feat(orchestrator): slice 2 — launch lifecycle + signed launch-broker (#352)
Second slice of PRD 0070, still a backend-neutral dev-harness:
* orchestrator/broker.py — the launch-broker contract. A LaunchRequest is
structured (static ids/flags only — bottle id, pool slot, a
content-addressed image_ref; never a path/argv) and signed as a compact
HS256 JWT so the broker verifies PROVENANCE before acting: a compromised
co-located component can't forge a launch without the shared secret.
verify_request is fail-closed (bad sig / malformed / off-schema -> raise).
Stdlib only (no runtime deps). Ships a StubBroker that records verified
requests for the harness/tests.
* orchestrator/service.py — the Orchestrator: owns the registry and brokers
the lifecycle. launch_bottle mints the bottle + sends a signed launch,
rolling the registry entry back if the launch fails (no orphans);
teardown_bottle brokers teardown then deregisters; attribute delegates.
* control_plane.py — POST /bottles now launches, DELETE tears down (both go
through the Orchestrator + broker). dispatch/server take an Orchestrator.
* __main__.py wires an ephemeral secret + StubBroker for the harness.
Tests: broker sign/verify round-trip, tamper/wrong-secret/malformed/off-schema
rejection, StubBroker fail-closed; Orchestrator launch->registry->attribute,
teardown, rollback-on-broker-failure; control-plane updated for launch/teardown.
Full suite green (only the pre-existing /bin/sleep errors); harness does
launch -> attribute -> teardown over HTTP.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WBMWTEtQdJ4W5UrWuLHCck
This commit is contained in:
@@ -2,23 +2,25 @@
|
||||
|
||||
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). Endpoints mutate the live
|
||||
registry, so register/deregister are the *live-reload* path — no restart:
|
||||
vsock / unix-socket portability caveats):
|
||||
|
||||
GET /health -> 200 {"status": "ok"}
|
||||
GET /bottles -> 200 {"bottles": [ <redacted record>, ... ]}
|
||||
POST /bottles -> 201 {"bottle_id", "identity_token"}
|
||||
body: {"source_ip", ["bottle_id"], ["metadata"]}
|
||||
DELETE /bottles/<bottle_id> -> 200 {"deregistered": true} | 404
|
||||
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.
|
||||
|
||||
Note the listing redacts identity tokens — they are never returned except
|
||||
once, to the caller that registers the bottle.
|
||||
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
|
||||
@@ -30,7 +32,7 @@ import socketserver
|
||||
import typing
|
||||
from urllib.parse import urlsplit
|
||||
|
||||
from .registry import RegistryStore
|
||||
from .service import Orchestrator
|
||||
|
||||
# JSON body payload type (parsed request / rendered response).
|
||||
Json = dict[str, object]
|
||||
@@ -47,17 +49,17 @@ def _parse_json_object(body: bytes) -> Json:
|
||||
|
||||
|
||||
def dispatch( # pylint: disable=too-many-return-statements
|
||||
registry: RegistryStore, method: str, path: str, body: bytes
|
||||
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 registry — so it is fully testable without a socket."""
|
||||
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 == "/bottles":
|
||||
return 200, {"bottles": [r.redacted() for r in registry.all()]}
|
||||
return 200, {"bottles": [r.redacted() for r in orch.registry.all()]}
|
||||
|
||||
if method == "POST" and route == "/bottles":
|
||||
try:
|
||||
@@ -67,19 +69,19 @@ 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"}
|
||||
bottle_id = data.get("bottle_id")
|
||||
image_ref = data.get("image_ref")
|
||||
metadata = data.get("metadata")
|
||||
rec = registry.register(
|
||||
rec = orch.launch_bottle(
|
||||
source_ip,
|
||||
bottle_id=bottle_id if isinstance(bottle_id, str) else None,
|
||||
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 registry.deregister(bottle_id):
|
||||
return 200, {"deregistered": True}
|
||||
if orch.teardown_bottle(bottle_id):
|
||||
return 200, {"torn_down": True}
|
||||
return 404, {"error": "no such bottle"}
|
||||
|
||||
if method == "POST" and route == "/attribute":
|
||||
@@ -91,7 +93,7 @@ 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 = registry.attribute(source_ip, token)
|
||||
rec = orch.attribute(source_ip, token)
|
||||
if rec is None:
|
||||
return 403, {"error": "unattributed"}
|
||||
return 200, {"bottle_id": rec.bottle_id}
|
||||
@@ -114,7 +116,7 @@ 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.registry, method, self.path, body)
|
||||
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")
|
||||
@@ -133,22 +135,22 @@ class Handler(http.server.BaseHTTPRequestHandler):
|
||||
|
||||
|
||||
class ControlPlaneServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
|
||||
"""Threading HTTP server that carries the registry for its handlers."""
|
||||
"""Threading HTTP server that carries the orchestrator for its handlers."""
|
||||
|
||||
daemon_threads = True
|
||||
allow_reuse_address = True
|
||||
|
||||
def __init__(self, address: tuple[str, int], registry: RegistryStore) -> None:
|
||||
self.registry = registry
|
||||
def __init__(self, address: tuple[str, int], orchestrator: Orchestrator) -> None:
|
||||
self.orchestrator = orchestrator
|
||||
super().__init__(address, Handler)
|
||||
|
||||
|
||||
def make_server(
|
||||
registry: RegistryStore, host: str = "127.0.0.1", port: int = 0
|
||||
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), registry)
|
||||
return ControlPlaneServer((host, port), orchestrator)
|
||||
|
||||
|
||||
__all__ = ["dispatch", "Handler", "ControlPlaneServer", "make_server", "Json"]
|
||||
|
||||
Reference in New Issue
Block a user