Compare commits
18 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 67652899eb | |||
| f85cbdeebf | |||
| 44e611d14e | |||
| 4fb0f64249 | |||
| 9226d45041 | |||
| 6847fdf0ab | |||
| 421d31c32f | |||
| b4b4e08f62 | |||
| b174442c60 | |||
| ed7307e0e3 | |||
| 1702664b81 | |||
| 8d54fc38ea | |||
| 73a7582abe | |||
| 095896817c | |||
| a30dd49967 | |||
| 2b970d1170 | |||
| 1bfc6c5d16 | |||
| ed9adfb678 |
@@ -66,6 +66,7 @@ COPY bot_bottle/egress_dlp_config.py /app/egress_dlp_config.py
|
||||
COPY bot_bottle/egress_addon.py /app/egress_addon.py
|
||||
COPY bot_bottle/dlp_detectors.py /app/dlp_detectors.py
|
||||
COPY bot_bottle/yaml_subset.py /app/yaml_subset.py
|
||||
COPY bot_bottle/paths.py /app/paths.py
|
||||
COPY bot_bottle/migrations.py /app/migrations.py
|
||||
COPY bot_bottle/db_store.py /app/db_store.py
|
||||
COPY bot_bottle/supervise_types.py /app/supervise_types.py
|
||||
|
||||
@@ -5,7 +5,7 @@
|
||||
# bot-bottle
|
||||
|
||||
[](https://gitea.dideric.is/didericis/bot-bottle/actions?workflow=test.yml)
|
||||
[](https://coverage.readthedocs.io/)
|
||||
[](https://coverage.readthedocs.io/)
|
||||
[](https://gitea.dideric.is/didericis/bot-bottle/src/branch/main/docs/decisions/0004-coverage-policy.md)
|
||||
|
||||
**Problem:** Developer wants to run a coding agent without supervision, but they don't want a prompt injected or misbehaving agent wrecking their environment or exfiltrating sensitive data.
|
||||
|
||||
@@ -6,11 +6,13 @@ import sqlite3
|
||||
from pathlib import Path
|
||||
|
||||
try:
|
||||
from .supervise_types import AuditEntry, host_db_path
|
||||
from .supervise_types import AuditEntry
|
||||
from .paths import host_db_path
|
||||
from .db_store import DbStore
|
||||
from .migrations import TableMigrations
|
||||
except ImportError:
|
||||
from supervise_types import AuditEntry, host_db_path # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
from supervise_types import AuditEntry # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
from paths import host_db_path # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
from db_store import DbStore # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
from migrations import TableMigrations # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
|
||||
|
||||
@@ -26,7 +26,7 @@ from __future__ import annotations
|
||||
import shutil
|
||||
import subprocess
|
||||
|
||||
from ... import supervise as _supervise
|
||||
from ...paths import bot_bottle_root
|
||||
from ...log import info, warn
|
||||
from . import util as docker_mod
|
||||
from .bottle_cleanup_plan import DockerBottleCleanupPlan
|
||||
@@ -94,7 +94,7 @@ def _list_orphan_state_dirs(
|
||||
ANY backend — used so this docker-side check doesn't reap a
|
||||
running non-docker bottle's state dir (the layout is shared
|
||||
across backends)."""
|
||||
state_root = _supervise.bot_bottle_root() / "state"
|
||||
state_root = bot_bottle_root() / "state"
|
||||
if not state_root.is_dir():
|
||||
return []
|
||||
orphans: list[str] = []
|
||||
|
||||
@@ -0,0 +1,17 @@
|
||||
# Firecracker network-pool defaults — the SINGLE source of these values.
|
||||
#
|
||||
# Read by every consumer so they can't drift:
|
||||
# * netpool.py — parses this for the Python defaults (below).
|
||||
# * scripts/firecracker-netpool.sh — falls back to these when the
|
||||
# matching BOT_BOTTLE_FC_* env var is unset.
|
||||
# * nix/firecracker-netpool.nix — readFile-parses this for its option
|
||||
# defaults, then passes the resolved values back as Environment=.
|
||||
#
|
||||
# Plain KEY=VALUE (no quoting, no inline comments, no spaces around `=`)
|
||||
# so it is bash-sourceable, systemd EnvironmentFile-compatible, and
|
||||
# trivially parseable from Python and Nix. A real BOT_BOTTLE_FC_* env
|
||||
# var of the same name always overrides the value here.
|
||||
BOT_BOTTLE_FC_POOL_SIZE=8
|
||||
BOT_BOTTLE_FC_IP_BASE=10.243.0.0
|
||||
BOT_BOTTLE_FC_IFACE_PREFIX=bbfc
|
||||
BOT_BOTTLE_FC_NFT_TABLE=bot_bottle_fc
|
||||
@@ -4,11 +4,13 @@ config renderers (shell command + NixOS module) shown to operators.
|
||||
The Firecracker backend needs a privileged one-time network setup:
|
||||
a pool of point-to-point TAP devices (owned by the invoking user, so
|
||||
`./cli.py start` never needs root) and a dedicated nftables table that
|
||||
isolates every VM. This module is the single source of truth for the
|
||||
pool parameters — the shell script (`scripts/firecracker-netpool.sh`),
|
||||
the NixOS module (`nix/firecracker-netpool.nix`), and the backend's
|
||||
fail-closed preflight all derive from these constants so they can't
|
||||
drift.
|
||||
isolates every VM. The pool parameters live in exactly one place —
|
||||
`netpool.defaults.env`, a plain KEY=VALUE file next to this module —
|
||||
and every consumer reads *that*: this module (below), the shell script
|
||||
(`scripts/firecracker-netpool.sh`), and the NixOS module
|
||||
(`nix/firecracker-netpool.nix`). A `BOT_BOTTLE_FC_*` env var of the
|
||||
same name always overrides the file, and the backend's fail-closed
|
||||
preflight derives from these accessors, so nothing can drift.
|
||||
|
||||
Topology (per slot i):
|
||||
* TAP ``bbfc{i}`` — no shared bridge, so no docker0 / virbr0 / cni0
|
||||
@@ -43,18 +45,47 @@ from typing import IO
|
||||
from ...log import die
|
||||
|
||||
|
||||
# The pool defaults live in one shared file (see module docstring); the
|
||||
# shell script and NixOS module read the same file, so the values can't
|
||||
# drift. This is a packaged data file — a missing/broken install is a
|
||||
# hard error, surfaced here rather than as confusing empty defaults.
|
||||
DEFAULTS_FILE = Path(__file__).with_name("netpool.defaults.env")
|
||||
|
||||
|
||||
def _load_defaults() -> dict[str, str]:
|
||||
out: dict[str, str] = {}
|
||||
for raw in DEFAULTS_FILE.read_text().splitlines():
|
||||
line = raw.strip()
|
||||
if not line or line.startswith("#") or "=" not in line:
|
||||
continue
|
||||
key, _, value = line.partition("=")
|
||||
out[key.strip()] = value.strip()
|
||||
return out
|
||||
|
||||
|
||||
_DEFAULTS = _load_defaults()
|
||||
|
||||
|
||||
def _cfg(key: str) -> str:
|
||||
"""A `BOT_BOTTLE_FC_*` env var overrides the shared-file default."""
|
||||
try:
|
||||
return os.environ.get(key) or _DEFAULTS[key]
|
||||
except KeyError:
|
||||
die(f"{key} is missing from {DEFAULTS_FILE.name} (broken install)")
|
||||
|
||||
|
||||
# Interface names are capped at 15 chars (IFNAMSIZ-1); "bbfc" + a small
|
||||
# index stays well under that and is distinctive enough to grep for.
|
||||
IFACE_PREFIX = os.environ.get("BOT_BOTTLE_FC_IFACE_PREFIX", "bbfc")
|
||||
NFT_TABLE = "bot_bottle_fc"
|
||||
IFACE_PREFIX = _cfg("BOT_BOTTLE_FC_IFACE_PREFIX")
|
||||
NFT_TABLE = _cfg("BOT_BOTTLE_FC_NFT_TABLE")
|
||||
|
||||
|
||||
def pool_size() -> int:
|
||||
return int(os.environ.get("BOT_BOTTLE_FC_POOL_SIZE", "8"))
|
||||
return int(_cfg("BOT_BOTTLE_FC_POOL_SIZE"))
|
||||
|
||||
|
||||
def ip_base() -> str:
|
||||
return os.environ.get("BOT_BOTTLE_FC_IP_BASE", "10.243.0.0")
|
||||
return _cfg("BOT_BOTTLE_FC_IP_BASE")
|
||||
|
||||
|
||||
# Sidecar ports the VM reaches at its host-side TAP IP. Kept in sync
|
||||
|
||||
@@ -36,7 +36,7 @@ from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
from typing import cast
|
||||
|
||||
from . import supervise as _supervise
|
||||
from .paths import bot_bottle_root
|
||||
|
||||
|
||||
# Directory layout: ~/.bot-bottle/state/<identity>/...
|
||||
@@ -163,7 +163,7 @@ def read_metadata(identity: str) -> BottleMetadata | None:
|
||||
def bottle_state_dir(identity: str) -> Path:
|
||||
"""Per-bottle state directory on the host. Created lazily by the
|
||||
write helpers; readers tolerate its absence."""
|
||||
return _supervise.bot_bottle_root() / _STATE_SUBDIR / identity
|
||||
return bot_bottle_root() / _STATE_SUBDIR / identity
|
||||
|
||||
|
||||
def per_bottle_dockerfile_path(identity: str) -> Path:
|
||||
|
||||
@@ -19,7 +19,7 @@ from dataclasses import dataclass
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
|
||||
from .. import supervise as _supervise
|
||||
from ..paths import bot_bottle_root
|
||||
from ..bottle_state import read_metadata
|
||||
from ..backend.docker.egress_apply import (
|
||||
EgressApplyError,
|
||||
@@ -276,7 +276,7 @@ def _write_crash_log(exc: BaseException) -> Path:
|
||||
)
|
||||
entry = f"=== supervise crash {stamp} ===\n{body}\n"
|
||||
try:
|
||||
log_dir = _supervise.bot_bottle_root() / "logs"
|
||||
log_dir = bot_bottle_root() / "logs"
|
||||
log_dir.mkdir(parents=True, exist_ok=True)
|
||||
path = log_dir / "supervise-crash.log"
|
||||
with path.open("a", encoding="utf-8") as fh:
|
||||
|
||||
@@ -0,0 +1,27 @@
|
||||
"""Lean, framework-free `docker` subprocess primitive.
|
||||
|
||||
Deliberately a top-level module with a single stdlib import so it can be
|
||||
reused from anywhere without cost. It is intentionally *not* placed in
|
||||
`backend.docker.util`: importing that module runs `backend/__init__.py`,
|
||||
which eagerly loads all three bottle backends (docker + firecracker +
|
||||
macos) plus the manifest/egress/git-gate/supervise framework — ~76 modules
|
||||
— which would drag the whole backend layer into the deliberately-lean
|
||||
orchestrator. This primitive stays free of that so both the orchestrator's
|
||||
docker components and (in time) `backend.docker.util` can share it."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import subprocess
|
||||
|
||||
|
||||
def run_docker(argv: list[str]) -> subprocess.CompletedProcess[str]:
|
||||
"""Run a `docker` command, capturing stdout/stderr as text. Never raises
|
||||
on a non-zero exit — callers inspect `returncode` / `stderr` so they can
|
||||
stay fail-closed or tolerate idempotent no-ops (e.g. removing an
|
||||
already-absent container)."""
|
||||
return subprocess.run(
|
||||
argv, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, check=False,
|
||||
)
|
||||
|
||||
|
||||
__all__ = ["run_docker"]
|
||||
@@ -0,0 +1,64 @@
|
||||
"""Per-host orchestrator service (PRD 0070).
|
||||
|
||||
A single persistent per-host service that will run the sidecar functions
|
||||
(egress / git-gate / supervise), coordinate with the console, and broker
|
||||
agent launches. This package is being built bottom-up, starting with the
|
||||
backend-neutral "consolidation core" that needs no VM packaging:
|
||||
|
||||
* `registry` — the SQLite runtime-state store + fail-closed
|
||||
attribution (source IP + per-bottle identity token).
|
||||
* `broker` — the signed, structured launch-request contract + a
|
||||
`LaunchBroker` (stub for the harness) that verifies
|
||||
provenance before acting.
|
||||
* `sidecar` — the consolidated per-host sidecar: a `Sidecar`
|
||||
lifecycle contract (idempotent singleton) + a
|
||||
`DockerSidecar` impl. One sidecar shared by all
|
||||
bottles instead of one per bottle.
|
||||
* `service` — the `Orchestrator`: owns the registry, brokers the
|
||||
launch lifecycle (launch/teardown), manages the
|
||||
shared sidecar, attributes.
|
||||
* `control_plane` — the HTTP control-plane RPC (launch / teardown /
|
||||
list / attribute / sidecar / health).
|
||||
|
||||
The actual backend-native launch (a real docker/firecracker broker) and
|
||||
the egress/git/supervise data plane land in later slices once this core is
|
||||
proven (see the PRD sequencing: plain-process dev-harness -> docker
|
||||
orchestrator -> firecracker).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from .registry import BottleRecord, RegistryStore, new_identity_token
|
||||
from .broker import (
|
||||
BrokerAuthError,
|
||||
LaunchBroker,
|
||||
LaunchRequest,
|
||||
StubBroker,
|
||||
sign_request,
|
||||
verify_request,
|
||||
)
|
||||
from .docker_broker import DockerBroker, DockerBrokerError
|
||||
from .sidecar import DockerSidecar, Sidecar, SidecarError
|
||||
from .service import Orchestrator
|
||||
from .control_plane import ControlPlaneServer, dispatch, make_server
|
||||
|
||||
__all__ = [
|
||||
"BottleRecord",
|
||||
"RegistryStore",
|
||||
"new_identity_token",
|
||||
"BrokerAuthError",
|
||||
"LaunchBroker",
|
||||
"LaunchRequest",
|
||||
"StubBroker",
|
||||
"DockerBroker",
|
||||
"DockerBrokerError",
|
||||
"Sidecar",
|
||||
"DockerSidecar",
|
||||
"SidecarError",
|
||||
"sign_request",
|
||||
"verify_request",
|
||||
"Orchestrator",
|
||||
"ControlPlaneServer",
|
||||
"dispatch",
|
||||
"make_server",
|
||||
]
|
||||
@@ -0,0 +1,78 @@
|
||||
"""Run the orchestrator control plane as a plain process (PRD 0070 dev-harness).
|
||||
|
||||
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
|
||||
reload) can be exercised with fast iteration, decoupled from any VM /
|
||||
container packaging. Wrapping this exact service in a backend-native unit
|
||||
(docker container, then Firecracker VM) comes later.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import secrets
|
||||
from pathlib import Path
|
||||
|
||||
from .. import log
|
||||
from .broker import LaunchBroker, StubBroker
|
||||
from .control_plane import make_server
|
||||
from .docker_broker import DockerBroker
|
||||
from .registry import RegistryStore, default_db_path
|
||||
from .service import Orchestrator
|
||||
from .sidecar import DockerSidecar, Sidecar
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
"""Parse args, migrate the registry, and serve the control plane."""
|
||||
parser = argparse.ArgumentParser(prog="bot_bottle.orchestrator")
|
||||
parser.add_argument("--host", default="127.0.0.1", help="bind address")
|
||||
parser.add_argument("--port", type=int, default=8080, help="bind port (0 = ephemeral)")
|
||||
parser.add_argument(
|
||||
"--db", type=Path, default=None,
|
||||
help=f"registry DB path (default: {default_db_path()})",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--broker", choices=("stub", "docker"), default="stub",
|
||||
help="launch broker: 'stub' records requests; 'docker' runs containers",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--sidecar-image", default=None,
|
||||
help="if set, run one consolidated per-host sidecar from this image",
|
||||
)
|
||||
args = parser.parse_args(argv)
|
||||
|
||||
registry = RegistryStore(args.db)
|
||||
registry.migrate()
|
||||
|
||||
# An ephemeral signing secret ties the orchestrator (signer) to its
|
||||
# broker (verifier). 'stub' records launches instead of starting
|
||||
# anything; 'docker' runs real containers (firecracker drops in later).
|
||||
secret = secrets.token_bytes(32)
|
||||
broker: LaunchBroker = DockerBroker(secret) if args.broker == "docker" else StubBroker(secret)
|
||||
sidecar: Sidecar | None = DockerSidecar(args.sidecar_image) if args.sidecar_image else None
|
||||
orchestrator = Orchestrator(registry, broker, secret, sidecar)
|
||||
|
||||
# One persistent per-host sidecar, shared by every bottle (idempotent).
|
||||
if sidecar is not None:
|
||||
orchestrator.ensure_sidecar()
|
||||
log.info("consolidated sidecar ensured", context={"name": sidecar.name})
|
||||
|
||||
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": bound_host, "port": bound_port, "db": str(registry.db_path)},
|
||||
)
|
||||
try:
|
||||
server.serve_forever()
|
||||
except KeyboardInterrupt:
|
||||
log.info("orchestrator shutting down")
|
||||
finally:
|
||||
server.server_close()
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,176 @@
|
||||
"""Launch broker contract (PRD 0070).
|
||||
|
||||
A VM/container can't spawn its own host-network siblings, so the
|
||||
orchestrator brokers agent launches through a small privileged component.
|
||||
The request it sends is:
|
||||
|
||||
* **structured** — static flags + ids only (bottle id, pool slot, a
|
||||
content-addressed image ref), never a free-form path or argv, so a
|
||||
request can't be coerced into launching an arbitrary payload; and
|
||||
* **signed** — wrapped as a compact JWS/JWT the broker verifies before
|
||||
acting, so a *compromised co-located component* (an agent-facing
|
||||
sidecar, say) can't forge a launch. This is the concrete form of the
|
||||
"structured requests only" rule in the PRD security review.
|
||||
|
||||
Signing is **HS256** over a secret shared by the orchestrator (signer) and
|
||||
the broker (verifier) — appropriate here because both are trusted host
|
||||
components provisioned together; the secret is exactly what an
|
||||
agent-facing component does not have. (Stdlib only — the project takes no
|
||||
runtime deps; a cross-host deployment could swap in an asymmetric alg.)
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import abc
|
||||
import base64
|
||||
import hashlib
|
||||
import hmac
|
||||
import json
|
||||
import secrets
|
||||
import time
|
||||
from dataclasses import dataclass
|
||||
|
||||
_JWT_HEADER = {"alg": "HS256", "typ": "JWT"}
|
||||
_ALLOWED_OPS = ("launch", "teardown")
|
||||
|
||||
|
||||
class BrokerAuthError(Exception):
|
||||
"""A broker request failed provenance or schema verification —
|
||||
bad/absent signature, malformed token, or a payload that doesn't match
|
||||
the fixed launch-request shape. Fail-closed: the broker must not act."""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class LaunchRequest:
|
||||
"""The structured, un-coercible launch/teardown request. Ids + flags
|
||||
only — `image_ref` is a content-addressed id, never a path/argv."""
|
||||
|
||||
op: str # one of _ALLOWED_OPS
|
||||
bottle_id: str
|
||||
source_ip: str = ""
|
||||
image_ref: str = ""
|
||||
slot: int | None = None
|
||||
|
||||
|
||||
# --- minimal JWS/JWT (HS256), stdlib only ----------------------------------
|
||||
|
||||
def _b64url(data: bytes) -> str:
|
||||
return base64.urlsafe_b64encode(data).rstrip(b"=").decode("ascii")
|
||||
|
||||
|
||||
def _b64url_decode(text: str) -> bytes:
|
||||
return base64.urlsafe_b64decode(text + "=" * (-len(text) % 4))
|
||||
|
||||
|
||||
def _mac(signing_input: str, secret: bytes) -> str:
|
||||
digest = hmac.new(secret, signing_input.encode("ascii"), hashlib.sha256).digest()
|
||||
return _b64url(digest)
|
||||
|
||||
|
||||
def sign_request(req: LaunchRequest, secret: bytes) -> str:
|
||||
"""Serialize `req` to signed-JWT form. Adds a per-signature `jti`
|
||||
(replay id) and `iat` (issued-at)."""
|
||||
claims: dict[str, object] = {
|
||||
"op": req.op,
|
||||
"bottle_id": req.bottle_id,
|
||||
"source_ip": req.source_ip,
|
||||
"image_ref": req.image_ref,
|
||||
"slot": req.slot,
|
||||
"jti": secrets.token_hex(8),
|
||||
"iat": int(time.time()),
|
||||
}
|
||||
header = _b64url(json.dumps(_JWT_HEADER, sort_keys=True, separators=(",", ":")).encode())
|
||||
payload = _b64url(json.dumps(claims, sort_keys=True, separators=(",", ":")).encode())
|
||||
signing_input = f"{header}.{payload}"
|
||||
return f"{signing_input}.{_mac(signing_input, secret)}"
|
||||
|
||||
|
||||
def verify_request(token: str, secret: bytes) -> LaunchRequest:
|
||||
"""Verify the signature and the request shape; return the parsed
|
||||
request. Raises `BrokerAuthError` on any failure (fail-closed)."""
|
||||
parts = token.split(".")
|
||||
if len(parts) != 3:
|
||||
raise BrokerAuthError("malformed token")
|
||||
header_b, payload_b, sig = parts
|
||||
if not hmac.compare_digest(_mac(f"{header_b}.{payload_b}", secret), sig):
|
||||
raise BrokerAuthError("bad signature")
|
||||
try:
|
||||
header = json.loads(_b64url_decode(header_b))
|
||||
claims = json.loads(_b64url_decode(payload_b))
|
||||
except (ValueError, json.JSONDecodeError) as e:
|
||||
raise BrokerAuthError("malformed token payload") from e
|
||||
if not isinstance(header, dict) or header.get("alg") != "HS256":
|
||||
raise BrokerAuthError("unexpected header/alg")
|
||||
if not isinstance(claims, dict):
|
||||
raise BrokerAuthError("claims are not an object")
|
||||
|
||||
op = claims.get("op")
|
||||
bottle_id = claims.get("bottle_id")
|
||||
source_ip = claims.get("source_ip", "")
|
||||
image_ref = claims.get("image_ref", "")
|
||||
slot = claims.get("slot")
|
||||
if (
|
||||
not isinstance(op, str) or op not in _ALLOWED_OPS
|
||||
or not isinstance(bottle_id, str) or not bottle_id
|
||||
or not isinstance(source_ip, str) or not isinstance(image_ref, str)
|
||||
or not (slot is None or isinstance(slot, int))
|
||||
):
|
||||
raise BrokerAuthError("request does not match the launch-request schema")
|
||||
return LaunchRequest(
|
||||
op=op, bottle_id=bottle_id, source_ip=source_ip, image_ref=image_ref, slot=slot
|
||||
)
|
||||
|
||||
|
||||
# --- the broker itself ------------------------------------------------------
|
||||
|
||||
class LaunchBroker(abc.ABC):
|
||||
"""Verifies a signed request came from the orchestrator, then performs
|
||||
the backend-native launch/teardown. Subclasses implement `_launch` /
|
||||
`_teardown`; verification is shared and fail-closed."""
|
||||
|
||||
def __init__(self, secret: bytes) -> None:
|
||||
self._secret = secret
|
||||
|
||||
def submit(self, token: str) -> LaunchRequest:
|
||||
"""Verify `token` and perform its op. Returns the verified request;
|
||||
raises `BrokerAuthError` if provenance/shape fails."""
|
||||
req = verify_request(token, self._secret)
|
||||
if req.op == "launch":
|
||||
self._launch(req)
|
||||
else:
|
||||
self._teardown(req)
|
||||
return req
|
||||
|
||||
@abc.abstractmethod
|
||||
def _launch(self, req: LaunchRequest) -> None:
|
||||
...
|
||||
|
||||
@abc.abstractmethod
|
||||
def _teardown(self, req: LaunchRequest) -> None:
|
||||
...
|
||||
|
||||
|
||||
class StubBroker(LaunchBroker):
|
||||
"""Dev-harness broker: records verified requests without launching
|
||||
anything. Exercises the full sign -> verify -> act contract in-process."""
|
||||
|
||||
def __init__(self, secret: bytes) -> None:
|
||||
super().__init__(secret)
|
||||
self.launched: list[LaunchRequest] = []
|
||||
self.torn_down: list[LaunchRequest] = []
|
||||
|
||||
def _launch(self, req: LaunchRequest) -> None:
|
||||
self.launched.append(req)
|
||||
|
||||
def _teardown(self, req: LaunchRequest) -> None:
|
||||
self.torn_down.append(req)
|
||||
|
||||
|
||||
__all__ = [
|
||||
"BrokerAuthError",
|
||||
"LaunchRequest",
|
||||
"LaunchBroker",
|
||||
"StubBroker",
|
||||
"sign_request",
|
||||
"verify_request",
|
||||
]
|
||||
@@ -0,0 +1,160 @@
|
||||
"""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 /sidecar -> 200 {"configured", ["name", "running"]}
|
||||
GET /bottles -> 200 {"bottles": [ <redacted record>, ... ]}
|
||||
POST /bottles -> 201 {"bottle_id", "identity_token"} (launch)
|
||||
body: {"source_ip", ["image_ref"], ["metadata"]}
|
||||
DELETE /bottles/<bottle_id> -> 200 {"torn_down": true} | 404 (teardown)
|
||||
POST /attribute -> 200 {"bottle_id"} | 403
|
||||
body: {"source_ip", "identity_token"}
|
||||
|
||||
`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
|
||||
`Orchestrator`, not exposed here.
|
||||
|
||||
Routing/handling is the pure function `dispatch()` so it is unit-testable
|
||||
without a socket; `Handler` / `ControlPlaneServer` / `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 os
|
||||
import socketserver
|
||||
import typing
|
||||
from urllib.parse import urlsplit
|
||||
|
||||
from .service import Orchestrator
|
||||
|
||||
# JSON body payload type (parsed request / rendered response).
|
||||
Json = dict[str, object]
|
||||
|
||||
|
||||
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
|
||||
orch: Orchestrator, method: str, path: str, body: bytes
|
||||
) -> 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."""
|
||||
route = urlsplit(path).path.rstrip("/") or "/"
|
||||
|
||||
if method == "GET" and route == "/health":
|
||||
return 200, {"status": "ok"}
|
||||
|
||||
if method == "GET" and route == "/sidecar":
|
||||
return 200, orch.sidecar_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:
|
||||
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")
|
||||
rec = orch.launch_bottle(
|
||||
source_ip,
|
||||
image_ref=image_ref if isinstance(image_ref, str) else "",
|
||||
metadata=metadata if isinstance(metadata, str) else "",
|
||||
)
|
||||
return 201, {"bottle_id": rec.bottle_id, "identity_token": rec.identity_token}
|
||||
|
||||
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 == "/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}
|
||||
|
||||
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."""
|
||||
server = self.server
|
||||
assert isinstance(server, ControlPlaneServer)
|
||||
length = int(self.headers.get("Content-Length") or 0)
|
||||
body = self.rfile.read(length) if length > 0 else b""
|
||||
status, payload = dispatch(server.orchestrator, method, self.path, body)
|
||||
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_DELETE(self) -> None:
|
||||
self._serve("DELETE")
|
||||
|
||||
|
||||
class ControlPlaneServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
|
||||
"""Threading HTTP server that carries the orchestrator for its handlers."""
|
||||
|
||||
daemon_threads = True
|
||||
allow_reuse_address = True
|
||||
|
||||
def __init__(self, address: tuple[str, int], orchestrator: Orchestrator) -> None:
|
||||
self.orchestrator = orchestrator
|
||||
super().__init__(address, Handler)
|
||||
|
||||
|
||||
def make_server(
|
||||
orchestrator: Orchestrator, host: str = "127.0.0.1", port: int = 0
|
||||
) -> ControlPlaneServer:
|
||||
"""Build (but do not start) a control-plane server. `port=0` binds an
|
||||
ephemeral port — read `server.server_address` for the actual one."""
|
||||
return ControlPlaneServer((host, port), orchestrator)
|
||||
|
||||
|
||||
__all__ = ["dispatch", "Handler", "ControlPlaneServer", "make_server", "Json"]
|
||||
@@ -0,0 +1,83 @@
|
||||
"""Docker launch broker (PRD 0070) — the first *real* LaunchBroker.
|
||||
|
||||
On a verified launch request it starts a Docker container; on teardown it
|
||||
removes it. This proves the orchestrator -> backend seam on the cheapest
|
||||
backend (the sidecar bundle is already containers). Only the request's
|
||||
static ids/flags reach `docker`, so nothing free-form crosses the boundary.
|
||||
|
||||
Slice 3 launches a single container from the request's `image_ref`, named
|
||||
after the bottle id and labelled for cleanup. Wiring the full agent +
|
||||
sidecar bundle (networks, mounts, the consolidated sidecar) is a later
|
||||
slice — this is the seam, not the finished launcher.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import subprocess
|
||||
|
||||
from ..docker_cmd import run_docker
|
||||
from .broker import LaunchBroker, LaunchRequest
|
||||
|
||||
CONTAINER_PREFIX = "bot-bottle-orch-"
|
||||
BOTTLE_ID_LABEL = "bot-bottle-bottle-id"
|
||||
|
||||
|
||||
class DockerBrokerError(Exception):
|
||||
"""A brokered docker launch/teardown failed (non-zero `docker` exit)."""
|
||||
|
||||
|
||||
def container_name(bottle_id: str) -> str:
|
||||
"""Deterministic container name for a bottle."""
|
||||
return f"{CONTAINER_PREFIX}{bottle_id}"
|
||||
|
||||
|
||||
def run_argv(req: LaunchRequest) -> list[str]:
|
||||
"""`docker run` argv for a launch request — built only from its static
|
||||
fields, so it can't be coerced into an arbitrary command."""
|
||||
return [
|
||||
"docker", "run", "--detach",
|
||||
"--name", container_name(req.bottle_id),
|
||||
"--label", f"{BOTTLE_ID_LABEL}={req.bottle_id}",
|
||||
req.image_ref,
|
||||
]
|
||||
|
||||
|
||||
def rm_argv(req: LaunchRequest) -> list[str]:
|
||||
"""`docker rm --force` argv to tear a bottle's container down."""
|
||||
return ["docker", "rm", "--force", container_name(req.bottle_id)]
|
||||
|
||||
|
||||
class DockerBroker(LaunchBroker):
|
||||
"""A `LaunchBroker` that runs / removes a Docker container per bottle.
|
||||
Provenance + schema verification are inherited from `LaunchBroker`."""
|
||||
|
||||
def _docker(self, argv: list[str]) -> subprocess.CompletedProcess[str]:
|
||||
return run_docker(argv)
|
||||
|
||||
def _launch(self, req: LaunchRequest) -> None:
|
||||
if not req.image_ref:
|
||||
raise DockerBrokerError(f"launch request for {req.bottle_id} has no image_ref")
|
||||
proc = self._docker(run_argv(req))
|
||||
if proc.returncode != 0:
|
||||
raise DockerBrokerError(
|
||||
f"docker run failed for {req.bottle_id}: {proc.stderr.strip()}"
|
||||
)
|
||||
|
||||
def _teardown(self, req: LaunchRequest) -> None:
|
||||
proc = self._docker(rm_argv(req))
|
||||
# Idempotent: an already-absent container is a successful teardown.
|
||||
if proc.returncode != 0 and "No such container" not in proc.stderr:
|
||||
raise DockerBrokerError(
|
||||
f"docker rm failed for {req.bottle_id}: {proc.stderr.strip()}"
|
||||
)
|
||||
|
||||
|
||||
__all__ = [
|
||||
"DockerBroker",
|
||||
"DockerBrokerError",
|
||||
"container_name",
|
||||
"run_argv",
|
||||
"rm_argv",
|
||||
"CONTAINER_PREFIX",
|
||||
"BOTTLE_ID_LABEL",
|
||||
]
|
||||
@@ -0,0 +1,219 @@
|
||||
"""Orchestrator bottle registry — the per-host runtime-state store (PRD 0070).
|
||||
|
||||
SQLite-backed registry mapping each live bottle to its source IP and
|
||||
per-bottle identity token, plus the **fail-closed attribution** the data
|
||||
plane relies on: a request is attributed to a bottle only when its source
|
||||
IP *and* its identity token both match a single active record.
|
||||
|
||||
The registry co-tenants the shared host `bot-bottle.db` (the `DbStore`
|
||||
framework namespaces each store by `schema_key`), so all bot-bottle
|
||||
runtime state lives in one queryable file — one place to back up, inspect,
|
||||
and integrate a console against.
|
||||
|
||||
This is the "runtime state" tier of PRD 0070 (leases / approvals /
|
||||
registry) — deliberately NOT config (which stays declarative under
|
||||
`~/.bot-bottle/`) and NOT the build-time constants (a flat file). It is the
|
||||
source of truth the orchestrator sweeps on restart to re-adopt running
|
||||
bottles, so it lives in a durable store rather than process memory.
|
||||
|
||||
Attribution combines two independent signals, and needs both:
|
||||
|
||||
* source IP — the network-layer invariant (on Firecracker the `/31` TAP
|
||||
+ nft make it unspoofable by construction; weaker on other backends).
|
||||
* identity token — an application-layer per-bottle secret, defence in
|
||||
depth that doesn't lean on network anti-spoof. A bottle can only ever
|
||||
prove it is *itself* (it can't learn another bottle's token), so a
|
||||
hostile agent gains nothing by presenting it.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import hmac
|
||||
import secrets
|
||||
import sqlite3
|
||||
import time
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
from ..db_store import DbStore
|
||||
from ..migrations import TableMigrations
|
||||
from ..paths import host_db_path
|
||||
|
||||
# 256 bits of urandom, URL-safe — unguessable per-bottle identity token.
|
||||
IDENTITY_TOKEN_BYTES = 32
|
||||
|
||||
|
||||
def new_identity_token() -> str:
|
||||
"""A fresh per-bottle identity token (PRD 0070 attribution defence)."""
|
||||
return secrets.token_urlsafe(IDENTITY_TOKEN_BYTES)
|
||||
|
||||
|
||||
def default_db_path() -> Path:
|
||||
"""The shared host state DB (`bot-bottle.db`) — all bot-bottle runtime
|
||||
state in one file, co-tenanted via schema_key. Host-resident so it
|
||||
survives orchestrator restarts (re-adoption sweeps it)."""
|
||||
return host_db_path()
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class BottleRecord:
|
||||
"""One live bottle in the registry."""
|
||||
|
||||
bottle_id: str
|
||||
source_ip: str
|
||||
identity_token: str
|
||||
state: str = "active"
|
||||
created_at: float = 0.0
|
||||
# Opaque JSON blob for forward-compat (policy refs, pool slot, ...) —
|
||||
# the registry doesn't interpret it, so new fields need no migration.
|
||||
metadata: str = ""
|
||||
|
||||
def redacted(self) -> dict[str, object]:
|
||||
"""Public view for listing — never exposes the identity token."""
|
||||
return {
|
||||
"bottle_id": self.bottle_id,
|
||||
"source_ip": self.source_ip,
|
||||
"state": self.state,
|
||||
"created_at": self.created_at,
|
||||
"metadata": self.metadata,
|
||||
}
|
||||
|
||||
|
||||
_MIGRATIONS = TableMigrations(
|
||||
"orchestrator_registry",
|
||||
[
|
||||
# v1 — the live bottle registry.
|
||||
"""
|
||||
CREATE TABLE IF NOT EXISTS orchestrator_bottles (
|
||||
bottle_id TEXT PRIMARY KEY,
|
||||
source_ip TEXT NOT NULL,
|
||||
identity_token TEXT NOT NULL,
|
||||
state TEXT NOT NULL DEFAULT 'active',
|
||||
created_at REAL NOT NULL,
|
||||
metadata TEXT NOT NULL DEFAULT ''
|
||||
)
|
||||
""",
|
||||
# source_ip is the data-plane attribution key — index it, and make
|
||||
# the "one active bottle per source IP" check cheap.
|
||||
"CREATE INDEX IF NOT EXISTS idx_orchestrator_bottles_source_ip "
|
||||
"ON orchestrator_bottles (source_ip)",
|
||||
],
|
||||
)
|
||||
|
||||
|
||||
def _row_to_record(row: sqlite3.Row) -> BottleRecord:
|
||||
"""Build a BottleRecord from a registry row."""
|
||||
return BottleRecord(
|
||||
bottle_id=row["bottle_id"],
|
||||
source_ip=row["source_ip"],
|
||||
identity_token=row["identity_token"],
|
||||
state=row["state"],
|
||||
created_at=row["created_at"],
|
||||
metadata=row["metadata"],
|
||||
)
|
||||
|
||||
|
||||
class RegistryStore(DbStore):
|
||||
"""SQLite-backed registry of live bottles + fail-closed attribution."""
|
||||
|
||||
def __init__(self, db_path: Path | None = None) -> None:
|
||||
super().__init__(db_path or default_db_path(), _MIGRATIONS)
|
||||
|
||||
def _connect(self) -> sqlite3.Connection:
|
||||
"""Open a connection with a busy timeout for the shared DB."""
|
||||
conn = super()._connect()
|
||||
# The registry co-tenants the shared bot-bottle.db, so a busy_timeout
|
||||
# rides out brief lock contention with the other stores. WAL for the
|
||||
# shared DB is a deliberate future change (it affects supervise/audit
|
||||
# and is finicky over guest shares) — not flipped here.
|
||||
conn.execute("PRAGMA busy_timeout=5000")
|
||||
return conn
|
||||
|
||||
def register(
|
||||
self,
|
||||
source_ip: str,
|
||||
*,
|
||||
bottle_id: str | None = None,
|
||||
identity_token: str | None = None,
|
||||
metadata: str = "",
|
||||
) -> BottleRecord:
|
||||
"""Register (or replace) a bottle. Mints a bottle_id / identity token
|
||||
when not supplied. Live — this is the control-plane reload path."""
|
||||
rec = BottleRecord(
|
||||
bottle_id=bottle_id or secrets.token_hex(8),
|
||||
source_ip=source_ip,
|
||||
identity_token=identity_token or new_identity_token(),
|
||||
state="active",
|
||||
created_at=time.time(),
|
||||
metadata=metadata,
|
||||
)
|
||||
with self._connect() as conn:
|
||||
conn.execute(
|
||||
"INSERT OR REPLACE INTO orchestrator_bottles "
|
||||
"(bottle_id, source_ip, identity_token, state, created_at, metadata) "
|
||||
"VALUES (?, ?, ?, ?, ?, ?)",
|
||||
(
|
||||
rec.bottle_id,
|
||||
rec.source_ip,
|
||||
rec.identity_token,
|
||||
rec.state,
|
||||
rec.created_at,
|
||||
rec.metadata,
|
||||
),
|
||||
)
|
||||
self._chmod()
|
||||
return rec
|
||||
|
||||
def deregister(self, bottle_id: str) -> bool:
|
||||
"""Remove a bottle. Returns True if a row was deleted."""
|
||||
with self._connect() as conn:
|
||||
cur = conn.execute(
|
||||
"DELETE FROM orchestrator_bottles WHERE bottle_id = ?", (bottle_id,)
|
||||
)
|
||||
return cur.rowcount > 0
|
||||
|
||||
def get(self, bottle_id: str) -> BottleRecord | None:
|
||||
"""Return the bottle by id, or None if absent."""
|
||||
with self._connect() as conn:
|
||||
row = conn.execute(
|
||||
"SELECT * FROM orchestrator_bottles WHERE bottle_id = ?", (bottle_id,)
|
||||
).fetchone()
|
||||
return _row_to_record(row) if row else None
|
||||
|
||||
def all(self) -> list[BottleRecord]:
|
||||
"""Every registered bottle, oldest first."""
|
||||
with self._connect() as conn:
|
||||
rows = conn.execute(
|
||||
"SELECT * FROM orchestrator_bottles ORDER BY created_at"
|
||||
).fetchall()
|
||||
return [_row_to_record(r) for r in rows]
|
||||
|
||||
def attribute(self, source_ip: str, identity_token: str) -> BottleRecord | None:
|
||||
"""Fail-closed attribution. Returns the bottle only when exactly one
|
||||
active record has this source IP AND its identity token matches
|
||||
(constant-time). Either signal alone is insufficient: an unknown IP,
|
||||
an ambiguous IP (more than one active bottle — a misconfiguration),
|
||||
an empty token, or a token mismatch all deny."""
|
||||
if not identity_token:
|
||||
return None
|
||||
with self._connect() as conn:
|
||||
rows = conn.execute(
|
||||
"SELECT * FROM orchestrator_bottles "
|
||||
"WHERE source_ip = ? AND state = 'active'",
|
||||
(source_ip,),
|
||||
).fetchall()
|
||||
if len(rows) != 1:
|
||||
return None
|
||||
rec = _row_to_record(rows[0])
|
||||
if not hmac.compare_digest(rec.identity_token, identity_token):
|
||||
return None
|
||||
return rec
|
||||
|
||||
|
||||
__all__ = [
|
||||
"BottleRecord",
|
||||
"RegistryStore",
|
||||
"new_identity_token",
|
||||
"default_db_path",
|
||||
"IDENTITY_TOKEN_BYTES",
|
||||
]
|
||||
@@ -0,0 +1,102 @@
|
||||
"""The per-host orchestrator core (PRD 0070).
|
||||
|
||||
`Orchestrator` is the single backend-neutral object the control plane talks
|
||||
to: it owns the registry (runtime state) and brokers agent launches. It
|
||||
never branches on backend — the `LaunchBroker` abstracts the backend-native
|
||||
launch, so this same object drives docker / firecracker / apple once a real
|
||||
broker is wired in.
|
||||
|
||||
Launch lifecycle:
|
||||
|
||||
* `launch_bottle` mints the bottle (registry: source IP + identity
|
||||
token), sends a *signed, structured* launch request through the broker,
|
||||
and returns the record. If the broker rejects/fails, the registry entry
|
||||
is rolled back so a failed launch leaves no orphan.
|
||||
* `teardown_bottle` sends a signed teardown request, then deregisters.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from .broker import LaunchBroker, LaunchRequest, sign_request
|
||||
from .registry import BottleRecord, RegistryStore
|
||||
from .sidecar import Sidecar
|
||||
|
||||
|
||||
class Orchestrator:
|
||||
"""Owns the registry + brokers launches, and manages the single
|
||||
consolidated per-host sidecar. Backend-neutral (broker and sidecar
|
||||
abstract the backend-native pieces)."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
registry: RegistryStore,
|
||||
broker: LaunchBroker,
|
||||
sign_secret: bytes,
|
||||
sidecar: Sidecar | None = None,
|
||||
) -> None:
|
||||
self.registry = registry
|
||||
self._broker = broker
|
||||
self._secret = sign_secret
|
||||
self._sidecar = sidecar
|
||||
|
||||
def launch_bottle(
|
||||
self,
|
||||
source_ip: str,
|
||||
*,
|
||||
image_ref: str = "",
|
||||
slot: int | None = None,
|
||||
metadata: str = "",
|
||||
) -> BottleRecord:
|
||||
"""Register a bottle and broker its launch. Rolls the registry entry
|
||||
back if the launch doesn't take, so a failure leaves no orphan."""
|
||||
rec = self.registry.register(source_ip, metadata=metadata)
|
||||
req = LaunchRequest(
|
||||
op="launch",
|
||||
bottle_id=rec.bottle_id,
|
||||
source_ip=source_ip,
|
||||
image_ref=image_ref,
|
||||
slot=slot,
|
||||
)
|
||||
launched = False
|
||||
try:
|
||||
self._broker.submit(sign_request(req, self._secret))
|
||||
launched = True
|
||||
finally:
|
||||
if not launched:
|
||||
self.registry.deregister(rec.bottle_id)
|
||||
return rec
|
||||
|
||||
def teardown_bottle(self, bottle_id: str) -> bool:
|
||||
"""Broker teardown then deregister. False if the bottle is unknown."""
|
||||
rec = self.registry.get(bottle_id)
|
||||
if rec is None:
|
||||
return False
|
||||
req = LaunchRequest(op="teardown", bottle_id=bottle_id, source_ip=rec.source_ip)
|
||||
self._broker.submit(sign_request(req, self._secret))
|
||||
self.registry.deregister(bottle_id)
|
||||
return True
|
||||
|
||||
def attribute(self, source_ip: str, identity_token: str) -> BottleRecord | None:
|
||||
"""Fail-closed attribution (delegates to the registry)."""
|
||||
return self.registry.attribute(source_ip, identity_token)
|
||||
|
||||
# --- consolidated sidecar ----------------------------------------------
|
||||
|
||||
def ensure_sidecar(self) -> None:
|
||||
"""Bring the single per-host sidecar up (idempotent). No-op when no
|
||||
sidecar is configured."""
|
||||
if self._sidecar is not None:
|
||||
self._sidecar.ensure_running()
|
||||
|
||||
def sidecar_status(self) -> dict[str, object]:
|
||||
"""Report the shared sidecar for the control plane / console."""
|
||||
if self._sidecar is None:
|
||||
return {"configured": False}
|
||||
return {
|
||||
"configured": True,
|
||||
"name": self._sidecar.name,
|
||||
"running": self._sidecar.is_running(),
|
||||
}
|
||||
|
||||
|
||||
__all__ = ["Orchestrator"]
|
||||
@@ -0,0 +1,88 @@
|
||||
"""The consolidated per-host sidecar (PRD 0070).
|
||||
|
||||
The core consolidation win: **one** persistent sidecar per host, shared by
|
||||
every bottle, instead of a sidecar bundle per bottle. It's safe to share
|
||||
because the attribution invariant (source IP + identity token, see
|
||||
`registry`) lets the sidecar attribute each request to the right bottle —
|
||||
so per-bottle policy lives in one long-lived process keyed on who's calling.
|
||||
|
||||
`Sidecar` is the backend-neutral lifecycle contract (mirrors `LaunchBroker`):
|
||||
ensure the single instance is up, report it, tear it down. `DockerSidecar`
|
||||
is the docker implementation; a firecracker sidecar VM slots in later.
|
||||
|
||||
The defining behaviour is **idempotent singleton**: `ensure_running` starts
|
||||
the instance if absent and is a no-op if it's already up, so N bottle
|
||||
launches never spawn N sidecars.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import abc
|
||||
|
||||
from ..docker_cmd import run_docker
|
||||
|
||||
SIDECAR_NAME = "bot-bottle-orch-sidecar"
|
||||
SIDECAR_LABEL = "bot-bottle-orch-sidecar=1"
|
||||
|
||||
|
||||
class SidecarError(Exception):
|
||||
"""The shared sidecar failed to start/stop (non-zero `docker` exit)."""
|
||||
|
||||
|
||||
class Sidecar(abc.ABC):
|
||||
"""Lifecycle of the single per-host sidecar. Backend-neutral."""
|
||||
|
||||
name: str
|
||||
|
||||
@abc.abstractmethod
|
||||
def ensure_running(self) -> None:
|
||||
"""Start the sidecar if it isn't already up. Idempotent: a no-op
|
||||
when it's already running (that's the whole point — one per host)."""
|
||||
|
||||
@abc.abstractmethod
|
||||
def is_running(self) -> bool:
|
||||
"""True iff the sidecar instance is currently up."""
|
||||
|
||||
@abc.abstractmethod
|
||||
def stop(self) -> None:
|
||||
"""Remove the sidecar. Idempotent — absent is success."""
|
||||
|
||||
|
||||
class DockerSidecar(Sidecar):
|
||||
"""The consolidated sidecar as a single, fixed-name Docker container."""
|
||||
|
||||
def __init__(self, image_ref: str, *, name: str = SIDECAR_NAME) -> None:
|
||||
self.image_ref = image_ref
|
||||
self.name = name
|
||||
|
||||
def is_running(self) -> bool:
|
||||
proc = run_docker([
|
||||
"docker", "ps",
|
||||
"--filter", f"name=^{self.name}$",
|
||||
"--filter", "status=running",
|
||||
"--format", "{{.Names}}",
|
||||
])
|
||||
return self.name in proc.stdout.split()
|
||||
|
||||
def ensure_running(self) -> None:
|
||||
if self.is_running():
|
||||
return
|
||||
# Clear any stale (stopped) container holding the fixed name, then
|
||||
# start fresh. `rm --force` on an absent name is a tolerated no-op.
|
||||
run_docker(["docker", "rm", "--force", self.name])
|
||||
proc = run_docker([
|
||||
"docker", "run", "--detach",
|
||||
"--name", self.name,
|
||||
"--label", SIDECAR_LABEL,
|
||||
self.image_ref,
|
||||
])
|
||||
if proc.returncode != 0:
|
||||
raise SidecarError(f"sidecar failed to start: {proc.stderr.strip()}")
|
||||
|
||||
def stop(self) -> None:
|
||||
proc = run_docker(["docker", "rm", "--force", self.name])
|
||||
if proc.returncode != 0 and "No such container" not in proc.stderr:
|
||||
raise SidecarError(f"sidecar failed to stop: {proc.stderr.strip()}")
|
||||
|
||||
|
||||
__all__ = ["Sidecar", "DockerSidecar", "SidecarError", "SIDECAR_NAME", "SIDECAR_LABEL"]
|
||||
@@ -0,0 +1,43 @@
|
||||
"""Foundational filesystem paths for bot-bottle.
|
||||
|
||||
`bot_bottle_root()` is the app data root — state, queue, audit logs,
|
||||
git-gate keys, and the shared DB all live under it. It defaults to
|
||||
`~/.bot-bottle` and is overridable with the **`BOT_BOTTLE_ROOT`** env var.
|
||||
|
||||
The env override is the single knob for redirecting the root: the test
|
||||
suite points it at a throwaway dir instead of monkey-patching the function
|
||||
(every module and every flat/package copy reads the same env var, so one
|
||||
override covers them all), and operators can relocate the root if needed.
|
||||
|
||||
This module has no bot-bottle imports, so it is safe to import from any
|
||||
layer (and to COPY flat into the sidecar bundle).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
# The single shared host state DB. All bot-bottle SQLite stores (supervise
|
||||
# queue, audit, the orchestrator registry) co-tenant this one file — the
|
||||
# TableMigrations schema_key namespaces each store's tables.
|
||||
HOST_DB_FILENAME = "bot-bottle.db"
|
||||
|
||||
|
||||
def bot_bottle_root() -> Path:
|
||||
"""The app data root — `$BOT_BOTTLE_ROOT` if set, else `~/.bot-bottle`."""
|
||||
override = os.environ.get("BOT_BOTTLE_ROOT")
|
||||
return Path(override) if override else Path.home() / ".bot-bottle"
|
||||
|
||||
|
||||
def host_db_path() -> Path:
|
||||
"""Path to the shared host state DB, `<root>/db/bot-bottle.db`.
|
||||
|
||||
Kept in its own `db/` subdirectory (not directly under the root) so a
|
||||
backend that can only bind-mount *directories* can share this one file
|
||||
with a sidecar without exposing the root's other contents (git-gate
|
||||
keys, per-bottle state, ...)."""
|
||||
return bot_bottle_root() / "db" / HOST_DB_FILENAME
|
||||
|
||||
|
||||
__all__ = ["HOST_DB_FILENAME", "bot_bottle_root", "host_db_path"]
|
||||
@@ -7,11 +7,13 @@ import sqlite3
|
||||
from pathlib import Path
|
||||
|
||||
try:
|
||||
from .supervise_types import Proposal, Response, host_db_path
|
||||
from .supervise_types import Proposal, Response
|
||||
from .paths import host_db_path
|
||||
from .db_store import DbStore
|
||||
from .migrations import TableMigrations
|
||||
except ImportError:
|
||||
from supervise_types import Proposal, Response, host_db_path # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
from supervise_types import Proposal, Response # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
from paths import host_db_path # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
from db_store import DbStore # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
from migrations import TableMigrations # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
|
||||
|
||||
@@ -23,13 +23,10 @@ class StoreManager:
|
||||
|
||||
def __init__(self, db_path: Path | None = None) -> None:
|
||||
if db_path is None:
|
||||
# Lazy import to avoid a circular dependency: supervise imports
|
||||
# StoreManager at module level; StoreManager must not import
|
||||
# supervise at module level in return.
|
||||
try:
|
||||
from .supervise import host_db_path
|
||||
from .paths import host_db_path
|
||||
except ImportError:
|
||||
from supervise import host_db_path # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
from paths import host_db_path # type: ignore[import-not-found] # pylint: disable=import-error,no-name-in-module
|
||||
db_path = host_db_path()
|
||||
self.db_path = db_path
|
||||
|
||||
|
||||
+6
-16
@@ -41,7 +41,6 @@ try:
|
||||
from .supervise_types import (
|
||||
ACTION_OPERATOR_EDIT,
|
||||
AuditEntry,
|
||||
HOST_DB_FILENAME,
|
||||
Proposal,
|
||||
Response,
|
||||
STATUSES,
|
||||
@@ -54,13 +53,11 @@ try:
|
||||
TOOL_EGRESS_TOKEN_ALLOW,
|
||||
TOOL_GITLEAKS_ALLOW,
|
||||
TOOL_LIST_EGRESS_ROUTES,
|
||||
bot_bottle_root,
|
||||
)
|
||||
except ImportError:
|
||||
from supervise_types import ( # type: ignore[import-not-found,no-redef] # pylint: disable=import-error,no-name-in-module
|
||||
ACTION_OPERATOR_EDIT,
|
||||
AuditEntry,
|
||||
HOST_DB_FILENAME,
|
||||
Proposal,
|
||||
Response,
|
||||
STATUSES,
|
||||
@@ -73,10 +70,15 @@ except ImportError:
|
||||
TOOL_EGRESS_TOKEN_ALLOW,
|
||||
TOOL_GITLEAKS_ALLOW,
|
||||
TOOL_LIST_EGRESS_ROUTES,
|
||||
bot_bottle_root,
|
||||
)
|
||||
|
||||
|
||||
try:
|
||||
from .paths import bot_bottle_root
|
||||
except ImportError: # flat imports inside the sidecar bundle
|
||||
from paths import bot_bottle_root # type: ignore[import-not-found,no-redef] # pylint: disable=import-error,no-name-in-module
|
||||
|
||||
|
||||
SUPERVISE_HOSTNAME = "supervise"
|
||||
SUPERVISE_PORT = 9100
|
||||
|
||||
@@ -106,16 +108,6 @@ def audit_dir() -> Path:
|
||||
return bot_bottle_root() / "audit"
|
||||
|
||||
|
||||
def host_db_path() -> Path:
|
||||
# Calls bot_bottle_root() through this module's globals so that patches
|
||||
# on supervise.bot_bottle_root propagate to callers going through
|
||||
# supervise.host_db_path().
|
||||
#
|
||||
# Kept in its own "db" subdirectory (see supervise_types.host_db_path
|
||||
# for why) — must stay in sync with that copy.
|
||||
return bot_bottle_root() / "db" / HOST_DB_FILENAME
|
||||
|
||||
|
||||
def audit_log_path(component: str, slug: str) -> Path:
|
||||
return audit_dir() / f"{component}-{slug}.log"
|
||||
|
||||
@@ -297,8 +289,6 @@ __all__ = [
|
||||
"archive_proposal",
|
||||
"audit_dir",
|
||||
"audit_log_path",
|
||||
"bot_bottle_root",
|
||||
"host_db_path",
|
||||
"list_pending_proposals",
|
||||
"list_all_pending_proposals",
|
||||
"read_audit_entries",
|
||||
|
||||
@@ -1,26 +1,19 @@
|
||||
"""Shared types and path helpers for supervise stores (PRD 0013).
|
||||
"""Shared types for supervise stores (PRD 0013).
|
||||
|
||||
Extracted from supervise.py so queue_store and audit_store can import
|
||||
Proposal, Response, AuditEntry, and host_db_path without creating a
|
||||
circular import (supervise imports from queue_store/audit_store and
|
||||
vice-versa).
|
||||
Proposal, Response, and AuditEntry without creating a circular import
|
||||
(supervise imports from queue_store/audit_store and vice-versa).
|
||||
|
||||
Patching bot_bottle_root on this module propagates through host_db_path
|
||||
because host_db_path looks up bot_bottle_root via sys.modules[__name__]
|
||||
at call time rather than capturing it at import time.
|
||||
The path helpers (`bot_bottle_root`, `host_db_path`, `HOST_DB_FILENAME`)
|
||||
live in `paths` — import them from there.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import dataclasses
|
||||
import sys
|
||||
import uuid
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
|
||||
|
||||
HOST_DB_FILENAME = "bot-bottle.db"
|
||||
|
||||
TOOL_EGRESS_BLOCK = "egress-block"
|
||||
TOOL_EGRESS_ALLOW = "egress-allow"
|
||||
@@ -43,23 +36,6 @@ STATUSES: tuple[str, ...] = (STATUS_APPROVED, STATUS_MODIFIED, STATUS_REJECTED)
|
||||
ACTION_OPERATOR_EDIT = "operator-edit"
|
||||
|
||||
|
||||
def bot_bottle_root() -> Path:
|
||||
return Path.home() / ".bot-bottle"
|
||||
|
||||
|
||||
def host_db_path() -> Path:
|
||||
# Look up bot_bottle_root through this module's live namespace so that
|
||||
# monkey-patches on supervise_types.bot_bottle_root take effect.
|
||||
#
|
||||
# Lives in its own "db" subdirectory, not directly under
|
||||
# bot_bottle_root(), so backends that can only bind-mount
|
||||
# directories (macos_container's `container run --mount`, which
|
||||
# rejects file sources with "is not a directory") can share this
|
||||
# one file with a sidecar without also exposing bot_bottle_root()'s
|
||||
# other contents (git-gate keys, per-bottle state, etc.).
|
||||
return sys.modules[__name__].bot_bottle_root() / "db" / HOST_DB_FILENAME
|
||||
|
||||
|
||||
def _require_str(raw: dict[str, object], key: str) -> str:
|
||||
value = raw.get(key)
|
||||
if not isinstance(value, str):
|
||||
@@ -171,7 +147,6 @@ class AuditEntry:
|
||||
__all__ = [
|
||||
"ACTION_OPERATOR_EDIT",
|
||||
"AuditEntry",
|
||||
"HOST_DB_FILENAME",
|
||||
"Proposal",
|
||||
"Response",
|
||||
"STATUSES",
|
||||
@@ -184,6 +159,4 @@ __all__ = [
|
||||
"TOOL_EGRESS_TOKEN_ALLOW",
|
||||
"TOOL_GITLEAKS_ALLOW",
|
||||
"TOOL_LIST_EGRESS_ROUTES",
|
||||
"bot_bottle_root",
|
||||
"host_db_path",
|
||||
]
|
||||
|
||||
@@ -1,10 +1,16 @@
|
||||
# PRD 0069: Firecracker-native, Docker-free backend
|
||||
|
||||
- **Status:** Draft
|
||||
- **Status:** Draft (partially superseded)
|
||||
- **Author:** Claude
|
||||
- **Created:** 2026-07-12
|
||||
- **Issue:** #348
|
||||
|
||||
> **Superseded in part by [PRD 0070](0070-per-host-orchestrator.md) (#351):**
|
||||
> the sidecar-consolidation framing here (Stage 1, per-host sidecar; Stage 4,
|
||||
> sidecar-as-VM) is taken over by 0070's per-host orchestrator. This PRD still
|
||||
> owns the docker-free **image-building** work — Stage 2 (nix-built fixed
|
||||
> images, a dependency of 0070) and Stage 3 (in-VM Dockerfile builder).
|
||||
|
||||
## Summary
|
||||
|
||||
Make the Firecracker backend depend on **firecracker + KVM only**, removing
|
||||
|
||||
@@ -0,0 +1,401 @@
|
||||
# PRD 0070: Per-host orchestrator service
|
||||
|
||||
- **Status:** Draft
|
||||
- **Author:** Claude
|
||||
- **Created:** 2026-07-12
|
||||
- **Issue:** #351
|
||||
- **Supersedes:** the Stage-1 / Stage-4 sidecar-consolidation framing of
|
||||
PRD 0069 (#348). Depends on 0069's nix-built fixed images (Stage 2) for
|
||||
bootstrapping; 0069 still owns the docker-free image-building work.
|
||||
|
||||
## Summary
|
||||
|
||||
Replace the **per-bottle sidecar bundle** with a single **persistent,
|
||||
per-host orchestrator**: one long-lived service that runs the sidecar
|
||||
functions (egress / git-gate / supervise), coordinates with the console,
|
||||
and brokers agent launches and teardown. It is **virtualized from the
|
||||
start** using each backend's native isolation primitive — a Firecracker
|
||||
microVM on the Firecracker backend, an Apple container on macOS, a Docker
|
||||
container on the legacy backend — and is fronted by a single
|
||||
**backend-agnostic contract**. Per-backend variation lives on
|
||||
`BottleBackend`, not in the orchestrator.
|
||||
|
||||
## Motivation
|
||||
|
||||
Today each bottle spins up its own sidecar bundle (egress mitmproxy +
|
||||
git-gate + supervise). That costs:
|
||||
|
||||
- **Resources.** N bottles → N heavy bundles booting and idling.
|
||||
- **Operational churn.** Per-launch container/VM lifecycle for the
|
||||
sidecars, a control path baked at launch and torn down at exit.
|
||||
- **A blurry contract.** "How a bottle talks to its sidecar" is
|
||||
re-implemented per backend instead of being one agreed interface.
|
||||
|
||||
A per-host orchestrator collapses the first two and forces the third to
|
||||
be made explicit. It's also the component that will own per-host runtime
|
||||
**state** (slot leases, the approval queue, the bottle registry) — today
|
||||
that's ad-hoc `fcntl`-locked files.
|
||||
|
||||
## Security review (read this first)
|
||||
|
||||
Consolidation is a real change to the trust model. The goal is to **not
|
||||
significantly weaken** the posture; some properties strengthen, some
|
||||
weaken, and the weakened ones must be mitigated by design, not hand-waved.
|
||||
|
||||
### What gets stronger
|
||||
|
||||
- **Build/host isolation of untrusted inputs** (with 0069 Stage 3): user
|
||||
Dockerfiles build in a disposable VM instead of on the host.
|
||||
- **One audited privileged surface.** Today the launcher runs as the full
|
||||
host user and needs the Docker socket (root-equivalent). The orchestrator
|
||||
model replaces that with a **thin launch broker** (below) — a small,
|
||||
structured, auditable privileged core instead of a fat socket.
|
||||
- **Attribution is enforced, not assumed.** Making source-IP identity a
|
||||
first-class contract invariant (below) means each backend must *prove*
|
||||
it, rather than the sidecar implicitly trusting network position.
|
||||
|
||||
### What gets weaker, and the mitigation
|
||||
|
||||
1. **Secret concentration.** Per-bottle sidecars isolate secrets at the
|
||||
process boundary — each holds only its bottle's tokens/keys. A host
|
||||
orchestrator concentrates **every bottle's** egress tokens, git deploy
|
||||
keys, and the console credential in one long-lived process. A single
|
||||
attribution bug leaks bottle A's token into bottle B's request — a class
|
||||
of bug that *cannot exist* per-bottle.
|
||||
- *Mitigation:* lean on the enforced source-IP invariant for
|
||||
attribution; keep the most secret-dense, least-shareable service
|
||||
(**git-gate**, per-repo deploy keys, no natural source-IP scoping)
|
||||
**per-bottle** unless there's a compelling reason; scope each secret
|
||||
to the bottle in the state DB so a lookup can't return the wrong
|
||||
bottle's secret by construction (key every secret access by the
|
||||
verified source identity, never by ambient state).
|
||||
|
||||
2. **Shared fate.** Orchestrator down = no new launches, and running
|
||||
agents lose egress / git / supervise. Compromise = the whole host's
|
||||
fleet, plus launch authority, plus the console token.
|
||||
- *Mitigation:* the orchestrator is itself confined (its own VM/container
|
||||
with its own fail-closed egress); make it **restartable without killing
|
||||
running agent VMs** (agents keep running; they briefly lose sidecar
|
||||
connectivity until it's back); persist state to a host volume so a
|
||||
restart re-adopts live bottles rather than losing them.
|
||||
|
||||
3. **The launch broker is the new privileged core.** We don't eliminate
|
||||
host privilege — we shrink and relocate it. If the broker accepts
|
||||
arbitrary paths/commands, the orchestrator VM can escape through it.
|
||||
- *Mitigation:* the broker takes **structured requests only** — "launch
|
||||
bottle from *this* content-addressed, nix-built rootfs on TAP slot
|
||||
*k*", never "run this argv". It validates against a fixed image set,
|
||||
not caller-supplied paths. It is small enough to audit line-by-line.
|
||||
|
||||
4. **The egress proxy now parses every bottle's traffic in one process.**
|
||||
Higher blast radius for a mitmproxy/TLS-bump bug.
|
||||
- *Mitigation:* this is the argument for virtualizing the orchestrator
|
||||
from the start (Stage B, not a host daemon) — the code that TLS-bumps
|
||||
and parses agent traffic and holds every token runs **inside its own
|
||||
confined VM**, not as a host process. If egress sharing's blast radius
|
||||
feels too high, egress can stay per-bottle while supervise (near-zero
|
||||
secrets) goes host-level first.
|
||||
|
||||
### The attribution invariant
|
||||
|
||||
Source-IP attribution is what makes a shared orchestrator safe: one
|
||||
process serves every bottle and tells them apart by source address. The
|
||||
*mechanism* is identical everywhere (read source IP → look up bottle); the
|
||||
**guarantee that the address can't be forged is a per-backend
|
||||
responsibility** and part of the contract:
|
||||
|
||||
> **Invariant:** a packet's source address, as seen by the orchestrator,
|
||||
> *provably* identifies the originating bottle.
|
||||
|
||||
- **Firecracker** — enforced by the `/31` point-to-point TAP + the
|
||||
`bot_bottle_fc` nft table (strongest; already built).
|
||||
- **Docker** — the per-bottle `--internal` network + anti-spoof; weaker,
|
||||
must be made explicit.
|
||||
- **Apple** — the host-only network.
|
||||
|
||||
If a backend can't honor the invariant, source-IP consolidation is not
|
||||
safe there and that backend keeps per-bottle sidecars. The invariant is a
|
||||
hard precondition, not an aspiration.
|
||||
|
||||
**Defense-in-depth — a per-bottle identity token.** On top of the
|
||||
network-layer invariant, inject a per-bottle secret token into every
|
||||
request the agent makes to the orchestrator (the agent already egresses
|
||||
through the sidecar proxy, so this is cheap to add). It gives an
|
||||
**application-layer** proof of identity independent of the network layer:
|
||||
|
||||
- On **Firecracker** the `/31` + nft already make source IP unspoofable
|
||||
*by construction*, so the token is belt-and-suspenders there — but cheap
|
||||
insurance against a misconfigured invariant.
|
||||
- On **weaker backends** (Docker) it is load-bearing, providing attribution
|
||||
that doesn't lean on network anti-spoof.
|
||||
|
||||
Requirements: the token is **per-bottle, unguessable, and
|
||||
non-cross-leakable** — a bottle can only ever prove it is *itself* (it
|
||||
can't learn another bottle's token, given bottle isolation), so a hostile
|
||||
agent gains nothing by presenting it. The orchestrator provisions the
|
||||
token at launch and the sidecar requires it to attribute + authorize.
|
||||
Note this hardens *attribution*, not *secret exposure*: it's app-layer, so
|
||||
a compromised orchestrator still sees every token (that's the
|
||||
concentration problem, addressed separately under Secret handling).
|
||||
|
||||
### Secret handling — a FUTURE pattern (not v1)
|
||||
|
||||
> **Status: future / not required for the initial orchestrator.** The
|
||||
> initial cut can inject secrets as today; this section records the
|
||||
> direction so v1 doesn't paint itself into a corner. Tracked as its own
|
||||
> work in **#355** (generic `SecretProvider`).
|
||||
|
||||
The residual weakness after all of the above is **long-lived credential
|
||||
concentration** — the data-plane proxies must hold every bottle's upstream
|
||||
tokens because the agent must never see them. You can't policy-gate the
|
||||
component whose job is to *use* all the secrets, so a full RCE of a proxy
|
||||
drains its authorized set regardless. Two moves bound this without
|
||||
pretending to prevent it:
|
||||
|
||||
1. **Vault as a separate trust domain.** The long-lived *roots* live in a
|
||||
distinct process (ideally its own VM) that the byte-parsing data plane
|
||||
never shares memory with. The proxies request secrets from it; the
|
||||
crown jewels are not in the process an agent-facing parser can pop.
|
||||
2. **Derive short-lived, scoped creds where the upstream allows it.** The
|
||||
vault holds the root and mints expiring, narrowly-scoped credentials
|
||||
per bottle-start (or per request) — GitHub App installation tokens,
|
||||
OAuth/STS token exchange, forge deploy tokens. A compromise then leaks
|
||||
short-lived material, not permanent keys. For upstreams stuck on static
|
||||
keys the vault passes the value through (only the at-rest / audit /
|
||||
revocation benefits apply, not lifetime reduction) — this residue is
|
||||
accepted and documented, not solved.
|
||||
|
||||
Even a plain per-request fetch (no derivation) still buys **at-rest**
|
||||
reduction (process memory holds only in-flight secrets), a **detection /
|
||||
rate-limit / revocation chokepoint**, and clean **cross-component
|
||||
scoping** (an egress RCE can't request git-gate's creds). It does *not*
|
||||
prevent abuse of currently-authorized access during the compromise window.
|
||||
|
||||
**Mechanism (see #355):** generalize the existing `DeployKeyProvisioner`
|
||||
(PRD 0048) into a user-extensible **`SecretProvider`** droppable into the
|
||||
manifest anywhere a raw token value is accepted, discovered from
|
||||
`~/.bot-bottle/contrib/<name>/secret_provider.py` exactly as user
|
||||
`AgentProvider`s are — because maintaining every forge/cloud/OAuth
|
||||
provider in-tree is untenable. The orchestrator's vault mints via these
|
||||
providers; but the abstraction is shippable independently and today's
|
||||
per-bottle sidecars can use it too.
|
||||
|
||||
## Design
|
||||
|
||||
### The contract (backend-agnostic)
|
||||
|
||||
Three surfaces; only one is per-backend.
|
||||
|
||||
1. **Control plane (CLI / console → orchestrator)** — an RPC:
|
||||
`launch_bottle`, `teardown_bottle`, `register_policy`,
|
||||
`deregister_bottle`, `supervise_queue`. Fully backend-agnostic. Both the
|
||||
local `cli.py` and the remote console funnel through it, so policy is
|
||||
uniform and `cli.py` becomes a thin client rather than a parallel
|
||||
launcher. **Transport: HTTP** — the most universal/reliable choice on
|
||||
every host (no vsock/unix-socket portability caveats); a local unix
|
||||
socket is a fine optimization, but HTTP is the wire contract.
|
||||
2. **Data plane (agent → orchestrator)** — the egress / git / supervise
|
||||
endpoints. Already agnostic today (agents dial `http://sidecar:9099`);
|
||||
only the *address* and *how packets get there* are per-backend.
|
||||
3. **Launch / wire (orchestrator → backend)** — the irreducibly
|
||||
backend-specific part; lives on `BottleBackend`.
|
||||
|
||||
### One `Orchestrator`, no subclass tree
|
||||
|
||||
The orchestrator is a **single concrete class** holding all the
|
||||
backend-neutral logic — egress addon, git-gate, supervise, source-IP
|
||||
attribution, live-reload control plane, console client. It never branches
|
||||
on backend; it *composes* a `BottleBackend`. That composition is what makes
|
||||
the contract agnostic: there is nothing backend-specific left in the
|
||||
orchestrator to leak.
|
||||
|
||||
Rejected alternative: an `Orchestrator` ABC with per-backend
|
||||
implementations. The interesting logic (proxies, attribution, control
|
||||
plane) is backend-neutral, so three subclasses would triplicate the hard
|
||||
part; and a second hierarchy paralleling `BottleBackend` reintroduces the
|
||||
same hand-maintained lockstep coupling we just removed from the netpool
|
||||
constants (PR #350). Composition over a parallel tree.
|
||||
|
||||
### `BottleBackend` absorbs the per-backend variation
|
||||
|
||||
A small, cohesive surface — reused for launching agent bottles *and* the
|
||||
orchestrator's own unit (the orchestrator is just another native unit):
|
||||
|
||||
```
|
||||
launch_unit(spec) -> Handle # agent bottle OR the orchestrator itself
|
||||
# (fc microVM / apple ctr / docker ctr)
|
||||
wire(unit, endpoint) -> None # DNAT+forward (fc) | attach shared net (docker/apple)
|
||||
endpoint_of(unit) -> Endpoint # address resolution
|
||||
health(unit) -> Status
|
||||
```
|
||||
|
||||
Plus the **launch broker** — the answer to "a VM/container can't spawn its
|
||||
own host-network siblings." The orchestrator can't directly open host
|
||||
`/dev/kvm` + a host TAP fd (Firecracker), and a container can't spawn
|
||||
siblings without a root-equivalent socket (Docker). So every backend
|
||||
exposes a broker the orchestrator calls to launch an agent:
|
||||
|
||||
- **Firecracker** — a thin, structured host shim (see security #3). This
|
||||
replaces today's implicit "launcher runs as host user."
|
||||
- **Docker** — the socket today (fat, root-equivalent — the thing 0069's
|
||||
Stage 3 removes); a narrower broker later.
|
||||
- **Apple** — the `container` CLI/daemon.
|
||||
|
||||
**Broker request schema:** human-readable JSON of **static flags + ids
|
||||
only** (never free-form paths/argv — that's what keeps it un-coercible
|
||||
into arbitrary launches), wrapped as a **signed JWT** so the broker
|
||||
verifies *provenance*: the request came from the real orchestrator, not a
|
||||
forged one from a compromised co-located component. The orchestrator signs;
|
||||
the broker verifies with the orchestrator's public key (provisioned at
|
||||
broker install). This is the concrete form of security #3's "structured
|
||||
requests only." Same JSON-with-ids + JWT shape for all
|
||||
orchestrator↔broker/sidecar communication; cases that don't fit get
|
||||
handled as they arise, with this as the default.
|
||||
|
||||
If `BottleBackend` bloats, the pressure valve is composition one level
|
||||
down: vend a `backend.network()` / `Wiring` collaborator rather than
|
||||
piling methods on — the same discipline, recursed.
|
||||
|
||||
### State: one SQLite DB, owned by the orchestrator
|
||||
|
||||
The orchestrator is the natural owner of per-host **runtime state**:
|
||||
|
||||
- pool **slot leases** (which bottle holds slot *i*) — replaces today's
|
||||
`fcntl`-locked files with SQLite transactions;
|
||||
- the **supervise approval queue** + remembered approvals;
|
||||
- the **live bottle registry** (source IP → bottle → policy/secrets refs),
|
||||
the lookup table the attribution invariant reads.
|
||||
|
||||
This is deliberately **not** a "single source of truth for all config."
|
||||
Config splits into three tiers with different homes:
|
||||
|
||||
| Tier | Example | Home |
|
||||
|---|---|---|
|
||||
| Build-time constants | pool size, IP base, nft table | flat `.env` (PR #350) — must be readable by Nix eval + root bash, zero runtime |
|
||||
| User-authored config | bottle manifests, egress routes, secret refs | declarative files under `~/.bot-bottle/` — trust boundary at `$HOME`, git-trackable, "unknown keys die at load" |
|
||||
| Runtime state | slot leases, approvals, registry | one shared **`bot-bottle.db`**, solely owned by the orchestrator |
|
||||
|
||||
SQLite is right for the runtime tier (mutable, concurrent, queried) and
|
||||
wrong for the other two (Nix can't read it at eval time; it fights the
|
||||
declarative manifest trust model). Keep the tiers separate.
|
||||
|
||||
**One shared `bot-bottle.db` for all runtime state** (decided in review).
|
||||
The registry co-tenants the existing host `bot-bottle.db` — the `DbStore`
|
||||
framework already namespaces each store by `schema_key`, so slot
|
||||
leases / approvals / registry share one file. One place to query, back up,
|
||||
and integrate a console against.
|
||||
|
||||
- **Host-resident, for durability.** Re-adoption sweeps the registry after
|
||||
an orchestrator restart, so state *must* outlive the orchestrator
|
||||
instance. The file lives on the host (`bot_bottle_root()/db/bot-bottle.db`);
|
||||
the orchestrator unit reaches it, it doesn't carry it.
|
||||
- **Integrity by sole ownership, not mount permissions.** Agents can't
|
||||
touch the DB directly wherever it lives (network-isolated in their
|
||||
bottles). The risk is a *compromised agent-facing data-plane service*
|
||||
(egress/git-gate, which parse hostile bytes) writing the registry and
|
||||
forging attribution. Because it's now one shared file, coarse `ro`/`rw`
|
||||
mount-splitting no longer isolates the registry — so the rule is stronger
|
||||
and simpler: **only the orchestrator (control plane) opens `bot-bottle.db`;
|
||||
the data plane and the console reach state through the control-plane RPC,
|
||||
never a direct file handle.** No agent-facing component gets the file, so
|
||||
none can forge attribution. (This supersedes the earlier `ro`-mount idea.)
|
||||
- *Transitional caveat:* today the per-bottle **supervise sidecar
|
||||
rw-bind-mounts `bot-bottle.db`** to write proposals — exactly the
|
||||
pattern the orchestrator removes (supervise consolidates into the
|
||||
orchestrator; sidecar writes become RPC calls). Until that lands, don't
|
||||
put the attribution registry behind a data-plane-writable mount.
|
||||
|
||||
Implementation note for the VM slices: SQLite **WAL** over a guest share
|
||||
(virtiofs/9p) is finicky (the `-shm`/`-wal` files need real mmap/locking),
|
||||
which is a second reason the DB wants a **host-side owner** the orchestrator
|
||||
reaches over the RPC rather than a shared mount into the VM. WAL on the
|
||||
shared DB is therefore a deliberate, tested future change — not enabled ad
|
||||
hoc. `sqlite3` itself is stdlib, so "the host needs SQLite" is a non-cost.
|
||||
|
||||
## Sequencing
|
||||
|
||||
Jump straight to the **virtualized** end state (not a host-daemon stepping
|
||||
stone): a host daemon's agent→`localhost` transport is throwaway once the
|
||||
orchestrator becomes a VM. Decouple the two risks instead:
|
||||
|
||||
- **Consolidation risk** (one process, all secrets, attribution, reload)
|
||||
and **packaging/transport risk** (VM-to-VM wiring, the shim) are
|
||||
independent. Develop the orchestrator **service as a plain process
|
||||
dev-harness** first, so the consolidation logic (attribution, reload,
|
||||
secret handling) is proven with fast iteration — *then* wrap that exact
|
||||
service in the VM and solve wiring separately.
|
||||
|
||||
Backend order (cheapest proof → hardest → last):
|
||||
|
||||
1. **Docker orchestrator** — nearly free (the sidecar bundle is already
|
||||
containers; collapse N bundles into one persistent container). Proves
|
||||
consolidation + the `BottleBackend` seam with the least moving parts.
|
||||
2. **Firecracker orchestrator** — the real work: the shim + VM-to-VM
|
||||
routing (host forwards `bbfcN` → orchestrator TAP; the nft table grows
|
||||
forward rules where today it drops all non-DNAT egress). Built against
|
||||
the dev-harness so the app logic is already proven.
|
||||
3. **macOS (Apple container)** — last (container-to-container networking).
|
||||
|
||||
Keep the sidecar **service one shared thing** throughout.
|
||||
|
||||
## Non-goals
|
||||
|
||||
- Removing OCI/Dockerfile support for agent images (0069's concern).
|
||||
- A single database for *all* config (see the three-tier table).
|
||||
- Changing the per-bottle isolation of agent workloads — only the sidecar
|
||||
is consolidated; agents stay one-VM/container-each.
|
||||
|
||||
## Relationship to other work
|
||||
|
||||
- **PRD 0069 (#348):** 0070 subsumes its Stage 1 (per-host sidecar) and
|
||||
Stage 4 (sidecar-as-VM). 0069 retains Stage 2 (nix-built fixed images —
|
||||
a **dependency** here: the orchestrator and agent base must be
|
||||
nix-built so the broker launches from a fixed image set and bootstrapping
|
||||
has no chicken-and-egg) and Stage 3 (in-VM Dockerfile builder).
|
||||
- **Minimal CI runner (paused):** the Firecracker broker + no host Docker
|
||||
is what lets a dedicated `gitea` runner user drop the root-equivalent
|
||||
`docker` group — it only needs broker-socket access + `kvm`/pool group
|
||||
membership. This work unblocks it.
|
||||
- **Generic `SecretProvider` (#355):** the future secret-handling
|
||||
mechanism (see "Secret handling") — generalizes PRD 0048's
|
||||
`DeployKeyProvisioner` into a user-extensible provider that mints
|
||||
short-lived creds. Shippable independently; the orchestrator's vault
|
||||
mints through it.
|
||||
- **PR #350 (netpool single-source):** the same "one source per fact,
|
||||
composition over parallel hierarchies" discipline the contract follows.
|
||||
|
||||
## Decisions (review 2026-07-13)
|
||||
|
||||
- **Egress sharing:** **consolidate egress** (worth it). Treat it as a
|
||||
minimal, hardened attack surface for a malicious agent rather than
|
||||
keeping it per-bottle; pair it with the identity token above and the
|
||||
short-lived-vault-token mitigations (Secret handling / #355).
|
||||
- **Control-plane transport:** **HTTP** — most universal/reliable on every
|
||||
host; unix socket is an optional local optimization (see the contract).
|
||||
- **Broker request schema:** **signed-JWT JSON, static flags + ids only**
|
||||
(see the launch broker) — provenance + un-coercible by construction.
|
||||
- **State re-adoption:** the restart procedure is:
|
||||
1. **Singleton:** a new orchestrator launch requires no pre-existing
|
||||
orchestrator; any found (healthy or not) is fully shut down first.
|
||||
2. Re-adoption **waits for the new orchestrator to be healthy**.
|
||||
3. Once healthy, it discovers all agents needing adoption via **both the
|
||||
SQLite registry and live process/VM inspection** *before serving any
|
||||
other request*. The two-source sweep is what closes the *in-flight
|
||||
launch* race — a launch that started (VM booting / slot claimed) but
|
||||
hadn't committed to SQLite when the old orchestrator died would be
|
||||
invisible to a SQLite-only sweep; process inspection catches it.
|
||||
Launches should also write an **intent record ahead of committing
|
||||
resources** so the sweep can reconcile intent vs. actual.
|
||||
|
||||
## Open questions
|
||||
|
||||
- **VM-to-VM routing:** per-backend, and in the design it *is*
|
||||
`BottleBackend.wire()` (DNAT+forward for fc, shared-net for
|
||||
docker/apple), not orchestrator logic. **Not a blocker** — resolvable at
|
||||
implementation time (may require a bit of host modification, as the pool
|
||||
setup already does on NixOS); an earlier "sidecars in VMs" spike showed
|
||||
it's feasible.
|
||||
- **Live-reload protocol** for per-bottle policy over the HTTP control
|
||||
plane (add/remove routes/keys/proposals without a restart).
|
||||
- **Identity-token delivery:** exactly how the per-bottle token is placed
|
||||
where the agent can present it but not swap in another bottle's.
|
||||
+67
-93
@@ -1,104 +1,70 @@
|
||||
# bot-bottle Firecracker network pool — declarative NixOS module.
|
||||
#
|
||||
# The one-time privileged setup the Firecracker backend needs: a pool of
|
||||
# user-owned point-to-point TAP devices plus a fail-closed nftables table
|
||||
# that confines every microVM to its own sidecar.
|
||||
# user- (or group-) owned point-to-point TAP devices plus a fail-closed
|
||||
# nftables table that confines every microVM to its own sidecar.
|
||||
#
|
||||
# NON-INVASIVE BY DESIGN. It does NOT flip `networking.nftables.enable`
|
||||
# (which would switch your whole host firewall backend) or
|
||||
# `systemd.network.enable` (which would hand your interfaces to
|
||||
# systemd-networkd). Instead a single systemd oneshot service brings the
|
||||
# pool up on boot — the declarative equivalent of
|
||||
# `sudo ./scripts/firecracker-netpool.sh up`. The `inet <tableName>` table
|
||||
# is independent (its own hooks at priority -10), so it coexists with an
|
||||
# iptables `networking.firewall`, Docker, ufw, firewalld, etc.
|
||||
# systemd-networkd). Instead a single systemd oneshot brings the pool up
|
||||
# on boot by running the SAME bring-up script as every other install
|
||||
# path (`scripts/firecracker-netpool.sh`) — so the TAP/nft logic lives in
|
||||
# exactly one place. The `inet <tableName>` table is independent (its own
|
||||
# hooks at priority -10), so it coexists with an iptables
|
||||
# `networking.firewall`, Docker, ufw, firewalld, etc.
|
||||
#
|
||||
# The oneshot is only restarted when this config changes, so a
|
||||
# `nixos-rebuild switch` doesn't tear down TAPs out from under running
|
||||
# VMs unless you actually changed the pool.
|
||||
# The oneshot is only restarted when this config changes, and the shared
|
||||
# script is non-destructive (it never tears down an existing TAP), so a
|
||||
# `nixos-rebuild switch` won't cut TAPs out from under running VMs.
|
||||
#
|
||||
# The option defaults MUST match the backend constants in
|
||||
# bot_bottle/backend/firecracker/netpool.py (pool size, IP base, iface
|
||||
# prefix, table name). The backend reads the same values at launch from
|
||||
# the BOT_BOTTLE_FC_* env vars; if you override an option here, override
|
||||
# the matching env var for the CLI too (or set writeEnvFile = true below
|
||||
# to have this module emit them). Keep the two sides in lockstep.
|
||||
# Single source of the pool defaults: bot_bottle/backend/firecracker/
|
||||
# netpool.defaults.env. This module readFile-parses it for the option
|
||||
# defaults below, then passes the resolved values back to the script as
|
||||
# Environment=, so the host pool and the CLI launcher can't drift.
|
||||
{ config, lib, pkgs, ... }:
|
||||
|
||||
let
|
||||
cfg = config.services.bot-bottle-firecracker;
|
||||
|
||||
# --- IPv4 <-> int (full 32-bit carry math) -------------------------
|
||||
toOctets = s: map lib.toInt (lib.splitString "." s);
|
||||
ipToInt = s:
|
||||
let o = toOctets s; in
|
||||
(lib.elemAt o 0) * 16777216
|
||||
+ (lib.elemAt o 1) * 65536
|
||||
+ (lib.elemAt o 2) * 256
|
||||
+ (lib.elemAt o 3);
|
||||
intToIp = n:
|
||||
# --- shared single-source defaults ---------------------------------
|
||||
# Parse the KEY=VALUE defaults file (the same one netpool.py and the
|
||||
# shell script read). Pure eval — just readFile, no import-from-
|
||||
# derivation — so it works for both flake and channel consumers.
|
||||
readDefaults = file:
|
||||
let
|
||||
b0 = n / 16777216; r0 = n - b0 * 16777216;
|
||||
b1 = r0 / 65536; r1 = r0 - b1 * 65536;
|
||||
b2 = r1 / 256;
|
||||
b3 = r1 - b2 * 256;
|
||||
in "${toString b0}.${toString b1}.${toString b2}.${toString b3}";
|
||||
lines = lib.splitString "\n" (builtins.readFile file);
|
||||
keep = l: l != "" && !(lib.hasPrefix "#" l) && lib.hasInfix "=" l;
|
||||
toPair = l:
|
||||
let parts = lib.splitString "=" l;
|
||||
in lib.nameValuePair (lib.head parts)
|
||||
(lib.concatStringsSep "=" (lib.tail parts));
|
||||
in lib.listToAttrs (map toPair (lib.filter keep lines));
|
||||
|
||||
baseInt = ipToInt cfg.ipBase;
|
||||
defaults = readDefaults ../bot_bottle/backend/firecracker/netpool.defaults.env;
|
||||
|
||||
# Slot i: host = base + 2i (the VM's gateway), on its own /31.
|
||||
slots = lib.genList (i: {
|
||||
iface = "${cfg.ifacePrefix}${toString i}";
|
||||
hostIp = intToIp (baseInt + 2 * i);
|
||||
}) cfg.poolSize;
|
||||
# The one bring-up implementation, shared with the sudo/systemd paths.
|
||||
netpoolScript = ../scripts/firecracker-netpool.sh;
|
||||
|
||||
ip = "${pkgs.iproute2}/bin/ip";
|
||||
nft = "${pkgs.nftables}/bin/nft";
|
||||
# /31 alignment == an even final octet (only bit 0 matters for base+2i).
|
||||
lastOctet = lib.toInt (lib.last (lib.splitString "." cfg.ipBase));
|
||||
|
||||
# Idempotent ruleset: (create-if-absent → delete → recreate) is atomic
|
||||
# within one `nft -f`, so re-running `up` always lands a clean table.
|
||||
nftFile = pkgs.writeText "bot-bottle-fc.nft" ''
|
||||
table inet ${cfg.tableName}
|
||||
delete table inet ${cfg.tableName}
|
||||
table inet ${cfg.tableName} {
|
||||
chain forward {
|
||||
type filter hook forward priority -10; policy accept;
|
||||
iifname != "${cfg.ifacePrefix}*" return
|
||||
ct state established,related accept
|
||||
ct status dnat accept
|
||||
drop
|
||||
}
|
||||
chain input {
|
||||
type filter hook input priority -10; policy accept;
|
||||
iifname != "${cfg.ifacePrefix}*" return
|
||||
ct state established,related accept
|
||||
drop
|
||||
}
|
||||
}
|
||||
'';
|
||||
# The script needs ip/nft/sysctl + the usual coreutils. It gets every
|
||||
# pool value via the unit's Environment=, so it never reads the shared
|
||||
# defaults file (which isn't beside it once copied to the store).
|
||||
runtimePath = with pkgs; [ iproute2 nftables procps coreutils gnused ];
|
||||
|
||||
# A non-owner user can't open a user-owned TAP, but any member of a
|
||||
# TAP's owning GROUP can (the kernel checks owner-uid OR owning-group).
|
||||
# So `group` lets an interactive user and a CI-runner user share one
|
||||
# pool; `owner` is the single-user default.
|
||||
tapOwn = if cfg.group != null then "group ${cfg.group}" else "user ${cfg.owner}";
|
||||
ownEnv =
|
||||
if cfg.group != null
|
||||
then { BOT_BOTTLE_FC_GROUP = cfg.group; }
|
||||
else { BOT_BOTTLE_FC_OWNER = cfg.owner; };
|
||||
|
||||
upScript = pkgs.writeShellScript "bot-bottle-fc-netpool-up" ''
|
||||
set -eu
|
||||
${lib.concatMapStringsSep "\n" (s: ''
|
||||
${ip} link show ${s.iface} >/dev/null 2>&1 || ${ip} tuntap add dev ${s.iface} mode tap ${tapOwn}
|
||||
${ip} addr replace ${s.hostIp}/31 dev ${s.iface}
|
||||
${ip} link set ${s.iface} up
|
||||
'') slots}
|
||||
${nft} -f ${nftFile}
|
||||
'';
|
||||
|
||||
downScript = pkgs.writeShellScript "bot-bottle-fc-netpool-down" ''
|
||||
${nft} delete table inet ${cfg.tableName} 2>/dev/null || true
|
||||
${lib.concatMapStringsSep "\n" (s: ''
|
||||
${ip} link show ${s.iface} >/dev/null 2>&1 && ${ip} tuntap del dev ${s.iface} mode tap || true
|
||||
'') slots}
|
||||
'';
|
||||
unitEnv = {
|
||||
BOT_BOTTLE_FC_POOL_SIZE = toString cfg.poolSize;
|
||||
BOT_BOTTLE_FC_IP_BASE = cfg.ipBase;
|
||||
BOT_BOTTLE_FC_IFACE_PREFIX = cfg.ifacePrefix;
|
||||
BOT_BOTTLE_FC_NFT_TABLE = cfg.tableName;
|
||||
} // ownEnv;
|
||||
in
|
||||
{
|
||||
options.services.bot-bottle-firecracker = {
|
||||
@@ -106,25 +72,28 @@ in
|
||||
|
||||
poolSize = lib.mkOption {
|
||||
type = lib.types.ints.positive;
|
||||
default = 8;
|
||||
default = lib.toInt defaults.BOT_BOTTLE_FC_POOL_SIZE;
|
||||
defaultText = lib.literalMD "the shared `netpool.defaults.env` value";
|
||||
description = "Number of pool slots (concurrent bottles). Must match BOT_BOTTLE_FC_POOL_SIZE.";
|
||||
};
|
||||
|
||||
ipBase = lib.mkOption {
|
||||
type = lib.types.str;
|
||||
default = "10.243.0.0";
|
||||
default = defaults.BOT_BOTTLE_FC_IP_BASE;
|
||||
defaultText = lib.literalMD "the shared `netpool.defaults.env` value";
|
||||
description = ''
|
||||
Base IPv4 of the /31 pool; slot i uses host = base + 2i. Must
|
||||
be /31-aligned (even final address) and must match
|
||||
BOT_BOTTLE_FC_IP_BASE. Default is an obscure RFC-1918 /16 that
|
||||
dodges docker/libvirt/k8s/LAN and, deliberately, Tailscale's
|
||||
100.64.0.0/10 CGNAT range.
|
||||
be /31-aligned (even final octet) and must match
|
||||
BOT_BOTTLE_FC_IP_BASE. The shared default is an obscure RFC-1918
|
||||
/16 that dodges docker/libvirt/k8s/LAN and, deliberately,
|
||||
Tailscale's 100.64.0.0/10 CGNAT range.
|
||||
'';
|
||||
};
|
||||
|
||||
ifacePrefix = lib.mkOption {
|
||||
type = lib.types.str;
|
||||
default = "bbfc";
|
||||
default = defaults.BOT_BOTTLE_FC_IFACE_PREFIX;
|
||||
defaultText = lib.literalMD "the shared `netpool.defaults.env` value";
|
||||
description = "TAP interface name prefix. Must match BOT_BOTTLE_FC_IFACE_PREFIX.";
|
||||
};
|
||||
|
||||
@@ -153,7 +122,8 @@ in
|
||||
|
||||
tableName = lib.mkOption {
|
||||
type = lib.types.str;
|
||||
default = "bot_bottle_fc";
|
||||
default = defaults.BOT_BOTTLE_FC_NFT_TABLE;
|
||||
defaultText = lib.literalMD "the shared `netpool.defaults.env` value";
|
||||
description = "nftables table name for the isolation boundary. Must match netpool.NFT_TABLE.";
|
||||
};
|
||||
|
||||
@@ -171,7 +141,7 @@ in
|
||||
config = lib.mkIf cfg.enable {
|
||||
assertions = [
|
||||
{
|
||||
assertion = lib.mod baseInt 2 == 0;
|
||||
assertion = lib.mod lastOctet 2 == 0;
|
||||
message = "services.bot-bottle-firecracker.ipBase must be /31-aligned (even final octet); got ${cfg.ipBase}.";
|
||||
}
|
||||
{
|
||||
@@ -183,17 +153,20 @@ in
|
||||
# VM->sidecar traffic is DNAT'd and forwarded, so forwarding must be on.
|
||||
boot.kernel.sysctl."net.ipv4.ip_forward" = 1;
|
||||
|
||||
# One oneshot brings up the whole pool (TAPs + independent nft table).
|
||||
# No networking.nftables.enable / systemd.network.enable — see header.
|
||||
# One oneshot brings up the whole pool (TAPs + independent nft table)
|
||||
# by running the shared bring-up script. No networking.nftables.enable
|
||||
# / systemd.network.enable — see header.
|
||||
systemd.services."bot-bottle-firecracker-netpool" = {
|
||||
description = "bot-bottle Firecracker TAP pool + nft isolation table";
|
||||
wantedBy = [ "multi-user.target" ];
|
||||
after = [ "network-pre.target" ];
|
||||
path = runtimePath;
|
||||
environment = unitEnv;
|
||||
serviceConfig = {
|
||||
Type = "oneshot";
|
||||
RemainAfterExit = true;
|
||||
ExecStart = upScript;
|
||||
ExecStop = downScript;
|
||||
ExecStart = "${pkgs.bash}/bin/bash ${netpoolScript} up";
|
||||
ExecStop = "${pkgs.bash}/bin/bash ${netpoolScript} down";
|
||||
};
|
||||
};
|
||||
|
||||
@@ -202,6 +175,7 @@ in
|
||||
BOT_BOTTLE_FC_POOL_SIZE=${toString cfg.poolSize}
|
||||
BOT_BOTTLE_FC_IP_BASE=${cfg.ipBase}
|
||||
BOT_BOTTLE_FC_IFACE_PREFIX=${cfg.ifacePrefix}
|
||||
BOT_BOTTLE_FC_NFT_TABLE=${cfg.tableName}
|
||||
'';
|
||||
};
|
||||
};
|
||||
|
||||
@@ -33,24 +33,44 @@
|
||||
# sudo ./scripts/firecracker-netpool.sh down
|
||||
# ./scripts/firecracker-netpool.sh status
|
||||
#
|
||||
# Env overrides (must match the backend's util.py constants):
|
||||
# BOT_BOTTLE_FC_POOL_SIZE number of slots (default 8)
|
||||
# BOT_BOTTLE_FC_IP_BASE base IPv4 of the /31 pool (default 10.243.0.0)
|
||||
# BOT_BOTTLE_FC_IFACE_PREFIX TAP name prefix (default bbfc)
|
||||
# BOT_BOTTLE_FC_OWNER owning user (default $SUDO_USER or $USER)
|
||||
# BOT_BOTTLE_FC_GROUP owning group; if set, TAPs are group-owned
|
||||
# instead of user-owned, so any group member
|
||||
# (e.g. an interactive user + a CI runner
|
||||
# user) can open the pool. Overrides OWNER.
|
||||
# Pool params default to the shared single-source file
|
||||
# (bot_bottle/backend/firecracker/netpool.defaults.env); a matching
|
||||
# env var overrides its key:
|
||||
# BOT_BOTTLE_FC_POOL_SIZE number of slots
|
||||
# BOT_BOTTLE_FC_IP_BASE base IPv4 of the /31 pool
|
||||
# BOT_BOTTLE_FC_IFACE_PREFIX TAP name prefix
|
||||
# BOT_BOTTLE_FC_NFT_TABLE isolation table name
|
||||
# BOT_BOTTLE_FC_OWNER owning user (default $SUDO_USER or $USER)
|
||||
# BOT_BOTTLE_FC_GROUP owning group; if set, TAPs are group-owned
|
||||
# instead of user-owned, so any group member
|
||||
# (e.g. an interactive user + a CI runner
|
||||
# user) can open the pool. Overrides OWNER.
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
POOL_SIZE="${BOT_BOTTLE_FC_POOL_SIZE:-8}"
|
||||
IP_BASE="${BOT_BOTTLE_FC_IP_BASE:-10.243.0.0}"
|
||||
PREFIX="${BOT_BOTTLE_FC_IFACE_PREFIX:-bbfc}"
|
||||
# The single source of the pool defaults, shared with netpool.py and the
|
||||
# Nix module. The Nix path passes every value as env (the script runs
|
||||
# from the store, detached from this file), so this lookup only matters
|
||||
# on the direct/sudo path where the script sits in the repo tree.
|
||||
_SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
_DEFAULTS="$_SCRIPT_DIR/../bot_bottle/backend/firecracker/netpool.defaults.env"
|
||||
_default() { # value of KEY=... from the shared file; empty if unavailable
|
||||
[ -f "$_DEFAULTS" ] || return 0
|
||||
sed -n "s/^$1=//p" "$_DEFAULTS" | tail -1
|
||||
}
|
||||
|
||||
POOL_SIZE="${BOT_BOTTLE_FC_POOL_SIZE:-$(_default BOT_BOTTLE_FC_POOL_SIZE)}"
|
||||
IP_BASE="${BOT_BOTTLE_FC_IP_BASE:-$(_default BOT_BOTTLE_FC_IP_BASE)}"
|
||||
PREFIX="${BOT_BOTTLE_FC_IFACE_PREFIX:-$(_default BOT_BOTTLE_FC_IFACE_PREFIX)}"
|
||||
TABLE="${BOT_BOTTLE_FC_NFT_TABLE:-$(_default BOT_BOTTLE_FC_NFT_TABLE)}"
|
||||
OWNER="${BOT_BOTTLE_FC_OWNER:-${SUDO_USER:-$USER}}"
|
||||
GROUP="${BOT_BOTTLE_FC_GROUP:-}"
|
||||
TABLE="bot_bottle_fc"
|
||||
|
||||
# Fail loudly rather than provisioning a half/empty range if a value
|
||||
# resolved to nothing (env unset AND the shared file unreadable).
|
||||
for _v in POOL_SIZE IP_BASE PREFIX TABLE; do
|
||||
[ -n "${!_v}" ] || { echo "error: $_v unresolved (set BOT_BOTTLE_FC_* or fix $_DEFAULTS)" >&2; exit 1; }
|
||||
done
|
||||
|
||||
# Sidecar ports (must match the backend). egress=9099, supervise=9100,
|
||||
# git-http=9420. Reached by the VM at its host-side TAP IP.
|
||||
@@ -94,12 +114,13 @@ cmd_up() {
|
||||
for i in $(seq 0 $((POOL_SIZE-1))); do
|
||||
local dev host
|
||||
dev="$(iface "$i")" ; host="$(host_ip "$i")"
|
||||
if ip link show "$dev" >/dev/null 2>&1; then
|
||||
ip link set "$dev" down 2>/dev/null || true
|
||||
ip tuntap del dev "$dev" mode tap 2>/dev/null || true
|
||||
fi
|
||||
ip tuntap add dev "$dev" mode tap "${own_args[@]}"
|
||||
ip addr add "$host/31" dev "$dev"
|
||||
# Non-destructive + idempotent: only create a missing TAP (tearing
|
||||
# an existing one down would cut a running VM), and `addr replace`
|
||||
# is safe to re-run. Ownership is fixed at creation, so to change
|
||||
# owner/group run `down` then `up`.
|
||||
ip link show "$dev" >/dev/null 2>&1 \
|
||||
|| ip tuntap add dev "$dev" mode tap "${own_args[@]}"
|
||||
ip addr replace "$host/31" dev "$dev"
|
||||
ip link set "$dev" up
|
||||
echo " $dev host=$host guest=$(guest_ip "$i") $own_desc"
|
||||
done
|
||||
|
||||
@@ -0,0 +1,56 @@
|
||||
"""Integration: the Docker launch broker starts and removes a real container.
|
||||
|
||||
Gated on a reachable Docker daemon (skips cleanly otherwise). Uses a tiny
|
||||
image; the container may exit immediately — we only assert it exists after
|
||||
launch and is gone after teardown.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import secrets
|
||||
import subprocess
|
||||
import unittest
|
||||
|
||||
from bot_bottle.orchestrator.broker import LaunchRequest, sign_request
|
||||
from bot_bottle.orchestrator.docker_broker import DockerBroker, container_name
|
||||
from tests._docker import skip_unless_docker
|
||||
|
||||
IMAGE = "busybox"
|
||||
|
||||
|
||||
@skip_unless_docker()
|
||||
class TestDockerBrokerIntegration(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.secret = secrets.token_bytes(16)
|
||||
self.broker = DockerBroker(self.secret)
|
||||
self.bottle_id = "itest" + secrets.token_hex(4)
|
||||
self.name = container_name(self.bottle_id)
|
||||
self.addCleanup(
|
||||
lambda: subprocess.run(
|
||||
["docker", "rm", "--force", self.name],
|
||||
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
|
||||
)
|
||||
)
|
||||
|
||||
def _exists(self) -> bool:
|
||||
proc = subprocess.run(
|
||||
["docker", "ps", "-a", "--filter", f"name=^{self.name}$",
|
||||
"--format", "{{.Names}}"],
|
||||
stdout=subprocess.PIPE, text=True, check=False,
|
||||
)
|
||||
return self.name in proc.stdout.split()
|
||||
|
||||
def _submit(self, req: LaunchRequest) -> None:
|
||||
self.broker.submit(sign_request(req, self.secret))
|
||||
|
||||
def test_launch_creates_then_teardown_removes(self) -> None:
|
||||
self._submit(
|
||||
LaunchRequest(op="launch", bottle_id=self.bottle_id, image_ref=IMAGE)
|
||||
)
|
||||
self.assertTrue(self._exists(), "container should exist after launch")
|
||||
self._submit(LaunchRequest(op="teardown", bottle_id=self.bottle_id))
|
||||
self.assertFalse(self._exists(), "container should be gone after teardown")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,45 @@
|
||||
"""Integration: the consolidated Docker sidecar is an idempotent singleton.
|
||||
|
||||
Gated on a reachable Docker daemon. Uses a unique name so it never
|
||||
collides with a real per-host sidecar or a leftover from another run.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import secrets
|
||||
import subprocess
|
||||
import unittest
|
||||
|
||||
from bot_bottle.orchestrator.sidecar import DockerSidecar
|
||||
from tests._docker import skip_unless_docker
|
||||
|
||||
IMAGE = "busybox"
|
||||
|
||||
|
||||
@skip_unless_docker()
|
||||
class TestDockerSidecarIntegration(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.name = "bot-bottle-orch-sidecar-itest-" + secrets.token_hex(4)
|
||||
self.sc = DockerSidecar(IMAGE, name=self.name)
|
||||
self.addCleanup(self.sc.stop)
|
||||
|
||||
def _count(self) -> int:
|
||||
proc = subprocess.run(
|
||||
["docker", "ps", "-a", "--filter", f"name=^{self.name}$",
|
||||
"--format", "{{.Names}}"],
|
||||
stdout=subprocess.PIPE, text=True, check=False,
|
||||
)
|
||||
return sum(1 for n in proc.stdout.split() if n == self.name)
|
||||
|
||||
def test_ensure_is_idempotent_singleton(self) -> None:
|
||||
self.sc.ensure_running()
|
||||
self.assertEqual(1, self._count())
|
||||
# A second ensure must not spawn a second container — one per host.
|
||||
self.sc.ensure_running()
|
||||
self.assertEqual(1, self._count())
|
||||
self.sc.stop()
|
||||
self.assertEqual(0, self._count())
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
+22
-3
@@ -2,7 +2,7 @@
|
||||
|
||||
Isolates ``HOME`` to a throwaway directory for the entire unit suite so
|
||||
no test ever reads or writes the real ``~/.bot-bottle`` (state, queue,
|
||||
and audit dirs all derive from ``supervise.bot_bottle_root()`` →
|
||||
and audit dirs all derive from ``paths.bot_bottle_root()`` →
|
||||
``Path.home()``). Without this, a test that takes a ``flock`` on the
|
||||
real audit log can **block indefinitely** when a live bottle's supervise
|
||||
sidecar holds that lock — observed as a hung ``coverage run`` at 0% CPU —
|
||||
@@ -10,8 +10,12 @@ and unisolated tests otherwise pollute the developer's home dir.
|
||||
|
||||
Individual tests that need their own ``HOME`` still override
|
||||
``os.environ['HOME']`` and restore it; they now restore to this isolated
|
||||
dir rather than the real one, so isolation holds either way. Tests that
|
||||
patch ``supervise.bot_bottle_root`` directly are unaffected.
|
||||
dir rather than the real one, so isolation holds either way.
|
||||
|
||||
Tests that need their own app-data root call ``use_bottle_root`` (below),
|
||||
which sets ``BOT_BOTTLE_ROOT`` — the supported override read by
|
||||
``paths.bot_bottle_root`` — instead of monkey-patching. One env setting
|
||||
covers every module and every flat/package copy of the helper.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -20,6 +24,9 @@ import atexit
|
||||
import os
|
||||
import shutil
|
||||
import tempfile
|
||||
from collections.abc import Callable
|
||||
from pathlib import Path
|
||||
from unittest import mock
|
||||
|
||||
_real_home = os.environ.get("HOME")
|
||||
_tmp_home = tempfile.mkdtemp(prefix="bot-bottle-unit-home.")
|
||||
@@ -35,3 +42,15 @@ def _restore_home() -> None:
|
||||
|
||||
|
||||
atexit.register(_restore_home)
|
||||
|
||||
|
||||
def use_bottle_root(root: Path) -> Callable[[], None]:
|
||||
"""Redirect ``paths.bot_bottle_root()`` to ``root`` by setting
|
||||
``BOT_BOTTLE_ROOT`` — the supported override. Returns a callable that
|
||||
undoes it (store it as the test's restore hook, or pass to addCleanup).
|
||||
|
||||
Replaces monkey-patching ``paths.bot_bottle_root``; one env var covers
|
||||
every module and the flat/package copies alike (they all read it)."""
|
||||
patcher = mock.patch.dict(os.environ, {"BOT_BOTTLE_ROOT": str(root)})
|
||||
patcher.start()
|
||||
return patcher.stop
|
||||
|
||||
@@ -7,7 +7,8 @@ import unittest
|
||||
from pathlib import Path
|
||||
from unittest.mock import patch
|
||||
|
||||
from bot_bottle import supervise, bottle_state
|
||||
from bot_bottle import bottle_state
|
||||
from tests.unit import use_bottle_root
|
||||
from bot_bottle.backend import ActiveAgent
|
||||
from bot_bottle.backend.freeze import get_freezer
|
||||
from bot_bottle.backend.docker.freezer import DockerFreezer
|
||||
@@ -18,13 +19,7 @@ from bot_bottle.backend.firecracker.freezer import FirecrackerFreezer
|
||||
class _FakeHomeMixin:
|
||||
def _setup_fake_home(self):
|
||||
self._tmp = tempfile.TemporaryDirectory(prefix="freezer-test.")
|
||||
original = supervise.bot_bottle_root
|
||||
|
||||
def fake_root() -> Path:
|
||||
return Path(self._tmp.name) / ".bot-bottle"
|
||||
|
||||
supervise.bot_bottle_root = fake_root # type: ignore[assignment]
|
||||
self._restore = lambda: setattr(supervise, "bot_bottle_root", original)
|
||||
self._restore = use_bottle_root(Path(self._tmp.name) / ".bot-bottle")
|
||||
|
||||
def _teardown_fake_home(self):
|
||||
self._restore()
|
||||
|
||||
@@ -13,7 +13,7 @@ from pathlib import Path
|
||||
from unittest.mock import patch
|
||||
|
||||
from bot_bottle import bottle_state
|
||||
from bot_bottle import supervise
|
||||
from tests.unit import use_bottle_root
|
||||
from bot_bottle.backend import BottleSpec
|
||||
from bot_bottle.backend.docker import DockerBottleBackend
|
||||
from bot_bottle.backend.resolve_common import mint_slug
|
||||
@@ -55,11 +55,10 @@ class _FakeStateMixin:
|
||||
def setUp(self) -> None:
|
||||
self.tmp = tempfile.TemporaryDirectory(prefix="backend-prepare.")
|
||||
self.root = Path(self.tmp.name) / ".bot-bottle"
|
||||
self.original_root = supervise.bot_bottle_root
|
||||
supervise.bot_bottle_root = lambda: self.root # type: ignore[assignment]
|
||||
self._restore = use_bottle_root(self.root)
|
||||
|
||||
def tearDown(self) -> None:
|
||||
supervise.bot_bottle_root = self.original_root # type: ignore[assignment]
|
||||
self._restore()
|
||||
self.tmp.cleanup()
|
||||
|
||||
|
||||
|
||||
@@ -13,7 +13,7 @@ from pathlib import Path
|
||||
from unittest.mock import MagicMock, call, patch
|
||||
|
||||
from bot_bottle import bottle_state
|
||||
from bot_bottle import supervise
|
||||
from tests.unit import use_bottle_root
|
||||
from bot_bottle.backend import Bottle, BottleSpec, ExecResult
|
||||
from bot_bottle.backend.docker import DockerBottleBackend
|
||||
from bot_bottle.backend.firecracker import FirecrackerBottleBackend
|
||||
@@ -55,11 +55,10 @@ class _FakeStateMixin:
|
||||
self.tmp_dir = tempfile.TemporaryDirectory(prefix="backend-workspace.")
|
||||
self.tmp = Path(self.tmp_dir.name)
|
||||
self.root = self.tmp / ".bot-bottle"
|
||||
self.original_root = supervise.bot_bottle_root
|
||||
supervise.bot_bottle_root = lambda: self.root # type: ignore[assignment]
|
||||
self._restore = use_bottle_root(self.root)
|
||||
|
||||
def tearDown(self) -> None:
|
||||
supervise.bot_bottle_root = self.original_root # type: ignore[assignment]
|
||||
self._restore()
|
||||
self.tmp_dir.cleanup()
|
||||
|
||||
|
||||
|
||||
@@ -6,7 +6,7 @@ import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
from bot_bottle import supervise
|
||||
from tests.unit import use_bottle_root
|
||||
from bot_bottle import bottle_state
|
||||
from bot_bottle.bottle_state import (
|
||||
BottleMetadata,
|
||||
@@ -18,13 +18,7 @@ from bot_bottle.bottle_state import (
|
||||
class _FakeHomeMixin:
|
||||
def _setup_fake_home(self):
|
||||
self._tmp = tempfile.TemporaryDirectory(prefix="bottle-state-test.")
|
||||
original = supervise.bot_bottle_root
|
||||
|
||||
def fake_root() -> Path:
|
||||
return Path(self._tmp.name) / ".bot-bottle"
|
||||
|
||||
supervise.bot_bottle_root = fake_root # type: ignore[assignment]
|
||||
self._restore = lambda: setattr(supervise, "bot_bottle_root", original)
|
||||
self._restore = use_bottle_root(Path(self._tmp.name) / ".bot-bottle")
|
||||
|
||||
def _teardown_fake_home(self):
|
||||
self._restore()
|
||||
|
||||
@@ -8,7 +8,7 @@ from pathlib import Path
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
from bot_bottle.cli.commit import cmd_commit
|
||||
from bot_bottle import supervise
|
||||
from tests.unit import use_bottle_root
|
||||
from bot_bottle import bottle_state
|
||||
from bot_bottle.backend.freeze import CommitCancelled
|
||||
|
||||
@@ -16,13 +16,7 @@ from bot_bottle.backend.freeze import CommitCancelled
|
||||
class _FakeHomeMixin:
|
||||
def _setup_fake_home(self):
|
||||
self._tmp = tempfile.TemporaryDirectory(prefix="cli-commit-test.")
|
||||
original = supervise.bot_bottle_root
|
||||
|
||||
def fake_root() -> Path:
|
||||
return Path(self._tmp.name) / ".bot-bottle"
|
||||
|
||||
supervise.bot_bottle_root = fake_root # type: ignore[assignment]
|
||||
self._restore = lambda: setattr(supervise, "bot_bottle_root", original)
|
||||
self._restore = use_bottle_root(Path(self._tmp.name) / ".bot-bottle")
|
||||
|
||||
def _teardown_fake_home(self):
|
||||
self._restore()
|
||||
|
||||
@@ -8,7 +8,7 @@ import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
from bot_bottle import supervise
|
||||
from tests.unit import use_bottle_root
|
||||
from bot_bottle import bottle_state
|
||||
from bot_bottle.cli import start as start_mod
|
||||
|
||||
@@ -16,15 +16,10 @@ from bot_bottle.cli import start as start_mod
|
||||
class _FakeHomeMixin:
|
||||
def _setup_fake_home(self):
|
||||
self._tmp = tempfile.TemporaryDirectory(prefix="cli-start-settle.")
|
||||
self._original = supervise.bot_bottle_root
|
||||
|
||||
def fake_root() -> Path:
|
||||
return Path(self._tmp.name) / ".bot-bottle"
|
||||
|
||||
supervise.bot_bottle_root = fake_root # type: ignore[assignment]
|
||||
self._restore = use_bottle_root(Path(self._tmp.name) / ".bot-bottle")
|
||||
|
||||
def _teardown_fake_home(self):
|
||||
supervise.bot_bottle_root = self._original # type: ignore[assignment]
|
||||
self._restore()
|
||||
self._tmp.cleanup()
|
||||
|
||||
|
||||
|
||||
@@ -15,7 +15,7 @@ import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
from bot_bottle import supervise
|
||||
from tests.unit import use_bottle_root
|
||||
from bot_bottle import bottle_state
|
||||
from bot_bottle.backend.docker.cleanup import _list_orphan_state_dirs
|
||||
|
||||
@@ -23,13 +23,7 @@ from bot_bottle.backend.docker.cleanup import _list_orphan_state_dirs
|
||||
class _FakeHomeMixin:
|
||||
def _setup_fake_home(self) -> None:
|
||||
self._tmp = tempfile.TemporaryDirectory(prefix="docker-cleanup-test.")
|
||||
original = supervise.bot_bottle_root
|
||||
|
||||
def fake_root() -> Path:
|
||||
return Path(self._tmp.name) / ".bot-bottle"
|
||||
|
||||
supervise.bot_bottle_root = fake_root # type: ignore[assignment]
|
||||
self._restore = lambda: setattr(supervise, "bot_bottle_root", original)
|
||||
self._restore = use_bottle_root(Path(self._tmp.name) / ".bot-bottle")
|
||||
|
||||
def _teardown_fake_home(self) -> None:
|
||||
self._restore()
|
||||
|
||||
@@ -23,7 +23,7 @@ import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
from bot_bottle import supervise
|
||||
from tests.unit import use_bottle_root
|
||||
from bot_bottle import bottle_state
|
||||
from bot_bottle.backend.docker import enumerate as _enumerate
|
||||
|
||||
@@ -75,13 +75,7 @@ class TestParseServicesByProject(unittest.TestCase):
|
||||
class _FakeHomeMixin:
|
||||
def _setup_fake_home(self) -> None:
|
||||
self._tmp = tempfile.TemporaryDirectory(prefix="enum-active.")
|
||||
original = supervise.bot_bottle_root
|
||||
|
||||
def fake_root() -> Path:
|
||||
return Path(self._tmp.name) / ".bot-bottle"
|
||||
|
||||
supervise.bot_bottle_root = fake_root # type: ignore[assignment]
|
||||
self._restore_home = lambda: setattr(supervise, "bot_bottle_root", original)
|
||||
self._restore_home = use_bottle_root(Path(self._tmp.name) / ".bot-bottle")
|
||||
|
||||
def _teardown_fake_home(self) -> None:
|
||||
self._restore_home()
|
||||
|
||||
@@ -8,7 +8,7 @@ from pathlib import Path
|
||||
from types import SimpleNamespace
|
||||
from unittest.mock import patch
|
||||
|
||||
from bot_bottle import supervise
|
||||
from tests.unit import use_bottle_root
|
||||
from bot_bottle.backend.egress_apply import EgressApplyError
|
||||
from bot_bottle.backend.docker.egress_apply import applicator
|
||||
|
||||
@@ -67,14 +67,8 @@ class TestValidateRoutesContent(unittest.TestCase):
|
||||
class TestApplyRoutesChange(unittest.TestCase):
|
||||
def setUp(self):
|
||||
self._tmp = tempfile.TemporaryDirectory(prefix="egress-apply-test.")
|
||||
original = supervise.bot_bottle_root
|
||||
|
||||
def fake_root() -> Path:
|
||||
return Path(self._tmp.name) / ".bot-bottle"
|
||||
|
||||
supervise.bot_bottle_root = fake_root # type: ignore[assignment]
|
||||
self.addCleanup(lambda: setattr(supervise, "bot_bottle_root", original))
|
||||
self.addCleanup(self._tmp.cleanup)
|
||||
self.addCleanup(use_bottle_root(Path(self._tmp.name) / ".bot-bottle"))
|
||||
|
||||
def test_writes_live_routes_and_signals_reload(self):
|
||||
calls: list[list[str]] = []
|
||||
|
||||
@@ -67,10 +67,24 @@ class TestNetpoolRenderers(unittest.TestCase):
|
||||
self.assertNotIn("networking.nftables.enable = true", mod)
|
||||
self.assertNotIn("systemd.network.enable = true", mod)
|
||||
self.assertIn("bot-bottle-firecracker-netpool", mod) # the oneshot
|
||||
self.assertIn(netpool.NFT_TABLE, mod)
|
||||
self.assertIn('iifname != "${cfg.ifacePrefix}*" return', mod)
|
||||
# Supports group-owned TAPs (shared pool for a multi-user host).
|
||||
self.assertIn("group ${cfg.group}", mod)
|
||||
self.assertIn("BOT_BOTTLE_FC_GROUP", mod)
|
||||
|
||||
def test_nixos_module_delegates_and_holds_no_literals(self):
|
||||
# Single-source discipline: the module must NOT re-implement the
|
||||
# bring-up (it delegates to the shared script) and must NOT hard-
|
||||
# code the pool defaults (it readFile-parses the shared .env), so
|
||||
# nothing can drift from netpool.py / the shell script.
|
||||
root = Path(__file__).resolve().parents[2]
|
||||
mod = (root / "nix" / "firecracker-netpool.nix").read_text()
|
||||
# Delegation to the one bring-up implementation + shared defaults.
|
||||
self.assertIn("scripts/firecracker-netpool.sh", mod)
|
||||
self.assertIn("netpool.defaults.env", mod)
|
||||
self.assertIn("BOT_BOTTLE_FC_NFT_TABLE", mod)
|
||||
# No duplicated literals or nft ruleset.
|
||||
self.assertNotIn(netpool.ip_base(), mod) # 10.243.0.0
|
||||
self.assertNotIn(netpool.NFT_TABLE, mod) # bot_bottle_fc
|
||||
self.assertNotIn("ct status dnat", mod) # the nft ruleset
|
||||
|
||||
def test_shell_setup_reflects_overrides(self):
|
||||
with patch.dict(os.environ, {"BOT_BOTTLE_FC_POOL_SIZE": "3"}):
|
||||
@@ -262,26 +276,43 @@ class TestBottleAgentArgv(unittest.TestCase):
|
||||
self.assertIn("USER=node", argv)
|
||||
|
||||
|
||||
class TestSetupScriptConsistency(unittest.TestCase):
|
||||
"""The shell setup script duplicates the pool defaults; keep them in
|
||||
lockstep with the Python constants so the two setup paths agree."""
|
||||
class TestNetpoolDefaultsSingleSource(unittest.TestCase):
|
||||
"""The pool defaults live in one shared file (netpool.defaults.env);
|
||||
Python parses it and the shell script + Nix module read the same file,
|
||||
so the three setup paths can't drift."""
|
||||
|
||||
def _script(self) -> str:
|
||||
root = Path(__file__).resolve().parent.parent.parent
|
||||
return (root / "scripts" / "firecracker-netpool.sh").read_text()
|
||||
def _root(self) -> Path:
|
||||
return Path(__file__).resolve().parents[2]
|
||||
|
||||
def test_defaults_match_python(self):
|
||||
script = self._script()
|
||||
def _shared_defaults(self) -> dict[str, str]:
|
||||
text = netpool.DEFAULTS_FILE.read_text()
|
||||
out: dict[str, str] = {}
|
||||
for raw in text.splitlines():
|
||||
line = raw.strip()
|
||||
if line and not line.startswith("#") and "=" in line:
|
||||
k, _, v = line.partition("=")
|
||||
out[k.strip()] = v.strip()
|
||||
return out
|
||||
|
||||
def test_python_reads_the_shared_file(self):
|
||||
d = self._shared_defaults()
|
||||
with patch.dict(os.environ, {}, clear=True):
|
||||
self.assertIn(f'POOL_SIZE:-{netpool.pool_size()}', script)
|
||||
self.assertIn(f'BOT_BOTTLE_FC_IP_BASE:-{netpool.ip_base()}', script)
|
||||
self.assertIn(f'IFACE_PREFIX:-{netpool.IFACE_PREFIX}', script)
|
||||
self.assertEqual(int(d["BOT_BOTTLE_FC_POOL_SIZE"]), netpool.pool_size())
|
||||
self.assertEqual(d["BOT_BOTTLE_FC_IP_BASE"], netpool.ip_base())
|
||||
# Module constants resolve through the same shared file.
|
||||
self.assertEqual(d["BOT_BOTTLE_FC_IFACE_PREFIX"], netpool.IFACE_PREFIX)
|
||||
self.assertEqual(d["BOT_BOTTLE_FC_NFT_TABLE"], netpool.NFT_TABLE)
|
||||
|
||||
def test_table_name_and_ports_match(self):
|
||||
script = self._script()
|
||||
self.assertIn(f'TABLE="{netpool.NFT_TABLE}"', script)
|
||||
for port in netpool.SIDECAR_PORTS:
|
||||
self.assertIn(str(port), script)
|
||||
def test_env_var_overrides_the_shared_default(self):
|
||||
with patch.dict(os.environ, {"BOT_BOTTLE_FC_IP_BASE": "10.99.0.0"}):
|
||||
self.assertEqual("10.99.0.0", netpool.ip_base())
|
||||
|
||||
def test_script_defers_to_shared_file_without_literals(self):
|
||||
script = (self._root() / "scripts" / "firecracker-netpool.sh").read_text()
|
||||
# Delegates its defaults to the shared file, not hardcoded values.
|
||||
self.assertIn("netpool.defaults.env", script)
|
||||
self.assertIn("BOT_BOTTLE_FC_POOL_SIZE:-$(_default BOT_BOTTLE_FC_POOL_SIZE)", script)
|
||||
self.assertIn('TABLE="${BOT_BOTTLE_FC_NFT_TABLE:-$(_default BOT_BOTTLE_FC_NFT_TABLE)}"', script)
|
||||
|
||||
|
||||
class TestBootArgs(unittest.TestCase):
|
||||
|
||||
@@ -0,0 +1,86 @@
|
||||
"""Unit tests for the orchestrator launch broker (PRD 0070)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import secrets
|
||||
import unittest
|
||||
|
||||
from bot_bottle.orchestrator.broker import (
|
||||
BrokerAuthError,
|
||||
LaunchRequest,
|
||||
StubBroker,
|
||||
sign_request,
|
||||
verify_request,
|
||||
)
|
||||
|
||||
|
||||
class TestSignVerify(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.secret = secrets.token_bytes(16)
|
||||
|
||||
def test_launch_round_trip(self) -> None:
|
||||
req = LaunchRequest(
|
||||
op="launch", bottle_id="b1", source_ip="10.243.0.1",
|
||||
image_ref="sha256:abc", slot=3,
|
||||
)
|
||||
self.assertEqual(req, verify_request(sign_request(req, self.secret), self.secret))
|
||||
|
||||
def test_teardown_round_trip(self) -> None:
|
||||
req = LaunchRequest(op="teardown", bottle_id="b1")
|
||||
got = verify_request(sign_request(req, self.secret), self.secret)
|
||||
self.assertEqual(("teardown", "b1"), (got.op, got.bottle_id))
|
||||
|
||||
def test_wrong_secret_rejected(self) -> None:
|
||||
token = sign_request(LaunchRequest(op="launch", bottle_id="b1"), self.secret)
|
||||
with self.assertRaises(BrokerAuthError):
|
||||
verify_request(token, secrets.token_bytes(16))
|
||||
|
||||
def test_tampered_payload_rejected(self) -> None:
|
||||
token = sign_request(LaunchRequest(op="launch", bottle_id="b1"), self.secret)
|
||||
header, payload, sig = token.split(".")
|
||||
flipped = payload[:-1] + ("A" if payload[-1] != "A" else "B")
|
||||
with self.assertRaises(BrokerAuthError):
|
||||
verify_request(f"{header}.{flipped}.{sig}", self.secret)
|
||||
|
||||
def test_malformed_tokens_rejected(self) -> None:
|
||||
for bad in ("", "a.b", "a.b.c.d", "not-a-token"):
|
||||
with self.assertRaises(BrokerAuthError):
|
||||
verify_request(bad, self.secret)
|
||||
|
||||
def test_unknown_op_rejected_despite_valid_signature(self) -> None:
|
||||
# A correctly-signed token whose op isn't in the allow-list must
|
||||
# still be refused — the schema guard is independent of provenance.
|
||||
token = sign_request(LaunchRequest(op="rm-rf", bottle_id="b1"), self.secret)
|
||||
with self.assertRaises(BrokerAuthError):
|
||||
verify_request(token, self.secret)
|
||||
|
||||
|
||||
class TestStubBroker(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.secret = secrets.token_bytes(16)
|
||||
self.broker = StubBroker(self.secret)
|
||||
|
||||
def test_submit_launch_records_verified_request(self) -> None:
|
||||
req = LaunchRequest(op="launch", bottle_id="b1", source_ip="10.243.0.1")
|
||||
got = self.broker.submit(sign_request(req, self.secret))
|
||||
self.assertEqual(req, got)
|
||||
self.assertEqual(["b1"], [r.bottle_id for r in self.broker.launched])
|
||||
self.assertEqual([], self.broker.torn_down)
|
||||
|
||||
def test_submit_teardown_records(self) -> None:
|
||||
self.broker.submit(
|
||||
sign_request(LaunchRequest(op="teardown", bottle_id="b1"), self.secret)
|
||||
)
|
||||
self.assertEqual(["b1"], [r.bottle_id for r in self.broker.torn_down])
|
||||
|
||||
def test_submit_forged_token_is_fail_closed(self) -> None:
|
||||
forged = sign_request(
|
||||
LaunchRequest(op="launch", bottle_id="b1"), secrets.token_bytes(16)
|
||||
)
|
||||
with self.assertRaises(BrokerAuthError):
|
||||
self.broker.submit(forged)
|
||||
self.assertEqual([], self.broker.launched) # nothing acted on
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,163 @@
|
||||
"""Unit tests for the orchestrator HTTP control plane (PRD 0070).
|
||||
|
||||
Mostly exercises the pure `dispatch()` (socket-free, like the supervise
|
||||
server tests), plus one real-socket round-trip to prove the handler wiring.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import secrets
|
||||
import tempfile
|
||||
import threading
|
||||
import unittest
|
||||
import urllib.request
|
||||
from pathlib import Path
|
||||
|
||||
from bot_bottle.orchestrator.broker import StubBroker
|
||||
from bot_bottle.orchestrator.control_plane import dispatch, make_server
|
||||
from bot_bottle.orchestrator.registry import RegistryStore
|
||||
from bot_bottle.orchestrator.service import Orchestrator
|
||||
|
||||
|
||||
def _body(obj: object) -> bytes:
|
||||
return json.dumps(obj).encode()
|
||||
|
||||
|
||||
def _orchestrator(db_path: Path) -> Orchestrator:
|
||||
store = RegistryStore(db_path)
|
||||
store.migrate()
|
||||
secret = secrets.token_bytes(16)
|
||||
return Orchestrator(store, StubBroker(secret), secret)
|
||||
|
||||
|
||||
class TestDispatch(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self._tmp = tempfile.TemporaryDirectory()
|
||||
self.orch = _orchestrator(Path(self._tmp.name) / "r.db")
|
||||
|
||||
def tearDown(self) -> None:
|
||||
self._tmp.cleanup()
|
||||
|
||||
def test_health(self) -> None:
|
||||
status, payload = dispatch(self.orch, "GET", "/health", b"")
|
||||
self.assertEqual(200, status)
|
||||
self.assertEqual("ok", payload["status"])
|
||||
|
||||
def test_register_returns_id_and_token(self) -> None:
|
||||
status, payload = dispatch(
|
||||
self.orch, "POST", "/bottles", _body({"source_ip": "10.243.0.1"})
|
||||
)
|
||||
self.assertEqual(201, status)
|
||||
self.assertTrue(payload["bottle_id"])
|
||||
self.assertTrue(payload["identity_token"])
|
||||
|
||||
def test_register_requires_source_ip(self) -> None:
|
||||
status, _ = dispatch(self.orch, "POST", "/bottles", _body({}))
|
||||
self.assertEqual(400, status)
|
||||
|
||||
def test_register_rejects_bad_json(self) -> None:
|
||||
status, _ = dispatch(self.orch, "POST", "/bottles", b"{not json")
|
||||
self.assertEqual(400, status)
|
||||
|
||||
def test_list_redacts_identity_token(self) -> None:
|
||||
dispatch(self.orch, "POST", "/bottles", _body({"source_ip": "10.243.0.1"}))
|
||||
status, payload = dispatch(self.orch, "GET", "/bottles", b"")
|
||||
self.assertEqual(200, status)
|
||||
bottles = payload["bottles"]
|
||||
assert isinstance(bottles, list)
|
||||
self.assertEqual(1, len(bottles))
|
||||
first = bottles[0]
|
||||
assert isinstance(first, dict)
|
||||
self.assertNotIn("identity_token", first)
|
||||
self.assertEqual("10.243.0.1", first["source_ip"])
|
||||
|
||||
def test_attribute_ok_and_forbidden(self) -> None:
|
||||
_, reg = dispatch(
|
||||
self.orch, "POST", "/bottles", _body({"source_ip": "10.243.0.5"})
|
||||
)
|
||||
token = reg["identity_token"]
|
||||
ok_status, ok = dispatch(
|
||||
self.orch, "POST", "/attribute",
|
||||
_body({"source_ip": "10.243.0.5", "identity_token": token}),
|
||||
)
|
||||
self.assertEqual(200, ok_status)
|
||||
self.assertEqual(reg["bottle_id"], ok["bottle_id"])
|
||||
|
||||
bad_status, _ = dispatch(
|
||||
self.orch, "POST", "/attribute",
|
||||
_body({"source_ip": "10.243.0.5", "identity_token": "nope"}),
|
||||
)
|
||||
self.assertEqual(403, bad_status)
|
||||
|
||||
def test_attribute_requires_both_fields(self) -> None:
|
||||
status, _ = dispatch(
|
||||
self.orch, "POST", "/attribute", _body({"source_ip": "10.243.0.5"})
|
||||
)
|
||||
self.assertEqual(400, status)
|
||||
|
||||
def test_delete(self) -> None:
|
||||
_, reg = dispatch(
|
||||
self.orch, "POST", "/bottles", _body({"source_ip": "10.243.0.1"})
|
||||
)
|
||||
bid = reg["bottle_id"]
|
||||
status, payload = dispatch(self.orch, "DELETE", f"/bottles/{bid}", b"")
|
||||
self.assertEqual(200, status)
|
||||
self.assertEqual(True, payload["torn_down"])
|
||||
self.assertEqual([], self.orch.registry.all())
|
||||
|
||||
def test_delete_missing_404(self) -> None:
|
||||
status, _ = dispatch(self.orch, "DELETE", "/bottles/ghost", b"")
|
||||
self.assertEqual(404, status)
|
||||
|
||||
def test_unknown_route_404(self) -> None:
|
||||
status, _ = dispatch(self.orch, "GET", "/nope", b"")
|
||||
self.assertEqual(404, status)
|
||||
|
||||
def test_trailing_slash_normalized(self) -> None:
|
||||
status, _ = dispatch(self.orch, "GET", "/health/", b"")
|
||||
self.assertEqual(200, status)
|
||||
|
||||
def test_sidecar_status_unconfigured(self) -> None:
|
||||
status, payload = dispatch(self.orch, "GET", "/sidecar", b"")
|
||||
self.assertEqual(200, status)
|
||||
self.assertEqual(False, payload["configured"])
|
||||
|
||||
|
||||
class TestServerRoundTrip(unittest.TestCase):
|
||||
def test_http_register_health_attribute(self) -> None:
|
||||
tmp = tempfile.TemporaryDirectory()
|
||||
self.addCleanup(tmp.cleanup)
|
||||
orch = _orchestrator(Path(tmp.name) / "r.db")
|
||||
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]
|
||||
base = f"http://{host}:{port}"
|
||||
|
||||
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"},
|
||||
), timeout=5,
|
||||
))
|
||||
self.assertTrue(reg["bottle_id"])
|
||||
|
||||
health = json.load(urllib.request.urlopen(f"{base}/health", timeout=5))
|
||||
self.assertEqual("ok", health["status"])
|
||||
|
||||
attr = json.load(urllib.request.urlopen(
|
||||
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"},
|
||||
), timeout=5,
|
||||
))
|
||||
self.assertEqual(reg["bottle_id"], attr["bottle_id"])
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,100 @@
|
||||
"""Unit tests for the Docker launch broker (PRD 0070). Docker is mocked."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import secrets
|
||||
import unittest
|
||||
from unittest.mock import Mock, patch
|
||||
|
||||
from bot_bottle.orchestrator.broker import (
|
||||
BrokerAuthError,
|
||||
LaunchRequest,
|
||||
sign_request,
|
||||
)
|
||||
from bot_bottle.orchestrator.docker_broker import (
|
||||
BOTTLE_ID_LABEL,
|
||||
DockerBroker,
|
||||
DockerBrokerError,
|
||||
container_name,
|
||||
rm_argv,
|
||||
run_argv,
|
||||
)
|
||||
|
||||
|
||||
class TestArgv(unittest.TestCase):
|
||||
def test_run_argv_uses_only_static_fields(self) -> None:
|
||||
req = LaunchRequest(op="launch", bottle_id="b1", image_ref="busybox")
|
||||
argv = run_argv(req)
|
||||
self.assertEqual(["docker", "run"], argv[:2])
|
||||
self.assertIn("--name", argv)
|
||||
self.assertIn(container_name("b1"), argv)
|
||||
self.assertIn(f"{BOTTLE_ID_LABEL}=b1", argv)
|
||||
self.assertEqual("busybox", argv[-1]) # image is the terminal arg
|
||||
|
||||
def test_rm_argv(self) -> None:
|
||||
req = LaunchRequest(op="teardown", bottle_id="b1")
|
||||
self.assertEqual(["docker", "rm", "--force", container_name("b1")], rm_argv(req))
|
||||
|
||||
def test_container_name_is_prefixed(self) -> None:
|
||||
name = container_name("b1")
|
||||
self.assertTrue(name.startswith("bot-bottle-orch-"))
|
||||
self.assertTrue(name.endswith("b1"))
|
||||
|
||||
|
||||
class TestDockerBroker(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.secret = secrets.token_bytes(16)
|
||||
self.broker = DockerBroker(self.secret)
|
||||
|
||||
def _submit(self, req: LaunchRequest) -> None:
|
||||
self.broker.submit(sign_request(req, self.secret))
|
||||
|
||||
def test_launch_invokes_docker_run(self) -> None:
|
||||
req = LaunchRequest(op="launch", bottle_id="b1", image_ref="busybox")
|
||||
with patch.object(self.broker, "_docker", return_value=Mock(returncode=0, stderr="")) as m:
|
||||
self._submit(req)
|
||||
m.assert_called_once()
|
||||
self.assertEqual(run_argv(req), m.call_args.args[0])
|
||||
|
||||
def test_launch_without_image_raises_and_skips_docker(self) -> None:
|
||||
req = LaunchRequest(op="launch", bottle_id="b1", image_ref="")
|
||||
with patch.object(self.broker, "_docker") as m:
|
||||
with self.assertRaises(DockerBrokerError):
|
||||
self._submit(req)
|
||||
m.assert_not_called()
|
||||
|
||||
def test_launch_docker_failure_raises(self) -> None:
|
||||
req = LaunchRequest(op="launch", bottle_id="b1", image_ref="busybox")
|
||||
with patch.object(self.broker, "_docker", return_value=Mock(returncode=1, stderr="boom")):
|
||||
with self.assertRaises(DockerBrokerError):
|
||||
self._submit(req)
|
||||
|
||||
def test_teardown_invokes_docker_rm(self) -> None:
|
||||
req = LaunchRequest(op="teardown", bottle_id="b1")
|
||||
with patch.object(self.broker, "_docker", return_value=Mock(returncode=0, stderr="")) as m:
|
||||
self._submit(req)
|
||||
self.assertEqual(rm_argv(req), m.call_args.args[0])
|
||||
|
||||
def test_teardown_is_idempotent_on_missing_container(self) -> None:
|
||||
req = LaunchRequest(op="teardown", bottle_id="b1")
|
||||
absent = Mock(returncode=1, stderr="Error: No such container: bot-bottle-orch-b1")
|
||||
with patch.object(self.broker, "_docker", return_value=absent):
|
||||
self._submit(req) # must not raise
|
||||
|
||||
def test_teardown_other_failure_raises(self) -> None:
|
||||
req = LaunchRequest(op="teardown", bottle_id="b1")
|
||||
with patch.object(self.broker, "_docker", return_value=Mock(returncode=1, stderr="daemon down")):
|
||||
with self.assertRaises(DockerBrokerError):
|
||||
self._submit(req)
|
||||
|
||||
def test_forged_token_never_touches_docker(self) -> None:
|
||||
req = LaunchRequest(op="launch", bottle_id="b1", image_ref="busybox")
|
||||
forged = sign_request(req, secrets.token_bytes(16))
|
||||
with patch.object(self.broker, "_docker") as m:
|
||||
with self.assertRaises(BrokerAuthError):
|
||||
self.broker.submit(forged)
|
||||
m.assert_not_called()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,102 @@
|
||||
"""Unit tests for the orchestrator bottle registry + attribution (PRD 0070)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
from bot_bottle.orchestrator.registry import (
|
||||
BottleRecord,
|
||||
RegistryStore,
|
||||
new_identity_token,
|
||||
)
|
||||
|
||||
|
||||
class TestRegistryStore(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self._tmp = tempfile.TemporaryDirectory()
|
||||
self.db = Path(self._tmp.name) / "registry.db"
|
||||
self.store = RegistryStore(self.db)
|
||||
self.store.migrate()
|
||||
|
||||
def tearDown(self) -> None:
|
||||
self._tmp.cleanup()
|
||||
|
||||
def test_register_mints_id_and_token(self) -> None:
|
||||
rec = self.store.register("10.243.0.1")
|
||||
self.assertTrue(rec.bottle_id)
|
||||
self.assertTrue(rec.identity_token)
|
||||
self.assertEqual("active", rec.state)
|
||||
self.assertEqual(rec, self.store.get(rec.bottle_id))
|
||||
|
||||
def test_identity_tokens_are_unique(self) -> None:
|
||||
tokens = {new_identity_token() for _ in range(200)}
|
||||
self.assertEqual(200, len(tokens))
|
||||
a = self.store.register("10.243.0.1")
|
||||
b = self.store.register("10.243.0.3")
|
||||
self.assertNotEqual(a.identity_token, b.identity_token)
|
||||
|
||||
def test_all_and_deregister(self) -> None:
|
||||
a = self.store.register("10.243.0.1")
|
||||
b = self.store.register("10.243.0.3")
|
||||
self.assertEqual({a.bottle_id, b.bottle_id}, {r.bottle_id for r in self.store.all()})
|
||||
self.assertTrue(self.store.deregister(a.bottle_id))
|
||||
self.assertEqual([b.bottle_id], [r.bottle_id for r in self.store.all()])
|
||||
|
||||
def test_deregister_missing_is_false(self) -> None:
|
||||
self.assertFalse(self.store.deregister("nope"))
|
||||
|
||||
def test_explicit_id_replaces(self) -> None:
|
||||
self.store.register("10.243.0.1", bottle_id="fixed", metadata="a")
|
||||
self.store.register("10.243.0.9", bottle_id="fixed", metadata="b")
|
||||
rec = self.store.get("fixed")
|
||||
assert rec is not None
|
||||
self.assertEqual("10.243.0.9", rec.source_ip)
|
||||
self.assertEqual("b", rec.metadata)
|
||||
self.assertEqual(1, len(self.store.all()))
|
||||
|
||||
def test_attribute_success_requires_ip_and_token(self) -> None:
|
||||
rec = self.store.register("10.243.0.1")
|
||||
got = self.store.attribute("10.243.0.1", rec.identity_token)
|
||||
assert got is not None
|
||||
self.assertEqual(rec.bottle_id, got.bottle_id)
|
||||
|
||||
def test_attribute_wrong_token_denied(self) -> None:
|
||||
self.store.register("10.243.0.1")
|
||||
self.assertIsNone(self.store.attribute("10.243.0.1", "wrong-token"))
|
||||
|
||||
def test_attribute_unknown_ip_denied(self) -> None:
|
||||
rec = self.store.register("10.243.0.1")
|
||||
self.assertIsNone(self.store.attribute("10.243.9.9", rec.identity_token))
|
||||
|
||||
def test_attribute_empty_token_denied(self) -> None:
|
||||
self.store.register("10.243.0.1")
|
||||
self.assertIsNone(self.store.attribute("10.243.0.1", ""))
|
||||
|
||||
def test_attribute_ambiguous_ip_denied(self) -> None:
|
||||
# Two active bottles on one source IP is a misconfiguration — deny
|
||||
# rather than guess (fail-closed), even with a valid token.
|
||||
a = self.store.register("10.243.0.1", bottle_id="a")
|
||||
self.store.register("10.243.0.1", bottle_id="b")
|
||||
self.assertIsNone(self.store.attribute("10.243.0.1", a.identity_token))
|
||||
|
||||
def test_state_persists_across_reopen(self) -> None:
|
||||
rec = self.store.register("10.243.0.1")
|
||||
reopened = RegistryStore(self.db)
|
||||
got = reopened.get(rec.bottle_id)
|
||||
assert got is not None
|
||||
self.assertEqual(rec, got)
|
||||
# Attribution works against the reopened (durable) store too.
|
||||
self.assertIsNotNone(reopened.attribute("10.243.0.1", rec.identity_token))
|
||||
|
||||
def test_redacted_hides_token(self) -> None:
|
||||
rec = BottleRecord(
|
||||
bottle_id="x", source_ip="10.243.0.1", identity_token="secret"
|
||||
)
|
||||
self.assertNotIn("identity_token", rec.redacted())
|
||||
self.assertEqual("10.243.0.1", rec.redacted()["source_ip"])
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,111 @@
|
||||
"""Unit tests for the Orchestrator launch lifecycle (PRD 0070)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import secrets
|
||||
import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
from bot_bottle.orchestrator.broker import LaunchBroker, LaunchRequest, StubBroker
|
||||
from bot_bottle.orchestrator.registry import RegistryStore
|
||||
from bot_bottle.orchestrator.service import Orchestrator
|
||||
from bot_bottle.orchestrator.sidecar import Sidecar
|
||||
|
||||
|
||||
class _FailingBroker(LaunchBroker):
|
||||
"""Verifies the token like any broker, then fails the launch — to
|
||||
exercise the orchestrator's registry rollback."""
|
||||
|
||||
def _launch(self, req: LaunchRequest) -> None:
|
||||
raise RuntimeError("launch failed")
|
||||
|
||||
def _teardown(self, req: LaunchRequest) -> None:
|
||||
pass
|
||||
|
||||
|
||||
class _FakeSidecar(Sidecar):
|
||||
"""In-memory sidecar for wiring tests."""
|
||||
|
||||
def __init__(self) -> None:
|
||||
self.name = "fake-sidecar"
|
||||
self.ensured = 0
|
||||
self._running = False
|
||||
|
||||
def ensure_running(self) -> None:
|
||||
self.ensured += 1
|
||||
self._running = True
|
||||
|
||||
def is_running(self) -> bool:
|
||||
return self._running
|
||||
|
||||
def stop(self) -> None:
|
||||
self._running = False
|
||||
|
||||
|
||||
class TestOrchestrator(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self._tmp = tempfile.TemporaryDirectory()
|
||||
self.secret = secrets.token_bytes(16)
|
||||
self.store = RegistryStore(Path(self._tmp.name) / "r.db")
|
||||
self.store.migrate()
|
||||
self.broker = StubBroker(self.secret)
|
||||
self.orch = Orchestrator(self.store, self.broker, self.secret)
|
||||
|
||||
def tearDown(self) -> None:
|
||||
self._tmp.cleanup()
|
||||
|
||||
def test_launch_registers_and_brokers_signed_request(self) -> None:
|
||||
rec = self.orch.launch_bottle("10.243.0.1", image_ref="sha256:abc", slot=2)
|
||||
self.assertIsNotNone(self.store.get(rec.bottle_id))
|
||||
self.assertEqual(1, len(self.broker.launched))
|
||||
req = self.broker.launched[0]
|
||||
self.assertEqual("launch", req.op)
|
||||
self.assertEqual(rec.bottle_id, req.bottle_id)
|
||||
self.assertEqual("10.243.0.1", req.source_ip)
|
||||
self.assertEqual("sha256:abc", req.image_ref)
|
||||
self.assertEqual(2, req.slot)
|
||||
|
||||
def test_launch_then_attribute(self) -> None:
|
||||
rec = self.orch.launch_bottle("10.243.0.3")
|
||||
got = self.orch.attribute("10.243.0.3", rec.identity_token)
|
||||
assert got is not None
|
||||
self.assertEqual(rec.bottle_id, got.bottle_id)
|
||||
self.assertIsNone(self.orch.attribute("10.243.0.3", "wrong-token"))
|
||||
|
||||
def test_teardown_brokers_and_deregisters(self) -> None:
|
||||
rec = self.orch.launch_bottle("10.243.0.1")
|
||||
self.assertTrue(self.orch.teardown_bottle(rec.bottle_id))
|
||||
self.assertIsNone(self.store.get(rec.bottle_id))
|
||||
self.assertEqual(["teardown"], [r.op for r in self.broker.torn_down])
|
||||
|
||||
def test_teardown_unknown_is_false(self) -> None:
|
||||
self.assertFalse(self.orch.teardown_bottle("ghost"))
|
||||
|
||||
def test_launch_rolls_back_registry_on_broker_failure(self) -> None:
|
||||
orch = Orchestrator(self.store, _FailingBroker(self.secret), self.secret)
|
||||
with self.assertRaises(RuntimeError):
|
||||
orch.launch_bottle("10.243.0.9")
|
||||
self.assertEqual([], self.store.all()) # no orphan
|
||||
|
||||
def test_sidecar_unconfigured_by_default(self) -> None:
|
||||
self.assertEqual({"configured": False}, self.orch.sidecar_status())
|
||||
self.orch.ensure_sidecar() # no-op, must not raise
|
||||
|
||||
def test_sidecar_wired_and_ensured(self) -> None:
|
||||
sc = _FakeSidecar()
|
||||
orch = Orchestrator(self.store, self.broker, self.secret, sidecar=sc)
|
||||
self.assertEqual(
|
||||
{"configured": True, "name": "fake-sidecar", "running": False},
|
||||
orch.sidecar_status(),
|
||||
)
|
||||
orch.ensure_sidecar()
|
||||
self.assertEqual(1, sc.ensured)
|
||||
self.assertEqual(
|
||||
{"configured": True, "name": "fake-sidecar", "running": True},
|
||||
orch.sidecar_status(),
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,79 @@
|
||||
"""Unit tests for the consolidated Docker sidecar (PRD 0070). Docker mocked."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import unittest
|
||||
from unittest.mock import Mock, patch
|
||||
|
||||
from bot_bottle.orchestrator.sidecar import (
|
||||
SIDECAR_NAME,
|
||||
DockerSidecar,
|
||||
SidecarError,
|
||||
)
|
||||
|
||||
_RUN_DOCKER = "bot_bottle.orchestrator.sidecar.run_docker"
|
||||
|
||||
|
||||
def _proc(returncode: int = 0, stdout: str = "", stderr: str = "") -> Mock:
|
||||
return Mock(returncode=returncode, stdout=stdout, stderr=stderr)
|
||||
|
||||
|
||||
class TestDockerSidecar(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.sc = DockerSidecar("bot-bottle-sidecars:latest")
|
||||
|
||||
def test_default_name(self) -> None:
|
||||
self.assertEqual(SIDECAR_NAME, self.sc.name)
|
||||
|
||||
def test_is_running_reads_docker_ps(self) -> None:
|
||||
with patch(_RUN_DOCKER, return_value=_proc(stdout=self.sc.name + "\n")):
|
||||
self.assertTrue(self.sc.is_running())
|
||||
with patch(_RUN_DOCKER, return_value=_proc(stdout="")):
|
||||
self.assertFalse(self.sc.is_running())
|
||||
|
||||
def test_ensure_running_is_noop_when_already_up(self) -> None:
|
||||
with patch(_RUN_DOCKER, return_value=_proc(stdout=self.sc.name)) as m:
|
||||
self.sc.ensure_running()
|
||||
# Only the is_running() ps probe — no rm / run.
|
||||
self.assertEqual(1, m.call_count)
|
||||
|
||||
def test_ensure_running_starts_the_singleton_when_absent(self) -> None:
|
||||
calls: list[list[str]] = []
|
||||
|
||||
def fake(argv: list[str]) -> Mock:
|
||||
calls.append(argv)
|
||||
return _proc(stdout="") if argv[:2] == ["docker", "ps"] else _proc()
|
||||
|
||||
with patch(_RUN_DOCKER, side_effect=fake):
|
||||
self.sc.ensure_running()
|
||||
|
||||
runs = [c for c in calls if c[:2] == ["docker", "run"]]
|
||||
self.assertEqual(1, len(runs))
|
||||
self.assertIn(self.sc.name, runs[0])
|
||||
self.assertIn("bot-bottle-sidecars:latest", runs[0])
|
||||
|
||||
def test_ensure_running_raises_on_docker_failure(self) -> None:
|
||||
def fake(argv: list[str]) -> Mock:
|
||||
if argv[:2] == ["docker", "ps"]:
|
||||
return _proc(stdout="")
|
||||
if argv[:2] == ["docker", "run"]:
|
||||
return _proc(returncode=1, stderr="boom")
|
||||
return _proc()
|
||||
|
||||
with patch(_RUN_DOCKER, side_effect=fake):
|
||||
with self.assertRaises(SidecarError):
|
||||
self.sc.ensure_running()
|
||||
|
||||
def test_stop_is_idempotent_on_missing(self) -> None:
|
||||
absent = _proc(returncode=1, stderr="Error: No such container: x")
|
||||
with patch(_RUN_DOCKER, return_value=absent):
|
||||
self.sc.stop() # must not raise
|
||||
|
||||
def test_stop_raises_on_other_failure(self) -> None:
|
||||
with patch(_RUN_DOCKER, return_value=_proc(returncode=1, stderr="daemon down")):
|
||||
with self.assertRaises(SidecarError):
|
||||
self.sc.stop()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -8,7 +8,8 @@ from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
|
||||
from bot_bottle import supervise
|
||||
from bot_bottle import supervise_types as sv_types
|
||||
from bot_bottle.paths import host_db_path
|
||||
from tests.unit import use_bottle_root
|
||||
from bot_bottle.audit_store import AuditStore
|
||||
from bot_bottle.queue_store import QueueStore
|
||||
from bot_bottle.supervise import (
|
||||
@@ -21,7 +22,6 @@ from bot_bottle.supervise import (
|
||||
TOOL_EGRESS_ALLOW,
|
||||
TOOL_GITLEAKS_ALLOW,
|
||||
archive_proposal,
|
||||
host_db_path,
|
||||
list_pending_proposals,
|
||||
read_audit_entries,
|
||||
read_proposal,
|
||||
@@ -123,20 +123,7 @@ class TestQueueIO(unittest.TestCase):
|
||||
self._tmp.cleanup()
|
||||
|
||||
def _patch_home(self, fake_home: Path):
|
||||
original_sv = supervise.bot_bottle_root
|
||||
original_svt = sv_types.bot_bottle_root
|
||||
|
||||
def fake_root() -> Path:
|
||||
return fake_home / ".bot-bottle"
|
||||
|
||||
supervise.bot_bottle_root = fake_root # type: ignore[assignment]
|
||||
sv_types.bot_bottle_root = fake_root # type: ignore[assignment]
|
||||
|
||||
def restore() -> None:
|
||||
supervise.bot_bottle_root = original_sv # type: ignore[assignment]
|
||||
sv_types.bot_bottle_root = original_svt # type: ignore[assignment]
|
||||
|
||||
return restore
|
||||
return use_bottle_root(fake_home / ".bot-bottle")
|
||||
|
||||
def test_write_and_read_proposal(self):
|
||||
p = _proposal()
|
||||
@@ -240,20 +227,7 @@ class TestAuditLog(unittest.TestCase):
|
||||
self._tmp.cleanup()
|
||||
|
||||
def _patch_home(self, fake_home: Path):
|
||||
original_sv = supervise.bot_bottle_root
|
||||
original_svt = sv_types.bot_bottle_root
|
||||
|
||||
def fake_root() -> Path:
|
||||
return fake_home / ".bot-bottle"
|
||||
|
||||
supervise.bot_bottle_root = fake_root # type: ignore[assignment]
|
||||
sv_types.bot_bottle_root = fake_root # type: ignore[assignment]
|
||||
|
||||
def restore() -> None:
|
||||
supervise.bot_bottle_root = original_sv # type: ignore[assignment]
|
||||
sv_types.bot_bottle_root = original_svt # type: ignore[assignment]
|
||||
|
||||
return restore
|
||||
return use_bottle_root(fake_home / ".bot-bottle")
|
||||
|
||||
def test_write_then_read_single_entry(self):
|
||||
e = AuditEntry(
|
||||
@@ -400,20 +374,7 @@ class TestSupervisePrepare(unittest.TestCase):
|
||||
self._tmp.cleanup()
|
||||
|
||||
def _patch_home(self, fake_home: Path):
|
||||
original_sv = supervise.bot_bottle_root
|
||||
original_svt = sv_types.bot_bottle_root
|
||||
|
||||
def fake_root() -> Path:
|
||||
return fake_home / ".bot-bottle"
|
||||
|
||||
supervise.bot_bottle_root = fake_root # type: ignore[assignment]
|
||||
sv_types.bot_bottle_root = fake_root # type: ignore[assignment]
|
||||
|
||||
def restore() -> None:
|
||||
supervise.bot_bottle_root = original_sv # type: ignore[assignment]
|
||||
sv_types.bot_bottle_root = original_svt # type: ignore[assignment]
|
||||
|
||||
return restore
|
||||
return use_bottle_root(fake_home / ".bot-bottle")
|
||||
|
||||
def test_prepare_creates_queue(self):
|
||||
plan = _StubSupervise().prepare("dev", self.stage_dir)
|
||||
|
||||
@@ -12,7 +12,7 @@ from pathlib import Path
|
||||
from unittest.mock import patch
|
||||
|
||||
from bot_bottle import supervise
|
||||
from bot_bottle import supervise_types as sv_types
|
||||
from tests.unit import use_bottle_root
|
||||
from bot_bottle.audit_store import AuditStore
|
||||
from bot_bottle.cli import supervise as supervise_cli
|
||||
from bot_bottle.queue_store import QueueStore
|
||||
@@ -51,24 +51,11 @@ def _proposal(slug: str = "dev", tool: str = TOOL_EGRESS_ALLOW) -> Proposal:
|
||||
|
||||
|
||||
class _FakeHomeMixin:
|
||||
"""Patch supervise.bot_bottle_root to a temp dir for the test."""
|
||||
"""Point bot_bottle_root at a temp dir (via BOT_BOTTLE_ROOT) for the test."""
|
||||
|
||||
def _setup_fake_home(self):
|
||||
self._tmp = tempfile.TemporaryDirectory(prefix="supervise-test.")
|
||||
original_sv = supervise.bot_bottle_root
|
||||
original_svt = sv_types.bot_bottle_root
|
||||
|
||||
def fake_root() -> Path:
|
||||
return Path(self._tmp.name) / ".bot-bottle"
|
||||
|
||||
supervise.bot_bottle_root = fake_root # type: ignore[assignment]
|
||||
sv_types.bot_bottle_root = fake_root # type: ignore[assignment]
|
||||
|
||||
def restore() -> None:
|
||||
supervise.bot_bottle_root = original_sv # type: ignore[assignment]
|
||||
sv_types.bot_bottle_root = original_svt # type: ignore[assignment]
|
||||
|
||||
self._restore_home = restore
|
||||
self._restore_home = use_bottle_root(Path(self._tmp.name) / ".bot-bottle")
|
||||
QueueStore("").migrate()
|
||||
AuditStore().migrate()
|
||||
|
||||
|
||||
@@ -11,12 +11,13 @@ from __future__ import annotations
|
||||
|
||||
import contextlib
|
||||
import io
|
||||
import os
|
||||
import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
from unittest import mock
|
||||
|
||||
from bot_bottle import supervise
|
||||
from tests.unit import use_bottle_root
|
||||
from bot_bottle.cli import supervise as supervise_cli
|
||||
from bot_bottle.log import Die, die
|
||||
|
||||
@@ -39,18 +40,16 @@ class TestDieCarriesMessage(unittest.TestCase):
|
||||
|
||||
|
||||
class _FakeHomeMixin:
|
||||
"""Point supervise.bot_bottle_root (what _write_crash_log resolves
|
||||
through) at a temp dir so the crash log doesn't touch the real
|
||||
~/.bot-bottle."""
|
||||
"""Point bot_bottle_root (what _write_crash_log resolves through) at a
|
||||
temp dir so the crash log doesn't touch the real ~/.bot-bottle."""
|
||||
|
||||
def _setup_fake_home(self):
|
||||
self._tmp = tempfile.TemporaryDirectory(prefix="supervise-crash-test.")
|
||||
self._orig_root = supervise.bot_bottle_root
|
||||
self._root = Path(self._tmp.name) / ".bot-bottle"
|
||||
supervise.bot_bottle_root = lambda: self._root # type: ignore[assignment]
|
||||
self._restore_root = use_bottle_root(self._root)
|
||||
|
||||
def _teardown_fake_home(self):
|
||||
supervise.bot_bottle_root = self._orig_root # type: ignore[assignment]
|
||||
self._restore_root()
|
||||
self._tmp.cleanup()
|
||||
|
||||
|
||||
@@ -127,11 +126,11 @@ class TestWriteCrashLog(_FakeHomeMixin, unittest.TestCase):
|
||||
# OSError and the helper must fall back to a tempfile.
|
||||
bad = Path(self._tmp.name) / "not-a-dir"
|
||||
bad.write_text("x")
|
||||
supervise.bot_bottle_root = lambda: bad # type: ignore[assignment]
|
||||
try:
|
||||
raise RuntimeError("explode2")
|
||||
except RuntimeError as e:
|
||||
path = supervise_cli._write_crash_log(e)
|
||||
with mock.patch.dict(os.environ, {"BOT_BOTTLE_ROOT": str(bad)}):
|
||||
try:
|
||||
raise RuntimeError("explode2")
|
||||
except RuntimeError as e:
|
||||
path = supervise_cli._write_crash_log(e)
|
||||
self.assertTrue(path.exists())
|
||||
self.assertIn("explode2", path.read_text())
|
||||
|
||||
|
||||
@@ -12,6 +12,7 @@ from unittest.mock import patch
|
||||
|
||||
from bot_bottle import supervise
|
||||
from bot_bottle.audit_store import AuditStore
|
||||
from bot_bottle.paths import bot_bottle_root
|
||||
from bot_bottle.queue_store import QueueStore
|
||||
from bot_bottle.supervise import (
|
||||
AuditEntry,
|
||||
@@ -39,7 +40,7 @@ def _proposal() -> Proposal:
|
||||
|
||||
class TestPathHelpers(unittest.TestCase):
|
||||
def test_bot_bottle_root(self) -> None:
|
||||
self.assertTrue(str(supervise.bot_bottle_root()).endswith(".bot-bottle"))
|
||||
self.assertTrue(str(bot_bottle_root()).endswith(".bot-bottle"))
|
||||
|
||||
|
||||
class TestReadMalformed(unittest.TestCase):
|
||||
|
||||
@@ -10,6 +10,8 @@ import unittest
|
||||
from pathlib import Path
|
||||
from unittest.mock import patch
|
||||
|
||||
from tests.unit import use_bottle_root
|
||||
|
||||
|
||||
# The server module loads `supervise` via same-directory import inside
|
||||
# the container (Dockerfile.supervise WORKDIRs into /app). For tests
|
||||
@@ -19,10 +21,8 @@ sys.path.insert(0, str(Path(__file__).resolve().parent.parent.parent / "bot_bott
|
||||
import supervise as _sv # noqa: E402 # type: ignore
|
||||
import queue_store as _qs # noqa: E402 # type: ignore
|
||||
import audit_store as _as # noqa: E402 # type: ignore
|
||||
import supervise_types as svt_flat # noqa: E402 # type: ignore
|
||||
|
||||
from bot_bottle import supervise_server # noqa: E402
|
||||
from bot_bottle import supervise_types as svt_pkg # noqa: E402
|
||||
from bot_bottle.supervise_server import (
|
||||
ERR_INTERNAL,
|
||||
ERR_INVALID_PARAMS,
|
||||
@@ -279,23 +279,7 @@ class TestHandleToolsCall(unittest.TestCase):
|
||||
self._tmp.cleanup()
|
||||
|
||||
def _patch_home(self, fake_home: Path):
|
||||
original_sv = _sv.bot_bottle_root
|
||||
original_flat = svt_flat.bot_bottle_root
|
||||
original_pkg = svt_pkg.bot_bottle_root
|
||||
|
||||
def fake_root() -> Path:
|
||||
return fake_home / ".bot-bottle"
|
||||
|
||||
_sv.bot_bottle_root = fake_root # type: ignore[assignment]
|
||||
svt_flat.bot_bottle_root = fake_root # type: ignore[assignment]
|
||||
svt_pkg.bot_bottle_root = fake_root # type: ignore[assignment]
|
||||
|
||||
def restore() -> None:
|
||||
_sv.bot_bottle_root = original_sv # type: ignore[assignment]
|
||||
svt_flat.bot_bottle_root = original_flat # type: ignore[assignment]
|
||||
svt_pkg.bot_bottle_root = original_pkg # type: ignore[assignment]
|
||||
|
||||
return restore
|
||||
return use_bottle_root(fake_home / ".bot-bottle")
|
||||
|
||||
def _respond_when_proposal_appears(self, status: str, notes: str = "") -> threading.Thread:
|
||||
"""Background thread: poll the queue for a fresh proposal, write a
|
||||
|
||||
Reference in New Issue
Block a user