docs(orchestrator): tighten auth-provisioning wording to concrete services

Address review on #482: drop the generic "credential boundary" framing in the
PRD and docstrings and talk about the specific services — the orchestrator holds
the control-plane key; the host controller (#468) gets a separate key the
orchestrator never holds, so the orchestrator can't mint the credentials it uses
to talk to the host controller that owns its lifecycle. Lead with that concrete
win. No code behaviour change.

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

README.md

@@ -5,7 +5,7 @@
 # bot-bottle
 
 [![test](https://gitea.dideric.is/didericis/bot-bottle/actions/workflows/test.yml/badge.svg?branch=main)](https://gitea.dideric.is/didericis/bot-bottle/actions?workflow=test.yml)
-[![coverage](https://img.shields.io/badge/coverage-84%25-brightgreen)](https://coverage.readthedocs.io/)
+[![coverage](https://img.shields.io/badge/coverage-83%25-brightgreen)](https://coverage.readthedocs.io/)
 [![core coverage](https://img.shields.io/badge/core%20coverage-94%25-brightgreen)](https://gitea.dideric.is/didericis/bot-bottle/src/branch/main/docs/decisions/0004-coverage-policy.md)
 
 **Problem:** Developer wants to run a coding agent without supervision, but they don't want a prompt injected or misbehaving agent wrecking their environment or exfiltrating sensitive data.

bot_bottle/backend/docker/orchestrator.py

@@ -19,7 +19,6 @@ from .util import run_docker
 from ...paths import (
     ORCHESTRATOR_TOKEN_ENV,
     bot_bottle_root,
-    host_orchestrator_token,
 )
 from ...gateway import GatewayError
 from ...orchestrator.lifecycle import (
@@ -171,7 +170,9 @@ class DockerOrchestrator(Orchestrator):
         fixed-name container first)."""
         self._ensure_control_network()
         run_docker(["docker", "rm", "--force", self.name])
-        _signing_key = host_orchestrator_token()
+        # The signing key comes through the shared provisioning contract (#476),
+        # which fail-closes rather than yield an empty key that would run OPEN.
+        _signing_key = self.control_plane_key()
         proc = run_docker([
             "docker", "run", "--detach",
             "--name", self.name,

bot_bottle/backend/firecracker/orchestrator.py

@@ -21,7 +21,6 @@ import time
 from pathlib import Path
 
 from ...log import die, info
-from ...paths import host_orchestrator_token
 from ...orchestrator.lifecycle import (
     DEFAULT_STARTUP_TIMEOUT_SECONDS,
     Orchestrator,
@@ -108,11 +107,13 @@ class FirecrackerOrchestrator(Orchestrator):
             data_drive=self._ensure_registry_volume(),
         )
         # Push the host-canonical signing key (the init waits for it before
-        # starting the control plane). The host token file stays the single
-        # source of truth, so a co-running docker/macOS control plane keeps
-        # working; the guest verifies tokens with the same key the CLI signs from.
+        # starting the control plane). It comes through the shared provisioning
+        # contract (#476) — the same host token file every backend uses, so a
+        # co-running docker/macOS control plane keeps working and the guest
+        # verifies tokens with the same key the CLI signs from; fail-closed, so
+        # the guest is never handed an empty key that would run it OPEN.
         infra_vm.push_secret(
-            vm, host_orchestrator_token(), infra_vm._GUEST_SIGNING_KEY_PATH,
+            vm, self.control_plane_key(), infra_vm._GUEST_SIGNING_KEY_PATH,
             "the control-plane signing key to the orchestrator VM "
             "(its control plane will not start)",
         )

bot_bottle/backend/macos_container/orchestrator.py

@@ -18,10 +18,7 @@ import urllib.request
 from pathlib import Path
 
 from ... import log
-from ...paths import (
-    ORCHESTRATOR_TOKEN_ENV,
-    host_orchestrator_token,
-)
+from ...paths import ORCHESTRATOR_TOKEN_ENV
 from ...orchestrator.lifecycle import (
     DEFAULT_HEALTH_TIMEOUT_SECONDS,
     DEFAULT_PORT,
@@ -134,7 +131,9 @@ class MacosOrchestrator(Orchestrator):
 
     def _run_container(self, current_hash: str) -> None:
         container_mod.force_remove_container(self.name)
-        _signing_key = host_orchestrator_token()
+        # The signing key comes through the shared provisioning contract (#476),
+        # which fail-closes rather than yield an empty key that would run OPEN.
+        _signing_key = self.control_plane_key()
         argv = [
             "container", "run", "--detach",
             "--name", self.name,

bot_bottle/orchestrator/client.py

@@ -18,8 +18,8 @@ import urllib.request
 from collections.abc import Iterable
 from dataclasses import dataclass
 
-from ..orchestrator_auth import ROLE_CLI, mint
-from ..paths import host_orchestrator_token
+from ..orchestrator_auth import ROLE_CLI
+from ..trust_domain import CONTROL_PLANE
 from .server import ORCHESTRATOR_AUTH_HEADER
 
 DEFAULT_TIMEOUT_SECONDS = 5.0
@@ -32,7 +32,7 @@ def _host_auth_token() -> str:
     "" means 'send no auth header' — correct against an open (unconfigured)
     control plane, and harmlessly rejected by a secured one."""
     try:
-        return mint(ROLE_CLI, host_orchestrator_token())
+        return CONTROL_PLANE.mint(ROLE_CLI)
     except (OSError, ValueError):
         return ""
 

bot_bottle/orchestrator/lifecycle.py

@@ -21,8 +21,7 @@ import urllib.error
 import urllib.request
 from pathlib import Path
 
-from ..orchestrator_auth import ROLE_GATEWAY, mint
-from ..paths import host_orchestrator_token
+from ..trust_domain import ControlPlaneProvisioning
 
 DEFAULT_PORT = 8099
 DEFAULT_STARTUP_TIMEOUT_SECONDS = 45.0
@@ -58,6 +57,13 @@ class Orchestrator(abc.ABC):
     so it — not the gateway — mints the gateway's role-scoped token.
     Backend-neutral."""
 
+    # The shared control-plane auth provisioning contract (#476). Every backend
+    # gets its signing key + gateway token through this one seam rather than
+    # re-deriving the wiring; the default topology is co-located + fail-closed,
+    # so a backend need not redeclare it (a truly isolated control plane would
+    # override this with a different `Topology`).
+    provisioning: ControlPlaneProvisioning = ControlPlaneProvisioning()
+
     def ensure_built(self) -> None:
         """Ensure the orchestrator's image / rootfs exists, building it if
         needed. Default: nothing to build (e.g. a pre-pulled image). Call before
@@ -105,9 +111,17 @@ class Orchestrator(abc.ABC):
     def mint_gateway_token(self) -> str:
         """Mint a role-scoped `gateway` JWT from the host signing key for the
         gateway to present. The orchestrator holds the key; the gateway never
-        does (#469). Backend-neutral — the same host token file is the single
-        source of truth across backends."""
-        return mint(ROLE_GATEWAY, host_orchestrator_token())
+        does (#469). Routed through the shared provisioning contract (#476), so
+        the same host token file is the single source of truth across backends."""
+        return self.provisioning.gateway_token()
+
+    def control_plane_key(self) -> str:
+        """The raw signing key the control-plane *process* must receive — the ONE
+        place a backend obtains it (docker/macOS inject it as `key_env`;
+        firecracker pushes it to the guest). Fail-closed via the provisioning
+        contract: it raises rather than yield an empty key that would run the
+        server OPEN (#476)."""
+        return self.provisioning.orchestrator_key()
 
 
 __all__ = [
@@ -117,4 +131,5 @@ __all__ = [
     "OrchestratorStartError",
     "source_hash",
     "Orchestrator",
+    "ControlPlaneProvisioning",
 ]

bot_bottle/orchestrator/server.py

@@ -63,8 +63,8 @@ import sys
 import typing
 from urllib.parse import urlsplit
 
-from ..orchestrator_auth import ROLE_CLI, ROLES, verify
-from ..paths import ORCHESTRATOR_TOKEN_ENV
+from ..orchestrator_auth import ROLE_CLI, ROLES
+from ..trust_domain import CONTROL_PLANE
 from ..supervisor.types import TOOLS
 from .service import OrchestratorCore
 
@@ -413,11 +413,13 @@ class OrchestratorServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
 
     def __init__(self, address: tuple[str, int], orchestrator: OrchestratorCore) -> None:
         self.orchestrator = orchestrator
-        self._signing_key = os.environ.get(ORCHESTRATOR_TOKEN_ENV, "").strip()
+        # 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"(${ORCHESTRATOR_TOKEN_ENV}); running WITHOUT caller "
+                f"(${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"
@@ -433,7 +435,7 @@ class OrchestratorServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
         role (→ per-route 401/403 in `dispatch`)."""
         if not self._signing_key:
             return ROLE_CLI
-        return verify(presented, self._signing_key)
+        return CONTROL_PLANE.verify(presented, self._signing_key)
 
 
 def make_server(

bot_bottle/orchestrator_auth.py

@@ -59,12 +59,17 @@ _HEADER_SEGMENT = _b64url_encode(
 )
 
 
-def mint(role: str, secret: str) -> str:
+def mint(role: str, secret: str, *, roles: frozenset[str] = ROLES) -> str:
     """A compact HS256 token asserting `role`, signed with `secret`.
 
-    Raises ValueError for an unknown role (mint only what the control plane will
-    accept) or an empty signing key (an unsigned credential is never valid)."""
-    if role not in ROLES:
+    `roles` is the set the signing key is allowed to sign (default: the
+    orchestrator's `{gateway, cli}`). A separate service (e.g. the host
+    controller) passes its own key + role set so its tokens can't be forged with
+    the orchestrator's key — see `trust_domain.py`, issues #476/#468.
+
+    Raises ValueError for a role outside `roles`, or an empty signing key (an
+    unsigned credential is never valid)."""
+    if role not in roles:
         raise ValueError(f"unknown control-plane role {role!r}")
     if not secret:
         raise ValueError("cannot mint a control-plane token without a signing key")
@@ -73,10 +78,11 @@ def mint(role: str, secret: str) -> str:
     return f"{signing_input}.{_sign(secret, signing_input)}"
 
 
-def verify(token: str, secret: str) -> str | None:
+def verify(token: str, secret: str, *, roles: frozenset[str] = ROLES) -> str | None:
     """The role a valid `token` carries, or None if it is malformed, wrongly
-    signed, or names an unknown role. Constant-time signature check; rejects any
-    header whose alg isn't HS256 (no alg-confusion / `none`)."""
+    signed, or names a role outside `roles` (the verifying trust domain's set —
+    default `{gateway, cli}`). Constant-time signature check; rejects any header
+    whose alg isn't HS256 (no alg-confusion / `none`)."""
     if not token or not secret:
         return None
     parts = token.split(".")
@@ -94,7 +100,7 @@ def verify(token: str, secret: str) -> str | None:
     if not isinstance(header, dict) or header.get("alg") != _ALG:
         return None
     role = payload.get("role") if isinstance(payload, dict) else None
-    return role if isinstance(role, str) and role in ROLES else None
+    return role if isinstance(role, str) and role in roles else None
 
 
 __all__ = ["ROLE_GATEWAY", "ROLE_CLI", "ROLES", "mint", "verify"]

bot_bottle/paths.py

@@ -97,16 +97,17 @@ def host_gateway_ca_dir() -> Path:
     return ca_dir
 
 
-def host_orchestrator_token() -> str:
-    """The per-host control-plane secret, minted (256-bit, url-safe) and
-    persisted 0600 on first use, then reused.
+def host_signing_key(filename: str) -> str:
+    """A per-host signing key at `<root>/<filename>`, minted (256-bit, url-safe)
+    and persisted 0600 on first use, then reused.
 
-    This is the shared secret the launchers inject into the control-plane and
-    gateway containers and that the host CLI presents on every call. It is a
-    *host* artifact — the file lives under the root the agent never mounts, and
-    the env var is set only on the trusted containers — so reading it here is
-    safe on the host launch path but the value never reaches a bottle."""
-    path = bot_bottle_root() / ORCHESTRATOR_TOKEN_FILENAME
+    The generic form of `host_orchestrator_token()`: each service names its own
+    key file (`trust_domain.py`), so the orchestrator and a separate service like
+    the host controller (#468) get distinct keys neither can read. It is a *host*
+    artifact — the file lives under the root the agent never mounts, and its value
+    is injected only into the trusted control-plane process — so reading it here
+    is safe on the launch path but the value never reaches a bottle."""
+    path = bot_bottle_root() / filename
     try:
         existing = path.read_text().strip()
         if existing:
@@ -128,6 +129,14 @@ def host_orchestrator_token() -> str:
     return token
 
 
+def host_orchestrator_token() -> str:
+    """The per-host control-plane signing key — the host-canonical key the
+    launchers inject into the control-plane process and the host CLI mints its
+    own `cli` token from. The `control-plane` trust domain's specialization of
+    `host_signing_key()`."""
+    return host_signing_key(ORCHESTRATOR_TOKEN_FILENAME)
+
+
 __all__ = [
     "HOST_DB_FILENAME",
     "ORCHESTRATOR_TOKEN_FILENAME",
@@ -138,5 +147,6 @@ __all__ = [
     "host_db_path",
     "host_db_dir",
     "host_gateway_ca_dir",
+    "host_signing_key",
     "host_orchestrator_token",
 ]

bot_bottle/trust_domain.py

@@ -0,0 +1,167 @@
+"""Per-service control-plane signing keys (issue #476).
+
+A `TrustDomain` is one service's signing material: its host-canonical key file,
+the roles that key may sign, and the env vars its key and a pre-minted token ride
+in. Scoping `mint`/`verify` to a domain's roles keeps one service's key from
+signing (or accepting) another service's tokens.
+
+Today there is one domain, `CONTROL_PLANE` — the orchestrator's key (roles
+`{gateway, cli}`): the orchestrator holds it and mints the gateway's and CLI's
+tokens. The host controller (#468) will add a **second** domain with its own key
+the orchestrator never holds. That is the point: the host controller starts and
+stops the orchestrator, so the orchestrator must not be able to mint the
+credentials it uses to talk to it. Adding a `host` role to `CONTROL_PLANE`
+instead would defeat that — the orchestrator holds that key, so it could forge
+`host` tokens.
+
+`ControlPlaneProvisioning` is the one seam every backend launcher uses to get the
+orchestrator its key and the gateway its token, instead of re-deriving that
+wiring per backend (the bug class behind PR #471 — see
+`docs/prds/prd-new-control-plane-auth-provisioning.md`).
+
+Stdlib-only: the HMAC lives in `orchestrator_auth`, the key file in `paths`.
+"""
+
+from __future__ import annotations
+
+import os
+from collections.abc import Mapping
+from dataclasses import dataclass, field
+
+from . import orchestrator_auth
+from .orchestrator_auth import ROLE_GATEWAY
+from .paths import (
+    ORCHESTRATOR_AUTH_JWT_ENV,
+    ORCHESTRATOR_TOKEN_ENV,
+    ORCHESTRATOR_TOKEN_FILENAME,
+    host_signing_key,
+)
+
+
+class ProvisioningError(RuntimeError):
+    """A control-plane auth invariant would be violated (e.g. starting a
+    co-located control plane without its signing key — which would run OPEN)."""
+
+
+@dataclass(frozen=True)
+class TrustDomain:
+    """One service's signing material: a host-canonical key file, the roles that
+    key may sign, and the env vars its key and a minted token ride in.
+
+    The service that *owns* the domain (e.g. the orchestrator) receives the raw
+    key via `key_env`; a delegate (e.g. the gateway) receives only a pre-minted,
+    role-scoped token via `token_env` it cannot rewrite. `mint`/`verify` are
+    scoped to `roles`, so this service's key can neither sign nor accept another
+    service's role."""
+
+    name: str
+    key_filename: str
+    roles: frozenset[str]
+    key_env: str
+    token_env: str
+
+    def signing_key(self) -> str:
+        """This service's host-canonical signing key (minted 0600 on first use).
+        Host-side only — the value is injected into the owning process."""
+        return host_signing_key(self.key_filename)
+
+    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; 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()
+
+    def mint(self, role: str) -> str:
+        """A role-scoped token for a delegate, signed with this service's key.
+        Raises ValueError for a role this service doesn't sign."""
+        if role not in self.roles:
+            raise ValueError(f"role {role!r} is not in trust domain {self.name!r}")
+        return orchestrator_auth.mint(role, self.signing_key(), roles=self.roles)
+
+    def verify(self, token: str, key: str) -> str | None:
+        """The role `token` carries under `key`, or None. `key` is passed in
+        (not read from disk) because the verifier — the control-plane process —
+        holds it in `key_env`, not on disk in its guest."""
+        return orchestrator_auth.verify(token, key, roles=self.roles)
+
+
+# The orchestrator's domain: the key the orchestrator (and host CLI) holds, the
+# `gateway` token it mints for the data plane, and the `cli` token the CLI mints
+# for itself. #468's host controller will add a second, separate domain.
+CONTROL_PLANE = TrustDomain(
+    name="control-plane",
+    key_filename=ORCHESTRATOR_TOKEN_FILENAME,
+    roles=orchestrator_auth.ROLES,
+    key_env=ORCHESTRATOR_TOKEN_ENV,
+    token_env=ORCHESTRATOR_AUTH_JWT_ENV,
+)
+
+
+@dataclass(frozen=True)
+class Topology:
+    """Where a backend runs the two planes, so the provisioning seam can decide
+    whether an open control plane is dangerous — the backend declares this
+    instead of hardcoding the decision in its launcher.
+
+    `data_plane_shares_control_host` — the gateway runs on the same host/VM as
+    the orchestrator, so an open orchestrator would hand the co-located gateway
+    full `cli`. The default, and what makes the signing key mandatory. Every
+    current backend is co-located (docker/macOS: two containers on one host;
+    firecracker: two VMs on one host, agents L3-isolated); an isolated control
+    plane on a separate trusted host may declare False.
+
+    `combined_guest` — both planes in one guest (the retired combined infra VM).
+    Informational; kept so a future combined backend declares it."""
+
+    data_plane_shares_control_host: bool = True
+    combined_guest: bool = False
+
+
+# The default posture: data plane co-located with the control plane. Fail-closed
+# — the signing key is mandatory. A backend opts out only by declaring otherwise.
+COLOCATED = Topology(data_plane_shares_control_host=True)
+
+
+@dataclass(frozen=True)
+class ControlPlaneProvisioning:
+    """The one seam every backend launcher uses to provision control-plane auth,
+    instead of re-deriving the four invariants that each cost a PR #471 review
+    round: the orchestrator gets the raw key (`orchestrator_key`), the gateway
+    gets a minted `gateway` token (`gateway_token`), the host CLI mints its own
+    `cli` token from the same host-canonical key, and the orchestrator never
+    starts open where its gateway is co-located."""
+
+    domain: TrustDomain = CONTROL_PLANE
+    topology: Topology = field(default=COLOCATED)
+
+    def orchestrator_key(self) -> str:
+        """The raw signing key the orchestrator process must receive (carry it in
+        `domain.key_env`). Fail-closed: raises rather than return "" for a
+        co-located topology, since an empty key runs the server open and hands
+        the co-located gateway full `cli`."""
+        key = self.domain.signing_key()
+        if not key and self.topology.data_plane_shares_control_host:
+            raise ProvisioningError(
+                f"refusing to start the {self.domain.name} orchestrator without "
+                "a signing key: its gateway shares this host/VM, so an open "
+                "orchestrator would grant that gateway full `cli` (#476)"
+            )
+        return key
+
+    def gateway_token(self) -> str:
+        """The `gateway`-role token the gateway receives (carry it in
+        `domain.token_env`) — minted from the key, never the key itself, so a
+        compromised gateway cannot forge a `cli` token."""
+        return self.domain.mint(ROLE_GATEWAY)
+
+
+__all__ = [
+    "ProvisioningError",
+    "TrustDomain",
+    "CONTROL_PLANE",
+    "Topology",
+    "COLOCATED",
+    "ControlPlaneProvisioning",
+]

docs/prds/prd-new-control-plane-auth-provisioning.md

@@ -0,0 +1,88 @@
+# PRD prd-new: Per-service signing keys for control-plane auth
+
+- **Status:** Draft
+- **Author:** claude
+- **Created:** 2026-07-26
+- **Issue:** #476
+
+## Summary
+
+Provision control-plane signing keys **per service**, through one shared seam, so
+no service can mint another's credentials. Concretely: the orchestrator holds the
+control-plane key and mints the gateway's and CLI's tokens; the host controller
+(#468, next) gets a **separate** key the orchestrator never holds — so the
+orchestrator cannot forge the credentials it uses to talk to the host controller
+that starts and stops it. Landing this seam also retires the per-backend
+provisioning duplication that made PR #471 take three review rounds.
+
+## Problem
+
+**1. The orchestrator could forge host-controller credentials.** The
+orchestrator's key signs roles `{gateway, cli}`. The tempting way to add the host
+controller (#468) is a third role, `host`, on that same key. But then the
+orchestrator — which holds the key — can mint `host` tokens, and the host
+controller, which owns the orchestrator's lifecycle, must not trust anything the
+orchestrator can mint. The two services need separate keys.
+
+**2. Every backend provisioned auth by hand.** Each launcher (docker
+gateway/infra, macOS infra, firecracker infra) re-derived how to generate the
+signing key, scope it to the orchestrator, mint the gateway JWT, and keep the
+host key file canonical. All three PR #471 High-severity findings were this one
+integration bug in different launchers: the data plane got the full `cli` token;
+the firecracker control plane ran open; the firecracker guest clobbered the host
+key.
+
+## Goals / Success Criteria
+
+- The orchestrator and the host controller sign with **different** keys; neither
+  can mint the other's tokens. (This PR provisions the orchestrator's key and
+  leaves a drop-in seam for the host controller's.)
+- One shared provisioning seam every backend uses — a new backend or daemon
+  implements it instead of rediscovering these four invariants:
+  1. the signing key is host-canonical: a guest is handed it, never generates or
+     overwrites it;
+  2. only the orchestrator process gets the raw key; the gateway gets a
+     pre-minted `gateway` token it can't rewrite into `cli`;
+  3. the host CLI's `cli` token is minted from the same key, so it stays valid
+     across co-running backends;
+  4. the control plane never runs open where its data plane shares the host/VM.
+
+## Non-goals
+
+- The host controller itself (#468) — this only provisions the orchestrator's
+  key and the seam #468 plugs into.
+- 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, the plane split (#469), or the server's open-mode fallback
+  for tests.
+
+## Design
+
+A **`TrustDomain`** is one service's signing material: its host-canonical key
+file, the roles that key may sign, and the env vars its key and a pre-minted
+token ride in. `mint`/`verify` are scoped to that domain's roles, so a token
+signed by one service's key neither carries nor verifies another service's role.
+
+- `CONTROL_PLANE` — the orchestrator's domain: key `orchestrator-token`, roles
+  `{gateway, cli}`. The orchestrator process holds the key; the gateway holds
+  only a minted `gateway` token; the host CLI mints its own `cli` token.
+- The host controller (#468) will add a second `TrustDomain` — its own key file
+  and role(s) — that the orchestrator never holds.
+
+**`ControlPlaneProvisioning`** is the seam the backends call.
+`orchestrator_key()` returns the raw key for the control-plane process
+(fail-closed: it raises rather than hand back an empty key that would run the
+server open where the data plane is co-located). `gateway_token()` mints the
+gateway's token. Each backend applies these through its own transport —
+docker/macOS inject env vars, firecracker pushes over SSH — but none re-derives
+*which* key or role.
+
+`paths.host_signing_key(filename)` generalizes `host_orchestrator_token()` so each
+domain names its own key file.
+
+## Open questions
+
+None blocking. #468 adds its `TrustDomain` and a second
+`ControlPlaneProvisioning`-shaped consumer; renaming that class to something
+service-neutral is a cosmetic call to make then.

tests/unit/test_docker_orchestrator.py

@@ -19,7 +19,9 @@ _ORCH = "bot_bottle.backend.docker.orchestrator"
 _RUN = f"{_ORCH}.run_docker"
 _SLEEP = f"{_ORCH}.time.sleep"
 _MONOTONIC = f"{_ORCH}.time.monotonic"
-_TOKEN = f"{_ORCH}.host_orchestrator_token"
+# The signing key is read through the shared provisioning contract (#476); patch
+# its host-canonical key file read to keep it off the real host file.
+_TOKEN = "bot_bottle.trust_domain.host_signing_key"
 # The ABC's is_healthy probes /health via urllib in the lifecycle module.
 _URLOPEN = "bot_bottle.orchestrator.lifecycle.urllib.request.urlopen"
 

tests/unit/test_firecracker_orchestrator.py

@@ -44,7 +44,7 @@ class TestEnsureRunning(unittest.TestCase):
         vm = infra_vm.InfraVm(guest_ip="10.243.255.1", private_key=Path("/k"), vm=MagicMock())
         with patch.object(infra_vm, "boot_vm", return_value=vm) as boot, \
                 patch.object(infra_vm, "push_secret") as push, \
-                patch(f"{_ORCH}.host_orchestrator_token", return_value="host-key"), \
+                patch("bot_bottle.trust_domain.host_signing_key", return_value="host-key"), \
                 patch.object(orch, "is_running", return_value=False), \
                 patch.object(orch, "_ensure_registry_volume", return_value=Path("/reg")), \
                 patch.object(orch, "_wait_for_health"):

tests/unit/test_macos_orchestrator.py

@@ -33,7 +33,7 @@ class TestMacosOrchestratorRun(unittest.TestCase):
     def _run(self) -> list[str]:
         run = Mock(return_value=_ok())
         with patch(f"{_ORCH}.container_mod") as mod, \
-                patch(f"{_ORCH}.host_orchestrator_token", return_value="k"):
+                patch("bot_bottle.trust_domain.host_signing_key", return_value="k"):
             mod.dns_server.return_value = "1.1.1.1"
             mod.bind_mount_spec.side_effect = _spec
             mod.run_container_argv = run
@@ -65,7 +65,7 @@ class TestMacosOrchestratorRun(unittest.TestCase):
 
     def test_start_failure_raises(self) -> None:
         with patch(f"{_ORCH}.container_mod") as mod, \
-                patch(f"{_ORCH}.host_orchestrator_token", return_value="k"):
+                patch("bot_bottle.trust_domain.host_signing_key", return_value="k"):
             mod.dns_server.return_value = "1.1.1.1"
             mod.run_container_argv = Mock(return_value=_fail())
             with self.assertRaises(OrchestratorStartError):

tests/unit/test_orchestrator_auth.py

@@ -82,5 +82,26 @@ class TestMintVerify(unittest.TestCase):
             mint(ROLE_GATEWAY, "")
 
 
+class TestCustomRoleSet(unittest.TestCase):
+    """The `roles=` seam a trust domain other than the control plane uses (#476):
+    mint/verify are scoped to the passed role set, not the module default."""
+
+    _ROLES = frozenset({"host"})
+
+    def test_round_trips_a_role_in_the_custom_set(self) -> None:
+        tok = mint("host", _KEY, roles=self._ROLES)
+        self.assertEqual("host", verify(tok, _KEY, roles=self._ROLES))
+
+    def test_mint_rejects_a_role_outside_the_custom_set(self) -> None:
+        with self.assertRaises(ValueError):
+            mint(ROLE_CLI, _KEY, roles=self._ROLES)
+
+    def test_verify_rejects_a_role_outside_the_verifiers_set(self) -> None:
+        # A validly signed token whose role isn't in the verifier's set fails —
+        # this is what keeps one domain's key from asserting another's role.
+        tok = mint(ROLE_CLI, _KEY)  # a control-plane `cli` token
+        self.assertIsNone(verify(tok, _KEY, roles=self._ROLES))
+
+
 if __name__ == "__main__":
     unittest.main()

tests/unit/test_orchestrator_client.py

@@ -20,13 +20,15 @@ _URLOPEN = "bot_bottle.orchestrator.client.urllib.request.urlopen"
 
 class TestHostAuthToken(unittest.TestCase):
     def test_mints_a_cli_token_from_the_host_key(self) -> None:
-        with patch("bot_bottle.orchestrator.client.host_orchestrator_token",
+        # The CLI mints its `cli` token from the control-plane trust domain's
+        # host-canonical key (#476) — patch the key file read underneath it.
+        with patch("bot_bottle.trust_domain.host_signing_key",
                    return_value="signing-key"):
             tok = _host_auth_token()
         self.assertEqual(ROLE_CLI, verify(tok, "signing-key"))
 
     def test_returns_empty_when_key_unreadable(self) -> None:
-        with patch("bot_bottle.orchestrator.client.host_orchestrator_token",
+        with patch("bot_bottle.trust_domain.host_signing_key",
                    side_effect=OSError("no host root")):
             self.assertEqual("", _host_auth_token())
 

tests/unit/test_trust_domain.py

@@ -0,0 +1,113 @@
+"""Unit: trust domains + the shared control-plane provisioning contract (#476)."""
+
+from __future__ import annotations
+
+import unittest
+from unittest.mock import patch
+
+from bot_bottle import orchestrator_auth
+from bot_bottle.orchestrator_auth import ROLE_CLI, ROLE_GATEWAY
+from bot_bottle.trust_domain import (
+    CONTROL_PLANE,
+    ControlPlaneProvisioning,
+    ProvisioningError,
+    Topology,
+    TrustDomain,
+)
+
+# A second, unrelated domain — the shape #468's host controller would take: its
+# own key file, its own role, its own env vars. Distinct from CONTROL_PLANE.
+_HOST_CTRL = TrustDomain(
+    name="host-controller",
+    key_filename="host-controller-token",
+    roles=frozenset({"host"}),
+    key_env="BOT_BOTTLE_HOST_CONTROLLER_TOKEN",
+    token_env="BOT_BOTTLE_HOST_CONTROLLER_JWT",
+)
+
+
+class TestTrustDomainMintVerify(unittest.TestCase):
+    def test_mint_verify_round_trips_within_a_domain(self) -> None:
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value="k"):
+            tok = CONTROL_PLANE.mint(ROLE_GATEWAY)
+        self.assertEqual(ROLE_GATEWAY, CONTROL_PLANE.verify(tok, "k"))
+
+    def test_mint_rejects_a_role_outside_the_domain(self) -> None:
+        # `host` is a valid role in _HOST_CTRL but not in the control plane —
+        # the control-plane key must refuse to mint it.
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value="k"):
+            with self.assertRaises(ValueError):
+                CONTROL_PLANE.mint("host")
+
+    def test_a_custom_role_set_verifies_its_own_role(self) -> None:
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value="k"):
+            tok = _HOST_CTRL.mint("host")
+        self.assertEqual("host", _HOST_CTRL.verify(tok, "k"))
+
+    def test_key_from_env_reads_the_domains_env_var(self) -> None:
+        self.assertEqual(
+            "secret", CONTROL_PLANE.key_from_env({CONTROL_PLANE.key_env: " secret "}))
+        self.assertEqual("", CONTROL_PLANE.key_from_env({}))
+
+
+class TestDomainBoundary(unittest.TestCase):
+    """The #476/#468 invariant: two domains, two keys, two role sets — one
+    domain's key can neither mint nor verify the other's tokens."""
+
+    def test_a_control_plane_token_does_not_verify_under_another_domains_key(
+        self,
+    ) -> None:
+        # Even with an IDENTICAL underlying key, a `cli` token minted under the
+        # control-plane domain must not verify as a role in the host-controller
+        # domain — the role isn't in that domain's set.
+        cli_tok = orchestrator_auth.mint(ROLE_CLI, "shared-bytes")
+        self.assertIsNone(_HOST_CTRL.verify(cli_tok, "shared-bytes"))
+
+    def test_distinct_keys_do_not_cross_verify(self) -> None:
+        # The realistic case: distinct host-canonical keys per domain. A token
+        # signed by one key never verifies under the other.
+        host_tok = orchestrator_auth.mint(
+            "host", "host-ctrl-key", roles=_HOST_CTRL.roles)
+        self.assertIsNone(_HOST_CTRL.verify(host_tok, "control-plane-key"))
+        self.assertEqual("host", _HOST_CTRL.verify(host_tok, "host-ctrl-key"))
+
+
+class TestControlPlaneProvisioning(unittest.TestCase):
+    def test_orchestrator_key_returns_the_canonical_key(self) -> None:
+        prov = ControlPlaneProvisioning()
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value="key"):
+            self.assertEqual("key", prov.orchestrator_key())
+
+    def test_orchestrator_key_fail_closes_when_colocated_and_empty(self) -> None:
+        # Invariant 4: a co-located backend must never start the control plane
+        # without a key (it would run OPEN and hand the co-located data plane
+        # full `cli`).
+        prov = ControlPlaneProvisioning()  # default topology: co-located
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value=""):
+            with self.assertRaises(ProvisioningError):
+                prov.orchestrator_key()
+
+    def test_orchestrator_key_allows_empty_when_isolated(self) -> None:
+        # A genuinely isolated control plane (no co-located data plane) may run
+        # without a key — the only topology where open mode is permissible.
+        prov = ControlPlaneProvisioning(
+            topology=Topology(data_plane_shares_control_host=False))
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value=""):
+            self.assertEqual("", prov.orchestrator_key())
+
+    def test_gateway_token_is_a_verifiable_gateway_role_token(self) -> None:
+        prov = ControlPlaneProvisioning()
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value="k"):
+            tok = prov.gateway_token()
+        self.assertEqual(ROLE_GATEWAY, CONTROL_PLANE.verify(tok, "k"))
+
+    def test_gateway_token_cannot_be_reused_as_cli(self) -> None:
+        # The data plane's token is `gateway`-scoped: it never carries `cli`.
+        prov = ControlPlaneProvisioning()
+        with patch("bot_bottle.trust_domain.host_signing_key", return_value="k"):
+            tok = prov.gateway_token()
+        self.assertNotEqual(ROLE_CLI, CONTROL_PLANE.verify(tok, "k"))
+
+
+if __name__ == "__main__":
+    unittest.main()