Compare commits
23 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 9896986810 | |||
| 20e83258bf | |||
| c5ba33bf0a | |||
| 72286f188d | |||
| 77aaabae63 | |||
| d0b35b5506 | |||
| ea0c070cfe | |||
| 24df322c31 | |||
| 80d75de08a | |||
| 8827c64a83 | |||
| 115a64c161 | |||
| 08aef30d87 | |||
| e0b0429cd1 | |||
| d3e08cf039 | |||
| de9da29027 | |||
| 72ea500342 | |||
| f754c575d7 | |||
| a092d00312 | |||
| 67652899eb | |||
| f85cbdeebf | |||
| 44e611d14e | |||
| 4fb0f64249 | |||
| 9226d45041 |
@@ -64,6 +64,7 @@ COPY --from=gitleaks-src /usr/bin/gitleaks /usr/bin/gitleaks
|
||||
COPY bot_bottle/egress_addon_core.py /app/egress_addon_core.py
|
||||
COPY bot_bottle/egress_dlp_config.py /app/egress_dlp_config.py
|
||||
COPY bot_bottle/egress_addon.py /app/egress_addon.py
|
||||
COPY bot_bottle/policy_resolver.py /app/policy_resolver.py
|
||||
COPY bot_bottle/dlp_detectors.py /app/dlp_detectors.py
|
||||
COPY bot_bottle/yaml_subset.py /app/yaml_subset.py
|
||||
COPY bot_bottle/paths.py /app/paths.py
|
||||
|
||||
@@ -0,0 +1,145 @@
|
||||
"""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 OrchestratorProcess
|
||||
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 _taken_ips(client: OrchestratorClient, gateway_ip: str) -> list[str]:
|
||||
"""Every address already in use on the gateway network: the gateway
|
||||
container plus every live bottle the registry knows."""
|
||||
taken = [gateway_ip]
|
||||
for rec in client.list_bottles():
|
||||
src = rec.get("source_ip")
|
||||
if isinstance(src, str) and src:
|
||||
taken.append(src)
|
||||
return taken
|
||||
|
||||
|
||||
def launch_consolidated(
|
||||
egress_plan: EgressPlan,
|
||||
git_gate_plan: GitGatePlan,
|
||||
*,
|
||||
image_ref: str = "",
|
||||
process: OrchestratorProcess | 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."""
|
||||
process = process or OrchestratorProcess()
|
||||
url = process.ensure_running()
|
||||
client = OrchestratorClient(url)
|
||||
|
||||
cidr = _network_cidr(network)
|
||||
gateway_ip = _container_ip(gateway_name, network)
|
||||
source_ip = next_free_ip(cidr, _taken_ips(client, gateway_ip))
|
||||
|
||||
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 +1,94 @@
|
||||
"""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
|
||||
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"]
|
||||
@@ -0,0 +1,27 @@
|
||||
"""Lean, framework-free `docker` subprocess primitive.
|
||||
|
||||
Deliberately a top-level module with a single stdlib import so it can be
|
||||
reused from anywhere without cost. It is intentionally *not* placed in
|
||||
`backend.docker.util`: importing that module runs `backend/__init__.py`,
|
||||
which eagerly loads all three bottle backends (docker + firecracker +
|
||||
macos) plus the manifest/egress/git-gate/supervise framework — ~76 modules
|
||||
— which would drag the whole backend layer into the deliberately-lean
|
||||
orchestrator. This primitive stays free of that so both the orchestrator's
|
||||
docker components and (in time) `backend.docker.util` can share it."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import subprocess
|
||||
|
||||
|
||||
def run_docker(argv: list[str]) -> subprocess.CompletedProcess[str]:
|
||||
"""Run a `docker` command, capturing stdout/stderr as text. Never raises
|
||||
on a non-zero exit — callers inspect `returncode` / `stderr` so they can
|
||||
stay fail-closed or tolerate idempotent no-ops (e.g. removing an
|
||||
already-absent container)."""
|
||||
return subprocess.run(
|
||||
argv, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, check=False,
|
||||
)
|
||||
|
||||
|
||||
__all__ = ["run_docker"]
|
||||
+88
-25
@@ -1,4 +1,4 @@
|
||||
"""mitmproxy addon entrypoint for the egress sidecar (PRD 0017, PRD 0053).
|
||||
"""mitmproxy addon entrypoint for the egress gateway (PRD 0017, PRD 0053).
|
||||
|
||||
Loaded by `mitmdump -s /app/egress_addon.py` inside the
|
||||
egress container."""
|
||||
@@ -32,6 +32,7 @@ from egress_addon_core import ( # type: ignore[import-not-found] # pylint: dis
|
||||
is_git_push_request,
|
||||
load_config,
|
||||
match_route,
|
||||
resolve_client_context,
|
||||
outbound_scan_headers,
|
||||
route_to_yaml_dict,
|
||||
scan_inbound,
|
||||
@@ -51,11 +52,26 @@ try:
|
||||
except ImportError: # pragma: no cover - host-side path
|
||||
from bot_bottle import supervise as _sv # type: ignore[import-not-found]
|
||||
|
||||
try:
|
||||
from policy_resolver import PolicyResolver # type: ignore[import-not-found]
|
||||
except ImportError: # pragma: no cover - host-side path
|
||||
from bot_bottle.policy_resolver import PolicyResolver
|
||||
|
||||
|
||||
DEFAULT_ROUTES_PATH = "/etc/egress/routes.yaml"
|
||||
|
||||
INTROSPECT_HOST = "_egress.local"
|
||||
|
||||
# Consolidated (multi-tenant) mode: when this points at the per-host
|
||||
# orchestrator's control plane, the addon resolves each client's Config by
|
||||
# source IP per request instead of using a single static routes file. Unset
|
||||
# → legacy per-bottle single-tenant mode (unchanged).
|
||||
ORCHESTRATOR_URL_ENV = "BOT_BOTTLE_ORCHESTRATOR_URL"
|
||||
|
||||
# App-layer identity token (defense-in-depth over the source-IP invariant);
|
||||
# the agent injects it, the addon strips it so it never leaks upstream.
|
||||
IDENTITY_HEADER = "x-bot-bottle-identity"
|
||||
|
||||
# Seconds the egress proxy holds a token-blocked request open waiting for the
|
||||
# operator's supervisor decision (PRD 0062), overridable via env.
|
||||
DEFAULT_TOKEN_ALLOW_TIMEOUT_SECONDS = 300.0
|
||||
@@ -72,20 +88,40 @@ _TOKEN_ALLOW_JUSTIFICATION = (
|
||||
|
||||
|
||||
class EgressAddon:
|
||||
# Class default so addons built via __new__ (e.g. in tests) default to
|
||||
# single-tenant; __init__ sets the instance attribute for real runs.
|
||||
_resolver: "PolicyResolver | None" = None
|
||||
|
||||
def __init__(self) -> None:
|
||||
self.routes_path = os.environ.get("EGRESS_ROUTES", DEFAULT_ROUTES_PATH)
|
||||
self.config: Config = Config(routes=())
|
||||
# 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()
|
||||
# Consolidated mode: resolve per-client Config from the orchestrator.
|
||||
# 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), 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:
|
||||
@@ -194,6 +230,22 @@ class EgressAddon:
|
||||
+ "\n"
|
||||
)
|
||||
|
||||
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, 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_context(self._resolver, client_ip, token)
|
||||
|
||||
async def request(self, flow: http.HTTPFlow) -> None:
|
||||
request_path, _, query = flow.request.path.partition("?")
|
||||
|
||||
@@ -201,12 +253,14 @@ class EgressAddon:
|
||||
self._serve_introspection(flow, request_path)
|
||||
return
|
||||
|
||||
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(self.config.routes, flow.request.pretty_host)
|
||||
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.
|
||||
@@ -224,7 +278,7 @@ class EgressAddon:
|
||||
|
||||
if is_git_fetch_request(request_path, query):
|
||||
git_decision = decide_git_fetch(
|
||||
self.config.routes, flow.request.pretty_host,
|
||||
config.routes, flow.request.pretty_host,
|
||||
)
|
||||
if git_decision.action == "block":
|
||||
self._block(
|
||||
@@ -235,14 +289,14 @@ class EgressAddon:
|
||||
return
|
||||
|
||||
# Strip agent-set Authorization after DLP scan so smuggled tokens
|
||||
# are caught above; the route may inject sidecar-owned auth below.
|
||||
# are caught above; the route may inject gateway-owned auth below.
|
||||
flow.request.headers.pop("authorization", None)
|
||||
|
||||
# Build headers mapping for match evaluation
|
||||
req_headers = {k.lower(): v for k, v in flow.request.headers.items()}
|
||||
|
||||
decision = decide(
|
||||
self.config.routes,
|
||||
config.routes,
|
||||
flow.request.pretty_host,
|
||||
request_path,
|
||||
os.environ,
|
||||
@@ -257,7 +311,7 @@ class EgressAddon:
|
||||
if decision.inject_authorization is not None:
|
||||
flow.request.headers["authorization"] = decision.inject_authorization
|
||||
|
||||
if self.config.log >= LOG_FULL:
|
||||
if config.log >= LOG_FULL:
|
||||
self._log_request(flow)
|
||||
|
||||
def _block_dlp(self, flow: http.HTTPFlow, result: ScanResult) -> None:
|
||||
@@ -270,6 +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
|
||||
@@ -291,7 +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
|
||||
@@ -326,10 +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.
|
||||
@@ -372,12 +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),
|
||||
@@ -386,7 +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,
|
||||
@@ -409,13 +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",
|
||||
@@ -438,6 +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."""
|
||||
@@ -445,7 +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.
|
||||
@@ -499,6 +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
|
||||
@@ -509,7 +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")
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
Split out of `egress_addon.py` so the host's unit tests can
|
||||
exercise the parse + decision functions without depending on the
|
||||
`mitmproxy` package. The companion module wraps these with the
|
||||
`mitmproxy.http.HTTPFlow` API and is loaded inside the sidecar
|
||||
`mitmproxy.http.HTTPFlow` API and is loaded inside the gateway
|
||||
container.
|
||||
|
||||
Imports: stdlib + `yaml_subset` (which is itself stdlib-only and
|
||||
@@ -22,7 +22,7 @@ except ImportError: # pragma: no cover - host-side path
|
||||
from .yaml_subset import YamlSubsetError, parse_yaml_subset
|
||||
|
||||
# DLP detector-config parsing lives in a sibling module (also flat-bundled
|
||||
# into the sidecar — see Dockerfile.sidecars). Re-exported below so existing
|
||||
# into the gateway — see Dockerfile.sidecars). Re-exported below so existing
|
||||
# `from egress_addon_core import ON_MATCH_*` callers keep working.
|
||||
try:
|
||||
from egress_dlp_config import ( # type: ignore[import-not-found]
|
||||
@@ -120,7 +120,7 @@ class ScanResult:
|
||||
reason: str
|
||||
location: str = "" # where the match was found, e.g. "body", "authorization header"
|
||||
context: str = "" # surrounding text with the match replaced by REDACT
|
||||
# Raw substring the detector matched. Used inside the sidecar to key the
|
||||
# Raw substring the detector matched. Used inside the gateway to key the
|
||||
# supervisor-approved "safe tokens" set (PRD 0062); never logged or written
|
||||
# to a proposal file. Empty for structural detectors (CRLF) that carry no
|
||||
# safelist-able value.
|
||||
@@ -413,6 +413,67 @@ def load_config(text: str) -> "Config":
|
||||
return parse_config(payload)
|
||||
|
||||
|
||||
class PolicyResolverLike(typing.Protocol):
|
||||
"""The bit of `policy_resolver.PolicyResolver` this module needs — kept a
|
||||
Protocol so egress_addon_core stays free of that import."""
|
||||
|
||||
def resolve(self, source_ip: str, identity_token: str = ...) -> "str | None":
|
||||
...
|
||||
|
||||
|
||||
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":
|
||||
"""The calling client's egress Config, resolved from the orchestrator via
|
||||
`resolver` and parsed — **fail-closed**. An unattributed client (None), a
|
||||
resolver error, or an unparseable policy all yield a deny-all Config (no
|
||||
routes → every request blocked). A compromised, absent, or confused
|
||||
orchestrator must never *widen* a bottle's egress."""
|
||||
try:
|
||||
policy = resolver.resolve(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)
|
||||
|
||||
|
||||
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:
|
||||
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 "")
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Match evaluation
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -613,7 +674,7 @@ def outbound_scan_headers(
|
||||
) -> dict[str, str]:
|
||||
"""Return request headers that should be included in outbound DLP.
|
||||
|
||||
Routes that inject sidecar-owned auth always strip the agent's
|
||||
Routes that inject gateway-owned auth always strip the agent's
|
||||
Authorization header before forwarding. Scanning that header first
|
||||
creates false positives for provider clients that insist on sending
|
||||
their own bearer-shaped placeholder, while still not changing what
|
||||
@@ -664,7 +725,7 @@ def scan_outbound(
|
||||
crlf_text: str | None = None,
|
||||
) -> ScanResult | None:
|
||||
# Lazy import to avoid circular deps and keep dlp_detectors optional
|
||||
# at import time (the sidecar copies it flat alongside this file).
|
||||
# at import time (the gateway copies it flat alongside this file).
|
||||
try:
|
||||
from dlp_detectors import ( # type: ignore[import-not-found]
|
||||
scan_crlf_injection,
|
||||
@@ -804,6 +865,10 @@ __all__ = [
|
||||
"is_git_push_request",
|
||||
"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
|
||||
|
||||
@@ -1,29 +1,63 @@
|
||||
"""Per-host orchestrator service (PRD 0070).
|
||||
|
||||
A single persistent per-host service that will run the sidecar functions
|
||||
A single persistent per-host service that will run the gateway functions
|
||||
(egress / git-gate / supervise), coordinate with the console, and broker
|
||||
agent launches. This package is being built bottom-up, starting with the
|
||||
backend-neutral "consolidation core" that needs no VM packaging:
|
||||
|
||||
* `registry` — the SQLite runtime-state store + fail-closed
|
||||
attribution (source IP + per-bottle identity token).
|
||||
* `control_plane` — the HTTP control-plane RPC (register / deregister /
|
||||
list / attribute / health), with live reload.
|
||||
* `broker` — the signed, structured launch-request contract + a
|
||||
`LaunchBroker` (stub for the harness) that verifies
|
||||
provenance before acting.
|
||||
* `gateway` — the consolidated per-host gateway: a `Gateway`
|
||||
lifecycle contract (idempotent singleton) + a
|
||||
`DockerGateway` impl. One gateway shared by all
|
||||
bottles instead of one per bottle.
|
||||
* `service` — the `Orchestrator`: owns the registry, brokers the
|
||||
launch lifecycle (launch/teardown), manages the
|
||||
shared gateway, attributes.
|
||||
* `control_plane` — the HTTP control-plane RPC (launch / teardown /
|
||||
list / attribute / gateway / health).
|
||||
|
||||
Launch/teardown, the launch broker, and the actual egress/git/supervise
|
||||
data plane land in later slices once this core is proven (see the PRD's
|
||||
sequencing: plain-process dev-harness -> docker orchestrator -> firecracker).
|
||||
The actual backend-native launch (a real docker/firecracker broker) and
|
||||
the egress/git/supervise data plane land in later slices once this core is
|
||||
proven (see the PRD sequencing: plain-process dev-harness -> docker
|
||||
orchestrator -> firecracker).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from .registry import BottleRecord, RegistryStore, new_identity_token
|
||||
from .broker import (
|
||||
BrokerAuthError,
|
||||
LaunchBroker,
|
||||
LaunchRequest,
|
||||
StubBroker,
|
||||
sign_request,
|
||||
verify_request,
|
||||
)
|
||||
from .docker_broker import DockerBroker, DockerBrokerError
|
||||
from .gateway import DockerGateway, Gateway, GatewayError
|
||||
from .service import Orchestrator
|
||||
from .control_plane import ControlPlaneServer, dispatch, make_server
|
||||
|
||||
__all__ = [
|
||||
"BottleRecord",
|
||||
"RegistryStore",
|
||||
"new_identity_token",
|
||||
"BrokerAuthError",
|
||||
"LaunchBroker",
|
||||
"LaunchRequest",
|
||||
"StubBroker",
|
||||
"DockerBroker",
|
||||
"DockerBrokerError",
|
||||
"Gateway",
|
||||
"DockerGateway",
|
||||
"GatewayError",
|
||||
"sign_request",
|
||||
"verify_request",
|
||||
"Orchestrator",
|
||||
"ControlPlaneServer",
|
||||
"dispatch",
|
||||
"make_server",
|
||||
|
||||
@@ -12,11 +12,16 @@ container packaging. Wrapping this exact service in a backend-native unit
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import secrets
|
||||
from pathlib import Path
|
||||
|
||||
from .. import log
|
||||
from .broker import LaunchBroker, StubBroker
|
||||
from .control_plane import make_server
|
||||
from .docker_broker import DockerBroker
|
||||
from .registry import RegistryStore, default_db_path
|
||||
from .service import Orchestrator
|
||||
from .gateway import DockerGateway, Gateway
|
||||
|
||||
|
||||
def main(argv: list[str] | None = None) -> int:
|
||||
@@ -28,12 +33,34 @@ def main(argv: list[str] | None = None) -> int:
|
||||
"--db", type=Path, default=None,
|
||||
help=f"registry DB path (default: {default_db_path()})",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--broker", choices=("stub", "docker"), default="stub",
|
||||
help="launch broker: 'stub' records requests; 'docker' runs containers",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--gateway", action="store_true",
|
||||
help="run one consolidated per-host sidecar bundle (build-if-missing)",
|
||||
)
|
||||
args = parser.parse_args(argv)
|
||||
|
||||
registry = RegistryStore(args.db)
|
||||
registry.migrate()
|
||||
|
||||
server = make_server(registry, host=args.host, port=args.port)
|
||||
# An ephemeral signing secret ties the orchestrator (signer) to its
|
||||
# broker (verifier). 'stub' records launches instead of starting
|
||||
# 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
|
||||
orchestrator = Orchestrator(registry, broker, secret, gateway)
|
||||
|
||||
# One persistent per-host gateway, shared by every bottle: build the
|
||||
# bundle image if missing, then bring the singleton up (idempotent).
|
||||
if gateway is not None:
|
||||
orchestrator.ensure_gateway()
|
||||
log.info("consolidated gateway ensured", context={"name": gateway.name})
|
||||
|
||||
server = make_server(orchestrator, host=args.host, port=args.port)
|
||||
bound_host, bound_port = server.server_address[0], server.server_address[1]
|
||||
log.info(
|
||||
"orchestrator control plane listening",
|
||||
|
||||
@@ -0,0 +1,176 @@
|
||||
"""Launch broker contract (PRD 0070).
|
||||
|
||||
A VM/container can't spawn its own host-network siblings, so the
|
||||
orchestrator brokers agent launches through a small privileged component.
|
||||
The request it sends is:
|
||||
|
||||
* **structured** — static flags + ids only (bottle id, pool slot, a
|
||||
content-addressed image ref), never a free-form path or argv, so a
|
||||
request can't be coerced into launching an arbitrary payload; and
|
||||
* **signed** — wrapped as a compact JWS/JWT the broker verifies before
|
||||
acting, so a *compromised co-located component* (an agent-facing
|
||||
gateway, say) can't forge a launch. This is the concrete form of the
|
||||
"structured requests only" rule in the PRD security review.
|
||||
|
||||
Signing is **HS256** over a secret shared by the orchestrator (signer) and
|
||||
the broker (verifier) — appropriate here because both are trusted host
|
||||
components provisioned together; the secret is exactly what an
|
||||
agent-facing component does not have. (Stdlib only — the project takes no
|
||||
runtime deps; a cross-host deployment could swap in an asymmetric alg.)
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import abc
|
||||
import base64
|
||||
import hashlib
|
||||
import hmac
|
||||
import json
|
||||
import secrets
|
||||
import time
|
||||
from dataclasses import dataclass
|
||||
|
||||
_JWT_HEADER = {"alg": "HS256", "typ": "JWT"}
|
||||
_ALLOWED_OPS = ("launch", "teardown")
|
||||
|
||||
|
||||
class BrokerAuthError(Exception):
|
||||
"""A broker request failed provenance or schema verification —
|
||||
bad/absent signature, malformed token, or a payload that doesn't match
|
||||
the fixed launch-request shape. Fail-closed: the broker must not act."""
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class LaunchRequest:
|
||||
"""The structured, un-coercible launch/teardown request. Ids + flags
|
||||
only — `image_ref` is a content-addressed id, never a path/argv."""
|
||||
|
||||
op: str # one of _ALLOWED_OPS
|
||||
bottle_id: str
|
||||
source_ip: str = ""
|
||||
image_ref: str = ""
|
||||
slot: int | None = None
|
||||
|
||||
|
||||
# --- minimal JWS/JWT (HS256), stdlib only ----------------------------------
|
||||
|
||||
def _b64url(data: bytes) -> str:
|
||||
return base64.urlsafe_b64encode(data).rstrip(b"=").decode("ascii")
|
||||
|
||||
|
||||
def _b64url_decode(text: str) -> bytes:
|
||||
return base64.urlsafe_b64decode(text + "=" * (-len(text) % 4))
|
||||
|
||||
|
||||
def _mac(signing_input: str, secret: bytes) -> str:
|
||||
digest = hmac.new(secret, signing_input.encode("ascii"), hashlib.sha256).digest()
|
||||
return _b64url(digest)
|
||||
|
||||
|
||||
def sign_request(req: LaunchRequest, secret: bytes) -> str:
|
||||
"""Serialize `req` to signed-JWT form. Adds a per-signature `jti`
|
||||
(replay id) and `iat` (issued-at)."""
|
||||
claims: dict[str, object] = {
|
||||
"op": req.op,
|
||||
"bottle_id": req.bottle_id,
|
||||
"source_ip": req.source_ip,
|
||||
"image_ref": req.image_ref,
|
||||
"slot": req.slot,
|
||||
"jti": secrets.token_hex(8),
|
||||
"iat": int(time.time()),
|
||||
}
|
||||
header = _b64url(json.dumps(_JWT_HEADER, sort_keys=True, separators=(",", ":")).encode())
|
||||
payload = _b64url(json.dumps(claims, sort_keys=True, separators=(",", ":")).encode())
|
||||
signing_input = f"{header}.{payload}"
|
||||
return f"{signing_input}.{_mac(signing_input, secret)}"
|
||||
|
||||
|
||||
def verify_request(token: str, secret: bytes) -> LaunchRequest:
|
||||
"""Verify the signature and the request shape; return the parsed
|
||||
request. Raises `BrokerAuthError` on any failure (fail-closed)."""
|
||||
parts = token.split(".")
|
||||
if len(parts) != 3:
|
||||
raise BrokerAuthError("malformed token")
|
||||
header_b, payload_b, sig = parts
|
||||
if not hmac.compare_digest(_mac(f"{header_b}.{payload_b}", secret), sig):
|
||||
raise BrokerAuthError("bad signature")
|
||||
try:
|
||||
header = json.loads(_b64url_decode(header_b))
|
||||
claims = json.loads(_b64url_decode(payload_b))
|
||||
except (ValueError, json.JSONDecodeError) as e:
|
||||
raise BrokerAuthError("malformed token payload") from e
|
||||
if not isinstance(header, dict) or header.get("alg") != "HS256":
|
||||
raise BrokerAuthError("unexpected header/alg")
|
||||
if not isinstance(claims, dict):
|
||||
raise BrokerAuthError("claims are not an object")
|
||||
|
||||
op = claims.get("op")
|
||||
bottle_id = claims.get("bottle_id")
|
||||
source_ip = claims.get("source_ip", "")
|
||||
image_ref = claims.get("image_ref", "")
|
||||
slot = claims.get("slot")
|
||||
if (
|
||||
not isinstance(op, str) or op not in _ALLOWED_OPS
|
||||
or not isinstance(bottle_id, str) or not bottle_id
|
||||
or not isinstance(source_ip, str) or not isinstance(image_ref, str)
|
||||
or not (slot is None or isinstance(slot, int))
|
||||
):
|
||||
raise BrokerAuthError("request does not match the launch-request schema")
|
||||
return LaunchRequest(
|
||||
op=op, bottle_id=bottle_id, source_ip=source_ip, image_ref=image_ref, slot=slot
|
||||
)
|
||||
|
||||
|
||||
# --- the broker itself ------------------------------------------------------
|
||||
|
||||
class LaunchBroker(abc.ABC):
|
||||
"""Verifies a signed request came from the orchestrator, then performs
|
||||
the backend-native launch/teardown. Subclasses implement `_launch` /
|
||||
`_teardown`; verification is shared and fail-closed."""
|
||||
|
||||
def __init__(self, secret: bytes) -> None:
|
||||
self._secret = secret
|
||||
|
||||
def submit(self, token: str) -> LaunchRequest:
|
||||
"""Verify `token` and perform its op. Returns the verified request;
|
||||
raises `BrokerAuthError` if provenance/shape fails."""
|
||||
req = verify_request(token, self._secret)
|
||||
if req.op == "launch":
|
||||
self._launch(req)
|
||||
else:
|
||||
self._teardown(req)
|
||||
return req
|
||||
|
||||
@abc.abstractmethod
|
||||
def _launch(self, req: LaunchRequest) -> None:
|
||||
...
|
||||
|
||||
@abc.abstractmethod
|
||||
def _teardown(self, req: LaunchRequest) -> None:
|
||||
...
|
||||
|
||||
|
||||
class StubBroker(LaunchBroker):
|
||||
"""Dev-harness broker: records verified requests without launching
|
||||
anything. Exercises the full sign -> verify -> act contract in-process."""
|
||||
|
||||
def __init__(self, secret: bytes) -> None:
|
||||
super().__init__(secret)
|
||||
self.launched: list[LaunchRequest] = []
|
||||
self.torn_down: list[LaunchRequest] = []
|
||||
|
||||
def _launch(self, req: LaunchRequest) -> None:
|
||||
self.launched.append(req)
|
||||
|
||||
def _teardown(self, req: LaunchRequest) -> None:
|
||||
self.torn_down.append(req)
|
||||
|
||||
|
||||
__all__ = [
|
||||
"BrokerAuthError",
|
||||
"LaunchRequest",
|
||||
"LaunchBroker",
|
||||
"StubBroker",
|
||||
"sign_request",
|
||||
"verify_request",
|
||||
]
|
||||
@@ -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",
|
||||
]
|
||||
@@ -2,23 +2,30 @@
|
||||
|
||||
The backend-agnostic control-plane RPC (CLI / console -> orchestrator) over
|
||||
**HTTP** — the universal transport chosen in 0070 (works on every host; no
|
||||
vsock / unix-socket portability caveats). Endpoints mutate the live
|
||||
registry, so register/deregister are the *live-reload* path — no restart:
|
||||
vsock / unix-socket portability caveats):
|
||||
|
||||
GET /health -> 200 {"status": "ok"}
|
||||
GET /bottles -> 200 {"bottles": [ <redacted record>, ... ]}
|
||||
POST /bottles -> 201 {"bottle_id", "identity_token"}
|
||||
body: {"source_ip", ["bottle_id"], ["metadata"]}
|
||||
DELETE /bottles/<bottle_id> -> 200 {"deregistered": true} | 404
|
||||
POST /attribute -> 200 {"bottle_id"} | 403
|
||||
body: {"source_ip", "identity_token"}
|
||||
GET /health -> 200 {"status": "ok"}
|
||||
GET /gateway -> 200 {"configured", ["name","running"]}
|
||||
GET /bottles -> 200 {"bottles": [ <redacted record>, ...]}
|
||||
POST /bottles -> 201 {"bottle_id","identity_token"} (launch)
|
||||
body: {"source_ip", ["image_ref"],
|
||||
["metadata"], ["policy"]}
|
||||
PUT /bottles/<bottle_id>/policy -> 200 {"updated": true} | 404 (live reload)
|
||||
body: {"policy"}
|
||||
DELETE /bottles/<bottle_id> -> 200 {"torn_down": true} | 404 (teardown)
|
||||
POST /attribute -> 200 {"bottle_id"} | 403
|
||||
POST /resolve -> 200 {"bottle_id","policy"} | 403
|
||||
body: {"source_ip","identity_token"}
|
||||
|
||||
`POST /bottles` / `DELETE` drive the full launch lifecycle: they mint (or
|
||||
tear down) the bottle in the registry AND broker the backend-native launch
|
||||
via the orchestrator. Register/deregister without a launch are internal to
|
||||
`Orchestrator`, not exposed here.
|
||||
|
||||
Routing/handling is the pure function `dispatch()` so it is unit-testable
|
||||
without a socket; `Handler` / `ControlPlaneServer` / `make_server` are a
|
||||
thin stdlib adapter around it.
|
||||
|
||||
Note the listing redacts identity tokens — they are never returned except
|
||||
once, to the caller that registers the bottle.
|
||||
thin stdlib adapter around it. Listing redacts identity tokens — they are
|
||||
returned only once, to the caller that launches the bottle.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -30,7 +37,7 @@ import socketserver
|
||||
import typing
|
||||
from urllib.parse import urlsplit
|
||||
|
||||
from .registry import RegistryStore
|
||||
from .service import Orchestrator
|
||||
|
||||
# JSON body payload type (parsed request / rendered response).
|
||||
Json = dict[str, object]
|
||||
@@ -46,18 +53,21 @@ def _parse_json_object(body: bytes) -> Json:
|
||||
return obj
|
||||
|
||||
|
||||
def dispatch( # pylint: disable=too-many-return-statements
|
||||
registry: RegistryStore, method: str, path: str, body: bytes
|
||||
def dispatch( # pylint: disable=too-many-return-statements,too-many-branches
|
||||
orch: Orchestrator, method: str, path: str, body: bytes
|
||||
) -> tuple[int, Json]:
|
||||
"""Route one control-plane request to a (status, payload) pair. Pure —
|
||||
no I/O beyond the registry — so it is fully testable without a socket."""
|
||||
no I/O beyond the orchestrator — so it is fully testable without a socket."""
|
||||
route = urlsplit(path).path.rstrip("/") or "/"
|
||||
|
||||
if method == "GET" and route == "/health":
|
||||
return 200, {"status": "ok"}
|
||||
|
||||
if method == "GET" and route == "/gateway":
|
||||
return 200, orch.gateway_status()
|
||||
|
||||
if method == "GET" and route == "/bottles":
|
||||
return 200, {"bottles": [r.redacted() for r in registry.all()]}
|
||||
return 200, {"bottles": [r.redacted() for r in orch.registry.all()]}
|
||||
|
||||
if method == "POST" and route == "/bottles":
|
||||
try:
|
||||
@@ -67,19 +77,34 @@ def dispatch( # pylint: disable=too-many-return-statements
|
||||
source_ip = data.get("source_ip")
|
||||
if not isinstance(source_ip, str) or not source_ip:
|
||||
return 400, {"error": "source_ip (string) is required"}
|
||||
bottle_id = data.get("bottle_id")
|
||||
image_ref = data.get("image_ref")
|
||||
metadata = data.get("metadata")
|
||||
rec = registry.register(
|
||||
policy = data.get("policy")
|
||||
rec = orch.launch_bottle(
|
||||
source_ip,
|
||||
bottle_id=bottle_id if isinstance(bottle_id, str) else None,
|
||||
image_ref=image_ref if isinstance(image_ref, str) else "",
|
||||
metadata=metadata if isinstance(metadata, str) else "",
|
||||
policy=policy if isinstance(policy, str) else "",
|
||||
)
|
||||
return 201, {"bottle_id": rec.bottle_id, "identity_token": rec.identity_token}
|
||||
|
||||
if method == "PUT" and route.startswith("/bottles/") and route.endswith("/policy"):
|
||||
bottle_id = route[len("/bottles/"):-len("/policy")]
|
||||
try:
|
||||
data = _parse_json_object(body)
|
||||
except ValueError as e:
|
||||
return 400, {"error": f"invalid JSON: {e}"}
|
||||
policy = data.get("policy")
|
||||
if not isinstance(policy, str):
|
||||
return 400, {"error": "policy (string) is required"}
|
||||
if orch.set_policy(bottle_id, policy):
|
||||
return 200, {"updated": True}
|
||||
return 404, {"error": "no such bottle"}
|
||||
|
||||
if method == "DELETE" and route.startswith("/bottles/"):
|
||||
bottle_id = route[len("/bottles/"):]
|
||||
if registry.deregister(bottle_id):
|
||||
return 200, {"deregistered": True}
|
||||
if orch.teardown_bottle(bottle_id):
|
||||
return 200, {"torn_down": True}
|
||||
return 404, {"error": "no such bottle"}
|
||||
|
||||
if method == "POST" and route == "/attribute":
|
||||
@@ -91,11 +116,28 @@ def dispatch( # pylint: disable=too-many-return-statements
|
||||
token = data.get("identity_token")
|
||||
if not isinstance(source_ip, str) or not isinstance(token, str):
|
||||
return 400, {"error": "source_ip and identity_token (strings) required"}
|
||||
rec = registry.attribute(source_ip, token)
|
||||
rec = orch.attribute(source_ip, token)
|
||||
if rec is None:
|
||||
return 403, {"error": "unattributed"}
|
||||
return 200, {"bottle_id": rec.bottle_id}
|
||||
|
||||
if method == "POST" and route == "/resolve":
|
||||
# The per-request lookup the multi-tenant gateway makes: returns the
|
||||
# bottle's policy. identity_token is OPTIONAL — absent means resolve
|
||||
# by source IP alone (network-layer attribution).
|
||||
try:
|
||||
data = _parse_json_object(body)
|
||||
except ValueError as e:
|
||||
return 400, {"error": f"invalid JSON: {e}"}
|
||||
source_ip = data.get("source_ip")
|
||||
token = data.get("identity_token")
|
||||
if not isinstance(source_ip, str) or not source_ip:
|
||||
return 400, {"error": "source_ip (string) is required"}
|
||||
rec = orch.resolve(source_ip, token if isinstance(token, str) else "")
|
||||
if rec is None:
|
||||
return 403, {"error": "unattributed"}
|
||||
return 200, {"bottle_id": rec.bottle_id, "policy": rec.policy}
|
||||
|
||||
return 404, {"error": "not found"}
|
||||
|
||||
|
||||
@@ -114,7 +156,7 @@ class Handler(http.server.BaseHTTPRequestHandler):
|
||||
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.registry, method, self.path, body)
|
||||
status, payload = dispatch(server.orchestrator, method, self.path, body)
|
||||
data = json.dumps(payload).encode()
|
||||
self.send_response(status)
|
||||
self.send_header("Content-Type", "application/json")
|
||||
@@ -128,27 +170,30 @@ class Handler(http.server.BaseHTTPRequestHandler):
|
||||
def do_POST(self) -> None:
|
||||
self._serve("POST")
|
||||
|
||||
def do_PUT(self) -> None:
|
||||
self._serve("PUT")
|
||||
|
||||
def do_DELETE(self) -> None:
|
||||
self._serve("DELETE")
|
||||
|
||||
|
||||
class ControlPlaneServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
|
||||
"""Threading HTTP server that carries the registry for its handlers."""
|
||||
"""Threading HTTP server that carries the orchestrator for its handlers."""
|
||||
|
||||
daemon_threads = True
|
||||
allow_reuse_address = True
|
||||
|
||||
def __init__(self, address: tuple[str, int], registry: RegistryStore) -> None:
|
||||
self.registry = registry
|
||||
def __init__(self, address: tuple[str, int], orchestrator: Orchestrator) -> None:
|
||||
self.orchestrator = orchestrator
|
||||
super().__init__(address, Handler)
|
||||
|
||||
|
||||
def make_server(
|
||||
registry: RegistryStore, host: str = "127.0.0.1", port: int = 0
|
||||
orchestrator: Orchestrator, host: str = "127.0.0.1", port: int = 0
|
||||
) -> ControlPlaneServer:
|
||||
"""Build (but do not start) a control-plane server. `port=0` binds an
|
||||
ephemeral port — read `server.server_address` for the actual one."""
|
||||
return ControlPlaneServer((host, port), registry)
|
||||
return ControlPlaneServer((host, port), orchestrator)
|
||||
|
||||
|
||||
__all__ = ["dispatch", "Handler", "ControlPlaneServer", "make_server", "Json"]
|
||||
|
||||
@@ -0,0 +1,83 @@
|
||||
"""Docker launch broker (PRD 0070) — the first *real* LaunchBroker.
|
||||
|
||||
On a verified launch request it starts a Docker container; on teardown it
|
||||
removes it. This proves the orchestrator -> backend seam on the cheapest
|
||||
backend (the sidecar bundle is already containers). Only the request's
|
||||
static ids/flags reach `docker`, so nothing free-form crosses the boundary.
|
||||
|
||||
Slice 3 launches a single container from the request's `image_ref`, named
|
||||
after the bottle id and labelled for cleanup. Wiring the full agent +
|
||||
sidecar bundle (networks, mounts, the consolidated sidecar) is a later
|
||||
slice — this is the seam, not the finished launcher.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import subprocess
|
||||
|
||||
from ..docker_cmd import run_docker
|
||||
from .broker import LaunchBroker, LaunchRequest
|
||||
|
||||
CONTAINER_PREFIX = "bot-bottle-orch-"
|
||||
BOTTLE_ID_LABEL = "bot-bottle-bottle-id"
|
||||
|
||||
|
||||
class DockerBrokerError(Exception):
|
||||
"""A brokered docker launch/teardown failed (non-zero `docker` exit)."""
|
||||
|
||||
|
||||
def container_name(bottle_id: str) -> str:
|
||||
"""Deterministic container name for a bottle."""
|
||||
return f"{CONTAINER_PREFIX}{bottle_id}"
|
||||
|
||||
|
||||
def run_argv(req: LaunchRequest) -> list[str]:
|
||||
"""`docker run` argv for a launch request — built only from its static
|
||||
fields, so it can't be coerced into an arbitrary command."""
|
||||
return [
|
||||
"docker", "run", "--detach",
|
||||
"--name", container_name(req.bottle_id),
|
||||
"--label", f"{BOTTLE_ID_LABEL}={req.bottle_id}",
|
||||
req.image_ref,
|
||||
]
|
||||
|
||||
|
||||
def rm_argv(req: LaunchRequest) -> list[str]:
|
||||
"""`docker rm --force` argv to tear a bottle's container down."""
|
||||
return ["docker", "rm", "--force", container_name(req.bottle_id)]
|
||||
|
||||
|
||||
class DockerBroker(LaunchBroker):
|
||||
"""A `LaunchBroker` that runs / removes a Docker container per bottle.
|
||||
Provenance + schema verification are inherited from `LaunchBroker`."""
|
||||
|
||||
def _docker(self, argv: list[str]) -> subprocess.CompletedProcess[str]:
|
||||
return run_docker(argv)
|
||||
|
||||
def _launch(self, req: LaunchRequest) -> None:
|
||||
if not req.image_ref:
|
||||
raise DockerBrokerError(f"launch request for {req.bottle_id} has no image_ref")
|
||||
proc = self._docker(run_argv(req))
|
||||
if proc.returncode != 0:
|
||||
raise DockerBrokerError(
|
||||
f"docker run failed for {req.bottle_id}: {proc.stderr.strip()}"
|
||||
)
|
||||
|
||||
def _teardown(self, req: LaunchRequest) -> None:
|
||||
proc = self._docker(rm_argv(req))
|
||||
# Idempotent: an already-absent container is a successful teardown.
|
||||
if proc.returncode != 0 and "No such container" not in proc.stderr:
|
||||
raise DockerBrokerError(
|
||||
f"docker rm failed for {req.bottle_id}: {proc.stderr.strip()}"
|
||||
)
|
||||
|
||||
|
||||
__all__ = [
|
||||
"DockerBroker",
|
||||
"DockerBrokerError",
|
||||
"container_name",
|
||||
"run_argv",
|
||||
"rm_argv",
|
||||
"CONTAINER_PREFIX",
|
||||
"BOTTLE_ID_LABEL",
|
||||
]
|
||||
@@ -0,0 +1,160 @@
|
||||
"""The consolidated per-host gateway (PRD 0070).
|
||||
|
||||
The core consolidation win: **one** persistent gateway per host, shared by
|
||||
every bottle, instead of a sidecar bundle per bottle. It's safe to share
|
||||
because the attribution invariant (source IP + identity token, see
|
||||
`registry`) lets the gateway attribute each request to the right bottle —
|
||||
so per-bottle policy lives in one long-lived process keyed on who's calling.
|
||||
|
||||
`Gateway` is the backend-neutral lifecycle contract (mirrors `LaunchBroker`):
|
||||
ensure the single instance is up, report it, tear it down. `DockerGateway`
|
||||
is the docker implementation; a firecracker gateway VM slots in later.
|
||||
|
||||
The defining behaviour is **idempotent singleton**: `ensure_running` starts
|
||||
the instance if absent and is a no-op if it's already up, so N bottle
|
||||
launches never spawn N gateways.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import abc
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
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"
|
||||
|
||||
# The real sidecar-bundle image + its Dockerfile. Kept as a local constant
|
||||
# rather than imported from backend.docker.sidecar_bundle, which would drag
|
||||
# the whole backend layer into the lean orchestrator (see #359); unify when
|
||||
# that lands. Env override matches the backend's BOT_BOTTLE_SIDECAR_IMAGE.
|
||||
GATEWAY_IMAGE = os.environ.get("BOT_BOTTLE_SIDECAR_IMAGE", "bot-bottle-sidecars:latest")
|
||||
GATEWAY_DOCKERFILE = "Dockerfile.sidecars"
|
||||
_REPO_ROOT = Path(__file__).resolve().parents[2]
|
||||
|
||||
|
||||
class GatewayError(Exception):
|
||||
"""The shared gateway failed to build/start/stop (non-zero `docker` exit)."""
|
||||
|
||||
|
||||
class Gateway(abc.ABC):
|
||||
"""Lifecycle of the single per-host gateway. Backend-neutral."""
|
||||
|
||||
name: str
|
||||
|
||||
def ensure_built(self) -> None:
|
||||
"""Ensure the gateway's image / rootfs exists, building it if needed.
|
||||
Default: nothing to build (e.g. a stub or a pre-pulled image)."""
|
||||
return
|
||||
|
||||
@abc.abstractmethod
|
||||
def ensure_running(self) -> None:
|
||||
"""Start the gateway if it isn't already up. Idempotent: a no-op
|
||||
when it's already running (that's the whole point — one per host).
|
||||
Assumes the image exists — call `ensure_built()` first."""
|
||||
|
||||
@abc.abstractmethod
|
||||
def is_running(self) -> bool:
|
||||
"""True iff the gateway instance is currently up."""
|
||||
|
||||
@abc.abstractmethod
|
||||
def stop(self) -> None:
|
||||
"""Remove the gateway. Idempotent — absent is success."""
|
||||
|
||||
|
||||
class DockerGateway(Gateway):
|
||||
"""The consolidated gateway as a single, fixed-name Docker container.
|
||||
|
||||
`image_ref` defaults to the real sidecar-bundle image; `ensure_built`
|
||||
builds it from `Dockerfile.sidecars` when it's missing. (Note: slice 5
|
||||
builds + launches the bundle container; wiring its per-bottle,
|
||||
source-IP-keyed config is a later slice — see PRD 0070.)"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
image_ref: str = GATEWAY_IMAGE,
|
||||
*,
|
||||
name: str = GATEWAY_NAME,
|
||||
network: str = GATEWAY_NETWORK,
|
||||
build_context: Path | None = None,
|
||||
dockerfile: str | None = GATEWAY_DOCKERFILE,
|
||||
) -> None:
|
||||
self.image_ref = image_ref
|
||||
self.name = name
|
||||
self.network = network
|
||||
self._build_context = build_context or _REPO_ROOT
|
||||
self._dockerfile = dockerfile
|
||||
|
||||
def image_exists(self) -> bool:
|
||||
return run_docker(["docker", "image", "inspect", self.image_ref]).returncode == 0
|
||||
|
||||
def ensure_built(self) -> None:
|
||||
"""Build the bundle image from its Dockerfile 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():
|
||||
return
|
||||
proc = run_docker([
|
||||
"docker", "build",
|
||||
"-t", self.image_ref,
|
||||
"-f", str(self._build_context / self._dockerfile),
|
||||
str(self._build_context),
|
||||
])
|
||||
if proc.returncode != 0:
|
||||
raise GatewayError(f"gateway image build failed: {proc.stderr.strip()}")
|
||||
|
||||
def is_running(self) -> bool:
|
||||
proc = run_docker([
|
||||
"docker", "ps",
|
||||
"--filter", f"name=^{self.name}$",
|
||||
"--filter", "status=running",
|
||||
"--format", "{{.Names}}",
|
||||
])
|
||||
return self.name in proc.stdout.split()
|
||||
|
||||
def _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([
|
||||
"docker", "run", "--detach",
|
||||
"--name", self.name,
|
||||
"--label", GATEWAY_LABEL,
|
||||
"--network", self.network,
|
||||
self.image_ref,
|
||||
])
|
||||
if proc.returncode != 0:
|
||||
raise GatewayError(f"gateway failed to start: {proc.stderr.strip()}")
|
||||
|
||||
def stop(self) -> None:
|
||||
proc = run_docker(["docker", "rm", "--force", self.name])
|
||||
if proc.returncode != 0 and "No such container" not in proc.stderr:
|
||||
raise GatewayError(f"gateway failed to stop: {proc.stderr.strip()}")
|
||||
|
||||
|
||||
__all__ = [
|
||||
"Gateway", "DockerGateway", "GatewayError",
|
||||
"GATEWAY_NAME", "GATEWAY_LABEL", "GATEWAY_IMAGE", "GATEWAY_NETWORK",
|
||||
]
|
||||
@@ -0,0 +1,141 @@
|
||||
"""Orchestrator process lifecycle (PRD 0070, docker slice).
|
||||
|
||||
Before the CLI can register or launch bottles against the consolidated
|
||||
model, exactly one orchestrator control plane — and the single per-host
|
||||
gateway it manages — must be running. This starts the orchestrator
|
||||
dev-harness (`python -m bot_bottle.orchestrator`) as a background host
|
||||
process and health-checks it.
|
||||
|
||||
It is an **idempotent singleton**: `ensure_running` returns immediately if a
|
||||
healthy control plane already answers on the port, and otherwise spawns one
|
||||
and waits for it to come up. The control-plane port is the singleton key —
|
||||
a second orchestrator can't bind it, so a stray double-start fails fast
|
||||
rather than forking a rival.
|
||||
|
||||
Host-process (not container) on purpose: the PRD sequences the orchestrator
|
||||
as a plain-process dev-harness first (fast iteration, and it already has the
|
||||
host user's docker access to broker launches), while the data-plane
|
||||
*gateway* it manages runs as a container. Wrapping the orchestrator itself
|
||||
in a backend-native unit is a later step.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
|
||||
from .. import log
|
||||
from ..paths import bot_bottle_root
|
||||
|
||||
DEFAULT_HOST = "127.0.0.1"
|
||||
DEFAULT_PORT = 8080
|
||||
# Poll cadence + default ceiling while waiting for a freshly-spawned control
|
||||
# plane to answer /health (the first start also builds/boots the gateway).
|
||||
_HEALTH_POLL_SECONDS = 0.25
|
||||
DEFAULT_STARTUP_TIMEOUT_SECONDS = 45.0
|
||||
_HEALTH_REQUEST_TIMEOUT_SECONDS = 1.0
|
||||
|
||||
|
||||
class OrchestratorStartError(RuntimeError):
|
||||
"""The orchestrator process did not become healthy within the timeout."""
|
||||
|
||||
|
||||
class OrchestratorProcess:
|
||||
"""Manages the local orchestrator control-plane process for the docker
|
||||
backend. Backend-neutral callers only need `ensure_running()` + `url`."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
host: str = DEFAULT_HOST,
|
||||
port: int = DEFAULT_PORT,
|
||||
*,
|
||||
broker: str = "docker",
|
||||
gateway: bool = True,
|
||||
) -> None:
|
||||
self.host = host
|
||||
self.port = port
|
||||
self._broker = broker
|
||||
self._gateway = gateway
|
||||
|
||||
@property
|
||||
def url(self) -> str:
|
||||
"""The control-plane base URL — also what the data plane's
|
||||
BOT_BOTTLE_ORCHESTRATOR_URL points at."""
|
||||
return f"http://{self.host}:{self.port}"
|
||||
|
||||
def is_healthy(self, *, timeout: float = _HEALTH_REQUEST_TIMEOUT_SECONDS) -> bool:
|
||||
"""True iff a control plane answers `GET /health` with 200 — the
|
||||
singleton liveness check."""
|
||||
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 ensure_running(
|
||||
self, *, startup_timeout: float = DEFAULT_STARTUP_TIMEOUT_SECONDS,
|
||||
) -> str:
|
||||
"""Return the control-plane URL, starting the orchestrator first if it
|
||||
isn't already healthy. Idempotent — a healthy control plane is left
|
||||
untouched. Raises `OrchestratorStartError` if a freshly-spawned one
|
||||
doesn't answer within `startup_timeout`."""
|
||||
if self.is_healthy():
|
||||
return self.url
|
||||
log.info("starting orchestrator", context={"url": self.url, "broker": self._broker})
|
||||
self._spawn()
|
||||
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 "
|
||||
f"{startup_timeout:g}s"
|
||||
)
|
||||
|
||||
def _argv(self) -> list[str]:
|
||||
"""`python -m bot_bottle.orchestrator ...` — static flags only."""
|
||||
argv = [
|
||||
sys.executable, "-m", "bot_bottle.orchestrator",
|
||||
"--host", self.host, "--port", str(self.port),
|
||||
"--broker", self._broker,
|
||||
]
|
||||
if self._gateway:
|
||||
argv.append("--gateway")
|
||||
return argv
|
||||
|
||||
def _log_path(self) -> str:
|
||||
"""Where the detached orchestrator's stdout/stderr goes so a failed
|
||||
start is diagnosable after the CLI has moved on."""
|
||||
return str(bot_bottle_root() / "orchestrator.log")
|
||||
|
||||
def _spawn(self) -> None:
|
||||
"""Launch the orchestrator detached so it outlives this CLI process,
|
||||
with its output tee'd to a log file under the bot-bottle root."""
|
||||
root = bot_bottle_root()
|
||||
root.mkdir(parents=True, exist_ok=True)
|
||||
logfile = open(self._log_path(), "a", encoding="utf-8") # noqa: SIM115 # pylint: disable=consider-using-with
|
||||
try:
|
||||
subprocess.Popen( # noqa: S603 # pylint: disable=consider-using-with
|
||||
self._argv(),
|
||||
stdout=logfile,
|
||||
stderr=subprocess.STDOUT,
|
||||
stdin=subprocess.DEVNULL,
|
||||
start_new_session=True,
|
||||
)
|
||||
finally:
|
||||
# The child inherits its own dup'd fd; this handle is ours to drop.
|
||||
logfile.close()
|
||||
|
||||
|
||||
__all__ = [
|
||||
"OrchestratorProcess",
|
||||
"OrchestratorStartError",
|
||||
"DEFAULT_HOST",
|
||||
"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"]
|
||||
@@ -64,9 +64,13 @@ class BottleRecord:
|
||||
identity_token: str
|
||||
state: str = "active"
|
||||
created_at: float = 0.0
|
||||
# Opaque JSON blob for forward-compat (policy refs, pool slot, ...) —
|
||||
# the registry doesn't interpret it, so new fields need no migration.
|
||||
# Opaque JSON blob for forward-compat (pool slot, ...) — the registry
|
||||
# doesn't interpret it, so new fields need no migration.
|
||||
metadata: str = ""
|
||||
# The bottle's gateway policy (opaque JSON — egress allowlist / routes /
|
||||
# git config). The registry stores and serves it verbatim, keyed by
|
||||
# source IP; the multi-tenant gateway interprets it.
|
||||
policy: str = ""
|
||||
|
||||
def redacted(self) -> dict[str, object]:
|
||||
"""Public view for listing — never exposes the identity token."""
|
||||
@@ -76,6 +80,7 @@ class BottleRecord:
|
||||
"state": self.state,
|
||||
"created_at": self.created_at,
|
||||
"metadata": self.metadata,
|
||||
"policy": self.policy,
|
||||
}
|
||||
|
||||
|
||||
@@ -97,6 +102,10 @@ _MIGRATIONS = TableMigrations(
|
||||
# the "one active bottle per source IP" check cheap.
|
||||
"CREATE INDEX IF NOT EXISTS idx_orchestrator_bottles_source_ip "
|
||||
"ON orchestrator_bottles (source_ip)",
|
||||
# v3 — per-bottle policy (opaque JSON the gateway interprets): the
|
||||
# egress allowlist / routes / git config selected by source IP. The
|
||||
# multi-tenant gateway resolves it per request via `attribute`.
|
||||
"ALTER TABLE orchestrator_bottles ADD COLUMN policy TEXT NOT NULL DEFAULT ''",
|
||||
],
|
||||
)
|
||||
|
||||
@@ -110,6 +119,7 @@ def _row_to_record(row: sqlite3.Row) -> BottleRecord:
|
||||
state=row["state"],
|
||||
created_at=row["created_at"],
|
||||
metadata=row["metadata"],
|
||||
policy=row["policy"],
|
||||
)
|
||||
|
||||
|
||||
@@ -136,6 +146,7 @@ class RegistryStore(DbStore):
|
||||
bottle_id: str | None = None,
|
||||
identity_token: str | None = None,
|
||||
metadata: str = "",
|
||||
policy: str = "",
|
||||
) -> BottleRecord:
|
||||
"""Register (or replace) a bottle. Mints a bottle_id / identity token
|
||||
when not supplied. Live — this is the control-plane reload path."""
|
||||
@@ -146,12 +157,13 @@ class RegistryStore(DbStore):
|
||||
state="active",
|
||||
created_at=time.time(),
|
||||
metadata=metadata,
|
||||
policy=policy,
|
||||
)
|
||||
with self._connect() as conn:
|
||||
conn.execute(
|
||||
"INSERT OR REPLACE INTO orchestrator_bottles "
|
||||
"(bottle_id, source_ip, identity_token, state, created_at, metadata) "
|
||||
"VALUES (?, ?, ?, ?, ?, ?)",
|
||||
"(bottle_id, source_ip, identity_token, state, created_at, metadata, policy) "
|
||||
"VALUES (?, ?, ?, ?, ?, ?, ?)",
|
||||
(
|
||||
rec.bottle_id,
|
||||
rec.source_ip,
|
||||
@@ -159,11 +171,23 @@ class RegistryStore(DbStore):
|
||||
rec.state,
|
||||
rec.created_at,
|
||||
rec.metadata,
|
||||
rec.policy,
|
||||
),
|
||||
)
|
||||
self._chmod()
|
||||
return rec
|
||||
|
||||
def set_policy(self, bottle_id: str, policy: str) -> bool:
|
||||
"""Update a bottle's policy in place (live reload). Returns True if
|
||||
the bottle exists."""
|
||||
with self._connect() as conn:
|
||||
cur = conn.execute(
|
||||
"UPDATE orchestrator_bottles SET policy = ? WHERE bottle_id = ?",
|
||||
(policy, bottle_id),
|
||||
)
|
||||
self._chmod()
|
||||
return cur.rowcount > 0
|
||||
|
||||
def deregister(self, bottle_id: str) -> bool:
|
||||
"""Remove a bottle. Returns True if a row was deleted."""
|
||||
with self._connect() as conn:
|
||||
@@ -188,14 +212,13 @@ class RegistryStore(DbStore):
|
||||
).fetchall()
|
||||
return [_row_to_record(r) for r in rows]
|
||||
|
||||
def attribute(self, source_ip: str, identity_token: str) -> BottleRecord | None:
|
||||
"""Fail-closed attribution. Returns the bottle only when exactly one
|
||||
active record has this source IP AND its identity token matches
|
||||
(constant-time). Either signal alone is insufficient: an unknown IP,
|
||||
an ambiguous IP (more than one active bottle — a misconfiguration),
|
||||
an empty token, or a token mismatch all deny."""
|
||||
if not identity_token:
|
||||
return None
|
||||
def by_source_ip(self, source_ip: str) -> BottleRecord | None:
|
||||
"""Network-layer attribution: the single active bottle at this source
|
||||
IP, or None if unknown or ambiguous (more than one — a
|
||||
misconfiguration). Safe as the *sole* attributor only where the
|
||||
source IP is unspoofable (Firecracker `/31` + nft) and the control
|
||||
plane is reachable only by the trusted gateway; pair with the
|
||||
identity token (`attribute`) elsewhere."""
|
||||
with self._connect() as conn:
|
||||
rows = conn.execute(
|
||||
"SELECT * FROM orchestrator_bottles "
|
||||
@@ -204,7 +227,17 @@ class RegistryStore(DbStore):
|
||||
).fetchall()
|
||||
if len(rows) != 1:
|
||||
return None
|
||||
rec = _row_to_record(rows[0])
|
||||
return _row_to_record(rows[0])
|
||||
|
||||
def attribute(self, source_ip: str, identity_token: str) -> BottleRecord | None:
|
||||
"""Fail-closed attribution: `by_source_ip` AND a matching identity
|
||||
token (constant-time). Either signal alone is insufficient here — an
|
||||
unknown/ambiguous IP, an empty token, or a token mismatch all deny."""
|
||||
if not identity_token:
|
||||
return None
|
||||
rec = self.by_source_ip(source_ip)
|
||||
if rec is None:
|
||||
return None
|
||||
if not hmac.compare_digest(rec.identity_token, identity_token):
|
||||
return None
|
||||
return rec
|
||||
|
||||
@@ -0,0 +1,121 @@
|
||||
"""The per-host orchestrator core (PRD 0070).
|
||||
|
||||
`Orchestrator` is the single backend-neutral object the control plane talks
|
||||
to: it owns the registry (runtime state) and brokers agent launches. It
|
||||
never branches on backend — the `LaunchBroker` abstracts the backend-native
|
||||
launch, so this same object drives docker / firecracker / apple once a real
|
||||
broker is wired in.
|
||||
|
||||
Launch lifecycle:
|
||||
|
||||
* `launch_bottle` mints the bottle (registry: source IP + identity
|
||||
token), sends a *signed, structured* launch request through the broker,
|
||||
and returns the record. If the broker rejects/fails, the registry entry
|
||||
is rolled back so a failed launch leaves no orphan.
|
||||
* `teardown_bottle` sends a signed teardown request, then deregisters.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from .broker import LaunchBroker, LaunchRequest, sign_request
|
||||
from .registry import BottleRecord, RegistryStore
|
||||
from .gateway import Gateway
|
||||
|
||||
|
||||
class Orchestrator:
|
||||
"""Owns the registry + brokers launches, and manages the single
|
||||
consolidated per-host gateway. Backend-neutral (broker and gateway
|
||||
abstract the backend-native pieces)."""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
registry: RegistryStore,
|
||||
broker: LaunchBroker,
|
||||
sign_secret: bytes,
|
||||
gateway: Gateway | None = None,
|
||||
) -> None:
|
||||
self.registry = registry
|
||||
self._broker = broker
|
||||
self._secret = sign_secret
|
||||
self._gateway = gateway
|
||||
|
||||
def launch_bottle(
|
||||
self,
|
||||
source_ip: str,
|
||||
*,
|
||||
image_ref: str = "",
|
||||
slot: int | None = None,
|
||||
metadata: str = "",
|
||||
policy: str = "",
|
||||
) -> BottleRecord:
|
||||
"""Register a bottle (with its gateway policy) and broker its launch.
|
||||
Rolls the registry entry back if the launch doesn't take, so a
|
||||
failure leaves no orphan."""
|
||||
rec = self.registry.register(source_ip, metadata=metadata, policy=policy)
|
||||
req = LaunchRequest(
|
||||
op="launch",
|
||||
bottle_id=rec.bottle_id,
|
||||
source_ip=source_ip,
|
||||
image_ref=image_ref,
|
||||
slot=slot,
|
||||
)
|
||||
launched = False
|
||||
try:
|
||||
self._broker.submit(sign_request(req, self._secret))
|
||||
launched = True
|
||||
finally:
|
||||
if not launched:
|
||||
self.registry.deregister(rec.bottle_id)
|
||||
return rec
|
||||
|
||||
def teardown_bottle(self, bottle_id: str) -> bool:
|
||||
"""Broker teardown then deregister. False if the bottle is unknown."""
|
||||
rec = self.registry.get(bottle_id)
|
||||
if rec is None:
|
||||
return False
|
||||
req = LaunchRequest(op="teardown", bottle_id=bottle_id, source_ip=rec.source_ip)
|
||||
self._broker.submit(sign_request(req, self._secret))
|
||||
self.registry.deregister(bottle_id)
|
||||
return True
|
||||
|
||||
def attribute(self, source_ip: str, identity_token: str) -> BottleRecord | None:
|
||||
"""Fail-closed attribution (delegates to the registry)."""
|
||||
return self.registry.attribute(source_ip, identity_token)
|
||||
|
||||
def resolve(self, source_ip: str, identity_token: str = "") -> BottleRecord | None:
|
||||
"""Resolve the bottle behind a request — the source-IP-keyed lookup
|
||||
the multi-tenant gateway makes per request; the returned record
|
||||
carries its `policy`. With a token, full attribution (source IP +
|
||||
token); without, network-layer attribution by source IP alone
|
||||
(valid where the IP is unspoofable and the control plane is
|
||||
gateway-only)."""
|
||||
if identity_token:
|
||||
return self.registry.attribute(source_ip, identity_token)
|
||||
return self.registry.by_source_ip(source_ip)
|
||||
|
||||
def set_policy(self, bottle_id: str, policy: str) -> bool:
|
||||
"""Update a bottle's gateway policy in place (live reload). False if
|
||||
the bottle is unknown."""
|
||||
return self.registry.set_policy(bottle_id, policy)
|
||||
|
||||
# --- consolidated gateway ----------------------------------------------
|
||||
|
||||
def ensure_gateway(self) -> None:
|
||||
"""Ensure the single per-host gateway is built and up (idempotent).
|
||||
No-op when no gateway is configured."""
|
||||
if self._gateway is not None:
|
||||
self._gateway.ensure_built()
|
||||
self._gateway.ensure_running()
|
||||
|
||||
def gateway_status(self) -> dict[str, object]:
|
||||
"""Report the shared gateway for the control plane / console."""
|
||||
if self._gateway is None:
|
||||
return {"configured": False}
|
||||
return {
|
||||
"configured": True,
|
||||
"name": self._gateway.name,
|
||||
"running": self._gateway.is_running(),
|
||||
}
|
||||
|
||||
|
||||
__all__ = ["Orchestrator"]
|
||||
@@ -0,0 +1,123 @@
|
||||
"""Gateway-side per-client policy resolver (PRD 0070).
|
||||
|
||||
The consolidated gateway serves every bottle from one process, so for each
|
||||
request it must apply the *calling* bottle's policy, selected by the source
|
||||
IP the attribution invariant makes unspoofable. This resolves that policy
|
||||
from the orchestrator's control plane (`POST /resolve`), keyed on the
|
||||
`(source_ip, identity_token)` pair.
|
||||
|
||||
**Always fresh — no cache.** The resolver is called rarely enough that a
|
||||
round-trip doesn't matter, and correctness matters more than speed: every
|
||||
resolve reflects the orchestrator's *current* view, so a revocation, a
|
||||
policy change, or a bottle teardown the orchestrator knows about is honored
|
||||
immediately rather than lingering for a cache TTL. (If this ever becomes a
|
||||
hot path, add caching with orchestrator-driven invalidation — not a blind
|
||||
TTL.)
|
||||
|
||||
**Fail-closed:** an unattributed client (the orchestrator answers `403`)
|
||||
resolves to `None`, and the caller (the egress addon, git-gate) must then
|
||||
deny — exactly as an unknown bottle should be treated. Orchestrator
|
||||
*errors* (unreachable / unexpected status) raise, so the caller can fail
|
||||
closed too rather than silently serving stale or empty policy.
|
||||
|
||||
The resolved value is the policy blob the orchestrator stores verbatim; the
|
||||
consumer parses it (e.g. the egress addon's `load_config`). This module is
|
||||
stdlib-only and free of bot-bottle imports so it can be COPYed flat into
|
||||
the sidecar bundle.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import urllib.error
|
||||
import urllib.request
|
||||
|
||||
DEFAULT_TIMEOUT_SECONDS = 2.0
|
||||
|
||||
|
||||
class PolicyResolveError(RuntimeError):
|
||||
"""The orchestrator was unreachable or returned an unexpected status —
|
||||
distinct from a clean `403` (unattributed), which returns None."""
|
||||
|
||||
|
||||
class PolicyResolver:
|
||||
"""Resolves each client's policy from the orchestrator, fresh per call."""
|
||||
|
||||
def __init__(self, base_url: str, *, timeout: float = DEFAULT_TIMEOUT_SECONDS) -> None:
|
||||
self._base = base_url.rstrip("/")
|
||||
self._timeout = timeout
|
||||
|
||||
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()
|
||||
req = urllib.request.Request(
|
||||
f"{self._base}/resolve", data=body, method="POST",
|
||||
headers={"Content-Type": "application/json"},
|
||||
)
|
||||
try:
|
||||
with urllib.request.urlopen(req, timeout=self._timeout) as resp:
|
||||
payload = json.loads(resp.read())
|
||||
except urllib.error.HTTPError as e:
|
||||
if e.code == 403:
|
||||
return None # unattributed → fail closed (caller denies)
|
||||
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
|
||||
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
|
||||
|
||||
|
||||
@@ -10,8 +10,8 @@
|
||||
|
||||
## Summary
|
||||
|
||||
Replace the **per-bottle sidecar bundle** with a single **persistent,
|
||||
per-host orchestrator**: one long-lived service that runs the sidecar
|
||||
Replace the **per-bottle gateway bundle** with a single **persistent,
|
||||
per-host orchestrator**: one long-lived service that runs the gateway
|
||||
functions (egress / git-gate / supervise), coordinates with the console,
|
||||
and brokers agent launches and teardown. It is **virtualized from the
|
||||
start** using each backend's native isolation primitive — a Firecracker
|
||||
@@ -22,13 +22,13 @@ container on the legacy backend — and is fronted by a single
|
||||
|
||||
## Motivation
|
||||
|
||||
Today each bottle spins up its own sidecar bundle (egress mitmproxy +
|
||||
Today each bottle spins up its own gateway bundle (egress mitmproxy +
|
||||
git-gate + supervise). That costs:
|
||||
|
||||
- **Resources.** N bottles → N heavy bundles booting and idling.
|
||||
- **Operational churn.** Per-launch container/VM lifecycle for the
|
||||
sidecars, a control path baked at launch and torn down at exit.
|
||||
- **A blurry contract.** "How a bottle talks to its sidecar" is
|
||||
gateways, a control path baked at launch and torn down at exit.
|
||||
- **A blurry contract.** "How a bottle talks to its gateway" is
|
||||
re-implemented per backend instead of being one agreed interface.
|
||||
|
||||
A per-host orchestrator collapses the first two and forces the third to
|
||||
@@ -52,11 +52,11 @@ weaken, and the weakened ones must be mitigated by design, not hand-waved.
|
||||
structured, auditable privileged core instead of a fat socket.
|
||||
- **Attribution is enforced, not assumed.** Making source-IP identity a
|
||||
first-class contract invariant (below) means each backend must *prove*
|
||||
it, rather than the sidecar implicitly trusting network position.
|
||||
it, rather than the gateway implicitly trusting network position.
|
||||
|
||||
### What gets weaker, and the mitigation
|
||||
|
||||
1. **Secret concentration.** Per-bottle sidecars isolate secrets at the
|
||||
1. **Secret concentration.** Per-bottle gateways isolate secrets at the
|
||||
process boundary — each holds only its bottle's tokens/keys. A host
|
||||
orchestrator concentrates **every bottle's** egress tokens, git deploy
|
||||
keys, and the console credential in one long-lived process. A single
|
||||
@@ -75,7 +75,7 @@ weaken, and the weakened ones must be mitigated by design, not hand-waved.
|
||||
fleet, plus launch authority, plus the console token.
|
||||
- *Mitigation:* the orchestrator is itself confined (its own VM/container
|
||||
with its own fail-closed egress); make it **restartable without killing
|
||||
running agent VMs** (agents keep running; they briefly lose sidecar
|
||||
running agent VMs** (agents keep running; they briefly lose gateway
|
||||
connectivity until it's back); persist state to a host volume so a
|
||||
restart re-adopts live bottles rather than losing them.
|
||||
|
||||
@@ -114,13 +114,13 @@ responsibility** and part of the contract:
|
||||
- **Apple** — the host-only network.
|
||||
|
||||
If a backend can't honor the invariant, source-IP consolidation is not
|
||||
safe there and that backend keeps per-bottle sidecars. The invariant is a
|
||||
safe there and that backend keeps per-bottle gateways. The invariant is a
|
||||
hard precondition, not an aspiration.
|
||||
|
||||
**Defense-in-depth — a per-bottle identity token.** On top of the
|
||||
network-layer invariant, inject a per-bottle secret token into every
|
||||
request the agent makes to the orchestrator (the agent already egresses
|
||||
through the sidecar proxy, so this is cheap to add). It gives an
|
||||
through the gateway proxy, so this is cheap to add). It gives an
|
||||
**application-layer** proof of identity independent of the network layer:
|
||||
|
||||
- On **Firecracker** the `/31` + nft already make source IP unspoofable
|
||||
@@ -133,7 +133,7 @@ Requirements: the token is **per-bottle, unguessable, and
|
||||
non-cross-leakable** — a bottle can only ever prove it is *itself* (it
|
||||
can't learn another bottle's token, given bottle isolation), so a hostile
|
||||
agent gains nothing by presenting it. The orchestrator provisions the
|
||||
token at launch and the sidecar requires it to attribute + authorize.
|
||||
token at launch and the gateway requires it to attribute + authorize.
|
||||
Note this hardens *attribution*, not *secret exposure*: it's app-layer, so
|
||||
a compromised orchestrator still sees every token (that's the
|
||||
concentration problem, addressed separately under Secret handling).
|
||||
@@ -178,7 +178,7 @@ manifest anywhere a raw token value is accepted, discovered from
|
||||
`AgentProvider`s are — because maintaining every forge/cloud/OAuth
|
||||
provider in-tree is untenable. The orchestrator's vault mints via these
|
||||
providers; but the abstraction is shippable independently and today's
|
||||
per-bottle sidecars can use it too.
|
||||
per-bottle gateways can use it too.
|
||||
|
||||
## Design
|
||||
|
||||
@@ -195,7 +195,7 @@ Three surfaces; only one is per-backend.
|
||||
every host (no vsock/unix-socket portability caveats); a local unix
|
||||
socket is a fine optimization, but HTTP is the wire contract.
|
||||
2. **Data plane (agent → orchestrator)** — the egress / git / supervise
|
||||
endpoints. Already agnostic today (agents dial `http://sidecar:9099`);
|
||||
endpoints. Already agnostic today (agents dial `http://gateway:9099`);
|
||||
only the *address* and *how packets get there* are per-backend.
|
||||
3. **Launch / wire (orchestrator → backend)** — the irreducibly
|
||||
backend-specific part; lives on `BottleBackend`.
|
||||
@@ -249,7 +249,7 @@ forged one from a compromised co-located component. The orchestrator signs;
|
||||
the broker verifies with the orchestrator's public key (provisioned at
|
||||
broker install). This is the concrete form of security #3's "structured
|
||||
requests only." Same JSON-with-ids + JWT shape for all
|
||||
orchestrator↔broker/sidecar communication; cases that don't fit get
|
||||
orchestrator↔broker/gateway communication; cases that don't fit get
|
||||
handled as they arise, with this as the default.
|
||||
|
||||
If `BottleBackend` bloats, the pressure valve is composition one level
|
||||
@@ -299,10 +299,10 @@ and integrate a console against.
|
||||
the data plane and the console reach state through the control-plane RPC,
|
||||
never a direct file handle.** No agent-facing component gets the file, so
|
||||
none can forge attribution. (This supersedes the earlier `ro`-mount idea.)
|
||||
- *Transitional caveat:* today the per-bottle **supervise sidecar
|
||||
- *Transitional caveat:* today the per-bottle **supervise gateway
|
||||
rw-bind-mounts `bot-bottle.db`** to write proposals — exactly the
|
||||
pattern the orchestrator removes (supervise consolidates into the
|
||||
orchestrator; sidecar writes become RPC calls). Until that lands, don't
|
||||
orchestrator; gateway writes become RPC calls). Until that lands, don't
|
||||
put the attribution registry behind a data-plane-writable mount.
|
||||
|
||||
Implementation note for the VM slices: SQLite **WAL** over a guest share
|
||||
@@ -327,7 +327,7 @@ orchestrator becomes a VM. Decouple the two risks instead:
|
||||
|
||||
Backend order (cheapest proof → hardest → last):
|
||||
|
||||
1. **Docker orchestrator** — nearly free (the sidecar bundle is already
|
||||
1. **Docker orchestrator** — nearly free (the gateway bundle is already
|
||||
containers; collapse N bundles into one persistent container). Proves
|
||||
consolidation + the `BottleBackend` seam with the least moving parts.
|
||||
2. **Firecracker orchestrator** — the real work: the shim + VM-to-VM
|
||||
@@ -336,13 +336,13 @@ Backend order (cheapest proof → hardest → last):
|
||||
the dev-harness so the app logic is already proven.
|
||||
3. **macOS (Apple container)** — last (container-to-container networking).
|
||||
|
||||
Keep the sidecar **service one shared thing** throughout.
|
||||
Keep the gateway **service one shared thing** throughout.
|
||||
|
||||
## Non-goals
|
||||
|
||||
- Removing OCI/Dockerfile support for agent images (0069's concern).
|
||||
- A single database for *all* config (see the three-tier table).
|
||||
- Changing the per-bottle isolation of agent workloads — only the sidecar
|
||||
- Changing the per-bottle isolation of agent workloads — only the gateway
|
||||
is consolidated; agents stay one-VM/container-each.
|
||||
|
||||
## Relationship to other work
|
||||
@@ -393,7 +393,7 @@ Keep the sidecar **service one shared thing** throughout.
|
||||
`BottleBackend.wire()` (DNAT+forward for fc, shared-net for
|
||||
docker/apple), not orchestrator logic. **Not a blocker** — resolvable at
|
||||
implementation time (may require a bit of host modification, as the pool
|
||||
setup already does on NixOS); an earlier "sidecars in VMs" spike showed
|
||||
setup already does on NixOS); an earlier "gateways in VMs" spike showed
|
||||
it's feasible.
|
||||
- **Live-reload protocol** for per-bottle policy over the HTTP control
|
||||
plane (add/remove routes/keys/proposals without a restart).
|
||||
|
||||
@@ -0,0 +1,56 @@
|
||||
"""Integration: the Docker launch broker starts and removes a real container.
|
||||
|
||||
Gated on a reachable Docker daemon (skips cleanly otherwise). Uses a tiny
|
||||
image; the container may exit immediately — we only assert it exists after
|
||||
launch and is gone after teardown.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import secrets
|
||||
import subprocess
|
||||
import unittest
|
||||
|
||||
from bot_bottle.orchestrator.broker import LaunchRequest, sign_request
|
||||
from bot_bottle.orchestrator.docker_broker import DockerBroker, container_name
|
||||
from tests._docker import skip_unless_docker
|
||||
|
||||
IMAGE = "busybox"
|
||||
|
||||
|
||||
@skip_unless_docker()
|
||||
class TestDockerBrokerIntegration(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.secret = secrets.token_bytes(16)
|
||||
self.broker = DockerBroker(self.secret)
|
||||
self.bottle_id = "itest" + secrets.token_hex(4)
|
||||
self.name = container_name(self.bottle_id)
|
||||
self.addCleanup(
|
||||
lambda: subprocess.run(
|
||||
["docker", "rm", "--force", self.name],
|
||||
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
|
||||
)
|
||||
)
|
||||
|
||||
def _exists(self) -> bool:
|
||||
proc = subprocess.run(
|
||||
["docker", "ps", "-a", "--filter", f"name=^{self.name}$",
|
||||
"--format", "{{.Names}}"],
|
||||
stdout=subprocess.PIPE, text=True, check=False,
|
||||
)
|
||||
return self.name in proc.stdout.split()
|
||||
|
||||
def _submit(self, req: LaunchRequest) -> None:
|
||||
self.broker.submit(sign_request(req, self.secret))
|
||||
|
||||
def test_launch_creates_then_teardown_removes(self) -> None:
|
||||
self._submit(
|
||||
LaunchRequest(op="launch", bottle_id=self.bottle_id, image_ref=IMAGE)
|
||||
)
|
||||
self.assertTrue(self._exists(), "container should exist after launch")
|
||||
self._submit(LaunchRequest(op="teardown", bottle_id=self.bottle_id))
|
||||
self.assertFalse(self._exists(), "container should be gone after teardown")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,45 @@
|
||||
"""Integration: the consolidated Docker gateway is an idempotent singleton.
|
||||
|
||||
Gated on a reachable Docker daemon. Uses a unique name so it never
|
||||
collides with a real per-host gateway or a leftover from another run.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import secrets
|
||||
import subprocess
|
||||
import unittest
|
||||
|
||||
from bot_bottle.orchestrator.gateway import DockerGateway
|
||||
from tests._docker import skip_unless_docker
|
||||
|
||||
IMAGE = "busybox"
|
||||
|
||||
|
||||
@skip_unless_docker()
|
||||
class TestDockerGatewayIntegration(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.name = "bot-bottle-orch-gateway-itest-" + secrets.token_hex(4)
|
||||
self.sc = DockerGateway(IMAGE, name=self.name)
|
||||
self.addCleanup(self.sc.stop)
|
||||
|
||||
def _count(self) -> int:
|
||||
proc = subprocess.run(
|
||||
["docker", "ps", "-a", "--filter", f"name=^{self.name}$",
|
||||
"--format", "{{.Names}}"],
|
||||
stdout=subprocess.PIPE, text=True, check=False,
|
||||
)
|
||||
return sum(1 for n in proc.stdout.split() if n == self.name)
|
||||
|
||||
def test_ensure_is_idempotent_singleton(self) -> None:
|
||||
self.sc.ensure_running()
|
||||
self.assertEqual(1, self._count())
|
||||
# A second ensure must not spawn a second container — one per host.
|
||||
self.sc.ensure_running()
|
||||
self.assertEqual(1, self._count())
|
||||
self.sc.stop()
|
||||
self.assertEqual(0, self._count())
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,36 @@
|
||||
"""Integration: DockerGateway.image_exists reflects real docker state.
|
||||
|
||||
Gated on a reachable Docker daemon. Deliberately does NOT build the full
|
||||
sidecar bundle (a heavy, slow image build) — it exercises the `image_exists`
|
||||
primitive that `ensure_built` gates on, against a tiny pulled image and a
|
||||
name that can't exist.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import subprocess
|
||||
import unittest
|
||||
|
||||
from bot_bottle.orchestrator.gateway import DockerGateway
|
||||
from tests._docker import skip_unless_docker
|
||||
|
||||
IMAGE = "busybox"
|
||||
|
||||
|
||||
@skip_unless_docker()
|
||||
class TestDockerGatewayImageExists(unittest.TestCase):
|
||||
def test_image_exists_true_for_present_false_for_absent(self) -> None:
|
||||
# Ensure the tiny image is present (build_if_missing is disabled here
|
||||
# so this never triggers a Dockerfile.sidecars build).
|
||||
subprocess.run(
|
||||
["docker", "pull", IMAGE],
|
||||
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
|
||||
)
|
||||
self.assertTrue(DockerGateway(IMAGE, dockerfile=None).image_exists())
|
||||
self.assertFalse(
|
||||
DockerGateway("bot-bottle-nonexistent:doesnotexist", dockerfile=None).image_exists()
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,91 @@
|
||||
"""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):
|
||||
process = MagicMock()
|
||||
process.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}.OrchestratorClient", return_value=client), \
|
||||
patch(f"{_MOD}.provision_git_gate", provision or Mock()):
|
||||
return launch_consolidated(_egress_plan(), _git_plan(), process=process)
|
||||
|
||||
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_gateway_and_live_bottle_addresses(self) -> None:
|
||||
client = _client(bottles=[{"source_ip": "172.18.0.3"}])
|
||||
ctx = self._run(client)
|
||||
self.assertEqual("172.18.0.4", ctx.source_ip) # .2 gw, .3 taken → .4
|
||||
|
||||
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()
|
||||
@@ -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()
|
||||
|
||||
@@ -0,0 +1,100 @@
|
||||
"""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, resolve_client_context
|
||||
from bot_bottle.policy_resolver import PolicyResolveError
|
||||
|
||||
|
||||
class _FakeResolver:
|
||||
def __init__(self, result: str | None = None, raises: bool = False) -> None:
|
||||
self._result = result
|
||||
self._raises = raises
|
||||
self.calls: list[tuple[str, str]] = []
|
||||
|
||||
def resolve(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._result
|
||||
|
||||
|
||||
class TestResolveClientConfig(unittest.TestCase):
|
||||
def test_valid_policy_is_parsed(self) -> None:
|
||||
cfg = resolve_client_config(
|
||||
_FakeResolver(result="routes:\n - host: example.com\n"), "10.243.0.1"
|
||||
)
|
||||
self.assertEqual(("example.com",), tuple(r.host for r in cfg.routes))
|
||||
|
||||
def test_unattributed_none_denies_all(self) -> None:
|
||||
cfg = resolve_client_config(_FakeResolver(result=None), "10.243.0.9")
|
||||
self.assertEqual((), cfg.routes) # no routes → default-deny
|
||||
|
||||
def test_empty_policy_denies_all(self) -> None:
|
||||
self.assertEqual((), resolve_client_config(_FakeResolver(result=""), "10.243.0.1").routes)
|
||||
|
||||
def test_resolver_error_denies_all(self) -> None:
|
||||
# Orchestrator unreachable/errored must never widen egress.
|
||||
self.assertEqual((), resolve_client_config(_FakeResolver(raises=True), "10.243.0.1").routes)
|
||||
|
||||
def test_unparseable_policy_denies_all(self) -> None:
|
||||
cfg = resolve_client_config(_FakeResolver(result="routes: notalist\n"), "10.243.0.1")
|
||||
self.assertEqual((), cfg.routes)
|
||||
|
||||
def test_forwards_source_ip_and_token(self) -> None:
|
||||
r = _FakeResolver(result=None)
|
||||
resolve_client_config(r, "10.243.0.1", "tok")
|
||||
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 +1,111 @@
|
||||
"""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(),
|
||||
hook_script=Path(),
|
||||
access_hook_script=Path(),
|
||||
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 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
|
||||
cps = [c for c in calls if c[:2] == ["docker", "cp"]]
|
||||
self.assertEqual(1, len(cps)) # only the key, not known_hosts
|
||||
self.assertTrue(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 +1,86 @@
|
||||
"""Unit tests for the orchestrator launch broker (PRD 0070)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import secrets
|
||||
import unittest
|
||||
|
||||
from bot_bottle.orchestrator.broker import (
|
||||
BrokerAuthError,
|
||||
LaunchRequest,
|
||||
StubBroker,
|
||||
sign_request,
|
||||
verify_request,
|
||||
)
|
||||
|
||||
|
||||
class TestSignVerify(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.secret = secrets.token_bytes(16)
|
||||
|
||||
def test_launch_round_trip(self) -> None:
|
||||
req = LaunchRequest(
|
||||
op="launch", bottle_id="b1", source_ip="10.243.0.1",
|
||||
image_ref="sha256:abc", slot=3,
|
||||
)
|
||||
self.assertEqual(req, verify_request(sign_request(req, self.secret), self.secret))
|
||||
|
||||
def test_teardown_round_trip(self) -> None:
|
||||
req = LaunchRequest(op="teardown", bottle_id="b1")
|
||||
got = verify_request(sign_request(req, self.secret), self.secret)
|
||||
self.assertEqual(("teardown", "b1"), (got.op, got.bottle_id))
|
||||
|
||||
def test_wrong_secret_rejected(self) -> None:
|
||||
token = sign_request(LaunchRequest(op="launch", bottle_id="b1"), self.secret)
|
||||
with self.assertRaises(BrokerAuthError):
|
||||
verify_request(token, secrets.token_bytes(16))
|
||||
|
||||
def test_tampered_payload_rejected(self) -> None:
|
||||
token = sign_request(LaunchRequest(op="launch", bottle_id="b1"), self.secret)
|
||||
header, payload, sig = token.split(".")
|
||||
flipped = payload[:-1] + ("A" if payload[-1] != "A" else "B")
|
||||
with self.assertRaises(BrokerAuthError):
|
||||
verify_request(f"{header}.{flipped}.{sig}", self.secret)
|
||||
|
||||
def test_malformed_tokens_rejected(self) -> None:
|
||||
for bad in ("", "a.b", "a.b.c.d", "not-a-token"):
|
||||
with self.assertRaises(BrokerAuthError):
|
||||
verify_request(bad, self.secret)
|
||||
|
||||
def test_unknown_op_rejected_despite_valid_signature(self) -> None:
|
||||
# A correctly-signed token whose op isn't in the allow-list must
|
||||
# still be refused — the schema guard is independent of provenance.
|
||||
token = sign_request(LaunchRequest(op="rm-rf", bottle_id="b1"), self.secret)
|
||||
with self.assertRaises(BrokerAuthError):
|
||||
verify_request(token, self.secret)
|
||||
|
||||
|
||||
class TestStubBroker(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.secret = secrets.token_bytes(16)
|
||||
self.broker = StubBroker(self.secret)
|
||||
|
||||
def test_submit_launch_records_verified_request(self) -> None:
|
||||
req = LaunchRequest(op="launch", bottle_id="b1", source_ip="10.243.0.1")
|
||||
got = self.broker.submit(sign_request(req, self.secret))
|
||||
self.assertEqual(req, got)
|
||||
self.assertEqual(["b1"], [r.bottle_id for r in self.broker.launched])
|
||||
self.assertEqual([], self.broker.torn_down)
|
||||
|
||||
def test_submit_teardown_records(self) -> None:
|
||||
self.broker.submit(
|
||||
sign_request(LaunchRequest(op="teardown", bottle_id="b1"), self.secret)
|
||||
)
|
||||
self.assertEqual(["b1"], [r.bottle_id for r in self.broker.torn_down])
|
||||
|
||||
def test_submit_forged_token_is_fail_closed(self) -> None:
|
||||
forged = sign_request(
|
||||
LaunchRequest(op="launch", bottle_id="b1"), secrets.token_bytes(16)
|
||||
)
|
||||
with self.assertRaises(BrokerAuthError):
|
||||
self.broker.submit(forged)
|
||||
self.assertEqual([], self.broker.launched) # nothing acted on
|
||||
|
||||
|
||||
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()
|
||||
@@ -7,53 +7,62 @@ server tests), plus one real-socket round-trip to prove the handler wiring.
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import secrets
|
||||
import tempfile
|
||||
import threading
|
||||
import unittest
|
||||
import urllib.request
|
||||
from pathlib import Path
|
||||
|
||||
from bot_bottle.orchestrator.broker import StubBroker
|
||||
from bot_bottle.orchestrator.control_plane import dispatch, make_server
|
||||
from bot_bottle.orchestrator.registry import RegistryStore
|
||||
from bot_bottle.orchestrator.service import Orchestrator
|
||||
|
||||
|
||||
def _body(obj: object) -> bytes:
|
||||
return json.dumps(obj).encode()
|
||||
|
||||
|
||||
def _orchestrator(db_path: Path) -> Orchestrator:
|
||||
store = RegistryStore(db_path)
|
||||
store.migrate()
|
||||
secret = secrets.token_bytes(16)
|
||||
return Orchestrator(store, StubBroker(secret), secret)
|
||||
|
||||
|
||||
class TestDispatch(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self._tmp = tempfile.TemporaryDirectory()
|
||||
self.store = RegistryStore(Path(self._tmp.name) / "r.db")
|
||||
self.store.migrate()
|
||||
self.orch = _orchestrator(Path(self._tmp.name) / "r.db")
|
||||
|
||||
def tearDown(self) -> None:
|
||||
self._tmp.cleanup()
|
||||
|
||||
def test_health(self) -> None:
|
||||
status, payload = dispatch(self.store, "GET", "/health", b"")
|
||||
status, payload = dispatch(self.orch, "GET", "/health", b"")
|
||||
self.assertEqual(200, status)
|
||||
self.assertEqual("ok", payload["status"])
|
||||
|
||||
def test_register_returns_id_and_token(self) -> None:
|
||||
status, payload = dispatch(
|
||||
self.store, "POST", "/bottles", _body({"source_ip": "10.243.0.1"})
|
||||
self.orch, "POST", "/bottles", _body({"source_ip": "10.243.0.1"})
|
||||
)
|
||||
self.assertEqual(201, status)
|
||||
self.assertTrue(payload["bottle_id"])
|
||||
self.assertTrue(payload["identity_token"])
|
||||
|
||||
def test_register_requires_source_ip(self) -> None:
|
||||
status, _ = dispatch(self.store, "POST", "/bottles", _body({}))
|
||||
status, _ = dispatch(self.orch, "POST", "/bottles", _body({}))
|
||||
self.assertEqual(400, status)
|
||||
|
||||
def test_register_rejects_bad_json(self) -> None:
|
||||
status, _ = dispatch(self.store, "POST", "/bottles", b"{not json")
|
||||
status, _ = dispatch(self.orch, "POST", "/bottles", b"{not json")
|
||||
self.assertEqual(400, status)
|
||||
|
||||
def test_list_redacts_identity_token(self) -> None:
|
||||
dispatch(self.store, "POST", "/bottles", _body({"source_ip": "10.243.0.1"}))
|
||||
status, payload = dispatch(self.store, "GET", "/bottles", b"")
|
||||
dispatch(self.orch, "POST", "/bottles", _body({"source_ip": "10.243.0.1"}))
|
||||
status, payload = dispatch(self.orch, "GET", "/bottles", b"")
|
||||
self.assertEqual(200, status)
|
||||
bottles = payload["bottles"]
|
||||
assert isinstance(bottles, list)
|
||||
@@ -65,58 +74,126 @@ class TestDispatch(unittest.TestCase):
|
||||
|
||||
def test_attribute_ok_and_forbidden(self) -> None:
|
||||
_, reg = dispatch(
|
||||
self.store, "POST", "/bottles", _body({"source_ip": "10.243.0.5"})
|
||||
self.orch, "POST", "/bottles", _body({"source_ip": "10.243.0.5"})
|
||||
)
|
||||
token = reg["identity_token"]
|
||||
ok_status, ok = dispatch(
|
||||
self.store, "POST", "/attribute",
|
||||
self.orch, "POST", "/attribute",
|
||||
_body({"source_ip": "10.243.0.5", "identity_token": token}),
|
||||
)
|
||||
self.assertEqual(200, ok_status)
|
||||
self.assertEqual(reg["bottle_id"], ok["bottle_id"])
|
||||
|
||||
bad_status, _ = dispatch(
|
||||
self.store, "POST", "/attribute",
|
||||
self.orch, "POST", "/attribute",
|
||||
_body({"source_ip": "10.243.0.5", "identity_token": "nope"}),
|
||||
)
|
||||
self.assertEqual(403, bad_status)
|
||||
|
||||
def test_attribute_requires_both_fields(self) -> None:
|
||||
status, _ = dispatch(
|
||||
self.store, "POST", "/attribute", _body({"source_ip": "10.243.0.5"})
|
||||
self.orch, "POST", "/attribute", _body({"source_ip": "10.243.0.5"})
|
||||
)
|
||||
self.assertEqual(400, status)
|
||||
|
||||
def test_delete(self) -> None:
|
||||
_, reg = dispatch(
|
||||
self.store, "POST", "/bottles", _body({"source_ip": "10.243.0.1"})
|
||||
self.orch, "POST", "/bottles", _body({"source_ip": "10.243.0.1"})
|
||||
)
|
||||
bid = reg["bottle_id"]
|
||||
status, payload = dispatch(self.store, "DELETE", f"/bottles/{bid}", b"")
|
||||
status, payload = dispatch(self.orch, "DELETE", f"/bottles/{bid}", b"")
|
||||
self.assertEqual(200, status)
|
||||
self.assertEqual(True, payload["deregistered"])
|
||||
self.assertEqual([], self.store.all())
|
||||
self.assertEqual(True, payload["torn_down"])
|
||||
self.assertEqual([], self.orch.registry.all())
|
||||
|
||||
def test_delete_missing_404(self) -> None:
|
||||
status, _ = dispatch(self.store, "DELETE", "/bottles/ghost", b"")
|
||||
status, _ = dispatch(self.orch, "DELETE", "/bottles/ghost", b"")
|
||||
self.assertEqual(404, status)
|
||||
|
||||
def test_unknown_route_404(self) -> None:
|
||||
status, _ = dispatch(self.store, "GET", "/nope", b"")
|
||||
status, _ = dispatch(self.orch, "GET", "/nope", b"")
|
||||
self.assertEqual(404, status)
|
||||
|
||||
def test_trailing_slash_normalized(self) -> None:
|
||||
status, _ = dispatch(self.store, "GET", "/health/", b"")
|
||||
status, _ = dispatch(self.orch, "GET", "/health/", b"")
|
||||
self.assertEqual(200, status)
|
||||
|
||||
def test_gateway_status_unconfigured(self) -> None:
|
||||
status, payload = dispatch(self.orch, "GET", "/gateway", b"")
|
||||
self.assertEqual(200, status)
|
||||
self.assertEqual(False, payload["configured"])
|
||||
|
||||
def test_launch_stores_policy_and_resolve_returns_it(self) -> None:
|
||||
_, reg = dispatch(
|
||||
self.orch, "POST", "/bottles",
|
||||
_body({"source_ip": "10.243.0.5", "policy": '{"a":1}'}),
|
||||
)
|
||||
status, payload = dispatch(
|
||||
self.orch, "POST", "/resolve",
|
||||
_body({"source_ip": "10.243.0.5", "identity_token": reg["identity_token"]}),
|
||||
)
|
||||
self.assertEqual(200, status)
|
||||
self.assertEqual(reg["bottle_id"], payload["bottle_id"])
|
||||
self.assertEqual('{"a":1}', payload["policy"])
|
||||
|
||||
def test_resolve_forbidden_on_bad_token(self) -> None:
|
||||
dispatch(self.orch, "POST", "/bottles", _body({"source_ip": "10.243.0.5"}))
|
||||
status, _ = dispatch(
|
||||
self.orch, "POST", "/resolve",
|
||||
_body({"source_ip": "10.243.0.5", "identity_token": "nope"}),
|
||||
)
|
||||
self.assertEqual(403, status)
|
||||
|
||||
def test_put_policy_updates_live(self) -> None:
|
||||
_, reg = dispatch(self.orch, "POST", "/bottles", _body({"source_ip": "10.243.0.1"}))
|
||||
bid = reg["bottle_id"]
|
||||
status, payload = dispatch(
|
||||
self.orch, "PUT", f"/bottles/{bid}/policy", _body({"policy": '{"v":9}'})
|
||||
)
|
||||
self.assertEqual(200, status)
|
||||
self.assertEqual(True, payload["updated"])
|
||||
_, resolved = dispatch(
|
||||
self.orch, "POST", "/resolve",
|
||||
_body({"source_ip": "10.243.0.1", "identity_token": reg["identity_token"]}),
|
||||
)
|
||||
self.assertEqual('{"v":9}', resolved["policy"])
|
||||
|
||||
def test_put_policy_missing_bottle_404(self) -> None:
|
||||
status, _ = dispatch(
|
||||
self.orch, "PUT", "/bottles/ghost/policy", _body({"policy": "{}"})
|
||||
)
|
||||
self.assertEqual(404, status)
|
||||
|
||||
def test_put_policy_requires_string(self) -> None:
|
||||
_, reg = dispatch(self.orch, "POST", "/bottles", _body({"source_ip": "10.243.0.1"}))
|
||||
status, _ = dispatch(
|
||||
self.orch, "PUT", f"/bottles/{reg['bottle_id']}/policy", _body({})
|
||||
)
|
||||
self.assertEqual(400, status)
|
||||
|
||||
def test_resolve_without_token_by_source_ip(self) -> None:
|
||||
_, reg = dispatch(
|
||||
self.orch, "POST", "/bottles",
|
||||
_body({"source_ip": "10.243.0.5", "policy": "P"}),
|
||||
)
|
||||
status, payload = dispatch(
|
||||
self.orch, "POST", "/resolve", _body({"source_ip": "10.243.0.5"})
|
||||
)
|
||||
self.assertEqual(200, status)
|
||||
self.assertEqual(reg["bottle_id"], payload["bottle_id"])
|
||||
self.assertEqual("P", payload["policy"])
|
||||
|
||||
def test_resolve_requires_source_ip(self) -> None:
|
||||
status, _ = dispatch(self.orch, "POST", "/resolve", _body({}))
|
||||
self.assertEqual(400, status)
|
||||
|
||||
|
||||
class TestServerRoundTrip(unittest.TestCase):
|
||||
def test_http_register_health_attribute(self) -> None:
|
||||
tmp = tempfile.TemporaryDirectory()
|
||||
self.addCleanup(tmp.cleanup)
|
||||
store = RegistryStore(Path(tmp.name) / "r.db")
|
||||
store.migrate()
|
||||
server = make_server(store, "127.0.0.1", 0)
|
||||
orch = _orchestrator(Path(tmp.name) / "r.db")
|
||||
server = make_server(orch, "127.0.0.1", 0)
|
||||
self.addCleanup(server.server_close)
|
||||
thread = threading.Thread(target=server.serve_forever, daemon=True)
|
||||
thread.start()
|
||||
|
||||
@@ -0,0 +1,100 @@
|
||||
"""Unit tests for the Docker launch broker (PRD 0070). Docker is mocked."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import secrets
|
||||
import unittest
|
||||
from unittest.mock import Mock, patch
|
||||
|
||||
from bot_bottle.orchestrator.broker import (
|
||||
BrokerAuthError,
|
||||
LaunchRequest,
|
||||
sign_request,
|
||||
)
|
||||
from bot_bottle.orchestrator.docker_broker import (
|
||||
BOTTLE_ID_LABEL,
|
||||
DockerBroker,
|
||||
DockerBrokerError,
|
||||
container_name,
|
||||
rm_argv,
|
||||
run_argv,
|
||||
)
|
||||
|
||||
|
||||
class TestArgv(unittest.TestCase):
|
||||
def test_run_argv_uses_only_static_fields(self) -> None:
|
||||
req = LaunchRequest(op="launch", bottle_id="b1", image_ref="busybox")
|
||||
argv = run_argv(req)
|
||||
self.assertEqual(["docker", "run"], argv[:2])
|
||||
self.assertIn("--name", argv)
|
||||
self.assertIn(container_name("b1"), argv)
|
||||
self.assertIn(f"{BOTTLE_ID_LABEL}=b1", argv)
|
||||
self.assertEqual("busybox", argv[-1]) # image is the terminal arg
|
||||
|
||||
def test_rm_argv(self) -> None:
|
||||
req = LaunchRequest(op="teardown", bottle_id="b1")
|
||||
self.assertEqual(["docker", "rm", "--force", container_name("b1")], rm_argv(req))
|
||||
|
||||
def test_container_name_is_prefixed(self) -> None:
|
||||
name = container_name("b1")
|
||||
self.assertTrue(name.startswith("bot-bottle-orch-"))
|
||||
self.assertTrue(name.endswith("b1"))
|
||||
|
||||
|
||||
class TestDockerBroker(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.secret = secrets.token_bytes(16)
|
||||
self.broker = DockerBroker(self.secret)
|
||||
|
||||
def _submit(self, req: LaunchRequest) -> None:
|
||||
self.broker.submit(sign_request(req, self.secret))
|
||||
|
||||
def test_launch_invokes_docker_run(self) -> None:
|
||||
req = LaunchRequest(op="launch", bottle_id="b1", image_ref="busybox")
|
||||
with patch.object(self.broker, "_docker", return_value=Mock(returncode=0, stderr="")) as m:
|
||||
self._submit(req)
|
||||
m.assert_called_once()
|
||||
self.assertEqual(run_argv(req), m.call_args.args[0])
|
||||
|
||||
def test_launch_without_image_raises_and_skips_docker(self) -> None:
|
||||
req = LaunchRequest(op="launch", bottle_id="b1", image_ref="")
|
||||
with patch.object(self.broker, "_docker") as m:
|
||||
with self.assertRaises(DockerBrokerError):
|
||||
self._submit(req)
|
||||
m.assert_not_called()
|
||||
|
||||
def test_launch_docker_failure_raises(self) -> None:
|
||||
req = LaunchRequest(op="launch", bottle_id="b1", image_ref="busybox")
|
||||
with patch.object(self.broker, "_docker", return_value=Mock(returncode=1, stderr="boom")):
|
||||
with self.assertRaises(DockerBrokerError):
|
||||
self._submit(req)
|
||||
|
||||
def test_teardown_invokes_docker_rm(self) -> None:
|
||||
req = LaunchRequest(op="teardown", bottle_id="b1")
|
||||
with patch.object(self.broker, "_docker", return_value=Mock(returncode=0, stderr="")) as m:
|
||||
self._submit(req)
|
||||
self.assertEqual(rm_argv(req), m.call_args.args[0])
|
||||
|
||||
def test_teardown_is_idempotent_on_missing_container(self) -> None:
|
||||
req = LaunchRequest(op="teardown", bottle_id="b1")
|
||||
absent = Mock(returncode=1, stderr="Error: No such container: bot-bottle-orch-b1")
|
||||
with patch.object(self.broker, "_docker", return_value=absent):
|
||||
self._submit(req) # must not raise
|
||||
|
||||
def test_teardown_other_failure_raises(self) -> None:
|
||||
req = LaunchRequest(op="teardown", bottle_id="b1")
|
||||
with patch.object(self.broker, "_docker", return_value=Mock(returncode=1, stderr="daemon down")):
|
||||
with self.assertRaises(DockerBrokerError):
|
||||
self._submit(req)
|
||||
|
||||
def test_forged_token_never_touches_docker(self) -> None:
|
||||
req = LaunchRequest(op="launch", bottle_id="b1", image_ref="busybox")
|
||||
forged = sign_request(req, secrets.token_bytes(16))
|
||||
with patch.object(self.broker, "_docker") as m:
|
||||
with self.assertRaises(BrokerAuthError):
|
||||
self.broker.submit(forged)
|
||||
m.assert_not_called()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,156 @@
|
||||
"""Unit tests for the consolidated Docker gateway (PRD 0070). Docker mocked."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import unittest
|
||||
from unittest.mock import Mock, patch
|
||||
|
||||
from bot_bottle.orchestrator.gateway import (
|
||||
GATEWAY_NAME,
|
||||
DockerGateway,
|
||||
GatewayError,
|
||||
)
|
||||
|
||||
_RUN_DOCKER = "bot_bottle.orchestrator.gateway.run_docker"
|
||||
|
||||
|
||||
def _proc(returncode: int = 0, stdout: str = "", stderr: str = "") -> Mock:
|
||||
return Mock(returncode=returncode, stdout=stdout, stderr=stderr)
|
||||
|
||||
|
||||
class TestDockerGateway(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.sc = DockerGateway("bot-bottle-sidecars:latest")
|
||||
|
||||
def test_default_name(self) -> None:
|
||||
self.assertEqual(GATEWAY_NAME, self.sc.name)
|
||||
|
||||
def test_is_running_reads_docker_ps(self) -> None:
|
||||
with patch(_RUN_DOCKER, return_value=_proc(stdout=self.sc.name + "\n")):
|
||||
self.assertTrue(self.sc.is_running())
|
||||
with patch(_RUN_DOCKER, return_value=_proc(stdout="")):
|
||||
self.assertFalse(self.sc.is_running())
|
||||
|
||||
def test_ensure_running_is_noop_when_already_up(self) -> None:
|
||||
with patch(_RUN_DOCKER, return_value=_proc(stdout=self.sc.name)) as m:
|
||||
self.sc.ensure_running()
|
||||
# Only the is_running() ps probe — no rm / run.
|
||||
self.assertEqual(1, m.call_count)
|
||||
|
||||
def test_ensure_running_starts_the_singleton_when_absent(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()
|
||||
|
||||
runs = [c for c in calls if c[:2] == ["docker", "run"]]
|
||||
self.assertEqual(1, len(runs))
|
||||
self.assertIn(self.sc.name, runs[0])
|
||||
self.assertIn("bot-bottle-sidecars:latest", runs[0])
|
||||
# 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])
|
||||
|
||||
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_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:
|
||||
if argv[:2] == ["docker", "ps"]:
|
||||
return _proc(stdout="")
|
||||
if argv[:2] == ["docker", "run"]:
|
||||
return _proc(returncode=1, stderr="boom")
|
||||
return _proc()
|
||||
|
||||
with patch(_RUN_DOCKER, side_effect=fake):
|
||||
with self.assertRaises(GatewayError):
|
||||
self.sc.ensure_running()
|
||||
|
||||
def test_stop_is_idempotent_on_missing(self) -> None:
|
||||
absent = _proc(returncode=1, stderr="Error: No such container: x")
|
||||
with patch(_RUN_DOCKER, return_value=absent):
|
||||
self.sc.stop() # must not raise
|
||||
|
||||
def test_stop_raises_on_other_failure(self) -> None:
|
||||
with patch(_RUN_DOCKER, return_value=_proc(returncode=1, stderr="daemon down")):
|
||||
with self.assertRaises(GatewayError):
|
||||
self.sc.stop()
|
||||
|
||||
|
||||
class TestDockerGatewayBuild(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.sc = DockerGateway() # defaults to the real bundle image + dockerfile
|
||||
|
||||
def test_image_exists_reads_docker_inspect(self) -> None:
|
||||
with patch(_RUN_DOCKER, return_value=_proc(returncode=0)):
|
||||
self.assertTrue(self.sc.image_exists())
|
||||
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:
|
||||
calls: list[list[str]] = []
|
||||
|
||||
def fake(argv: list[str]) -> Mock:
|
||||
calls.append(argv)
|
||||
if argv[:3] == ["docker", "image", "inspect"]:
|
||||
return _proc(returncode=1) # missing
|
||||
return _proc()
|
||||
|
||||
with patch(_RUN_DOCKER, side_effect=fake):
|
||||
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]))
|
||||
|
||||
def test_ensure_built_noop_when_no_dockerfile(self) -> None:
|
||||
sc = DockerGateway("busybox", dockerfile=None)
|
||||
with patch(_RUN_DOCKER) as m:
|
||||
sc.ensure_built()
|
||||
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 self.assertRaises(GatewayError):
|
||||
self.sc.ensure_built()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,87 @@
|
||||
"""Unit: orchestrator process 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, patch
|
||||
|
||||
from bot_bottle.orchestrator.lifecycle import (
|
||||
OrchestratorProcess,
|
||||
OrchestratorStartError,
|
||||
)
|
||||
from tests.unit import use_bottle_root
|
||||
|
||||
_URLOPEN = "bot_bottle.orchestrator.lifecycle.urllib.request.urlopen"
|
||||
_POPEN = "bot_bottle.orchestrator.lifecycle.subprocess.Popen"
|
||||
_SLEEP = "bot_bottle.orchestrator.lifecycle.time.sleep"
|
||||
_MONOTONIC = "bot_bottle.orchestrator.lifecycle.time.monotonic"
|
||||
|
||||
|
||||
def _health(status: int) -> MagicMock:
|
||||
"""A urlopen() context-manager whose `.status` is `status`."""
|
||||
m = MagicMock()
|
||||
m.__enter__.return_value.status = status
|
||||
return m
|
||||
|
||||
|
||||
class TestOrchestratorProcess(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.p = OrchestratorProcess(port=8099)
|
||||
|
||||
def test_url(self) -> None:
|
||||
self.assertEqual("http://127.0.0.1:8099", self.p.url)
|
||||
|
||||
def test_is_healthy_true_on_200(self) -> None:
|
||||
with patch(_URLOPEN, return_value=_health(200)):
|
||||
self.assertTrue(self.p.is_healthy())
|
||||
|
||||
def test_is_healthy_false_on_error(self) -> None:
|
||||
with patch(_URLOPEN, side_effect=urllib.error.URLError("refused")):
|
||||
self.assertFalse(self.p.is_healthy())
|
||||
|
||||
def test_ensure_running_noop_when_already_healthy(self) -> None:
|
||||
with patch(_URLOPEN, return_value=_health(200)), patch(_POPEN) as popen:
|
||||
self.assertEqual(self.p.url, self.p.ensure_running())
|
||||
popen.assert_not_called() # a live control plane is left untouched
|
||||
|
||||
def test_ensure_running_spawns_then_waits_for_health(self) -> None:
|
||||
# First check (before spawn) fails; after spawn the poll succeeds.
|
||||
with patch(_URLOPEN, side_effect=[urllib.error.URLError("down"), _health(200)]), \
|
||||
patch(_POPEN) as popen, patch(_SLEEP):
|
||||
url = self.p.ensure_running()
|
||||
self.assertEqual(self.p.url, url)
|
||||
popen.assert_called_once()
|
||||
|
||||
def test_ensure_running_raises_on_startup_timeout(self) -> None:
|
||||
with patch(_URLOPEN, side_effect=urllib.error.URLError("down")), \
|
||||
patch(_POPEN), patch(_SLEEP), \
|
||||
patch(_MONOTONIC, side_effect=[0.0, 0.5, 2.0]):
|
||||
with self.assertRaises(OrchestratorStartError):
|
||||
self.p.ensure_running(startup_timeout=1.0)
|
||||
|
||||
def test_argv_includes_gateway_and_broker(self) -> None:
|
||||
argv = OrchestratorProcess(port=8099, broker="docker", gateway=True)._argv()
|
||||
self.assertIn("--gateway", argv)
|
||||
self.assertIn("bot_bottle.orchestrator", argv)
|
||||
self.assertEqual("docker", argv[argv.index("--broker") + 1])
|
||||
|
||||
def test_argv_omits_gateway_when_disabled(self) -> None:
|
||||
self.assertNotIn("--gateway", OrchestratorProcess(gateway=False)._argv())
|
||||
|
||||
def test_spawn_launches_detached_and_logs(self) -> None:
|
||||
with patch(_POPEN) as popen:
|
||||
self.p._spawn()
|
||||
popen.assert_called_once()
|
||||
kwargs = popen.call_args.kwargs
|
||||
self.assertTrue(kwargs["start_new_session"]) # outlives the CLI
|
||||
self.assertTrue((Path(self._tmp.name) / "orchestrator.log").exists())
|
||||
|
||||
|
||||
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()
|
||||
@@ -97,6 +97,42 @@ class TestRegistryStore(unittest.TestCase):
|
||||
self.assertNotIn("identity_token", rec.redacted())
|
||||
self.assertEqual("10.243.0.1", rec.redacted()["source_ip"])
|
||||
|
||||
def test_register_with_policy_resolves_via_attribution(self) -> None:
|
||||
rec = self.store.register("10.243.0.1", policy='{"allow":["x"]}')
|
||||
self.assertEqual('{"allow":["x"]}', rec.policy)
|
||||
got = self.store.attribute("10.243.0.1", rec.identity_token)
|
||||
assert got is not None
|
||||
self.assertEqual('{"allow":["x"]}', got.policy)
|
||||
|
||||
def test_set_policy_updates_live(self) -> None:
|
||||
rec = self.store.register("10.243.0.1")
|
||||
self.assertEqual("", rec.policy)
|
||||
self.assertTrue(self.store.set_policy(rec.bottle_id, '{"v":2}'))
|
||||
got = self.store.get(rec.bottle_id)
|
||||
assert got is not None
|
||||
self.assertEqual('{"v":2}', got.policy)
|
||||
|
||||
def test_set_policy_missing_is_false(self) -> None:
|
||||
self.assertFalse(self.store.set_policy("ghost", "{}"))
|
||||
|
||||
def test_policy_defaults_empty_and_persists(self) -> None:
|
||||
rec = self.store.register("10.243.0.1")
|
||||
got = RegistryStore(self.db).get(rec.bottle_id)
|
||||
assert got is not None
|
||||
self.assertEqual("", got.policy)
|
||||
|
||||
def test_by_source_ip_returns_single_active(self) -> None:
|
||||
rec = self.store.register("10.243.0.1")
|
||||
got = self.store.by_source_ip("10.243.0.1")
|
||||
assert got is not None
|
||||
self.assertEqual(rec.bottle_id, got.bottle_id)
|
||||
|
||||
def test_by_source_ip_unknown_or_ambiguous_denied(self) -> None:
|
||||
self.assertIsNone(self.store.by_source_ip("10.243.9.9")) # unknown
|
||||
self.store.register("10.243.0.1", bottle_id="a")
|
||||
self.store.register("10.243.0.1", bottle_id="b")
|
||||
self.assertIsNone(self.store.by_source_ip("10.243.0.1")) # ambiguous
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
||||
@@ -0,0 +1,144 @@
|
||||
"""Unit tests for the Orchestrator launch lifecycle (PRD 0070)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import secrets
|
||||
import tempfile
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
from bot_bottle.orchestrator.broker import LaunchBroker, LaunchRequest, StubBroker
|
||||
from bot_bottle.orchestrator.registry import RegistryStore
|
||||
from bot_bottle.orchestrator.service import Orchestrator
|
||||
from bot_bottle.orchestrator.gateway import Gateway
|
||||
|
||||
|
||||
class _FailingBroker(LaunchBroker):
|
||||
"""Verifies the token like any broker, then fails the launch — to
|
||||
exercise the orchestrator's registry rollback."""
|
||||
|
||||
def _launch(self, req: LaunchRequest) -> None:
|
||||
raise RuntimeError("launch failed")
|
||||
|
||||
def _teardown(self, req: LaunchRequest) -> None:
|
||||
pass
|
||||
|
||||
|
||||
class _FakeGateway(Gateway):
|
||||
"""In-memory gateway for wiring tests."""
|
||||
|
||||
def __init__(self) -> None:
|
||||
self.name = "fake-gateway"
|
||||
self.ensured = 0
|
||||
self.built = 0
|
||||
self._running = False
|
||||
|
||||
def ensure_built(self) -> None:
|
||||
self.built += 1
|
||||
|
||||
def ensure_running(self) -> None:
|
||||
self.ensured += 1
|
||||
self._running = True
|
||||
|
||||
def is_running(self) -> bool:
|
||||
return self._running
|
||||
|
||||
def stop(self) -> None:
|
||||
self._running = False
|
||||
|
||||
|
||||
class TestOrchestrator(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self._tmp = tempfile.TemporaryDirectory()
|
||||
self.secret = secrets.token_bytes(16)
|
||||
self.store = RegistryStore(Path(self._tmp.name) / "r.db")
|
||||
self.store.migrate()
|
||||
self.broker = StubBroker(self.secret)
|
||||
self.orch = Orchestrator(self.store, self.broker, self.secret)
|
||||
|
||||
def tearDown(self) -> None:
|
||||
self._tmp.cleanup()
|
||||
|
||||
def test_launch_registers_and_brokers_signed_request(self) -> None:
|
||||
rec = self.orch.launch_bottle("10.243.0.1", image_ref="sha256:abc", slot=2)
|
||||
self.assertIsNotNone(self.store.get(rec.bottle_id))
|
||||
self.assertEqual(1, len(self.broker.launched))
|
||||
req = self.broker.launched[0]
|
||||
self.assertEqual("launch", req.op)
|
||||
self.assertEqual(rec.bottle_id, req.bottle_id)
|
||||
self.assertEqual("10.243.0.1", req.source_ip)
|
||||
self.assertEqual("sha256:abc", req.image_ref)
|
||||
self.assertEqual(2, req.slot)
|
||||
|
||||
def test_launch_then_attribute(self) -> None:
|
||||
rec = self.orch.launch_bottle("10.243.0.3")
|
||||
got = self.orch.attribute("10.243.0.3", rec.identity_token)
|
||||
assert got is not None
|
||||
self.assertEqual(rec.bottle_id, got.bottle_id)
|
||||
self.assertIsNone(self.orch.attribute("10.243.0.3", "wrong-token"))
|
||||
|
||||
def test_teardown_brokers_and_deregisters(self) -> None:
|
||||
rec = self.orch.launch_bottle("10.243.0.1")
|
||||
self.assertTrue(self.orch.teardown_bottle(rec.bottle_id))
|
||||
self.assertIsNone(self.store.get(rec.bottle_id))
|
||||
self.assertEqual(["teardown"], [r.op for r in self.broker.torn_down])
|
||||
|
||||
def test_teardown_unknown_is_false(self) -> None:
|
||||
self.assertFalse(self.orch.teardown_bottle("ghost"))
|
||||
|
||||
def test_launch_with_policy_is_resolvable(self) -> None:
|
||||
rec = self.orch.launch_bottle("10.243.0.1", policy='{"routes":[]}')
|
||||
got = self.orch.attribute("10.243.0.1", rec.identity_token)
|
||||
assert got is not None
|
||||
self.assertEqual('{"routes":[]}', got.policy)
|
||||
|
||||
def test_set_policy_live_reload(self) -> None:
|
||||
rec = self.orch.launch_bottle("10.243.0.3")
|
||||
self.assertTrue(self.orch.set_policy(rec.bottle_id, '{"x":1}'))
|
||||
got = self.orch.attribute("10.243.0.3", rec.identity_token)
|
||||
assert got is not None
|
||||
self.assertEqual('{"x":1}', got.policy)
|
||||
|
||||
def test_set_policy_unknown_is_false(self) -> None:
|
||||
self.assertFalse(self.orch.set_policy("ghost", "{}"))
|
||||
|
||||
def test_resolve_by_source_ip_without_token(self) -> None:
|
||||
rec = self.orch.launch_bottle("10.243.0.1", policy="P")
|
||||
got = self.orch.resolve("10.243.0.1") # network-layer, no token
|
||||
assert got is not None
|
||||
self.assertEqual(rec.bottle_id, got.bottle_id)
|
||||
self.assertEqual("P", got.policy)
|
||||
|
||||
def test_resolve_with_token_stays_strict(self) -> None:
|
||||
rec = self.orch.launch_bottle("10.243.0.3")
|
||||
self.assertIsNotNone(self.orch.resolve("10.243.0.3", rec.identity_token))
|
||||
self.assertIsNone(self.orch.resolve("10.243.0.3", "wrong-token"))
|
||||
|
||||
def test_launch_rolls_back_registry_on_broker_failure(self) -> None:
|
||||
orch = Orchestrator(self.store, _FailingBroker(self.secret), self.secret)
|
||||
with self.assertRaises(RuntimeError):
|
||||
orch.launch_bottle("10.243.0.9")
|
||||
self.assertEqual([], self.store.all()) # no orphan
|
||||
|
||||
def test_gateway_unconfigured_by_default(self) -> None:
|
||||
self.assertEqual({"configured": False}, self.orch.gateway_status())
|
||||
self.orch.ensure_gateway() # no-op, must not raise
|
||||
|
||||
def test_gateway_wired_and_ensured(self) -> None:
|
||||
sc = _FakeGateway()
|
||||
orch = Orchestrator(self.store, self.broker, self.secret, gateway=sc)
|
||||
self.assertEqual(
|
||||
{"configured": True, "name": "fake-gateway", "running": False},
|
||||
orch.gateway_status(),
|
||||
)
|
||||
orch.ensure_gateway()
|
||||
self.assertEqual(1, sc.built) # ensure_gateway builds first,
|
||||
self.assertEqual(1, sc.ensured) # then runs
|
||||
self.assertEqual(
|
||||
{"configured": True, "name": "fake-gateway", "running": True},
|
||||
orch.gateway_status(),
|
||||
)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,107 @@
|
||||
"""Unit tests for the gateway-side PolicyResolver (PRD 0070). HTTP mocked."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import unittest
|
||||
import urllib.error
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
from bot_bottle.policy_resolver import PolicyResolveError, PolicyResolver
|
||||
|
||||
_URLOPEN = "bot_bottle.policy_resolver.urllib.request.urlopen"
|
||||
|
||||
|
||||
def _resp(payload: object) -> MagicMock:
|
||||
"""A urlopen() return value: a context manager whose read() yields JSON."""
|
||||
m = MagicMock()
|
||||
m.__enter__.return_value.read.return_value = json.dumps(payload).encode()
|
||||
return m
|
||||
|
||||
|
||||
def _http_error(code: int) -> urllib.error.HTTPError:
|
||||
return urllib.error.HTTPError("http://x/resolve", code, "err", {}, None) # type: ignore[arg-type]
|
||||
|
||||
|
||||
class TestPolicyResolver(unittest.TestCase):
|
||||
def setUp(self) -> None:
|
||||
self.r = PolicyResolver("http://orch:8080")
|
||||
|
||||
def test_resolve_returns_policy(self) -> None:
|
||||
with patch(_URLOPEN, return_value=_resp({"bottle_id": "b1", "policy": "P"})):
|
||||
self.assertEqual("P", self.r.resolve("10.243.0.1", "tok"))
|
||||
|
||||
def test_resolve_always_fetches_fresh(self) -> None:
|
||||
# No cache — every resolve hits the orchestrator so revocations /
|
||||
# policy changes are honored immediately.
|
||||
with patch(_URLOPEN, return_value=_resp({"policy": "P"})) as m:
|
||||
self.r.resolve("10.243.0.1", "tok")
|
||||
self.r.resolve("10.243.0.1", "tok")
|
||||
self.assertEqual(2, m.call_count)
|
||||
|
||||
def test_unattributed_403_is_none_fail_closed(self) -> None:
|
||||
with patch(_URLOPEN, side_effect=_http_error(403)):
|
||||
self.assertIsNone(self.r.resolve("10.243.0.9", "tok"))
|
||||
|
||||
def test_other_http_error_raises(self) -> None:
|
||||
with patch(_URLOPEN, side_effect=_http_error(500)):
|
||||
with self.assertRaises(PolicyResolveError):
|
||||
self.r.resolve("10.243.0.1", "tok")
|
||||
|
||||
def test_unreachable_raises(self) -> None:
|
||||
with patch(_URLOPEN, side_effect=urllib.error.URLError("refused")):
|
||||
with self.assertRaises(PolicyResolveError):
|
||||
self.r.resolve("10.243.0.1", "tok")
|
||||
|
||||
def test_missing_policy_field_is_empty(self) -> None:
|
||||
with patch(_URLOPEN, return_value=_resp({"bottle_id": "b1"})):
|
||||
self.assertEqual("", self.r.resolve("10.243.0.1", "tok"))
|
||||
|
||||
def test_posts_source_ip_and_token(self) -> None:
|
||||
with patch(_URLOPEN, return_value=_resp({"policy": "P"})) as m:
|
||||
self.r.resolve("10.243.0.7", "the-token")
|
||||
req = m.call_args.args[0]
|
||||
self.assertTrue(req.full_url.endswith("/resolve"))
|
||||
sent = json.loads(req.data)
|
||||
self.assertEqual("10.243.0.7", sent["source_ip"])
|
||||
self.assertEqual("the-token", sent["identity_token"])
|
||||
|
||||
def test_resolve_without_token_sends_empty(self) -> None:
|
||||
with patch(_URLOPEN, return_value=_resp({"policy": "P"})) as m:
|
||||
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