feat(orchestrator): per-host consolidated orchestrator + multi-tenant gateway (PRD 0070) #380

Merged
didericis merged 45 commits from orchestrator-cutover into main 2026-07-14 03:35:46 -04:00
12 changed files with 225 additions and 25 deletions
Showing only changes of commit 2cbb178f88 - Show all commits
+1
View File
@@ -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
+44 -4
View File
@@ -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:
+30
View File
@@ -413,6 +413,34 @@ 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 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
if not policy:
return Config(routes=()) # unattributed or empty → deny-all
try:
return load_config(policy)
except ValueError:
return Config(routes=()) # unparseable policy → deny
# ---------------------------------------------------------------------------
# Match evaluation
# ---------------------------------------------------------------------------
@@ -804,6 +832,8 @@ __all__ = [
"is_git_push_request",
"is_git_fetch_request",
"load_config",
"resolve_client_config",
"PolicyResolverLike",
"match_route",
"outbound_scan_headers",
"parse_config",
+18 -6
View File
@@ -107,7 +107,7 @@ def dispatch( # pylint: disable=too-many-return-statements,too-many-branches
return 200, {"torn_down": True}
return 404, {"error": "no such bottle"}
if method == "POST" and route in ("/attribute", "/resolve"):
if method == "POST" and route == "/attribute":
try:
data = _parse_json_object(body)
except ValueError as e:
@@ -119,13 +119,25 @@ def dispatch( # pylint: disable=too-many-return-statements,too-many-branches
rec = orch.attribute(source_ip, token)
if rec is None:
return 403, {"error": "unattributed"}
# /attribute is the lightweight identity check; /resolve additionally
# returns the bottle's policy — the source-IP-keyed lookup the
# multi-tenant sidecar makes per request.
if route == "/resolve":
return 200, {"bottle_id": rec.bottle_id, "policy": rec.policy}
return 200, {"bottle_id": rec.bottle_id}
if method == "POST" and route == "/resolve":
# The per-request lookup the multi-tenant sidecar 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"}
+18 -9
View File
@@ -212,14 +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 sidecar; pair with the
identity token (`attribute`) elsewhere."""
with self._connect() as conn:
rows = conn.execute(
"SELECT * FROM orchestrator_bottles "
@@ -228,7 +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
+12 -3
View File
@@ -79,11 +79,20 @@ class Orchestrator:
return True
def attribute(self, source_ip: str, identity_token: str) -> BottleRecord | None:
"""Fail-closed attribution (delegates to the registry). The returned
record carries the bottle's `policy` — this is the source-IP-keyed
resolution the multi-tenant sidecar makes per request."""
"""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 sidecar 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
sidecar-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 sidecar policy in place (live reload). False if
the bottle is unknown."""
+4 -3
View File
@@ -47,11 +47,12 @@ class PolicyResolver:
self._base = base_url.rstrip("/")
self._timeout = timeout
def resolve(self, source_ip: str, identity_token: str) -> str | None:
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. Raises `PolicyResolveError` if the
orchestrator can't be reached / errors."""
are honored immediately. `identity_token` is optional omit it to
resolve by source IP alone (the network-layer attribution).
Raises `PolicyResolveError` if the orchestrator can't be reached."""
body = json.dumps(
{"source_ip": source_ip, "identity_token": identity_token}
).encode()
+53
View File
@@ -0,0 +1,53 @@
"""Unit: resolve_client_config — fail-closed per-client egress config (PRD 0070)."""
from __future__ import annotations
import unittest
from bot_bottle.egress_addon_core import resolve_client_config
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])
if __name__ == "__main__":
unittest.main()
@@ -171,6 +171,22 @@ class TestDispatch(unittest.TestCase):
)
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:
+12
View File
@@ -121,6 +121,18 @@ class TestRegistryStore(unittest.TestCase):
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()
+12
View File
@@ -102,6 +102,18 @@ class TestOrchestrator(unittest.TestCase):
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):
+5
View File
@@ -66,6 +66,11 @@ class TestPolicyResolver(unittest.TestCase):
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"])
if __name__ == "__main__":
unittest.main()