docs: analyze Sandbox Agent SDK architecture

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/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/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/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/supervisor/mcp_dispatch.py

@@ -1,79 +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.context import resolve_client_context
-from bot_bottle.gateway.egress.schema import route_to_yaml_dict
-from bot_bottle.gateway.policy_resolver import 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."""
-
-
-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 the calling bottle's routes, failing closed to an empty list."""
-    config, _slug, _tokens = resolve_client_context(
-        resolver, source_ip, identity_token,
-    )
-    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",
-    "dispatch",
-    "resolved_routes_payload",
-]

bot_bottle/gateway/supervisor/server.py

@@ -58,15 +58,10 @@ import typing
 from dataclasses import dataclass
 
 from bot_bottle.constants import IDENTITY_HEADER
-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,
-    dispatch,
-    resolved_routes_payload,
-)
 from bot_bottle.supervisor import types as _sv
 
 
@@ -616,11 +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
@@ -643,37 +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:
+        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,
+                )
+            # 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(
-                params,
-                config,
-                resolver=self._resolver_or_fail(),
-                source_ip=self.client_address[0],
-                identity_token=self._identity_token(),
+                req.params, config, resolver=resolver,
+                source_ip=source_ip, identity_token=token,
             )
-
-        return dispatch(
-            req,
-            DispatchHandlers(
-                initialize=handle_initialize,
-                tools_list=handle_tools_list,
-                list_routes=lambda _params: resolved_routes_payload(
-                    self._resolver_or_fail(),
-                    self.client_address[0],
-                    self._identity_token(),
-                ),
-                check_proposal=check,
-                propose=propose,
-            ),
-        )
+        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
@@ -692,6 +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")

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 +16,12 @@ 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 .broker import LaunchBroker, StubBroker
+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:
@@ -40,11 +38,6 @@ def main(argv: list[str] | None = None) -> int:
         help="launch broker: 'stub' records requests; 'docker' runs containers",
     )
     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()
@@ -62,14 +55,17 @@ def main(argv: list[str] | None = None) -> int:
     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/client.py

@@ -21,7 +21,7 @@ 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
 

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 +1,464 @@
-"""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: {"live_source_ips": [...],
+                                                ["grace_seconds"]}
+    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: the caller enumerates its live bottles (only
+        # the host can see the backend) and the orchestrator drops rows for
+        # every other active bottle. Trusted-caller only — an agent that could
+        # reach this would be able to unregister its neighbours.
+        try:
+            data = _parse_json_object(body)
+        except ValueError as e:
+            return 400, {"error": f"invalid JSON: {e}"}
+        raw_ips = data.get("live_source_ips")
+        if not isinstance(raw_ips, list):
+            return 400, {"error": "live_source_ips (list of strings) is required"}
+        if any(not isinstance(ip, str) or not ip for ip in raw_ips):
+            return 400, {"error": "live_source_ips must contain non-empty strings"}
+        live = raw_ips
+        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(live, **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

@@ -366,23 +366,15 @@ 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

@@ -12,15 +12,9 @@ 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 (stdlib-only,
+no external deps). Each value is encrypted independently. The output blob is
+``nonce (16 bytes) || ciphertext`` 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)]
@@ -36,8 +30,6 @@ import secrets
 _KEY_BYTES = 32    # 256-bit key from ENV_VAR_SECRET
 _NONCE_BYTES = 16  # 128-bit random nonce per encrypt call
 _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 +41,7 @@ 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:
@@ -67,90 +53,42 @@ def _keystream(key: bytes, nonce: bytes, block_index: int) -> bytes:
 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`` 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)]
+        ks = _keystream(key, nonce, i)[: 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()
+    return base64.urlsafe_b64encode(nonce + bytes(ct)).rstrip(b"=").decode()
 
 
-def is_legacy_blob(blob_b64: str) -> bool:
-    """Whether *blob_b64* uses the pre-authentication storage format."""
+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 or a key mismatch (wrong key produces garbage, not an error, unless
+    the plaintext is non-UTF-8 — treat all such failures as wrong key)."""
+    key = _b64dec(secret_b64)
     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."""
+        blob = _b64dec(blob_b64)
+    except Exception as exc:
+        raise ValueError(f"invalid ciphertext blob: {exc}") from exc
     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
-
-
-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."""
-    key = _b64dec(secret_b64)
-    try:
-        blob = _b64dec(blob_b64)
-    except (ValueError, TypeError) 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:
-        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))
-    try:
-        return bytes(pt).decode()
     except UnicodeDecodeError as exc:
         raise ValueError(f"decryption produced non-UTF-8 output (wrong key?): {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/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

@@ -40,7 +40,7 @@ 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 +67,9 @@ 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()
 

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/research/agent-sandbox-landscape.md

@@ -32,9 +32,17 @@ not a principled scope exclusion: both are major hosted sandbox platforms and
 belong in this landscape even though they target platform builders rather than
 bot-bottle's local single-operator workflow.
 
+Updated 2026-07-27 after a scan of recent Show HN launches: **Black LLAB,
+Eve, CloudRouter, Nucleus, yolo-cage, and Sandbox Agent SDK** added as a
+dated entrant cohort. They sharpen the comparison on three axes the original
+table underweighted: the browser/preview loop, parallel-agent operator UX, and
+a provider-neutral automation/session API.
+
 ## Summary
 
-The main table compares bot-bottle against fifteen isolation/sandbox tools.
+The main table compares bot-bottle against fifteen canonical
+isolation/sandbox tools; a later section evaluates six recent HN entrants
+without widening an already unwieldy table.
 Governance/pre-action authorization and credential-only layers are covered
 separately because they don't provide VM or container isolation. None
 duplicate bot-bottle's combination of local
@@ -542,6 +550,199 @@ them.
   framework runtime is not compromised.
 - **Maturity**: Specification + reference implementation, 2026.
 
+## Recent HN entrants (added 2026-07-27)
+
+These are grouped by launch date rather than promoted into the main table.
+Several are young or sparsely documented, and putting them beside mature
+runtime platforms with false precision would obscure the useful comparison.
+The HN launch posts are the evidence snapshot; feature claims should be
+rechecked against their repositories before relying on them for a security
+decision.
+
+### Black LLAB
+
+- **Source**: https://github.com/isaacdear/black-llab ;
+  HN launch https://news.ycombinator.com/item?id=47402394
+- **Isolation/locality**: Local Docker environment, with an isolated container
+  created for each agent task. Shared host kernel; no stronger boundary is
+  claimed.
+- **Agent integration**: General local/cloud model workspace. Its headline is
+  dynamic routing of simple prompts to local models and complex prompts to
+  hosted models, with code execution and web scraping inside the task
+  container.
+- **Network/credentials**: No default-deny egress, payload inspection, or
+  host-side credential injection documented in the launch.
+- **Competitive read**: Superficial overlap ("a container per agent task"),
+  but not a direct security-policy competitor. Its useful challenge is the
+  integrated model-selection UX, which bot-bottle intentionally leaves to the
+  selected agent provider.
+- **Maturity**: Early solo project; HN launch received 1 point.
+
+### Eve
+
+- **Source**: https://eve.new/ ;
+  HN launch https://news.ycombinator.com/item?id=47721255
+- **Isolation/locality**: Managed, hosted Linux sandbox per user/session
+  (claimed 2 vCPU, 4 GB RAM, 10 GB disk), with filesystem, code execution,
+  headless Chromium, and service connectors.
+- **Agent integration**: End-user OpenClaw-style agent product. An orchestrator
+  routes subtasks to specialist models and can run parallel subagents that
+  coordinate through a shared filesystem. Web UI and iMessage are primary
+  interaction surfaces.
+- **Network/credentials**: Broad connectors are a product feature; the launch
+  does not document bot-bottle-style default-deny route policy, content DLP,
+  or credentials held outside the sandbox.
+- **Competitive read**: Adjacent, not direct. Eve sells a managed colleague;
+  bot-bottle lets an operator run existing coding-agent CLIs under local
+  containment. Eve nevertheless demonstrates the appeal of background work,
+  live progress, browser capability, and mobile notification.
+- **Maturity**: Commercial hosted product; HN launch received 71 points and
+  39 comments.
+
+### CloudRouter
+
+- **Source**: https://github.com/manaflow-ai/manaflow/tree/main/packages/cloudrouter ;
+  HN launch https://news.ycombinator.com/item?id=47006393
+- **Isolation/locality**: Claude Code or Codex runs locally and provisions
+  remote cloud VMs/GPUs for execution. Project files are uploaded to the VM;
+  each machine exposes auth-protected VNC, VS Code, and Jupyter surfaces.
+- **Agent integration**: A skill plus CLI lets the coding agent itself start,
+  command, inspect, and tear down machines. Browser automation is integrated,
+  including snapshots and screenshots. Parallel disposable compute is the
+  central workflow.
+- **Network/credentials**: The launch emphasizes remote resource isolation and
+  authenticated UI endpoints, not default-deny guest egress, payload DLP, or
+  proxy-held application credentials.
+- **Competitive read**: The closest recent workflow competitor. It directly
+  addresses parallel coding agents, environmental conflict, and closing the
+  browser/test loop, but trades local custody for elastic cloud compute.
+  Cloud VMs and GPUs could be a future bot-bottle backend; they do not replace
+  its manifest/policy layer.
+- **Maturity**: Active open-source monorepo project; HN launch received
+  138 points and 36 comments.
+
+### Nucleus
+
+- **Source**: https://github.com/coproduct-opensource/nucleus ;
+  HN launch https://news.ycombinator.com/item?id=46855770
+- **Isolation/locality**: Firecracker microVM with an enforcing MCP tool proxy.
+- **Agent integration/config**: Compositional permission envelope for
+  read/write/run actions. The envelope is non-escalating and can tighten or
+  terminate, with scoped approval tokens for gated operations.
+- **Network/credentials**: Default-deny egress, DNS allowlist, iptables drift
+  detection, time/budget caps, and hash-chained audit logging are claimed.
+  Remote append-only audit storage and attestation were roadmap items at
+  launch.
+- **Competitive read**: Direct on security architecture, especially
+  non-escalating policy and tamper-evident audit. It is an early execution/tool
+  proxy rather than a provider-neutral, one-command coding-agent product. Its
+  tool-level action envelope is semantically finer than bot-bottle's network
+  boundary; bot-bottle is stronger on turnkey agent/provider integration,
+  credential custody, Git mediation, and long-running operator workflow.
+- **Maturity**: Early OSS experiment; HN launch received 3 points.
+
+### yolo-cage
+
+- **Source**: https://github.com/borenstein/yolo-cage ;
+  HN launch https://news.ycombinator.com/item?id=46706796
+- **Isolation/locality**: Local sandbox for running multiple coding agents in
+  YOLO mode. The launch discussion describes a VM boundary.
+- **Agent integration**: Built around the native Claude Code experience and
+  motivated by running many agents in parallel without permission-prompt
+  fatigue.
+- **Network/Git/credentials**: Strict egress filtering, configurable HTTP
+  middleware, and mediated `git`/`gh` dispatch are the main value. The launch
+  discussion explicitly identifies provider credential handling as unfinished
+  and difficult because Claude state spans multiple host paths.
+- **Competitive read**: The closest new threat-model competitor. It shares
+  bot-bottle's premise that filesystem isolation alone is insufficient and
+  that Git plus authorized HTTP channels need mediation. bot-bottle currently
+  leads on cross-provider support, proxy-held Claude/Codex/forge credentials,
+  typed per-role manifests, content DLP, and supervision. yolo-cage's simpler
+  pitch and narrower Claude-first setup may be easier to explain.
+- **Maturity**: Early local tool; HN launch received 60 points and 76 comments.
+
+### Sandbox Agent SDK
+
+- **Source**: https://github.com/rivet-dev/sandbox-agent ;
+  HN launch https://news.ycombinator.com/item?id=46795584
+- **Isolation/locality**: Does not provide the isolation primitive. It runs
+  inside E2B, Daytona, Modal, Cloudflare Containers, Agent Computer, BoxLite,
+  Docker, or another sandbox provider. Embedded mode can also run locally
+  without a sandbox.
+- **Agent integration**: Provider-neutral Rust server/SDK exposing a common
+  HTTP/SSE/OpenAPI interface across Claude Code, Codex, OpenCode, Cursor, Amp,
+  and Pi, plus a universal event/session schema for external storage and
+  replay. It also exposes filesystem, managed-process, terminal, MCP, skills,
+  custom-tool, and computer-use APIs. TypeScript is the primary SDK surface.
+- **Network/credentials**: Delegated to the chosen sandbox provider.
+- **Credential posture**: Its documented convenience command extracts real
+  OpenAI/Anthropic credentials from local agent configuration and passes them
+  as environment variables into the sandbox. That is materially weaker than
+  bot-bottle's host-side credential custody, but it is an integration choice,
+  not a structural limitation: a sandbox provider could put a credential
+  proxy underneath the same SDK.
+- **Competitive read**: A serious architectural threat despite not supplying
+  isolation. Sandbox Agent is trying to standardize the boundary *above* the
+  sandbox: one client protocol, session model, and UI/control surface across
+  every coding agent and runtime. If that boundary becomes the ecosystem
+  standard, users and application builders may choose a sandbox provider plus
+  Sandbox Agent rather than a vertically integrated launcher. bot-bottle's
+  manifests would then be valuable chiefly as a local policy/backend
+  implementation unless they expose an equally usable control contract.
+- **Maturity**: Apache 2.0, ~1.5k stars and 426 commits at the 2026-07-27
+  check; HN launch received 41 points.
+
+#### Why the Sandbox Agent architecture is strategically different
+
+The manifest and the universal control protocol solve different layers:
+
+- A bot-bottle manifest is a **trusted launch-time policy composition**. It
+  selects the agent role, isolation backend, image, skills, egress routes,
+  credentials, Git mediation, and supervision policy. Crucially, identity and
+  secret references live on the host side of the trust boundary.
+- Sandbox Agent is a **runtime control and observation protocol**. A remote
+  client creates sessions, sends messages, handles permissions, configures
+  skills/MCP, manipulates files/processes/desktops, and streams normalized
+  events. It deliberately delegates sandbox lifecycle, Git management,
+  storage, network policy, and credential security to other products.
+
+That makes it complementary in a component diagram but competitive in product
+architecture. The layer that becomes the stable integration point tends to own
+the ecosystem. Three plausible threat paths matter:
+
+1. **Standard control plane, interchangeable runtimes.** Applications integrate
+   once with Sandbox Agent and treat E2B, Daytona, BoxLite, Docker, or a future
+   local microVM as replaceable compute. A provider that bundles adequate
+   egress and credential custody makes bot-bottle's end-to-end launcher less
+   necessary.
+2. **Policy grows upward.** Sandbox Agent already configures permissions,
+   skills, MCP, custom tools, filesystem/process access, and computer use. If
+   it adds a declarative, host-verifiable policy document, the overlap with
+   agent/bottle manifests becomes substantial even if enforcement remains
+   delegated.
+3. **UI and session ownership.** Its universal transcript schema, Inspector,
+   React components, event replay, and remote terminal/computer APIs can become
+   the natural basis for desktop, web, and mobile agent managers. bot-bottle's
+   security layer could remain stronger while losing the operator surface and
+   distribution channel.
+
+The counter-position is not to claim that manifests and an API are mutually
+exclusive. The defensible split is:
+
+- bot-bottle owns the trusted policy and enforcement plane outside the agent;
+- a provider-neutral protocol owns agent process control and normalized
+  events; and
+- the operator UI consumes both.
+
+This suggests an explicit compatibility decision rather than parallel,
+accidental protocol design: evaluate running Sandbox Agent inside a bottle and
+exposing it only through the authenticated bot-bottle control plane. If its
+schema is suitable, adopting it could turn a threat into an integration while
+keeping manifests as the higher-trust policy source. If it is unsuitable,
+bot-bottle should still publish a stable provider-neutral session/event API so
+frontends do not depend on Claude/Codex/Pi-specific process behavior.
+
 ## Comparison table
 
 *Isolation/sandbox tools only. AGT and OAP are governance layers — see their per-project notes above.*
@@ -616,6 +817,70 @@ would be a *backend* bot-bottle could call, not a competitor to its
 manifest layer. endo-familiar is in a different paradigm entirely:
 capability passing rather than kernel boundaries.
 
+**Recent entrants change two parts of this read.** yolo-cage is closer to the
+actual threat model than agent-safehouse or litterbox: it combines a VM-style
+boundary with mediated Git and filtered HTTP specifically for parallel coding
+agents. Sandbox Agent SDK is the more important strategic entrant even though
+it supplies no isolation. It can become the standard agent-control layer above
+all of these runtimes, including a future bot-bottle backend. CloudRouter is
+the clearest workflow challenge because its browser/desktop/GPU loop makes
+parallel agents visibly more capable, not merely safer.
+
+## Gap evaluation after the 2026-07-27 entrant scan
+
+### Material gaps
+
+1. **A stable provider-neutral control and event protocol.** This is the
+   largest newly visible gap. bot-bottle normalizes launch/provisioning across
+   providers, but an external UI or orchestrator still lacks one documented
+   contract for creating a Claude/Codex/Pi session, sending input, handling
+   permission/supervision events, streaming normalized output, reconnecting,
+   and replaying history. Sandbox Agent SDK addresses exactly this layer and
+   is already portable across many sandbox providers.
+2. **Browser/preview closure.** CloudRouter and Eve make a browser or desktop
+   part of the standard agent environment and expose screenshots/live viewing
+   to the operator. bot-bottle can run dev servers and supports nested
+   containers, but it does not present a first-class browser/computer-use
+   primitive or an auth-protected preview surface. For coding agents expected
+   to verify UI work, this is a real product gap.
+3. **Unified parallel-session operator UX.** Named persistent bottles and
+   supervision provide the substrate, but the recent products make task
+   switching, live progress, notifications, terminal attach, diffs, and
+   session history the product. Security depth will not compensate for a
+   visibly rougher daily loop.
+4. **Normalized transcript persistence and replay.** bot-bottle preserves
+   provider-specific state for resume; it does not expose a provider-neutral
+   event record suitable for audit, replay, analytics, or a web/mobile client.
+   This is both a UX gap and an audit gap.
+
+### Important, but not necessarily bot-bottle features
+
+- **Cloud VM/GPU provisioning.** Valuable for elastic workloads and could be a
+  backend, but it conflicts with the local-custody default and should not
+  displace core policy work.
+- **Automatic model routing.** Black LLAB and Eve sell task-to-model routing.
+  bot-bottle's provider-template boundary can host that choice without making
+  it part of the trusted sandbox policy.
+- **A thousand SaaS connectors.** This broadens capability and blast radius.
+  The bot-bottle-native answer should remain explicit, scoped forge/egress
+  associations rather than connector count as a goal.
+- **SDK-driven sandbox lifecycle as the primary configuration model.** Useful
+  for platform builders, but not a replacement for reviewable, host-owned
+  manifests. A control API and a declarative policy source are compatible;
+  neither should silently become the other.
+
+### Areas where bot-bottle remains ahead
+
+- real provider and forge credentials remain outside the agent process rather
+  than being extracted into its environment;
+- authorized HTTP payloads are scanned, not merely destination-filtered;
+- Git writes traverse a distinct gate with secret scanning and host-held
+  upstream credentials;
+- role policy is host-owned, composable, and separate from untrusted repo
+  content; and
+- local Firecracker/Apple Container execution preserves operator custody
+  without requiring a hosted sandbox platform.
+
 ## Borrowable ideas
 
 ### Already shipped or otherwise addressed
@@ -642,6 +907,19 @@ capability passing rather than kernel boundaries.
 
 ### Still worth considering
 
+- **Sandbox Agent compatibility or an equivalent stable protocol (highest
+  priority):** spike running its server inside a bottle behind bot-bottle's
+  authenticated control plane. Compare its session/event schema, permission
+  model, restore semantics, and provider coverage with current provider
+  adapters. Adopt compatibility if it preserves the host-owned trust boundary;
+  otherwise specify bot-bottle's own stable API before building another UI.
+- **First-class browser/preview loop** (from CloudRouter and Eve): give a
+  bottle an optional browser/computer-use capability plus an operator-visible,
+  authenticated preview/screenshot surface. Treat its network access as part
+  of the bottle policy, not an implicit bypass.
+- **Provider-neutral transcript/event persistence** (from Sandbox Agent SDK):
+  retain enough normalized structure for replay and audit while preserving the
+  provider-native state needed for exact resume.
 - **Live network activity in the supervisor TUI** (from Docker sbx): show
   allowed and blocked connections and let the operator propose policy changes
   from the existing supervision surface.
@@ -652,10 +930,11 @@ capability passing rather than kernel boundaries.
   closer review. This needs a carefully specified trust model before it can be
   more than a heuristic.
 
-Not worth borrowing: the SDK-first programmatic API style of boxlite /
-microsandbox (cuts against the declarative-manifest stance), and the
-hosted-SaaS dashboard model of tilde.run (cuts against the
-"infrastructure I control" goal).
+Not worth borrowing: SDK-first *policy configuration* as used by boxlite /
+microsandbox (cuts against the reviewable declarative-manifest stance), and
+the hosted-SaaS custody model of tilde.run (cuts against the "infrastructure I
+control" goal). A provider-neutral runtime-control API is a separate concern
+and is worth borrowing.
 
 ## Publishing and positioning verdict
 
@@ -679,9 +958,15 @@ bot-bottle remains unusual in combining:
 The practical wedge is “as easy as native yolo, with declarative role policy
 and self-hosted custody,” including scoped access to private LAN/Tailnet
 services that cloud-first runtimes cannot provide without additional network
-plumbing. The main competitive risks are a local wrapper such as claudebox or
-Docker sbx growing a role-manifest layer, and GUI products such as SuperHQ
-adding equivalent policy and audit depth.
+plumbing. The main competitive risks are now:
+
+- a local wrapper such as yolo-cage, claudebox, or Docker sbx growing a
+  role-manifest and credential-custody layer;
+- Sandbox Agent SDK becoming the standard control/session boundary and making
+  the runtime beneath it interchangeable; and
+- GUI products such as SuperHQ or CloudRouter adding equivalent policy and
+  audit depth before bot-bottle closes the browser/preview and
+  parallel-session UX gaps.
 
 ## Caveats
 

docs/research/sandbox-agent-sdk-architecture.md

@@ -0,0 +1,536 @@
+# Sandbox Agent SDK and bot-bottle: protocol versus product
+
+This note asks whether [Sandbox Agent SDK](https://github.com/rivet-dev/sandbox-agent)
+and bot-bottle compete for the same architectural layer, whether bot-bottle
+can productize the turnkey ecosystem/DX layer above it, and how far the
+Docker/OCI analogy actually holds.
+
+Research conducted 2026-07-27. Sandbox Agent SDK was at the `0.4.x` line,
+Apache 2.0, and documented support for Claude Code, Codex, OpenCode, Cursor,
+Amp, and Pi at the time of review.
+
+## Summary
+
+**The projects are complementary at the component boundary and competitive at
+the product boundary.** Sandbox Agent SDK normalizes how software controls a
+coding-agent process inside an arbitrary sandbox. bot-bottle decides what
+sandbox to create, what trusted role and policy it receives, how credentials
+and Git access cross the boundary, how traffic is constrained, and how an
+operator launches and supervises the result.
+
+The Docker analogy is useful with one correction:
+
+- Sandbox Agent SDK is not equivalent to Linux container APIs or OCI itself.
+  It is closer to a **containerd shim plus a portable exec/session API for
+  coding agents**. It adapts incompatible agent processes to one HTTP/SSE
+  contract.
+- A future independent agent-session specification would be the closer OCI
+  analogue.
+- bot-bottle can credibly occupy the **Docker Engine / Compose / Desktop**
+  layer: packaging, policy composition, lifecycle, networking, credentials,
+  storage, operator UX, and a one-command experience above interchangeable
+  agent adapters and isolation runtimes.
+
+That is a viable position, but “turnkey wrapper” undersells it. A thin wrapper
+is replaceable. The valuable product is a **turnkey, policy-first coding-agent
+runtime** whose manifest compiles trusted operator intent into multiple
+enforcement planes. Sandbox Agent SDK may be one internal process-control
+component of that product.
+
+The recommended direction is:
+
+1. Keep the bot-bottle manifest as the host-owned source of trusted policy.
+2. Spike Sandbox Agent SDK as the in-bottle provider/session adapter.
+3. Expose a stable, provider-neutral bot-bottle control API, compatible with
+   Sandbox Agent where practical.
+4. Keep security decisions and authoritative audit outside the sandbox.
+5. Build the ecosystem around policy packs, agent images, skills, backends,
+   operator UI, and trusted integrations—not around a proprietary transcript
+   protocol.
+
+## What each project is today
+
+### Sandbox Agent SDK
+
+Sandbox Agent is a Rust server that runs alongside the coding agent. A client
+connects over HTTP, streams events over SSE, and uses one API across agent
+implementations. Its documented surface includes:
+
+- creating and restoring agent sessions;
+- sending messages and streaming normalized events;
+- handling permissions;
+- configuring MCP servers, skills, and custom tools;
+- filesystem and managed-process APIs;
+- interactive terminal access;
+- computer-use/desktop operations;
+- a universal session/transcript schema;
+- an Inspector UI, React components, CLI, TypeScript SDK, and OpenAPI spec.
+
+It can run in embedded mode or inside E2B, Daytona, Modal, Cloudflare
+Containers, Agent Computer, BoxLite, Docker, and other environments. It
+explicitly leaves these concerns to the caller or sandbox provider:
+
+- sandbox creation and lifecycle;
+- Git repository management;
+- durable session storage;
+- network policy;
+- isolation strength; and
+- secure credential delivery.
+
+Its documented credential convenience path extracts real provider credentials
+from local agent configuration and passes them into the sandbox environment.
+That is convenient but is not an acceptable security boundary for bot-bottle.
+
+Sources:
+
+- [Sandbox Agent repository and architecture](https://github.com/rivet-dev/sandbox-agent)
+- [Sandbox Agent documentation](https://sandboxagent.dev/docs)
+- [HTTP API](https://sandboxagent.dev/docs/api-reference)
+- [Universal session/transcript schema](https://sandboxagent.dev/docs/session-transcript-schema)
+
+### bot-bottle
+
+bot-bottle is a host-side launch, policy, and enforcement system for existing
+coding-agent CLIs. Its current architecture includes:
+
+- agent and bottle manifests with composition via `extends:`;
+- a host-only trust boundary for roles, identity, and secret references;
+- provider templates and plugins for Claude Code, Codex, Pi, and custom
+  providers;
+- Firecracker on KVM Linux and Apple Container on macOS, with Docker fallback;
+- image construction and provider-specific provisioning;
+- default-deny inspected egress with path/method/header policy;
+- payload DLP on authorized channels;
+- real credentials held outside the agent and injected by the gateway;
+- Git mediation, upstream credential custody, and gitleaks scanning;
+- a per-host authenticated orchestrator and shared gateway;
+- named bottle lifecycle, resume, supervision, and audit state; and
+- a CLI/TUI intended to make full-permission agents operationally tolerable.
+
+The provider layer currently normalizes launch-time concerns—command, image,
+prompt delivery, files, skills, environment, verification, and provider-owned
+egress routes. It does **not** yet expose a stable provider-neutral runtime
+contract for sessions, messages, transcripts, terminals, or normalized events.
+That is the gap Sandbox Agent directly illuminates.
+
+Sources in this repository:
+
+- [`README.md`](../../README.md)
+- [`0070-per-host-orchestrator.md`](../prds/0070-per-host-orchestrator.md)
+- [`0026-agent-provider-templates.md`](../prds/0026-agent-provider-templates.md)
+- [`0053-user-provider-plugins.md`](../prds/0053-user-provider-plugins.md)
+- [`agent_provider.py`](../../bot_bottle/agent_provider.py)
+
+## The layer model
+
+The cleanest architecture has four layers:
+
+| Layer | Responsibility | Likely owner |
+|---|---|---|
+| Operator product | Install, select a role, launch, observe, intervene, resume, review changes | bot-bottle |
+| Trusted policy and lifecycle | Compose manifest, choose backend/image, hold credentials, enforce egress/Git, persist authoritative audit | bot-bottle |
+| Agent control protocol | Start provider process, create session, send input, stream normalized events, terminal/computer operations | Sandbox Agent or a compatible protocol |
+| Isolation primitive | VM/container/process boundary, filesystem, CPU/memory, networking substrate | Firecracker, Apple Container, Docker, E2B, Daytona, BoxLite, etc. |
+
+The important boundary is between trusted policy/lifecycle and agent control.
+The agent-control daemon runs in the environment being treated as untrusted.
+It can report what the agent says happened, but it cannot authoritatively prove
+that policy was enforced. Egress decisions, credential custody, Git scanning,
+bottle identity, and security audit must remain outside it.
+
+### Proposed composition
+
+```text
+operator UI / CLI / API
+          |
+          v
+bot-bottle orchestrator  (trusted)
+  - resolves manifest
+  - owns bottle identity and lifecycle
+  - stores authoritative audit
+  - authenticates clients
+          |
+          +--------------------------+
+          |                          |
+          v                          v
+isolation backend              shared gateway  (trusted)
+Firecracker / Apple / Docker   - egress policy + DLP
+          |                    - credential injection
+          |                    - Git mediation
+          v
+bottle / guest  (untrusted)
+  - Sandbox Agent server
+  - Claude Code / Codex / Pi subprocess
+  - workspace, skills, MCP configuration
+```
+
+The bot-bottle manifest would compile into both sides:
+
+- **outside the bottle:** backend, network, egress, credentials, Git,
+  supervision, identity, and authoritative lifecycle;
+- **inside the bottle:** selected provider, prompt, skills, MCP configuration,
+  startup arguments, and non-secret session metadata.
+
+Sandbox Agent should never receive real secrets merely because its API offers
+a credential extraction helper. Provider and forge requests should continue
+to use bot-bottle's placeholder/proxy pattern.
+
+## How accurate is the Docker/OCI analogy?
+
+### The useful part
+
+The container ecosystem separates low-level execution from a product that
+ordinary developers operate. OCI defines interoperable image, runtime, and
+distribution specifications. Docker Engine adds a daemon, API, CLI, object
+model, images, networks, volumes, and lifecycle; Docker Desktop and related
+products add installation, updates, UI, integrations, policy, and team
+workflows.
+
+The same separation can exist for coding agents:
+
+| Container ecosystem | Agent-sandbox ecosystem |
+|---|---|
+| OCI/runtime contract | A future open agent session/event contract |
+| `runc` / runtime adapter | Claude/Codex/Pi adapter |
+| containerd shim and task/exec API | Sandbox Agent server and HTTP/SSE session API |
+| containerd / CRI-style lifecycle | Sandbox-provider lifecycle APIs |
+| Docker Engine / Compose | bot-bottle orchestrator + manifests + backends + gateway |
+| Docker Desktop / Hub ecosystem | bot-bottle desktop/mobile UX, policy packs, agent images, skills, trusted integrations |
+
+Sandbox Agent makes coding-agent processes portable in roughly the way a shim
+makes runtimes consumable through a common lifecycle interface. bot-bottle can
+make the entire safe-agent system usable without asking the operator to
+assemble that plumbing.
+
+Official container references:
+
+- [Open Container Initiative](https://opencontainers.org/)
+- [OCI Runtime Specification](https://github.com/opencontainers/runtime-spec)
+- [Docker Engine architecture](https://docs.docker.com/engine/)
+- [Docker alternative runtimes and containerd shims](https://docs.docker.com/engine/daemon/alternative-runtimes/)
+
+### Where the analogy breaks
+
+1. **Sandbox Agent is an implementation, not an independent standard.**
+   Its OpenAPI document is public, but the project currently owns the server,
+   adapters, schema, and evolution. OCI is an independently governed set of
+   specifications with multiple implementations.
+2. **It sits above, not below, the isolation boundary.** Linux namespaces,
+   cgroups, VMs, and OCI runtimes create the boundary. Sandbox Agent controls a
+   process after some other system has created that boundary.
+3. **It reaches into product territory.** Inspector, React components,
+   computer-use APIs, skills/MCP configuration, transcripts, and restoration
+   are not merely low-level primitives. Sandbox Agent can continue growing
+   upward into the same UI and orchestration space bot-bottle might occupy.
+4. **Coding agents are semantically uneven.** Normalizing a container
+   lifecycle is easier than claiming full behavioral parity across Claude
+   Code, Codex, Cursor, Amp, OpenCode, and Pi. A universal schema can become a
+   lowest common denominator or accumulate provider-specific escape hatches.
+5. **The security contract is not standardized.** An agent-session API says
+   little about whether credentials are visible, egress is controlled, Git is
+   mediated, or audit is trustworthy. Those are core bot-bottle concerns.
+
+The positioning should therefore say “Docker-like product layer above an open
+agent-control protocol,” not “Sandbox Agent is OCI” or “bot-bottle implements
+OCI for agents.”
+
+## Can bot-bottle be the turnkey product layer?
+
+Yes, if it owns substantially more than launch syntax.
+
+The turnkey promise is:
+
+> Choose a trusted role, point it at a project, and run any supported coding
+> agent with full permissions. bot-bottle builds the environment, isolates it,
+> supplies only the capabilities it needs, keeps credentials outside, mediates
+> external writes, and gives the operator one place to watch and intervene.
+
+That product has several defensible jobs:
+
+### 1. Packaging and reproducibility
+
+- provider and toolchain images;
+- pinned, verified build inputs;
+- skills and MCP configuration;
+- role/bottle composition;
+- cached startup and portable environment definitions; and
+- compatibility testing across agents and backends.
+
+### 2. Trusted policy compilation
+
+The manifest is valuable because one reviewable document compiles into:
+
+- an isolation plan;
+- gateway routes and DLP policy;
+- credential slots;
+- Git-gate repositories and identities;
+- provider configuration;
+- supervision behavior; and
+- operator-facing preflight.
+
+Sandbox Agent's runtime configuration does not replace this. The policy must
+be resolved before an untrusted guest or agent-control daemon exists.
+
+### 3. Security enforcement
+
+- dedicated-kernel isolation where available;
+- no direct guest route to the internet;
+- credentials injected outside the agent;
+- content inspection on allowed destinations;
+- Git secrets scanning and upstream-key custody;
+- fail-closed policy resolution; and
+- authoritative host-side audit.
+
+This is the strongest current differentiation from a generic
+“Sandbox Agent + Docker/E2B” assembly.
+
+### 4. Lifecycle and operations
+
+- install and host preflight;
+- image build/update;
+- start, stop, resume, cleanup, and migration;
+- concurrent named agents;
+- state recovery after crashes;
+- live supervision and policy remediation; and
+- backend selection without changing the role definition.
+
+### 5. Ecosystem and DX
+
+A product layer can support:
+
+- curated provider images;
+- signed policy/bottle packs;
+- reusable role templates;
+- skills and MCP bundles;
+- backend plugins;
+- an authenticated desktop/web/mobile operator client;
+- browser/preview integration;
+- normalized transcripts and change review; and
+- team policy distribution and compliance exports.
+
+The analogy to Docker is strongest here: users adopt the coherent workflow and
+ecosystem, not because the low-level process API is proprietary.
+
+## Business and product positioning
+
+“Turnkey wrapper” is understandable internally but weak externally. It implies
+that the hard work lives underneath and that another wrapper can replace it.
+Prefer one of:
+
+- **The policy-first runtime for coding agents**
+- **Run any coding agent with full permissions, without giving it your host or
+  credentials**
+- **A turnkey local control plane for isolated coding agents**
+- **Docker-like packaging and operations for coding agents, with the security
+  boundary outside the agent**
+
+The open/product split could resemble the container ecosystem:
+
+### Open foundation
+
+- manifest schema and composition;
+- local CLI and core orchestrator;
+- provider adapters;
+- Firecracker/Apple Container/Docker backends;
+- gateway policy format and enforcement;
+- Sandbox Agent compatibility;
+- local audit and supervision; and
+- conformance tests for providers/backends/policy.
+
+### Productizable ecosystem/DX
+
+- polished desktop and mobile clients;
+- fleet/remote-host management;
+- signed and curated role/image/policy registry;
+- team policy distribution and administrative controls;
+- durable searchable transcripts and audit exports;
+- SSO, RBAC, retention, and tamper-evident audit;
+- managed update/compatibility channels;
+- remote browser/preview relay;
+- enterprise support; and
+- optional managed build/cache infrastructure.
+
+OCI itself is not the thing Docker sells. Interoperability expands the market;
+the product captures value through reliable packaging, workflow, distribution,
+management, and trust. bot-bottle should follow that logic rather than trying
+to make its session protocol the moat.
+
+## Strategic threat from Sandbox Agent
+
+Sandbox Agent is a real threat for three reasons:
+
+1. **It can become the integration default.** A frontend or agent platform can
+   integrate one API and choose among many agents and sandbox vendors.
+2. **It can own session data and UI.** The universal event schema, Inspector,
+   React components, restoration, terminal, and computer-use APIs give it a
+   natural path toward the operator surface.
+3. **Sandbox providers can move upward.** If E2B, Daytona, BoxLite, or another
+   runtime combines Sandbox Agent with adequate network policy and credential
+   custody, it can offer much of the turnkey stack.
+
+The threat is not that its manifest syntax is better. It currently has no
+equivalent trusted policy composition. The threat is that **the ecosystem may
+standardize around its API before bot-bottle has a stable external control
+surface**. In that world bot-bottle is evaluated as one sandbox provider,
+while the SDK and its consumers own the user relationship.
+
+## Why bot-bottle can still win its layer
+
+Sandbox Agent's scope exclusions align with bot-bottle's deepest work:
+
+- it does not choose or operate the sandbox provider;
+- it does not mediate Git;
+- it does not own network policy;
+- it does not securely deliver credentials;
+- it does not durably store sessions; and
+- it cannot make guest-generated telemetry authoritative.
+
+Those are not incidental features. Together they define the trusted system
+around an untrusted coding agent. bot-bottle also has a narrower and coherent
+initial customer: a developer or small operator who wants existing agent CLIs
+to run locally with broad permissions and bounded consequences.
+
+The durable advantage is therefore:
+
+> Sandbox Agent makes agents controllable. bot-bottle makes them safe and
+> operable.
+
+That sentence remains true only if bot-bottle closes its operator-DX gaps.
+Security without a browser/preview loop, stable API, normalized session view,
+and good parallel-task UX risks becoming an invisible backend feature.
+
+## Integration options
+
+### Option A — Embed Sandbox Agent inside each bottle
+
+bot-bottle launches Sandbox Agent as the provider process supervisor and
+connects it to the host orchestrator through a bottle-scoped authenticated
+channel.
+
+**Benefits**
+
+- immediate provider-neutral session API;
+- more supported agents;
+- normalized streaming and transcripts;
+- terminal, filesystem, process, and computer-use primitives;
+- Inspector/React ecosystem; and
+- less provider-specific reverse engineering in bot-bottle.
+
+**Risks**
+
+- `0.x` API/schema churn;
+- extra binary and release-supply-chain dependency;
+- lowest-common-denominator normalization;
+- conflict with provider-native resume state;
+- an in-guest daemon is attacker-controlled after guest compromise;
+- duplicate orchestration responsibilities; and
+- upstream can move into policy/lifecycle and compete more directly.
+
+**Security rule**
+
+Treat every event and state claim from Sandbox Agent as untrusted telemetry.
+Never delegate egress authorization, credential release, bottle identity,
+authoritative audit, or Git policy to it.
+
+### Option B — Implement a Sandbox Agent-compatible endpoint
+
+bot-bottle maps the external protocol onto its existing provider adapters and
+process model without running the upstream server.
+
+**Benefits**
+
+- ecosystem compatibility with tighter component control;
+- no in-guest daemon dependency; and
+- room to preserve bot-bottle-native lifecycle semantics.
+
+**Risks**
+
+- large and continuing compatibility burden;
+- “full feature coverage” is expensive across all providers;
+- accidental protocol fork; and
+- effort diverted from policy and UX differentiation.
+
+### Option C — Define an independent bot-bottle session API
+
+Build only the control surface bot-bottle needs.
+
+**Benefits**
+
+- clean fit with the trust model and persistent named bottles;
+- no upstream dependency; and
+- deliberate support for supervision and security events.
+
+**Risks**
+
+- recreates a fast-growing open-source project;
+- no existing client ecosystem;
+- slower browser/desktop/mobile work; and
+- increases the chance that Sandbox Agent becomes the de facto standard first.
+
+### Recommendation
+
+Start with **Option A as a bounded compatibility spike**, not a product
+commitment. Do not begin with a clean-room competing protocol.
+
+The spike should answer:
+
+1. Can Claude Code, Codex, and Pi retain exact native resume behavior?
+2. Can Sandbox Agent run without receiving real provider credentials?
+3. Can its server be reached through a bottle-scoped authenticated channel
+   without exposing the orchestrator or broadening guest egress?
+4. Which permission events overlap or conflict with bot-bottle supervision?
+5. Can normalized events be stored while clearly separating untrusted
+   transcript telemetry from authoritative gateway/Git audit?
+6. Can manifest skills, MCP servers, prompt, and startup arguments compile
+   deterministically into its configuration?
+7. Does its versioning policy permit a compatibility contract bot-bottle can
+   support?
+8. What image-size, startup-time, and update burden does the binary add?
+
+If the answers are favorable, adopt it behind a bot-bottle-owned interface and
+pin/test the supported version. If not, implement the smallest compatible
+subset needed by external clients before inventing a wholly separate API.
+
+## Product roadmap implications
+
+The competitor scan and this architecture comparison reorder the likely work:
+
+1. **Provider-neutral control/session compatibility spike**
+2. **Stable authenticated external bot-bottle API**
+3. **Normalized transcript/event persistence**
+4. **Parallel-session operator UI**
+5. **Browser/preview/computer-use capability**
+6. **Policy/image/skill distribution and signing**
+7. **Remote host/fleet management**
+
+This does not mean pausing security work. It means exposing the shipped
+security work through a product surface that can compete with the SDK-plus-
+sandbox ecosystem.
+
+## Decision
+
+Treat Sandbox Agent SDK as a potentially standard **agent process-control
+layer**, not as a sandbox replacement and not as a minor complementary
+library. Position bot-bottle one layer above it:
+
+- manifests express trusted role and environment policy;
+- bot-bottle compiles and enforces that policy across host, gateway, Git, and
+  isolation backends;
+- Sandbox Agent or a compatible protocol controls the selected agent process;
+  and
+- bot-bottle owns the turnkey operator experience.
+
+The Docker analogy is strategically sound when stated as:
+
+> Sandbox Agent can be the portable task/exec protocol; bot-bottle can be the
+> opinionated engine, Compose-like policy layer, and Desktop-like operator
+> product.
+
+It is not sound when stated as:
+
+> Sandbox Agent is OCI and bot-bottle is Docker.
+
+There is no independent OCI-equivalent agent specification yet, and Sandbox
+Agent already reaches into UI/session territory. Compatibility should be
+pursued quickly, while the trusted manifest/enforcement plane and operator
+experience remain the parts bot-bottle deliberately owns.

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

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_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_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_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

tests/unit/test_orchestrator_secret_store.py

@@ -2,9 +2,6 @@
 
 from __future__ import annotations
 
-import base64
-import hashlib
-import hmac
 import unittest
 
 from bot_bottle.orchestrator.store.secret_store import (
@@ -71,28 +68,15 @@ class TestDecryptErrors(unittest.TestCase):
     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_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"):
-            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))
+        # Wrong key produces garbage bytes; decrypt_value raises ValueError
+        # when the result is non-UTF-8 (which is very likely for 12-char data).
+        # We allow it to succeed only if garbage happens to be valid UTF-8, but
+        # the plaintext must not match.
+        try:
+            result = decrypt_value(other_key, ct)
+            self.assertNotEqual("secret-token", result)
+        except ValueError:
+            pass
 
     def test_truncated_blob_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):

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,
 )
 
@@ -703,14 +701,9 @@ 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]
@@ -720,14 +713,9 @@ class TestResolvedRoutesPayload(unittest.TestCase):
     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 = resolved_routes_payload(
-            typing.cast(
-                supervise_server.PolicyResolver,
-                _FakeSuperviseResolver(raises=True),
-            ),
-            _SRC,
-            _TOK,
-        )
+        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"])
@@ -736,13 +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

@@ -78,7 +78,8 @@ 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()

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: