feat(orchestrator+egress): slice 8 — multi-tenant egress via the resolver (#352)
The egress addon now selects each request's Config by the calling bottle's
source IP, so one shared sidecar serves every bottle. Opt-in and fail-closed;
single-tenant behaviour is unchanged.
Orchestrator side (source-IP-primary attribution, per the PRD invariant):
* registry: `by_source_ip` (the single active bottle at a source IP —
network-layer attribution); `attribute` now composes it + the token.
* service: `resolve(source_ip, token="")` — with a token, strict
attribution; without, source IP alone.
* control_plane: `POST /resolve`'s identity_token is now OPTIONAL (absent
→ source-IP-only); split cleanly from the token-required `/attribute`.
* policy_resolver: `resolve` token now optional.
Egress side:
* egress_addon_core: `resolve_client_config(resolver, client_ip, token)` —
fetches + parses the client's Config, **fail-closed**: unattributed, a
resolver error, or an unparseable policy all yield deny-all (no routes).
Host-testable; `PolicyResolverLike` Protocol keeps it import-free.
* egress_addon: consolidated mode when `BOT_BOTTLE_ORCHESTRATOR_URL` is
set → `_active_config(flow)` resolves per client IP (reads + strips the
`x-bot-bottle-identity` header); `request()` uses it. Unset → the static
routes file, exactly as before. `PolicyResolver` added to the bundle.
Security note: source-IP-only resolution is safe where the IP is unspoofable
(Firecracker /31 + nft) AND the control plane is reachable only by the
trusted sidecar; the identity token, when the agent injects it, strengthens
it on weaker backends.
Scope note: the egress data plane is now multi-tenant. Remaining to be fully
live: the network topology routing every bottle's proxy to the one shared
sidecar, git-gate multitenancy, and agent-side identity-token injection.
Tests: registry by_source_ip; orchestrator resolve (with/without token);
control-plane /resolve token-optional; resolver token-optional;
resolve_client_config fail-closed matrix. All 182 egress tests still pass
(single-tenant unchanged). Full suite green.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WBMWTEtQdJ4W5UrWuLHCck
This commit is contained in:
@@ -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_config,
|
||||
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
|
||||
@@ -72,9 +88,17 @@ _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=())
|
||||
# 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). In-memory
|
||||
# only — a restart re-prompts. Mutated only from the asyncio loop that
|
||||
# runs the addon hooks, so no lock is needed.
|
||||
@@ -194,6 +218,20 @@ class EgressAddon:
|
||||
+ "\n"
|
||||
)
|
||||
|
||||
def _active_config(self, flow: http.HTTPFlow) -> Config:
|
||||
"""The Config to apply to this request. Single-tenant → the static
|
||||
`self.config`. Consolidated → the calling bottle's Config, resolved
|
||||
by source IP (fail-closed to deny-all if unattributed). The identity
|
||||
token, if the agent injected one, is read then stripped so it never
|
||||
leaks upstream."""
|
||||
if self._resolver is None:
|
||||
return self.config
|
||||
conn = flow.client_conn
|
||||
client_ip = conn.peername[0] if conn and conn.peername else ""
|
||||
token = flow.request.headers.get(IDENTITY_HEADER, "")
|
||||
flow.request.headers.pop(IDENTITY_HEADER, None)
|
||||
return resolve_client_config(self._resolver, client_ip, token)
|
||||
|
||||
async def request(self, flow: http.HTTPFlow) -> None:
|
||||
request_path, _, query = flow.request.path.partition("?")
|
||||
|
||||
@@ -201,10 +239,12 @@ class EgressAddon:
|
||||
self._serve_introspection(flow, request_path)
|
||||
return
|
||||
|
||||
config = self._active_config(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):
|
||||
return
|
||||
@@ -224,7 +264,7 @@ 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(
|
||||
@@ -242,7 +282,7 @@ class EgressAddon:
|
||||
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 +297,7 @@ 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:
|
||||
|
||||
Reference in New Issue
Block a user