Compare commits

..

2 Commits

Author SHA1 Message Date
didericis-claude 794e4e662d docs: defer broker replay protection to its own issue (#494)
prd-number-check / require-numbered-prds (pull_request) Failing after 7s
tracker-policy-pr / check-pr (pull_request) Successful in 10s
refresh-image-locks / refresh (push) Successful in 30s
lint / lint (push) Successful in 1m6s
Per PR review, replay protection is too heavy for the host control
server MVP. Drop it from the four-gap framing (now three gaps), remove
the enforcement design section and implementation chunk, and track the
iat-window + jti-cache work in #494 as an independent in-process change.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-26 22:35:13 +00:00
didericis-claude f2fe1f9b2d docs: PRD for host-side control server (#468)
Promote the in-process launch broker into a standalone host control
server: the single privileged host component that brokers launches, owns
orchestrator lifecycle, and is the sole writer of host-durable state.

Closes the four broker gaps (transport, durable provisioned secret,
replay protection, disciplined op vocabulary) and splits host state by
owner and lifetime (orchestrator SQLite / host JSONL audit / gateway
none). The payoff is dropping the Docker socket from the CLI.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-26 22:35:13 +00:00
47 changed files with 877 additions and 1603 deletions
+2 -16
View File
@@ -102,20 +102,6 @@ jobs:
python3 --version
python3 cli.py backend status --backend=docker
- name: Preflight — clear any leftover poisoned gateway network
run: |
# The gateway network has a fixed name and persists across jobs on
# this shared runner. A pre-fix or concurrent launch can leave it with
# a malformed IPv6 subnet that trips docker's own ParseAddr in
# `network inspect` (see PR #515); the code now self-heals it, but the
# heal can't run if `network inspect` is what's broken on some daemon
# versions. Drop the network here so this run recreates it IPv4-only.
# Remove the attached gateway container first (else `network rm` fails
# on active endpoints); both are recreated by ensure_running. Harmless
# when absent.
docker rm --force bot-bottle-orch-gateway 2>/dev/null || true
docker network rm bot-bottle-gateway 2>/dev/null || true
- name: Run integration tests (docker) with coverage
env:
BOT_BOTTLE_BACKEND: docker
@@ -298,7 +284,7 @@ jobs:
- name: Combined coverage (unit + docker integration)
run: PYTHON=python3 bash scripts/coverage.sh aggregate critical
- name: Diff-coverage gate (changed lines >= 80%)
- name: Diff-coverage gate (changed lines >= 90%)
run: |
git fetch --no-tags origin main:refs/remotes/origin/main
python3 scripts/diff_coverage.py --base origin/main --min 80
python3 scripts/diff_coverage.py --base origin/main --min 90
+6 -8
View File
@@ -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.
-3
View File
@@ -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",
-4
View File
@@ -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
+13 -27
View File
@@ -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
)
@@ -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])
+12 -12
View File
@@ -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 "")
+4 -35
View File
@@ -140,43 +140,12 @@ class DockerGateway(Gateway):
marker = inspected.stdout.strip()
if marker in {"", self._subnet}:
return
# Inspectable but mislabelled: the stale auto-IPAM network created
# by older releases. Replace it below.
stale = True
else:
# inspect failed. Classify by stderr — do NOT assume "not absent"
# implies "poisoned": a transient daemon/API error, permission
# failure, timeout, or bad context also fails here, and destroying
# the shared gateway on that guess would tear the network out from
# under every live bottle.
err = inspected.stderr.lower()
if "no such network" in err or "not found" in err:
# Absent: nothing to replace — create it below.
stale = False
elif "parseaddr" in err:
# Present but poisoned. A daemon that default-enables IPv6
# attaches an fdd0::/64 subnet whose `::1/64` gateway trips
# docker's own netip.ParseAddr in `network inspect`/`ls`, so the
# command exits non-zero with that signature. A fixed release
# never *creates* such a network, but one can survive on a
# shared host from an older or concurrent launch — and
# `--ipv6=false` alone can't heal it, since the create below only
# no-ops on "already exists". Force-replace it so later reads
# (e.g. `_network_cidr` pinning a source IP) stop failing.
stale = True
else:
# Unrecognized failure: no evidence the network is malformed.
# Surface it rather than mutate shared state on a guess.
raise GatewayError(
f"gateway network {self.network} could not be inspected: "
f"{inspected.stderr.strip()}"
)
if stale:
# Migrate the stale/poisoned network. Removing the fixed gateway is
# safe here: this launch recreates it.
if inspected.returncode == 0:
# Migrate the stale auto-IPAM network created by older releases.
# Removing the fixed gateway is safe here: this launch recreates it.
run_docker(["docker", "rm", "--force", self.name])
removed = run_docker(["docker", "network", "rm", self.network])
if removed.returncode != 0 and "no such network" not in removed.stderr.lower():
if removed.returncode != 0:
raise GatewayError(
f"gateway network {self.network} needs explicit subnet "
f"{self._subnet} but could not be replaced: "
+5 -17
View File
@@ -29,7 +29,6 @@ import subprocess
from pathlib import Path
from ...log import info
from .. import EnumerationError
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():
+4 -22
View File
@@ -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 []
@@ -54,7 +54,6 @@ _BUILD_INPUTS = {
"image-build-args.json",
"Dockerfile.orchestrator",
"Dockerfile.orchestrator.fc",
"requirements.orchestrator.lock",
),
"gateway": (
"image-build-args.json",
+11 -12
View File
@@ -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: "
+24 -37
View File
@@ -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.
@@ -412,29 +422,6 @@ 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):
return
self._apply_route_policy(flow, config, route, request_path, env)
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."""
if is_git_push_request(request_path, query):
self._block(
flow,
@@ -443,20 +430,20 @@ class EgressAddon:
"git-gate's pre-receive hook).",
ctx=self._req_ctx(flow),
)
return False
if not is_git_fetch_request(request_path, query):
return True
git_decision = decide_git_fetch(config.routes, flow.request.pretty_host)
if git_decision.action != "block":
return True
self._block(flow, git_decision.reason, ctx=self._req_ctx(flow))
return False
return
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 _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
+3 -3
View File
@@ -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",
]
+10 -14
View File
@@ -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
-339
View File
@@ -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",
]
+1 -1
View File
@@ -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
-11
View File
@@ -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",
]
+439 -55
View File
@@ -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",
]
+3 -11
View File
@@ -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 ----------------------------------------------
+18 -80
View File
@@ -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"]
-1
View File
@@ -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",
)
+4 -3
View File
@@ -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()
+2 -6
View File
@@ -3,10 +3,6 @@
- **Status:** Accepted
- **Date:** 2026-06-25
- **Deciders:** didericis
- **Revised:** 2026-07-27 — thresholds relaxed (critical minimum 90→85%,
diff-coverage gate 90→80%) to cut low-value test churn on changed lines.
The risk-weighting structure and the "global is informational" rule are
unchanged.
## Context
@@ -38,7 +34,7 @@ a regression (Goodhart's law).
Coverage is **risk-weighted**, measured over the **combined unit +
integration** suites, with three rules:
1. **Critical modules must remain ≥ 85%.** The curated security/logic core
1. **Critical modules must remain ≥ 90%.** The curated security/logic core
covers the host and gateway egress policy, manifest trust boundary,
git-gate enforcement, supervise protocol/server, YAML parser, and bottle
state. The concrete module list lives in `scripts/critical-modules.txt`;
@@ -59,7 +55,7 @@ integration** suites, with three rules:
The forward-looking guard is a **diff-coverage gate**
(`scripts/diff_coverage.py`): new/changed executable lines on a branch
must be ≥ 80% covered. This catches regressions where they are
must be ≥ 90% covered. This catches regressions where they are
introduced without forcing a back-fill crusade through legacy glue. The
gate skips lines in omitted files (there is no coverage data for them),
so the omit list cannot launder *new* logic into the dark: anything that
@@ -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
@@ -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.
+273
View File
@@ -0,0 +1,273 @@
# PRD prd-new: Host control server
- **Status:** Draft
- **Author:** Claude
- **Created:** 2026-07-26
- **Issue:** #468
## Summary
Promote the in-process launch broker into a standalone **host control
server**: the single privileged component on the host. Both the CLI and the
orchestrator drive it over HTTP; it brokers agent launches, owns the
orchestrator's own lifecycle, and is the sole writer of host-durable state (the
tamper-evident audit record). This closes the three gaps between today's
well-formed broker *contract* ([`orchestrator/broker.py`](../../bot_bottle/orchestrator/broker.py))
and a real out-of-process service — transport, durable provisioned secret,
and a disciplined op vocabulary — and splits host state by
owner and lifetime. The prize: **the CLI no longer needs the Docker socket**,
which is what finally lets a dedicated Gitea runner user drop the
root-equivalent `docker` group (PRD 0070, "Relationship to other work").
## Problem
Container launches run directly from a short-lived CLI process against the
Docker socket. That socket is root-equivalent, so every host that launches
bottles hands root to whoever invokes the CLI — including a CI runner user we
want to keep unprivileged. PRD 0070 already argues for replacing the fat socket
with a **thin, structured, auditable** launch broker, and the contract for that
broker exists and is tested in-process. But it is *only* in-process:
`LaunchBroker.submit(token)` is a method call from
`OrchestratorCore.launch_bottle` ([`service.py:116`](../../bot_bottle/orchestrator/service.py)),
and `DockerBroker` is on no production path — every backend starts the
orchestrator with `--broker stub` ([`__main__.py:54`](../../bot_bottle/orchestrator/__main__.py)).
Three gaps stand between that scaffold and a host service:
1. **No transport.** `submit` is an in-process call. A real service needs a
`BrokerClient` that POSTs the signed token and a host-side HTTP server that
verifies and acts.
2. **The signing secret is ephemeral and self-generated.**
[`__main__.py:53`](../../bot_bottle/orchestrator/__main__.py) does
`secrets.token_bytes(32)` and hands the *same value* to signer and verifier —
viable only because they share a process. A separate daemon needs the secret
provisioned out of band and durable across orchestrator restarts.
3. **The op vocabulary is `launch` / `teardown` only.** Everything else
host-privileged still lives in the CLI, so the schema has to grow — carefully,
since PRD 0070's security argument rests on "structured requests only, static
flags + ids."
Separately, host state has no clear owner. `OrchestratorCore.reconcile` takes
`live_source_ips` as a parameter *only because the orchestrator cannot see the
backend* ([`service.py:137`](../../bot_bottle/orchestrator/service.py)); the
egress traffic log is written to the container's stderr; and there is no durable,
tamper-evident home for the audit record that survives orchestrator destruction.
## Goals / Success Criteria
- A standalone host control server that the CLI and orchestrator reach over
**HTTP**, with three entry paths working end to end:
- `web console -(iroh)-> orchestrator -(http)-> host controller -> launch`
- `cli -(http)-> orchestrator -(http)-> host controller -> launch`
- `cli -(http)-> host controller` — start / restart / status of the
orchestrator **itself** (the bootstrap/recovery path #391 targets).
- The launch op is expressed as a **signed JWT of static flags + ids only**,
verified against a closed schema.
- The signing secret is **provisioned out of band and durable** across
orchestrator restarts (a `TrustDomain` per #476, with a key the orchestrator
never holds for the host controller's *own* endpoints).
- Host-privileged operations move off the CLI to the control server; **the CLI
no longer opens the Docker socket** for bottle operations.
- `Orchestrator.reconcile` no longer takes `live_source_ips` — live-bottle
enumeration becomes an internal control-server call.
- Host-durable state lands as an **append-only, hash-chained JSONL** audit log
owned solely by the host controller; operational state stays SQLite owned
solely by the orchestrator.
## Non-goals
- **Removing standing privilege.** This converts on-demand privilege (a CLI the
user invokes) into standing privilege (a daemon under launchd/systemd). The
win is that the privilege is *narrower* (structured requests vs. a raw socket),
not that it disappears. "Always running" is an accepted new property.
- **Asymmetric signing.** We stay HS256 — see Design / "Signing stays
symmetric."
- **Integrity against a live compromised orchestrator.** Host-location of the
audit log does not buy this: the orchestrator makes the decisions being audited
and can forge or omit entries wherever the file lives. An off-box copy is the
answer, tracked separately.
- **A single unified DB for all state.** Impossible over a guest-kernel share
(SQLite locking is not coherent); state is split by owner and lifetime instead.
- **The generic `SecretProvider` (#355)** and **remote terminal design (#478)**
both ride the same door but are their own work.
## Design
### Topology
The host controller is the sole privileged component. The orchestrator becomes a
client of it for launches, and the CLI becomes a client of it for *both* bottle
operations (indirectly, through the orchestrator) and orchestrator lifecycle
(directly, for bootstrap/recovery — startup can't route through the thing being
started).
```
web console ─(iroh)─▶ orchestrator ─┐
├─(http, signed JWT)─▶ host controller ─▶ launch
cli ────────(http)──▶ orchestrator ─┘
cli ────────(http, bearer)──────────────────────────────▶ host controller (orchestrator lifecycle)
```
### Transport: `BrokerClient` + host server
`LaunchBroker.submit(token)` keeps its exact signature and semantics; only the
*wire* changes. A new `BrokerClient` implements the same submit contract by
POSTing the signed token to the host controller (stdlib `urllib`, like the
existing [`orchestrator/client.py`](../../bot_bottle/orchestrator/client.py)),
and the host controller's launch handler is the existing `verify_request` +
`_launch`/`_teardown` path, now reached over HTTP instead of a method call. The
in-process `StubBroker` stays for the dev-harness and tests; `DockerBroker`'s
`_launch`/`_teardown` bodies move behind the server unchanged. Because the client
satisfies the same interface `OrchestratorCore` already depends on, the core does
not change to gain a real backend.
### Signing stays symmetric (HS256)
PRD 0070 nominally specifies asymmetric; the code is HS256 and we keep it.
Asymmetric matters when the verifier is *less* privileged than the signer — here
it is the reverse: the host controller (verifier) is strictly more privileged
than the orchestrator (signer), and a controller that could forge orchestrator
requests gains nothing, since it is already the component that launches. Staying
symmetric also honors the no-runtime-deps policy (stdlib has no Ed25519). This
matches the reasoning already inlined in `broker.py`'s module docstring.
### Replay protection is out of scope (tracked in #494)
Once the launch token travels over a wire, a captured token could be replayed —
`sign_request` already emits `jti`/`iat` but `verify_request` reads neither, so
there is no expiry window or `jti` cache today. Enforcing that (an `iat` window +
a self-trimming `jti` cache) is a pure in-process change that lands independently
of this work, and it is deferred to **#494** rather than gating the MVP of the
host control server. Nothing here depends on it; it can merge before or after.
### Op vocabulary and the "ids + static flags" rule (gap 3)
Each op moved off the CLI widens the privileged surface, so growth is governed by
one explicit rule, enforced in `verify_request`'s schema check:
> A broker op carries **only ids and enumerated static flags** — a bottle id, a
> pool slot, a **content-addressed** image ref chosen from a fixed set, an op
> name from a closed vocabulary. Never a free-form path, argv, command, or
> caller-supplied filesystem location. If an operation cannot be expressed that
> way, it does not become a broker op.
Operations that fit and move off the CLI (all today in
`backend/*/consolidated_launch.py`, driven by a short-lived CLI process):
| Op | What it does | Fits the rule because |
|---|---|---|
| `launch` / `teardown` | existing | ids + slot + image ref |
| `orchestrator.ensure_running` | start the infra container | no arguments |
| `orchestrator.{start,restart,status}` | lifecycle (the #391 path) | no arguments |
| `list_live` | enumerate running bottles for reconcile | no arguments; returns ids/IPs |
| `allocate_ip` | `next_free_ip` over `_network_container_ips` | no arguments; returns an IP |
| `provision_git_gate` | `cp`/`exec` a per-bottle deploy key into the gateway | bottle id + key handle, no path |
| `reprovision` | `docker exec printenv <ENV_VAR_SECRET>` on a live agent | bottle id + secret *name* |
Image **builds** stay with the orchestrator for v1 (PRD 0070 §Memory: builds run
control-plane-side; a dedicated slim build unit is later, #468-adjacent), so no
`build` broker op is added here.
With `list_live` as an internal control-server call, `Orchestrator.reconcile`'s
`live_source_ips` parameter goes away — the tell PRD 0070 called out that the
orchestrator couldn't see the backend disappears with it.
### Secret provisioning (gap 2)
The shared HS256 secret becomes a durable, out-of-band artifact via the
**`TrustDomain`** seam (#476,
[`trust_domain.py`](../../bot_bottle/trust_domain.py)):
- The **launch-broker secret** is a `TrustDomain` whose key
(`host_signing_key(<file>)`, minted 0600 on first use, durable under
`bot_bottle_root()`) is provisioned to the orchestrator (signer) and the host
controller (verifier). Durability across orchestrator restarts is what makes
re-adoption work — a restart re-verifies against the same key.
- The **host controller's own lifecycle endpoints** (the direct `cli -> host
controller` path) get a **separate** `TrustDomain` key the orchestrator never
holds — exactly the second domain #476's PRD reserves. The orchestrator must
not be able to mint the credentials used to start and stop it.
This reuses the seam #476 landed rather than re-deriving provisioning per
backend (the PR #471 bug class).
### One daemon, structurally separate handlers (open decision 1)
The audit writer and the broker live in **one daemon** for install simplicity,
but with **no shared parsing** and **different credentials per handler**:
- the **launch** handler requires the signed launch **JWT** (provenance +
un-coercible schema);
- the **audit-append** handler takes a plain **bearer token** and writes to the
JSONL log.
This does not defend against orchestrator compromise (it holds both creds) — it
stops a bug in the boring audit path from reaching the privileged launch path.
The launcher stays small enough to audit line-by-line, per PRD 0070.
### State ownership: split by owner and lifetime
A single mounted DB is impossible — SQLite locking is not coherent across guest
kernels over a share, which is why the macOS backend already uses a container-only
volume (`INFRA_DB_VOLUME`). So state splits three ways (depends on #469, which
gets `bot-bottle.db` off the data plane first):
| Owner | State | Home | Shape |
|---|---|---|---|
| **Orchestrator** | `orchestrator_bottles` registry; `bottled_agent_secrets` (encrypted egress tokens); `supervise_proposals` / `supervise_responses` | volume nothing else mounts (generalizing the macOS design) | **SQLite** — mutable, transactional, queried |
| **Host controller** | supervise audit entries; egress traffic log (today → container stderr); host-side config | host filesystem, survives orchestrator/volume destruction | **JSONL** — append-only |
| **Gateway** | none | — | after #469 the data plane holds no DB state |
The historical record is **JSONL, not SQLite**, because it is append-only, never
updated, never transactionally queried: `O_APPEND` writes are atomic, there is no
locking protocol to get wrong, hash-chaining for tamper-evidence is cheap, and it
survives container-runtime volume pruning (the #450 lesson) and stays readable
without the orchestrator running. Both halves of "the audit record" — supervise
decisions and the egress traffic log — land in the one place.
The orchestrator is **sole mounter and sole writer** of its SQLite volume; the
host controller is **sole writer** of the JSONL log, over the authenticated
audit-append channel.
## Implementation chunks
Ordered, each independently mergeable:
1. **`BrokerClient` + host launch server** over HTTP, reusing `verify_request`
and the existing `DockerBroker` bodies. Wire `OrchestratorCore` to a
`BrokerClient` behind a flag; keep `StubBroker` for the dev-harness. Closes
gap 1.
2. **Durable secret via `TrustDomain`** — provision the launch-broker key to
signer + verifier; add the host controller's own lifecycle `TrustDomain`.
Closes gap 2.
3. **Grow the op vocabulary** one op at a time (`list_live` first — it also
removes `reconcile`'s `live_source_ips`), each behind the ids + static-flags
rule. Closes gap 3.
4. **JSONL audit log** — the host-controller-owned, hash-chained historical
record with the plain-bearer audit-append handler; redirect the egress traffic
log into it.
5. **Drop the Docker socket from the CLI** once every host-privileged op it used
is a broker op — the payoff that unblocks the unprivileged Gitea runner user.
## Open questions
1. **Schema-width rule enforcement.** The "ids + static flags" rule is stated;
should `verify_request` reject unknown claim keys outright (strict schema) to
keep the surface from drifting? Leaning yes.
2. **Audit-append back-pressure.** What the audit handler does if the JSONL sink
is unavailable (fail-closed vs. buffer) — resolve before shipping chunk 5.
## References
- **PRD 0070** — the contract, the launch broker, and the state tiers this
implements.
- **#469** — get `bot-bottle.db` off the data plane (lands underneath this).
- **#476** ([`prd-new-control-plane-auth-provisioning`](prd-new-control-plane-auth-provisioning.md))
— the `TrustDomain` seam this plugs the host controller's key into.
- **#391** — backend-agnostic orchestrator restart (the bootstrap path).
- **#494** — enforce broker replay protection (`iat` window + `jti` cache); split
out of this PRD as an independent in-process change.
- **#386** — prebuilt images from the Gitea OCI registry (the fixed image set the
broker validates against).
- **#355** — generic `SecretProvider`.
- **#478** — remote terminal design.
-3
View File
@@ -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
-3
View File
@@ -1,3 +0,0 @@
# Runtime dependencies baked only into the orchestrator images.
fastapi==0.140.0
uvicorn==0.51.0
-182
View File
@@ -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
+5 -5
View File
@@ -13,7 +13,7 @@
# are re-executed; no KVM or Docker dependency.
#
# Pass "critical" as the last argument in either mode to also report just the
# critical modules (ADR 0004 target: 85%).
# critical modules (ADR 0004 target: 90%).
set -euo pipefail
cd "$(dirname "$0")/.."
@@ -34,8 +34,8 @@ if [ "${1:-}" = "aggregate" ]; then
"$PY" -m coverage report -m
if [ "${2:-}" = "critical" ]; then
echo "== critical modules (ADR 0004 minimum: 85%) ==" >&2
"$PY" -m coverage report --include="$CRITICAL" --fail-under=85
echo "== critical modules (ADR 0004 minimum: 90%) ==" >&2
"$PY" -m coverage report --include="$CRITICAL" --fail-under=90
fi
exit 0
fi
@@ -55,6 +55,6 @@ echo "== combined report ==" >&2
"$PY" -m coverage report -m
if [ "${1:-}" = "critical" ]; then
echo "== critical modules (ADR 0004 minimum: 85%) ==" >&2
"$PY" -m coverage report --include="$CRITICAL" --fail-under=85
echo "== critical modules (ADR 0004 minimum: 90%) ==" >&2
"$PY" -m coverage report --include="$CRITICAL" --fail-under=90
fi
+1 -1
View File
@@ -1,4 +1,4 @@
# Critical security/logic core held to the >=85% coverage bar by
# Critical security/logic core held to the >=90% coverage bar by
# docs/decisions/0004-coverage-policy.md.
#
# SINGLE SOURCE OF TRUTH: scripts/coverage.sh (the `critical` report) and
+3 -3
View File
@@ -13,8 +13,8 @@ policy.
Usage:
scripts/coverage.sh # produce .coverage first
python3 scripts/diff_coverage.py # gate against origin/main, min 80%
python3 scripts/diff_coverage.py --base main --min 75
python3 scripts/diff_coverage.py # gate against origin/main, min 90%
python3 scripts/diff_coverage.py --base main --min 85
"""
from __future__ import annotations
@@ -74,7 +74,7 @@ def main() -> int:
ap = argparse.ArgumentParser()
ap.add_argument("--base", default="origin/main",
help="git ref to diff against (default: origin/main)")
ap.add_argument("--min", type=float, default=80.0,
ap.add_argument("--min", type=float, default=90.0,
help="minimum %% of changed executable lines covered")
args = ap.parse_args()
-1
View File
@@ -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",
)
-14
View File
@@ -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()
-12
View File
@@ -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()
@@ -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.")
+1 -29
View File
@@ -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",
-64
View File
@@ -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()
-16
View File
@@ -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)
+1 -10
View File
@@ -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,
@@ -70,18 +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()
-26
View File
@@ -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
-82
View File
@@ -248,88 +248,6 @@ class TestDockerGateway(unittest.TestCase):
calls,
)
def test_ensure_running_replaces_poisoned_ipv6_network(self) -> None:
# A daemon that default-enables IPv6 leaves the gateway network with a
# malformed fdd0::/64 gateway, so `docker network inspect` exits
# non-zero with a ParseAddr error (not "No such network"). `--ipv6=false`
# can't heal an already-poisoned network — the create just no-ops on
# "already exists" — so _ensure_network must force-remove and recreate
# it, else every later subnet read keeps failing.
calls: list[list[str]] = []
def fake(argv: list[str], **_kw: object) -> Mock:
calls.append(argv)
if argv[:2] == ["docker", "ps"]:
return _proc(stdout="")
if argv[:3] == ["docker", "network", "inspect"]:
return _proc(
returncode=1,
stderr='ParseAddr("fdd0:0:0:4::1/64"): unexpected character, '
'want colon (at "/64")',
)
return _proc()
with patch(_RUN_DOCKER, side_effect=fake):
self.sc.connect_to_orchestrator(_ORCH_URL, _TOKEN)
self.assertIn(["docker", "rm", "--force", self.sc.name], calls)
self.assertIn(["docker", "network", "rm", self.sc.network], calls)
creates = [c for c in calls if c[:3] == ["docker", "network", "create"]]
self.assertEqual(
[[
"docker", "network", "create",
"--ipv6=false",
"--subnet", DEFAULT_GATEWAY_SUBNET,
"--label",
f"bot-bottle.gateway-subnet={DEFAULT_GATEWAY_SUBNET}",
self.sc.network,
]],
creates,
)
def test_ensure_running_creates_network_when_inspect_reports_absent(self) -> None:
# The absent case (inspect fails with "No such network") must NOT try to
# remove anything — it just creates. Guards the poisoned-vs-absent split.
calls: list[list[str]] = []
def fake(argv: list[str], **_kw: object) -> Mock:
calls.append(argv)
if argv[:3] == ["docker", "network", "inspect"]:
return _proc(returncode=1, stderr="Error: No such network: x")
return _proc(stdout="") if argv[:2] == ["docker", "ps"] else _proc()
with patch(_RUN_DOCKER, side_effect=fake):
self.sc.connect_to_orchestrator(_ORCH_URL, _TOKEN)
self.assertNotIn(["docker", "network", "rm", self.sc.network], calls)
creates = [c for c in calls if c[:3] == ["docker", "network", "create"]]
self.assertEqual(1, len(creates))
def test_ensure_running_does_not_destroy_on_generic_inspect_error(self) -> None:
# A generic inspect failure (daemon hiccup, permission, timeout) is NOT
# evidence of a poisoned network. Only the ParseAddr poison signature may
# take the destructive heal path; anything else must surface as an error
# without tearing down a possibly-healthy shared gateway.
calls: list[list[str]] = []
def fake(argv: list[str], **_kw: object) -> Mock:
calls.append(argv)
if argv[:2] == ["docker", "ps"]:
return _proc(stdout="")
if argv[:3] == ["docker", "network", "inspect"]:
return _proc(
returncode=1,
stderr="Cannot connect to the Docker daemon at unix:///var/run/docker.sock",
)
return _proc()
with patch(_RUN_DOCKER, side_effect=fake):
with self.assertRaises(GatewayError):
self.sc.connect_to_orchestrator(_ORCH_URL, _TOKEN)
# No mutation of the shared gateway: neither the container nor the
# network is removed, and nothing is recreated.
self.assertNotIn(["docker", "network", "rm", self.sc.network], calls)
self.assertFalse(any(c[:3] == ["docker", "rm", "--force"] for c in calls))
self.assertEqual([], [c for c in calls if c[:3] == ["docker", "network", "create"]])
def test_ca_cert_pem_reads_from_container(self) -> None:
with patch(_RUN_DOCKER, return_value=_proc(stdout=_CA_PEM)) as m:
self.assertEqual(_CA_PEM, self.sc.ca_cert_pem())
+9 -25
View File
@@ -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):
+18 -186
View File
@@ -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):
+2 -1
View File
@@ -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()
+1 -4
View File
@@ -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: