Dockerfile.gateway

@@ -1,4 +1,12 @@
-# Per-bottle sidecar bundle image (PRD 0024).
+# Gateway data-plane image (PRD 0024 bundle shape; PRD 0070 gateway).
+#
+# The egress / git-gate / supervise *data plane* — one image, shared by
+# the consolidated per-host gateway (PRD 0070) and, on backends that
+# still run a per-bottle bundle, each bottle's sidecar. It is NOT the
+# orchestrator control plane: that is the separate, lean
+# `bot-bottle-orchestrator` image (Dockerfile.orchestrator, #384), which
+# ships only python + the stdlib-only `bot_bottle` package and none of
+# this image's mitmproxy / git / gitleaks payload.
 #
 # Collapses the prior per-sidecar images (egress, git-gate,
 # supervise) into one. A small stdlib-Python init supervisor at

Dockerfile.orchestrator

@@ -0,0 +1,27 @@
+# Orchestrator control-plane image (PRD 0070, #384).
+#
+# The per-host orchestrator runs `python3 -m bot_bottle.orchestrator`.
+# The `bot_bottle` package is **stdlib-only** by design, so the control
+# plane needs nothing but a Python runtime — none of the gateway's
+# mitmproxy / git / gitleaks payload (that is the separate
+# `bot-bottle-gateway` image, Dockerfile.gateway). Splitting them keeps
+# the secret-dense control plane (it concentrates every bottle's egress
+# tokens — see PRD 0070's "secret concentration") on a minimal
+# dependency surface.
+#
+# The repo is bind-mounted read-only into the container at run time (see
+# `orchestrator/lifecycle.py`), so the source is NOT copied in here: the
+# image is just the runtime. `ensure_running` recreates the container
+# only when the bind-mounted source hash changes (#381), which is why
+# the code stays a mount rather than a baked layer.
+
+FROM python:3.12-slim
+
+# No third-party deps to install — stdlib only. Kept as an explicit,
+# self-documenting stage so a future confinement step (baking the
+# package, dropping the bind mount) has an obvious home.
+WORKDIR /app
+
+# Documentation only; lifecycle.py overrides the entrypoint to
+# `python3 -m bot_bottle.orchestrator` with the runtime flags.
+ENTRYPOINT ["python3", "-m", "bot_bottle.orchestrator"]

bot_bottle/backend/docker/sidecar_bundle.py

@@ -1,30 +1,33 @@
 """Sidecar bundle constants + helpers for the Docker backend
 (PRD 0024).
 
-The bundle image (built by Dockerfile.sidecars, PRD 0024 chunk 1)
-runs egress + git-gate + supervise as one container per bottle
-under a small Python init supervisor. As of chunk 5 the bundle
-is the only shape — the legacy four-sidecar topology and its
-`BOT_BOTTLE_SIDECAR_BUNDLE` feature flag are gone."""
+A per-bottle sidecar bundle runs egress + git-gate + supervise as one
+container under a small Python init supervisor. As of PRD 0024 chunk 5
+the bundle is the only shape — the legacy four-sidecar topology and its
+`BOT_BOTTLE_SIDECAR_BUNDLE` feature flag are gone.
+
+The bundle's image is the **same data plane** as the consolidated
+per-host gateway (PRD 0070), so it is one image with one name and one
+Dockerfile: `bot-bottle-gateway` / `Dockerfile.gateway` (#384). These
+constants alias the gateway's so a per-bottle bundle and the shared
+gateway can never drift onto different images."""
 
 from __future__ import annotations
 
-import os
+from ...orchestrator.gateway import GATEWAY_DOCKERFILE, GATEWAY_IMAGE
 
 
-# Bundle image. Defaults to a built-locally tag (built from the
-# repo's Dockerfile.sidecars via compose `build:`). Operators
-# pinning to a published digest can override via env.
-SIDECAR_BUNDLE_IMAGE = os.environ.get(
-    "BOT_BOTTLE_SIDECAR_IMAGE",
-    "bot-bottle-sidecars:latest",
-)
-
-SIDECAR_BUNDLE_DOCKERFILE = "Dockerfile.sidecars"
+# The per-bottle bundle image == the gateway data-plane image (aliased so
+# there is one source of truth; the `BOT_BOTTLE_GATEWAY_IMAGE` env override
+# on the gateway constant applies here too).
+SIDECAR_BUNDLE_IMAGE = GATEWAY_IMAGE
+SIDECAR_BUNDLE_DOCKERFILE = GATEWAY_DOCKERFILE
 
 
 def sidecar_bundle_container_name(slug: str) -> str:
     """`bot-bottle-sidecars-<slug>`. Same prefix scheme as the
     per-sidecar containers it replaces, so the dashboard's
-    discovery-by-prefix logic keeps working."""
+    discovery-by-prefix logic keeps working. (The per-bottle *container*
+    name keeps the historical `sidecars-` prefix; only the *image* was
+    renamed to `bot-bottle-gateway` in #384.)"""
     return f"bot-bottle-sidecars-{slug}"

bot_bottle/egress_addon_core.py

@@ -8,7 +8,7 @@ container.
 
 Imports: stdlib + `yaml_subset` (which is itself stdlib-only and
 ships flat into the sidecar bundle image alongside this file —
-see `Dockerfile.sidecars`)."""
+see `Dockerfile.gateway`)."""
 
 from __future__ import annotations
 
@@ -22,7 +22,7 @@ except ImportError:  # pragma: no cover - host-side path
     from .yaml_subset import YamlSubsetError, parse_yaml_subset
 
 # DLP detector-config parsing lives in a sibling module (also flat-bundled
-# into the gateway — see Dockerfile.sidecars). Re-exported below so existing
+# into the gateway — see Dockerfile.gateway). Re-exported below so existing
 # `from egress_addon_core import ON_MATCH_*` callers keep working.
 try:
     from egress_dlp_config import (  # type: ignore[import-not-found]

bot_bottle/egress_dlp_config.py

@@ -7,7 +7,7 @@ kept apart from the request-time scan/decision flow in `egress_addon_core`
 so each half reads top-to-bottom without scrolling past the other.
 
 Stdlib-only; ships flat into the sidecar bundle image alongside
-`egress_addon_core.py` — see `Dockerfile.sidecars`."""
+`egress_addon_core.py` — see `Dockerfile.gateway`."""
 
 from __future__ import annotations
 

bot_bottle/git_http_backend.py

@@ -28,7 +28,7 @@ from pathlib import Path
 from urllib.parse import urlsplit
 
 # policy_resolver ships flat alongside this file in the sidecar bundle
-# image (see Dockerfile.sidecars); the bot_bottle.* fallback is the
+# image (see Dockerfile.gateway); the bot_bottle.* fallback is the
 # host-side / test path. Mirrors egress_addon's import shape.
 try:
     from policy_resolver import (  # type: ignore[import-not-found]
@@ -104,7 +104,7 @@ def resolve_sandbox_root(
 
 # Mirrors git_gate_render.GIT_GATE_TIMEOUT_SECS. Duplicated rather than
 # imported: this module ships as a flat top-level sibling in the sidecar
-# bundle image (see Dockerfile.sidecars), not as part of the bot_bottle
+# bundle image (see Dockerfile.gateway), not as part of the bot_bottle
 # package, so `bot_bottle.git_gate` and its dependency chain aren't
 # available at runtime.
 GIT_GATE_TIMEOUT_SECS = 15

bot_bottle/orchestrator/gateway.py

@@ -45,12 +45,12 @@ MITMPROXY_HOME = "/home/mitmproxy/.mitmproxy"
 GATEWAY_CA_VOLUME = "bot-bottle-gateway-mitmproxy"
 GATEWAY_CA_CERT = f"{MITMPROXY_HOME}/mitmproxy-ca-cert.pem"
 
-# The real sidecar-bundle image + its Dockerfile. Kept as a local constant
+# The gateway data-plane image + its Dockerfile. Kept as a local constant
 # rather than imported from backend.docker.sidecar_bundle, which would drag
 # the whole backend layer into the lean orchestrator (see #359); unify when
-# that lands. Env override matches the backend's BOT_BOTTLE_SIDECAR_IMAGE.
-GATEWAY_IMAGE = os.environ.get("BOT_BOTTLE_SIDECAR_IMAGE", "bot-bottle-sidecars:latest")
-GATEWAY_DOCKERFILE = "Dockerfile.sidecars"
+# 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]
 
 
@@ -86,8 +86,8 @@ class Gateway(abc.ABC):
 class DockerGateway(Gateway):
     """The consolidated gateway as a single, fixed-name Docker container.
 
-    `image_ref` defaults to the real sidecar-bundle image; `ensure_built`
-    builds it from `Dockerfile.sidecars` when it's missing. (Note: slice 5
+    `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.)"""
 

bot_bottle/orchestrator/lifecycle.py

@@ -17,6 +17,7 @@ names + the published port).
 from __future__ import annotations
 
 import hashlib
+import os
 import time
 import urllib.error
 import urllib.request
@@ -25,11 +26,19 @@ from pathlib import Path
 from .. import log
 from ..docker_cmd import run_docker
 from ..paths import bot_bottle_root
-from .gateway import GATEWAY_IMAGE, GATEWAY_NETWORK, DockerGateway
+from .gateway import GATEWAY_IMAGE, GATEWAY_NETWORK, DockerGateway, GatewayError
 
 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.
+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`.
@@ -37,7 +46,7 @@ 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 bundle image's python is enough).
+# is stdlib-only, so the lean orchestrator image's python is enough).
 _REPO_ROOT = Path(__file__).resolve().parents[2]
 _APP_DIR = "/app"
 _ROOT_IN_CONTAINER = "/bot-bottle-root"
@@ -76,13 +85,19 @@ class OrchestratorService:
         *,
         port: int = DEFAULT_PORT,
         network: str = GATEWAY_NETWORK,
-        image: str = GATEWAY_IMAGE,
+        image: str = ORCHESTRATOR_IMAGE,
+        gateway_image: str = GATEWAY_IMAGE,
         repo_root: Path = _REPO_ROOT,
         host_root: Path | None = None,
     ) -> 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._repo_root = repo_root
         self._host_root = host_root or bot_bottle_root()
 
@@ -141,7 +156,29 @@ class OrchestratorService:
             )
 
     def _gateway(self) -> DockerGateway:
-        return DockerGateway(self.image, network=self.network, orchestrator_url=self.internal_url)
+        return DockerGateway(
+            self._gateway_image, 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
@@ -181,6 +218,7 @@ class OrchestratorService:
         if self.is_healthy() and self._orchestrator_source_current(current_hash):
             return self.url
 
+        self._ensure_orchestrator_image()
         log.info("starting orchestrator container", context={"name": ORCHESTRATOR_NAME})
         self._run_orchestrator_container(current_hash)
 
@@ -204,6 +242,7 @@ __all__ = [
     "OrchestratorService",
     "OrchestratorStartError",
     "ORCHESTRATOR_NAME",
+    "ORCHESTRATOR_IMAGE",
     "DEFAULT_PORT",
     "DEFAULT_STARTUP_TIMEOUT_SECONDS",
 ]

bot_bottle/sidecar_init.py

@@ -1,6 +1,6 @@
 """Per-bottle sidecar supervisor (PRD 0024 chunk 1).
 
-PID 1 inside the `bot-bottle-sidecars` bundle image. Spawns
+PID 1 inside the `bot-bottle-gateway` data-plane image. Spawns
 the configured daemons (egress, git-gate, supervise),
 forwards SIGTERM/SIGINT to each child, and propagates per-daemon
 stdout+stderr to the container log with a `[name] ` prefix.

bot_bottle/supervise_server.py

@@ -50,7 +50,7 @@ from dataclasses import dataclass, replace
 
 try:
     # Same-directory imports inside the bundle container; these files are
-    # COPYed flat under /app by Dockerfile.sidecars.
+    # COPYed flat under /app by Dockerfile.gateway.
     from egress_addon_core import LOG_OFF, load_config
     from policy_resolver import PolicyResolveError, PolicyResolver
     import supervise as _sv

tests/README.md

@@ -48,7 +48,7 @@ Discovery is invoked with `-t .` (top-level dir = repo root) so the
   the bottle's runtime, and creates zero Docker resources.
 - `test_orphan_cleanup.py` — `network_remove` is idempotent against
   missing resources, so the EXIT trap can call it unconditionally.
-- `test_sidecar_bundle_image.py` — builds Dockerfile.sidecars and
+- `test_sidecar_bundle_image.py` — builds Dockerfile.gateway and
   probes that gitleaks / mitmdump / supervise are all reachable
   inside the bundle.
 - `test_sidecar_bundle_compose.py` — end-to-end compose-up of an

tests/integration/test_orchestrator_docker_gateway_build.py

@@ -21,7 +21,7 @@ IMAGE = "busybox"
 class TestDockerGatewayImageExists(unittest.TestCase):
     def test_image_exists_true_for_present_false_for_absent(self) -> None:
         # Ensure the tiny image is present (build_if_missing is disabled here
-        # so this never triggers a Dockerfile.sidecars build).
+        # so this never triggers a Dockerfile.gateway build).
         subprocess.run(
             ["docker", "pull", IMAGE],
             stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,

tests/integration/test_sidecar_bundle_image.py

@@ -6,7 +6,7 @@ config (routes.yaml, etc) — that lands in chunk 2 when the
 renderer wires the bundle into compose. What we verify here is
 the chunk-1 contract:
 
-  - Dockerfile.sidecars builds (multi-stage works, base layers
+  - Dockerfile.gateway builds (multi-stage works, base layers
     pull, COPYs resolve).
   - gitleaks, mitmdump are at the documented paths and answer
     `--version`.
@@ -28,8 +28,8 @@ import unittest
 from tests._docker import skip_unless_docker
 
 
-_IMAGE = "bot-bottle-sidecars-test:chunk1"
-_DOCKERFILE = "Dockerfile.sidecars"
+_IMAGE = "bot-bottle-gateway-test:chunk1"
+_DOCKERFILE = "Dockerfile.gateway"
 
 
 @skip_unless_docker()

tests/unit/test_compose.py

@@ -297,8 +297,8 @@ class TestSidecarBundleShape(unittest.TestCase):
 
     def test_bundle_uses_bundle_image_and_dockerfile(self):
         sc = self._render()["services"]["sidecars"]
-        self.assertEqual("bot-bottle-sidecars:latest", sc["image"])
-        self.assertEqual("Dockerfile.sidecars", sc["build"]["dockerfile"])
+        self.assertEqual("bot-bottle-gateway:latest", sc["image"])
+        self.assertEqual("Dockerfile.gateway", sc["build"]["dockerfile"])
 
     def test_bundle_container_name_uses_sidecars_prefix(self):
         sc = self._render()["services"]["sidecars"]

tests/unit/test_macos_container_util.py

@@ -88,14 +88,14 @@ resolver #2
                  "BOT_BOTTLE_MACOS_CONTAINER_DNS": "9.9.9.9",
              }):
             util.build_image(
-                "bot-bottle-sidecars:latest",
+                "bot-bottle-gateway:latest",
                 "/repo",
-                dockerfile="Dockerfile.sidecars",
+                dockerfile="Dockerfile.gateway",
             )
         self.assertEqual(
             [
-                "container", "build", "-t", "bot-bottle-sidecars:latest",
-                "--dns", "9.9.9.9", "-f", "/repo/Dockerfile.sidecars", "/repo",
+                "container", "build", "-t", "bot-bottle-gateway:latest",
+                "--dns", "9.9.9.9", "-f", "/repo/Dockerfile.gateway", "/repo",
             ],
             run.call_args_list[-1].args[0],
         )

tests/unit/test_orchestrator_gateway.py

@@ -24,7 +24,7 @@ def _proc(returncode: int = 0, stdout: str = "", stderr: str = "") -> Mock:
 
 class TestDockerGateway(unittest.TestCase):
     def setUp(self) -> None:
-        self.sc = DockerGateway("bot-bottle-sidecars:latest")
+        self.sc = DockerGateway("bot-bottle-gateway:latest")
 
     def test_default_name(self) -> None:
         self.assertEqual(GATEWAY_NAME, self.sc.name)
@@ -86,7 +86,7 @@ class TestDockerGateway(unittest.TestCase):
         runs = [c for c in calls if c[:2] == ["docker", "run"]]
         self.assertEqual(1, len(runs))
         self.assertIn(self.sc.name, runs[0])
-        self.assertIn("bot-bottle-sidecars:latest", runs[0])
+        self.assertIn("bot-bottle-gateway:latest", runs[0])
         # Runs on the shared gateway network so agents can reach it by IP.
         self.assertEqual(self.sc.network, runs[0][runs[0].index("--network") + 1])
         # Persists its CA on a named volume so agents keep trusting it.
@@ -183,7 +183,7 @@ class TestDockerGatewayBuild(unittest.TestCase):
         builds = [c for c in calls if c[:2] == ["docker", "build"]]
         self.assertEqual(1, len(builds))
         self.assertIn(self.sc.image_ref, builds[0])
-        self.assertTrue(any(a.endswith("Dockerfile.sidecars") for a in builds[0]))
+        self.assertTrue(any(a.endswith("Dockerfile.gateway") for a in builds[0]))
         self.assertNotIn("--no-cache", builds[0])
 
     def test_ensure_built_no_cache_env_forces_full_rebuild(self) -> None:

tests/unit/test_orchestrator_lifecycle.py

@@ -9,6 +9,7 @@ from pathlib import Path
 from unittest.mock import MagicMock, Mock, patch
 
 from bot_bottle.orchestrator.lifecycle import (
+    ORCHESTRATOR_IMAGE,
     ORCHESTRATOR_NAME,
     ORCHESTRATOR_SOURCE_HASH_LABEL,
     OrchestratorService,
@@ -121,6 +122,45 @@ class TestOrchestratorService(unittest.TestCase):
         self.assertIn("bot_bottle.orchestrator", argv)
         self.assertEqual("127.0.0.1:8099:8099", argv[argv.index("--publish") + 1])
 
+    def test_ensure_running_builds_lean_orchestrator_image_when_missing(self) -> None:
+        # The control plane runs its own lean image (#384), distinct from the
+        # gateway data plane — built from Dockerfile.orchestrator when absent.
+        calls: list[list[str]] = []
+
+        def fake(argv: list[str]) -> Mock:
+            calls.append(argv)
+            if argv[:2] == ["docker", "ps"]:
+                return _proc(stdout="")                 # orchestrator not running
+            if argv[:3] == ["docker", "image", "inspect"]:
+                return _proc(returncode=1)               # image absent -> build
+            return _proc()
+
+        with patch(_URLOPEN, side_effect=[urllib.error.URLError("down"), _health(200)]), \
+                patch(_GATEWAY), patch(_RUN, side_effect=fake), patch(_SLEEP):
+            self.svc.ensure_running()
+        builds = [c for c in calls if c[:2] == ["docker", "build"]]
+        self.assertEqual(1, len(builds))
+        self.assertIn(ORCHESTRATOR_IMAGE, builds[0])
+        self.assertTrue(any(a.endswith("Dockerfile.orchestrator") for a in builds[0]))
+        # It is NOT the gateway image/dockerfile — the split is the point.
+        self.assertFalse(any("Dockerfile.gateway" in a for a in builds[0]))
+
+    def test_ensure_running_skips_orchestrator_image_build_when_present(self) -> None:
+        calls: list[list[str]] = []
+
+        def fake(argv: list[str]) -> Mock:
+            calls.append(argv)
+            if argv[:2] == ["docker", "ps"]:
+                return _proc(stdout="")
+            if argv[:3] == ["docker", "image", "inspect"]:
+                return _proc(returncode=0)               # image present -> no build
+            return _proc()
+
+        with patch(_URLOPEN, side_effect=[urllib.error.URLError("down"), _health(200)]), \
+                patch(_GATEWAY), patch(_RUN, side_effect=fake), patch(_SLEEP):
+            self.svc.ensure_running()
+        self.assertEqual([], [c for c in calls if c[:2] == ["docker", "build"]])
+
     def test_ensure_running_raises_on_timeout(self) -> None:
         with patch(_URLOPEN, side_effect=urllib.error.URLError("down")), \
                 patch(_GATEWAY), patch(_RUN, return_value=Mock(returncode=0, stderr="")), \