feat(docker): consolidate to single infra container under gateway_init supervise tree

Collapses the two-container Docker model (gateway + orchestrator) into one
bot-bottle-infra container, matching the macOS and Firecracker backends.

- Dockerfile.infra: now a shared gateway+orchestrator base (COPY bot_bottle
  from orchestrator build, no CMD override)
- Dockerfile.infra.fc: new Firecracker-specific layer (buildah/crun/netavark)
- gateway_init: adds orchestrator daemon with _OPT_IN_DAEMONS gating so it
  only starts when BOT_BOTTLE_GATEWAY_DAEMONS explicitly includes it
- orchestrator/lifecycle: OrchestratorService manages one infra container;
  builds orchestrator (intermediate) then infra; live source bind-mounted at
  /bot-bottle-src with PYTHONPATH so the subprocess uses the checkout
- backend/consolidated_util: extracts provision_bottle + teardown_consolidated
  shared across all three backends; removes duplication in docker/fc/macos
  consolidated_launch modules
- firecracker/infra_vm: builds four images (orchestrator→gateway→infra→infra.fc)
- All unit tests updated and passing (1878 tests)
- PRD status: Draft → Active
This commit is contained in:
2026-07-20 19:35:33 +00:00
parent 31a5ec2fc8
commit 2f45f5afec
15 changed files with 381 additions and 397 deletions
@@ -38,8 +38,7 @@ from ...egress import EgressPlan
from ...git_gate import GitGatePlan
from ...log import info
from ...orchestrator.client import OrchestratorClient, OrchestratorClientError
from ...orchestrator.registration import registration_inputs
from ..docker.gateway_provision import deprovision_git_gate, provision_git_gate
from ..consolidated_util import provision_bottle, teardown_consolidated as _teardown_util
from . import util as container_mod
from .enumerate import CONTAINER_NAME_PREFIX, EnumerationError, enumerate_active
from .gateway import GATEWAY_NETWORK
@@ -142,17 +141,10 @@ def register_agent(
client.reconcile(live_source_ips(endpoint.network))
except (OrchestratorClientError, EnumerationError) as e:
info(f"registry reconciliation skipped: {e}")
inputs = registration_inputs(egress_plan)
reg = client.register_bottle(
source_ip, image_ref=image_ref, policy=inputs.policy,
metadata=inputs.metadata, tokens=tokens,
reg = provision_bottle(
client, source_ip, egress_plan, git_gate_plan, AppleGatewayTransport(),
image_ref=image_ref, tokens=tokens,
)
try:
provision_git_gate(AppleGatewayTransport(), 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,
@@ -169,12 +161,8 @@ def teardown_consolidated(
"""Deregister the bottle and remove its git-gate state from the gateway.
Both steps are idempotent so this is safe from a cleanup trap. Does NOT
stop the gateway — it's a persistent per-host singleton."""
from ...orchestrator.config_store import DEFAULT_TEARDOWN_TIMEOUT_SECONDS
OrchestratorClient(
orchestrator_url,
timeout=timeout if timeout is not None else DEFAULT_TEARDOWN_TIMEOUT_SECONDS,
).teardown_bottle(bottle_id)
deprovision_git_gate(AppleGatewayTransport(), bottle_id)
_teardown_util(bottle_id, AppleGatewayTransport(),
orchestrator_url=orchestrator_url, timeout=timeout)
__all__ = [