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:
@@ -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__ = [
|
||||
|
||||
@@ -61,6 +61,11 @@ class _DaemonSpec:
|
||||
_EGRESS_ONLY_ENV_PREFIXES: tuple[str, ...] = ("EGRESS_TOKEN_",)
|
||||
_READY_GATED_DAEMONS: tuple[str, ...] = ("git-gate", "git-http")
|
||||
|
||||
# Daemons that must be requested explicitly via BOT_BOTTLE_GATEWAY_DAEMONS
|
||||
# and are NOT started in the default (env-var-unset) case. The orchestrator
|
||||
# only runs in the combined infra container, never in a standalone gateway.
|
||||
_OPT_IN_DAEMONS: frozenset[str] = frozenset({"orchestrator"})
|
||||
|
||||
|
||||
def _env_for_daemon(name: str, base_env: dict[str, str]) -> dict[str, str]:
|
||||
"""Egress sees the full bundle env. Everyone else gets a copy
|
||||
@@ -75,7 +80,14 @@ def _env_for_daemon(name: str, base_env: dict[str, str]) -> dict[str, str]:
|
||||
}
|
||||
|
||||
|
||||
# The orchestrator is listed first so it starts before the gateway daemons,
|
||||
# giving the control plane a head start to accept /resolve calls. The gateway
|
||||
# daemons tolerate early /resolve failures and retry per-request.
|
||||
_DAEMONS: tuple[_DaemonSpec, ...] = (
|
||||
_DaemonSpec("orchestrator", (
|
||||
"python3", "-m", "bot_bottle.orchestrator",
|
||||
"--host", "0.0.0.0", "--port", "8099", "--broker", "stub",
|
||||
)),
|
||||
_DaemonSpec("egress", ("/bin/sh", "/app/egress-entrypoint.sh")),
|
||||
_DaemonSpec("git-gate", ("/bin/sh", "/git-gate-entrypoint.sh")),
|
||||
_DaemonSpec("git-http", ("python3", "-m", "bot_bottle.git_http_backend")),
|
||||
@@ -103,18 +115,20 @@ def _selected_daemons(
|
||||
env: dict[str, str],
|
||||
all_daemons: Sequence[_DaemonSpec] | None = None,
|
||||
) -> tuple[_DaemonSpec, ...]:
|
||||
"""Filter the daemon set by the BOT_BOTTLE_GATEWAY_DAEMONS env
|
||||
var. Unknown names in the list are ignored — the caller is the
|
||||
source of truth for which daemons are wired.
|
||||
"""Filter the daemon set by the BOT_BOTTLE_GATEWAY_DAEMONS env var.
|
||||
|
||||
`all_daemons` defaults to `_DAEMONS` resolved at call time (not
|
||||
at definition time), so tests can monkey-patch the module-level
|
||||
`_DAEMONS` and have the new value take effect."""
|
||||
When the var is unset/empty, return all non-opt-in daemons (the
|
||||
standard gateway subset). Opt-in daemons (e.g. `orchestrator`) only
|
||||
run when explicitly named — they never start in a plain gateway
|
||||
container that doesn't set the env var. Unknown names are ignored.
|
||||
|
||||
`all_daemons` defaults to `_DAEMONS` resolved at call time (not at
|
||||
definition time), so tests can pass a custom list."""
|
||||
if all_daemons is None:
|
||||
all_daemons = _DAEMONS
|
||||
raw = env.get("BOT_BOTTLE_GATEWAY_DAEMONS", "").strip()
|
||||
if not raw:
|
||||
return tuple(all_daemons)
|
||||
return tuple(d for d in all_daemons if d.name not in _OPT_IN_DAEMONS)
|
||||
wanted = {n.strip() for n in raw.split(",") if n.strip()}
|
||||
return tuple(d for d in all_daemons if d.name in wanted)
|
||||
|
||||
|
||||
@@ -1,17 +1,15 @@
|
||||
"""Orchestrator + gateway lifecycle (PRD 0070, docker slice).
|
||||
|
||||
Runs the orchestrator control plane **as a container** on the shared gateway
|
||||
network, alongside the gateway container. This is the PRD's "virtualize the
|
||||
orchestrator": container↔container between the gateway and the orchestrator
|
||||
avoids the host firewall (which drops container→host traffic), and the gateway
|
||||
reaches the control plane by container name over docker DNS. The host CLI
|
||||
reaches it via a published loopback port.
|
||||
Runs both the orchestrator control plane and the gateway data plane inside
|
||||
a single `bot-bottle-infra` container on the shared gateway network —
|
||||
matching the structure already used by the macOS and Firecracker backends.
|
||||
`gateway_init` is PID 1 and supervises both; the infra container is an
|
||||
idempotent per-host singleton.
|
||||
|
||||
The orchestrator runs with the **register-only broker** — the *backend*
|
||||
launches agent containers (compose), so the orchestrator needs no docker
|
||||
socket. That keeps this control-plane container unprivileged; the host manages
|
||||
both containers. `ensure_running` is an idempotent singleton (fixed container
|
||||
names + the published port).
|
||||
The combined container replaces the prior two-container split
|
||||
(bot-bottle-orchestrator + bot-bottle-orch-gateway). The host CLI reaches
|
||||
the control plane via a published loopback port; gateway daemons reach it
|
||||
over 127.0.0.1 (same container).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -26,49 +24,68 @@ from pathlib import Path
|
||||
from .. import log
|
||||
from ..docker_cmd import run_docker
|
||||
from ..paths import CONTROL_PLANE_TOKEN_ENV, bot_bottle_root, host_control_plane_token
|
||||
from .gateway import GATEWAY_IMAGE, GATEWAY_NAME, GATEWAY_NETWORK, DockerGateway, GatewayError
|
||||
from ..supervise import DB_PATH_IN_CONTAINER
|
||||
from .gateway import (
|
||||
GATEWAY_CA_VOLUME,
|
||||
GATEWAY_NETWORK,
|
||||
GatewayError,
|
||||
MITMPROXY_HOME,
|
||||
_host_db_dir,
|
||||
)
|
||||
|
||||
DEFAULT_PORT = 8099
|
||||
ORCHESTRATOR_NAME = "bot-bottle-orchestrator"
|
||||
ORCHESTRATOR_LABEL = "bot-bottle-orchestrator=1"
|
||||
# The control-plane's own runtime image — lean (python + the stdlib-only
|
||||
# `bot_bottle` package, bind-mounted at run time), distinct from the heavy
|
||||
# gateway data-plane image it used to borrow (#384). Env override for
|
||||
# operators pinning a published build.
|
||||
DEFAULT_STARTUP_TIMEOUT_SECONDS = 45.0
|
||||
|
||||
INFRA_NAME = "bot-bottle-infra"
|
||||
INFRA_LABEL = "bot-bottle-infra=1"
|
||||
# The combined infra image: gateway data plane + orchestrator content.
|
||||
# Built from Dockerfile.infra (FROM gateway + COPY --from orchestrator).
|
||||
INFRA_IMAGE = os.environ.get("BOT_BOTTLE_INFRA_IMAGE", "bot-bottle-infra:latest")
|
||||
INFRA_DOCKERFILE = "Dockerfile.infra"
|
||||
# Baked as a container label so `ensure_running` can detect whether the
|
||||
# running container is executing the current bind-mounted source.
|
||||
INFRA_SOURCE_HASH_LABEL = "bot-bottle-infra-source-hash"
|
||||
|
||||
# Orchestrator image: the single canonical definition of the control-plane
|
||||
# content (lean: python:3.12-slim + bot_bottle package, no mitmproxy/git).
|
||||
# Used as a build intermediate: `Dockerfile.infra` COPY --from this image.
|
||||
ORCHESTRATOR_IMAGE = os.environ.get(
|
||||
"BOT_BOTTLE_ORCHESTRATOR_IMAGE", "bot-bottle-orchestrator:latest"
|
||||
)
|
||||
ORCHESTRATOR_DOCKERFILE = "Dockerfile.orchestrator"
|
||||
# Baked onto the container as a label so `ensure_running` can tell whether the
|
||||
# running process is executing the *current* bind-mounted source — see
|
||||
# `source_hash`.
|
||||
ORCHESTRATOR_SOURCE_HASH_LABEL = "bot-bottle-orchestrator-source-hash"
|
||||
|
||||
# The repo root is bind-mounted into the control-plane container so
|
||||
# `python -m bot_bottle.orchestrator` resolves the package (the orchestrator
|
||||
# is stdlib-only, so the lean orchestrator image's python is enough).
|
||||
_REPO_ROOT = Path(__file__).resolve().parents[2]
|
||||
_APP_DIR = "/app"
|
||||
# The gateway daemons + orchestrator the infra container runs.
|
||||
# BOT_BOTTLE_GATEWAY_DAEMONS listing `orchestrator` opts it in to
|
||||
# gateway_init's supervise tree (see gateway_init._OPT_IN_DAEMONS).
|
||||
_INFRA_DAEMONS = "egress,git-http,supervise,orchestrator"
|
||||
|
||||
# The bind-mount path for the live control-plane source inside the
|
||||
# container. Separate from /app so the gateway's baked scripts
|
||||
# (egress_addon.py, egress-entrypoint.sh) are not overlaid.
|
||||
_SRC_IN_CONTAINER = "/bot-bottle-src"
|
||||
# Bot-bottle host-root bind-mount inside the container (DB + state).
|
||||
_ROOT_IN_CONTAINER = "/bot-bottle-root"
|
||||
|
||||
# The supervise daemon writes proposals into the host DB directory.
|
||||
_SUPERVISE_DB_DIR_IN_CONTAINER = os.path.dirname(DB_PATH_IN_CONTAINER)
|
||||
|
||||
_HEALTH_POLL_SECONDS = 0.25
|
||||
DEFAULT_STARTUP_TIMEOUT_SECONDS = 45.0
|
||||
_HEALTH_REQUEST_TIMEOUT_SECONDS = 1.0
|
||||
|
||||
_REPO_ROOT = Path(__file__).resolve().parents[2]
|
||||
|
||||
|
||||
class OrchestratorStartError(RuntimeError):
|
||||
"""The orchestrator container did not become healthy within the timeout."""
|
||||
"""The infra container did not become healthy within the timeout."""
|
||||
|
||||
|
||||
def source_hash(repo_root: Path) -> str:
|
||||
"""Content hash of the orchestrator's bind-mounted Python source (the
|
||||
`bot_bottle` package the control-plane process imports). This only
|
||||
changes when the code that would actually run inside the container
|
||||
changes — `ensure_running` recreates the container on a mismatch and
|
||||
otherwise leaves a healthy one alone, so a bottle launch that isn't
|
||||
accompanied by a code change doesn't restart the process and drop every
|
||||
*other* active bottle's in-memory egress tokens (`Orchestrator._tokens`
|
||||
in `service.py`, never persisted to disk by design)."""
|
||||
`bot_bottle` package the control-plane process imports). Changes only
|
||||
when the code that would actually run changes — `ensure_running`
|
||||
recreates the container on a mismatch so a code change takes effect,
|
||||
but leaves a healthy up-to-date container alone to preserve in-memory
|
||||
egress tokens."""
|
||||
h = hashlib.sha256()
|
||||
for path in sorted((repo_root / "bot_bottle").rglob("*.py")):
|
||||
h.update(str(path.relative_to(repo_root)).encode())
|
||||
@@ -77,57 +94,37 @@ def source_hash(repo_root: Path) -> str:
|
||||
|
||||
|
||||
class OrchestratorService:
|
||||
"""Manages the orchestrator control-plane container + the shared gateway.
|
||||
"""Manages the single per-host infra container (control plane + gateway).
|
||||
Callers only need `ensure_running()` + `url`.
|
||||
|
||||
`orchestrator_name` / `orchestrator_label` let backends run independent
|
||||
orchestrators on the same host without name collisions (e.g. the
|
||||
Firecracker backend uses `bot-bottle-fc-orchestrator` alongside the Docker
|
||||
backend's `bot-bottle-orchestrator`); `gateway_name` gives the paired
|
||||
gateway container the same treatment (e.g. isolated integration tests
|
||||
that can't share the production `GATEWAY_NAME` singleton). Subclass and
|
||||
override `_gateway()` for anything `_gateway_image`/`gateway_name` can't
|
||||
express (a genuinely backend-specific gateway variant)."""
|
||||
`infra_name` / `infra_label` let backends run independent infra containers
|
||||
on the same host without name collisions (e.g. isolated integration tests
|
||||
that can't share the production INFRA_NAME singleton)."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
port: int = DEFAULT_PORT,
|
||||
network: str = GATEWAY_NETWORK,
|
||||
image: str = ORCHESTRATOR_IMAGE,
|
||||
gateway_image: str = GATEWAY_IMAGE,
|
||||
gateway_name: str = GATEWAY_NAME,
|
||||
image: str = INFRA_IMAGE,
|
||||
repo_root: Path = _REPO_ROOT,
|
||||
host_root: Path | None = None,
|
||||
orchestrator_name: str = ORCHESTRATOR_NAME,
|
||||
orchestrator_label: str = ORCHESTRATOR_LABEL,
|
||||
infra_name: str = INFRA_NAME,
|
||||
infra_label: str = INFRA_LABEL,
|
||||
) -> None:
|
||||
self.port = port
|
||||
self.network = network
|
||||
# Two distinct images (#384): `image` is the lean control-plane
|
||||
# runtime this container runs; `_gateway_image` is the heavy egress /
|
||||
# git-gate / supervise data plane the gateway container runs. They
|
||||
# were one conflated image before the split.
|
||||
self.image = image
|
||||
self._gateway_image = gateway_image
|
||||
self._gateway_name = gateway_name
|
||||
self._repo_root = repo_root
|
||||
self._host_root = host_root or bot_bottle_root()
|
||||
self._orchestrator_name = orchestrator_name
|
||||
self._orchestrator_label = orchestrator_label
|
||||
self._infra_name = infra_name
|
||||
self._infra_label = infra_label
|
||||
|
||||
@property
|
||||
def url(self) -> str:
|
||||
"""Host-side control-plane URL (published loopback port)."""
|
||||
return f"http://127.0.0.1:{self.port}"
|
||||
|
||||
@property
|
||||
def internal_url(self) -> str:
|
||||
"""Control-plane URL as the gateway container reaches it — by name over
|
||||
docker DNS on the shared network. This is the gateway's
|
||||
BOT_BOTTLE_ORCHESTRATOR_URL."""
|
||||
return f"http://{self._orchestrator_name}:{self.port}"
|
||||
|
||||
def is_healthy(self, *, timeout: float = _HEALTH_REQUEST_TIMEOUT_SECONDS) -> bool:
|
||||
try:
|
||||
with urllib.request.urlopen(f"{self.url}/health", timeout=timeout) as resp:
|
||||
@@ -139,139 +136,125 @@ class OrchestratorService:
|
||||
proc = run_docker(["docker", "ps", "--filter", f"name=^/{name}$", "--format", "{{.Names}}"])
|
||||
return name in proc.stdout.split()
|
||||
|
||||
def _run_orchestrator_container(self, current_hash: str) -> None:
|
||||
"""Start the control-plane container (idempotent: clears a stale
|
||||
fixed-name container first). Register-only broker → no docker socket.
|
||||
Labels the container with `current_hash` so a later `ensure_running`
|
||||
can detect a real code change (see `source_hash`)."""
|
||||
run_docker(["docker", "rm", "--force", self._orchestrator_name])
|
||||
proc = run_docker([
|
||||
"docker", "run", "--detach",
|
||||
"--name", self._orchestrator_name,
|
||||
"--label", self._orchestrator_label,
|
||||
"--label", f"{ORCHESTRATOR_SOURCE_HASH_LABEL}={current_hash}",
|
||||
"--network", self.network,
|
||||
# Host CLI reaches the control plane here; bound to loopback so it
|
||||
# is not exposed on the host's external interfaces. NOTE: the
|
||||
# container is still on `self.network` (the shared gateway network),
|
||||
# so agents can reach it by container IP — which is exactly why the
|
||||
# control plane requires the secret below rather than trusting the
|
||||
# network boundary.
|
||||
"--publish", f"127.0.0.1:{self.port}:{self.port}",
|
||||
"--volume", f"{self._repo_root}:{_APP_DIR}:ro",
|
||||
"--workdir", _APP_DIR,
|
||||
# Persist the registry DB on the host (sole-owner: only the
|
||||
# orchestrator opens bot-bottle.db).
|
||||
"--volume", f"{self._host_root}:{_ROOT_IN_CONTAINER}",
|
||||
"--env", f"BOT_BOTTLE_ROOT={_ROOT_IN_CONTAINER}",
|
||||
# The control-plane secret it requires on every route but /health.
|
||||
# Bare `--env NAME` → docker inherits the value from the run env
|
||||
# below, so the secret never lands on argv / `docker inspect`.
|
||||
"--env", CONTROL_PLANE_TOKEN_ENV,
|
||||
"--entrypoint", "python3",
|
||||
self.image,
|
||||
"-m", "bot_bottle.orchestrator",
|
||||
"--host", "0.0.0.0", "--port", str(self.port), "--broker", "stub",
|
||||
], env={**os.environ, CONTROL_PLANE_TOKEN_ENV: host_control_plane_token()})
|
||||
if proc.returncode != 0:
|
||||
raise OrchestratorStartError(
|
||||
f"orchestrator container failed to start: {proc.stderr.strip()}"
|
||||
)
|
||||
|
||||
def _gateway(self) -> DockerGateway:
|
||||
return DockerGateway(
|
||||
self._gateway_image,
|
||||
name=self._gateway_name,
|
||||
network=self.network,
|
||||
orchestrator_url=self.internal_url,
|
||||
)
|
||||
|
||||
def _ensure_orchestrator_image(self) -> None:
|
||||
"""Build the lean control-plane image from `Dockerfile.orchestrator`
|
||||
when it's missing (#384). Cheap — a `FROM python:*-slim` base with no
|
||||
deps to install, so the layer cache makes rebuilds a no-op. Unlike the
|
||||
gateway image this is build-if-missing, not build-every-time: the
|
||||
control plane bind-mounts its source, so a code change is caught by the
|
||||
source-hash recreate (below), not by an image rebuild."""
|
||||
if run_docker(["docker", "image", "inspect", self.image]).returncode == 0:
|
||||
return
|
||||
argv = ["docker", "build", "-t", self.image,
|
||||
"-f", str(self._repo_root / ORCHESTRATOR_DOCKERFILE),
|
||||
str(self._repo_root)]
|
||||
if os.environ.get("BOT_BOTTLE_NO_CACHE"):
|
||||
argv.insert(2, "--no-cache")
|
||||
proc = run_docker(argv)
|
||||
if proc.returncode != 0:
|
||||
raise GatewayError(
|
||||
f"orchestrator image build failed: {proc.stderr.strip()}"
|
||||
)
|
||||
|
||||
def _orchestrator_source_current(self, current_hash: str) -> bool:
|
||||
"""True iff the running orchestrator container was created from the
|
||||
*current* bind-mounted source. Mirrors `DockerGateway`'s
|
||||
image-staleness check, but by content hash rather than image id since
|
||||
the orchestrator runs bind-mounted source, not a built image."""
|
||||
if not self._container_running(self._orchestrator_name):
|
||||
def _infra_source_current(self, current_hash: str) -> bool:
|
||||
"""True iff the running infra container was started from the current
|
||||
bind-mounted source. Mirrors the macOS backend's `_source_current`."""
|
||||
if not self._container_running(self._infra_name):
|
||||
return False
|
||||
proc = run_docker([
|
||||
"docker", "inspect", "--format",
|
||||
"{{ index .Config.Labels \"" + ORCHESTRATOR_SOURCE_HASH_LABEL + "\" }}",
|
||||
self._orchestrator_name,
|
||||
"{{ index .Config.Labels \"" + INFRA_SOURCE_HASH_LABEL + "\" }}",
|
||||
self._infra_name,
|
||||
])
|
||||
if proc.returncode != 0:
|
||||
return True # can't compare -> don't churn a working container
|
||||
return True # can't compare → don't churn a working container
|
||||
return proc.stdout.strip() == current_hash
|
||||
|
||||
def _ensure_network(self) -> None:
|
||||
if run_docker(["docker", "network", "inspect", self.network]).returncode == 0:
|
||||
return
|
||||
proc = run_docker(["docker", "network", "create", self.network])
|
||||
if proc.returncode != 0 and "already exists" not in proc.stderr:
|
||||
raise GatewayError(
|
||||
f"gateway network {self.network} failed to create: {proc.stderr.strip()}"
|
||||
)
|
||||
|
||||
def _build_images(self) -> None:
|
||||
"""Build the orchestrator image (build intermediate), then the infra
|
||||
image. Both are cache-aware: a no-op when nothing changed."""
|
||||
for tag, dockerfile in (
|
||||
(ORCHESTRATOR_IMAGE, ORCHESTRATOR_DOCKERFILE),
|
||||
(self.image, INFRA_DOCKERFILE),
|
||||
):
|
||||
argv = ["docker", "build", "-t", tag,
|
||||
"-f", str(self._repo_root / dockerfile),
|
||||
str(self._repo_root)]
|
||||
if os.environ.get("BOT_BOTTLE_NO_CACHE"):
|
||||
argv.insert(2, "--no-cache")
|
||||
proc = run_docker(argv)
|
||||
if proc.returncode != 0:
|
||||
raise GatewayError(f"{dockerfile} build failed: {proc.stderr.strip()}")
|
||||
|
||||
def _run_infra_container(self, current_hash: str) -> None:
|
||||
"""Start the combined infra container (idempotent: clears a stale
|
||||
fixed-name container first). Labels the container with `current_hash`
|
||||
so a later `ensure_running` can detect a real code change."""
|
||||
self._ensure_network()
|
||||
run_docker(["docker", "rm", "--force", self._infra_name])
|
||||
proc = run_docker([
|
||||
"docker", "run", "--detach",
|
||||
"--name", self._infra_name,
|
||||
"--label", self._infra_label,
|
||||
"--label", f"{INFRA_SOURCE_HASH_LABEL}={current_hash}",
|
||||
"--network", self.network,
|
||||
# Host CLI reaches the control plane here (loopback only).
|
||||
"--publish", f"127.0.0.1:{self.port}:{self.port}",
|
||||
# Persist the mitmproxy CA so it survives container recreation.
|
||||
"--volume", f"{GATEWAY_CA_VOLUME}:{MITMPROXY_HOME}",
|
||||
# Shared supervise DB (same file the operator reads over HTTP).
|
||||
"--volume", f"{_host_db_dir()}:{_SUPERVISE_DB_DIR_IN_CONTAINER}",
|
||||
"--env", f"SUPERVISE_DB_PATH={DB_PATH_IN_CONTAINER}",
|
||||
# Live control-plane source, mounted to a path that does not
|
||||
# overlay the gateway's baked /app scripts.
|
||||
"--volume", f"{self._repo_root}:{_SRC_IN_CONTAINER}:ro",
|
||||
# PYTHONPATH lets the orchestrator (and other Python daemons)
|
||||
# import the live source ahead of the installed package.
|
||||
"--env", f"PYTHONPATH={_SRC_IN_CONTAINER}",
|
||||
# Orchestrator registry DB on the host (sole writer: control plane).
|
||||
"--volume", f"{self._host_root}:{_ROOT_IN_CONTAINER}",
|
||||
"--env", f"BOT_BOTTLE_ROOT={_ROOT_IN_CONTAINER}",
|
||||
# Control-plane secret: required by the orchestrator (to enforce)
|
||||
# and by the gateway daemons (to present on /resolve calls).
|
||||
"--env", CONTROL_PLANE_TOKEN_ENV,
|
||||
# Gateway daemons reach the orchestrator over loopback.
|
||||
"--env", f"BOT_BOTTLE_ORCHESTRATOR_URL=http://127.0.0.1:{self.port}",
|
||||
# Opt the orchestrator into gateway_init's supervise tree.
|
||||
"--env", f"BOT_BOTTLE_GATEWAY_DAEMONS={_INFRA_DAEMONS}",
|
||||
self.image,
|
||||
], env={**os.environ, CONTROL_PLANE_TOKEN_ENV: host_control_plane_token()})
|
||||
if proc.returncode != 0:
|
||||
raise OrchestratorStartError(
|
||||
f"infra container failed to start: {proc.stderr.strip()}"
|
||||
)
|
||||
|
||||
def ensure_running(
|
||||
self, *, startup_timeout: float = DEFAULT_STARTUP_TIMEOUT_SECONDS,
|
||||
) -> str:
|
||||
"""Ensure the control plane + shared gateway are up; return the host
|
||||
control-plane URL. Idempotent — a healthy control plane running
|
||||
current code and a running gateway are left untouched. Raises
|
||||
`OrchestratorStartError` on timeout."""
|
||||
gateway = self._gateway()
|
||||
gateway.ensure_built() # rebuild the bundle image on a source change
|
||||
gateway.ensure_running() # creates the shared network + (re)starts gateway
|
||||
"""Ensure the infra container (control plane + gateway) is up; return
|
||||
the host control-plane URL. Idempotent — a healthy container on current
|
||||
source is left untouched. Raises `OrchestratorStartError` on timeout."""
|
||||
self._build_images()
|
||||
|
||||
# Recreate the orchestrator container only when its bind-mounted
|
||||
# source has actually changed since it started — its Python process
|
||||
# loaded that code at startup and won't reload, so a stale container
|
||||
# would keep running OLD control-plane code. Recreating on *every*
|
||||
# launch (the prior behaviour) would drop every other active
|
||||
# bottle's in-memory egress tokens each time a new bottle starts,
|
||||
# since the orchestrator process holds them only in memory (#381).
|
||||
current_hash = source_hash(self._repo_root)
|
||||
if self.is_healthy() and self._orchestrator_source_current(current_hash):
|
||||
if self.is_healthy() and self._infra_source_current(current_hash):
|
||||
return self.url
|
||||
|
||||
self._ensure_orchestrator_image()
|
||||
log.info(
|
||||
"starting orchestrator container",
|
||||
context={"name": self._orchestrator_name},
|
||||
)
|
||||
self._run_orchestrator_container(current_hash)
|
||||
log.info("starting infra container", context={"name": self._infra_name})
|
||||
self._run_infra_container(current_hash)
|
||||
|
||||
deadline = time.monotonic() + startup_timeout
|
||||
while time.monotonic() < deadline:
|
||||
if self.is_healthy():
|
||||
log.info("orchestrator healthy", context={"url": self.url})
|
||||
log.info("infra container healthy", context={"url": self.url})
|
||||
return self.url
|
||||
time.sleep(_HEALTH_POLL_SECONDS)
|
||||
raise OrchestratorStartError(
|
||||
f"orchestrator at {self.url} did not become healthy within {startup_timeout:g}s"
|
||||
f"infra container at {self.url} did not become healthy within {startup_timeout:g}s"
|
||||
)
|
||||
|
||||
def stop(self) -> None:
|
||||
"""Remove the orchestrator + gateway containers (idempotent)."""
|
||||
run_docker(["docker", "rm", "--force", self._orchestrator_name])
|
||||
self._gateway().stop()
|
||||
"""Remove the infra container (idempotent)."""
|
||||
run_docker(["docker", "rm", "--force", self._infra_name])
|
||||
|
||||
|
||||
__all__ = [
|
||||
"OrchestratorService",
|
||||
"OrchestratorStartError",
|
||||
"ORCHESTRATOR_NAME",
|
||||
"INFRA_NAME",
|
||||
"INFRA_IMAGE",
|
||||
"INFRA_SOURCE_HASH_LABEL",
|
||||
"ORCHESTRATOR_IMAGE",
|
||||
"DEFAULT_PORT",
|
||||
"DEFAULT_STARTUP_TIMEOUT_SECONDS",
|
||||
"source_hash",
|
||||
]
|
||||
|
||||
Reference in New Issue
Block a user