feat(supervise): start orchestrator on demand via backend-agnostic bring-up

Add BottleBackend.ensure_orchestrator() -> str: the backend-agnostic
entry point that brings up the per-host orchestrator + shared gateway
(idempotent) and returns its host-reachable control-plane URL. Docker
starts the orchestrator + gateway containers (OrchestratorService);
firecracker boots the infra VM; macos-container dies with a pointer
(no orchestrator). Previously bring-up was reachable only through each
backend's consolidated_launch, with no shared handle.

Wire it into `bot-bottle supervise`: supervise is often the first thing
an operator runs, before any bottle has booted the control plane, so
`_resolve_orchestrator_url` now starts the selected backend's
orchestrator on demand when discovery finds nothing, instead of failing
with "launch a bottle first".

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UoEZHDjv84ChoZbozQERhJ
This commit is contained in:
2026-07-16 21:52:11 -04:00
parent 265119d601
commit 2641ab70fd
6 changed files with 105 additions and 2 deletions
+12
View File
@@ -511,6 +511,18 @@ class BottleBackend(ABC, Generic[PlanT, CleanupT]):
del plan
return ""
def ensure_orchestrator(self) -> str:
"""Bring up this backend's per-host orchestrator + shared gateway
(idempotent) and return the host-reachable control-plane URL.
This is the backend-agnostic bring-up entry point: `launch` calls
it as part of starting a bottle, and operator tools (`supervise`)
call it to start the control plane on demand when none is running
yet. Docker starts the orchestrator + gateway containers;
firecracker boots the infra VM. Backends with no orchestrator
(macos-container) die with a pointer — the default here."""
die(f"backend {self.name!r} has no orchestrator control plane")
@abstractmethod
def prepare_cleanup(self) -> CleanupT:
"""Enumerate orphaned resources from previous bottles. No side
+4
View File
@@ -105,6 +105,10 @@ class DockerBottleBackend(BottleBackend["DockerBottlePlan", "DockerBottleCleanup
with _launch.launch(plan, provision=self.provision) as bottle:
yield bottle
def ensure_orchestrator(self) -> str:
from ...orchestrator.lifecycle import OrchestratorService
return OrchestratorService().ensure_running()
def supervise_mcp_url(self, plan: DockerBottlePlan) -> str:
"""Docker bottles reach the supervise daemon via the
compose-network alias `supervise:9100`. No per-bottle URL
@@ -110,3 +110,7 @@ class FirecrackerBottleBackend(
def supervise_mcp_url(self, plan: FirecrackerBottlePlan) -> str:
return plan.agent_supervise_url
def ensure_orchestrator(self) -> str:
from . import infra_vm
return infra_vm.ensure_running().control_plane_url
+24 -2
View File
@@ -65,10 +65,26 @@ ApplyError = (OrchestratorClientError,)
_client_instance: OrchestratorClient | None = None
def _resolve_orchestrator_url() -> str:
"""URL of the running orchestrator control plane, starting one on demand.
Supervise is often the first thing an operator runs — before any bottle
has booted the control plane. So when discovery finds nothing, bring up
the selected backend's orchestrator + gateway (idempotent) rather than
failing with "launch a bottle first"."""
try:
return discover_orchestrator_url()
except OrchestratorClientError:
from ..backend import get_bottle_backend
backend = get_bottle_backend()
info(f"no orchestrator control plane running; starting one ({backend.name})…")
return backend.ensure_orchestrator()
def _client() -> OrchestratorClient:
global _client_instance # noqa: PLW0603 — CLI-session singleton
if _client_instance is None:
_client_instance = OrchestratorClient(discover_orchestrator_url())
_client_instance = OrchestratorClient(_resolve_orchestrator_url())
return _client_instance
@@ -204,12 +220,18 @@ def cmd_supervise(argv: list[str]) -> int:
args = parser.parse_args(argv)
# Establish the orchestrator connection up front so a missing control
# plane is a clean one-line error, not a curses crash mid-loop.
# plane is a clean one-line error, not a curses crash mid-loop. This also
# starts the orchestrator on demand when none is running (see `_client`).
try:
_client()
except OrchestratorClientError as e:
error(str(e))
return 1
except Die as e:
# Backend has no orchestrator to start (e.g. macos-container).
if e.message:
error(e.message)
return e.code if isinstance(e.code, int) else 1
if args.once:
return _list_once()