refactor(gateway): move DockerGateway to the backend layer, drop the dead standalone-gateway path
lint / lint (push) Successful in 54s

The `DockerGateway` container-lifecycle impl now lives in
`backend/docker/gateway.py` (the shape backend gateway classes will share);
`orchestrator/gateway.py` keeps only the backend-neutral pieces (the `Gateway`
ABC, constants, `rotate_gateway_ca`).

Delete the standalone-gateway path it was the only consumer of. `--gateway` on
`python -m bot_bottle.orchestrator` was invoked nowhere — the production docker
flow runs the gateway data plane inside the combined `bot-bottle-infra`
container via `OrchestratorService`, never this class. Removing it takes with it
`Orchestrator.ensure_gateway()` and the `gateway` ctor arg; `gateway_status()`
becomes a stub reporting `configured: false` so the documented `GET /gateway`
control-plane route keeps its contract.

Fix a latent bug the move surfaced: `launch.py` read the shared gateway CA via
`docker exec bot-bottle-orch-gateway`, a container the consolidated flow never
creates — so the agent CA install was reaching a nonexistent name. Read it from
`bot-bottle-infra` (INFRA_NAME) instead.

Repoint the affected tests to the new module; drop the unit test + fake that
covered the deleted standalone wiring.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
2026-07-24 12:39:58 -04:00
parent aac27d8a40
commit dfce3d9505
10 changed files with 226 additions and 277 deletions
+7 -185
View File
@@ -7,8 +7,9 @@ because the attribution invariant (source IP + identity token, see
so per-bottle policy lives in one long-lived process keyed on who's calling.
`Gateway` is the backend-neutral lifecycle contract (mirrors `LaunchBroker`):
ensure the single instance is up, report it, tear it down. `DockerGateway`
is the docker implementation; a firecracker gateway VM slots in later.
ensure the single instance is up, report it, tear it down. The docker
implementation (`DockerGateway`) lives in `backend/docker/gateway.py`; a
firecracker gateway VM slots in later.
The defining behaviour is **idempotent singleton**: `ensure_running` starts
the instance if absent and is a no-op if it's already up, so N bottle
@@ -19,20 +20,13 @@ from __future__ import annotations
import abc
import os
import time
from pathlib import Path
from ..control_auth import ROLE_GATEWAY, mint
from ..docker_cmd import run_docker
from ..paths import (
CONTROL_AUTH_JWT_ENV,
host_control_plane_token,
host_gateway_ca_dir,
)
from ..paths import host_gateway_ca_dir
# The gateway's mitmproxy writes its CA a beat after the container starts, so
# reads poll for it rather than assuming it's there on a fresh launch.
_CA_POLL_SECONDS = 0.5
CA_POLL_SECONDS = 0.5
DEFAULT_CA_TIMEOUT_SECONDS = 30.0
GATEWAY_NAME = "bot-bottle-orch-gateway"
@@ -66,7 +60,7 @@ GATEWAY_CA_GLOB = "mitmproxy-ca*"
# that lands. Env override matches the backend's BOT_BOTTLE_GATEWAY_IMAGE.
GATEWAY_IMAGE = os.environ.get("BOT_BOTTLE_GATEWAY_IMAGE", "bot-bottle-gateway:latest")
GATEWAY_DOCKERFILE = "Dockerfile.gateway"
_REPO_ROOT = Path(__file__).resolve().parents[2]
REPO_ROOT = Path(__file__).resolve().parents[2]
def rotate_gateway_ca(ca_dir: Path | None = None) -> list[Path]:
@@ -118,180 +112,8 @@ class Gateway(abc.ABC):
"""Remove the gateway. Idempotent — absent is success."""
class DockerGateway(Gateway):
"""The consolidated gateway as a single, fixed-name Docker container.
`image_ref` defaults to the gateway data-plane image; `ensure_built`
builds it from `Dockerfile.gateway` when it's missing. (Note: slice 5
builds + launches the bundle container; wiring its per-bottle,
source-IP-keyed config is a later slice — see PRD 0070.)"""
def __init__(
self,
image_ref: str = GATEWAY_IMAGE,
*,
name: str = GATEWAY_NAME,
network: str = GATEWAY_NETWORK,
orchestrator_url: str = "",
build_context: Path | None = None,
dockerfile: str | None = GATEWAY_DOCKERFILE,
host_port_bindings: tuple[int, ...] = (),
) -> None:
self.image_ref = image_ref
self.name = name
self.network = network
# The control-plane URL the gateway's data plane resolves per bottle
# against — reached by container name over docker DNS on the shared
# network (container↔container, no host firewall). Mandatory to *run*
# the gateway (see `ensure_running`); empty is tolerated only for the
# construct-then-read-CA path (`ca_cert_pem` on an already-running
# container), which never launches a container.
self._orchestrator_url = orchestrator_url
self._build_context = build_context or _REPO_ROOT
self._dockerfile = dockerfile
# Ports published on the host (0.0.0.0). Used by the Firecracker
# backend's dev-harness gateway so VMs can reach it via their TAP link;
# Docker's DNAT + the nft `ct status dnat accept` rule handle the rest.
self._host_port_bindings = host_port_bindings
def image_exists(self) -> bool:
return run_docker(["docker", "image", "inspect", self.image_ref]).returncode == 0
def ensure_built(self) -> None:
"""Build the bundle image from its Dockerfile, **cache-aware** — cheap
(a cache check) when nothing changed, a real rebuild when the flat
sources (egress addon / git-http / policy_resolver / supervise) moved.
This deliberately builds every time rather than build-if-missing: the
per-bottle model kept the image fresh via compose's `build:` on up, and
a stale image silently runs the OLD single-tenant daemons. No-op only
when no dockerfile is configured (a pre-pulled image). BOT_BOTTLE_NO_CACHE
forces a full rebuild (parity with `start --no-cache`)."""
if self._dockerfile is None:
return
argv = ["docker", "build", "-t", self.image_ref,
"-f", str(self._build_context / self._dockerfile),
str(self._build_context)]
if os.environ.get("BOT_BOTTLE_NO_CACHE"):
argv.insert(2, "--no-cache")
proc = run_docker(argv)
if proc.returncode != 0:
raise GatewayError(f"gateway image build failed: {proc.stderr.strip()}")
def is_running(self) -> bool:
proc = run_docker([
"docker", "ps",
"--filter", f"name=^{self.name}$",
"--filter", "status=running",
"--format", "{{.Names}}",
])
return self.name in proc.stdout.split()
def _running_image_is_current(self) -> bool:
"""True iff the running gateway was created from the *current*
`image_ref`. When `ensure_built` rebuilds the image (a source change),
the running container is still the OLD image running the OLD flat
daemons — so this is how a rebuild actually takes effect: a mismatch
means recreate."""
running = run_docker(["docker", "inspect", "--format", "{{.Image}}", self.name])
current = run_docker(["docker", "image", "inspect", "--format", "{{.Id}}", self.image_ref])
if running.returncode != 0 or current.returncode != 0:
return True # can't compare → don't churn a working container
return running.stdout.strip() == current.stdout.strip()
def _ensure_network(self) -> None:
"""Create the shared gateway network if it doesn't exist. Idempotent —
a concurrent create loses harmlessly (the loser sees 'already exists').
Docker picks the subnet; the launcher reads it back to allocate IPs."""
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 ensure_running(self) -> None:
# Fail closed on a missing policy source. The data-plane daemons are
# resolver-only now (PRD 0070) — without an orchestrator URL egress
# raises, git-http exits 1, and supervise exits 2 — so launching a
# gateway without one would only crash-loop its daemons. Refuse here so
# the misconfiguration surfaces as a clear error, not a broken container.
if not self._orchestrator_url:
raise GatewayError(
"gateway requires an orchestrator URL to run "
"(resolver-only data plane; no single-tenant fallback)"
)
# Recreate when the running container's image is stale (a rebuild),
# so source changes to the gateway's flat daemons take effect — not
# just when the container is absent.
if self.is_running() and self._running_image_is_current():
return
self._ensure_network()
# Clear any stale (stopped OR outdated-image) container holding the
# fixed name, then start fresh. `rm --force` on an absent name is a
# tolerated no-op.
run_docker(["docker", "rm", "--force", self.name])
argv = [
"docker", "run", "--detach",
"--name", self.name,
"--label", GATEWAY_LABEL,
"--network", self.network,
# Persist the self-generated CA on the host so it survives both
# container recreation AND docker volume pruning (agents trust it)
# — see host_gateway_ca_dir / issue #450.
"--volume", f"{host_gateway_ca_dir()}:{MITMPROXY_HOME}",
# No DB mount: the data plane (egress / supervise / git-gate) reaches
# the supervise queue over the control-plane RPC and never opens
# bot-bottle.db, so the gateway container gets no file handle on it
# (PRD 0070 / issue #469).
]
for port in self._host_port_bindings:
argv += ["--publish", f"0.0.0.0:{port}:{port}"]
run_env = dict(os.environ)
# The gateway's egress / git / supervise daemons resolve source-IP ->
# policy against the control plane per request (guaranteed non-empty by
# the check above).
argv += ["--env", f"BOT_BOTTLE_ORCHESTRATOR_URL={self._orchestrator_url}"]
# ...presenting a role-scoped `gateway` token (a signed JWT minted from
# the host signing key) on those calls. The gateway never receives the
# signing key — only this pre-minted token, which it cannot rewrite into
# a `cli` token, so a compromised data-plane process can't drive the
# operator routes (issue #469 review). Bare `--env NAME` keeps the value
# off argv / `docker inspect`; only the gateway (not the agent) is given it.
argv += ["--env", CONTROL_AUTH_JWT_ENV]
run_env[CONTROL_AUTH_JWT_ENV] = mint(ROLE_GATEWAY, host_control_plane_token())
argv.append(self.image_ref)
proc = run_docker(argv, env=run_env)
if proc.returncode != 0:
raise GatewayError(f"gateway failed to start: {proc.stderr.strip()}")
def ca_cert_pem(self, *, timeout: float = DEFAULT_CA_TIMEOUT_SECONDS) -> str:
"""The gateway's CA certificate (PEM) that agents install to trust its
TLS interception. mitmproxy generates it a moment after the container
starts, so this **polls** for it (up to `timeout`) rather than assuming
it's already there on a fresh gateway — raising only if it never
appears."""
deadline = time.monotonic() + timeout
while True:
proc = run_docker(["docker", "exec", self.name, "cat", GATEWAY_CA_CERT])
if proc.returncode == 0 and proc.stdout.strip():
return proc.stdout
if time.monotonic() >= deadline:
raise GatewayError(
f"gateway CA cert not available after {timeout:g}s: "
f"{proc.stderr.strip() or 'empty'}"
)
time.sleep(_CA_POLL_SECONDS)
def stop(self) -> None:
proc = run_docker(["docker", "rm", "--force", self.name])
if proc.returncode != 0 and "No such container" not in proc.stderr:
raise GatewayError(f"gateway failed to stop: {proc.stderr.strip()}")
__all__ = [
"Gateway", "DockerGateway", "GatewayError", "rotate_gateway_ca",
"Gateway", "GatewayError", "rotate_gateway_ca",
"GATEWAY_NAME", "GATEWAY_LABEL", "GATEWAY_IMAGE", "GATEWAY_NETWORK",
"GATEWAY_CA_CERT", "GATEWAY_CA_GLOB",
]