Compare commits
40 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| dcf81ee2ce | |||
| 65af83b441 | |||
| 716928315e | |||
| 0c2d0aca63 | |||
| 610c4173a5 | |||
| 6492cc258a | |||
| d9c8a4645d | |||
| 5537b29bbc | |||
| 90c69fb30b | |||
| 21f3436d03 | |||
| 2f71d48189 | |||
| 1f9b957604 | |||
| 9e2e953de6 | |||
| d9e3b61c37 | |||
| 8a79450b0a | |||
| b6eb728a4d | |||
| 71f40fe528 | |||
| fd7448c6a2 | |||
| 3178453f83 | |||
| 47268f6fd6 | |||
| fc86b0309f | |||
| 21a89c7c1f | |||
| af1d1ef304 | |||
| 4692a92c19 | |||
| 004c530194 | |||
| 713566ad85 | |||
| 47bc627ead | |||
| 13d9f3843d | |||
| 219fd7493f | |||
| 1175e17d4e | |||
| 590f3cebd7 | |||
| 36bb8a30ef | |||
| 124b1f473c | |||
| 7b2098cad0 | |||
| 0e89d6ae5a | |||
| 0fb4a026ac | |||
| 7c57785f48 | |||
| 58e5275e8f | |||
| 3b1b716822 | |||
| ce440fabc4 |
@@ -111,6 +111,11 @@ class DockerBottleBackend(BottleBackend["DockerBottlePlan", "DockerBottleCleanup
|
||||
plumbing needed; the alias resolves inside the bridge."""
|
||||
if plan.supervise_plan is None:
|
||||
return ""
|
||||
# Consolidated: the supervise daemon lives on the shared gateway, so
|
||||
# the agent registers the gateway address (NO_PROXY bypasses egress),
|
||||
# not the per-bottle `supervise` alias.
|
||||
if plan.agent_supervise_url:
|
||||
return plan.agent_supervise_url
|
||||
return f"http://{SUPERVISE_HOSTNAME}:{SUPERVISE_PORT}/"
|
||||
|
||||
def prepare_cleanup(self) -> DockerBottleCleanupPlan:
|
||||
|
||||
@@ -28,11 +28,30 @@ class DockerBottlePlan(BottlePlan):
|
||||
# accidental log of the plan dataclass.
|
||||
forwarded_env: dict[str, str] = field(repr=False)
|
||||
use_runsc: bool
|
||||
# Consolidated mode (PRD 0070): the agent reaches git-gate over HTTP at the
|
||||
# shared gateway's address (`http://<gateway_ip>:9420`), set at launch.
|
||||
# Empty → single-tenant defaults (the `git-gate` alias over git://).
|
||||
agent_git_gate_url: str = ""
|
||||
# Likewise the supervise MCP endpoint at the gateway (`http://<gw>:9100/`);
|
||||
# empty → the single-tenant `supervise` alias.
|
||||
agent_supervise_url: str = ""
|
||||
|
||||
@property
|
||||
def container_name(self) -> str:
|
||||
return self.agent_provision.instance_name
|
||||
|
||||
@property
|
||||
def git_gate_insteadof_host(self) -> str:
|
||||
if self.agent_git_gate_url.startswith("http://"):
|
||||
return self.agent_git_gate_url.removeprefix("http://").rstrip("/")
|
||||
return super().git_gate_insteadof_host
|
||||
|
||||
@property
|
||||
def git_gate_insteadof_scheme(self) -> str:
|
||||
if self.agent_git_gate_url.startswith("http://"):
|
||||
return "http"
|
||||
return super().git_gate_insteadof_scheme
|
||||
|
||||
@property
|
||||
def image(self) -> str:
|
||||
return self.agent_provision.image
|
||||
|
||||
@@ -0,0 +1,78 @@
|
||||
"""Agent-only compose for the consolidated docker backend (PRD 0070).
|
||||
|
||||
The per-bottle model rendered a compose project with the agent *and* a
|
||||
sidecar bundle on two per-bottle networks. In the consolidated model the
|
||||
sidecars are gone — one shared gateway serves every bottle — so this renders
|
||||
just the agent, attached to the **external shared gateway network** with the
|
||||
pinned source IP the orchestrator allocated, and pointed at the gateway's
|
||||
address for egress (and, around the proxy, for git-http / supervise).
|
||||
|
||||
Pure: it takes the launch-time `LaunchContext` values (gateway address,
|
||||
source IP, network) and the prepared plan, and returns a compose dict — no
|
||||
docker, so it's testable in isolation.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any
|
||||
|
||||
from ...egress import egress_agent_env_entries
|
||||
from ..util import AGENT_CA_BUNDLE, AGENT_CA_PATH
|
||||
from .bottle_plan import DockerBottlePlan
|
||||
from .egress import EGRESS_PORT
|
||||
|
||||
|
||||
def consolidated_agent_compose(
|
||||
plan: DockerBottlePlan,
|
||||
*,
|
||||
gateway_ip: str,
|
||||
source_ip: str,
|
||||
network: str,
|
||||
) -> dict[str, Any]:
|
||||
"""A compose spec with only the agent service, on the external gateway
|
||||
network at `source_ip`, proxying egress through `gateway_ip`."""
|
||||
proxy_url = f"http://{gateway_ip}:{EGRESS_PORT}"
|
||||
# git-http + supervise live on the gateway too and must NOT go through the
|
||||
# egress proxy — the agent reaches them directly by the gateway address.
|
||||
no_proxy = f"localhost,127.0.0.1,{gateway_ip}"
|
||||
env: list[str] = [
|
||||
f"HTTPS_PROXY={proxy_url}",
|
||||
f"HTTP_PROXY={proxy_url}",
|
||||
f"https_proxy={proxy_url}",
|
||||
f"http_proxy={proxy_url}",
|
||||
f"NO_PROXY={no_proxy}",
|
||||
f"no_proxy={no_proxy}",
|
||||
f"NODE_EXTRA_CA_CERTS={AGENT_CA_PATH}",
|
||||
f"SSL_CERT_FILE={AGENT_CA_BUNDLE}",
|
||||
f"REQUESTS_CA_BUNDLE={AGENT_CA_BUNDLE}",
|
||||
]
|
||||
for name, value in sorted(plan.agent_provision.guest_env.items()):
|
||||
env.append(f"{name}={value}")
|
||||
# Forwarded vars: bare name → inherits from the compose-up process env so
|
||||
# the secret value never lands on argv or in the compose file.
|
||||
for name in sorted(plan.forwarded_env.keys()):
|
||||
env.append(name)
|
||||
env.extend(egress_agent_env_entries(plan.egress_plan))
|
||||
|
||||
service: dict[str, Any] = {
|
||||
"image": plan.image,
|
||||
"container_name": plan.container_name,
|
||||
"command": ["sleep", "infinity"],
|
||||
# Pinned address on the shared gateway network — the orchestrator
|
||||
# registered this IP, and the gateway attributes the bottle by it.
|
||||
"networks": {network: {"ipv4_address": source_ip}},
|
||||
"environment": env,
|
||||
}
|
||||
if plan.use_runsc:
|
||||
service["runtime"] = "runsc"
|
||||
|
||||
return {
|
||||
"name": f"bot-bottle-{plan.slug}",
|
||||
"services": {"agent": service},
|
||||
# The gateway network is created + owned by the orchestrator; compose
|
||||
# attaches to it (external) and must not create or destroy it.
|
||||
"networks": {network: {"external": True}},
|
||||
}
|
||||
|
||||
|
||||
__all__ = ["consolidated_agent_compose"]
|
||||
@@ -0,0 +1,151 @@
|
||||
"""Consolidated bottle launch sequence for the docker backend (PRD 0070).
|
||||
|
||||
Composes the orchestrator primitives into the register/teardown sequence that
|
||||
replaces the per-bottle sidecar bundle:
|
||||
|
||||
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.
|
||||
|
||||
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
|
||||
orchestrator-facing wiring so that sequence stays testable in isolation.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass
|
||||
|
||||
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 .gateway_net import next_free_ip
|
||||
from .gateway_provision import deprovision_git_gate, provision_git_gate
|
||||
|
||||
|
||||
class ConsolidatedLaunchError(RuntimeError):
|
||||
"""The consolidated register/provision sequence could not complete."""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class LaunchContext:
|
||||
"""What the agent container needs to join the shared gateway."""
|
||||
|
||||
bottle_id: str
|
||||
identity_token: str
|
||||
source_ip: str # the agent's pinned address (attribution key)
|
||||
network: str # the shared gateway network to attach to
|
||||
gateway_ip: str # the gateway's address — the agent's proxy target
|
||||
orchestrator_url: str
|
||||
|
||||
|
||||
def _network_cidr(network: str) -> str:
|
||||
"""The gateway network's IPv4 subnet, or raise."""
|
||||
proc = run_docker([
|
||||
"docker", "network", "inspect",
|
||||
"--format", "{{range .IPAM.Config}}{{.Subnet}}{{end}}", network,
|
||||
])
|
||||
cidr = proc.stdout.strip()
|
||||
if proc.returncode != 0 or not cidr:
|
||||
raise ConsolidatedLaunchError(
|
||||
f"gateway network {network} has no subnet: {proc.stderr.strip()}"
|
||||
)
|
||||
return cidr
|
||||
|
||||
|
||||
def _container_ip(name: str, network: str) -> str:
|
||||
"""A container's IPv4 address on `network`, or raise."""
|
||||
proc = run_docker([
|
||||
"docker", "inspect", "--format",
|
||||
f'{{{{(index .NetworkSettings.Networks "{network}").IPAddress}}}}', name,
|
||||
])
|
||||
ip = proc.stdout.strip()
|
||||
if proc.returncode != 0 or not ip:
|
||||
raise ConsolidatedLaunchError(
|
||||
f"gateway {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)."""
|
||||
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
|
||||
|
||||
|
||||
def launch_consolidated(
|
||||
egress_plan: EgressPlan,
|
||||
git_gate_plan: GitGatePlan,
|
||||
*,
|
||||
image_ref: str = "",
|
||||
service: OrchestratorService | None = None,
|
||||
gateway_name: str = GATEWAY_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."""
|
||||
service = service or OrchestratorService()
|
||||
url = service.ensure_running()
|
||||
client = OrchestratorClient(url)
|
||||
|
||||
cidr = _network_cidr(network)
|
||||
gateway_ip = _container_ip(gateway_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,
|
||||
)
|
||||
try:
|
||||
provision_git_gate(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,
|
||||
source_ip=source_ip,
|
||||
network=network,
|
||||
gateway_ip=gateway_ip,
|
||||
orchestrator_url=url,
|
||||
)
|
||||
|
||||
|
||||
def teardown_consolidated(
|
||||
bottle_id: str, *, orchestrator_url: str, gateway_name: str = GATEWAY_NAME,
|
||||
) -> 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."""
|
||||
OrchestratorClient(orchestrator_url).teardown_bottle(bottle_id)
|
||||
deprovision_git_gate(gateway_name, bottle_id)
|
||||
|
||||
|
||||
__all__ = [
|
||||
"LaunchContext",
|
||||
"launch_consolidated",
|
||||
"teardown_consolidated",
|
||||
"ConsolidatedLaunchError",
|
||||
]
|
||||
@@ -0,0 +1,47 @@
|
||||
"""Shared-gateway source-IP allocation for the consolidated docker backend
|
||||
(PRD 0070).
|
||||
|
||||
In the consolidated model one gateway container serves every bottle over a
|
||||
single shared docker network, and each agent bottle attaches with a pinned,
|
||||
deterministic address that the gateway uses as its **attribution key**. This
|
||||
allocates those addresses from the network's subnet, skipping the reserved
|
||||
ones — the network address and broadcast (excluded by `hosts()`), docker's
|
||||
router `.1`, and everything already in use (`taken`: the gateway container
|
||||
plus every live bottle, which the caller reads from the registry).
|
||||
|
||||
Pure `ipaddress` logic — the docker-specific bits (the subnet CIDR, the
|
||||
gateway container's own address) are gathered by the caller and passed in, so
|
||||
this stays testable without docker.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import ipaddress
|
||||
from collections.abc import Iterable
|
||||
|
||||
|
||||
class NoFreeAddressError(RuntimeError):
|
||||
"""The shared gateway network's subnet is exhausted — every host address
|
||||
is reserved or already assigned to a bottle."""
|
||||
|
||||
|
||||
def next_free_ip(cidr: str, taken: Iterable[str]) -> str:
|
||||
"""The lowest host address in `cidr` not in `taken` and not docker's
|
||||
router (`.1`). `taken` must include the gateway container's own address
|
||||
and every live bottle's. Raises `NoFreeAddressError` if the subnet is
|
||||
full."""
|
||||
net = ipaddress.ip_network(cidr, strict=False)
|
||||
reserved = {str(a) for a in taken}
|
||||
# Docker assigns the network's first host (.1) to the bridge router; a
|
||||
# bottle must never be handed that address.
|
||||
reserved.add(str(net.network_address + 1))
|
||||
for host in net.hosts(): # hosts() already excludes network + broadcast
|
||||
candidate = str(host)
|
||||
if candidate not in reserved:
|
||||
return candidate
|
||||
raise NoFreeAddressError(
|
||||
f"no free address in {cidr} ({len(reserved)} reserved/assigned)"
|
||||
)
|
||||
|
||||
|
||||
__all__ = ["next_free_ip", "NoFreeAddressError"]
|
||||
@@ -0,0 +1,100 @@
|
||||
"""Provision one bottle's git-gate state into the running shared gateway
|
||||
(PRD 0070, docker slice).
|
||||
|
||||
The consolidated gateway serves every bottle's repos under `/git/<bottle_id>/`
|
||||
with per-repo credentials under `/git-gate/creds/<bottle_id>/`. When a bottle
|
||||
is registered the launcher must place *its* deploy keys + known_hosts into
|
||||
that per-bottle creds dir and init its bare repos there — so this copies the
|
||||
credential files into the live gateway container and runs the (namespaced,
|
||||
init-only) provisioning script produced by `git_gate_render_provision`.
|
||||
|
||||
Isolating each bottle's creds dir + repo root by id is what keeps one
|
||||
bottle's push credentials out of another's repos on the shared gateway.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
|
||||
from ...docker_cmd import run_docker
|
||||
from ...git_gate import GitGatePlan, git_gate_render_provision
|
||||
|
||||
# bottle ids index the gateway's per-bottle repo + creds dirs; they land in
|
||||
# `docker cp`/`rm` path arguments, so validate before any path is built (a
|
||||
# traversal id like "../etc" must never reach the container). Registry ids are
|
||||
# token_hex — this is defense in depth at the docker boundary.
|
||||
_SAFE_BOTTLE_ID = re.compile(r"[A-Za-z0-9_-]+")
|
||||
|
||||
|
||||
class GatewayProvisionError(RuntimeError):
|
||||
"""A git-gate provisioning step against the running gateway failed."""
|
||||
|
||||
|
||||
def _require_safe(bottle_id: str) -> None:
|
||||
if not _SAFE_BOTTLE_ID.fullmatch(bottle_id):
|
||||
raise GatewayProvisionError(f"unsafe bottle id {bottle_id!r}")
|
||||
|
||||
|
||||
def _creds_dir(bottle_id: str) -> str:
|
||||
return f"/git-gate/creds/{bottle_id}"
|
||||
|
||||
|
||||
def _exec(gateway: str, argv: list[str]) -> None:
|
||||
"""`docker exec` a command in the gateway, raising on non-zero exit."""
|
||||
proc = run_docker(["docker", "exec", gateway, *argv])
|
||||
if proc.returncode != 0:
|
||||
raise GatewayProvisionError(
|
||||
f"gateway exec {argv!r} failed: {proc.stderr.strip()}"
|
||||
)
|
||||
|
||||
|
||||
def _cp_into(gateway: str, src: str, dest: str) -> None:
|
||||
"""`docker cp` a host file into the gateway, raising on non-zero exit."""
|
||||
proc = run_docker(["docker", "cp", src, f"{gateway}:{dest}"])
|
||||
if proc.returncode != 0:
|
||||
raise GatewayProvisionError(
|
||||
f"gateway cp {src} -> {dest} failed: {proc.stderr.strip()}"
|
||||
)
|
||||
|
||||
|
||||
def provision_git_gate(gateway: str, bottle_id: str, plan: GitGatePlan) -> None:
|
||||
"""Place `bottle_id`'s git-gate credentials into the running `gateway`
|
||||
container and init its bare repos under `/git/<bottle_id>/`.
|
||||
|
||||
Copies each upstream's identity key (and known_hosts, when present) into
|
||||
`/git-gate/creds/<bottle_id>/`, then runs the namespaced provisioning
|
||||
script. No-op for a bottle with no git upstreams."""
|
||||
_require_safe(bottle_id)
|
||||
if not plan.upstreams:
|
||||
return
|
||||
# The pre-receive + access hooks are bottle-agnostic and shared by every
|
||||
# bottle's repos; install them into the gateway (idempotent — same content
|
||||
# each time). The per-bottle model cp'd these into each bundle at start.
|
||||
_exec(gateway, ["mkdir", "-p", "/etc/git-gate"])
|
||||
_cp_into(gateway, str(plan.hook_script), "/etc/git-gate/pre-receive")
|
||||
_cp_into(gateway, str(plan.access_hook_script), "/etc/git-gate/access-hook")
|
||||
creds = _creds_dir(bottle_id)
|
||||
_exec(gateway, ["mkdir", "-p", creds])
|
||||
for u in plan.upstreams:
|
||||
if u.identity_file:
|
||||
_cp_into(gateway, u.identity_file, f"{creds}/{u.name}-key")
|
||||
known_hosts = str(u.known_hosts_file)
|
||||
if known_hosts and known_hosts != ".":
|
||||
_cp_into(gateway, known_hosts, f"{creds}/{u.name}-known_hosts")
|
||||
# Init the bare repos + per-repo credential config for this namespace.
|
||||
script = git_gate_render_provision(bottle_id, plan.upstreams)
|
||||
_exec(gateway, ["sh", "-c", script])
|
||||
|
||||
|
||||
def deprovision_git_gate(gateway: str, bottle_id: str) -> None:
|
||||
"""Remove a bottle's repos + creds from the gateway on teardown. Idempotent
|
||||
— an already-absent namespace is a clean no-op (best effort; a stray dir
|
||||
can't leak, since attribution is by source IP and the bottle is gone)."""
|
||||
_require_safe(bottle_id)
|
||||
run_docker([
|
||||
"docker", "exec", gateway, "rm", "-rf",
|
||||
f"/git/{bottle_id}", _creds_dir(bottle_id),
|
||||
])
|
||||
|
||||
|
||||
__all__ = ["provision_git_gate", "deprovision_git_gate", "GatewayProvisionError"]
|
||||
@@ -36,13 +36,11 @@ from contextlib import ExitStack, contextmanager
|
||||
from pathlib import Path
|
||||
from typing import Callable, Generator
|
||||
|
||||
from ...egress import egress_resolve_token_values
|
||||
from ...git_gate import (
|
||||
provision_git_gate_dynamic_keys,
|
||||
revoke_git_gate_provisioned_keys,
|
||||
)
|
||||
from ...log import info, warn
|
||||
from . import network as network_mod
|
||||
from . import util as docker_mod
|
||||
from .bottle import DockerBottle
|
||||
from .bottle_plan import DockerBottlePlan
|
||||
@@ -53,7 +51,6 @@ from ...bottle_state import (
|
||||
read_committed_image,
|
||||
)
|
||||
from .compose import (
|
||||
bottle_plan_to_compose,
|
||||
compose_down,
|
||||
compose_dump_logs,
|
||||
compose_file_path,
|
||||
@@ -62,7 +59,9 @@ from .compose import (
|
||||
compose_up,
|
||||
write_compose_file,
|
||||
)
|
||||
from .egress import egress_tls_init
|
||||
from .consolidated_compose import consolidated_agent_compose
|
||||
from .consolidated_launch import launch_consolidated, teardown_consolidated
|
||||
from ...orchestrator.gateway import DockerGateway
|
||||
|
||||
|
||||
# Where the repo root lives, for `docker build` context. Computed once.
|
||||
@@ -97,8 +96,7 @@ def launch(
|
||||
try:
|
||||
# Step 1: agent image. Use a committed snapshot when one exists
|
||||
# and is present in the local daemon; otherwise build from the
|
||||
# Dockerfile. Sidecar images get built lazily by `docker compose
|
||||
# up` via the renderer's `build:` directives.
|
||||
# Dockerfile. (The gateway image is built by the orchestrator.)
|
||||
committed = read_committed_image(plan.slug)
|
||||
if committed and docker_mod.image_exists(committed):
|
||||
info(f"using committed image {committed!r}")
|
||||
@@ -112,82 +110,73 @@ def launch(
|
||||
dockerfile=plan.dockerfile_path,
|
||||
)
|
||||
|
||||
internal_network = network_mod.network_name_for_slug(plan.slug)
|
||||
egress_network = network_mod.network_egress_name_for_slug(plan.slug)
|
||||
|
||||
egress_ca_host, egress_ca_cert_only = egress_tls_init(
|
||||
egress_state_dir(plan.slug),
|
||||
)
|
||||
|
||||
# Step 2: mint the git-gate dynamic (gitea) deploy keys, if any, before
|
||||
# provisioning the bottle's repos into the shared gateway.
|
||||
git_gate_plan = plan.git_gate_plan
|
||||
if git_gate_plan.upstreams:
|
||||
git_gate_plan = provision_git_gate_dynamic_keys(
|
||||
plan.manifest.bottle,
|
||||
git_gate_plan,
|
||||
git_gate_state_dir(plan.slug),
|
||||
)
|
||||
git_gate_plan = dataclasses.replace(
|
||||
git_gate_plan,
|
||||
internal_network=internal_network,
|
||||
egress_network=egress_network,
|
||||
plan.manifest.bottle, git_gate_plan, git_gate_state_dir(plan.slug),
|
||||
)
|
||||
|
||||
# Step 3: register on the orchestrator + provision this bottle's
|
||||
# git-gate state into the shared gateway; get the agent's attach
|
||||
# context (pinned source IP, gateway address, shared network).
|
||||
ctx = launch_consolidated(plan.egress_plan, git_gate_plan, image_ref=plan.image)
|
||||
stack.callback(
|
||||
teardown_consolidated, ctx.bottle_id, orchestrator_url=ctx.orchestrator_url,
|
||||
)
|
||||
|
||||
# Step 4: install the SHARED gateway CA into the agent (replaces the
|
||||
# per-bottle CA) — read it out of the running gateway.
|
||||
ca_dir = egress_state_dir(plan.slug) / "gateway-ca"
|
||||
ca_dir.mkdir(parents=True, exist_ok=True)
|
||||
ca_file = ca_dir / "gateway-ca.pem"
|
||||
ca_file.write_text(DockerGateway(network=ctx.network).ca_cert_pem())
|
||||
egress_plan = dataclasses.replace(
|
||||
plan.egress_plan,
|
||||
internal_network=internal_network,
|
||||
egress_network=egress_network,
|
||||
mitmproxy_ca_host_path=egress_ca_host,
|
||||
mitmproxy_ca_cert_only_host_path=egress_ca_cert_only,
|
||||
mitmproxy_ca_host_path=ca_file,
|
||||
mitmproxy_ca_cert_only_host_path=ca_file,
|
||||
)
|
||||
# Point the agent's git-gate insteadOf rewrites at the shared gateway's
|
||||
# HTTP git endpoint (9420) instead of the dead per-bottle `git-gate`
|
||||
# alias. git-http + supervise on the gateway bypass the egress proxy
|
||||
# (NO_PROXY includes the gateway address).
|
||||
git_gate_url = (
|
||||
f"http://{ctx.gateway_ip}:9420" if git_gate_plan.upstreams else ""
|
||||
)
|
||||
supervise_url = (
|
||||
f"http://{ctx.gateway_ip}:9100/" if plan.supervise_plan is not None else ""
|
||||
)
|
||||
supervise_plan = plan.supervise_plan
|
||||
if supervise_plan is not None:
|
||||
supervise_plan = dataclasses.replace(
|
||||
supervise_plan,
|
||||
internal_network=internal_network,
|
||||
)
|
||||
plan = dataclasses.replace(
|
||||
plan,
|
||||
git_gate_plan=git_gate_plan,
|
||||
egress_plan=egress_plan,
|
||||
supervise_plan=supervise_plan,
|
||||
agent_git_gate_url=git_gate_url,
|
||||
agent_supervise_url=supervise_url,
|
||||
)
|
||||
|
||||
# Step 6: render + write the compose file. metadata.json
|
||||
# was written at prepare time and already carries
|
||||
# compose_project; nothing to update here.
|
||||
# Step 5: render + up the agent-only compose, pinned on the shared
|
||||
# gateway network and proxied through the gateway's address.
|
||||
state_dir = bottle_state_dir(plan.slug)
|
||||
spec = bottle_plan_to_compose(plan)
|
||||
spec = consolidated_agent_compose(
|
||||
plan, gateway_ip=ctx.gateway_ip, source_ip=ctx.source_ip, network=ctx.network,
|
||||
)
|
||||
compose_file = write_compose_file(spec, compose_file_path(state_dir))
|
||||
project = compose_project_name(plan.slug)
|
||||
|
||||
# Step 7: compose up. Token values + the OAuth placeholder
|
||||
# flow through subprocess env; the compose file holds only
|
||||
# bare names for the secret-carrying entries.
|
||||
effective_env = {**dict(os.environ), **plan.agent_provision.provisioned_env}
|
||||
token_values = egress_resolve_token_values(
|
||||
plan.egress_plan.token_env_map, effective_env,
|
||||
)
|
||||
compose_env: dict[str, str] = {
|
||||
**os.environ,
|
||||
**plan.forwarded_env,
|
||||
**token_values,
|
||||
}
|
||||
# Forwarded vars (OAuth token, host interpolations) flow through the
|
||||
# subprocess env as bare names so values never land in the file.
|
||||
compose_env: dict[str, str] = {**os.environ, **plan.forwarded_env}
|
||||
info(
|
||||
f"docker compose up -d (project {project}, "
|
||||
f"{len(spec['services'])} services)"
|
||||
f"docker compose up -d (project {project}, agent on shared "
|
||||
f"gateway {ctx.gateway_ip}, ip {ctx.source_ip})"
|
||||
)
|
||||
compose_up(project, compose_file, env=compose_env)
|
||||
|
||||
# Register teardown in reverse order: log dump first, then
|
||||
# `compose down`. Networks come down last via callbacks
|
||||
# registered in step 2.
|
||||
stack.callback(compose_down, project, compose_file)
|
||||
stack.callback(
|
||||
compose_dump_logs, project, compose_file, compose_log_path(state_dir),
|
||||
)
|
||||
|
||||
# Step 8: provision. Create the bottle first so provisioners
|
||||
# can use bottle.exec / bottle.cp_in; set the prompt path
|
||||
# returned by provision_prompt after the fact.
|
||||
# Step 6: provision (CA install now uses the gateway CA) + yield.
|
||||
bottle = DockerBottle(
|
||||
plan.container_name,
|
||||
teardown,
|
||||
@@ -200,10 +189,6 @@ def launch(
|
||||
agent_workdir=plan.workspace_plan.workdir,
|
||||
)
|
||||
bottle.prompt_path = provision(plan, bottle)
|
||||
|
||||
# Step 9: yield. exec_agent continues to use `docker exec -it`
|
||||
# — the agent runs `sleep infinity` per the renderer's
|
||||
# service spec.
|
||||
yield bottle
|
||||
finally:
|
||||
teardown()
|
||||
|
||||
+52
-29
@@ -32,7 +32,7 @@ from egress_addon_core import ( # type: ignore[import-not-found] # pylint: dis
|
||||
is_git_push_request,
|
||||
load_config,
|
||||
match_route,
|
||||
resolve_client_config,
|
||||
resolve_client_context,
|
||||
outbound_scan_headers,
|
||||
route_to_yaml_dict,
|
||||
scan_inbound,
|
||||
@@ -99,17 +99,29 @@ class EgressAddon:
|
||||
# Absent → single-tenant (static routes file); behaviour unchanged.
|
||||
orch_url = os.environ.get(ORCHESTRATOR_URL_ENV, "").strip()
|
||||
self._resolver = PolicyResolver(orch_url) if orch_url else None
|
||||
# Tokens the operator has approved this session (PRD 0062). In-memory
|
||||
# only — a restart re-prompts. Mutated only from the asyncio loop that
|
||||
# runs the addon hooks, so no lock is needed.
|
||||
self.safe_tokens: set[str] = set()
|
||||
# Tokens the operator has approved this session (PRD 0062), keyed by
|
||||
# bottle so the shared gateway keeps each bottle's safelist separate —
|
||||
# a global set would let bottle A's approved secret pass bottle B's DLP
|
||||
# scan. In-memory only (a restart re-prompts); mutated only from the
|
||||
# asyncio loop that runs the addon hooks, so no lock is needed.
|
||||
self._safe_tokens: dict[str, set[str]] = {}
|
||||
self._supervise_slug = os.environ.get("SUPERVISE_BOTTLE_SLUG", "").strip()
|
||||
self._token_allow_timeout = _token_allow_timeout_from_env(os.environ)
|
||||
self._reload(initial=True)
|
||||
self._install_sighup()
|
||||
|
||||
def _supervise_available(self) -> bool:
|
||||
return bool(self._supervise_slug)
|
||||
@staticmethod
|
||||
def _supervise_available(slug: str) -> bool:
|
||||
"""Supervise is reachable for this request iff we resolved a bottle to
|
||||
attribute its proposals to (single-tenant env slug, or a source-IP
|
||||
-attributed bottle id). Empty → fail closed (no queue to write to)."""
|
||||
return bool(slug)
|
||||
|
||||
def _safe_tokens_for(self, slug: str) -> set[str]:
|
||||
"""This bottle's operator-approved DLP safelist (PRD 0062), created on
|
||||
first use. Keyed by bottle so the shared gateway never leaks one
|
||||
bottle's approved token into another's scan."""
|
||||
return self._safe_tokens.setdefault(slug, set())
|
||||
|
||||
def _reload(self, *, initial: bool = False) -> None:
|
||||
try:
|
||||
@@ -218,19 +230,21 @@ class EgressAddon:
|
||||
+ "\n"
|
||||
)
|
||||
|
||||
def _active_config(self, flow: http.HTTPFlow) -> Config:
|
||||
"""The Config to apply to this request. Single-tenant → the static
|
||||
`self.config`. Consolidated → the calling bottle's Config, resolved
|
||||
by source IP (fail-closed to deny-all if unattributed). The identity
|
||||
token, if the agent injected one, is read then stripped so it never
|
||||
leaks upstream."""
|
||||
def _resolve_flow(self, flow: http.HTTPFlow) -> "tuple[Config, str]":
|
||||
"""The `(Config, supervise slug)` to apply to this request. Single-tenant
|
||||
→ the static `self.config` and the env slug. Consolidated → the calling
|
||||
bottle's Config and its bottle id, resolved by source IP in one
|
||||
round-trip (fail-closed to deny-all + empty slug if unattributed). The
|
||||
identity token, if the agent injected one, is read then stripped so it
|
||||
never leaks upstream. The slug keys both the proposal queue and the
|
||||
per-bottle safelist, so an approval only ever affects its own bottle."""
|
||||
if self._resolver is None:
|
||||
return self.config
|
||||
return self.config, self._supervise_slug
|
||||
conn = flow.client_conn
|
||||
client_ip = conn.peername[0] if conn and conn.peername else ""
|
||||
token = flow.request.headers.get(IDENTITY_HEADER, "")
|
||||
flow.request.headers.pop(IDENTITY_HEADER, None)
|
||||
return resolve_client_config(self._resolver, client_ip, token)
|
||||
return resolve_client_context(self._resolver, client_ip, token)
|
||||
|
||||
async def request(self, flow: http.HTTPFlow) -> None:
|
||||
request_path, _, query = flow.request.path.partition("?")
|
||||
@@ -239,14 +253,14 @@ class EgressAddon:
|
||||
self._serve_introspection(flow, request_path)
|
||||
return
|
||||
|
||||
config = self._active_config(flow)
|
||||
config, slug = self._resolve_flow(flow)
|
||||
|
||||
# DLP outbound scan BEFORE stripping auth — catches tokens the
|
||||
# agent tried to smuggle in any header, path, query param, or body.
|
||||
# Hostname is included to catch DNS-tunnelling exfiltration attempts.
|
||||
route = match_route(config.routes, flow.request.pretty_host)
|
||||
if route is not None:
|
||||
if not await self._handle_outbound_dlp(flow, route):
|
||||
if not await self._handle_outbound_dlp(flow, route, slug):
|
||||
return
|
||||
# The redact policy may have rewritten the request line; recompute
|
||||
# the path/query the git checks below rely on.
|
||||
@@ -310,6 +324,7 @@ class EgressAddon:
|
||||
self,
|
||||
flow: http.HTTPFlow,
|
||||
route: Route,
|
||||
slug: str,
|
||||
) -> bool:
|
||||
"""Scan the outbound request and apply the route's on-match policy
|
||||
(PRD 0062). Returns True if the request may be forwarded, False if a
|
||||
@@ -331,7 +346,7 @@ class EgressAddon:
|
||||
)
|
||||
result = scan_outbound(
|
||||
route, scan_text, os.environ,
|
||||
safe_tokens=self.safe_tokens, crlf_text=crlf_text,
|
||||
safe_tokens=self._safe_tokens_for(slug), crlf_text=crlf_text,
|
||||
)
|
||||
if result is None or result.severity != "block":
|
||||
return True
|
||||
@@ -366,10 +381,10 @@ class EgressAddon:
|
||||
|
||||
# supervise (default): hold the request for operator approval.
|
||||
# Fall back to a hard 403 when supervise isn't wired for the bottle.
|
||||
if not self._supervise_available():
|
||||
if not self._supervise_available(slug):
|
||||
self._block_dlp(flow, result)
|
||||
return False
|
||||
approved = await self._supervise_token_block(flow, request_path, result)
|
||||
approved = await self._supervise_token_block(flow, request_path, result, slug)
|
||||
if not approved:
|
||||
return False # _supervise_token_block wrote the 403 response
|
||||
# loop: the approved value is now in safe_tokens; re-scan.
|
||||
@@ -412,12 +427,16 @@ class EgressAddon:
|
||||
flow: http.HTTPFlow,
|
||||
request_path: str,
|
||||
result: ScanResult,
|
||||
slug: str,
|
||||
) -> bool:
|
||||
"""Route a token DLP block to the operator's supervisor queue and wait.
|
||||
|
||||
Returns True if the operator approved (the matched value is added to
|
||||
`self.safe_tokens` and the caller re-scans); False if the request must
|
||||
be blocked (a 403 response has been written to `flow`)."""
|
||||
`slug` attributes the proposal to the calling bottle (its own queue +
|
||||
safelist) — in the shared gateway this is what keeps one bottle's
|
||||
approval from unblocking another's request. Returns True if the operator
|
||||
approved (the matched value is added to that bottle's safelist and the
|
||||
caller re-scans); False if the request must be blocked (a 403 response
|
||||
has been written to `flow`)."""
|
||||
host = flow.request.pretty_host
|
||||
payload = build_token_allow_payload(
|
||||
redact_tokens(host, env=os.environ),
|
||||
@@ -426,7 +445,7 @@ class EgressAddon:
|
||||
result,
|
||||
)
|
||||
proposal = _sv.Proposal.new(
|
||||
bottle_slug=self._supervise_slug,
|
||||
bottle_slug=slug,
|
||||
tool=_sv.TOOL_EGRESS_TOKEN_ALLOW,
|
||||
proposed_file=payload,
|
||||
justification=_TOKEN_ALLOW_JUSTIFICATION,
|
||||
@@ -449,13 +468,13 @@ class EgressAddon:
|
||||
**self._req_ctx(flow),
|
||||
}) + "\n")
|
||||
|
||||
response = await self._await_token_response(proposal.id)
|
||||
_sv.archive_proposal(self._supervise_slug, proposal.id)
|
||||
response = await self._await_token_response(proposal.id, slug)
|
||||
_sv.archive_proposal(slug, proposal.id)
|
||||
|
||||
if response is not None and response.status in (
|
||||
_sv.STATUS_APPROVED, _sv.STATUS_MODIFIED,
|
||||
):
|
||||
self.safe_tokens.add(result.matched)
|
||||
self._safe_tokens_for(slug).add(result.matched)
|
||||
if self.config.log >= LOG_BLOCKS:
|
||||
sys.stderr.write(json.dumps({
|
||||
"event": "egress_token_allowed",
|
||||
@@ -478,6 +497,7 @@ class EgressAddon:
|
||||
async def _await_token_response(
|
||||
self,
|
||||
proposal_id: str,
|
||||
slug: str,
|
||||
) -> "_sv.Response | None":
|
||||
"""Poll the DB for the operator's response without blocking the
|
||||
proxy event loop. Returns the Response, or None on timeout."""
|
||||
@@ -485,7 +505,7 @@ class EgressAddon:
|
||||
deadline = loop.time() + self._token_allow_timeout
|
||||
while True:
|
||||
try:
|
||||
return _sv.read_response(self._supervise_slug, proposal_id)
|
||||
return _sv.read_response(slug, proposal_id)
|
||||
except (OSError, ValueError, KeyError):
|
||||
# Not written yet, or a partial/malformed write — retry until
|
||||
# the deadline, then fail closed.
|
||||
@@ -539,6 +559,9 @@ class EgressAddon:
|
||||
"""
|
||||
if flow.websocket is None: # type: ignore[union-attr]
|
||||
return
|
||||
# WebSocket DLP runs against the static config only (single-tenant); in
|
||||
# the consolidated gateway self.config has no routes, so this is inert
|
||||
# until websocket routing is made source-IP-aware (a separate slice).
|
||||
route = match_route(self.config.routes, flow.request.pretty_host)
|
||||
if route is None:
|
||||
return
|
||||
@@ -549,7 +572,7 @@ class EgressAddon:
|
||||
# not an injection vector here — scan only for credential leakage.
|
||||
result = scan_outbound(
|
||||
route, content, os.environ,
|
||||
safe_tokens=self.safe_tokens, crlf_text="",
|
||||
safe_tokens=self._safe_tokens_for(self._supervise_slug), crlf_text="",
|
||||
)
|
||||
if result is not None and result.severity == "block":
|
||||
sys.stderr.write(f"egress DLP: {result.reason}\n")
|
||||
|
||||
@@ -421,6 +421,18 @@ class PolicyResolverLike(typing.Protocol):
|
||||
...
|
||||
|
||||
|
||||
def _config_from_policy(policy: "str | None") -> "Config":
|
||||
"""Parse a resolved policy blob into a Config, fail-closed: None / empty /
|
||||
unparseable all become a deny-all Config (no routes → every request
|
||||
blocked)."""
|
||||
if not policy:
|
||||
return Config(routes=()) # unattributed or empty → deny-all
|
||||
try:
|
||||
return load_config(policy)
|
||||
except ValueError:
|
||||
return Config(routes=()) # unparseable policy → deny
|
||||
|
||||
|
||||
def resolve_client_config(
|
||||
resolver: PolicyResolverLike, client_ip: str, identity_token: str = ""
|
||||
) -> "Config":
|
||||
@@ -433,12 +445,33 @@ def resolve_client_config(
|
||||
policy = resolver.resolve(client_ip, identity_token)
|
||||
except Exception: # noqa: BLE001 # pylint: disable=broad-exception-caught
|
||||
return Config(routes=()) # orchestrator unreachable/errored → deny
|
||||
if not policy:
|
||||
return Config(routes=()) # unattributed or empty → deny-all
|
||||
return _config_from_policy(policy)
|
||||
|
||||
|
||||
class ContextResolverLike(typing.Protocol):
|
||||
"""The bit of `policy_resolver.PolicyResolver` `resolve_client_context`
|
||||
needs — one round-trip returning both policy and bottle id."""
|
||||
|
||||
def resolve_policy_and_bottle_id(
|
||||
self, source_ip: str, identity_token: str = ...,
|
||||
) -> "tuple[str | None, str | None]":
|
||||
...
|
||||
|
||||
|
||||
def resolve_client_context(
|
||||
resolver: ContextResolverLike, client_ip: str, identity_token: str = "",
|
||||
) -> "tuple[Config, str]":
|
||||
"""The calling client's `(Config, bottle_id)` in one round-trip —
|
||||
**fail-closed**. The Config follows `resolve_client_config`'s deny-all
|
||||
rules; the bottle id is `""` whenever unattributed or the orchestrator
|
||||
errored, which the caller treats as "supervise unavailable for this
|
||||
bottle" (never another bottle's queue). One `/resolve` keys both the
|
||||
per-request egress policy and the per-bottle supervise queue + safelist."""
|
||||
try:
|
||||
return load_config(policy)
|
||||
except ValueError:
|
||||
return Config(routes=()) # unparseable policy → deny
|
||||
policy, bottle_id = resolver.resolve_policy_and_bottle_id(client_ip, identity_token)
|
||||
except Exception: # noqa: BLE001 # pylint: disable=broad-exception-caught
|
||||
return Config(routes=()), "" # orchestrator unreachable/errored → deny
|
||||
return _config_from_policy(policy), (bottle_id or "")
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -833,7 +866,9 @@ __all__ = [
|
||||
"is_git_fetch_request",
|
||||
"load_config",
|
||||
"resolve_client_config",
|
||||
"resolve_client_context",
|
||||
"PolicyResolverLike",
|
||||
"ContextResolverLike",
|
||||
"match_route",
|
||||
"outbound_scan_headers",
|
||||
"parse_config",
|
||||
|
||||
@@ -46,6 +46,7 @@ from .git_gate_render import (
|
||||
git_gate_known_hosts_line,
|
||||
git_gate_render_access_hook,
|
||||
git_gate_render_entrypoint,
|
||||
git_gate_render_provision,
|
||||
git_gate_render_gitconfig,
|
||||
git_gate_render_hook,
|
||||
git_gate_upstreams_for_bottle,
|
||||
@@ -155,6 +156,7 @@ __all__ = [
|
||||
"git_gate_render_gitconfig",
|
||||
"git_gate_known_hosts_line",
|
||||
"git_gate_render_entrypoint",
|
||||
"git_gate_render_provision",
|
||||
"git_gate_render_hook",
|
||||
"git_gate_render_access_hook",
|
||||
"provision_git_gate_dynamic_keys",
|
||||
|
||||
@@ -9,6 +9,7 @@ own; `git_gate` re-exports these names for API stability."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
import shlex
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
@@ -125,22 +126,18 @@ def git_gate_known_hosts_line(host: str, port: str, key: str) -> str:
|
||||
return f"{target} {key}\n"
|
||||
|
||||
|
||||
def git_gate_render_entrypoint(upstreams: tuple[GitGateUpstream, ...]) -> str:
|
||||
"""Posix-sh entrypoint. One `init_repo` call per upstream, then
|
||||
`exec git daemon`. The function reads
|
||||
`/git-gate/creds/<name>-{key,known_hosts}` (bind-mounted into
|
||||
the bundle by the renderer) and wires them into each bare repo's
|
||||
config; the access-hook + pre-receive hook pick those paths up
|
||||
at fetch / push time."""
|
||||
lines = [
|
||||
"#!/bin/sh",
|
||||
"set -eu",
|
||||
"",
|
||||
def _git_gate_init_repo_fn(repo_root: str, creds_dir: str) -> list[str]:
|
||||
"""The `init_repo` shell function, parameterized by the bare-repo root
|
||||
and the per-bottle creds dir. Single source of the credential-wiring
|
||||
logic, shared by the single-tenant daemon entrypoint (`/git`,
|
||||
`/git-gate/creds`) and the consolidated per-bottle provisioning
|
||||
(`/git/<bottle_id>`, `/git-gate/creds/<bottle_id>`)."""
|
||||
return [
|
||||
"init_repo() {",
|
||||
" name=$1",
|
||||
" upstream_url=$2",
|
||||
" keyfile=/git-gate/creds/${name}-key",
|
||||
" hostsfile=/git-gate/creds/${name}-known_hosts",
|
||||
f" keyfile={creds_dir}/${{name}}-key",
|
||||
f" hostsfile={creds_dir}/${{name}}-known_hosts",
|
||||
"",
|
||||
# `|| true`: PRD 0018 chunk 3+ bind-mounts these RO from the
|
||||
# host, so chmod-syscalls fail with EROFS. The files already
|
||||
@@ -153,14 +150,14 @@ def git_gate_render_entrypoint(upstreams: tuple[GitGateUpstream, ...]) -> str:
|
||||
" chmod 600 \"$hostsfile\" 2>/dev/null || true",
|
||||
" fi",
|
||||
"",
|
||||
" repo=/git/${name}.git",
|
||||
f" repo={repo_root}/${{name}}.git",
|
||||
" if [ ! -d \"$repo\" ]; then",
|
||||
" git init --bare \"$repo\" >/dev/null",
|
||||
# --mirror=fetch sets remote.origin.fetch = +refs/*:refs/* so",
|
||||
# a later `git fetch origin` mirrors the upstream's full ref",
|
||||
# graph (heads, tags, notes) into the bare repo at canonical",
|
||||
# paths. It does NOT set remote.origin.mirror=true, so an",
|
||||
# explicit `git push origin <ref>:<ref>` still pushes one ref.",
|
||||
# --mirror=fetch sets remote.origin.fetch = +refs/*:refs/* so a later
|
||||
# `git fetch origin` mirrors the upstream's full ref graph (heads,
|
||||
# tags, notes) into the bare repo at canonical paths. It does NOT set
|
||||
# remote.origin.mirror=true, so an explicit `git push origin
|
||||
# <ref>:<ref>` still pushes one ref.
|
||||
" git -C \"$repo\" remote add --mirror=fetch origin \"$upstream_url\"",
|
||||
" fi",
|
||||
" git -C \"$repo\" config git-gate.identityFile \"$keyfile\"",
|
||||
@@ -170,9 +167,19 @@ def git_gate_render_entrypoint(upstreams: tuple[GitGateUpstream, ...]) -> str:
|
||||
" git -C \"$repo\" config http.receivepack true",
|
||||
" install -m 755 /etc/git-gate/pre-receive \"$repo/hooks/pre-receive\"",
|
||||
"}",
|
||||
"",
|
||||
"mkdir -p /git",
|
||||
]
|
||||
|
||||
|
||||
def git_gate_render_entrypoint(upstreams: tuple[GitGateUpstream, ...]) -> str:
|
||||
"""Posix-sh entrypoint. One `init_repo` call per upstream, then
|
||||
`exec git daemon`. The function reads
|
||||
`/git-gate/creds/<name>-{key,known_hosts}` (bind-mounted into
|
||||
the bundle by the renderer) and wires them into each bare repo's
|
||||
config; the access-hook + pre-receive hook pick those paths up
|
||||
at fetch / push time."""
|
||||
lines = ["#!/bin/sh", "set -eu", ""]
|
||||
lines += _git_gate_init_repo_fn("/git", "/git-gate/creds")
|
||||
lines += ["", "mkdir -p /git"]
|
||||
for u in upstreams:
|
||||
lines.append(f"init_repo {shlex.quote(u.name)} {shlex.quote(u.upstream_url)}")
|
||||
lines.extend([
|
||||
@@ -190,6 +197,35 @@ def git_gate_render_entrypoint(upstreams: tuple[GitGateUpstream, ...]) -> str:
|
||||
return "\n".join(lines) + "\n"
|
||||
|
||||
|
||||
# A bottle id namespaces the consolidated gateway's repo + creds dirs; it is
|
||||
# embedded unquoted in the provisioning script, so restrict it to a shell- and
|
||||
# path-safe alphabet (registry ids are token_hex — this is defense in depth).
|
||||
_SAFE_BOTTLE_ID = re.compile(r"[A-Za-z0-9_-]+")
|
||||
|
||||
|
||||
def git_gate_render_provision(
|
||||
bottle_id: str, upstreams: tuple[GitGateUpstream, ...],
|
||||
) -> str:
|
||||
"""Posix-sh script that provisions ONE bottle's bare repos into the
|
||||
consolidated gateway (PRD 0070), under `/git/<bottle_id>/` with creds
|
||||
read from `/git-gate/creds/<bottle_id>/`. Init-only — no `git daemon`,
|
||||
since the shared gateway already serves every bottle; run inside the
|
||||
running gateway when the bottle is registered.
|
||||
|
||||
Isolating each bottle's repo root and creds dir by id is what keeps one
|
||||
bottle's push credentials out of another's repos on the shared gateway."""
|
||||
if not _SAFE_BOTTLE_ID.fullmatch(bottle_id):
|
||||
raise ValueError(f"git-gate: unsafe bottle id {bottle_id!r}")
|
||||
repo_root = f"/git/{bottle_id}"
|
||||
creds_dir = f"/git-gate/creds/{bottle_id}"
|
||||
lines = ["#!/bin/sh", "set -eu", ""]
|
||||
lines += _git_gate_init_repo_fn(repo_root, creds_dir)
|
||||
lines += ["", f"mkdir -p {shlex.quote(repo_root)}"]
|
||||
for u in upstreams:
|
||||
lines.append(f"init_repo {shlex.quote(u.name)} {shlex.quote(u.upstream_url)}")
|
||||
return "\n".join(lines) + "\n"
|
||||
|
||||
|
||||
def git_gate_render_hook() -> str:
|
||||
"""The shared pre-receive hook: gitleaks-scan all incoming refs,
|
||||
then forward each accepted ref to the real upstream (`origin`)
|
||||
|
||||
@@ -6,6 +6,15 @@ where the guest reaches the sidecar over the point-to-point TAP). The
|
||||
wrapper serves the same `/git/*.git` bare repos through
|
||||
`git http-backend`, so pre-receive and upstream forwarding remain the
|
||||
git-gate enforcement point.
|
||||
|
||||
Consolidated (PRD 0070): when `BOT_BOTTLE_ORCHESTRATOR_URL` is set, one
|
||||
shared gateway serves every bottle, and each request is served from the
|
||||
calling bottle's repo namespace (`<root>/<bottle_id>`), attributed from
|
||||
the unspoofable source IP via the orchestrator. Per-repo credentials +
|
||||
hooks scope by repo directory, so isolating the *root* per bottle isolates
|
||||
its creds too. Unattributed clients fail closed (404). Unset → the legacy
|
||||
per-bottle single-tenant flat root, unchanged — a transitional path that
|
||||
gets stripped out once every backend runs the consolidated gateway.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -13,13 +22,86 @@ from __future__ import annotations
|
||||
import os
|
||||
import subprocess
|
||||
import sys
|
||||
import typing
|
||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||
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
|
||||
# host-side / test path. Mirrors egress_addon's import shape.
|
||||
try:
|
||||
from policy_resolver import ( # type: ignore[import-not-found]
|
||||
PolicyResolveError,
|
||||
PolicyResolver,
|
||||
)
|
||||
except ImportError: # pragma: no cover - host-side path
|
||||
from bot_bottle.policy_resolver import PolicyResolveError, PolicyResolver
|
||||
|
||||
|
||||
DEFAULT_PORT = 9420
|
||||
|
||||
# Consolidated (multi-tenant) mode: when this points at the per-host
|
||||
# orchestrator's control plane, the backend serves each request from the
|
||||
# *calling* bottle's repo namespace, selected by source IP, instead of a
|
||||
# single flat repo root. Unset → legacy per-bottle single-tenant mode
|
||||
# (unchanged). Same env the egress addon reads, so one orchestrator setting
|
||||
# flips the whole shared gateway multi-tenant.
|
||||
ORCHESTRATOR_URL_ENV = "BOT_BOTTLE_ORCHESTRATOR_URL"
|
||||
|
||||
# App-layer identity token (defense-in-depth over the source-IP invariant);
|
||||
# the agent injects it, the backend reads it for attribution and never
|
||||
# forwards it to `git http-backend`. Mirrors egress_addon.IDENTITY_HEADER
|
||||
# (duplicated, not imported: egress_addon pulls in mitmproxy).
|
||||
IDENTITY_HEADER = "x-bot-bottle-identity"
|
||||
|
||||
# Default flat repo root (single-tenant, and the base under which
|
||||
# consolidated mode nests each sandbox's namespace).
|
||||
DEFAULT_REPO_ROOT = "/git"
|
||||
|
||||
|
||||
class ResolverLike(typing.Protocol):
|
||||
"""Structural type for the resolver `resolve_sandbox_root` needs — just
|
||||
`resolve_bottle_id`. A Protocol so tests can pass a fake without
|
||||
importing PolicyResolver (mirrors egress_addon_core.PolicyResolverLike)."""
|
||||
|
||||
def resolve_bottle_id(
|
||||
self, source_ip: str, identity_token: str = ...,
|
||||
) -> "str | None": ...
|
||||
|
||||
|
||||
def resolve_sandbox_root(
|
||||
resolver: "ResolverLike | None",
|
||||
base_root: Path,
|
||||
source_ip: str,
|
||||
identity_token: str = "",
|
||||
) -> Path | None:
|
||||
"""The per-sandbox repo root to serve this request from, or None to
|
||||
deny (404).
|
||||
|
||||
Single-tenant (`resolver is None`): the flat `base_root`, unchanged.
|
||||
NOTE: this legacy per-bottle single-tenant path is transitional — it
|
||||
will be stripped out once every backend runs the consolidated gateway
|
||||
(PRD 0070), leaving only the source-IP-attributed path below.
|
||||
|
||||
Consolidated: `base_root/<bottle_id>`, where the sandbox is attributed
|
||||
from the source IP via the orchestrator. Fail-closed — an unattributed
|
||||
client, a resolver error, or a namespace that would escape `base_root`
|
||||
all deny, so one sandbox can never reach another's repos."""
|
||||
if resolver is None:
|
||||
return base_root
|
||||
try:
|
||||
bottle_id = resolver.resolve_bottle_id(source_ip, identity_token)
|
||||
except PolicyResolveError:
|
||||
return None # orchestrator unreachable/errored → deny
|
||||
if not bottle_id:
|
||||
return None # unattributed → deny
|
||||
base = base_root.resolve()
|
||||
namespace = (base / bottle_id).resolve()
|
||||
if base not in namespace.parents:
|
||||
return None # bottle_id tried to escape the root → deny
|
||||
return namespace
|
||||
|
||||
# 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
|
||||
@@ -40,10 +122,25 @@ class GitHttpHandler(BaseHTTPRequestHandler):
|
||||
def do_POST(self) -> None:
|
||||
self._run_backend()
|
||||
|
||||
def _sandbox_root(self) -> Path | None:
|
||||
"""This request's per-sandbox repo root, or None to deny. Single-tenant
|
||||
unless the server was started with a resolver (consolidated mode), in
|
||||
which case the root is the calling sandbox's source-IP-selected
|
||||
namespace. `GIT_PROJECT_ROOT` keeps git's own env-var name."""
|
||||
base = Path(os.environ.get("GIT_PROJECT_ROOT", DEFAULT_REPO_ROOT))
|
||||
resolver = getattr(self.server, "policy_resolver", None)
|
||||
token = self.headers.get(IDENTITY_HEADER, "")
|
||||
return resolve_sandbox_root(resolver, base, self.client_address[0], token)
|
||||
|
||||
def _run_backend(self) -> None:
|
||||
sandbox_root = self._sandbox_root()
|
||||
if sandbox_root is None:
|
||||
# Unattributed / resolver error: deny before touching any repo.
|
||||
self.send_error(404)
|
||||
return
|
||||
parsed = urlsplit(self.path)
|
||||
if self._is_upload_pack(parsed.path, parsed.query):
|
||||
repo_dir = self._repo_dir(parsed.path)
|
||||
repo_dir = self._repo_dir(sandbox_root, parsed.path)
|
||||
if repo_dir is None:
|
||||
self.send_error(404)
|
||||
return
|
||||
@@ -77,7 +174,7 @@ class GitHttpHandler(BaseHTTPRequestHandler):
|
||||
return
|
||||
env = os.environ.copy()
|
||||
env.update({
|
||||
"GIT_PROJECT_ROOT": os.environ.get("GIT_PROJECT_ROOT", "/git"),
|
||||
"GIT_PROJECT_ROOT": str(sandbox_root),
|
||||
"GIT_HTTP_EXPORT_ALL": "1",
|
||||
"REQUEST_METHOD": self.command,
|
||||
"PATH_INFO": parsed.path,
|
||||
@@ -91,6 +188,14 @@ class GitHttpHandler(BaseHTTPRequestHandler):
|
||||
"SERVER_PORT": str(self.server.server_port), # type: ignore
|
||||
"SERVER_PROTOCOL": self.request_version,
|
||||
})
|
||||
# Consolidated mode: attribute the gitleaks-allow supervise proposal
|
||||
# (written by receive-pack's pre-receive hook, a child of the CGI we
|
||||
# spawn below) to the calling bottle. The namespaced root is
|
||||
# `<base>/<bottle_id>`, so its final component is the bottle id — the
|
||||
# same per-bottle key egress uses. Single-tenant leaves the hook's
|
||||
# container-stamped SUPERVISE_BOTTLE_SLUG untouched.
|
||||
if getattr(self.server, "policy_resolver", None) is not None:
|
||||
env["SUPERVISE_BOTTLE_SLUG"] = sandbox_root.name
|
||||
for header, variable in (
|
||||
("accept", "HTTP_ACCEPT"),
|
||||
("content-encoding", "HTTP_CONTENT_ENCODING"),
|
||||
@@ -123,8 +228,8 @@ class GitHttpHandler(BaseHTTPRequestHandler):
|
||||
)
|
||||
self._write_cgi_response(proc.stdout)
|
||||
|
||||
def _repo_dir(self, path: str) -> Path | None:
|
||||
root = Path(os.environ.get("GIT_PROJECT_ROOT", "/git")).resolve()
|
||||
def _repo_dir(self, sandbox_root: Path, path: str) -> Path | None:
|
||||
root = sandbox_root.resolve()
|
||||
relative = path.lstrip("/").split(".git", 1)[0] + ".git"
|
||||
candidate = (root / relative).resolve()
|
||||
if root not in (candidate, *candidate.parents):
|
||||
@@ -181,7 +286,13 @@ class GitHttpHandler(BaseHTTPRequestHandler):
|
||||
def main() -> int:
|
||||
port = int(os.environ.get("GIT_HTTP_PORT", str(DEFAULT_PORT)))
|
||||
server = ThreadingHTTPServer(("0.0.0.0", port), GitHttpHandler)
|
||||
sys.stdout.write(f"git-http listening on 0.0.0.0:{port}\n")
|
||||
orch_url = os.environ.get(ORCHESTRATOR_URL_ENV, "").strip()
|
||||
# Consolidated mode: resolve each request's sandbox namespace by source
|
||||
# IP. Absent → single-tenant (flat repo root); behaviour unchanged.
|
||||
resolver = PolicyResolver(orch_url) if orch_url else None
|
||||
server.policy_resolver = resolver # type: ignore[attr-defined]
|
||||
mode = "multi-tenant" if orch_url else "single-tenant"
|
||||
sys.stdout.write(f"git-http listening on 0.0.0.0:{port} ({mode})\n")
|
||||
sys.stdout.flush()
|
||||
server.serve_forever()
|
||||
return 0
|
||||
|
||||
@@ -51,7 +51,13 @@ def main(argv: list[str] | None = None) -> int:
|
||||
# anything; 'docker' runs real containers (firecracker drops in later).
|
||||
secret = secrets.token_bytes(32)
|
||||
broker: LaunchBroker = DockerBroker(secret) if args.broker == "docker" else StubBroker(secret)
|
||||
gateway: Gateway | None = DockerGateway() if args.gateway else None
|
||||
# Standalone `--gateway` (not the consolidated flow, where the host
|
||||
# lifecycle runs the gateway). The gateway resolves against this same
|
||||
# process; the URL is only reachable when they share a docker network.
|
||||
gateway: Gateway | None = (
|
||||
DockerGateway(orchestrator_url=f"http://{args.host}:{args.port}")
|
||||
if args.gateway else None
|
||||
)
|
||||
orchestrator = Orchestrator(registry, broker, secret, gateway)
|
||||
|
||||
# One persistent per-host gateway, shared by every bottle: build the
|
||||
|
||||
@@ -0,0 +1,140 @@
|
||||
"""Host-side control-plane client (PRD 0070).
|
||||
|
||||
The launch path talks to the orchestrator over its HTTP control plane to
|
||||
register, re-policy, and tear down bottles — the counterpart to the
|
||||
gateway-side `PolicyResolver` (which only reads `/resolve`). Where
|
||||
`PolicyResolver` is fail-closed and lives in the untrusted data plane, this
|
||||
is the trusted control-plane caller: a non-success response is an error the
|
||||
launch path must surface, not silently swallow.
|
||||
|
||||
Stdlib-only, so the CLI can drive the orchestrator without any dependency.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
from dataclasses import dataclass
|
||||
|
||||
DEFAULT_TIMEOUT_SECONDS = 5.0
|
||||
|
||||
|
||||
class OrchestratorClientError(RuntimeError):
|
||||
"""A control-plane call failed (unreachable, or an unexpected status)."""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RegisteredBottle:
|
||||
"""What `POST /bottles` returns: the minted bottle id and the per-bottle
|
||||
identity token the agent presents for app-layer attribution."""
|
||||
|
||||
bottle_id: str
|
||||
identity_token: str
|
||||
|
||||
|
||||
class OrchestratorClient:
|
||||
"""Trusted host-side client for the orchestrator control plane."""
|
||||
|
||||
def __init__(self, base_url: str, *, timeout: float = DEFAULT_TIMEOUT_SECONDS) -> None:
|
||||
self._base = base_url.rstrip("/")
|
||||
self._timeout = timeout
|
||||
|
||||
def _request(
|
||||
self, method: str, path: str, body: dict[str, object] | None = None,
|
||||
) -> tuple[int, dict[str, object]]:
|
||||
"""Send one request; return `(status, payload)`. Raises
|
||||
`OrchestratorClientError` only when the orchestrator can't be reached
|
||||
or returns malformed data — HTTP *status* codes are returned so
|
||||
callers can treat 404 as a meaningful "no such bottle"."""
|
||||
data = json.dumps(body).encode() if body is not None else None
|
||||
headers = {"Content-Type": "application/json"} if data is not None else {}
|
||||
req = urllib.request.Request(
|
||||
f"{self._base}{path}", data=data, method=method, headers=headers,
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(req, timeout=self._timeout) as resp:
|
||||
raw = resp.read()
|
||||
payload = json.loads(raw) if raw else {}
|
||||
return resp.status, payload if isinstance(payload, dict) else {}
|
||||
except urllib.error.HTTPError as e:
|
||||
# A structured error response still carries a usable status.
|
||||
try:
|
||||
payload = json.loads(e.read() or b"{}")
|
||||
except (ValueError, OSError):
|
||||
payload = {}
|
||||
return e.code, payload if isinstance(payload, dict) else {}
|
||||
except (urllib.error.URLError, TimeoutError, OSError, ValueError) as e:
|
||||
raise OrchestratorClientError(f"{method} {path}: {e}") from e
|
||||
|
||||
def _ok(self, method: str, path: str, body: dict[str, object] | None = None) -> dict[str, object]:
|
||||
"""`_request` that requires a 2xx, raising otherwise."""
|
||||
status, payload = self._request(method, path, body)
|
||||
if not 200 <= status < 300:
|
||||
detail = payload.get("error", "")
|
||||
raise OrchestratorClientError(f"{method} {path}: HTTP {status} {detail}".rstrip())
|
||||
return payload
|
||||
|
||||
def health(self) -> bool:
|
||||
"""True iff the control plane answers `GET /health` with 200."""
|
||||
try:
|
||||
status, _ = self._request("GET", "/health")
|
||||
except OrchestratorClientError:
|
||||
return False
|
||||
return status == 200
|
||||
|
||||
def register_bottle(
|
||||
self,
|
||||
source_ip: str,
|
||||
*,
|
||||
image_ref: str = "",
|
||||
metadata: str = "",
|
||||
policy: str = "",
|
||||
) -> RegisteredBottle:
|
||||
"""Register a bottle and broker its launch (`POST /bottles`). Returns
|
||||
its minted id + identity token."""
|
||||
payload = self._ok("POST", "/bottles", {
|
||||
"source_ip": source_ip,
|
||||
"image_ref": image_ref,
|
||||
"metadata": metadata,
|
||||
"policy": policy,
|
||||
})
|
||||
bottle_id = payload.get("bottle_id")
|
||||
token = payload.get("identity_token")
|
||||
if not isinstance(bottle_id, str) or not isinstance(token, str):
|
||||
raise OrchestratorClientError("register: response missing bottle_id/identity_token")
|
||||
return RegisteredBottle(bottle_id=bottle_id, identity_token=token)
|
||||
|
||||
def teardown_bottle(self, bottle_id: str) -> bool:
|
||||
"""Tear a bottle down (`DELETE /bottles/<id>`). False if the
|
||||
orchestrator didn't know it (404) — idempotent for cleanup paths."""
|
||||
status, _ = self._request("DELETE", f"/bottles/{bottle_id}")
|
||||
if status == 404:
|
||||
return False
|
||||
if not 200 <= status < 300:
|
||||
raise OrchestratorClientError(f"teardown {bottle_id}: HTTP {status}")
|
||||
return True
|
||||
|
||||
def set_policy(self, bottle_id: str, policy: str) -> bool:
|
||||
"""Live-reload a bottle's policy (`PUT /bottles/<id>/policy`). False on
|
||||
404 (unknown bottle)."""
|
||||
status, _ = self._request("PUT", f"/bottles/{bottle_id}/policy", {"policy": policy})
|
||||
if status == 404:
|
||||
return False
|
||||
if not 200 <= status < 300:
|
||||
raise OrchestratorClientError(f"set_policy {bottle_id}: HTTP {status}")
|
||||
return True
|
||||
|
||||
def list_bottles(self) -> list[dict[str, object]]:
|
||||
"""Every registered bottle's redacted record (`GET /bottles`)."""
|
||||
payload = self._ok("GET", "/bottles")
|
||||
bottles = payload.get("bottles")
|
||||
return bottles if isinstance(bottles, list) else []
|
||||
|
||||
|
||||
__all__ = [
|
||||
"OrchestratorClient",
|
||||
"OrchestratorClientError",
|
||||
"RegisteredBottle",
|
||||
"DEFAULT_TIMEOUT_SECONDS",
|
||||
]
|
||||
@@ -34,6 +34,7 @@ import http.server
|
||||
import json
|
||||
import os
|
||||
import socketserver
|
||||
import sys
|
||||
import typing
|
||||
from urllib.parse import urlsplit
|
||||
|
||||
@@ -151,12 +152,20 @@ class Handler(http.server.BaseHTTPRequestHandler):
|
||||
super().log_message(format, *args)
|
||||
|
||||
def _serve(self, method: str) -> None:
|
||||
"""Read the request body, dispatch it, and write the JSON reply."""
|
||||
"""Read the request body, dispatch it, and write the JSON reply. A
|
||||
dispatch failure (e.g. a broker error) returns a 500 rather than
|
||||
crashing the connection, so one bad request can't take the control
|
||||
plane down for the caller."""
|
||||
server = self.server
|
||||
assert isinstance(server, ControlPlaneServer)
|
||||
length = int(self.headers.get("Content-Length") or 0)
|
||||
body = self.rfile.read(length) if length > 0 else b""
|
||||
status, payload = dispatch(server.orchestrator, method, self.path, body)
|
||||
try:
|
||||
status, payload = dispatch(server.orchestrator, method, self.path, body)
|
||||
except Exception as e: # noqa: BLE001 — the control plane must stay up
|
||||
sys.stderr.write(f"orchestrator: {method} {self.path} failed: {e!r}\n")
|
||||
sys.stderr.flush()
|
||||
status, payload = 500, {"error": f"internal error: {e}"}
|
||||
data = json.dumps(payload).encode()
|
||||
self.send_response(status)
|
||||
self.send_header("Content-Type", "application/json")
|
||||
|
||||
@@ -25,6 +25,19 @@ from ..docker_cmd import run_docker
|
||||
|
||||
GATEWAY_NAME = "bot-bottle-orch-gateway"
|
||||
GATEWAY_LABEL = "bot-bottle-orch-gateway=1"
|
||||
# The single user-defined network the gateway and every agent bottle share.
|
||||
# Agents attach here with a pinned IP and reach the gateway's egress /
|
||||
# git-http / supervise ports by its address — no host port publishing, and
|
||||
# the source IP the gateway attributes by is the address on this network.
|
||||
GATEWAY_NETWORK = "bot-bottle-gateway"
|
||||
|
||||
# mitmproxy's CA dir in the bundle. A persistent named volume here keeps the
|
||||
# gateway's self-generated CA STABLE across container recreation — every agent
|
||||
# installs this one CA to trust the shared gateway's TLS interception, so it
|
||||
# must not rotate when the gateway restarts.
|
||||
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
|
||||
# rather than imported from backend.docker.sidecar_bundle, which would drag
|
||||
@@ -77,11 +90,18 @@ class DockerGateway(Gateway):
|
||||
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,
|
||||
) -> 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). Empty → single-tenant.
|
||||
self._orchestrator_url = orchestrator_url
|
||||
self._build_context = build_context or _REPO_ROOT
|
||||
self._dockerfile = dockerfile
|
||||
|
||||
@@ -89,17 +109,23 @@ class DockerGateway(Gateway):
|
||||
return run_docker(["docker", "image", "inspect", self.image_ref]).returncode == 0
|
||||
|
||||
def ensure_built(self) -> None:
|
||||
"""Build the bundle image from its Dockerfile when it's missing.
|
||||
No-op when the image is already present, or when no dockerfile is
|
||||
configured (e.g. a pre-pulled image)."""
|
||||
if self._dockerfile is None or self.image_exists():
|
||||
"""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
|
||||
proc = run_docker([
|
||||
"docker", "build",
|
||||
"-t", self.image_ref,
|
||||
"-f", str(self._build_context / self._dockerfile),
|
||||
str(self._build_context),
|
||||
])
|
||||
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()}")
|
||||
|
||||
@@ -112,21 +138,55 @@ class DockerGateway(Gateway):
|
||||
])
|
||||
return self.name in proc.stdout.split()
|
||||
|
||||
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:
|
||||
if self.is_running():
|
||||
return
|
||||
self._ensure_network()
|
||||
# Clear any stale (stopped) 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])
|
||||
proc = run_docker([
|
||||
argv = [
|
||||
"docker", "run", "--detach",
|
||||
"--name", self.name,
|
||||
"--label", GATEWAY_LABEL,
|
||||
self.image_ref,
|
||||
])
|
||||
"--network", self.network,
|
||||
# Persist the self-generated CA so it survives restarts (agents
|
||||
# trust it) — see GATEWAY_CA_VOLUME.
|
||||
"--volume", f"{GATEWAY_CA_VOLUME}:{MITMPROXY_HOME}",
|
||||
]
|
||||
if self._orchestrator_url:
|
||||
# Makes the gateway's egress / git / supervise daemons multi-tenant:
|
||||
# each request resolves source-IP -> policy against the control plane.
|
||||
argv += ["--env", f"BOT_BOTTLE_ORCHESTRATOR_URL={self._orchestrator_url}"]
|
||||
argv.append(self.image_ref)
|
||||
proc = run_docker(argv)
|
||||
if proc.returncode != 0:
|
||||
raise GatewayError(f"gateway failed to start: {proc.stderr.strip()}")
|
||||
|
||||
def ca_cert_pem(self) -> str:
|
||||
"""The gateway's CA certificate (PEM) that agents install to trust its
|
||||
TLS interception. Read from the running container; raises if the
|
||||
gateway hasn't generated it yet (it's created on first mitmproxy
|
||||
start)."""
|
||||
proc = run_docker(["docker", "exec", self.name, "cat", GATEWAY_CA_CERT])
|
||||
if proc.returncode != 0 or not proc.stdout.strip():
|
||||
raise GatewayError(
|
||||
f"gateway CA cert not available: {proc.stderr.strip() or 'empty'}"
|
||||
)
|
||||
return proc.stdout
|
||||
|
||||
def stop(self) -> None:
|
||||
proc = run_docker(["docker", "rm", "--force", self.name])
|
||||
if proc.returncode != 0 and "No such container" not in proc.stderr:
|
||||
@@ -135,5 +195,6 @@ class DockerGateway(Gateway):
|
||||
|
||||
__all__ = [
|
||||
"Gateway", "DockerGateway", "GatewayError",
|
||||
"GATEWAY_NAME", "GATEWAY_LABEL", "GATEWAY_IMAGE",
|
||||
"GATEWAY_NAME", "GATEWAY_LABEL", "GATEWAY_IMAGE", "GATEWAY_NETWORK",
|
||||
"GATEWAY_CA_VOLUME", "GATEWAY_CA_CERT",
|
||||
]
|
||||
|
||||
@@ -0,0 +1,161 @@
|
||||
"""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.
|
||||
|
||||
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).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import time
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
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
|
||||
|
||||
DEFAULT_PORT = 8099
|
||||
ORCHESTRATOR_NAME = "bot-bottle-orchestrator"
|
||||
ORCHESTRATOR_LABEL = "bot-bottle-orchestrator=1"
|
||||
|
||||
# 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).
|
||||
_REPO_ROOT = Path(__file__).resolve().parents[2]
|
||||
_APP_DIR = "/app"
|
||||
_ROOT_IN_CONTAINER = "/bot-bottle-root"
|
||||
|
||||
_HEALTH_POLL_SECONDS = 0.25
|
||||
DEFAULT_STARTUP_TIMEOUT_SECONDS = 45.0
|
||||
_HEALTH_REQUEST_TIMEOUT_SECONDS = 1.0
|
||||
|
||||
|
||||
class OrchestratorStartError(RuntimeError):
|
||||
"""The orchestrator container did not become healthy within the timeout."""
|
||||
|
||||
|
||||
class OrchestratorService:
|
||||
"""Manages the orchestrator control-plane container + the shared gateway.
|
||||
Callers only need `ensure_running()` + `url`."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
port: int = DEFAULT_PORT,
|
||||
network: str = GATEWAY_NETWORK,
|
||||
image: str = GATEWAY_IMAGE,
|
||||
repo_root: Path = _REPO_ROOT,
|
||||
host_root: Path | None = None,
|
||||
) -> None:
|
||||
self.port = port
|
||||
self.network = network
|
||||
self.image = image
|
||||
self._repo_root = repo_root
|
||||
self._host_root = host_root or bot_bottle_root()
|
||||
|
||||
@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://{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:
|
||||
return resp.status == 200
|
||||
except (urllib.error.URLError, TimeoutError, OSError):
|
||||
return False
|
||||
|
||||
def _container_running(self, name: str) -> bool:
|
||||
proc = run_docker(["docker", "ps", "--filter", f"name=^/{name}$", "--format", "{{.Names}}"])
|
||||
return name in proc.stdout.split()
|
||||
|
||||
def _run_orchestrator_container(self) -> None:
|
||||
"""Start the control-plane container (idempotent: clears a stale
|
||||
fixed-name container first). Register-only broker → no docker socket."""
|
||||
run_docker(["docker", "rm", "--force", ORCHESTRATOR_NAME])
|
||||
proc = run_docker([
|
||||
"docker", "run", "--detach",
|
||||
"--name", ORCHESTRATOR_NAME,
|
||||
"--label", ORCHESTRATOR_LABEL,
|
||||
"--network", self.network,
|
||||
# Host CLI reaches the control plane here; bound to loopback so it
|
||||
# is not exposed on the host's external interfaces.
|
||||
"--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}",
|
||||
"--entrypoint", "python3",
|
||||
self.image,
|
||||
"-m", "bot_bottle.orchestrator",
|
||||
"--host", "0.0.0.0", "--port", str(self.port), "--broker", "stub",
|
||||
])
|
||||
if proc.returncode != 0:
|
||||
raise OrchestratorStartError(
|
||||
f"orchestrator container failed to start: {proc.stderr.strip()}"
|
||||
)
|
||||
|
||||
def _gateway(self) -> DockerGateway:
|
||||
return DockerGateway(self.image, network=self.network, orchestrator_url=self.internal_url)
|
||||
|
||||
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 and a running
|
||||
gateway are left untouched. Raises `OrchestratorStartError` on
|
||||
timeout."""
|
||||
gateway = self._gateway()
|
||||
gateway.ensure_built() # build the bundle image if missing (both use it)
|
||||
if self.is_healthy():
|
||||
gateway.ensure_running() # make sure the gateway is up too
|
||||
return self.url
|
||||
|
||||
log.info("starting orchestrator container", context={"name": ORCHESTRATOR_NAME})
|
||||
gateway.ensure_running() # creates the shared network + gateway
|
||||
self._run_orchestrator_container()
|
||||
|
||||
deadline = time.monotonic() + startup_timeout
|
||||
while time.monotonic() < deadline:
|
||||
if self.is_healthy():
|
||||
log.info("orchestrator 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"
|
||||
)
|
||||
|
||||
def stop(self) -> None:
|
||||
"""Remove the orchestrator + gateway containers (idempotent)."""
|
||||
run_docker(["docker", "rm", "--force", ORCHESTRATOR_NAME])
|
||||
self._gateway().stop()
|
||||
|
||||
|
||||
__all__ = [
|
||||
"OrchestratorService",
|
||||
"OrchestratorStartError",
|
||||
"ORCHESTRATOR_NAME",
|
||||
"DEFAULT_PORT",
|
||||
"DEFAULT_STARTUP_TIMEOUT_SECONDS",
|
||||
]
|
||||
@@ -0,0 +1,57 @@
|
||||
"""Consolidated registration inputs (PRD 0070, docker slice).
|
||||
|
||||
Bridges the existing per-bottle `prepare` output to the consolidated
|
||||
registry: turns a prepared bottle's egress plan into the backend-neutral
|
||||
inputs `Orchestrator.launch_bottle` takes — the egress **policy** blob and
|
||||
launch **metadata**.
|
||||
|
||||
The policy blob is the exact routes YAML the per-bottle egress sidecar used
|
||||
to read from a file; in the consolidated model the multi-tenant gateway's
|
||||
`PolicyResolver` fetches it from the registry per request (keyed by source
|
||||
IP) instead. Same render, so consolidated and single-tenant egress apply
|
||||
byte-identical policy — a bottle's allow-list doesn't change when it moves
|
||||
onto the shared gateway.
|
||||
|
||||
Host-side glue (imports `bot_bottle.egress`), used by the launch path — not
|
||||
by the lean orchestrator control-plane process itself.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from dataclasses import dataclass
|
||||
|
||||
from ..egress import EgressPlan, egress_render_routes
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class RegistrationInputs:
|
||||
"""What `Orchestrator.launch_bottle` needs to register a bottle, derived
|
||||
from its prepared plan. `policy` is served verbatim by the gateway's
|
||||
`/resolve`; `metadata` is opaque forward-compat state — it carries the
|
||||
human slug so the console / supervise can show a name, not just the
|
||||
minted bottle id."""
|
||||
|
||||
policy: str
|
||||
metadata: str
|
||||
|
||||
|
||||
def egress_policy(plan: EgressPlan) -> str:
|
||||
"""The bottle's egress policy blob: the routes YAML the gateway serves
|
||||
and the addon parses with `load_config`. Identical to the per-bottle
|
||||
`routes.yaml` render, so the consolidated path applies the same
|
||||
allow-list."""
|
||||
return egress_render_routes(plan.routes, log=plan.log)
|
||||
|
||||
|
||||
def registration_inputs(plan: EgressPlan) -> RegistrationInputs:
|
||||
"""Assemble the orchestrator registration inputs from a prepared egress
|
||||
plan. `metadata` records the slug so the shared registry can map a minted
|
||||
bottle id back to its human name."""
|
||||
return RegistrationInputs(
|
||||
policy=egress_policy(plan),
|
||||
metadata=json.dumps({"slug": plan.slug}),
|
||||
)
|
||||
|
||||
|
||||
__all__ = ["RegistrationInputs", "egress_policy", "registration_inputs"]
|
||||
@@ -47,12 +47,11 @@ class PolicyResolver:
|
||||
self._base = base_url.rstrip("/")
|
||||
self._timeout = timeout
|
||||
|
||||
def resolve(self, source_ip: str, identity_token: str = "") -> str | None:
|
||||
"""The calling bottle's policy blob, or None if unattributed. Always
|
||||
fetches from the orchestrator so revocations / changes / teardowns
|
||||
are honored immediately. `identity_token` is optional — omit it to
|
||||
resolve by source IP alone (the network-layer attribution).
|
||||
Raises `PolicyResolveError` if the orchestrator can't be reached."""
|
||||
def _post_resolve(self, source_ip: str, identity_token: str) -> dict[str, object] | None:
|
||||
"""The orchestrator's `/resolve` payload for this client, or None if
|
||||
unattributed (a clean `403`). Raises `PolicyResolveError` on an
|
||||
unreachable / unexpected-status / malformed response so every caller
|
||||
can fail closed. Shared by `resolve` and `resolve_bottle_id`."""
|
||||
body = json.dumps(
|
||||
{"source_ip": source_ip, "identity_token": identity_token}
|
||||
).encode()
|
||||
@@ -69,8 +68,56 @@ class PolicyResolver:
|
||||
raise PolicyResolveError(f"/resolve returned HTTP {e.code}") from e
|
||||
except (urllib.error.URLError, TimeoutError, OSError, ValueError) as e:
|
||||
raise PolicyResolveError(f"/resolve unreachable or malformed: {e}") from e
|
||||
policy = payload.get("policy") if isinstance(payload, dict) else None
|
||||
return payload if isinstance(payload, dict) else {}
|
||||
|
||||
def resolve(self, source_ip: str, identity_token: str = "") -> str | None:
|
||||
"""The calling bottle's policy blob, or None if unattributed. Always
|
||||
fetches from the orchestrator so revocations / changes / teardowns
|
||||
are honored immediately.
|
||||
|
||||
`identity_token` is optional *transitionally* — omitting it resolves
|
||||
by source IP alone (the network-layer attribution, sound by
|
||||
construction on Firecracker's `/31`+nft, weaker elsewhere). The
|
||||
consolidated end state makes the token mandatory so the app-layer
|
||||
defense is always enforced, not silently degraded; that flips at the
|
||||
`/resolve` boundary once identity-token *delivery* lands (a PRD 0070
|
||||
open question — we can't require what the agent can't yet present).
|
||||
Raises `PolicyResolveError` if the orchestrator can't be reached."""
|
||||
payload = self._post_resolve(source_ip, identity_token)
|
||||
if payload is None:
|
||||
return None
|
||||
policy = payload.get("policy")
|
||||
return policy if isinstance(policy, str) else ""
|
||||
|
||||
def resolve_bottle_id(self, source_ip: str, identity_token: str = "") -> str | None:
|
||||
"""The calling bottle's id, or None if unattributed. This is the
|
||||
source-IP-keyed identity the git-gate uses to select the bottle's
|
||||
repo namespace (there is no per-bottle policy blob to parse — the
|
||||
bottle *is* the namespace). Same fail-closed contract as `resolve`."""
|
||||
payload = self._post_resolve(source_ip, identity_token)
|
||||
if payload is None:
|
||||
return None
|
||||
bottle_id = payload.get("bottle_id")
|
||||
return bottle_id if isinstance(bottle_id, str) and bottle_id else None
|
||||
|
||||
def resolve_policy_and_bottle_id(
|
||||
self, source_ip: str, identity_token: str = "",
|
||||
) -> tuple[str | None, str | None]:
|
||||
"""Both the policy blob and the bottle id in a single `/resolve` — so
|
||||
a caller that needs each (the egress addon: policy for routing, bottle
|
||||
id to key the calling bottle's supervise queue + safelist) makes one
|
||||
round-trip, not two. Returns `(None, None)` when unattributed (a clean
|
||||
`403`). Raises `PolicyResolveError` if the orchestrator can't be
|
||||
reached, so the caller still fails closed."""
|
||||
payload = self._post_resolve(source_ip, identity_token)
|
||||
if payload is None:
|
||||
return None, None
|
||||
policy = payload.get("policy")
|
||||
bottle_id = payload.get("bottle_id")
|
||||
return (
|
||||
policy if isinstance(policy, str) else "",
|
||||
bottle_id if isinstance(bottle_id, str) and bottle_id else None,
|
||||
)
|
||||
|
||||
|
||||
__all__ = ["PolicyResolver", "PolicyResolveError"]
|
||||
|
||||
@@ -15,6 +15,12 @@ The bottle slug arrives via SUPERVISE_BOTTLE_SLUG env (stamped at
|
||||
container creation by the backend's start step). SUPERVISE_DB_PATH
|
||||
points at the bind-mounted host database.
|
||||
|
||||
Consolidated (PRD 0070): when BOT_BOTTLE_ORCHESTRATOR_URL is set, one
|
||||
shared server fronts every bottle and attributes each proposal to the
|
||||
calling bottle by source IP (resolved from the orchestrator) instead of a
|
||||
fixed slug — an unattributed source fails closed. Unset → the legacy
|
||||
per-bottle single-tenant server, unchanged.
|
||||
|
||||
Speaks MCP over HTTP+JSON-RPC. Methods handled:
|
||||
|
||||
* `initialize` — handshake; returns server info + caps.
|
||||
@@ -40,16 +46,18 @@ import time
|
||||
import typing
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
from dataclasses import dataclass
|
||||
from dataclasses import dataclass, replace
|
||||
|
||||
try:
|
||||
# Same-directory imports inside the bundle container; these files are
|
||||
# COPYed flat under /app by Dockerfile.sidecars.
|
||||
from egress_addon_core import LOG_OFF, load_config
|
||||
from policy_resolver import PolicyResolveError, PolicyResolver
|
||||
import supervise as _sv
|
||||
except ModuleNotFoundError:
|
||||
# Package imports for host-side tests and tooling.
|
||||
from .egress_addon_core import LOG_OFF, load_config
|
||||
from .policy_resolver import PolicyResolveError, PolicyResolver
|
||||
from . import supervise as _sv
|
||||
|
||||
|
||||
@@ -73,6 +81,12 @@ DEFAULT_RESPONSE_TIMEOUT_SECONDS = 30.0
|
||||
MIN_RESPONSE_POLL_INTERVAL_SECONDS = 0.05
|
||||
EGRESS_LIST_TIMEOUT_SECONDS = 5.0
|
||||
|
||||
# Consolidated (multi-tenant) mode: when set, one shared supervise server
|
||||
# fronts every bottle and attributes each proposal to the calling bottle by
|
||||
# source IP (resolved from the orchestrator), instead of a single
|
||||
# SUPERVISE_BOTTLE_SLUG env. Unset → legacy per-bottle single-tenant.
|
||||
ORCHESTRATOR_URL_ENV = "BOT_BOTTLE_ORCHESTRATOR_URL"
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class JsonRpcRequest:
|
||||
@@ -511,9 +525,30 @@ class MCPHandler(http.server.BaseHTTPRequestHandler):
|
||||
if method == "tools/list":
|
||||
return handle_tools_list(req.params)
|
||||
if method == "tools/call":
|
||||
return handle_tools_call(req.params, config)
|
||||
# Attribute the proposal to the calling bottle. Single-tenant → the
|
||||
# env slug on `config`; consolidated → the source-IP-resolved
|
||||
# bottle id, so one shared server queues each bottle's proposal
|
||||
# under its own slug.
|
||||
return handle_tools_call(req.params, self._attributed_config(config))
|
||||
raise _RpcClientError(ERR_METHOD_NOT_FOUND, f"method not found: {method}")
|
||||
|
||||
def _attributed_config(self, config: ServerConfig) -> ServerConfig:
|
||||
"""The ServerConfig with `bottle_slug` bound to *this request's* bottle.
|
||||
Single-tenant (no resolver): unchanged. Consolidated: the bottle id
|
||||
attributed from the source IP — **fail-closed**, an unattributed or
|
||||
unreachable source raises so no proposal is queued under the wrong (or
|
||||
empty) slug."""
|
||||
resolver = getattr(self.server, "policy_resolver", None)
|
||||
if resolver is None:
|
||||
return config
|
||||
try:
|
||||
bottle_id = resolver.resolve_bottle_id(self.client_address[0])
|
||||
except PolicyResolveError as e:
|
||||
raise _RpcInternalError(f"orchestrator unreachable, cannot attribute: {e}") from e
|
||||
if not bottle_id:
|
||||
raise _RpcInternalError("request source is not attributed to a bottle")
|
||||
return replace(config, bottle_slug=bottle_id)
|
||||
|
||||
def _write_jsonrpc(self, body: bytes) -> None:
|
||||
self.send_response(200)
|
||||
self.send_header("Content-Type", "application/json")
|
||||
@@ -537,6 +572,9 @@ class MCPServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
|
||||
allow_reuse_address = True
|
||||
daemon_threads = True
|
||||
config: ServerConfig = ServerConfig(bottle_slug="")
|
||||
# None → single-tenant (proposals use config.bottle_slug); set → consolidated
|
||||
# (each proposal attributed to the source-IP-resolved bottle).
|
||||
policy_resolver: "PolicyResolver | None" = None
|
||||
|
||||
|
||||
# --- Entry point -----------------------------------------------------------
|
||||
@@ -548,15 +586,17 @@ def serve(
|
||||
port: int = _sv.SUPERVISE_PORT,
|
||||
bind: str = "0.0.0.0",
|
||||
response_timeout_seconds: float = DEFAULT_RESPONSE_TIMEOUT_SECONDS,
|
||||
resolver: "PolicyResolver | None" = None,
|
||||
) -> typing.NoReturn:
|
||||
server = MCPServer((bind, port), MCPHandler)
|
||||
server.config = ServerConfig(
|
||||
bottle_slug=bottle_slug,
|
||||
response_timeout_seconds=response_timeout_seconds,
|
||||
)
|
||||
server.policy_resolver = resolver
|
||||
mode = "multi-tenant" if resolver else f"slug={bottle_slug!r}"
|
||||
sys.stderr.write(
|
||||
f"supervise listening on {bind}:{port}; "
|
||||
f"slug={bottle_slug!r}; "
|
||||
f"supervise listening on {bind}:{port}; {mode}; "
|
||||
f"tools: {', '.join(t['name'] for t in TOOL_DEFINITIONS)}\n" # type: ignore[arg-type]
|
||||
)
|
||||
sys.stderr.flush()
|
||||
@@ -571,8 +611,12 @@ def serve(
|
||||
|
||||
def main(argv: list[str]) -> int:
|
||||
del argv # config is env-only, no CLI flags
|
||||
orch_url = os.environ.get(ORCHESTRATOR_URL_ENV, "").strip()
|
||||
resolver = PolicyResolver(orch_url) if orch_url else None
|
||||
bottle_slug = os.environ.get("SUPERVISE_BOTTLE_SLUG", "")
|
||||
if not bottle_slug:
|
||||
# Consolidated mode resolves the slug per request, so the env slug is
|
||||
# optional there; single-tenant still requires it.
|
||||
if not bottle_slug and resolver is None:
|
||||
sys.stderr.write("supervise: SUPERVISE_BOTTLE_SLUG env is unset\n")
|
||||
return 2
|
||||
port = int(os.environ.get("SUPERVISE_PORT", str(_sv.SUPERVISE_PORT)))
|
||||
@@ -587,6 +631,7 @@ def main(argv: list[str]) -> int:
|
||||
port=port,
|
||||
bind=bind,
|
||||
response_timeout_seconds=response_timeout_seconds,
|
||||
resolver=resolver,
|
||||
)
|
||||
return 0 # serve() does not return
|
||||
|
||||
|
||||
@@ -36,6 +36,24 @@ small bot-bottle-specific reverse proxy modeled on the
|
||||
phantom-token shape is probably the right call. For Gitea / GitHub /
|
||||
GitLab, the same proxy generalizes by config.
|
||||
|
||||
**Updated 2026-07-14:** OneCLI ([onecli.sh](https://onecli.sh/)) —
|
||||
already listed below — has matured into a GA, YC-backed Rust
|
||||
credential gateway ("The Identity Gateway for AI Agents", ~2.5k⭐,
|
||||
300k+ downloads) that implements the **same phantom-token pattern**
|
||||
this note recommends: the agent holds a placeholder token, the
|
||||
gateway swaps it for the real (AES-256-GCM-encrypted) credential at
|
||||
request time. It's now the most mature open-source realization of the
|
||||
exact design proposed here — a production-ready alternative to
|
||||
alpha-stage nono — at the cost of being a broader product (built-in
|
||||
vault + management dashboard + hosted cloud tier + 50+ app
|
||||
integrations) rather than a minimal proxy. Its managed/cloud tier and
|
||||
per-agent dashboard also overlap bot-bottle's own planned paid control
|
||||
plane (bot-bottle-console, issue #327), so it's worth tracking as both
|
||||
a build-vs-adopt option *and* a product-level competitor. The
|
||||
build-first recommendation still stands (see synthesis below), but
|
||||
adopting OneCLI's OSS core is now a credible alternative where nono was
|
||||
too green.
|
||||
|
||||
## The shared problem
|
||||
|
||||
Linux has no per-env-var ACL. Once a var is in a process's
|
||||
@@ -223,7 +241,7 @@ Two categories:
|
||||
| **Infisical Agent Vault** | B | MIT (EE carve-out) | In-process HTTPS_PROXY forward proxy | TLS MITM, dummy-to-real swap | No — HTTPS_PROXY model | Service-level | Active; v0.19.0 May 2026, ~1k⭐ |
|
||||
| **nono** | B | Apache-2.0 | In-process reverse proxy | Phantom token, explicit URL routing | **Yes** — `BASE_URL=http://127.0.0.1:PORT/…` | Host + endpoint | Early alpha; v0.53.0 May 2026, 2.4k⭐ |
|
||||
| **Aegis** | B | Apache-2.0 | In-process reverse proxy | Path routing (`localhost:3100/{svc}/…`) | Configurable, undocumented for Anthropic | Method/path/rate/time | Very new, 10⭐ |
|
||||
| **OneCLI** | B | Apache-2.0 | Reverse proxy + management UI | Host/path matching, Bitwarden integration | Configurable | Per-agent scoping | Active; v1.23.0 May 2026, 2.1k⭐ |
|
||||
| **OneCLI** | B | Apache-2.0 | Reverse proxy + built-in vault + dashboard | **Phantom token** (placeholder→real swap at request time), AES-256-GCM vault | Yes (host match) | Per-agent + endpoint/method + rate limits | GA; Rust; YC-backed; ~2.5k⭐, 300k+ downloads (Jul 2026) |
|
||||
| **Aembit** | B | Proprietary | Sidecar + cloud control plane | TLS intercept, SPIFFE, JIT creds | No — intercepts by destination | Policy-based | GA (Apr 2026) |
|
||||
| **LiteLLM Proxy** | A | MIT | Reverse proxy | Virtual key → upstream key | Yes — set base URL to LiteLLM | Route-level | 45k⭐; **CVE-2026-42208 exploited Apr 2026**, patch v1.83.7 |
|
||||
| **Portkey Gateway** | A | MIT (OSS core) | Reverse proxy | Virtual key vault (cloud or Enterprise self-host) | Yes — documented for Claude Code | Config-based | Production; virtual-key vault needs Enterprise for self-host |
|
||||
@@ -242,6 +260,18 @@ Two categories:
|
||||
`ANTHROPIC_BASE_URL`. **Blocker:** nono is explicitly
|
||||
"early alpha, not security audited."
|
||||
|
||||
**Update (2026-07-14):** OneCLI ([onecli.sh](https://onecli.sh/))
|
||||
ships the same phantom-token shape but is GA and YC-backed (Rust,
|
||||
~2.5k⭐, 300k+ downloads) — the maturity nono lacks. Trade-offs: it's
|
||||
a full identity-gateway *product* (encrypted vault, management
|
||||
dashboard, 50+ one-click app integrations, hosted cloud tier), much
|
||||
heavier than the ~100-line proxy proposed below, and its hosted tier
|
||||
is a third-party credential custodian — precisely the trust
|
||||
dependency bot-bottle's isolation model exists to avoid. So: its
|
||||
Apache-2.0 OSS core is a credible *adopt* candidate for the
|
||||
phantom-token slice; its managed offering is a *competitor*, not a
|
||||
dependency to lean on.
|
||||
|
||||
- **TLS-MITM forward proxies** (Infisical Agent Vault, Cloudflare
|
||||
Sandbox Auth, Aembit, the existing pipelock) all double up on
|
||||
the CA-trust machinery PRD 0006 already built for pipelock.
|
||||
@@ -273,6 +303,15 @@ routing matches the design recommended here exactly; zero TLS
|
||||
work. But "not security audited" + "early alpha" means adopting it
|
||||
is a bet on the project rather than a buy-vs-build win.
|
||||
|
||||
**Mature phantom-token option (added 2026-07-14):** OneCLI — same
|
||||
architecture as nono, but GA, Rust, and YC-backed. Its Apache-2.0 OSS
|
||||
core is now the strongest *adopt* candidate for the phantom-token slice
|
||||
if building is undesirable; the caveats are product surface you don't
|
||||
need (bundled vault + dashboard) and that its hosted tier is a
|
||||
competitor rather than a dependency. Doesn't change the build-first
|
||||
recommendation for the narrow Anthropic-token slice, but it does mean
|
||||
"is there a mature drop-in?" now has a real answer.
|
||||
|
||||
**Most mature OSS purpose-built:** Infisical Agent Vault. MIT,
|
||||
v0.19.0 active, v0.17.0 added a containerized agent mode that
|
||||
maps directly to bot-bottle. Friction is the TLS-MITM topology
|
||||
@@ -376,6 +415,9 @@ already gives us for upstream push credentials.
|
||||
- [nono — phantom token blog](https://nono.sh/blog/blog-credential-injection)
|
||||
- [Aegis — GitHub](https://github.com/getaegis/aegis)
|
||||
- [OneCLI — GitHub](https://github.com/onecli/onecli)
|
||||
- [OneCLI — homepage](https://onecli.sh/)
|
||||
- [OneCLI — Y Combinator company page](https://www.ycombinator.com/companies/onecli)
|
||||
- [Show HN: OneCLI – Vault for AI Agents in Rust](https://news.ycombinator.com/item?id=47353558)
|
||||
- [Sandbox0 — GitHub](https://github.com/sandbox0-ai/sandbox0)
|
||||
- [Buildkite Cleanroom — GitHub](https://github.com/buildkite/cleanroom)
|
||||
- [Aembit IAM for Agentic AI — GA](https://aembit.io/blog/aembit-iam-for-agentic-ai-is-now-generally-available/)
|
||||
|
||||
@@ -71,6 +71,44 @@ manifest merge.
|
||||
network egress is logged by pipelock/mitmproxy, and per-run op-log/audit state
|
||||
is persisted to SQLite.
|
||||
|
||||
- **OneCLI** ([onecli.sh](https://onecli.sh/)) — YC-backed, GA, open-source
|
||||
(Apache-2.0, Rust) "identity gateway for AI agents": a credential/secret
|
||||
broker that holds API keys and OAuth tokens out of the agent's reach and
|
||||
injects them at the network layer (phantom-token — the agent sees a
|
||||
placeholder, the gateway swaps in the real, AES-256-GCM-encrypted credential
|
||||
at request time). Framework-agnostic and drop-in for any HTTP-calling agent,
|
||||
50+ app integrations, plus a hosted cloud tier with a per-agent dashboard and
|
||||
audit logs. Full technical breakdown in
|
||||
[`agent-credential-proxy-landscape.md`](agent-credential-proxy-landscape.md).
|
||||
|
||||
**How close a competitor:** near-exact on the *single axis of agent secret
|
||||
custody* — the exact thing bot-bottle sells as "the agent never sees real
|
||||
credentials, even via `printenv`." OneCLI does that one job well, is mature
|
||||
and funded, and is *more portable* (it sits in front of anything; bot-bottle
|
||||
only helps agents launched through bot-bottle). Takeaway: bot-bottle should
|
||||
stop treating secret custody as a *unique* differentiator. But OneCLI is
|
||||
**not** a competitor to bot-bottle's actual product — it does no agent
|
||||
sandboxing (containers/microVMs), no fleet/manifest layer, no named agents /
|
||||
skills / per-agent system prompts, no multi-provider launching, no egress
|
||||
firewall.
|
||||
|
||||
**Our edge:** (1) *Isolation is the product, not a proxy.* OneCLI keeps the
|
||||
key out of reach at the network layer, but the agent itself still runs
|
||||
unsandboxed — a hijacked agent behind OneCLI has full run of its host and can
|
||||
exfil captured data through any allowed host. bot-bottle runs the agent inside
|
||||
a kernel/VM-enforced sandbox, injects credentials across that same
|
||||
out-of-process boundary, *and* clamps egress with pipelock — defense in depth
|
||||
vs. a single network layer. (2) *Fleet + manifest model* with named agents,
|
||||
skills, per-agent system prompts, multi-provider and multi-backend — OneCLI
|
||||
has no equivalent. (3) *Trust posture:* OneCLI's managed tier reintroduces a
|
||||
third-party credential custodian, whereas bot-bottle's OSS-runtime +
|
||||
paid-control-plane split keeps custody inside the operator's own boundary —
|
||||
the stronger story for the security-minded self-hoster. **Tactical read:**
|
||||
adopt OneCLI's OSS core for the credential slice if building is undesirable
|
||||
(it's mature now); don't build atop its managed tier (competitor, not
|
||||
dependency); re-position bot-bottle on isolation + fleet + self-hosted custody
|
||||
rather than "we hide your secrets."
|
||||
|
||||
## What no found project does
|
||||
|
||||
None combine:
|
||||
|
||||
@@ -0,0 +1,51 @@
|
||||
"""Unit: agent-only consolidated compose render (PRD 0070)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import unittest
|
||||
|
||||
from bot_bottle.backend.docker.consolidated_compose import consolidated_agent_compose
|
||||
from tests.unit.test_compose import _plan
|
||||
|
||||
_GW = "172.18.0.2"
|
||||
_IP = "172.18.0.5"
|
||||
_NET = "bot-bottle-gateway"
|
||||
|
||||
|
||||
class TestConsolidatedAgentCompose(unittest.TestCase):
|
||||
def _spec(self, *, runsc: bool = False):
|
||||
plan = _plan(with_egress=True, supervise=True, with_git=True)
|
||||
if runsc:
|
||||
plan = type(plan)(**{**vars(plan), "use_runsc": True}) # type: ignore[arg-type]
|
||||
return consolidated_agent_compose(plan, gateway_ip=_GW, source_ip=_IP, network=_NET)
|
||||
|
||||
def test_only_agent_service_no_sidecars(self) -> None:
|
||||
# The whole point of consolidation: no per-bottle sidecar bundle.
|
||||
self.assertEqual(["agent"], list(self._spec()["services"]))
|
||||
|
||||
def test_agent_pinned_on_external_gateway_network(self) -> None:
|
||||
spec = self._spec()
|
||||
self.assertEqual({"external": True}, spec["networks"][_NET])
|
||||
agent_net = spec["services"]["agent"]["networks"][_NET]
|
||||
self.assertEqual(_IP, agent_net["ipv4_address"])
|
||||
|
||||
def test_proxy_and_ca_point_at_gateway(self) -> None:
|
||||
env = self._spec()["services"]["agent"]["environment"]
|
||||
self.assertIn(f"HTTPS_PROXY=http://{_GW}:9099", env)
|
||||
# git-http + supervise on the gateway must bypass the egress proxy.
|
||||
self.assertTrue(any(e.startswith("NO_PROXY=") and _GW in e for e in env))
|
||||
|
||||
def test_no_sidecar_dependency(self) -> None:
|
||||
self.assertNotIn("depends_on", self._spec()["services"]["agent"])
|
||||
|
||||
def test_runsc_runtime_when_enabled(self) -> None:
|
||||
self.assertEqual("runsc", self._spec(runsc=True)["services"]["agent"]["runtime"])
|
||||
|
||||
def test_forwarded_env_stays_bare_names(self) -> None:
|
||||
env = self._spec()["services"]["agent"]["environment"]
|
||||
# forwarded secrets are bare names (value inherited from process env).
|
||||
self.assertIn("CLAUDE_CODE_OAUTH_TOKEN", env)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,95 @@
|
||||
"""Unit: consolidated launch sequence — compose the orchestrator primitives (PRD 0070)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
from unittest.mock import MagicMock, Mock, patch
|
||||
|
||||
from bot_bottle.backend.docker.consolidated_launch import (
|
||||
launch_consolidated,
|
||||
teardown_consolidated,
|
||||
)
|
||||
from bot_bottle.egress import EgressPlan, EgressRoute
|
||||
from bot_bottle.git_gate import GitGatePlan
|
||||
from bot_bottle.orchestrator.client import RegisteredBottle
|
||||
|
||||
_MOD = "bot_bottle.backend.docker.consolidated_launch"
|
||||
|
||||
|
||||
def _egress_plan() -> EgressPlan:
|
||||
return EgressPlan(
|
||||
slug="demo", routes_path=Path("/x"), routes=(EgressRoute(host="api.example.com"),),
|
||||
token_env_map={},
|
||||
)
|
||||
|
||||
|
||||
def _git_plan() -> GitGatePlan:
|
||||
return GitGatePlan(
|
||||
slug="demo", entrypoint_script=Path(), hook_script=Path(),
|
||||
access_hook_script=Path(), upstreams=(),
|
||||
)
|
||||
|
||||
|
||||
def _client(*, bottles: list[dict[str, object]] | None = None) -> Mock:
|
||||
c = Mock()
|
||||
c.list_bottles.return_value = bottles or []
|
||||
c.register_bottle.return_value = RegisteredBottle("b1", "tok")
|
||||
return c
|
||||
|
||||
|
||||
class TestLaunchConsolidated(unittest.TestCase):
|
||||
def _run(
|
||||
self, client: Mock, provision: Mock | None = None,
|
||||
*, on_network: tuple[str, ...] = ("172.18.0.2",),
|
||||
):
|
||||
service = MagicMock()
|
||||
service.ensure_running.return_value = "http://orch:8080"
|
||||
with patch(f"{_MOD}._network_cidr", return_value="172.18.0.0/16"), \
|
||||
patch(f"{_MOD}._container_ip", return_value="172.18.0.2"), \
|
||||
patch(f"{_MOD}._network_container_ips", return_value=list(on_network)), \
|
||||
patch(f"{_MOD}.OrchestratorClient", return_value=client), \
|
||||
patch(f"{_MOD}.provision_git_gate", provision or Mock()):
|
||||
return launch_consolidated(_egress_plan(), _git_plan(), service=service)
|
||||
|
||||
def test_allocates_ip_registers_and_provisions(self) -> None:
|
||||
client = _client()
|
||||
provision = Mock()
|
||||
ctx = self._run(client, provision)
|
||||
# .1 is the router, .2 is the gateway → first bottle gets .3.
|
||||
self.assertEqual("172.18.0.3", ctx.source_ip)
|
||||
self.assertEqual("172.18.0.2", ctx.gateway_ip)
|
||||
self.assertEqual("b1", ctx.bottle_id)
|
||||
self.assertEqual("tok", ctx.identity_token)
|
||||
self.assertEqual("http://orch:8080", ctx.orchestrator_url)
|
||||
# Registered with the source IP + the egress policy blob.
|
||||
kwargs = client.register_bottle.call_args
|
||||
self.assertEqual("172.18.0.3", kwargs.args[0])
|
||||
self.assertIn("api.example.com", kwargs.kwargs["policy"])
|
||||
provision.assert_called_once()
|
||||
|
||||
def test_skips_all_addresses_on_the_network(self) -> None:
|
||||
# Gateway .2 + orchestrator .3 already attached -> agent gets .4.
|
||||
ctx = self._run(_client(), on_network=("172.18.0.2", "172.18.0.3"))
|
||||
self.assertEqual("172.18.0.4", ctx.source_ip)
|
||||
|
||||
def test_provision_failure_rolls_back_registration(self) -> None:
|
||||
client = _client()
|
||||
provision = Mock(side_effect=RuntimeError("provision boom"))
|
||||
with self.assertRaises(RuntimeError):
|
||||
self._run(client, provision)
|
||||
client.teardown_bottle.assert_called_once_with("b1") # no orphan left
|
||||
|
||||
|
||||
class TestTeardownConsolidated(unittest.TestCase):
|
||||
def test_deregisters_and_deprovisions(self) -> None:
|
||||
client = Mock()
|
||||
with patch(f"{_MOD}.OrchestratorClient", return_value=client), \
|
||||
patch(f"{_MOD}.deprovision_git_gate") as deprov:
|
||||
teardown_consolidated("b1", orchestrator_url="http://orch:8080")
|
||||
client.teardown_bottle.assert_called_once_with("b1")
|
||||
deprov.assert_called_once()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -1,4 +1,4 @@
|
||||
"""Unit: Docker launch step uses committed image when available."""
|
||||
"""Unit: Docker launch step uses committed image when available (consolidated)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -6,6 +6,7 @@ import contextlib
|
||||
import io
|
||||
import tempfile
|
||||
import unittest
|
||||
from collections.abc import Callable, Generator
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
from unittest import mock
|
||||
@@ -14,9 +15,11 @@ from bot_bottle.agent_provider import AgentProvisionPlan
|
||||
from bot_bottle.backend import BottleSpec
|
||||
from bot_bottle.backend.docker import launch as launch_mod
|
||||
from bot_bottle.backend.docker.bottle_plan import DockerBottlePlan
|
||||
from bot_bottle.backend.docker.consolidated_launch import LaunchContext
|
||||
from bot_bottle.egress import EgressPlan
|
||||
from bot_bottle.git_gate import GitGatePlan
|
||||
from bot_bottle.manifest import ManifestIndex
|
||||
from tests.unit import use_bottle_root
|
||||
|
||||
|
||||
_SLUG = "dev-abc12"
|
||||
@@ -28,163 +31,111 @@ _IDX = ManifestIndex.from_json_obj({
|
||||
"agents": {"demo": {"skills": [], "prompt": "", "bottle": "dev"}},
|
||||
})
|
||||
|
||||
_CTX = LaunchContext(
|
||||
bottle_id="b1", identity_token="t", source_ip="172.20.0.4",
|
||||
network="bot-bottle-gateway", gateway_ip="172.20.0.2",
|
||||
orchestrator_url="http://orch:8099",
|
||||
)
|
||||
|
||||
|
||||
def _plan(tmp: str) -> DockerBottlePlan:
|
||||
stage = Path(tmp)
|
||||
spec = BottleSpec(
|
||||
manifest=_IDX,
|
||||
agent_name="demo",
|
||||
copy_cwd=False,
|
||||
user_cwd=tmp,
|
||||
identity=_SLUG,
|
||||
manifest=_IDX, agent_name="demo", copy_cwd=False, user_cwd=tmp, identity=_SLUG,
|
||||
)
|
||||
return DockerBottlePlan(
|
||||
spec=spec,
|
||||
manifest=_IDX.load_for_agent("demo"),
|
||||
stage_dir=stage,
|
||||
git_gate_plan=GitGatePlan(
|
||||
slug=_SLUG,
|
||||
entrypoint_script=stage / "entrypoint.sh",
|
||||
hook_script=stage / "hook.sh",
|
||||
access_hook_script=stage / "access-hook.sh",
|
||||
upstreams=(),
|
||||
slug=_SLUG, entrypoint_script=stage / "e.sh", hook_script=stage / "h.sh",
|
||||
access_hook_script=stage / "a.sh", upstreams=(),
|
||||
),
|
||||
egress_plan=EgressPlan(
|
||||
slug=_SLUG,
|
||||
routes_path=stage / "egress.yaml",
|
||||
routes=(),
|
||||
token_env_map={},
|
||||
slug=_SLUG, routes_path=stage / "egress.yaml", routes=(), token_env_map={},
|
||||
),
|
||||
supervise_plan=None,
|
||||
agent_provision=AgentProvisionPlan(
|
||||
template="claude",
|
||||
command="claude",
|
||||
prompt_mode="append_file",
|
||||
image=_DEFAULT_IMAGE,
|
||||
dockerfile="",
|
||||
guest_home="/home/node",
|
||||
instance_name=f"bot-bottle-{_SLUG}",
|
||||
prompt_file=stage / "prompt.txt",
|
||||
template="claude", command="claude", prompt_mode="append_file",
|
||||
image=_DEFAULT_IMAGE, dockerfile="", guest_home="/home/node",
|
||||
instance_name=f"bot-bottle-{_SLUG}", prompt_file=stage / "prompt.txt",
|
||||
guest_env={},
|
||||
),
|
||||
slug=_SLUG,
|
||||
forwarded_env={},
|
||||
use_runsc=False,
|
||||
slug=_SLUG, forwarded_env={}, use_runsc=False,
|
||||
)
|
||||
|
||||
|
||||
class TestLaunchCommittedImage(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self._tmp = tempfile.mkdtemp(prefix="launch-committed-test.")
|
||||
self.addCleanup(lambda: __import__("shutil").rmtree(self._tmp, ignore_errors=True))
|
||||
# The launch writes the gateway CA under the bottle root — sandbox it.
|
||||
self.addCleanup(use_bottle_root(Path(self._tmp)))
|
||||
|
||||
def tearDown(self) -> None:
|
||||
import shutil
|
||||
shutil.rmtree(self._tmp, ignore_errors=True)
|
||||
|
||||
def _run_launch(
|
||||
@contextlib.contextmanager
|
||||
def _patched(
|
||||
self,
|
||||
plan: DockerBottlePlan,
|
||||
*,
|
||||
committed_tag: str | None = None,
|
||||
image_present: bool = True,
|
||||
) -> list[str]:
|
||||
"""Drive launch() through its full sequence with the committed-image
|
||||
behaviour controlled by the arguments. Returns the images that were
|
||||
passed to `build_image` (empty list if it was never called)."""
|
||||
committed_tag: str | None,
|
||||
image_present: bool,
|
||||
compose: Callable[..., dict[str, Any]],
|
||||
) -> Generator[list[str], None, None]:
|
||||
built: list[str] = []
|
||||
gw = mock.Mock()
|
||||
gw.ca_cert_pem.return_value = "-----BEGIN CERTIFICATE-----\nx\n-----END CERTIFICATE-----\n"
|
||||
|
||||
def fake_build(image: str, ctx: str, *, dockerfile: str = "") -> None:
|
||||
def _build(image: str, ctx: str, *, dockerfile: str = "") -> None:
|
||||
del ctx, dockerfile
|
||||
built.append(image)
|
||||
|
||||
with mock.patch.object(
|
||||
launch_mod, "read_committed_image", return_value=committed_tag,
|
||||
), mock.patch.object(
|
||||
launch_mod.docker_mod, "image_exists", return_value=image_present,
|
||||
), mock.patch.object(
|
||||
launch_mod.docker_mod, "build_image", side_effect=fake_build,
|
||||
), mock.patch.object(
|
||||
launch_mod, "egress_tls_init",
|
||||
return_value=(Path("/egress_ca"), Path("/egress_cert")),
|
||||
), mock.patch.object(
|
||||
launch_mod.network_mod, "network_name_for_slug",
|
||||
return_value="bb-internal",
|
||||
), mock.patch.object(
|
||||
launch_mod.network_mod, "network_egress_name_for_slug",
|
||||
return_value="bb-egress",
|
||||
), mock.patch.object(
|
||||
launch_mod, "bottle_plan_to_compose",
|
||||
return_value={"services": {"agent": {}}},
|
||||
), mock.patch.object(
|
||||
launch_mod, "write_compose_file",
|
||||
return_value=Path("/tmp/compose.yml"),
|
||||
), mock.patch.object(launch_mod, "compose_up"), \
|
||||
mock.patch.object(launch_mod, "compose_dump_logs"), \
|
||||
mock.patch.object(launch_mod, "compose_down"), \
|
||||
contextlib.redirect_stderr(io.StringIO()):
|
||||
provision = mock.Mock(return_value=None)
|
||||
with launch_mod.launch(plan, provision=provision):
|
||||
pass
|
||||
with mock.patch.object(launch_mod, "read_committed_image", return_value=committed_tag), \
|
||||
mock.patch.object(launch_mod.docker_mod, "image_exists", return_value=image_present), \
|
||||
mock.patch.object(launch_mod.docker_mod, "build_image", side_effect=_build), \
|
||||
mock.patch.object(launch_mod, "launch_consolidated", return_value=_CTX), \
|
||||
mock.patch.object(launch_mod, "teardown_consolidated"), \
|
||||
mock.patch.object(launch_mod, "DockerGateway", return_value=gw), \
|
||||
mock.patch.object(launch_mod, "consolidated_agent_compose", side_effect=compose), \
|
||||
mock.patch.object(launch_mod, "write_compose_file", return_value=Path("/tmp/c.yml")), \
|
||||
mock.patch.object(launch_mod, "compose_up"), \
|
||||
mock.patch.object(launch_mod, "compose_dump_logs"), \
|
||||
mock.patch.object(launch_mod, "compose_down"), \
|
||||
contextlib.redirect_stderr(io.StringIO()):
|
||||
yield built
|
||||
|
||||
def _run_launch(
|
||||
self, plan: DockerBottlePlan, *,
|
||||
committed_tag: str | None = None, image_present: bool = True,
|
||||
) -> list[str]:
|
||||
def compose(_p: DockerBottlePlan, **_kw: Any) -> dict[str, Any]:
|
||||
return {"services": {"agent": {}}}
|
||||
with self._patched(
|
||||
committed_tag=committed_tag, image_present=image_present, compose=compose,
|
||||
) as built:
|
||||
with launch_mod.launch(plan, provision=mock.Mock(return_value=None)):
|
||||
pass
|
||||
return built
|
||||
|
||||
def test_skips_build_when_committed_image_present(self) -> None:
|
||||
plan = _plan(self._tmp)
|
||||
built = self._run_launch(plan, committed_tag=_COMMITTED_TAG, image_present=True)
|
||||
self.assertEqual([], built, "build_image should not be called when committed image exists")
|
||||
built = self._run_launch(_plan(self._tmp), committed_tag=_COMMITTED_TAG, image_present=True)
|
||||
self.assertEqual([], built) # committed image reused, no build
|
||||
|
||||
def test_uses_committed_image_in_compose_spec(self) -> None:
|
||||
"""The compose spec renderer receives the committed image tag via
|
||||
plan.image — captured here by checking what bottle_plan_to_compose
|
||||
was called with."""
|
||||
plan = _plan(self._tmp)
|
||||
captured_plans: list[DockerBottlePlan] = []
|
||||
captured: list[DockerBottlePlan] = []
|
||||
|
||||
def fake_compose(p: DockerBottlePlan) -> dict[str, Any]:
|
||||
captured_plans.append(p)
|
||||
def compose(p: DockerBottlePlan, **_kw: Any) -> dict[str, Any]:
|
||||
captured.append(p)
|
||||
return {"services": {"agent": {}}}
|
||||
|
||||
with mock.patch.object(
|
||||
launch_mod, "read_committed_image", return_value=_COMMITTED_TAG,
|
||||
), mock.patch.object(
|
||||
launch_mod.docker_mod, "image_exists", return_value=True,
|
||||
), mock.patch.object(
|
||||
launch_mod.docker_mod, "build_image",
|
||||
), mock.patch.object(
|
||||
launch_mod, "egress_tls_init",
|
||||
return_value=(Path("/egress_ca"), Path("/egress_cert")),
|
||||
), mock.patch.object(
|
||||
launch_mod.network_mod, "network_name_for_slug",
|
||||
return_value="bb-internal",
|
||||
), mock.patch.object(
|
||||
launch_mod.network_mod, "network_egress_name_for_slug",
|
||||
return_value="bb-egress",
|
||||
), mock.patch.object(
|
||||
launch_mod, "bottle_plan_to_compose", side_effect=fake_compose,
|
||||
), mock.patch.object(
|
||||
launch_mod, "write_compose_file",
|
||||
return_value=Path("/tmp/compose.yml"),
|
||||
), mock.patch.object(launch_mod, "compose_up"), \
|
||||
mock.patch.object(launch_mod, "compose_dump_logs"), \
|
||||
mock.patch.object(launch_mod, "compose_down"), \
|
||||
contextlib.redirect_stderr(io.StringIO()):
|
||||
provision = mock.Mock(return_value=None)
|
||||
with launch_mod.launch(plan, provision=provision):
|
||||
with self._patched(committed_tag=_COMMITTED_TAG, image_present=True, compose=compose):
|
||||
with launch_mod.launch(_plan(self._tmp), provision=mock.Mock(return_value=None)):
|
||||
pass
|
||||
|
||||
self.assertEqual(1, len(captured_plans))
|
||||
self.assertEqual(_COMMITTED_TAG, captured_plans[0].image)
|
||||
self.assertEqual(_COMMITTED_TAG, captured[0].image)
|
||||
|
||||
def test_falls_back_to_build_when_no_committed_image(self) -> None:
|
||||
plan = _plan(self._tmp)
|
||||
built = self._run_launch(plan, committed_tag=None)
|
||||
self.assertEqual([_DEFAULT_IMAGE], built)
|
||||
self.assertEqual([_DEFAULT_IMAGE], self._run_launch(_plan(self._tmp), committed_tag=None))
|
||||
|
||||
def test_falls_back_to_build_when_committed_image_missing_from_daemon(self) -> None:
|
||||
plan = _plan(self._tmp)
|
||||
built = self._run_launch(
|
||||
plan, committed_tag=_COMMITTED_TAG, image_present=False,
|
||||
)
|
||||
built = self._run_launch(_plan(self._tmp), committed_tag=_COMMITTED_TAG, image_present=False)
|
||||
self.assertEqual([_DEFAULT_IMAGE], built)
|
||||
|
||||
|
||||
|
||||
@@ -19,9 +19,11 @@ from bot_bottle.agent_provider import AgentProvisionPlan
|
||||
from bot_bottle.backend import BottleSpec
|
||||
from bot_bottle.backend.docker import launch as launch_mod
|
||||
from bot_bottle.backend.docker.bottle_plan import DockerBottlePlan
|
||||
from bot_bottle.backend.docker.consolidated_launch import LaunchContext
|
||||
from bot_bottle.egress import EgressPlan
|
||||
from bot_bottle.git_gate import GitGatePlan
|
||||
from bot_bottle.manifest import ManifestIndex
|
||||
from tests.unit import use_bottle_root
|
||||
|
||||
_INDEX = ManifestIndex.from_json_obj({
|
||||
"bottles": {"dev": {}},
|
||||
@@ -77,41 +79,36 @@ def _plan(tmp: str) -> DockerBottlePlan:
|
||||
class TestTeardownWarning(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self._tmp = tempfile.mkdtemp(prefix="docker-launch-teardown-test.")
|
||||
|
||||
def tearDown(self) -> None:
|
||||
import shutil
|
||||
shutil.rmtree(self._tmp, ignore_errors=True)
|
||||
self.addCleanup(lambda: __import__("shutil").rmtree(self._tmp, ignore_errors=True))
|
||||
self.addCleanup(use_bottle_root(Path(self._tmp))) # sandbox the gateway CA write
|
||||
|
||||
def test_teardown_failure_emits_warning_with_container_and_operation(self):
|
||||
plan = _plan(self._tmp)
|
||||
buf = io.StringIO()
|
||||
gw = mock.Mock()
|
||||
gw.ca_cert_pem.return_value = "-----BEGIN CERTIFICATE-----\nx\n-----END CERTIFICATE-----\n"
|
||||
ctx = LaunchContext(
|
||||
bottle_id="b1", identity_token="t", source_ip="172.20.0.4",
|
||||
network="bot-bottle-gateway", gateway_ip="172.20.0.2",
|
||||
orchestrator_url="http://orch:8099",
|
||||
)
|
||||
|
||||
with mock.patch.object(launch_mod.docker_mod, "build_image"), \
|
||||
mock.patch.object(launch_mod, "launch_consolidated", return_value=ctx), \
|
||||
mock.patch.object(launch_mod, "teardown_consolidated"), \
|
||||
mock.patch.object(launch_mod, "DockerGateway", return_value=gw), \
|
||||
mock.patch.object(
|
||||
launch_mod, "egress_tls_init",
|
||||
return_value=(Path("/egress_ca"), Path("/egress_cert")),
|
||||
), \
|
||||
mock.patch.object(
|
||||
launch_mod.network_mod, "network_name_for_slug",
|
||||
return_value="bb-internal-test",
|
||||
), \
|
||||
mock.patch.object(
|
||||
launch_mod.network_mod, "network_egress_name_for_slug",
|
||||
return_value="bb-egress-test",
|
||||
), \
|
||||
mock.patch.object(
|
||||
launch_mod, "bottle_plan_to_compose",
|
||||
launch_mod, "consolidated_agent_compose",
|
||||
return_value={"services": {"agent": {}}},
|
||||
), \
|
||||
mock.patch.object(
|
||||
launch_mod, "write_compose_file",
|
||||
return_value=Path("/tmp/compose.yml"),
|
||||
launch_mod, "write_compose_file", return_value=Path("/tmp/compose.yml"),
|
||||
), \
|
||||
mock.patch.object(launch_mod, "compose_up"), \
|
||||
mock.patch.object(launch_mod, "compose_dump_logs"), \
|
||||
mock.patch.object(
|
||||
launch_mod, "compose_down",
|
||||
side_effect=RuntimeError("network remove failed"),
|
||||
side_effect=RuntimeError("compose down failed"),
|
||||
), \
|
||||
contextlib.redirect_stderr(buf):
|
||||
provision = mock.Mock(return_value=None)
|
||||
|
||||
@@ -46,7 +46,7 @@ def _addon() -> EgressAddon:
|
||||
"""Return a bare EgressAddon with LOG_FULL config and no routes file."""
|
||||
a: EgressAddon = EgressAddon.__new__(EgressAddon)
|
||||
a.config = Config(routes=(), log=LOG_FULL)
|
||||
a.safe_tokens = set()
|
||||
a._safe_tokens = {}
|
||||
a._supervise_slug = ""
|
||||
a._token_allow_timeout = 300.0
|
||||
return a
|
||||
|
||||
@@ -211,7 +211,7 @@ def _addon(config: Config) -> EgressAddon:
|
||||
"""Bare EgressAddon with a supplied config and no supervise wiring."""
|
||||
a: EgressAddon = EgressAddon.__new__(EgressAddon)
|
||||
a.config = config
|
||||
a.safe_tokens = set()
|
||||
a._safe_tokens = {}
|
||||
a._supervise_slug = ""
|
||||
a._token_allow_timeout = 300.0
|
||||
a.routes_path = "/nonexistent/routes.yaml"
|
||||
@@ -222,6 +222,29 @@ def _run_request(addon: EgressAddon, flow: _Flow) -> None:
|
||||
asyncio.run(addon.request(flow)) # type: ignore[arg-type]
|
||||
|
||||
|
||||
def _with_client_ip(flow: _Flow, ip: str) -> _Flow:
|
||||
"""Attach a mitmproxy-style client_conn so consolidated resolution can read
|
||||
the source IP (`flow.client_conn.peername[0]`)."""
|
||||
flow.client_conn = types.SimpleNamespace(peername=(ip, 54321)) # type: ignore[attr-defined]
|
||||
return flow
|
||||
|
||||
|
||||
class _CtxResolver:
|
||||
"""Fake orchestrator resolver: maps source IP -> bottle id, and grants the
|
||||
same allow-list to any attributed bottle (unattributed -> deny)."""
|
||||
|
||||
def __init__(self, ip_to_bottle: dict[str, str]) -> None:
|
||||
self._map = ip_to_bottle
|
||||
|
||||
def resolve_policy_and_bottle_id(
|
||||
self, source_ip: str, identity_token: str = "",
|
||||
) -> tuple[str | None, str | None]:
|
||||
del identity_token
|
||||
bottle_id = self._map.get(source_ip)
|
||||
policy = "routes:\n - host: api.example.com\n" if bottle_id else None
|
||||
return policy, bottle_id
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Introspection endpoint
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -418,7 +441,8 @@ class TestSuperviseBranch(unittest.TestCase):
|
||||
with patch.object(_ea_mod, "_sv", _fake_sv("approved")):
|
||||
_run_request(addon, flow)
|
||||
self.assertIsNone(flow.response) # forwarded after approval
|
||||
self.assertIn(_OPENAI_KEY, addon.safe_tokens)
|
||||
# Approval lands in the calling bottle's safelist (keyed by slug).
|
||||
self.assertIn(_OPENAI_KEY, addon._safe_tokens_for("test-bottle"))
|
||||
|
||||
def test_operator_rejection_blocks(self) -> None:
|
||||
addon = self._supervised_addon()
|
||||
@@ -735,5 +759,62 @@ class TestLogFullRequest(unittest.TestCase):
|
||||
self.assertTrue(any(e.get("event") == "egress_request" for e in logged))
|
||||
|
||||
|
||||
class TestSuperviseMultiTenant(unittest.TestCase):
|
||||
"""Consolidated gateway: supervise proposals + the DLP safelist are keyed
|
||||
per bottle, resolved by source IP (PRD 0070)."""
|
||||
|
||||
def _consolidated_addon(self) -> EgressAddon:
|
||||
# Static config is empty; the resolver supplies each bottle's config.
|
||||
addon = _addon(Config(routes=()))
|
||||
addon._resolver = cast(Any, _CtxResolver({"10.0.0.1": "bottle-a", "10.0.0.2": "bottle-b"}))
|
||||
addon._token_allow_timeout = 0.05
|
||||
return addon
|
||||
|
||||
def test_approval_is_scoped_to_the_calling_bottle(self) -> None:
|
||||
addon = self._consolidated_addon()
|
||||
# bottle-a (10.0.0.1) sends the token; the operator approves.
|
||||
flow = _with_client_ip(
|
||||
_Flow(_Request(host="api.example.com", method="POST", body=f"k={_OPENAI_KEY}")),
|
||||
"10.0.0.1",
|
||||
)
|
||||
with patch.object(_ea_mod, "_sv", _fake_sv("approved")):
|
||||
_run_request(addon, flow)
|
||||
self.assertIsNone(flow.response) # forwarded after approval
|
||||
# The approval lands ONLY in bottle-a's safelist — never bottle-b's.
|
||||
# A global set here would be the cross-tenant leak this slice closes.
|
||||
self.assertIn(_OPENAI_KEY, addon._safe_tokens_for("bottle-a"))
|
||||
self.assertNotIn(_OPENAI_KEY, addon._safe_tokens_for("bottle-b"))
|
||||
|
||||
def test_proposal_is_attributed_to_the_source_ip_bottle(self) -> None:
|
||||
addon = self._consolidated_addon()
|
||||
seen: list[str] = []
|
||||
fake = _fake_sv("approved")
|
||||
|
||||
def _capture(**kw: Any) -> Any:
|
||||
seen.append(kw["bottle_slug"])
|
||||
return types.SimpleNamespace(id="p")
|
||||
|
||||
fake.Proposal = types.SimpleNamespace(new=_capture)
|
||||
flow = _with_client_ip(
|
||||
_Flow(_Request(host="api.example.com", method="POST", body=f"k={_OPENAI_KEY}")),
|
||||
"10.0.0.2",
|
||||
)
|
||||
with patch.object(_ea_mod, "_sv", fake):
|
||||
_run_request(addon, flow)
|
||||
self.assertEqual(["bottle-b"], seen) # proposal keyed by the resolved bottle
|
||||
|
||||
def test_unattributed_source_ip_cannot_supervise(self) -> None:
|
||||
addon = self._consolidated_addon()
|
||||
# 10.9.9.9 is not in the resolver map -> deny-all config, empty slug.
|
||||
flow = _with_client_ip(
|
||||
_Flow(_Request(host="api.example.com", method="POST", body=f"k={_OPENAI_KEY}")),
|
||||
"10.9.9.9",
|
||||
)
|
||||
with patch.object(_ea_mod, "_sv", _fake_sv("approved")):
|
||||
_run_request(addon, flow)
|
||||
self.assertIsNotNone(flow.response) # blocked (no route, no supervise)
|
||||
self.assertNotIn(_OPENAI_KEY, addon._safe_tokens_for(""))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
||||
@@ -1,10 +1,10 @@
|
||||
"""Unit: resolve_client_config — fail-closed per-client egress config (PRD 0070)."""
|
||||
"""Unit: fail-closed per-client egress resolution — config + context (PRD 0070)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import unittest
|
||||
|
||||
from bot_bottle.egress_addon_core import resolve_client_config
|
||||
from bot_bottle.egress_addon_core import resolve_client_config, resolve_client_context
|
||||
from bot_bottle.policy_resolver import PolicyResolveError
|
||||
|
||||
|
||||
@@ -49,5 +49,52 @@ class TestResolveClientConfig(unittest.TestCase):
|
||||
self.assertEqual(("10.243.0.1", "tok"), r.calls[0])
|
||||
|
||||
|
||||
class _FakeContextResolver:
|
||||
def __init__(
|
||||
self, policy: str | None = None, bottle_id: str | None = None, raises: bool = False,
|
||||
) -> None:
|
||||
self._policy = policy
|
||||
self._bottle_id = bottle_id
|
||||
self._raises = raises
|
||||
|
||||
def resolve_policy_and_bottle_id(
|
||||
self, source_ip: str, identity_token: str = "",
|
||||
) -> tuple[str | None, str | None]:
|
||||
if self._raises:
|
||||
raise PolicyResolveError("orchestrator down")
|
||||
return self._policy, self._bottle_id
|
||||
|
||||
|
||||
class TestResolveClientContext(unittest.TestCase):
|
||||
def test_returns_config_and_bottle_id(self) -> None:
|
||||
cfg, slug = resolve_client_context(
|
||||
_FakeContextResolver(policy="routes:\n - host: example.com\n", bottle_id="b1"),
|
||||
"10.243.0.1",
|
||||
)
|
||||
self.assertEqual(("example.com",), tuple(r.host for r in cfg.routes))
|
||||
self.assertEqual("b1", slug)
|
||||
|
||||
def test_unattributed_denies_and_empty_slug(self) -> None:
|
||||
cfg, slug = resolve_client_context(
|
||||
_FakeContextResolver(policy=None, bottle_id=None), "10.243.0.9",
|
||||
)
|
||||
self.assertEqual((), cfg.routes)
|
||||
self.assertEqual("", slug) # no bottle → supervise unavailable
|
||||
|
||||
def test_resolver_error_denies_and_empty_slug(self) -> None:
|
||||
cfg, slug = resolve_client_context(_FakeContextResolver(raises=True), "10.243.0.1")
|
||||
self.assertEqual((), cfg.routes)
|
||||
self.assertEqual("", slug)
|
||||
|
||||
def test_unparseable_policy_denies_but_keeps_slug(self) -> None:
|
||||
# A bad policy denies egress, but the bottle is still attributed (its
|
||||
# supervise queue is keyed by the id, independent of route parsing).
|
||||
cfg, slug = resolve_client_context(
|
||||
_FakeContextResolver(policy="routes: notalist\n", bottle_id="b2"), "10.243.0.1",
|
||||
)
|
||||
self.assertEqual((), cfg.routes)
|
||||
self.assertEqual("b2", slug)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
||||
@@ -0,0 +1,42 @@
|
||||
"""Unit: shared-gateway source-IP allocation (PRD 0070)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import unittest
|
||||
|
||||
from bot_bottle.backend.docker.gateway_net import NoFreeAddressError, next_free_ip
|
||||
|
||||
|
||||
class TestNextFreeIp(unittest.TestCase):
|
||||
def test_skips_router_and_returns_first_host(self) -> None:
|
||||
# .1 is docker's router; the first assignable address is .2.
|
||||
self.assertEqual("172.18.0.2", next_free_ip("172.18.0.0/16", []))
|
||||
|
||||
def test_skips_taken_addresses(self) -> None:
|
||||
# Gateway container holds .2, a live bottle holds .3 -> next is .4.
|
||||
self.assertEqual(
|
||||
"172.18.0.4", next_free_ip("172.18.0.0/16", ["172.18.0.2", "172.18.0.3"]),
|
||||
)
|
||||
|
||||
def test_taken_order_does_not_matter(self) -> None:
|
||||
self.assertEqual(
|
||||
"172.18.0.2", next_free_ip("172.18.0.0/16", ["172.18.0.3", "172.18.0.5"]),
|
||||
)
|
||||
|
||||
def test_allocation_is_deterministic(self) -> None:
|
||||
taken = ["172.18.0.2"]
|
||||
self.assertEqual(next_free_ip("172.18.0.0/16", taken),
|
||||
next_free_ip("172.18.0.0/16", taken))
|
||||
|
||||
def test_raises_when_subnet_exhausted(self) -> None:
|
||||
# /30: hosts are .1 (router, reserved) and .2; taking .2 leaves none.
|
||||
with self.assertRaises(NoFreeAddressError):
|
||||
next_free_ip("10.9.9.0/30", ["10.9.9.2"])
|
||||
|
||||
def test_accepts_host_bits_set_cidr(self) -> None:
|
||||
# A container's inspected address arrives as e.g. 172.18.0.2/16.
|
||||
self.assertEqual("172.18.0.2", next_free_ip("172.18.0.5/16", []))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,113 @@
|
||||
"""Unit: git-gate provisioning into the running shared gateway (PRD 0070)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
from unittest.mock import Mock, patch
|
||||
|
||||
from bot_bottle.backend.docker.gateway_provision import (
|
||||
GatewayProvisionError,
|
||||
deprovision_git_gate,
|
||||
provision_git_gate,
|
||||
)
|
||||
from bot_bottle.git_gate import GitGatePlan, GitGateUpstream
|
||||
|
||||
_RUN = "bot_bottle.backend.docker.gateway_provision.run_docker"
|
||||
|
||||
|
||||
def _proc(returncode: int = 0, stderr: str = "") -> Mock:
|
||||
return Mock(returncode=returncode, stderr=stderr)
|
||||
|
||||
|
||||
def _recorder(calls: list[list[str]]):
|
||||
"""A run_docker side_effect that records argv and returns success."""
|
||||
def fake(argv: list[str]) -> Mock:
|
||||
calls.append(argv)
|
||||
return _proc()
|
||||
return fake
|
||||
|
||||
|
||||
def _plan(*upstreams: GitGateUpstream) -> GitGatePlan:
|
||||
return GitGatePlan(
|
||||
slug="demo",
|
||||
entrypoint_script=Path("/stage/entrypoint.sh"),
|
||||
hook_script=Path("/stage/pre-receive"),
|
||||
access_hook_script=Path("/stage/access-hook"),
|
||||
upstreams=tuple(upstreams),
|
||||
)
|
||||
|
||||
|
||||
def _up(name: str, *, key: str = "/host/keys/id", known_hosts: str = "") -> GitGateUpstream:
|
||||
return GitGateUpstream(
|
||||
name=name,
|
||||
upstream_url=f"ssh://git@github.com/x/{name}.git",
|
||||
upstream_host="github.com",
|
||||
upstream_port="22",
|
||||
identity_file=key,
|
||||
known_host_key="",
|
||||
known_hosts_file=Path(known_hosts) if known_hosts else Path(),
|
||||
)
|
||||
|
||||
|
||||
class TestProvisionGitGate(unittest.TestCase):
|
||||
def test_copies_creds_and_runs_namespaced_init(self) -> None:
|
||||
calls: list[list[str]] = []
|
||||
with patch(_RUN, side_effect=_recorder(calls)):
|
||||
provision_git_gate("gw", "bottle1", _plan(_up("foo", known_hosts="/host/kh")))
|
||||
|
||||
cps = [c for c in calls if c[:2] == ["docker", "cp"]]
|
||||
self.assertIn(["docker", "cp", "/host/keys/id", "gw:/git-gate/creds/bottle1/foo-key"], cps)
|
||||
self.assertIn(
|
||||
["docker", "cp", "/host/kh", "gw:/git-gate/creds/bottle1/foo-known_hosts"], cps,
|
||||
)
|
||||
# The shared (bottle-agnostic) hooks are installed into the gateway.
|
||||
self.assertIn(["docker", "cp", "/stage/pre-receive", "gw:/etc/git-gate/pre-receive"], cps)
|
||||
# The init script runs in the gateway, namespaced under the bottle id.
|
||||
exec_scripts = [c for c in calls if c[:3] == ["docker", "exec", "gw"] and c[3] == "sh"]
|
||||
self.assertEqual(1, len(exec_scripts))
|
||||
self.assertIn("repo=/git/bottle1/${name}.git", exec_scripts[0][-1])
|
||||
|
||||
def test_omits_known_hosts_copy_when_absent(self) -> None:
|
||||
calls: list[list[str]] = []
|
||||
with patch(_RUN, side_effect=_recorder(calls)):
|
||||
provision_git_gate("gw", "b1", _plan(_up("foo"))) # no known_hosts
|
||||
creds_cps = [c for c in calls if c[:2] == ["docker", "cp"] and "/git-gate/creds/" in c[3]]
|
||||
self.assertEqual(1, len(creds_cps)) # only the key, not known_hosts
|
||||
self.assertTrue(creds_cps[0][3].endswith("/foo-key"))
|
||||
|
||||
def test_no_upstreams_is_noop(self) -> None:
|
||||
with patch(_RUN) as m:
|
||||
provision_git_gate("gw", "b1", _plan())
|
||||
m.assert_not_called()
|
||||
|
||||
def test_raises_on_docker_failure(self) -> None:
|
||||
with patch(_RUN, return_value=_proc(returncode=1, stderr="boom")):
|
||||
with self.assertRaises(GatewayProvisionError):
|
||||
provision_git_gate("gw", "b1", _plan(_up("foo")))
|
||||
|
||||
def test_rejects_unsafe_bottle_id_before_any_docker(self) -> None:
|
||||
with patch(_RUN) as m:
|
||||
with self.assertRaises(GatewayProvisionError):
|
||||
provision_git_gate("gw", "../etc", _plan(_up("foo")))
|
||||
m.assert_not_called() # rejected before a single docker call
|
||||
|
||||
|
||||
class TestDeprovision(unittest.TestCase):
|
||||
def test_removes_repo_and_creds(self) -> None:
|
||||
with patch(_RUN, return_value=_proc()) as m:
|
||||
deprovision_git_gate("gw", "b1")
|
||||
argv = m.call_args.args[0]
|
||||
self.assertEqual(["docker", "exec", "gw", "rm", "-rf"], argv[:5])
|
||||
self.assertIn("/git/b1", argv)
|
||||
self.assertIn("/git-gate/creds/b1", argv)
|
||||
|
||||
def test_rejects_unsafe_bottle_id(self) -> None:
|
||||
with patch(_RUN) as m:
|
||||
with self.assertRaises(GatewayProvisionError):
|
||||
deprovision_git_gate("gw", "a/b")
|
||||
m.assert_not_called()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,67 @@
|
||||
"""Unit: consolidated per-bottle git-gate provisioning render (PRD 0070)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import unittest
|
||||
|
||||
from bot_bottle.git_gate_render import (
|
||||
GitGateUpstream,
|
||||
git_gate_render_entrypoint,
|
||||
git_gate_render_provision,
|
||||
)
|
||||
|
||||
|
||||
def _ups(*names: str) -> tuple[GitGateUpstream, ...]:
|
||||
return tuple(
|
||||
GitGateUpstream(
|
||||
name=n,
|
||||
upstream_url=f"ssh://git@github.com/x/{n}.git",
|
||||
upstream_host="github.com",
|
||||
upstream_port="22",
|
||||
identity_file="",
|
||||
known_host_key="",
|
||||
)
|
||||
for n in names
|
||||
)
|
||||
|
||||
|
||||
class TestProvisionRender(unittest.TestCase):
|
||||
def test_namespaces_repos_and_creds_by_bottle_id(self) -> None:
|
||||
script = git_gate_render_provision("bottleab12", _ups("foo"))
|
||||
self.assertIn("repo=/git/bottleab12/${name}.git", script)
|
||||
self.assertIn("keyfile=/git-gate/creds/bottleab12/${name}-key", script)
|
||||
self.assertIn("mkdir -p /git/bottleab12", script)
|
||||
|
||||
def test_one_init_repo_call_per_upstream(self) -> None:
|
||||
script = git_gate_render_provision("b1", _ups("foo", "bar"))
|
||||
calls = [l for l in script.splitlines() if l.startswith("init_repo ")]
|
||||
self.assertEqual(2, len(calls))
|
||||
|
||||
def test_provision_does_not_start_the_daemon(self) -> None:
|
||||
# The shared gateway already serves; provisioning is init-only.
|
||||
self.assertNotIn("git daemon", git_gate_render_provision("b1", _ups("foo")))
|
||||
|
||||
def test_installs_pre_receive_hook(self) -> None:
|
||||
script = git_gate_render_provision("b1", _ups("foo"))
|
||||
self.assertIn("install -m 755 /etc/git-gate/pre-receive", script)
|
||||
|
||||
def test_rejects_unsafe_bottle_id(self) -> None:
|
||||
for bad in ("../etc", "a/b", "a b", "a;rm", ""):
|
||||
with self.assertRaises(ValueError):
|
||||
git_gate_render_provision(bad, _ups("foo"))
|
||||
|
||||
|
||||
class TestEntrypointUnchanged(unittest.TestCase):
|
||||
"""The shared `_git_gate_init_repo_fn` refactor must not alter the
|
||||
single-tenant daemon entrypoint's output."""
|
||||
|
||||
def test_entrypoint_still_single_tenant_flat(self) -> None:
|
||||
script = git_gate_render_entrypoint(_ups("foo"))
|
||||
self.assertIn("repo=/git/${name}.git", script) # flat, not namespaced
|
||||
self.assertIn("keyfile=/git-gate/creds/${name}-key", script)
|
||||
self.assertIn("--base-path=/git", script)
|
||||
self.assertIn("exec git daemon", script)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -13,6 +13,17 @@ from bot_bottle.git_gate import GIT_GATE_TIMEOUT_SECS
|
||||
from bot_bottle.git_http_backend import GitHttpHandler, MAX_BODY_BYTES
|
||||
|
||||
|
||||
class _FixedResolver:
|
||||
"""Maps every source IP to one bottle id (consolidated-mode stub)."""
|
||||
|
||||
def __init__(self, bottle_id: str) -> None:
|
||||
self._bottle_id = bottle_id
|
||||
|
||||
def resolve_bottle_id(self, source_ip: str, identity_token: str = "") -> str:
|
||||
del source_ip, identity_token
|
||||
return self._bottle_id
|
||||
|
||||
|
||||
class TestGitHttpBackend(unittest.TestCase):
|
||||
def test_real_git_push_reaches_bare_repo(self):
|
||||
from http.server import ThreadingHTTPServer
|
||||
@@ -94,6 +105,62 @@ class TestGitHttpBackend(unittest.TestCase):
|
||||
).strip()
|
||||
self.assertEqual(head, cloned)
|
||||
|
||||
def test_consolidated_push_stamps_bottle_slug_for_the_hook(self):
|
||||
# In consolidated mode the backend attributes the push by source IP and
|
||||
# stamps SUPERVISE_BOTTLE_SLUG=<bottle_id> into the CGI env, so the
|
||||
# gitleaks-allow pre-receive hook queues its proposal under the right
|
||||
# bottle. The hook here just records what it received.
|
||||
from http.server import ThreadingHTTPServer
|
||||
|
||||
bottle_id = "bottleab12"
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
root = Path(tmp)
|
||||
bare = root / bottle_id / "repo.git" # namespaced per bottle (slice 10)
|
||||
bare.parent.mkdir(parents=True)
|
||||
subprocess.run(["git", "init", "--bare", str(bare)],
|
||||
check=True, capture_output=True, text=True)
|
||||
subprocess.run(
|
||||
["git", "-C", str(bare), "config", "http.receivepack", "true"],
|
||||
check=True,
|
||||
)
|
||||
capture = root / "slug-capture"
|
||||
hook = bare / "hooks" / "pre-receive"
|
||||
hook.write_text(
|
||||
f"#!/bin/sh\nprintf '%s' \"${{SUPERVISE_BOTTLE_SLUG:-UNSET}}\" > "
|
||||
f"{capture}\ncat >/dev/null\nexit 0\n"
|
||||
)
|
||||
hook.chmod(0o755)
|
||||
|
||||
old_root = os.environ.get("GIT_PROJECT_ROOT")
|
||||
os.environ["GIT_PROJECT_ROOT"] = str(root) # base; backend nests per bottle
|
||||
self.addCleanup(self._restore_env, old_root)
|
||||
|
||||
server = ThreadingHTTPServer(("127.0.0.1", 0), GitHttpHandler)
|
||||
server.policy_resolver = _FixedResolver(bottle_id) # type: ignore[attr-defined]
|
||||
thread = threading.Thread(target=server.serve_forever, daemon=True)
|
||||
thread.start()
|
||||
self.addCleanup(server.shutdown)
|
||||
self.addCleanup(server.server_close)
|
||||
|
||||
work = root / "work"
|
||||
work.mkdir()
|
||||
subprocess.run(["git", "init"], cwd=work, check=True,
|
||||
capture_output=True, text=True)
|
||||
subprocess.run(["git", "config", "user.name", "test"], cwd=work, check=True)
|
||||
subprocess.run(["git", "config", "user.email", "t@example.invalid"],
|
||||
cwd=work, check=True)
|
||||
(work / "README.md").write_text("test\n")
|
||||
subprocess.run(["git", "add", "README.md"], cwd=work, check=True)
|
||||
subprocess.run(["git", "commit", "-m", "init"], cwd=work,
|
||||
check=True, capture_output=True, text=True)
|
||||
|
||||
url = f"http://127.0.0.1:{server.server_port}/repo.git"
|
||||
subprocess.run(
|
||||
["git", "push", url, "HEAD:refs/heads/main"],
|
||||
cwd=work, check=True, capture_output=True, text=True, timeout=5,
|
||||
)
|
||||
self.assertEqual(bottle_id, capture.read_text())
|
||||
|
||||
def test_post_forwards_git_cgi_headers(self):
|
||||
from http.server import ThreadingHTTPServer
|
||||
|
||||
|
||||
@@ -0,0 +1,65 @@
|
||||
"""Unit: resolve_sandbox_root — source-IP-keyed git-gate repo namespace (PRD 0070).
|
||||
|
||||
The consolidated git-http backend serves every bottle from one process and
|
||||
selects each request's repo root by the calling bottle's source IP. This is
|
||||
the fail-closed selection logic, tested without a live server.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
from bot_bottle.git_http_backend import resolve_sandbox_root
|
||||
from bot_bottle.policy_resolver import PolicyResolveError
|
||||
|
||||
_BASE = Path("/git")
|
||||
|
||||
|
||||
class _FakeResolver:
|
||||
def __init__(self, bottle_id: str | None = None, raises: bool = False) -> None:
|
||||
self._bottle_id = bottle_id
|
||||
self._raises = raises
|
||||
self.calls: list[tuple[str, str]] = []
|
||||
|
||||
def resolve_bottle_id(self, source_ip: str, identity_token: str = "") -> str | None:
|
||||
self.calls.append((source_ip, identity_token))
|
||||
if self._raises:
|
||||
raise PolicyResolveError("orchestrator down")
|
||||
return self._bottle_id
|
||||
|
||||
|
||||
class TestResolveRepoRoot(unittest.TestCase):
|
||||
def test_single_tenant_passthrough(self) -> None:
|
||||
# No resolver → the flat base root, unchanged (legacy per-bottle mode).
|
||||
self.assertEqual(_BASE, resolve_sandbox_root(None, _BASE, "10.243.0.1"))
|
||||
|
||||
def test_attributed_bottle_gets_namespaced_root(self) -> None:
|
||||
root = resolve_sandbox_root(_FakeResolver(bottle_id="ab12cd34"), _BASE, "10.243.0.1")
|
||||
self.assertEqual(Path("/git/ab12cd34"), root)
|
||||
|
||||
def test_unattributed_denies(self) -> None:
|
||||
self.assertIsNone(resolve_sandbox_root(_FakeResolver(bottle_id=None), _BASE, "10.243.0.9"))
|
||||
|
||||
def test_empty_bottle_id_denies(self) -> None:
|
||||
self.assertIsNone(resolve_sandbox_root(_FakeResolver(bottle_id=""), _BASE, "10.243.0.1"))
|
||||
|
||||
def test_resolver_error_denies(self) -> None:
|
||||
# Orchestrator unreachable/errored must never serve repos.
|
||||
self.assertIsNone(resolve_sandbox_root(_FakeResolver(raises=True), _BASE, "10.243.0.1"))
|
||||
|
||||
def test_namespace_escape_denies(self) -> None:
|
||||
# A bottle_id that would climb out of the root is rejected (defense in
|
||||
# depth — registry ids are token_hex, but never trust the namespace).
|
||||
self.assertIsNone(
|
||||
resolve_sandbox_root(_FakeResolver(bottle_id="../etc"), _BASE, "10.243.0.1")
|
||||
)
|
||||
|
||||
def test_forwards_source_ip_and_token(self) -> None:
|
||||
r = _FakeResolver(bottle_id="b1")
|
||||
resolve_sandbox_root(r, _BASE, "10.243.0.1", "tok")
|
||||
self.assertEqual(("10.243.0.1", "tok"), r.calls[0])
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,106 @@
|
||||
"""Unit: host-side orchestrator control-plane client (PRD 0070). HTTP mocked."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import unittest
|
||||
import urllib.error
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
from bot_bottle.orchestrator.client import (
|
||||
OrchestratorClient,
|
||||
OrchestratorClientError,
|
||||
RegisteredBottle,
|
||||
)
|
||||
|
||||
_URLOPEN = "bot_bottle.orchestrator.client.urllib.request.urlopen"
|
||||
|
||||
|
||||
def _resp(status: int, payload: object) -> MagicMock:
|
||||
m = MagicMock()
|
||||
inner = m.__enter__.return_value
|
||||
inner.status = status
|
||||
inner.read.return_value = json.dumps(payload).encode()
|
||||
return m
|
||||
|
||||
|
||||
def _http_error(code: int, payload: object = None) -> urllib.error.HTTPError:
|
||||
del payload # the client tolerates an empty error body; keep the signature
|
||||
return urllib.error.HTTPError("http://x", code, "err", {}, None) # type: ignore[arg-type]
|
||||
|
||||
|
||||
class TestRegister(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.c = OrchestratorClient("http://orch:8080")
|
||||
|
||||
def test_register_returns_id_and_token(self) -> None:
|
||||
with patch(_URLOPEN, return_value=_resp(201, {"bottle_id": "b1", "identity_token": "tok"})):
|
||||
got = self.c.register_bottle("10.0.0.2", policy="routes: []\n", metadata="{}")
|
||||
self.assertEqual(RegisteredBottle("b1", "tok"), got)
|
||||
|
||||
def test_register_posts_source_ip_and_policy(self) -> None:
|
||||
with patch(_URLOPEN, return_value=_resp(201, {"bottle_id": "b", "identity_token": "t"})) as m:
|
||||
self.c.register_bottle("10.0.0.9", policy="P", metadata="M", image_ref="img")
|
||||
sent = json.loads(m.call_args.args[0].data)
|
||||
self.assertEqual("10.0.0.9", sent["source_ip"])
|
||||
self.assertEqual("P", sent["policy"])
|
||||
self.assertEqual("img", sent["image_ref"])
|
||||
|
||||
def test_register_missing_fields_raises(self) -> None:
|
||||
with patch(_URLOPEN, return_value=_resp(201, {"bottle_id": "b1"})):
|
||||
with self.assertRaises(OrchestratorClientError):
|
||||
self.c.register_bottle("10.0.0.2")
|
||||
|
||||
def test_register_non_2xx_raises(self) -> None:
|
||||
with patch(_URLOPEN, side_effect=_http_error(400, {"error": "bad"})):
|
||||
with self.assertRaises(OrchestratorClientError):
|
||||
self.c.register_bottle("")
|
||||
|
||||
|
||||
class TestTeardown(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.c = OrchestratorClient("http://orch:8080")
|
||||
|
||||
def test_teardown_true_on_success(self) -> None:
|
||||
with patch(_URLOPEN, return_value=_resp(200, {"torn_down": True})):
|
||||
self.assertTrue(self.c.teardown_bottle("b1"))
|
||||
|
||||
def test_teardown_false_on_404(self) -> None:
|
||||
# Idempotent: an already-gone bottle is a clean no-op.
|
||||
with patch(_URLOPEN, side_effect=_http_error(404)):
|
||||
self.assertFalse(self.c.teardown_bottle("gone"))
|
||||
|
||||
def test_teardown_uses_delete(self) -> None:
|
||||
with patch(_URLOPEN, return_value=_resp(200, {"torn_down": True})) as m:
|
||||
self.c.teardown_bottle("b1")
|
||||
self.assertEqual("DELETE", m.call_args.args[0].get_method())
|
||||
|
||||
|
||||
class TestHealthAndPolicy(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.c = OrchestratorClient("http://orch:8080")
|
||||
|
||||
def test_health_true_on_200(self) -> None:
|
||||
with patch(_URLOPEN, return_value=_resp(200, {"status": "ok"})):
|
||||
self.assertTrue(self.c.health())
|
||||
|
||||
def test_health_false_when_unreachable(self) -> None:
|
||||
with patch(_URLOPEN, side_effect=urllib.error.URLError("refused")):
|
||||
self.assertFalse(self.c.health())
|
||||
|
||||
def test_set_policy_false_on_404(self) -> None:
|
||||
with patch(_URLOPEN, side_effect=_http_error(404)):
|
||||
self.assertFalse(self.c.set_policy("gone", "P"))
|
||||
|
||||
def test_set_policy_true_on_success(self) -> None:
|
||||
with patch(_URLOPEN, return_value=_resp(200, {"updated": True})):
|
||||
self.assertTrue(self.c.set_policy("b1", "P"))
|
||||
|
||||
def test_unreachable_raises(self) -> None:
|
||||
with patch(_URLOPEN, side_effect=urllib.error.URLError("refused")):
|
||||
with self.assertRaises(OrchestratorClientError):
|
||||
self.c.register_bottle("10.0.0.2")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -6,11 +6,15 @@ import unittest
|
||||
from unittest.mock import Mock, patch
|
||||
|
||||
from bot_bottle.orchestrator.gateway import (
|
||||
GATEWAY_CA_CERT,
|
||||
GATEWAY_NAME,
|
||||
DockerGateway,
|
||||
GatewayError,
|
||||
)
|
||||
|
||||
|
||||
_CA_PEM = "-----BEGIN CERTIFICATE-----\nMII...\n-----END CERTIFICATE-----\n"
|
||||
|
||||
_RUN_DOCKER = "bot_bottle.orchestrator.gateway.run_docker"
|
||||
|
||||
|
||||
@@ -51,6 +55,46 @@ class TestDockerGateway(unittest.TestCase):
|
||||
self.assertEqual(1, len(runs))
|
||||
self.assertIn(self.sc.name, runs[0])
|
||||
self.assertIn("bot-bottle-sidecars: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.
|
||||
self.assertTrue(any("mitmproxy" in a for a in runs[0]))
|
||||
|
||||
def test_ensure_running_creates_network_when_missing(self) -> None:
|
||||
calls: list[list[str]] = []
|
||||
|
||||
def fake(argv: list[str]) -> Mock:
|
||||
calls.append(argv)
|
||||
if argv[:3] == ["docker", "network", "inspect"]:
|
||||
return _proc(returncode=1, stderr="No such network")
|
||||
return _proc(stdout="") if argv[:2] == ["docker", "ps"] else _proc()
|
||||
|
||||
with patch(_RUN_DOCKER, side_effect=fake):
|
||||
self.sc.ensure_running()
|
||||
creates = [c for c in calls if c[:3] == ["docker", "network", "create"]]
|
||||
self.assertEqual([["docker", "network", "create", self.sc.network]], creates)
|
||||
|
||||
def test_ca_cert_pem_reads_from_container(self) -> None:
|
||||
with patch(_RUN_DOCKER, return_value=_proc(stdout=_CA_PEM)) as m:
|
||||
self.assertEqual(_CA_PEM, self.sc.ca_cert_pem())
|
||||
argv = m.call_args.args[0]
|
||||
self.assertEqual(["docker", "exec", self.sc.name, "cat", GATEWAY_CA_CERT], argv)
|
||||
|
||||
def test_ca_cert_pem_raises_when_absent(self) -> None:
|
||||
with patch(_RUN_DOCKER, return_value=_proc(returncode=1, stderr="No such file")):
|
||||
with self.assertRaises(GatewayError):
|
||||
self.sc.ca_cert_pem()
|
||||
|
||||
def test_ensure_running_reuses_existing_network(self) -> None:
|
||||
calls: list[list[str]] = []
|
||||
|
||||
def fake(argv: list[str]) -> Mock:
|
||||
calls.append(argv)
|
||||
return _proc(stdout="") if argv[:2] == ["docker", "ps"] else _proc()
|
||||
|
||||
with patch(_RUN_DOCKER, side_effect=fake):
|
||||
self.sc.ensure_running() # network inspect returns 0 → exists
|
||||
self.assertEqual([], [c for c in calls if c[:3] == ["docker", "network", "create"]])
|
||||
|
||||
def test_ensure_running_raises_on_docker_failure(self) -> None:
|
||||
def fake(argv: list[str]) -> Mock:
|
||||
@@ -85,28 +129,35 @@ class TestDockerGatewayBuild(unittest.TestCase):
|
||||
with patch(_RUN_DOCKER, return_value=_proc(returncode=1)):
|
||||
self.assertFalse(self.sc.image_exists())
|
||||
|
||||
def test_ensure_built_is_noop_when_image_present(self) -> None:
|
||||
with patch(_RUN_DOCKER, return_value=_proc(returncode=0)) as m:
|
||||
self.sc.ensure_built()
|
||||
self.assertEqual(1, m.call_count) # only the image-inspect probe
|
||||
|
||||
def test_ensure_built_builds_from_dockerfile_when_missing(self) -> None:
|
||||
def test_ensure_built_builds_even_when_image_present(self) -> None:
|
||||
# Always build (cache-aware) so a flat-source change rebuilds; the old
|
||||
# build-if-missing silently ran a stale single-tenant image.
|
||||
calls: list[list[str]] = []
|
||||
|
||||
def fake(argv: list[str]) -> Mock:
|
||||
def rec(argv: list[str]) -> Mock:
|
||||
calls.append(argv)
|
||||
if argv[:3] == ["docker", "image", "inspect"]:
|
||||
return _proc(returncode=1) # missing
|
||||
return _proc()
|
||||
return _proc() # image present, build succeeds
|
||||
|
||||
with patch(_RUN_DOCKER, side_effect=fake):
|
||||
with patch(_RUN_DOCKER, side_effect=rec):
|
||||
self.sc.ensure_built()
|
||||
|
||||
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.assertIn("-f", builds[0])
|
||||
self.assertTrue(any(a.endswith("Dockerfile.sidecars") for a in builds[0]))
|
||||
self.assertNotIn("--no-cache", builds[0])
|
||||
|
||||
def test_ensure_built_no_cache_env_forces_full_rebuild(self) -> None:
|
||||
calls: list[list[str]] = []
|
||||
|
||||
def rec(argv: list[str]) -> Mock:
|
||||
calls.append(argv)
|
||||
return _proc()
|
||||
|
||||
with patch(_RUN_DOCKER, side_effect=rec), \
|
||||
patch.dict("os.environ", {"BOT_BOTTLE_NO_CACHE": "1"}):
|
||||
self.sc.ensure_built()
|
||||
builds = [c for c in calls if c[:2] == ["docker", "build"]]
|
||||
self.assertIn("--no-cache", builds[0])
|
||||
|
||||
def test_ensure_built_noop_when_no_dockerfile(self) -> None:
|
||||
sc = DockerGateway("busybox", dockerfile=None)
|
||||
@@ -115,12 +166,7 @@ class TestDockerGatewayBuild(unittest.TestCase):
|
||||
m.assert_not_called()
|
||||
|
||||
def test_ensure_built_raises_on_build_failure(self) -> None:
|
||||
def fake(argv: list[str]) -> Mock:
|
||||
if argv[:3] == ["docker", "image", "inspect"]:
|
||||
return _proc(returncode=1)
|
||||
return _proc(returncode=1, stderr="build boom")
|
||||
|
||||
with patch(_RUN_DOCKER, side_effect=fake):
|
||||
with patch(_RUN_DOCKER, return_value=_proc(returncode=1, stderr="build boom")):
|
||||
with self.assertRaises(GatewayError):
|
||||
self.sc.ensure_built()
|
||||
|
||||
|
||||
@@ -0,0 +1,87 @@
|
||||
"""Unit: orchestrator+gateway container lifecycle — idempotent singleton (PRD 0070)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import tempfile
|
||||
import unittest
|
||||
import urllib.error
|
||||
from pathlib import Path
|
||||
from unittest.mock import MagicMock, Mock, patch
|
||||
|
||||
from bot_bottle.orchestrator.lifecycle import (
|
||||
ORCHESTRATOR_NAME,
|
||||
OrchestratorService,
|
||||
OrchestratorStartError,
|
||||
)
|
||||
from tests.unit import use_bottle_root
|
||||
|
||||
_URLOPEN = "bot_bottle.orchestrator.lifecycle.urllib.request.urlopen"
|
||||
_RUN = "bot_bottle.orchestrator.lifecycle.run_docker"
|
||||
_GATEWAY = "bot_bottle.orchestrator.lifecycle.DockerGateway"
|
||||
_SLEEP = "bot_bottle.orchestrator.lifecycle.time.sleep"
|
||||
_MONOTONIC = "bot_bottle.orchestrator.lifecycle.time.monotonic"
|
||||
|
||||
|
||||
def _health(status: int) -> MagicMock:
|
||||
m = MagicMock()
|
||||
m.__enter__.return_value.status = status
|
||||
return m
|
||||
|
||||
|
||||
class TestOrchestratorService(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self._tmp = tempfile.TemporaryDirectory()
|
||||
self.addCleanup(self._tmp.cleanup)
|
||||
self.addCleanup(use_bottle_root(Path(self._tmp.name)))
|
||||
self.svc = OrchestratorService(port=8099)
|
||||
|
||||
def test_urls(self) -> None:
|
||||
self.assertEqual("http://127.0.0.1:8099", self.svc.url)
|
||||
# The gateway reaches the control plane by container name over docker DNS.
|
||||
self.assertEqual(f"http://{ORCHESTRATOR_NAME}:8099", self.svc.internal_url)
|
||||
|
||||
def test_is_healthy(self) -> None:
|
||||
with patch(_URLOPEN, return_value=_health(200)):
|
||||
self.assertTrue(self.svc.is_healthy())
|
||||
with patch(_URLOPEN, side_effect=urllib.error.URLError("refused")):
|
||||
self.assertFalse(self.svc.is_healthy())
|
||||
|
||||
def test_ensure_running_healthy_still_ensures_gateway_but_not_orchestrator(self) -> None:
|
||||
with patch(_URLOPEN, return_value=_health(200)), \
|
||||
patch(_GATEWAY) as gw_cls, patch(_RUN) as run:
|
||||
self.assertEqual(self.svc.url, self.svc.ensure_running())
|
||||
gw = gw_cls.return_value
|
||||
gw.ensure_running.assert_called() # gateway kept up
|
||||
run.assert_not_called() # no orchestrator container run
|
||||
|
||||
def test_ensure_running_starts_orchestrator_container_when_absent(self) -> None:
|
||||
run = Mock(return_value=Mock(returncode=0, stderr=""))
|
||||
with patch(_URLOPEN, side_effect=[urllib.error.URLError("down"), _health(200)]), \
|
||||
patch(_GATEWAY), patch(_RUN, run), patch(_SLEEP):
|
||||
self.assertEqual(self.svc.url, self.svc.ensure_running())
|
||||
runs = [c.args[0] for c in run.call_args_list if c.args[0][:2] == ["docker", "run"]]
|
||||
self.assertEqual(1, len(runs))
|
||||
argv = runs[0]
|
||||
self.assertIn(ORCHESTRATOR_NAME, argv)
|
||||
self.assertIn("--broker", argv)
|
||||
self.assertEqual("stub", argv[argv.index("--broker") + 1]) # register-only, no socket
|
||||
self.assertIn("bot_bottle.orchestrator", argv)
|
||||
self.assertEqual("127.0.0.1:8099:8099", argv[argv.index("--publish") + 1])
|
||||
|
||||
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="")), \
|
||||
patch(_SLEEP), patch(_MONOTONIC, side_effect=[0.0, 0.5, 2.0]):
|
||||
with self.assertRaises(OrchestratorStartError):
|
||||
self.svc.ensure_running(startup_timeout=1.0)
|
||||
|
||||
def test_stop_removes_orchestrator_and_gateway(self) -> None:
|
||||
with patch(_RUN) as run, patch(_GATEWAY) as gw_cls:
|
||||
self.svc.stop()
|
||||
rms = [c.args[0] for c in run.call_args_list if c.args[0][:3] == ["docker", "rm", "--force"]]
|
||||
self.assertTrue(any(ORCHESTRATOR_NAME in a for a in rms))
|
||||
gw_cls.return_value.stop.assert_called_once()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,56 @@
|
||||
"""Unit: consolidated registration inputs — egress policy round-trip (PRD 0070)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
from bot_bottle.egress import EgressPlan, EgressRoute
|
||||
from bot_bottle.egress_addon_core import LOG_BLOCKS, load_config
|
||||
from bot_bottle.orchestrator.registration import (
|
||||
RegistrationInputs,
|
||||
egress_policy,
|
||||
registration_inputs,
|
||||
)
|
||||
|
||||
|
||||
def _plan(routes: tuple[EgressRoute, ...], *, slug: str = "demo", log: int = 0) -> EgressPlan:
|
||||
return EgressPlan(
|
||||
slug=slug,
|
||||
routes_path=Path("/unused/routes.yaml"),
|
||||
routes=routes,
|
||||
token_env_map={},
|
||||
log=log,
|
||||
)
|
||||
|
||||
|
||||
class TestEgressPolicy(unittest.TestCase):
|
||||
def test_policy_round_trips_through_load_config(self) -> None:
|
||||
# The policy the gateway serves must parse back to the same allow-list
|
||||
# the per-bottle sidecar applied — moving onto the shared gateway must
|
||||
# not change a bottle's egress.
|
||||
routes = (EgressRoute(host="api.example.com"), EgressRoute(host="pypi.org"))
|
||||
cfg = load_config(egress_policy(_plan(routes)))
|
||||
self.assertEqual(("api.example.com", "pypi.org"), tuple(r.host for r in cfg.routes))
|
||||
|
||||
def test_policy_preserves_log_level(self) -> None:
|
||||
plan = _plan((EgressRoute(host="x.example.com"),), log=LOG_BLOCKS)
|
||||
self.assertEqual(LOG_BLOCKS, load_config(egress_policy(plan)).log)
|
||||
|
||||
def test_empty_routes_yield_deny_all(self) -> None:
|
||||
cfg = load_config(egress_policy(_plan(())))
|
||||
self.assertEqual((), cfg.routes) # no routes → default-deny
|
||||
|
||||
|
||||
class TestRegistrationInputs(unittest.TestCase):
|
||||
def test_bundles_policy_and_slug_metadata(self) -> None:
|
||||
plan = _plan((EgressRoute(host="api.example.com"),), slug="my-bot")
|
||||
inputs = registration_inputs(plan)
|
||||
self.assertIsInstance(inputs, RegistrationInputs)
|
||||
self.assertEqual("my-bot", json.loads(inputs.metadata)["slug"])
|
||||
self.assertEqual(egress_policy(plan), inputs.policy) # same blob egress_policy renders
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -71,6 +71,37 @@ class TestPolicyResolver(unittest.TestCase):
|
||||
self.r.resolve("10.243.0.7") # token optional
|
||||
self.assertEqual("", json.loads(m.call_args.args[0].data)["identity_token"])
|
||||
|
||||
def test_resolve_bottle_id_returns_id(self) -> None:
|
||||
with patch(_URLOPEN, return_value=_resp({"bottle_id": "b1", "policy": "P"})):
|
||||
self.assertEqual("b1", self.r.resolve_bottle_id("10.243.0.1", "tok"))
|
||||
|
||||
def test_resolve_bottle_id_403_is_none_fail_closed(self) -> None:
|
||||
with patch(_URLOPEN, side_effect=_http_error(403)):
|
||||
self.assertIsNone(self.r.resolve_bottle_id("10.243.0.9", "tok"))
|
||||
|
||||
def test_resolve_bottle_id_missing_field_is_none(self) -> None:
|
||||
with patch(_URLOPEN, return_value=_resp({"policy": "P"})):
|
||||
self.assertIsNone(self.r.resolve_bottle_id("10.243.0.1", "tok"))
|
||||
|
||||
def test_resolve_bottle_id_error_raises(self) -> None:
|
||||
with patch(_URLOPEN, side_effect=_http_error(500)):
|
||||
with self.assertRaises(PolicyResolveError):
|
||||
self.r.resolve_bottle_id("10.243.0.1", "tok")
|
||||
|
||||
def test_resolve_policy_and_bottle_id_one_call(self) -> None:
|
||||
with patch(_URLOPEN, return_value=_resp({"bottle_id": "b1", "policy": "P"})) as m:
|
||||
self.assertEqual(("P", "b1"), self.r.resolve_policy_and_bottle_id("10.243.0.1", "t"))
|
||||
self.assertEqual(1, m.call_count) # both from a single /resolve
|
||||
|
||||
def test_resolve_policy_and_bottle_id_403_is_none_none(self) -> None:
|
||||
with patch(_URLOPEN, side_effect=_http_error(403)):
|
||||
self.assertEqual((None, None), self.r.resolve_policy_and_bottle_id("10.243.0.9"))
|
||||
|
||||
def test_resolve_policy_and_bottle_id_error_raises(self) -> None:
|
||||
with patch(_URLOPEN, side_effect=urllib.error.URLError("refused")):
|
||||
with self.assertRaises(PolicyResolveError):
|
||||
self.r.resolve_policy_and_bottle_id("10.243.0.1")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
||||
@@ -6,6 +6,7 @@ import sys
|
||||
import tempfile
|
||||
import threading
|
||||
import time
|
||||
import types
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
from unittest.mock import patch
|
||||
@@ -629,5 +630,57 @@ class TestHttpEndToEnd(unittest.TestCase):
|
||||
conn.close()
|
||||
|
||||
|
||||
class _FakeResolver:
|
||||
def __init__(self, bottle_id: str | None = None, raises: bool = False) -> None:
|
||||
self._bottle_id = bottle_id
|
||||
self._raises = raises
|
||||
self.calls: list[str] = []
|
||||
|
||||
def resolve_bottle_id(self, source_ip: str, identity_token: str = "") -> str | None:
|
||||
del identity_token
|
||||
self.calls.append(source_ip)
|
||||
if self._raises:
|
||||
# Raise the exact class supervise_server catches (it imports
|
||||
# policy_resolver flat inside the bundle, package-side in tests).
|
||||
raise supervise_server.PolicyResolveError("orchestrator down")
|
||||
return self._bottle_id
|
||||
|
||||
|
||||
def _handler(resolver: object) -> MCPHandler:
|
||||
"""A bare MCPHandler wired with a server (carrying the resolver) and a
|
||||
client address, enough to exercise `_attributed_config` off-socket."""
|
||||
h: MCPHandler = MCPHandler.__new__(MCPHandler)
|
||||
h.server = types.SimpleNamespace(policy_resolver=resolver) # type: ignore[assignment]
|
||||
h.client_address = ("10.0.0.7", 4321)
|
||||
return h
|
||||
|
||||
|
||||
class TestAttributedConfig(unittest.TestCase):
|
||||
"""Consolidated supervise: each proposal is attributed to the calling
|
||||
bottle by source IP; single-tenant keeps the env slug (PRD 0070)."""
|
||||
|
||||
def test_single_tenant_keeps_env_slug(self) -> None:
|
||||
cfg = _handler(None)._attributed_config(ServerConfig(bottle_slug="dev"))
|
||||
self.assertEqual("dev", cfg.bottle_slug)
|
||||
|
||||
def test_consolidated_binds_source_ip_bottle(self) -> None:
|
||||
r = _FakeResolver(bottle_id="bottle-x")
|
||||
cfg = _handler(r)._attributed_config(ServerConfig(bottle_slug="ignored"))
|
||||
self.assertEqual("bottle-x", cfg.bottle_slug) # resolved slug wins
|
||||
self.assertEqual(["10.0.0.7"], r.calls)
|
||||
|
||||
def test_unattributed_source_fails_closed(self) -> None:
|
||||
with self.assertRaises(_RpcInternalError):
|
||||
_handler(_FakeResolver(bottle_id=None))._attributed_config(
|
||||
ServerConfig(bottle_slug="x")
|
||||
)
|
||||
|
||||
def test_resolver_error_fails_closed(self) -> None:
|
||||
with self.assertRaises(_RpcInternalError):
|
||||
_handler(_FakeResolver(raises=True))._attributed_config(
|
||||
ServerConfig(bottle_slug="x")
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
||||
Reference in New Issue
Block a user