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
2026-07-20 19:35:33 +00:00
parent 31a5ec2fc8
commit 2f45f5afec
15 changed files with 381 additions and 397 deletions
@@ -0,0 +1,60 @@
+"""Shared helpers for the consolidated launch sequence (PRD 0070).
+
+Logic that was duplicated across the docker, macos_container, and
+firecracker consolidated_launch modules — extracted so each backend
+imports it rather than re-implementing it.
+"""
+
+from __future__ import annotations
+
+from ..egress import EgressPlan
+from ..git_gate import GitGatePlan
+from ..orchestrator.client import OrchestratorClient
+from ..orchestrator.registration import registration_inputs
+from .docker.gateway_provision import GatewayTransport, deprovision_git_gate, provision_git_gate
+
+
+def provision_bottle(
+    client: OrchestratorClient,
+    source_ip: str,
+    egress_plan: EgressPlan,
+    git_gate_plan: GitGatePlan,
+    transport: GatewayTransport,
+    *,
+    image_ref: str = "",
+    tokens: dict[str, str] | None = None,
+):
+    """Register the bottle and provision its git-gate state. Rolls back the
+    registration if provisioning fails so no orphan is left. Returns the
+    `RegisteredBottle` from the orchestrator."""
+    inputs = registration_inputs(egress_plan)
+    reg = client.register_bottle(
+        source_ip, image_ref=image_ref, policy=inputs.policy,
+        metadata=inputs.metadata, tokens=tokens,
+    )
+    try:
+        provision_git_gate(transport, reg.bottle_id, git_gate_plan)
+    except Exception:
+        client.teardown_bottle(reg.bottle_id)
+        raise
+    return reg
+
+
+def teardown_consolidated(
+    bottle_id: str,
+    transport: GatewayTransport,
+    *,
+    orchestrator_url: str,
+    timeout: float | None = None,
+) -> None:
+    """Deregister the bottle and remove its git-gate state. Both steps are
+    idempotent so this is safe from a cleanup trap."""
+    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(transport, bottle_id)
+
+
+__all__ = ["provision_bottle", "teardown_consolidated"]
@@ -1,19 +1,13 @@
 """Consolidated bottle launch sequence for the docker backend (PRD 0070).

-Composes the orchestrator primitives into the register/teardown sequence that
-replaces the per-bottle gateway:
+Composes the orchestrator primitives into the register/teardown sequence:

-  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.
+  1. ensure the single infra container (control plane + gateway) is up;
+  2. allocate the bottle a pinned source IP on the gateway network;
+  3. register it and provision its git-gate repos/creds into the 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
+Returns a `LaunchContext` with everything the agent container needs to
+attach. The agent `docker run` itself is the backend's job; this owns the
 orchestrator-facing wiring so that sequence stays testable in isolation.
 """

@@ -25,15 +19,12 @@ 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 ...orchestrator.gateway import GATEWAY_NETWORK
+from ...orchestrator.lifecycle import INFRA_NAME, OrchestratorService
+from ..consolidated_util import provision_bottle
+from ..consolidated_util import teardown_consolidated as _teardown_util
+from .gateway_provision import DockerGatewayTransport
 from .gateway_net import next_free_ip
-from .gateway_provision import (
-    DockerGatewayTransport,
-    deprovision_git_gate,
-    provision_git_gate,
-)


 class ConsolidatedLaunchError(RuntimeError):
@@ -75,24 +66,21 @@ def _container_ip(name: str, network: str) -> str:
    ip = proc.stdout.strip()
    if proc.returncode != 0 or not ip:
        raise ConsolidatedLaunchError(
-            f"gateway {name} has no address on {network}: {proc.stderr.strip()}"
+            f"container {name} has no address on {network}: {proc.stderr.strip()}"
        )
    return ip


 def _network_container_ips(network: str) -> list[str]:
    """Every address currently assigned on the gateway network — the ground
-    truth for "in use": the gateway + orchestrator infrastructure containers
-    and every live agent. Read from the network so a new bottle can't collide
-    with anything actually attached (a registry-only view would miss the
-    orchestrator/gateway containers)."""
+    truth for "in use": the infra container and every live agent. Read from
+    the network so a new bottle can't collide with anything actually attached."""
    proc = run_docker([
        "docker", "network", "inspect", "--format",
        "{{range .Containers}}{{.IPv4Address}} {{end}}", network,
    ])
    ips: list[str] = []
    for entry in proc.stdout.split():
-        # entries look like "172.20.0.2/16" — keep the address.
        ips.append(entry.split("/", 1)[0])
    return ips

@@ -104,33 +92,24 @@ def launch_consolidated(
    image_ref: str = "",
    tokens: dict[str, str] | None = None,
    service: OrchestratorService | None = None,
-    gateway_name: str = GATEWAY_NAME,
+    infra_name: str = INFRA_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."""
+    """Ensure the infra container is up, allocate + register the bottle, and
+    provision its git-gate state. Returns the agent's attach context."""
    service = service or OrchestratorService()
    url = service.ensure_running()
    client = OrchestratorClient(url)

    cidr = _network_cidr(network)
-    gateway_ip = _container_ip(gateway_name, network)
+    gateway_ip = _container_ip(infra_name, network)
    source_ip = next_free_ip(cidr, _network_container_ips(network))

-    inputs = registration_inputs(egress_plan)
-    reg = client.register_bottle(
-        source_ip, image_ref=image_ref, policy=inputs.policy,
-        metadata=inputs.metadata, tokens=tokens,
+    transport = DockerGatewayTransport(infra_name)
+    reg = provision_bottle(
+        client, source_ip, egress_plan, git_gate_plan, transport,
+        image_ref=image_ref, tokens=tokens,
    )
-    try:
-        provision_git_gate(
-            DockerGatewayTransport(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,
@@ -142,20 +121,12 @@ def launch_consolidated(


 def teardown_consolidated(
-    bottle_id: str,
-    *,
-    orchestrator_url: str,
-    gateway_name: str = GATEWAY_NAME,
+    bottle_id: str, *, orchestrator_url: str, infra_name: str = INFRA_NAME,
    timeout: float | None = None,
 ) -> 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."""
-    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(DockerGatewayTransport(gateway_name), bottle_id)
+    """Deregister the bottle and remove its git-gate state. Idempotent."""
+    _teardown_util(bottle_id, DockerGatewayTransport(infra_name),
+                   orchestrator_url=orchestrator_url, timeout=timeout)


 __all__ = [
@@ -33,8 +33,7 @@ from ...orchestrator.client import OrchestratorClient
 from ...orchestrator.lifecycle import (
    OrchestratorStartError,  # re-exported so callers can catch it
 )
-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 infra_vm


@@ -68,18 +67,11 @@ def launch_consolidated(
    url = infra.control_plane_url
    client = OrchestratorClient(url)

-    inputs = registration_inputs(egress_plan)
-    reg = client.register_bottle(
-        guest_ip, image_ref=image_ref, policy=inputs.policy,
-        metadata=inputs.metadata, tokens=tokens,
+    transport = infra_vm.gateway_transport()
+    reg = provision_bottle(
+        client, guest_ip, egress_plan, git_gate_plan, transport,
+        image_ref=image_ref, tokens=tokens,
    )
-    try:
-        provision_git_gate(
-            infra_vm.gateway_transport(), reg.bottle_id, git_gate_plan)
-    except Exception:
-        client.teardown_bottle(reg.bottle_id)
-        raise
-
    # The shared gateway CA every agent on this host trusts for TLS
    # interception — fetched from the infra VM over SSH.
    return LaunchContext(
@@ -98,12 +90,8 @@ def teardown_consolidated(
    VM. Both steps are idempotent so this is safe from a cleanup trap. Does
    NOT stop the infra VM — it's a persistent per-host singleton shared by
    every bottle."""
-    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(infra_vm.gateway_transport(), bottle_id)
+    _teardown_util(bottle_id, infra_vm.gateway_transport(),
+                   orchestrator_url=orchestrator_url, timeout=timeout)


 __all__ = [
@@ -41,7 +41,7 @@ from . import util
 _ARTIFACT_FORMAT = "1"

 _REPO_ROOT = Path(__file__).resolve().parents[3]
-_DOCKERFILES = ("Dockerfile.orchestrator", "Dockerfile.gateway", "Dockerfile.infra")
+_DOCKERFILES = ("Dockerfile.orchestrator", "Dockerfile.gateway", "Dockerfile.infra", "Dockerfile.infra.fc")

 _DEFAULT_BASE = "https://gitea.dideric.is"
 _DEFAULT_OWNER = "didericis"
@@ -125,16 +125,19 @@ def ensure_built() -> None:


 def build_infra_images_with_docker() -> None:
-    """Build the three fixed images from source with host Docker: orchestrator,
-    gateway, then the combined infra image (`COPY --from` orchestrator, `FROM`
-    gateway). The launch host uses this only in `BOT_BOTTLE_INFRA_BUILD=local`
-    mode; `publish_infra` uses it off-host to produce the published artifact."""
+    """Build the four fixed images from source with host Docker: orchestrator,
+    gateway, the shared infra base (Dockerfile.infra), then the Firecracker
+    infra image (Dockerfile.infra.fc: FROM infra + buildah). The launch host
+    uses this only in `BOT_BOTTLE_INFRA_BUILD=local` mode; `publish_infra`
+    uses it off-host to produce the published artifact."""
    docker_mod.build_image(
        _ORCHESTRATOR_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.orchestrator")
    docker_mod.build_image(
        _GATEWAY_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.gateway")
    docker_mod.build_image(
-        _INFRA_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.infra")
+        "bot-bottle-infra:latest", str(_REPO_ROOT), dockerfile="Dockerfile.infra")
+    docker_mod.build_image(
+        _INFRA_IMAGE, str(_REPO_ROOT), dockerfile="Dockerfile.infra.fc")


 def build_infra_rootfs_dir() -> Path:
@@ -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__ = [