Compare commits
2 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 32e9bb95e0 | |||
| 8e567edde4 |
@@ -7,45 +7,23 @@ 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.
|
||||
* `service` — the `Orchestrator`: owns the registry, brokers the
|
||||
launch lifecycle (launch/teardown), attributes.
|
||||
* `control_plane` — the HTTP control-plane RPC (launch / teardown /
|
||||
list / attribute / health).
|
||||
* `control_plane` — the HTTP control-plane RPC (register / deregister /
|
||||
list / attribute / health), with live reload.
|
||||
|
||||
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).
|
||||
Launch/teardown, the launch broker, and the actual egress/git/supervise
|
||||
data plane land in later slices once this core is proven (see the PRD's
|
||||
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 .service import Orchestrator
|
||||
from .control_plane import ControlPlaneServer, dispatch, make_server
|
||||
|
||||
__all__ = [
|
||||
"BottleRecord",
|
||||
"RegistryStore",
|
||||
"new_identity_token",
|
||||
"BrokerAuthError",
|
||||
"LaunchBroker",
|
||||
"LaunchRequest",
|
||||
"StubBroker",
|
||||
"sign_request",
|
||||
"verify_request",
|
||||
"Orchestrator",
|
||||
"ControlPlaneServer",
|
||||
"dispatch",
|
||||
"make_server",
|
||||
|
||||
@@ -12,14 +12,11 @@ container packaging. Wrapping this exact service in a backend-native unit
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import secrets
|
||||
from pathlib import Path
|
||||
|
||||
from .. import log
|
||||
from .broker import StubBroker
|
||||
from .control_plane import make_server
|
||||
from .registry import RegistryStore, default_db_path
|
||||
from .service import Orchestrator
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
@@ -36,13 +33,7 @@ def main(argv: list[str] | None = None) -> int:
|
||||
registry = RegistryStore(args.db)
|
||||
registry.migrate()
|
||||
|
||||
# Dev-harness wiring: an ephemeral signing secret + a stub broker that
|
||||
# records launches instead of starting anything. A real backend broker
|
||||
# (docker, then firecracker) drops in here later.
|
||||
secret = secrets.token_bytes(32)
|
||||
orchestrator = Orchestrator(registry, StubBroker(secret), secret)
|
||||
|
||||
server = make_server(orchestrator, host=args.host, port=args.port)
|
||||
server = make_server(registry, host=args.host, port=args.port)
|
||||
bound_host, bound_port = server.server_address[0], server.server_address[1]
|
||||
log.info(
|
||||
"orchestrator control plane listening",
|
||||
|
||||
@@ -1,176 +0,0 @@
|
||||
"""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",
|
||||
]
|
||||
@@ -2,25 +2,23 @@
|
||||
|
||||
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):
|
||||
vsock / unix-socket portability caveats). Endpoints mutate the live
|
||||
registry, so register/deregister are the *live-reload* path — no restart:
|
||||
|
||||
GET /health -> 200 {"status": "ok"}
|
||||
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 /bottles -> 201 {"bottle_id", "identity_token"}
|
||||
body: {"source_ip", ["bottle_id"], ["metadata"]}
|
||||
DELETE /bottles/<bottle_id> -> 200 {"deregistered": true} | 404
|
||||
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.
|
||||
thin stdlib adapter around it.
|
||||
|
||||
Note the listing redacts identity tokens — they are never returned except
|
||||
once, to the caller that registers the bottle.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -32,7 +30,7 @@ import socketserver
|
||||
import typing
|
||||
from urllib.parse import urlsplit
|
||||
|
||||
from .service import Orchestrator
|
||||
from .registry import RegistryStore
|
||||
|
||||
# JSON body payload type (parsed request / rendered response).
|
||||
Json = dict[str, object]
|
||||
@@ -49,17 +47,17 @@ def _parse_json_object(body: bytes) -> Json:
|
||||
|
||||
|
||||
def dispatch( # pylint: disable=too-many-return-statements
|
||||
orch: Orchestrator, method: str, path: str, body: bytes
|
||||
registry: RegistryStore, 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."""
|
||||
no I/O beyond the registry — 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 == "/bottles":
|
||||
return 200, {"bottles": [r.redacted() for r in orch.registry.all()]}
|
||||
return 200, {"bottles": [r.redacted() for r in registry.all()]}
|
||||
|
||||
if method == "POST" and route == "/bottles":
|
||||
try:
|
||||
@@ -69,19 +67,19 @@ def dispatch( # pylint: disable=too-many-return-statements
|
||||
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")
|
||||
bottle_id = data.get("bottle_id")
|
||||
metadata = data.get("metadata")
|
||||
rec = orch.launch_bottle(
|
||||
rec = registry.register(
|
||||
source_ip,
|
||||
image_ref=image_ref if isinstance(image_ref, str) else "",
|
||||
bottle_id=bottle_id if isinstance(bottle_id, str) else None,
|
||||
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}
|
||||
if registry.deregister(bottle_id):
|
||||
return 200, {"deregistered": True}
|
||||
return 404, {"error": "no such bottle"}
|
||||
|
||||
if method == "POST" and route == "/attribute":
|
||||
@@ -93,7 +91,7 @@ def dispatch( # pylint: disable=too-many-return-statements
|
||||
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)
|
||||
rec = registry.attribute(source_ip, token)
|
||||
if rec is None:
|
||||
return 403, {"error": "unattributed"}
|
||||
return 200, {"bottle_id": rec.bottle_id}
|
||||
@@ -116,7 +114,7 @@ class Handler(http.server.BaseHTTPRequestHandler):
|
||||
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)
|
||||
status, payload = dispatch(server.registry, method, self.path, body)
|
||||
data = json.dumps(payload).encode()
|
||||
self.send_response(status)
|
||||
self.send_header("Content-Type", "application/json")
|
||||
@@ -135,22 +133,22 @@ class Handler(http.server.BaseHTTPRequestHandler):
|
||||
|
||||
|
||||
class ControlPlaneServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
|
||||
"""Threading HTTP server that carries the orchestrator for its handlers."""
|
||||
"""Threading HTTP server that carries the registry for its handlers."""
|
||||
|
||||
daemon_threads = True
|
||||
allow_reuse_address = True
|
||||
|
||||
def __init__(self, address: tuple[str, int], orchestrator: Orchestrator) -> None:
|
||||
self.orchestrator = orchestrator
|
||||
def __init__(self, address: tuple[str, int], registry: RegistryStore) -> None:
|
||||
self.registry = registry
|
||||
super().__init__(address, Handler)
|
||||
|
||||
|
||||
def make_server(
|
||||
orchestrator: Orchestrator, host: str = "127.0.0.1", port: int = 0
|
||||
registry: RegistryStore, 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)
|
||||
return ControlPlaneServer((host, port), registry)
|
||||
|
||||
|
||||
__all__ = ["dispatch", "Handler", "ControlPlaneServer", "make_server", "Json"]
|
||||
|
||||
@@ -1,76 +0,0 @@
|
||||
"""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
|
||||
|
||||
|
||||
class Orchestrator:
|
||||
"""Owns the registry + brokers launches. Backend-neutral."""
|
||||
|
||||
def __init__(
|
||||
self, registry: RegistryStore, broker: LaunchBroker, sign_secret: bytes
|
||||
) -> None:
|
||||
self.registry = registry
|
||||
self._broker = broker
|
||||
self._secret = sign_secret
|
||||
|
||||
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)
|
||||
|
||||
|
||||
__all__ = ["Orchestrator"]
|
||||
@@ -325,18 +325,50 @@ orchestrator becomes a VM. Decouple the two risks instead:
|
||||
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):
|
||||
### Slices
|
||||
|
||||
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
|
||||
Built bottom-up as a stack of small PRs off this one (status: **1–5
|
||||
implemented** in #352 → #356 → #357 → #358 → #360):
|
||||
|
||||
1. **Dev-harness core** ✅ — SQLite registry (runtime state) + fail-closed
|
||||
attribution (source IP + identity token) + the HTTP control plane.
|
||||
2. **Launch lifecycle + broker contract** ✅ — `launch_bottle` /
|
||||
`teardown_bottle` + the signed, structured `LaunchBroker` request
|
||||
(HS256 JWT, static ids/flags only, provenance-verified, fail-closed),
|
||||
with a stub broker for the harness and registry rollback on failure.
|
||||
3. **Docker launch broker** ✅ — the first real broker: `docker run` / `rm`
|
||||
per bottle, built only from the request's static fields; proves the
|
||||
`BottleBackend` seam on the cheapest backend.
|
||||
|
||||
**The consolidated-sidecar arc** (the core consolidation win — one
|
||||
persistent sidecar shared by all bottles instead of one per bottle):
|
||||
|
||||
4. **Sidecar — lifecycle** ✅ — the idempotent-singleton `Sidecar` /
|
||||
`DockerSidecar` (ensure-running is a no-op when already up, stop is
|
||||
idempotent); one container per host.
|
||||
5. **Sidecar — build the real bundle image** ✅ — the orchestrator builds
|
||||
the `bot-bottle-sidecars` bundle from `Dockerfile.sidecars` when missing
|
||||
and launches *that* (not a placeholder) as the singleton.
|
||||
6. **Sidecar — source-IP-keyed multi-tenant config** — the functional
|
||||
core: the per-bottle CA / egress routes / git-gate keys / policy, today
|
||||
baked per bottle, become **multi-tenant and selected by the verified
|
||||
source IP**, with per-bottle add/remove (live reload) on launch/teardown
|
||||
through the control plane. Until this lands, one shared instance can't
|
||||
serve multiple bottles' distinct policies.
|
||||
7. **Sidecar — route agent bottles through it** — wire each agent bottle's
|
||||
egress/git to the shared sidecar (DNAT / network) instead of a per-bottle
|
||||
bundle.
|
||||
|
||||
**Remaining backends** (docker done above; the rest against the proven
|
||||
dev-harness):
|
||||
|
||||
8. **Firecracker broker + sidecar** — 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).
|
||||
forward rules where today it drops all non-DNAT egress).
|
||||
9. **macOS (Apple container)** — last (container-to-container networking).
|
||||
|
||||
Keep the sidecar **service one shared thing** throughout.
|
||||
Backends land cheapest-first (docker → firecracker → macOS); keep the
|
||||
sidecar **service one shared thing** throughout.
|
||||
|
||||
## Non-goals
|
||||
|
||||
|
||||
@@ -1,86 +0,0 @@
|
||||
"""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()
|
||||
@@ -7,62 +7,53 @@ 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")
|
||||
self.store = RegistryStore(Path(self._tmp.name) / "r.db")
|
||||
self.store.migrate()
|
||||
|
||||
def tearDown(self) -> None:
|
||||
self._tmp.cleanup()
|
||||
|
||||
def test_health(self) -> None:
|
||||
status, payload = dispatch(self.orch, "GET", "/health", b"")
|
||||
status, payload = dispatch(self.store, "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.store, "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({}))
|
||||
status, _ = dispatch(self.store, "POST", "/bottles", _body({}))
|
||||
self.assertEqual(400, status)
|
||||
|
||||
def test_register_rejects_bad_json(self) -> None:
|
||||
status, _ = dispatch(self.orch, "POST", "/bottles", b"{not json")
|
||||
status, _ = dispatch(self.store, "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"")
|
||||
dispatch(self.store, "POST", "/bottles", _body({"source_ip": "10.243.0.1"}))
|
||||
status, payload = dispatch(self.store, "GET", "/bottles", b"")
|
||||
self.assertEqual(200, status)
|
||||
bottles = payload["bottles"]
|
||||
assert isinstance(bottles, list)
|
||||
@@ -74,48 +65,48 @@ class TestDispatch(unittest.TestCase):
|
||||
|
||||
def test_attribute_ok_and_forbidden(self) -> None:
|
||||
_, reg = dispatch(
|
||||
self.orch, "POST", "/bottles", _body({"source_ip": "10.243.0.5"})
|
||||
self.store, "POST", "/bottles", _body({"source_ip": "10.243.0.5"})
|
||||
)
|
||||
token = reg["identity_token"]
|
||||
ok_status, ok = dispatch(
|
||||
self.orch, "POST", "/attribute",
|
||||
self.store, "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",
|
||||
self.store, "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.store, "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"})
|
||||
self.store, "POST", "/bottles", _body({"source_ip": "10.243.0.1"})
|
||||
)
|
||||
bid = reg["bottle_id"]
|
||||
status, payload = dispatch(self.orch, "DELETE", f"/bottles/{bid}", b"")
|
||||
status, payload = dispatch(self.store, "DELETE", f"/bottles/{bid}", b"")
|
||||
self.assertEqual(200, status)
|
||||
self.assertEqual(True, payload["torn_down"])
|
||||
self.assertEqual([], self.orch.registry.all())
|
||||
self.assertEqual(True, payload["deregistered"])
|
||||
self.assertEqual([], self.store.all())
|
||||
|
||||
def test_delete_missing_404(self) -> None:
|
||||
status, _ = dispatch(self.orch, "DELETE", "/bottles/ghost", b"")
|
||||
status, _ = dispatch(self.store, "DELETE", "/bottles/ghost", b"")
|
||||
self.assertEqual(404, status)
|
||||
|
||||
def test_unknown_route_404(self) -> None:
|
||||
status, _ = dispatch(self.orch, "GET", "/nope", b"")
|
||||
status, _ = dispatch(self.store, "GET", "/nope", b"")
|
||||
self.assertEqual(404, status)
|
||||
|
||||
def test_trailing_slash_normalized(self) -> None:
|
||||
status, _ = dispatch(self.orch, "GET", "/health/", b"")
|
||||
status, _ = dispatch(self.store, "GET", "/health/", b"")
|
||||
self.assertEqual(200, status)
|
||||
|
||||
|
||||
@@ -123,8 +114,9 @@ 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)
|
||||
store = RegistryStore(Path(tmp.name) / "r.db")
|
||||
store.migrate()
|
||||
server = make_server(store, "127.0.0.1", 0)
|
||||
self.addCleanup(server.server_close)
|
||||
thread = threading.Thread(target=server.serve_forever, daemon=True)
|
||||
thread.start()
|
||||
|
||||
@@ -1,73 +0,0 @@
|
||||
"""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
|
||||
|
||||
|
||||
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 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
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
Reference in New Issue
Block a user