0c2d0aca63
Real-on-host testing surfaced two issues the unit-mocked slices couldn't: 1. The host (NixOS) firewall DROPS container->host traffic, so a host-process orchestrator is unreachable from the gateway container. Fix: run the orchestrator AS a container on the shared gateway network (PRD 0070's "virtualize the orchestrator") — the gateway reaches it by container name over docker DNS (container<->container, no firewall), and the host CLI reaches it via a published loopback port. 2. The control plane crashed the connection on a dispatch error (e.g. a broker failure) instead of returning 500. Changes: - lifecycle: OrchestratorProcess (host process) -> OrchestratorService (containers). Runs the control plane in the bundle image with the repo bind-mounted (orchestrator is stdlib-only), register-only stub broker so it needs NO docker socket (the backend launches agents; the host manages both containers). Registry DB persists via a host-root mount. ensure_running is an idempotent singleton over both containers. - gateway: BOT_BOTTLE_ORCHESTRATOR_URL is now the orchestrator's *by-name* URL on the shared network (dropped the host.docker.internal hack). - control_plane: _serve wraps dispatch — a failure returns 500, never crashes the connection. - OrchestratorProcess default broker -> stub (register-only) for docker. Validated live end-to-end: both containers up, gateway->orchestrator by name OK, register -> resolve-by-source-IP returns the bottle's policy from inside the gateway. pyright 0 errors; pylint 9.83/10; unit suite green (1760 tests; the 13 test_sidecar_init /bin/sleep errors are pre-existing NixOS-local noise). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01WBMWTEtQdJ4W5UrWuLHCck
146 lines
5.2 KiB
Python
146 lines
5.2 KiB
Python
"""Consolidated bottle launch sequence for the docker backend (PRD 0070).
|
|
|
|
Composes the orchestrator primitives into the register/teardown sequence that
|
|
replaces the per-bottle sidecar bundle:
|
|
|
|
1. ensure the orchestrator control plane + shared gateway are up;
|
|
2. allocate the bottle a pinned source IP on the gateway network (the
|
|
attribution key), skipping the gateway's own address + live bottles;
|
|
3. register it (egress policy blob + slug metadata) → bottle id + identity
|
|
token;
|
|
4. provision its git-gate repos/creds into the running gateway.
|
|
|
|
It returns a `LaunchContext` with everything the agent container needs to
|
|
attach — network, pinned IP, the gateway's address (its proxy target), the
|
|
orchestrator URL, and the identity token. The agent `docker run` itself is
|
|
the backend's job (it owns provider provisioning); this owns the
|
|
orchestrator-facing wiring so that sequence stays testable in isolation.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass
|
|
|
|
from ...docker_cmd import run_docker
|
|
from ...egress import EgressPlan
|
|
from ...git_gate import GitGatePlan
|
|
from ...orchestrator.client import OrchestratorClient
|
|
from ...orchestrator.gateway import GATEWAY_NAME, GATEWAY_NETWORK
|
|
from ...orchestrator.lifecycle import OrchestratorService
|
|
from ...orchestrator.registration import registration_inputs
|
|
from .gateway_net import next_free_ip
|
|
from .gateway_provision import deprovision_git_gate, provision_git_gate
|
|
|
|
|
|
class ConsolidatedLaunchError(RuntimeError):
|
|
"""The consolidated register/provision sequence could not complete."""
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class LaunchContext:
|
|
"""What the agent container needs to join the shared gateway."""
|
|
|
|
bottle_id: str
|
|
identity_token: str
|
|
source_ip: str # the agent's pinned address (attribution key)
|
|
network: str # the shared gateway network to attach to
|
|
gateway_ip: str # the gateway's address — the agent's proxy target
|
|
orchestrator_url: str
|
|
|
|
|
|
def _network_cidr(network: str) -> str:
|
|
"""The gateway network's IPv4 subnet, or raise."""
|
|
proc = run_docker([
|
|
"docker", "network", "inspect",
|
|
"--format", "{{range .IPAM.Config}}{{.Subnet}}{{end}}", network,
|
|
])
|
|
cidr = proc.stdout.strip()
|
|
if proc.returncode != 0 or not cidr:
|
|
raise ConsolidatedLaunchError(
|
|
f"gateway network {network} has no subnet: {proc.stderr.strip()}"
|
|
)
|
|
return cidr
|
|
|
|
|
|
def _container_ip(name: str, network: str) -> str:
|
|
"""A container's IPv4 address on `network`, or raise."""
|
|
proc = run_docker([
|
|
"docker", "inspect", "--format",
|
|
f'{{{{(index .NetworkSettings.Networks "{network}").IPAddress}}}}', name,
|
|
])
|
|
ip = proc.stdout.strip()
|
|
if proc.returncode != 0 or not ip:
|
|
raise ConsolidatedLaunchError(
|
|
f"gateway {name} has no address on {network}: {proc.stderr.strip()}"
|
|
)
|
|
return ip
|
|
|
|
|
|
def _taken_ips(client: OrchestratorClient, gateway_ip: str) -> list[str]:
|
|
"""Every address already in use on the gateway network: the gateway
|
|
container plus every live bottle the registry knows."""
|
|
taken = [gateway_ip]
|
|
for rec in client.list_bottles():
|
|
src = rec.get("source_ip")
|
|
if isinstance(src, str) and src:
|
|
taken.append(src)
|
|
return taken
|
|
|
|
|
|
def launch_consolidated(
|
|
egress_plan: EgressPlan,
|
|
git_gate_plan: GitGatePlan,
|
|
*,
|
|
image_ref: str = "",
|
|
service: OrchestratorService | None = None,
|
|
gateway_name: str = GATEWAY_NAME,
|
|
network: str = GATEWAY_NETWORK,
|
|
) -> LaunchContext:
|
|
"""Ensure the orchestrator + gateway are up, allocate + register the
|
|
bottle, and provision its git-gate state. Returns the agent's attach
|
|
context. Raises `ConsolidatedLaunchError` (or the primitives' own errors)
|
|
if any step fails — the caller tears down on failure."""
|
|
service = service or OrchestratorService()
|
|
url = service.ensure_running()
|
|
client = OrchestratorClient(url)
|
|
|
|
cidr = _network_cidr(network)
|
|
gateway_ip = _container_ip(gateway_name, network)
|
|
source_ip = next_free_ip(cidr, _taken_ips(client, gateway_ip))
|
|
|
|
inputs = registration_inputs(egress_plan)
|
|
reg = client.register_bottle(
|
|
source_ip, image_ref=image_ref, policy=inputs.policy, metadata=inputs.metadata,
|
|
)
|
|
try:
|
|
provision_git_gate(gateway_name, reg.bottle_id, git_gate_plan)
|
|
except Exception:
|
|
# Roll the registration back so a provisioning failure leaves no orphan.
|
|
client.teardown_bottle(reg.bottle_id)
|
|
raise
|
|
return LaunchContext(
|
|
bottle_id=reg.bottle_id,
|
|
identity_token=reg.identity_token,
|
|
source_ip=source_ip,
|
|
network=network,
|
|
gateway_ip=gateway_ip,
|
|
orchestrator_url=url,
|
|
)
|
|
|
|
|
|
def teardown_consolidated(
|
|
bottle_id: str, *, orchestrator_url: str, gateway_name: str = GATEWAY_NAME,
|
|
) -> None:
|
|
"""Deregister the bottle and remove its git-gate state from the gateway.
|
|
Both steps are idempotent so this is safe from a cleanup trap."""
|
|
OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
|
|
deprovision_git_gate(gateway_name, bottle_id)
|
|
|
|
|
|
__all__ = [
|
|
"LaunchContext",
|
|
"launch_consolidated",
|
|
"teardown_consolidated",
|
|
"ConsolidatedLaunchError",
|
|
]
|