Compare commits
3 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 24df322c31 | |||
| 80d75de08a | |||
| 8827c64a83 |
+52
-29
@@ -32,7 +32,7 @@ from egress_addon_core import ( # type: ignore[import-not-found] # pylint: dis
|
|||||||
is_git_push_request,
|
is_git_push_request,
|
||||||
load_config,
|
load_config,
|
||||||
match_route,
|
match_route,
|
||||||
resolve_client_config,
|
resolve_client_context,
|
||||||
outbound_scan_headers,
|
outbound_scan_headers,
|
||||||
route_to_yaml_dict,
|
route_to_yaml_dict,
|
||||||
scan_inbound,
|
scan_inbound,
|
||||||
@@ -99,17 +99,29 @@ class EgressAddon:
|
|||||||
# Absent → single-tenant (static routes file); behaviour unchanged.
|
# Absent → single-tenant (static routes file); behaviour unchanged.
|
||||||
orch_url = os.environ.get(ORCHESTRATOR_URL_ENV, "").strip()
|
orch_url = os.environ.get(ORCHESTRATOR_URL_ENV, "").strip()
|
||||||
self._resolver = PolicyResolver(orch_url) if orch_url else None
|
self._resolver = PolicyResolver(orch_url) if orch_url else None
|
||||||
# Tokens the operator has approved this session (PRD 0062). In-memory
|
# Tokens the operator has approved this session (PRD 0062), keyed by
|
||||||
# only — a restart re-prompts. Mutated only from the asyncio loop that
|
# bottle so the shared gateway keeps each bottle's safelist separate —
|
||||||
# runs the addon hooks, so no lock is needed.
|
# a global set would let bottle A's approved secret pass bottle B's DLP
|
||||||
self.safe_tokens: set[str] = set()
|
# 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._supervise_slug = os.environ.get("SUPERVISE_BOTTLE_SLUG", "").strip()
|
||||||
self._token_allow_timeout = _token_allow_timeout_from_env(os.environ)
|
self._token_allow_timeout = _token_allow_timeout_from_env(os.environ)
|
||||||
self._reload(initial=True)
|
self._reload(initial=True)
|
||||||
self._install_sighup()
|
self._install_sighup()
|
||||||
|
|
||||||
def _supervise_available(self) -> bool:
|
@staticmethod
|
||||||
return bool(self._supervise_slug)
|
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:
|
def _reload(self, *, initial: bool = False) -> None:
|
||||||
try:
|
try:
|
||||||
@@ -218,19 +230,21 @@ class EgressAddon:
|
|||||||
+ "\n"
|
+ "\n"
|
||||||
)
|
)
|
||||||
|
|
||||||
def _active_config(self, flow: http.HTTPFlow) -> Config:
|
def _resolve_flow(self, flow: http.HTTPFlow) -> "tuple[Config, str]":
|
||||||
"""The Config to apply to this request. Single-tenant → the static
|
"""The `(Config, supervise slug)` to apply to this request. Single-tenant
|
||||||
`self.config`. Consolidated → the calling bottle's Config, resolved
|
→ the static `self.config` and the env slug. Consolidated → the calling
|
||||||
by source IP (fail-closed to deny-all if unattributed). The identity
|
bottle's Config and its bottle id, resolved by source IP in one
|
||||||
token, if the agent injected one, is read then stripped so it never
|
round-trip (fail-closed to deny-all + empty slug if unattributed). The
|
||||||
leaks upstream."""
|
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:
|
if self._resolver is None:
|
||||||
return self.config
|
return self.config, self._supervise_slug
|
||||||
conn = flow.client_conn
|
conn = flow.client_conn
|
||||||
client_ip = conn.peername[0] if conn and conn.peername else ""
|
client_ip = conn.peername[0] if conn and conn.peername else ""
|
||||||
token = flow.request.headers.get(IDENTITY_HEADER, "")
|
token = flow.request.headers.get(IDENTITY_HEADER, "")
|
||||||
flow.request.headers.pop(IDENTITY_HEADER, None)
|
flow.request.headers.pop(IDENTITY_HEADER, None)
|
||||||
return resolve_client_config(self._resolver, client_ip, token)
|
return resolve_client_context(self._resolver, client_ip, token)
|
||||||
|
|
||||||
async def request(self, flow: http.HTTPFlow) -> None:
|
async def request(self, flow: http.HTTPFlow) -> None:
|
||||||
request_path, _, query = flow.request.path.partition("?")
|
request_path, _, query = flow.request.path.partition("?")
|
||||||
@@ -239,14 +253,14 @@ class EgressAddon:
|
|||||||
self._serve_introspection(flow, request_path)
|
self._serve_introspection(flow, request_path)
|
||||||
return
|
return
|
||||||
|
|
||||||
config = self._active_config(flow)
|
config, slug = self._resolve_flow(flow)
|
||||||
|
|
||||||
# DLP outbound scan BEFORE stripping auth — catches tokens the
|
# DLP outbound scan BEFORE stripping auth — catches tokens the
|
||||||
# agent tried to smuggle in any header, path, query param, or body.
|
# agent tried to smuggle in any header, path, query param, or body.
|
||||||
# Hostname is included to catch DNS-tunnelling exfiltration attempts.
|
# Hostname is included to catch DNS-tunnelling exfiltration attempts.
|
||||||
route = match_route(config.routes, flow.request.pretty_host)
|
route = match_route(config.routes, flow.request.pretty_host)
|
||||||
if route is not None:
|
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
|
return
|
||||||
# The redact policy may have rewritten the request line; recompute
|
# The redact policy may have rewritten the request line; recompute
|
||||||
# the path/query the git checks below rely on.
|
# the path/query the git checks below rely on.
|
||||||
@@ -310,6 +324,7 @@ class EgressAddon:
|
|||||||
self,
|
self,
|
||||||
flow: http.HTTPFlow,
|
flow: http.HTTPFlow,
|
||||||
route: Route,
|
route: Route,
|
||||||
|
slug: str,
|
||||||
) -> bool:
|
) -> bool:
|
||||||
"""Scan the outbound request and apply the route's on-match policy
|
"""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
|
(PRD 0062). Returns True if the request may be forwarded, False if a
|
||||||
@@ -331,7 +346,7 @@ class EgressAddon:
|
|||||||
)
|
)
|
||||||
result = scan_outbound(
|
result = scan_outbound(
|
||||||
route, scan_text, os.environ,
|
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":
|
if result is None or result.severity != "block":
|
||||||
return True
|
return True
|
||||||
@@ -366,10 +381,10 @@ class EgressAddon:
|
|||||||
|
|
||||||
# supervise (default): hold the request for operator approval.
|
# supervise (default): hold the request for operator approval.
|
||||||
# Fall back to a hard 403 when supervise isn't wired for the bottle.
|
# 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)
|
self._block_dlp(flow, result)
|
||||||
return False
|
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:
|
if not approved:
|
||||||
return False # _supervise_token_block wrote the 403 response
|
return False # _supervise_token_block wrote the 403 response
|
||||||
# loop: the approved value is now in safe_tokens; re-scan.
|
# loop: the approved value is now in safe_tokens; re-scan.
|
||||||
@@ -412,12 +427,16 @@ class EgressAddon:
|
|||||||
flow: http.HTTPFlow,
|
flow: http.HTTPFlow,
|
||||||
request_path: str,
|
request_path: str,
|
||||||
result: ScanResult,
|
result: ScanResult,
|
||||||
|
slug: str,
|
||||||
) -> bool:
|
) -> bool:
|
||||||
"""Route a token DLP block to the operator's supervisor queue and wait.
|
"""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
|
`slug` attributes the proposal to the calling bottle (its own queue +
|
||||||
`self.safe_tokens` and the caller re-scans); False if the request must
|
safelist) — in the shared gateway this is what keeps one bottle's
|
||||||
be blocked (a 403 response has been written to `flow`)."""
|
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
|
host = flow.request.pretty_host
|
||||||
payload = build_token_allow_payload(
|
payload = build_token_allow_payload(
|
||||||
redact_tokens(host, env=os.environ),
|
redact_tokens(host, env=os.environ),
|
||||||
@@ -426,7 +445,7 @@ class EgressAddon:
|
|||||||
result,
|
result,
|
||||||
)
|
)
|
||||||
proposal = _sv.Proposal.new(
|
proposal = _sv.Proposal.new(
|
||||||
bottle_slug=self._supervise_slug,
|
bottle_slug=slug,
|
||||||
tool=_sv.TOOL_EGRESS_TOKEN_ALLOW,
|
tool=_sv.TOOL_EGRESS_TOKEN_ALLOW,
|
||||||
proposed_file=payload,
|
proposed_file=payload,
|
||||||
justification=_TOKEN_ALLOW_JUSTIFICATION,
|
justification=_TOKEN_ALLOW_JUSTIFICATION,
|
||||||
@@ -449,13 +468,13 @@ class EgressAddon:
|
|||||||
**self._req_ctx(flow),
|
**self._req_ctx(flow),
|
||||||
}) + "\n")
|
}) + "\n")
|
||||||
|
|
||||||
response = await self._await_token_response(proposal.id)
|
response = await self._await_token_response(proposal.id, slug)
|
||||||
_sv.archive_proposal(self._supervise_slug, proposal.id)
|
_sv.archive_proposal(slug, proposal.id)
|
||||||
|
|
||||||
if response is not None and response.status in (
|
if response is not None and response.status in (
|
||||||
_sv.STATUS_APPROVED, _sv.STATUS_MODIFIED,
|
_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:
|
if self.config.log >= LOG_BLOCKS:
|
||||||
sys.stderr.write(json.dumps({
|
sys.stderr.write(json.dumps({
|
||||||
"event": "egress_token_allowed",
|
"event": "egress_token_allowed",
|
||||||
@@ -478,6 +497,7 @@ class EgressAddon:
|
|||||||
async def _await_token_response(
|
async def _await_token_response(
|
||||||
self,
|
self,
|
||||||
proposal_id: str,
|
proposal_id: str,
|
||||||
|
slug: str,
|
||||||
) -> "_sv.Response | None":
|
) -> "_sv.Response | None":
|
||||||
"""Poll the DB for the operator's response without blocking the
|
"""Poll the DB for the operator's response without blocking the
|
||||||
proxy event loop. Returns the Response, or None on timeout."""
|
proxy event loop. Returns the Response, or None on timeout."""
|
||||||
@@ -485,7 +505,7 @@ class EgressAddon:
|
|||||||
deadline = loop.time() + self._token_allow_timeout
|
deadline = loop.time() + self._token_allow_timeout
|
||||||
while True:
|
while True:
|
||||||
try:
|
try:
|
||||||
return _sv.read_response(self._supervise_slug, proposal_id)
|
return _sv.read_response(slug, proposal_id)
|
||||||
except (OSError, ValueError, KeyError):
|
except (OSError, ValueError, KeyError):
|
||||||
# Not written yet, or a partial/malformed write — retry until
|
# Not written yet, or a partial/malformed write — retry until
|
||||||
# the deadline, then fail closed.
|
# the deadline, then fail closed.
|
||||||
@@ -539,6 +559,9 @@ class EgressAddon:
|
|||||||
"""
|
"""
|
||||||
if flow.websocket is None: # type: ignore[union-attr]
|
if flow.websocket is None: # type: ignore[union-attr]
|
||||||
return
|
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)
|
route = match_route(self.config.routes, flow.request.pretty_host)
|
||||||
if route is None:
|
if route is None:
|
||||||
return
|
return
|
||||||
@@ -549,7 +572,7 @@ class EgressAddon:
|
|||||||
# not an injection vector here — scan only for credential leakage.
|
# not an injection vector here — scan only for credential leakage.
|
||||||
result = scan_outbound(
|
result = scan_outbound(
|
||||||
route, content, os.environ,
|
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":
|
if result is not None and result.severity == "block":
|
||||||
sys.stderr.write(f"egress DLP: {result.reason}\n")
|
sys.stderr.write(f"egress DLP: {result.reason}\n")
|
||||||
|
|||||||
@@ -421,6 +421,18 @@ class PolicyResolverLike(typing.Protocol):
|
|||||||
...
|
...
|
||||||
|
|
||||||
|
|
||||||
|
def _config_from_policy(policy: "str | None") -> "Config":
|
||||||
|
"""Parse a resolved policy blob into a Config, fail-closed: None / empty /
|
||||||
|
unparseable all become a deny-all Config (no routes → every request
|
||||||
|
blocked)."""
|
||||||
|
if not policy:
|
||||||
|
return Config(routes=()) # unattributed or empty → deny-all
|
||||||
|
try:
|
||||||
|
return load_config(policy)
|
||||||
|
except ValueError:
|
||||||
|
return Config(routes=()) # unparseable policy → deny
|
||||||
|
|
||||||
|
|
||||||
def resolve_client_config(
|
def resolve_client_config(
|
||||||
resolver: PolicyResolverLike, client_ip: str, identity_token: str = ""
|
resolver: PolicyResolverLike, client_ip: str, identity_token: str = ""
|
||||||
) -> "Config":
|
) -> "Config":
|
||||||
@@ -433,12 +445,33 @@ def resolve_client_config(
|
|||||||
policy = resolver.resolve(client_ip, identity_token)
|
policy = resolver.resolve(client_ip, identity_token)
|
||||||
except Exception: # noqa: BLE001 # pylint: disable=broad-exception-caught
|
except Exception: # noqa: BLE001 # pylint: disable=broad-exception-caught
|
||||||
return Config(routes=()) # orchestrator unreachable/errored → deny
|
return Config(routes=()) # orchestrator unreachable/errored → deny
|
||||||
if not policy:
|
return _config_from_policy(policy)
|
||||||
return Config(routes=()) # unattributed or empty → deny-all
|
|
||||||
|
|
||||||
|
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:
|
try:
|
||||||
return load_config(policy)
|
policy, bottle_id = resolver.resolve_policy_and_bottle_id(client_ip, identity_token)
|
||||||
except ValueError:
|
except Exception: # noqa: BLE001 # pylint: disable=broad-exception-caught
|
||||||
return Config(routes=()) # unparseable policy → deny
|
return Config(routes=()), "" # orchestrator unreachable/errored → deny
|
||||||
|
return _config_from_policy(policy), (bottle_id or "")
|
||||||
|
|
||||||
|
|
||||||
# ---------------------------------------------------------------------------
|
# ---------------------------------------------------------------------------
|
||||||
@@ -833,7 +866,9 @@ __all__ = [
|
|||||||
"is_git_fetch_request",
|
"is_git_fetch_request",
|
||||||
"load_config",
|
"load_config",
|
||||||
"resolve_client_config",
|
"resolve_client_config",
|
||||||
|
"resolve_client_context",
|
||||||
"PolicyResolverLike",
|
"PolicyResolverLike",
|
||||||
|
"ContextResolverLike",
|
||||||
"match_route",
|
"match_route",
|
||||||
"outbound_scan_headers",
|
"outbound_scan_headers",
|
||||||
"parse_config",
|
"parse_config",
|
||||||
|
|||||||
@@ -188,6 +188,14 @@ class GitHttpHandler(BaseHTTPRequestHandler):
|
|||||||
"SERVER_PORT": str(self.server.server_port), # type: ignore
|
"SERVER_PORT": str(self.server.server_port), # type: ignore
|
||||||
"SERVER_PROTOCOL": self.request_version,
|
"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 (
|
for header, variable in (
|
||||||
("accept", "HTTP_ACCEPT"),
|
("accept", "HTTP_ACCEPT"),
|
||||||
("content-encoding", "HTTP_CONTENT_ENCODING"),
|
("content-encoding", "HTTP_CONTENT_ENCODING"),
|
||||||
|
|||||||
@@ -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",
|
||||||
|
]
|
||||||
@@ -100,5 +100,24 @@ class PolicyResolver:
|
|||||||
bottle_id = payload.get("bottle_id")
|
bottle_id = payload.get("bottle_id")
|
||||||
return bottle_id if isinstance(bottle_id, str) and bottle_id else None
|
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"]
|
__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
|
container creation by the backend's start step). SUPERVISE_DB_PATH
|
||||||
points at the bind-mounted host database.
|
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:
|
Speaks MCP over HTTP+JSON-RPC. Methods handled:
|
||||||
|
|
||||||
* `initialize` — handshake; returns server info + caps.
|
* `initialize` — handshake; returns server info + caps.
|
||||||
@@ -40,16 +46,18 @@ import time
|
|||||||
import typing
|
import typing
|
||||||
import urllib.error
|
import urllib.error
|
||||||
import urllib.request
|
import urllib.request
|
||||||
from dataclasses import dataclass
|
from dataclasses import dataclass, replace
|
||||||
|
|
||||||
try:
|
try:
|
||||||
# Same-directory imports inside the bundle container; these files are
|
# Same-directory imports inside the bundle container; these files are
|
||||||
# COPYed flat under /app by Dockerfile.sidecars.
|
# COPYed flat under /app by Dockerfile.sidecars.
|
||||||
from egress_addon_core import LOG_OFF, load_config
|
from egress_addon_core import LOG_OFF, load_config
|
||||||
|
from policy_resolver import PolicyResolveError, PolicyResolver
|
||||||
import supervise as _sv
|
import supervise as _sv
|
||||||
except ModuleNotFoundError:
|
except ModuleNotFoundError:
|
||||||
# Package imports for host-side tests and tooling.
|
# Package imports for host-side tests and tooling.
|
||||||
from .egress_addon_core import LOG_OFF, load_config
|
from .egress_addon_core import LOG_OFF, load_config
|
||||||
|
from .policy_resolver import PolicyResolveError, PolicyResolver
|
||||||
from . import supervise as _sv
|
from . import supervise as _sv
|
||||||
|
|
||||||
|
|
||||||
@@ -73,6 +81,12 @@ DEFAULT_RESPONSE_TIMEOUT_SECONDS = 30.0
|
|||||||
MIN_RESPONSE_POLL_INTERVAL_SECONDS = 0.05
|
MIN_RESPONSE_POLL_INTERVAL_SECONDS = 0.05
|
||||||
EGRESS_LIST_TIMEOUT_SECONDS = 5.0
|
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)
|
@dataclass(frozen=True)
|
||||||
class JsonRpcRequest:
|
class JsonRpcRequest:
|
||||||
@@ -511,9 +525,30 @@ class MCPHandler(http.server.BaseHTTPRequestHandler):
|
|||||||
if method == "tools/list":
|
if method == "tools/list":
|
||||||
return handle_tools_list(req.params)
|
return handle_tools_list(req.params)
|
||||||
if method == "tools/call":
|
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}")
|
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:
|
def _write_jsonrpc(self, body: bytes) -> None:
|
||||||
self.send_response(200)
|
self.send_response(200)
|
||||||
self.send_header("Content-Type", "application/json")
|
self.send_header("Content-Type", "application/json")
|
||||||
@@ -537,6 +572,9 @@ class MCPServer(socketserver.ThreadingMixIn, http.server.HTTPServer):
|
|||||||
allow_reuse_address = True
|
allow_reuse_address = True
|
||||||
daemon_threads = True
|
daemon_threads = True
|
||||||
config: ServerConfig = ServerConfig(bottle_slug="")
|
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 -----------------------------------------------------------
|
# --- Entry point -----------------------------------------------------------
|
||||||
@@ -548,15 +586,17 @@ def serve(
|
|||||||
port: int = _sv.SUPERVISE_PORT,
|
port: int = _sv.SUPERVISE_PORT,
|
||||||
bind: str = "0.0.0.0",
|
bind: str = "0.0.0.0",
|
||||||
response_timeout_seconds: float = DEFAULT_RESPONSE_TIMEOUT_SECONDS,
|
response_timeout_seconds: float = DEFAULT_RESPONSE_TIMEOUT_SECONDS,
|
||||||
|
resolver: "PolicyResolver | None" = None,
|
||||||
) -> typing.NoReturn:
|
) -> typing.NoReturn:
|
||||||
server = MCPServer((bind, port), MCPHandler)
|
server = MCPServer((bind, port), MCPHandler)
|
||||||
server.config = ServerConfig(
|
server.config = ServerConfig(
|
||||||
bottle_slug=bottle_slug,
|
bottle_slug=bottle_slug,
|
||||||
response_timeout_seconds=response_timeout_seconds,
|
response_timeout_seconds=response_timeout_seconds,
|
||||||
)
|
)
|
||||||
|
server.policy_resolver = resolver
|
||||||
|
mode = "multi-tenant" if resolver else f"slug={bottle_slug!r}"
|
||||||
sys.stderr.write(
|
sys.stderr.write(
|
||||||
f"supervise listening on {bind}:{port}; "
|
f"supervise listening on {bind}:{port}; {mode}; "
|
||||||
f"slug={bottle_slug!r}; "
|
|
||||||
f"tools: {', '.join(t['name'] for t in TOOL_DEFINITIONS)}\n" # type: ignore[arg-type]
|
f"tools: {', '.join(t['name'] for t in TOOL_DEFINITIONS)}\n" # type: ignore[arg-type]
|
||||||
)
|
)
|
||||||
sys.stderr.flush()
|
sys.stderr.flush()
|
||||||
@@ -571,8 +611,12 @@ def serve(
|
|||||||
|
|
||||||
def main(argv: list[str]) -> int:
|
def main(argv: list[str]) -> int:
|
||||||
del argv # config is env-only, no CLI flags
|
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", "")
|
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")
|
sys.stderr.write("supervise: SUPERVISE_BOTTLE_SLUG env is unset\n")
|
||||||
return 2
|
return 2
|
||||||
port = int(os.environ.get("SUPERVISE_PORT", str(_sv.SUPERVISE_PORT)))
|
port = int(os.environ.get("SUPERVISE_PORT", str(_sv.SUPERVISE_PORT)))
|
||||||
@@ -587,6 +631,7 @@ def main(argv: list[str]) -> int:
|
|||||||
port=port,
|
port=port,
|
||||||
bind=bind,
|
bind=bind,
|
||||||
response_timeout_seconds=response_timeout_seconds,
|
response_timeout_seconds=response_timeout_seconds,
|
||||||
|
resolver=resolver,
|
||||||
)
|
)
|
||||||
return 0 # serve() does not return
|
return 0 # serve() does not return
|
||||||
|
|
||||||
|
|||||||
@@ -46,7 +46,7 @@ def _addon() -> EgressAddon:
|
|||||||
"""Return a bare EgressAddon with LOG_FULL config and no routes file."""
|
"""Return a bare EgressAddon with LOG_FULL config and no routes file."""
|
||||||
a: EgressAddon = EgressAddon.__new__(EgressAddon)
|
a: EgressAddon = EgressAddon.__new__(EgressAddon)
|
||||||
a.config = Config(routes=(), log=LOG_FULL)
|
a.config = Config(routes=(), log=LOG_FULL)
|
||||||
a.safe_tokens = set()
|
a._safe_tokens = {}
|
||||||
a._supervise_slug = ""
|
a._supervise_slug = ""
|
||||||
a._token_allow_timeout = 300.0
|
a._token_allow_timeout = 300.0
|
||||||
return a
|
return a
|
||||||
|
|||||||
@@ -211,7 +211,7 @@ def _addon(config: Config) -> EgressAddon:
|
|||||||
"""Bare EgressAddon with a supplied config and no supervise wiring."""
|
"""Bare EgressAddon with a supplied config and no supervise wiring."""
|
||||||
a: EgressAddon = EgressAddon.__new__(EgressAddon)
|
a: EgressAddon = EgressAddon.__new__(EgressAddon)
|
||||||
a.config = config
|
a.config = config
|
||||||
a.safe_tokens = set()
|
a._safe_tokens = {}
|
||||||
a._supervise_slug = ""
|
a._supervise_slug = ""
|
||||||
a._token_allow_timeout = 300.0
|
a._token_allow_timeout = 300.0
|
||||||
a.routes_path = "/nonexistent/routes.yaml"
|
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]
|
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
|
# Introspection endpoint
|
||||||
# ---------------------------------------------------------------------------
|
# ---------------------------------------------------------------------------
|
||||||
@@ -418,7 +441,8 @@ class TestSuperviseBranch(unittest.TestCase):
|
|||||||
with patch.object(_ea_mod, "_sv", _fake_sv("approved")):
|
with patch.object(_ea_mod, "_sv", _fake_sv("approved")):
|
||||||
_run_request(addon, flow)
|
_run_request(addon, flow)
|
||||||
self.assertIsNone(flow.response) # forwarded after approval
|
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:
|
def test_operator_rejection_blocks(self) -> None:
|
||||||
addon = self._supervised_addon()
|
addon = self._supervised_addon()
|
||||||
@@ -735,5 +759,62 @@ class TestLogFullRequest(unittest.TestCase):
|
|||||||
self.assertTrue(any(e.get("event") == "egress_request" for e in logged))
|
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__":
|
if __name__ == "__main__":
|
||||||
unittest.main()
|
unittest.main()
|
||||||
|
|||||||
@@ -1,10 +1,10 @@
|
|||||||
"""Unit: resolve_client_config — fail-closed per-client egress config (PRD 0070)."""
|
"""Unit: fail-closed per-client egress resolution — config + context (PRD 0070)."""
|
||||||
|
|
||||||
from __future__ import annotations
|
from __future__ import annotations
|
||||||
|
|
||||||
import unittest
|
import unittest
|
||||||
|
|
||||||
from bot_bottle.egress_addon_core import resolve_client_config
|
from bot_bottle.egress_addon_core import resolve_client_config, resolve_client_context
|
||||||
from bot_bottle.policy_resolver import PolicyResolveError
|
from bot_bottle.policy_resolver import PolicyResolveError
|
||||||
|
|
||||||
|
|
||||||
@@ -49,5 +49,52 @@ class TestResolveClientConfig(unittest.TestCase):
|
|||||||
self.assertEqual(("10.243.0.1", "tok"), r.calls[0])
|
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__":
|
if __name__ == "__main__":
|
||||||
unittest.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
|
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):
|
class TestGitHttpBackend(unittest.TestCase):
|
||||||
def test_real_git_push_reaches_bare_repo(self):
|
def test_real_git_push_reaches_bare_repo(self):
|
||||||
from http.server import ThreadingHTTPServer
|
from http.server import ThreadingHTTPServer
|
||||||
@@ -94,6 +105,62 @@ class TestGitHttpBackend(unittest.TestCase):
|
|||||||
).strip()
|
).strip()
|
||||||
self.assertEqual(head, cloned)
|
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):
|
def test_post_forwards_git_cgi_headers(self):
|
||||||
from http.server import ThreadingHTTPServer
|
from http.server import ThreadingHTTPServer
|
||||||
|
|
||||||
|
|||||||
@@ -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()
|
||||||
@@ -88,6 +88,20 @@ class TestPolicyResolver(unittest.TestCase):
|
|||||||
with self.assertRaises(PolicyResolveError):
|
with self.assertRaises(PolicyResolveError):
|
||||||
self.r.resolve_bottle_id("10.243.0.1", "tok")
|
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__":
|
if __name__ == "__main__":
|
||||||
unittest.main()
|
unittest.main()
|
||||||
|
|||||||
@@ -6,6 +6,7 @@ import sys
|
|||||||
import tempfile
|
import tempfile
|
||||||
import threading
|
import threading
|
||||||
import time
|
import time
|
||||||
|
import types
|
||||||
import unittest
|
import unittest
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
from unittest.mock import patch
|
from unittest.mock import patch
|
||||||
@@ -629,5 +630,57 @@ class TestHttpEndToEnd(unittest.TestCase):
|
|||||||
conn.close()
|
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__":
|
if __name__ == "__main__":
|
||||||
unittest.main()
|
unittest.main()
|
||||||
|
|||||||
Reference in New Issue
Block a user