
+        self.assertEqual(["10.0.0.2"], live)
+
+    def test_list_live_override(self) -> None:
+        self.broker.live_source_ips = ["10.0.0.9"]
+        live = self.broker.list_live(
+            sign_request(LaunchRequest(op="list_live"), self.secret))
+        self.assertEqual(["10.0.0.9"], live)
+
+    def test_submit_rejects_a_list_live_token(self) -> None:
+        # The verbs don't cross: a query token routed to submit is fail-closed.
+        with self.assertRaises(BrokerAuthError):
+            self.broker.submit(sign_request(LaunchRequest(op="list_live"), self.secret))
+
+    def test_list_live_rejects_a_mutation_token(self) -> None:
+        with self.assertRaises(BrokerAuthError):
+            self.broker.list_live(
+                sign_request(LaunchRequest(op="launch", bottle_id="b1"), self.secret))
+
 
 if __name__ == "__main__":
     unittest.main()

tests/unit/test_orchestrator_broker_client.py

@@ -0,0 +1,160 @@
+"""Unit: orchestrator-side broker client (issue #468, chunk 1). HTTP mocked."""
+
+from __future__ import annotations
+
+import io
+import json
+import unittest
+import urllib.error
+from unittest.mock import MagicMock, patch
+
+from bot_bottle.orchestrator.broker import (
+    BrokerAuthError,
+    BrokerUnavailableError,
+    LaunchRequest,
+)
+from bot_bottle.orchestrator.broker_client import BrokerClient, BrokerClientError
+
+_URLOPEN = "bot_bottle.orchestrator.broker_client.urllib.request.urlopen"
+
+
+def _resp(payload: object) -> MagicMock:
+    m = MagicMock()
+    m.__enter__.return_value.read.return_value = json.dumps(payload).encode()
+    return m
+
+
+def _http_error(code: int, payload: object = None) -> urllib.error.HTTPError:
+    body = json.dumps(payload).encode() if payload is not None else b""
+    return urllib.error.HTTPError(
+        "http://host/broker", code, "err", {}, io.BytesIO(body))  # type: ignore[arg-type]
+
+
+class TestSubmit(unittest.TestCase):
+    def setUp(self) -> None:
+        self.c = BrokerClient("http://host:8091")
+
+    def test_returns_the_verified_request(self) -> None:
+        echo = {
+            "op": "launch", "bottle_id": "b1", "source_ip": "10.0.0.1",
+            "image_ref": "img", "slot": 3,
+        }
+        with patch(_URLOPEN, return_value=_resp(echo)):
+            got = self.c.submit("tok")
+        self.assertEqual(
+            LaunchRequest(op="launch", bottle_id="b1", source_ip="10.0.0.1",
+                          image_ref="img", slot=3),
+            got,
+        )
+
+    def test_posts_token_to_broker_endpoint(self) -> None:
+        with patch(_URLOPEN, return_value=_resp({"op": "teardown", "bottle_id": "b1"})) as m:
+            self.c.submit("signed-token")
+        request = m.call_args.args[0]
+        self.assertEqual("POST", request.get_method())
+        self.assertTrue(request.full_url.endswith("/broker"))
+        self.assertEqual({"token": "signed-token"}, json.loads(request.data))
+
+    def test_401_raises_broker_auth_error(self) -> None:
+        # A fail-closed provenance/schema rejection surfaces as the SAME exception
+        # the in-process broker raises, so the launch path's rollback is identical.
+        with patch(_URLOPEN, side_effect=_http_error(401, {"error": "bad signature"})):
+            with self.assertRaises(BrokerAuthError):
+                self.c.submit("forged")
+
+    def test_502_is_a_definite_client_error(self) -> None:
+        # The host responded — it processed the request and did not launch, so a
+        # definite BrokerClientError (the caller may safely roll back).
+        with patch(_URLOPEN, side_effect=_http_error(502, {"error": "docker down"})):
+            with self.assertRaises(BrokerClientError):
+                self.c.submit("tok")
+
+    def test_unreachable_is_ambiguous_unavailable(self) -> None:
+        # No response at all — the request may already have launched, so the
+        # AMBIGUOUS BrokerUnavailableError (the caller must NOT roll back).
+        with patch(_URLOPEN, side_effect=urllib.error.URLError("refused")):
+            with self.assertRaises(BrokerUnavailableError):
+                self.c.submit("tok")
+
+    def test_timeout_is_ambiguous_unavailable(self) -> None:
+        # A dropped/late response after the request was sent is the exact orphan
+        # risk: the host may have launched. Must be ambiguous, not a definite fail.
+        with patch(_URLOPEN, side_effect=TimeoutError("read timed out")):
+            with self.assertRaises(BrokerUnavailableError):
+                self.c.submit("tok")
+
+    def test_malformed_success_body_raises(self) -> None:
+        with patch(_URLOPEN, return_value=_resp({"op": "launch"})):  # missing bottle_id
+            with self.assertRaises(BrokerClientError):
+                self.c.submit("tok")
+
+    def test_empty_error_body_is_tolerated(self) -> None:
+        # An error with no readable JSON body still classifies by status code.
+        with patch(_URLOPEN, side_effect=_http_error(401)):
+            with self.assertRaises(BrokerAuthError):
+                self.c.submit("forged")
+
+    def test_non_json_success_body_raises(self) -> None:
+        # A 200 whose body isn't JSON is tolerated into {} then fails the
+        # missing-field check — a definite client error, not a crash.
+        m = MagicMock()
+        m.__enter__.return_value.read.return_value = b"not json at all"
+        with patch(_URLOPEN, return_value=m):
+            with self.assertRaises(BrokerClientError):
+                self.c.submit("tok")
+
+    def test_unreadable_error_body_is_tolerated(self) -> None:
+        # An HTTPError whose body can't be read (fp=None) still classifies by
+        # status — the error detail is best-effort.
+        err = urllib.error.HTTPError(
+            "http://host/broker", 502, "err", {}, None)  # type: ignore[arg-type]
+        with patch(_URLOPEN, side_effect=err):
+            with self.assertRaises(BrokerClientError):
+                self.c.submit("tok")
+
+
+class TestListLive(unittest.TestCase):
+    def setUp(self) -> None:
+        self.c = BrokerClient("http://host:8091")
+
+    def test_returns_source_ips(self) -> None:
+        with patch(_URLOPEN, return_value=_resp({"source_ips": ["10.0.0.1", "10.0.0.2"]})):
+            self.assertEqual(["10.0.0.1", "10.0.0.2"], self.c.list_live("tok"))
+
+    def test_posts_token_to_live_endpoint(self) -> None:
+        with patch(_URLOPEN, return_value=_resp({"source_ips": []})) as m:
+            self.c.list_live("signed-token")
+        request = m.call_args.args[0]
+        self.assertEqual("POST", request.get_method())
+        self.assertTrue(request.full_url.endswith("/broker/live"))
+        self.assertEqual({"token": "signed-token"}, json.loads(request.data))
+
+    def test_non_string_entries_are_filtered(self) -> None:
+        with patch(_URLOPEN, return_value=_resp({"source_ips": ["10.0.0.1", 5, None, ""]})):
+            self.assertEqual(["10.0.0.1"], self.c.list_live("tok"))
+
+    def test_missing_source_ips_raises(self) -> None:
+        # A response without the field is malformed — better to fail (reconcile
+        # skips) than to reconcile against a silent empty set.
+        with patch(_URLOPEN, return_value=_resp({})):
+            with self.assertRaises(BrokerClientError):
+                self.c.list_live("tok")
+
+    def test_401_raises_broker_auth_error(self) -> None:
+        with patch(_URLOPEN, side_effect=_http_error(401, {"error": "bad signature"})):
+            with self.assertRaises(BrokerAuthError):
+                self.c.list_live("forged")
+
+    def test_502_enumeration_failure_is_client_error(self) -> None:
+        with patch(_URLOPEN, side_effect=_http_error(502, {"error": "docker down"})):
+            with self.assertRaises(BrokerClientError):
+                self.c.list_live("tok")
+
+    def test_unreachable_is_unavailable(self) -> None:
+        with patch(_URLOPEN, side_effect=urllib.error.URLError("refused")):
+            with self.assertRaises(BrokerUnavailableError):
+                self.c.list_live("tok")
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/test_orchestrator_client.py

@@ -3,8 +3,6 @@
 from __future__ import annotations
 
 import json
-import subprocess
-import sys
 import unittest
 import urllib.error
 from unittest.mock import MagicMock, patch
@@ -22,30 +20,6 @@ from bot_bottle.orchestrator.client import (
 _URLOPEN = "bot_bottle.orchestrator.client.urllib.request.urlopen"
 
 
-class TestImportBoundary(unittest.TestCase):
-    def test_host_client_does_not_import_server_dependencies(self) -> None:
-        script = """
-import importlib.abc
-import sys
-
-class BlockServerDependencies(importlib.abc.MetaPathFinder):
-    def find_spec(self, fullname, path=None, target=None):
-        if fullname.split(".", 1)[0] in {"fastapi", "uvicorn"}:
-            raise ImportError(f"host import reached {fullname}")
-        return None
-
-sys.meta_path.insert(0, BlockServerDependencies())
-import bot_bottle.orchestrator.client
-"""
-        result = subprocess.run(
-            [sys.executable, "-c", script],
-            capture_output=True,
-            text=True,
-            check=False,
-        )
-        self.assertEqual(0, result.returncode, result.stderr)
-
-
 class TestHostAuthToken(unittest.TestCase):
     def test_mints_a_cli_token_from_the_host_key(self) -> None:
         # The CLI mints its `cli` token from the control-plane trust domain's
@@ -185,26 +159,27 @@ class TestReconcile(unittest.TestCase):
     def setUp(self) -> None:
         self.c = OrchestratorClient("http://orch:8080")
 
-    def test_posts_live_ips_and_returns_reaped(self) -> None:
+    def test_triggers_sweep_and_returns_reaped(self) -> None:
         with patch(_URLOPEN, return_value=_resp(200, {"reaped": ["b1", "b2"]})) as m:
-            got = self.c.reconcile(["10.0.0.2", "10.0.0.3"])
+            got = self.c.reconcile()
         self.assertEqual(["b1", "b2"], got)
         sent = json.loads(m.call_args.args[0].data)
-        self.assertEqual(["10.0.0.2", "10.0.0.3"], sent["live_source_ips"])
+        # The live set is no longer sent — the orchestrator enumerates it.
+        self.assertNotIn("live_source_ips", sent)
         self.assertNotIn("grace_seconds", sent)  # omitted -> server default
 
     def test_grace_seconds_is_forwarded_when_given(self) -> None:
         with patch(_URLOPEN, return_value=_resp(200, {"reaped": []})) as m:
-            self.c.reconcile([], grace_seconds=30)
+            self.c.reconcile(grace_seconds=30)
         self.assertEqual(30, json.loads(m.call_args.args[0].data)["grace_seconds"])
 
     def test_malformed_reaped_is_tolerated(self) -> None:
         with patch(_URLOPEN, return_value=_resp(200, {"reaped": ["ok", 5, None]})):
-            self.assertEqual(["ok"], self.c.reconcile([]))
+            self.assertEqual(["ok"], self.c.reconcile())
         with patch(_URLOPEN, return_value=_resp(200, {})):
-            self.assertEqual([], self.c.reconcile([]))
+            self.assertEqual([], self.c.reconcile())
 
     def test_error_status_raises(self) -> None:
         with patch(_URLOPEN, side_effect=_http_error(500)):
             with self.assertRaises(OrchestratorClientError):
-                self.c.reconcile([])
+                self.c.reconcile()

tests/unit/test_orchestrator_docker_broker.py

@@ -8,6 +8,7 @@ from unittest.mock import Mock, patch
 
 from bot_bottle.orchestrator.broker import (
     BrokerAuthError,
+    BrokerUnavailableError,
     LaunchRequest,
     sign_request,
 )
@@ -96,5 +97,50 @@ class TestDockerBroker(unittest.TestCase):
             m.assert_not_called()
 
 
+class TestDockerBrokerListLive(unittest.TestCase):
+    def setUp(self) -> None:
+        self.secret = secrets.token_bytes(16)
+        self.broker = DockerBroker(self.secret)
+
+    def test_enumerates_labeled_container_ips(self) -> None:
+        # `docker ps` lists two labeled containers; each inspect yields an IP.
+        ps = Mock(returncode=0, stdout="c1\nc2\n", stderr="")
+        i1 = Mock(returncode=0, stdout="10.0.0.1 \n", stderr="")
+        i2 = Mock(returncode=0, stdout="10.0.0.2 \n", stderr="")
+        with patch.object(self.broker, "_docker", side_effect=[ps, i1, i2]) as m:
+            got = self.broker._list_live()
+        self.assertEqual(["10.0.0.1", "10.0.0.2"], got)
+        # First call is the label-filtered `docker ps`.
+        ps_argv = m.call_args_list[0].args[0]
+        self.assertEqual(["docker", "ps", "--filter", f"label={BOTTLE_ID_LABEL}"], ps_argv[:4])
+
+    def test_no_containers_is_empty(self) -> None:
+        with patch.object(self.broker, "_docker",
+                          return_value=Mock(returncode=0, stdout="", stderr="")):
+            self.assertEqual([], self.broker._list_live())
+
+    def test_ps_failure_raises(self) -> None:
+        with patch.object(self.broker, "_docker",
+                          return_value=Mock(returncode=1, stdout="", stderr="daemon down")):
+            with self.assertRaises(DockerBrokerError):
+                self.broker._list_live()
+
+    def test_inspect_failure_raises(self) -> None:
+        ps = Mock(returncode=0, stdout="c1\n", stderr="")
+        bad = Mock(returncode=1, stdout="", stderr="no such container")
+        with patch.object(self.broker, "_docker", side_effect=[ps, bad]):
+            with self.assertRaises(DockerBrokerError):
+                self.broker._list_live()
+
+    def test_enumeration_failure_surfaces_as_unavailable_via_list_live(self) -> None:
+        # Through the verb, a backend failure is the single "live set unknown"
+        # signal (BrokerUnavailableError) reconcile catches to skip the sweep.
+        token = sign_request(LaunchRequest(op="list_live"), self.secret)
+        with patch.object(self.broker, "_docker",
+                          return_value=Mock(returncode=1, stdout="", stderr="down")):
+            with self.assertRaises(BrokerUnavailableError):
+                self.broker.list_live(token)
+
+
 if __name__ == "__main__":
     unittest.main()

tests/unit/test_orchestrator_gateway.py

@@ -248,88 +248,6 @@ class TestDockerGateway(unittest.TestCase):
             calls,
         )
 
-    def test_ensure_running_replaces_poisoned_ipv6_network(self) -> None:
-        # A daemon that default-enables IPv6 leaves the gateway network with a
-        # malformed fdd0::/64 gateway, so `docker network inspect` exits
-        # non-zero with a ParseAddr error (not "No such network"). `--ipv6=false`
-        # can't heal an already-poisoned network — the create just no-ops on
-        # "already exists" — so _ensure_network must force-remove and recreate
-        # it, else every later subnet read keeps failing.
-        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", "network", "inspect"]:
-                return _proc(
-                    returncode=1,
-                    stderr='ParseAddr("fdd0:0:0:4::1/64"): unexpected character, '
-                    'want colon (at "/64")',
-                )
-            return _proc()
-
-        with patch(_RUN_DOCKER, side_effect=fake):
-            self.sc.connect_to_orchestrator(_ORCH_URL, _TOKEN)
-        self.assertIn(["docker", "rm", "--force", self.sc.name], calls)
-        self.assertIn(["docker", "network", "rm", self.sc.network], calls)
-        creates = [c for c in calls if c[:3] == ["docker", "network", "create"]]
-        self.assertEqual(
-            [[
-                "docker", "network", "create",
-                "--ipv6=false",
-                "--subnet", DEFAULT_GATEWAY_SUBNET,
-                "--label",
-                f"bot-bottle.gateway-subnet={DEFAULT_GATEWAY_SUBNET}",
-                self.sc.network,
-            ]],
-            creates,
-        )
-
-    def test_ensure_running_creates_network_when_inspect_reports_absent(self) -> None:
-        # The absent case (inspect fails with "No such network") must NOT try to
-        # remove anything — it just creates. Guards the poisoned-vs-absent split.
-        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="Error: No such network: x")
-            return _proc(stdout="") if argv[:2] == ["docker", "ps"] else _proc()
-
-        with patch(_RUN_DOCKER, side_effect=fake):
-            self.sc.connect_to_orchestrator(_ORCH_URL, _TOKEN)
-        self.assertNotIn(["docker", "network", "rm", self.sc.network], calls)
-        creates = [c for c in calls if c[:3] == ["docker", "network", "create"]]
-        self.assertEqual(1, len(creates))
-
-    def test_ensure_running_does_not_destroy_on_generic_inspect_error(self) -> None:
-        # A generic inspect failure (daemon hiccup, permission, timeout) is NOT
-        # evidence of a poisoned network. Only the ParseAddr poison signature may
-        # take the destructive heal path; anything else must surface as an error
-        # without tearing down a possibly-healthy shared gateway.
-        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", "network", "inspect"]:
-                return _proc(
-                    returncode=1,
-                    stderr="Cannot connect to the Docker daemon at unix:///var/run/docker.sock",
-                )
-            return _proc()
-
-        with patch(_RUN_DOCKER, side_effect=fake):
-            with self.assertRaises(GatewayError):
-                self.sc.connect_to_orchestrator(_ORCH_URL, _TOKEN)
-        # No mutation of the shared gateway: neither the container nor the
-        # network is removed, and nothing is recreated.
-        self.assertNotIn(["docker", "network", "rm", self.sc.network], calls)
-        self.assertFalse(any(c[:3] == ["docker", "rm", "--force"] for c in calls))
-        self.assertEqual([], [c for c in calls if c[:3] == ["docker", "network", "create"]])
-
     def test_ca_cert_pem_reads_from_container(self) -> None:
         with patch(_RUN_DOCKER, return_value=_proc(stdout=_CA_PEM)) as m:
             self.assertEqual(_CA_PEM, self.sc.ca_cert_pem())

tests/unit/test_orchestrator_host_server.py

@@ -0,0 +1,354 @@
+"""Unit tests for the host control server (issue #468, chunk 1).
+
+Mostly exercises the pure `dispatch()` (socket-free, like the orchestrator
+server tests), plus a real-socket round-trip through `BrokerClient` that proves
+the full sign -> POST -> verify -> act seam over HTTP.
+"""
+
+from __future__ import annotations
+
+import http.client
+import io
+import json
+import os
+import secrets
+import tempfile
+import threading
+import typing
+import unittest
+from unittest.mock import MagicMock, patch
+
+from bot_bottle.orchestrator.broker import (
+    BrokerAuthError,
+    LaunchBroker,
+    LaunchRequest,
+    StubBroker,
+    sign_request,
+)
+from bot_bottle.orchestrator.broker_client import BrokerClient
+from bot_bottle.orchestrator.host_server import (
+    MAX_BODY_BYTES,
+    Handler,
+    HostControlServer,
+    broker_secret,
+    dispatch,
+    main,
+    make_host_server,
+)
+from bot_bottle.paths import LAUNCH_BROKER_KEY_ENV
+
+
+def _body(obj: object) -> bytes:
+    return json.dumps(obj).encode()
+
+
+class _RaisingBroker(LaunchBroker):
+    """A broker whose backend launch/enumeration always fails — exercises the
+    502 path (an operational backend failure, distinct from a fail-closed
+    provenance 401)."""
+
+    def _launch(self, req: LaunchRequest) -> None:
+        raise RuntimeError("docker down")
+
+    def _teardown(self, req: LaunchRequest) -> None:
+        raise RuntimeError("docker down")
+
+    def _list_live(self) -> list[str]:
+        raise RuntimeError("docker down")
+
+
+class TestDispatch(unittest.TestCase):
+    def setUp(self) -> None:
+        self.secret = secrets.token_bytes(16)
+        self.broker = StubBroker(self.secret)
+
+    def _token(self, **kwargs: object) -> str:
+        return sign_request(LaunchRequest(**kwargs), self.secret)  # type: ignore[arg-type]
+
+    def test_health(self) -> None:
+        status, payload = dispatch(self.broker, "GET", "/health", b"")
+        self.assertEqual(200, status)
+        self.assertEqual("ok", payload["status"])
+
+    def test_broker_launch_verifies_and_acts(self) -> None:
+        token = self._token(
+            op="launch", bottle_id="b1", source_ip="10.243.0.1",
+            image_ref="img", slot=2,
+        )
+        status, payload = dispatch(self.broker, "POST", "/broker", _body({"token": token}))
+        self.assertEqual(200, status)
+        self.assertEqual("launch", payload["op"])
+        self.assertEqual("b1", payload["bottle_id"])
+        self.assertEqual("img", payload["image_ref"])
+        self.assertEqual(2, payload["slot"])
+        self.assertEqual(["b1"], [r.bottle_id for r in self.broker.launched])
+
+    def test_broker_teardown_acts(self) -> None:
+        token = self._token(op="teardown", bottle_id="b1")
+        status, _ = dispatch(self.broker, "POST", "/broker", _body({"token": token}))
+        self.assertEqual(200, status)
+        self.assertEqual(["b1"], [r.bottle_id for r in self.broker.torn_down])
+
+    def test_forged_token_is_401_and_nothing_acted(self) -> None:
+        forged = sign_request(
+            LaunchRequest(op="launch", bottle_id="b1"), secrets.token_bytes(16))
+        status, payload = dispatch(self.broker, "POST", "/broker", _body({"token": forged}))
+        self.assertEqual(401, status)
+        self.assertIn("broker auth failed", str(payload["error"]))
+        self.assertEqual([], self.broker.launched)  # fail-closed: never launched
+
+    def test_backend_failure_is_502(self) -> None:
+        broker = _RaisingBroker(self.secret)
+        token = self._token(op="launch", bottle_id="b1", image_ref="img")
+        status, payload = dispatch(broker, "POST", "/broker", _body({"token": token}))
+        self.assertEqual(502, status)
+        self.assertIn("backend launch failed", str(payload["error"]))
+
+    def test_broker_live_returns_source_ips(self) -> None:
+        # Two launched bottles -> the stub reports both as live.
+        self.broker.submit(self._token(op="launch", bottle_id="b1", source_ip="10.0.0.1"))
+        self.broker.submit(self._token(op="launch", bottle_id="b2", source_ip="10.0.0.2"))
+        token = self._token(op="list_live")
+        status, payload = dispatch(self.broker, "POST", "/broker/live", _body({"token": token}))
+        self.assertEqual(200, status)
+        self.assertEqual(
+            ["10.0.0.1", "10.0.0.2"],
+            sorted(typing.cast("list[str]", payload["source_ips"])),
+        )
+
+    def test_broker_live_forged_token_is_401(self) -> None:
+        forged = sign_request(LaunchRequest(op="list_live"), secrets.token_bytes(16))
+        status, payload = dispatch(self.broker, "POST", "/broker/live", _body({"token": forged}))
+        self.assertEqual(401, status)
+        self.assertIn("broker auth failed", str(payload["error"]))
+
+    def test_broker_live_rejects_a_mutation_token(self) -> None:
+        # A launch token routed to the query endpoint is a fail-closed 401 — the
+        # endpoints don't share a schema even though they share a secret.
+        token = self._token(op="launch", bottle_id="b1", image_ref="img")
+        status, _ = dispatch(self.broker, "POST", "/broker/live", _body({"token": token}))
+        self.assertEqual(401, status)
+
+    def test_broker_live_backend_failure_is_502(self) -> None:
+        broker = _RaisingBroker(self.secret)
+        token = self._token(op="list_live")
+        status, payload = dispatch(broker, "POST", "/broker/live", _body({"token": token}))
+        self.assertEqual(502, status)
+        self.assertIn("backend enumeration failed", str(payload["error"]))
+
+    def test_broker_live_missing_token_is_400(self) -> None:
+        status, _ = dispatch(self.broker, "POST", "/broker/live", _body({}))
+        self.assertEqual(400, status)
+
+    def test_missing_token_is_400(self) -> None:
+        status, _ = dispatch(self.broker, "POST", "/broker", _body({}))
+        self.assertEqual(400, status)
+
+    def test_bad_json_is_400(self) -> None:
+        status, _ = dispatch(self.broker, "POST", "/broker", b"{not json")
+        self.assertEqual(400, status)
+
+    def test_empty_body_is_missing_token_400(self) -> None:
+        # Empty body parses to {} (no token) → 400, never reaching the broker.
+        status, _ = dispatch(self.broker, "POST", "/broker", b"")
+        self.assertEqual(400, status)
+        self.assertEqual([], self.broker.launched)
+
+    def test_non_object_body_is_400(self) -> None:
+        status, _ = dispatch(self.broker, "POST", "/broker", b"[1, 2]")
+        self.assertEqual(400, status)
+
+    def test_unknown_route_404(self) -> None:
+        status, _ = dispatch(self.broker, "GET", "/nope", b"")
+        self.assertEqual(404, status)
+
+    def test_trailing_slash_normalized(self) -> None:
+        status, _ = dispatch(self.broker, "GET", "/health/", b"")
+        self.assertEqual(200, status)
+
+
+class TestBrokerSecret(unittest.TestCase):
+    """The durable launch-broker key (#468/#476): prefer the env-injected key,
+    else the durable host key file, so signer and verifier resolve the same one."""
+
+    def test_reads_injected_key_from_env(self) -> None:
+        # The injected key is honoured regardless of allow_host_file — both the
+        # host controller and the guest orchestrator take an injected key.
+        self.assertEqual(
+            b"injected-key", broker_secret({LAUNCH_BROKER_KEY_ENV: "injected-key"}))
+        self.assertEqual(
+            b"injected-key",
+            broker_secret({LAUNCH_BROKER_KEY_ENV: "injected-key"}, allow_host_file=True))
+
+    def test_guest_without_injection_fails_closed(self) -> None:
+        # The default (guest orchestrator): no env key and NO host-file fallback,
+        # so it returns None rather than mint a divergent process-local key.
+        self.assertIsNone(broker_secret({}))
+
+    def test_host_side_falls_back_to_the_durable_key_file(self) -> None:
+        # allow_host_file=True (host controller / dev-harness): mint/read the
+        # durable host key file, the same key on every call (restart re-adoption).
+        with tempfile.TemporaryDirectory() as root:
+            with patch.dict("os.environ", {"BOT_BOTTLE_ROOT": root}, clear=False):
+                os.environ.pop(LAUNCH_BROKER_KEY_ENV, None)
+                first = broker_secret(allow_host_file=True)
+                second = broker_secret(allow_host_file=True)
+        self.assertTrue(first)
+        self.assertEqual(first, second)
+
+
+class TestSeamRoundTrip(unittest.TestCase):
+    """The whole point of chunk 1: a request signed by the orchestrator side is
+    POSTed to a real host control server, verified there, and acted on — over
+    HTTP, not an in-process call."""
+
+    def _serve(self, broker: LaunchBroker) -> BrokerClient:
+        server = make_host_server(broker, "127.0.0.1", 0)
+        self.addCleanup(server.server_close)
+        threading.Thread(target=server.serve_forever, daemon=True).start()
+        self.addCleanup(server.shutdown)
+        host, port = server.server_address[0], server.server_address[1]
+        return BrokerClient(f"http://{host}:{port}")
+
+    def test_sign_post_verify_act_over_http(self) -> None:
+        secret = secrets.token_bytes(16)
+        broker = StubBroker(secret)
+        client = self._serve(broker)
+        req = LaunchRequest(
+            op="launch", bottle_id="b1", source_ip="10.0.0.1", image_ref="img", slot=1)
+        got = client.submit(sign_request(req, secret))
+        self.assertEqual(req, got)  # the controller echoes the verified request
+        self.assertEqual(["b1"], [r.bottle_id for r in broker.launched])
+
+    def test_forged_token_raises_broker_auth_error_over_http(self) -> None:
+        secret = secrets.token_bytes(16)
+        broker = StubBroker(secret)
+        client = self._serve(broker)
+        forged = sign_request(
+            LaunchRequest(op="launch", bottle_id="b1"), secrets.token_bytes(16))
+        with self.assertRaises(BrokerAuthError):
+            client.submit(forged)
+        self.assertEqual([], broker.launched)  # fail-closed across the wire
+
+    def test_list_live_enumerates_over_http(self) -> None:
+        secret = secrets.token_bytes(16)
+        broker = StubBroker(secret)
+        broker.live_source_ips = ["10.0.0.7", "10.0.0.8"]
+        client = self._serve(broker)
+        got = client.list_live(sign_request(LaunchRequest(op="list_live"), secret))
+        self.assertEqual(["10.0.0.7", "10.0.0.8"], got)
+
+
+class TestRequestLimits(unittest.TestCase):
+    """The privileged listener must not let a caller that can merely reach the
+    socket (no signed token) exhaust it via an oversized declared body — and it
+    rejects on the Content-Length *header*, before reading the body."""
+
+    def _addr(self) -> tuple[str, int]:
+        self.broker = StubBroker(secrets.token_bytes(16))
+        server = make_host_server(self.broker, "127.0.0.1", 0)
+        self.addCleanup(server.server_close)
+        threading.Thread(target=server.serve_forever, daemon=True).start()
+        self.addCleanup(server.shutdown)
+        host, port = server.server_address[:2]
+        return typing.cast(str, host), port
+
+    def test_oversized_content_length_is_rejected_before_reading(self) -> None:
+        host, port = self._addr()
+        conn = http.client.HTTPConnection(host, port, timeout=5)
+        self.addCleanup(conn.close)
+        # Declare an oversized body but send only a sliver: the server must reject
+        # on the header before reading, so the caller gets a clean, deterministic
+        # 413 (no large unread body to race a connection reset).
+        conn.putrequest("POST", "/broker", skip_accept_encoding=True)
+        conn.putheader("Content-Type", "application/json")
+        conn.putheader("Content-Length", str(MAX_BODY_BYTES + 1))
+        conn.endheaders()
+        conn.send(b"{}")  # far short of the declared length; never read
+        resp = conn.getresponse()
+        self.assertEqual(413, resp.status)
+        self.assertEqual([], self.broker.launched)  # never reached the broker
+
+
+class TestServeUnit(unittest.TestCase):
+    """Drive `Handler._serve` directly (no socket). The real per-request handler
+    runs in a daemon thread whose coverage/trace data is lost, so the
+    bounded-body and error paths are exercised here in the main thread instead."""
+
+    def _handler(self, broker: LaunchBroker, headers: dict[str, str],
+                 body: bytes = b"") -> tuple[Handler, MagicMock]:
+        server = HostControlServer.__new__(HostControlServer)
+        server.broker = broker
+        h = Handler.__new__(Handler)
+        h.server = server
+        h.headers = headers  # type: ignore[assignment] — dict is a valid .get() stand-in
+        h.path = "/broker"
+        h.rfile = io.BytesIO(body)
+        h.wfile = io.BytesIO()
+        send_response = MagicMock()
+        h.send_response = send_response  # type: ignore[method-assign]
+        h.send_header = MagicMock()  # type: ignore[method-assign]
+        h.end_headers = MagicMock()  # type: ignore[method-assign]
+        return h, send_response
+
+    def test_oversized_content_length_is_413(self) -> None:
+        broker = StubBroker(secrets.token_bytes(16))
+        h, send_response = self._handler(broker, {"Content-Length": str(MAX_BODY_BYTES + 1)})
+        h.do_POST()  # exercises do_POST -> _serve
+        send_response.assert_called_once_with(413)
+        self.assertEqual([], broker.launched)  # rejected before the broker
+
+    def test_invalid_content_length_is_400(self) -> None:
+        h, send_response = self._handler(StubBroker(secrets.token_bytes(16)),
+                                         {"Content-Length": "not-a-number"})
+        h._serve("POST")
+        send_response.assert_called_once_with(400)
+
+    def test_valid_request_dispatches_200(self) -> None:
+        secret = secrets.token_bytes(16)
+        broker = StubBroker(secret)
+        body = _body({"token": sign_request(
+            LaunchRequest(op="teardown", bottle_id="b1"), secret)})
+        h, send_response = self._handler(broker, {"Content-Length": str(len(body))}, body)
+        h._serve("POST")
+        send_response.assert_called_once_with(200)
+        self.assertEqual(["b1"], [r.bottle_id for r in broker.torn_down])
+
+    def test_dispatch_exception_becomes_500(self) -> None:
+        # dispatch is total, but the handler still guards it: a raised dispatch
+        # returns 500 rather than dropping the connection.
+        h, send_response = self._handler(
+            StubBroker(secrets.token_bytes(16)), {"Content-Length": "0"})
+        with patch("bot_bottle.orchestrator.host_server.dispatch",
+                   side_effect=RuntimeError("boom")):
+            h._serve("POST")
+        send_response.assert_called_once_with(500)
+
+    def test_health_over_do_get(self) -> None:
+        h, send_response = self._handler(StubBroker(secrets.token_bytes(16)), {})
+        h.path = "/health"
+        h.do_GET()
+        send_response.assert_called_once_with(200)
+
+
+class TestMain(unittest.TestCase):
+    def test_fail_closed_without_secret(self) -> None:
+        with patch("bot_bottle.orchestrator.host_server.broker_secret",
+                   return_value=None):
+            self.assertEqual(2, main(["--port", "0"]))
+
+    def test_serves_then_shuts_down_cleanly(self) -> None:
+        fake = MagicMock()
+        fake.server_address = ("127.0.0.1", 0)
+        fake.serve_forever.side_effect = KeyboardInterrupt
+        with patch("bot_bottle.orchestrator.host_server.broker_secret",
+                   return_value=b"k"), \
+             patch("bot_bottle.orchestrator.host_server.make_host_server",
+                   return_value=fake):
+            self.assertEqual(0, main(["--port", "0"]))
+        fake.serve_forever.assert_called_once()
+        fake.server_close.assert_called_once()
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/test_orchestrator_main.py

@@ -0,0 +1,67 @@
+"""Unit: the orchestrator dev-harness entrypoint (`python -m bot_bottle.orchestrator`).
+
+Exercises broker selection (stub / docker / http) and the fail-closed http path,
+patching `make_server` so the serve loop returns instead of blocking.
+"""
+
+from __future__ import annotations
+
+import os
+import secrets
+import tempfile
+import unittest
+from pathlib import Path
+from unittest.mock import MagicMock, patch
+
+from bot_bottle.orchestrator.__main__ import main
+from bot_bottle.paths import LAUNCH_BROKER_KEY_ENV
+
+
+def _fake_server() -> MagicMock:
+    fake = MagicMock()
+    fake.server_address = ("127.0.0.1", 0)
+    # Break out of serve_forever immediately, exercising the try/finally.
+    fake.serve_forever.side_effect = KeyboardInterrupt
+    return fake
+
+
+class TestMain(unittest.TestCase):
+    def _run(self, broker: str, env: dict[str, str] | None = None) -> tuple[int, MagicMock]:
+        fake = _fake_server()
+        with tempfile.TemporaryDirectory() as d:
+            argv = ["--db", str(Path(d) / "r.db"), "--port", "0", "--broker", broker]
+            with patch("bot_bottle.orchestrator.__main__.make_server", return_value=fake), \
+                    patch.dict("os.environ", env or {}, clear=False):
+                if env is None:
+                    os.environ.pop(LAUNCH_BROKER_KEY_ENV, None)
+                rc = main(argv)
+        return rc, fake
+
+    def test_stub_broker_serves_and_closes(self) -> None:
+        rc, fake = self._run("stub")
+        self.assertEqual(0, rc)
+        fake.serve_forever.assert_called_once()
+        fake.server_close.assert_called_once()
+
+    def test_docker_broker_serves(self) -> None:
+        rc, _ = self._run("docker")
+        self.assertEqual(0, rc)
+
+    def test_http_broker_with_injected_key_serves(self) -> None:
+        # The guest orchestrator takes the launch-broker key by injection.
+        rc, _ = self._run(
+            "http", env={LAUNCH_BROKER_KEY_ENV: secrets.token_urlsafe(16)})
+        self.assertEqual(0, rc)
+
+    def test_http_broker_without_injected_key_exits(self) -> None:
+        # Fail-closed: no host-file fallback for the guest, so a missing injected
+        # key is a usage error rather than a silently-minted divergent key.
+        with tempfile.TemporaryDirectory() as d:
+            with patch.dict("os.environ", {}, clear=False):
+                os.environ.pop(LAUNCH_BROKER_KEY_ENV, None)
+                with self.assertRaises(SystemExit):
+                    main(["--db", str(Path(d) / "r.db"), "--broker", "http"])
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/test_orchestrator_secret_store.py

@@ -3,12 +3,11 @@
 from __future__ import annotations
 
 import base64
-import hashlib
-import hmac
 import unittest
 
 from bot_bottle.orchestrator.store.secret_store import (
     ENV_VAR_SECRET_NAME,
+    _NONCE_BYTES,
     decrypt_value,
     encrypt_value,
     new_env_var_secret,
@@ -68,35 +67,27 @@ class TestDecryptErrors(unittest.TestCase):
     def setUp(self) -> None:
         self.secret = new_env_var_secret()
 
-    def test_wrong_key_raises_value_error(self) -> None:
-        ct = encrypt_value(self.secret, "secret-token")
-        other_key = new_env_var_secret()
-        with self.assertRaisesRegex(ValueError, "authentication failed"):
-            decrypt_value(other_key, ct)
+    def test_wrong_key_always_raises_value_error(self) -> None:
+        # Deterministic: the authentication tag rejects a wrong key every time,
+        # so reprovision can never inject a garbage token. Repeat across many
+        # random keys (the old unauthenticated scheme let ~5% through when the
+        # garbage happened to decode as valid UTF-8).
+        for _ in range(200):
+            ct = encrypt_value(self.secret, "secret-token")
+            with self.assertRaises(ValueError):
+                decrypt_value(new_env_var_secret(), ct)
 
     def test_tampered_ciphertext_raises_value_error(self) -> None:
-        raw = bytearray(base64.urlsafe_b64decode(
-            encrypt_value(self.secret, "secret-token") + "=="
-        ))
-        raw[22] ^= 1
-        tampered = base64.urlsafe_b64encode(raw).rstrip(b"=").decode()
-        with self.assertRaisesRegex(ValueError, "authentication failed"):
+        ct = encrypt_value(self.secret, "secret-token")
+        raw = bytearray(base64.urlsafe_b64decode(ct + "=" * (-len(ct) % 4)))
+        raw[_NONCE_BYTES] ^= 0x01  # flip a bit in the ciphertext body → tag mismatch
+        tampered = base64.urlsafe_b64encode(bytes(raw)).rstrip(b"=").decode()
+        with self.assertRaises(ValueError):
             decrypt_value(self.secret, tampered)
 
-    def test_reads_legacy_ciphertext_for_migration(self) -> None:
-        key = base64.urlsafe_b64decode(self.secret + "==")
-        nonce = b"0123456789abcdef"
-        plaintext = b"legacy-token"
-        stream = hmac.new(
-            key, nonce + (0).to_bytes(4, "big"), hashlib.sha256,
-        ).digest()
-        ciphertext = bytes(p ^ k for p, k in zip(plaintext, stream))
-        legacy = base64.urlsafe_b64encode(nonce + ciphertext).rstrip(b"=").decode()
-        self.assertEqual("legacy-token", decrypt_value(self.secret, legacy))
-
     def test_truncated_blob_raises_value_error(self) -> None:
         with self.assertRaises(ValueError):
-            decrypt_value(self.secret, "dG9vc2hvcnQ")  # "tooshort" — under 16 nonce bytes
+            decrypt_value(self.secret, "dG9vc2hvcnQ")  # "tooshort" — under nonce+tag
 
     def test_invalid_base64_raises_value_error(self) -> None:
         with self.assertRaises(ValueError):

tests/unit/test_orchestrator_server.py

@@ -6,9 +6,7 @@ server tests), plus one real-socket round-trip to prove the handler wiring.
 
 from __future__ import annotations
 
-import asyncio
 import base64
-import http.client
 import io
 import json
 import secrets
@@ -18,17 +16,13 @@ import threading
 import unittest
 import urllib.error
 import urllib.request
-import httpx
 from contextlib import closing
-from collections.abc import Iterator
 from pathlib import Path
 from unittest.mock import MagicMock, patch
 
 from bot_bottle.orchestrator_auth import ROLE_CLI, ROLE_GATEWAY, mint
-from bot_bottle.orchestrator import api as orchestrator_api
 from bot_bottle.orchestrator.broker import StubBroker
-from bot_bottle.orchestrator.http_contract import ORCHESTRATOR_AUTH_HEADER
-from bot_bottle.orchestrator.server import MAX_BODY_BYTES, create_app, make_server
+from bot_bottle.orchestrator.server import dispatch, make_server
 from bot_bottle.orchestrator.store.registry_store import BottleRecord, RegistryStore
 from bot_bottle.orchestrator.service import OrchestratorCore
 from bot_bottle.orchestrator.store.store_manager import StoreManager
@@ -43,47 +37,6 @@ def _body(obj: object) -> bytes:
     return json.dumps(obj).encode()
 
 
-def dispatch(
-    orchestrator: OrchestratorCore,
-    method: str,
-    path: str,
-    body: bytes,
-    *,
-    role: str | None = ROLE_CLI,
-) -> tuple[int, dict[str, object]]:
-    """Exercise the real ASGI application without a network socket."""
-    key = "in-process-dispatch-key"
-    headers = {"content-type": "application/json"}
-    if role is not None:
-        headers[ORCHESTRATOR_AUTH_HEADER] = mint(role, key)
-
-    async def request() -> httpx.Response:
-        transport = httpx.ASGITransport(app=create_app(orchestrator, signing_key=key))
-        async with httpx.AsyncClient(
-            transport=transport,
-            base_url="http://orchestrator",
-            follow_redirects=True,
-        ) as client:
-            return await client.request(
-                method, path, content=body, headers=headers,
-            )
-
-    response = asyncio.run(request())
-    payload = response.json()
-    if response.status_code == 422:
-        detail = payload.get("detail", []) if isinstance(payload, dict) else []
-        field = ""
-        if isinstance(detail, list) and detail and isinstance(detail[0], dict):
-            location = detail[0].get("loc", ())
-            if isinstance(location, (list, tuple)) and len(location) > 1:
-                field = str(location[1])
-        suffix = f": {field}" if field else ""
-        return 400, {"error": f"invalid request body{suffix}"}
-    if isinstance(payload, dict) and "detail" in payload and "error" not in payload:
-        payload = {"error": payload["detail"]}
-    return response.status_code, payload
-
-
 def _orchestrator(db_path: Path) -> OrchestratorCore:
     store = RegistryStore(db_path)
     store.migrate()
@@ -298,51 +251,11 @@ class TestDispatch(unittest.TestCase):
 
 
 class TestServerRoundTrip(unittest.TestCase):
-    def _raw_status(self, content_length: str, *, authenticated: bool = True) -> int:
-        tmp = tempfile.TemporaryDirectory()
-        self.addCleanup(tmp.cleanup)
-        key = "request-limits-key"
-        server = make_server(
-            _orchestrator(Path(tmp.name) / "r.db"),
-            "127.0.0.1", 0, signing_key=key,
-        )
-        self.addCleanup(server.server_close)
-        threading.Thread(target=server.serve_forever, daemon=True).start()
-        self.addCleanup(server.shutdown)
-        conn = http.client.HTTPConnection(
-            str(server.server_address[0]), server.server_address[1], timeout=5,
-        )
-        self.addCleanup(conn.close)
-        conn.putrequest("POST", "/bottles")
-        conn.putheader("Content-Length", content_length)
-        if authenticated:
-            conn.putheader(
-                "x-bot-bottle-orchestrator-auth", mint(ROLE_CLI, key),
-            )
-        conn.endheaders()
-        return conn.getresponse().status
-
-    def test_rejects_malformed_content_length(self) -> None:
-        self.assertEqual(400, self._raw_status("not-a-number"))
-
-    def test_rejects_oversized_body_without_reading_it(self) -> None:
-        self.assertEqual(413, self._raw_status(str(MAX_BODY_BYTES + 1)))
-
-    def test_rejects_unauthenticated_request_before_reading_body(self) -> None:
-        self.assertEqual(
-            401,
-            self._raw_status(str(MAX_BODY_BYTES), authenticated=False),
-        )
-
     def test_http_register_health_attribute(self) -> None:
         tmp = tempfile.TemporaryDirectory()
         self.addCleanup(tmp.cleanup)
         orch = _orchestrator(Path(tmp.name) / "r.db")
-        signing_key = "round-trip-key"
-        auth = mint(ROLE_CLI, signing_key)
-        server = make_server(
-            orch, "127.0.0.1", 0, signing_key=signing_key,
-        )
+        server = make_server(orch, "127.0.0.1", 0)
         self.addCleanup(server.server_close)
         thread = threading.Thread(target=server.serve_forever, daemon=True)
         thread.start()
@@ -354,10 +267,7 @@ class TestServerRoundTrip(unittest.TestCase):
         reg = json.load(urllib.request.urlopen(
             urllib.request.Request(
                 f"{base}/bottles", data=_body({"source_ip": "10.243.0.7"}),
-                method="POST", headers={
-                    "Content-Type": "application/json",
-                    "x-bot-bottle-orchestrator-auth": auth,
-                },
+                method="POST", headers={"Content-Type": "application/json"},
             ), timeout=5,
         ))
         self.assertTrue(reg["bottle_id"])
@@ -369,10 +279,7 @@ class TestServerRoundTrip(unittest.TestCase):
             urllib.request.Request(
                 f"{base}/attribute",
                 data=_body({"source_ip": "10.243.0.7", "identity_token": reg["identity_token"]}),
-                method="POST", headers={
-                    "Content-Type": "application/json",
-                    "x-bot-bottle-orchestrator-auth": auth,
-                },
+                method="POST", headers={"Content-Type": "application/json"},
             ), timeout=5,
         ))
         self.assertEqual(reg["bottle_id"], attr["bottle_id"])
@@ -380,25 +287,15 @@ class TestServerRoundTrip(unittest.TestCase):
     def test_internal_failure_is_contextual_but_redacted(self) -> None:
         orch = MagicMock()
         orch.registry.all.side_effect = RuntimeError("SENSITIVE request value")
-        signing_key = "failure-path-key"
-        auth = mint(ROLE_CLI, signing_key)
         with patch("sys.stderr", io.StringIO()) as stderr:
-            server = make_server(
-                orch, "127.0.0.1", 0, signing_key=signing_key,
-            )
+            server = make_server(orch, "127.0.0.1", 0)
             self.addCleanup(server.server_close)
             thread = threading.Thread(target=server.serve_forever, daemon=True)
             thread.start()
             self.addCleanup(server.shutdown)
             host, port = server.server_address[0], server.server_address[1]
             with self.assertRaises(urllib.error.HTTPError) as raised:
-                urllib.request.urlopen(
-                    urllib.request.Request(
-                        f"http://{host}:{port}/bottles",
-                        headers={"x-bot-bottle-orchestrator-auth": auth},
-                    ),
-                    timeout=5,
-                )
+                urllib.request.urlopen(f"http://{host}:{port}/bottles", timeout=5)
             payload = json.loads(raised.exception.read())
             output = stderr.getvalue()
         self.assertEqual({"error": "internal error"}, payload)
@@ -407,76 +304,6 @@ class TestServerRoundTrip(unittest.TestCase):
         self.assertNotIn("SENSITIVE", output)
 
 
-class TestControlPlaneBoundary(unittest.IsolatedAsyncioTestCase):
-    @staticmethod
-    def _scope(key: str) -> dict[str, object]:
-        return {
-            "type": "http",
-            "asgi": {"version": "3.0"},
-            "http_version": "1.1",
-            "method": "POST",
-            "scheme": "http",
-            "path": "/bottles",
-            "raw_path": b"/bottles",
-            "query_string": b"",
-            "headers": [(
-                ORCHESTRATOR_AUTH_HEADER.encode(),
-                mint(ROLE_CLI, key).encode(),
-            )],
-            "client": ("127.0.0.1", 1),
-            "server": ("127.0.0.1", 80),
-            "state": {},
-        }
-
-    async def test_chunked_oversized_body_returns_413(self) -> None:
-        key = "stream-limit-key"
-        called = False
-        first: dict[str, object] = {
-            "type": "http.request",
-            "body": b"x" * MAX_BODY_BYTES,
-            "more_body": True,
-        }
-        last: dict[str, object] = {
-            "type": "http.request", "body": b"x", "more_body": False,
-        }
-        chunks: Iterator[dict[str, object]] = iter([first, last])
-        sent: list[dict[str, object]] = []
-
-        async def receive() -> dict[str, object]:
-            return next(chunks)
-
-        async def send(message: dict[str, object]) -> None:
-            sent.append(message)
-
-        async def inner(*_args: object) -> None:
-            nonlocal called
-            called = True
-
-        boundary = orchestrator_api.ControlPlaneBoundary(inner, key)
-        await boundary(self._scope(key), receive, send)  # type: ignore[arg-type]
-        self.assertFalse(called)
-        self.assertEqual(413, sent[0]["status"])
-
-    async def test_slow_stream_returns_408(self) -> None:
-        key = "stream-timeout-key"
-        sent: list[dict[str, object]] = []
-
-        async def receive() -> dict[str, object]:
-            await asyncio.sleep(1)
-            return {"type": "http.request", "body": b"", "more_body": False}
-
-        async def send(message: dict[str, object]) -> None:
-            sent.append(message)
-
-        async def inner(*_args: object) -> None:
-            self.fail("timed-out body reached the application")
-
-        boundary = orchestrator_api.ControlPlaneBoundary(inner, key)
-        with patch.object(orchestrator_api, "REQUEST_BODY_TIMEOUT_SECONDS", 0.01):
-            await boundary(self._scope(key), receive, send)  # type: ignore[arg-type]
-        self.assertEqual(408, sent[0]["status"])
-
-
 class TestOrchestratorAuth(unittest.TestCase):
     """Role-scoped control-plane tokens (issue #400 / #469 review): every route
     but /health needs a valid token, and the token's role gates which routes it
@@ -542,9 +369,8 @@ class TestOrchestratorAuth(unittest.TestCase):
         self.assertIsNotNone(self.orch.registry.get(rec.bottle_id))
 
     def _server_with_key(self, signing_key: str):
-        server = make_server(
-            self.orch, "127.0.0.1", 0, signing_key=signing_key,
-        )
+        with patch.dict("os.environ", {"BOT_BOTTLE_ORCHESTRATOR_TOKEN": signing_key}):
+            server = make_server(self.orch, "127.0.0.1", 0)
         self.addCleanup(server.server_close)
         threading.Thread(target=server.serve_forever, daemon=True).start()
         self.addCleanup(server.shutdown)
@@ -573,10 +399,16 @@ class TestOrchestratorAuth(unittest.TestCase):
         self.assertEqual(403, self._status(f"{base}/bottles", header=gateway_tok))
         self.assertEqual(200, self._status(f"{base}/bottles", header=cli_tok))
 
-    def test_unconfigured_server_refuses_to_start(self) -> None:
-        with patch.dict("os.environ", {}, clear=True):
-            with self.assertRaisesRegex(ValueError, "signing key is required"):
-                make_server(self.orch, "127.0.0.1", 0)
+    def test_unconfigured_server_runs_open(self) -> None:
+        """No signing key set (tests / nft-protected Firecracker): open mode
+        grants full cli access, so existing round-trip behavior is unchanged."""
+        with patch.dict("os.environ", {}, clear=False):
+            import os
+            os.environ.pop("BOT_BOTTLE_ORCHESTRATOR_TOKEN", None)
+            server = make_server(self.orch, "127.0.0.1", 0)
+        self.addCleanup(server.server_close)
+        self.assertEqual(ROLE_CLI, server.role_for(""))
+        self.assertEqual(ROLE_CLI, server.role_for("anything"))
 
 
 class TestDispatchSupervise(unittest.TestCase):
@@ -792,13 +624,18 @@ if __name__ == "__main__":
 
 
 class TestReconcileRoute(unittest.TestCase):
-    """`POST /reconcile` — the host tells the orchestrator which bottles are
-    actually up, since the orchestrator can't see the backend from inside the
-    infra container."""
+    """`POST /reconcile` — a bare self-heal trigger. The orchestrator pulls its
+    own live set from the broker (`list_live`); the caller no longer supplies it,
+    so the request body carries at most `grace_seconds`."""
 
     def setUp(self) -> None:
         self._tmp = tempfile.TemporaryDirectory()
-        self.orch = _orchestrator(Path(self._tmp.name) / "r.db")
+        store = RegistryStore(Path(self._tmp.name) / "r.db")
+        store.migrate()
+        secret = secrets.token_bytes(16)
+        # Hold a typed StubBroker so tests can set its live set directly.
+        self.broker = StubBroker(secret)
+        self.orch = OrchestratorCore(store, self.broker, secret)
 
     def tearDown(self) -> None:
         self._tmp.cleanup()
@@ -815,44 +652,35 @@ class TestReconcileRoute(unittest.TestCase):
     def test_reaps_absent_and_reports_ids(self) -> None:
         dead = self._old("10.0.0.1")
         alive = self._old("10.0.0.2")
-        status, payload = dispatch(
-            self.orch, "POST", "/reconcile", _body({"live_source_ips": ["10.0.0.2"]}))
+        self.broker.live_source_ips = ["10.0.0.2"]  # broker: only .2 is up
+        status, payload = dispatch(self.orch, "POST", "/reconcile", _body({}))
         self.assertEqual(200, status)
         self.assertEqual([dead], payload["reaped"])
         self.assertIsNone(self.orch.registry.get(dead))
         self.assertIsNotNone(self.orch.registry.get(alive))
 
-    def test_missing_live_source_ips_is_400(self) -> None:
-        status, _ = dispatch(self.orch, "POST", "/reconcile", _body({}))
-        self.assertEqual(400, status)
+    def test_empty_body_triggers_the_sweep(self) -> None:
+        """No body is fine — the live set comes from the broker, not the body."""
+        dead = self._old("10.0.0.1")
+        self.broker.live_source_ips = []  # broker: nothing running
+        status, payload = dispatch(self.orch, "POST", "/reconcile", b"")
+        self.assertEqual(200, status)
+        self.assertEqual([dead], payload["reaped"])
 
     def test_grace_seconds_is_honoured(self) -> None:
         """A grace window wide enough to cover the row protects it."""
         self.orch.registry.register("10.0.0.3")
+        self.broker.live_source_ips = []
         status, payload = dispatch(
-            self.orch, "POST", "/reconcile",
-            _body({"live_source_ips": [], "grace_seconds": 3600}))
+            self.orch, "POST", "/reconcile", _body({"grace_seconds": 3600}))
         self.assertEqual(200, status)
         self.assertEqual([], payload["reaped"])
 
-    def test_non_string_entries_are_rejected(self) -> None:
-        status, payload = dispatch(
-            self.orch, "POST", "/reconcile",
-            _body({"live_source_ips": [None, 7, "10.0.0.9"]}))
-        self.assertEqual(400, status)
-        self.assertIn("live_source_ips", str(payload["error"]))
-
-    def test_empty_live_source_ip_is_rejected(self) -> None:
-        status, payload = dispatch(
-            self.orch, "POST", "/reconcile", _body({"live_source_ips": [""]}))
-        self.assertEqual(400, status)
-        self.assertIn("live_source_ips", str(payload["error"]))
-
     def test_invalid_grace_seconds_is_rejected(self) -> None:
         for value in (True, "30", -1, float("inf"), float("nan")):
             with self.subTest(value=value):
                 status, payload = dispatch(
                     self.orch, "POST", "/reconcile",
-                    _body({"live_source_ips": [], "grace_seconds": value}))
+                    _body({"grace_seconds": value}))
                 self.assertEqual(400, status)
                 self.assertIn("grace_seconds", str(payload["error"]))

tests/unit/test_orchestrator_service.py

@@ -11,7 +11,12 @@ from contextlib import closing
 from pathlib import Path
 from unittest.mock import patch
 
-from bot_bottle.orchestrator.broker import LaunchBroker, LaunchRequest, StubBroker
+from bot_bottle.orchestrator.broker import (
+    BrokerUnavailableError,
+    LaunchBroker,
+    LaunchRequest,
+    StubBroker,
+)
 from bot_bottle.orchestrator.store.registry_store import RegistryStore
 from bot_bottle.orchestrator.service import OrchestratorCore
 from bot_bottle.orchestrator.store.secret_store import new_env_var_secret
@@ -25,8 +30,8 @@ from bot_bottle.orchestrator.supervisor import (
 
 
 class _FailingBroker(LaunchBroker):
-    """Verifies the token like any broker, then fails the launch — to
-    exercise the orchestrator's registry rollback."""
+    """Verifies the token like any broker, then fails the launch *definitely* —
+    to exercise the orchestrator's registry rollback."""
 
     def _launch(self, req: LaunchRequest) -> None:
         raise RuntimeError("launch failed")
@@ -34,6 +39,24 @@ class _FailingBroker(LaunchBroker):
     def _teardown(self, req: LaunchRequest) -> None:
         pass
 
+    def _list_live(self) -> list[str]:
+        return []
+
+
+class _UnavailableBroker(LaunchBroker):
+    """Verifies the token, then raises the *ambiguous* BrokerUnavailableError —
+    the host may already have launched — so the orchestrator must KEEP the
+    registry row rather than orphan a running container."""
+
+    def _launch(self, req: LaunchRequest) -> None:
+        raise BrokerUnavailableError("delivery dropped after send")
+
+    def _teardown(self, req: LaunchRequest) -> None:
+        pass
+
+    def _list_live(self) -> list[str]:
+        return []
+
 
 class TestOrchestrator(unittest.TestCase):
     def setUp(self) -> None:
@@ -144,11 +167,20 @@ class TestOrchestrator(unittest.TestCase):
         self.assertIsNotNone(self.orch.resolve("10.243.0.3", rec.identity_token))
         self.assertIsNone(self.orch.resolve("10.243.0.3", "wrong-token"))
 
-    def test_launch_rolls_back_registry_on_broker_failure(self) -> None:
+    def test_launch_rolls_back_registry_on_definite_broker_failure(self) -> None:
         orch = OrchestratorCore(self.store, _FailingBroker(self.secret), self.secret)
         with self.assertRaises(RuntimeError):
             orch.launch_bottle("10.243.0.9")
-        self.assertEqual([], self.store.all())  # no orphan
+        self.assertEqual([], self.store.all())  # no orphan row
+
+    def test_launch_keeps_registry_on_ambiguous_broker_failure(self) -> None:
+        # The host may already have launched the bottle before the response was
+        # lost, so deregistering would orphan a running container with no row.
+        # The row is kept for reconcile to reap iff the bottle is not live.
+        orch = OrchestratorCore(self.store, _UnavailableBroker(self.secret), self.secret)
+        with self.assertRaises(BrokerUnavailableError):
+            orch.launch_bottle("10.243.0.9")
+        self.assertEqual(1, len(self.store.all()))  # row survives — no orphan container
 
     def test_gateway_status_reports_unconfigured(self) -> None:
         # The orchestrator no longer owns a standalone gateway lifecycle; the
@@ -339,8 +371,9 @@ class TestOrchestratorSupervise(unittest.TestCase):
         pid = self.orch.supervise_queue_proposal(
             rec.bottle_id, tool=TOOL_EGRESS_ALLOW,
             proposed_file="routes:\n  - host: google.com\n", justification="j")
-        # No live source IPs -> the bottle is reaped (grace 0 so it's immediate).
-        self.assertEqual([rec.bottle_id], self.orch.reconcile([], grace_seconds=0))
+        # No live source IPs (nothing launched through the stub) -> the bottle
+        # is reaped (grace 0 so it's immediate).
+        self.assertEqual([rec.bottle_id], self.orch.reconcile(grace_seconds=0))
         self.assertEqual(
             {"status": "unknown"}, self.orch.supervise_poll_response(rec.bottle_id, pid))
 
@@ -385,7 +418,9 @@ class TestOrchestratorReconcile(unittest.TestCase):
         live = self.orch.launch_bottle("10.243.0.2", tokens={"EGRESS_TOKEN_0": "keep"})
         self._age_all(600)
 
-        self.assertEqual([dead.bottle_id], self.orch.reconcile(["10.243.0.2"]))
+        # The broker reports only .2 as still running -> .1 is reaped.
+        self.broker.live_source_ips = ["10.243.0.2"]
+        self.assertEqual([dead.bottle_id], self.orch.reconcile())
         self.assertIsNone(self.store.get(dead.bottle_id))
         self.assertIsNotNone(self.store.get(live.bottle_id))
         # The in-memory egress credential goes with the row.
@@ -397,14 +432,31 @@ class TestOrchestratorReconcile(unittest.TestCase):
         broker error must not stop the sweep clearing the row."""
         self.orch.launch_bottle("10.243.0.1")
         self._age_all(600)
-        self.broker.launched.clear()
-        self.orch.reconcile([])
+        self.broker.live_source_ips = []  # broker reports nothing running
+        self.orch.reconcile()
         self.assertEqual([], self.broker.torn_down)
 
     def test_reconcile_keeps_everything_when_all_are_live(self) -> None:
         a = self.orch.launch_bottle("10.243.0.1")
         b = self.orch.launch_bottle("10.243.0.2")
         self._age_all(600)
-        self.assertEqual([], self.orch.reconcile(["10.243.0.1", "10.243.0.2"]))
+        self.broker.live_source_ips = ["10.243.0.1", "10.243.0.2"]
+        self.assertEqual([], self.orch.reconcile())
+        self.assertIsNotNone(self.store.get(a.bottle_id))
+        self.assertIsNotNone(self.store.get(b.bottle_id))
+
+    def test_reconcile_skipped_when_broker_cannot_enumerate(self) -> None:
+        """A broker that can't return an authoritative live set must NOT be
+        treated as "nothing is live" — that would reap every healthy bottle.
+        The sweep is skipped instead."""
+        a = self.orch.launch_bottle("10.243.0.1")
+        b = self.orch.launch_bottle("10.243.0.2")
+        self._age_all(600)
+
+        def _boom() -> list[str]:
+            raise RuntimeError("docker ps failed")
+
+        self.broker._list_live = _boom  # type: ignore[method-assign]
+        self.assertEqual([], self.orch.reconcile())
         self.assertIsNotNone(self.store.get(a.bottle_id))
         self.assertIsNotNone(self.store.get(b.bottle_id))

tests/unit/test_supervise_server.py

@@ -13,7 +13,6 @@ import tempfile
 import threading
 import time
 import types
-import typing
 import unittest
 from pathlib import Path
 
@@ -48,7 +47,6 @@ from bot_bottle.gateway.supervisor.server import (
     jsonrpc_error,
     jsonrpc_result,
     parse_jsonrpc,
-    resolved_routes_payload,
     validate_proposed_file,
 )
 
@@ -703,40 +701,22 @@ class TestResolvedRoutesPayload(unittest.TestCase):
             "  - host: api.anthropic.com\n"
             "  - host: www.google.com\n"
         )
-        payload = resolved_routes_payload(
-            typing.cast(
-                supervise_server.PolicyResolver,
-                _FakeSuperviseResolver(bottle_id="b1", policy=policy),
-            ),
-            _SRC,
-            _TOK,
-        )
+        payload = _handler(
+            _FakeSuperviseResolver(bottle_id="b1", policy=policy)
+        )._resolved_routes_payload()
         assert payload is not None
         self.assertFalse(payload["isError"])  # type: ignore[index]
         data = json.loads(payload["content"][0]["text"])  # type: ignore[index]
         hosts = {r["host"] for r in data["routes"]}
         self.assertEqual({"api.anthropic.com", "www.google.com"}, hosts)
 
-    def test_orchestrator_error_is_not_reported_as_empty_policy(self) -> None:
-        with self.assertRaises(supervise_server.RouteResolutionError):
-            resolved_routes_payload(
-                typing.cast(
-                    supervise_server.PolicyResolver,
-                    _FakeSuperviseResolver(raises=True),
-                ),
-                _SRC,
-                _TOK,
-            )
-
-    def test_authoritative_empty_policy_remains_successful(self) -> None:
-        payload = resolved_routes_payload(
-            typing.cast(
-                supervise_server.PolicyResolver,
-                _FakeSuperviseResolver(bottle_id="b1", policy="routes: []\n"),
-            ),
-            _SRC,
-            _TOK,
-        )
+    def test_orchestrator_error_fails_closed_to_empty(self) -> None:
+        # resolve_client_context swallows resolver errors → deny-all (empty),
+        # never another bottle's routes.
+        payload = _handler(
+            _FakeSuperviseResolver(raises=True)
+        )._resolved_routes_payload()
+        assert payload is not None
         data = json.loads(payload["content"][0]["text"])  # type: ignore[index]
         self.assertEqual([], data["routes"])
 
@@ -744,13 +724,7 @@ class TestResolvedRoutesPayload(unittest.TestCase):
         # A server without a resolver is a misconfig, not a mode: raise rather
         # than list anything.
         with self.assertRaises(_RpcInternalError):
-            _handler(None)._dispatch(
-                parse_jsonrpc(
-                    b'{"jsonrpc":"2.0","id":1,"method":"tools/call",'
-                    b'"params":{"name":"list-egress-routes"}}',
-                ),
-                ServerConfig(),
-            )
+            _handler(None)._resolved_routes_payload()
 
 
 class TestNonBlockingSupervise(unittest.TestCase):

tests/unit/test_supervisor_mcp_dispatch.py

@@ -1,81 +0,0 @@
-"""Unit tests for framework-neutral supervisor MCP dispatch."""
-
-from __future__ import annotations
-
-import unittest
-from dataclasses import dataclass
-
-from bot_bottle.gateway.supervisor.mcp_dispatch import (
-    Handlers,
-    MethodNotFoundError,
-    dispatch,
-)
-from bot_bottle.supervisor import types as _sv
-
-
-@dataclass(frozen=True)
-class _Request:
-    method: str
-    params: dict[str, object]
-
-
-class TestDispatch(unittest.TestCase):
-    def setUp(self) -> None:
-        self.calls: list[str] = []
-
-        def handler(name: str):
-            def call(_params: dict[str, object]) -> str:
-                self.calls.append(name)
-                return name
-
-            return call
-
-        self.handlers = Handlers(
-            initialize=handler("initialize"),
-            tools_list=handler("tools_list"),
-            list_routes=handler("list_routes"),
-            check_proposal=handler("check_proposal"),
-            propose=handler("propose"),
-        )
-
-    def request(self, method: str, **params: object) -> _Request:
-        return _Request(method=method, params=params)
-
-    def test_routes_protocol_methods(self) -> None:
-        self.assertEqual(
-            "initialize", dispatch(self.request("initialize"), self.handlers),
-        )
-        self.assertEqual(
-            "tools_list", dispatch(self.request("tools/list"), self.handlers),
-        )
-        self.assertIsNone(
-            dispatch(self.request("notifications/initialized"), self.handlers),
-        )
-
-    def test_routes_each_tool_class(self) -> None:
-        self.assertEqual(
-            "list_routes",
-            dispatch(
-                self.request("tools/call", name=_sv.TOOL_LIST_EGRESS_ROUTES),
-                self.handlers,
-            ),
-        )
-        self.assertEqual(
-            "check_proposal",
-            dispatch(
-                self.request("tools/call", name=_sv.TOOL_CHECK_PROPOSAL),
-                self.handlers,
-            ),
-        )
-        self.assertEqual(
-            "propose",
-            dispatch(self.request("tools/call", name=_sv.TOOL_EGRESS_ALLOW), self.handlers),
-        )
-
-    def test_unknown_method_is_typed(self) -> None:
-        with self.assertRaisesRegex(MethodNotFoundError, "unknown"):
-            dispatch(self.request("unknown"), self.handlers)
-
-
-if __name__ == "__main__":
-    unittest.main()

tests/unit/test_trust_domain.py

@@ -6,10 +6,13 @@ import unittest
 from unittest.mock import patch
 
 from bot_bottle import orchestrator_auth
-from bot_bottle.orchestrator_auth import ROLE_CLI, ROLE_GATEWAY
+from bot_bottle.orchestrator_auth import ROLE_CLI, ROLE_GATEWAY, ROLE_HOST
 from bot_bottle.trust_domain import (
     CONTROL_PLANE,
+    HOST_CONTROLLER,
+    LAUNCH_BROKER,
     ControlPlaneProvisioning,
+    LaunchBrokerProvisioning,
     ProvisioningError,
     TrustDomain,
 )
@@ -78,7 +81,8 @@ class TestControlPlaneProvisioning(unittest.TestCase):
             self.assertEqual("key", prov.orchestrator_key())
 
     def test_orchestrator_key_fail_closes_when_empty(self) -> None:
-        # Invariant 4: the orchestrator must never start without a key. There is no
+        # Invariant 4: the orchestrator must never start without a key — it would
+        # run OPEN and grant every caller that reaches it full `cli`. There is no
         # topology opt-out: a separate host does not stop the gateway (or any
         # other caller) from reaching the control-plane listener.
         prov = ControlPlaneProvisioning()
@@ -100,5 +104,73 @@ class TestControlPlaneProvisioning(unittest.TestCase):
         self.assertNotEqual(ROLE_CLI, CONTROL_PLANE.verify(tok, "k"))
 
 
+class TestLaunchBrokerAndHostControllerDomains(unittest.TestCase):
+    """The real #468 domains: the launch-broker key (shared by orchestrator +
+    host controller) and the host controller's own lifecycle key."""
+
+    def test_launch_broker_mints_no_role_tokens(self) -> None:
+        # Empty role set — it provides durable key material for the broker's own
+        # launch JWT, not orchestrator_auth role tokens.
+        self.assertEqual(frozenset(), LAUNCH_BROKER.roles)
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value="k"):
+            with self.assertRaises(ValueError):
+                LAUNCH_BROKER.mint(ROLE_CLI)
+
+    def test_host_controller_signs_host_role_only(self) -> None:
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value="k"):
+            tok = HOST_CONTROLLER.mint(ROLE_HOST)
+        self.assertEqual(ROLE_HOST, HOST_CONTROLLER.verify(tok, "k"))
+        # A control-plane `cli` token (the orchestrator's key) never verifies as a
+        # host-controller role — the orchestrator can't forge lifecycle creds.
+        cli_tok = orchestrator_auth.mint(ROLE_CLI, "k")
+        self.assertIsNone(HOST_CONTROLLER.verify(cli_tok, "k"))
+
+    def test_control_plane_cannot_mint_the_host_role(self) -> None:
+        # `host` is outside the control-plane role set on purpose.
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value="k"):
+            with self.assertRaises(ValueError):
+                CONTROL_PLANE.mint(ROLE_HOST)
+
+    def test_the_three_domains_use_distinct_keys_and_env_vars(self) -> None:
+        self.assertEqual(3, len({
+            CONTROL_PLANE.key_filename,
+            LAUNCH_BROKER.key_filename,
+            HOST_CONTROLLER.key_filename,
+        }))
+        self.assertEqual(3, len({
+            CONTROL_PLANE.key_env, LAUNCH_BROKER.key_env, HOST_CONTROLLER.key_env,
+        }))
+
+
+class TestLaunchBrokerProvisioning(unittest.TestCase):
+    def test_broker_key_returns_the_durable_key(self) -> None:
+        prov = LaunchBrokerProvisioning()
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value="bk"):
+            self.assertEqual("bk", prov.broker_key())
+
+    def test_broker_key_fail_closes_when_empty(self) -> None:
+        # An empty key would leave the host controller unable to verify any
+        # launch — fail-closed rather than hand back a useless/dangerous key.
+        prov = LaunchBrokerProvisioning()
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value=""):
+            with self.assertRaises(ProvisioningError):
+                prov.broker_key()
+
+    def test_controller_key_is_distinct_from_the_broker_key(self) -> None:
+        # The orchestrator holds the broker key but NEVER the controller key.
+        prov = LaunchBrokerProvisioning()
+        keys = {"launch-broker-key": "bk", "host-controller-key": "ck"}
+        with patch("bot_bottle.trust_domain.host_signing_key",
+                   side_effect=keys.__getitem__):
+            self.assertEqual("bk", prov.broker_key())
+            self.assertEqual("ck", prov.controller_key())
+
+    def test_controller_key_fail_closes_when_empty(self) -> None:
+        prov = LaunchBrokerProvisioning()
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value=""):
+            with self.assertRaises(ProvisioningError):
+                prov.controller_key()
+
+
 if __name__ == "__main__":
     unittest.main()

tests/unit/test_wheel_install.py

@@ -62,10 +62,7 @@ class TestWheelInstall(unittest.TestCase):
 
         # Installing the freshly-built wheel must succeed — fail if it doesn't.
         install = subprocess.run(
-            [
-                str(cls.venv_py), "-m", "pip", "install", "--quiet",
-                "--force-reinstall", "--no-deps", str(wheels[0]),
-            ],
+            [str(cls.venv_py), "-m", "pip", "install", "--quiet", str(wheels[0])],
             capture_output=True, text=True, check=False,
         )
         if install.returncode != 0: