Compare commits
10 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 77aaabae63 | |||
| d0b35b5506 | |||
| ea0c070cfe | |||
| 24df322c31 | |||
| 80d75de08a | |||
| 8827c64a83 | |||
| 115a64c161 | |||
| 08aef30d87 | |||
| e0b0429cd1 | |||
| d3e08cf039 |
@@ -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_addon_core.py /app/egress_addon_core.py
|
||||||
COPY bot_bottle/egress_dlp_config.py /app/egress_dlp_config.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/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/dlp_detectors.py /app/dlp_detectors.py
|
||||||
COPY bot_bottle/yaml_subset.py /app/yaml_subset.py
|
COPY bot_bottle/yaml_subset.py /app/yaml_subset.py
|
||||||
COPY bot_bottle/paths.py /app/paths.py
|
COPY bot_bottle/paths.py /app/paths.py
|
||||||
|
|||||||
@@ -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"]
|
||||||
+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
|
Loaded by `mitmdump -s /app/egress_addon.py` inside the
|
||||||
egress container."""
|
egress container."""
|
||||||
@@ -32,6 +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_context,
|
||||||
outbound_scan_headers,
|
outbound_scan_headers,
|
||||||
route_to_yaml_dict,
|
route_to_yaml_dict,
|
||||||
scan_inbound,
|
scan_inbound,
|
||||||
@@ -51,11 +52,26 @@ try:
|
|||||||
except ImportError: # pragma: no cover - host-side path
|
except ImportError: # pragma: no cover - host-side path
|
||||||
from bot_bottle import supervise as _sv # type: ignore[import-not-found]
|
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"
|
DEFAULT_ROUTES_PATH = "/etc/egress/routes.yaml"
|
||||||
|
|
||||||
INTROSPECT_HOST = "_egress.local"
|
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
|
# Seconds the egress proxy holds a token-blocked request open waiting for the
|
||||||
# operator's supervisor decision (PRD 0062), overridable via env.
|
# operator's supervisor decision (PRD 0062), overridable via env.
|
||||||
DEFAULT_TOKEN_ALLOW_TIMEOUT_SECONDS = 300.0
|
DEFAULT_TOKEN_ALLOW_TIMEOUT_SECONDS = 300.0
|
||||||
@@ -72,20 +88,40 @@ _TOKEN_ALLOW_JUSTIFICATION = (
|
|||||||
|
|
||||||
|
|
||||||
class EgressAddon:
|
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:
|
def __init__(self) -> None:
|
||||||
self.routes_path = os.environ.get("EGRESS_ROUTES", DEFAULT_ROUTES_PATH)
|
self.routes_path = os.environ.get("EGRESS_ROUTES", DEFAULT_ROUTES_PATH)
|
||||||
self.config: Config = Config(routes=())
|
self.config: Config = Config(routes=())
|
||||||
# Tokens the operator has approved this session (PRD 0062). In-memory
|
# Consolidated mode: resolve per-client Config from the orchestrator.
|
||||||
# only — a restart re-prompts. Mutated only from the asyncio loop that
|
# Absent → single-tenant (static routes file); behaviour unchanged.
|
||||||
# runs the addon hooks, so no lock is needed.
|
orch_url = os.environ.get(ORCHESTRATOR_URL_ENV, "").strip()
|
||||||
self.safe_tokens: set[str] = set()
|
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._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:
|
||||||
@@ -194,6 +230,22 @@ class EgressAddon:
|
|||||||
+ "\n"
|
+ "\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:
|
async def request(self, flow: http.HTTPFlow) -> None:
|
||||||
request_path, _, query = flow.request.path.partition("?")
|
request_path, _, query = flow.request.path.partition("?")
|
||||||
|
|
||||||
@@ -201,12 +253,14 @@ class EgressAddon:
|
|||||||
self._serve_introspection(flow, request_path)
|
self._serve_introspection(flow, request_path)
|
||||||
return
|
return
|
||||||
|
|
||||||
|
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(self.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.
|
||||||
@@ -224,7 +278,7 @@ class EgressAddon:
|
|||||||
|
|
||||||
if is_git_fetch_request(request_path, query):
|
if is_git_fetch_request(request_path, query):
|
||||||
git_decision = decide_git_fetch(
|
git_decision = decide_git_fetch(
|
||||||
self.config.routes, flow.request.pretty_host,
|
config.routes, flow.request.pretty_host,
|
||||||
)
|
)
|
||||||
if git_decision.action == "block":
|
if git_decision.action == "block":
|
||||||
self._block(
|
self._block(
|
||||||
@@ -235,14 +289,14 @@ class EgressAddon:
|
|||||||
return
|
return
|
||||||
|
|
||||||
# Strip agent-set Authorization after DLP scan so smuggled tokens
|
# 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)
|
flow.request.headers.pop("authorization", None)
|
||||||
|
|
||||||
# Build headers mapping for match evaluation
|
# Build headers mapping for match evaluation
|
||||||
req_headers = {k.lower(): v for k, v in flow.request.headers.items()}
|
req_headers = {k.lower(): v for k, v in flow.request.headers.items()}
|
||||||
|
|
||||||
decision = decide(
|
decision = decide(
|
||||||
self.config.routes,
|
config.routes,
|
||||||
flow.request.pretty_host,
|
flow.request.pretty_host,
|
||||||
request_path,
|
request_path,
|
||||||
os.environ,
|
os.environ,
|
||||||
@@ -257,7 +311,7 @@ class EgressAddon:
|
|||||||
if decision.inject_authorization is not None:
|
if decision.inject_authorization is not None:
|
||||||
flow.request.headers["authorization"] = decision.inject_authorization
|
flow.request.headers["authorization"] = decision.inject_authorization
|
||||||
|
|
||||||
if self.config.log >= LOG_FULL:
|
if config.log >= LOG_FULL:
|
||||||
self._log_request(flow)
|
self._log_request(flow)
|
||||||
|
|
||||||
def _block_dlp(self, flow: http.HTTPFlow, result: ScanResult) -> None:
|
def _block_dlp(self, flow: http.HTTPFlow, result: ScanResult) -> None:
|
||||||
@@ -270,6 +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
|
||||||
@@ -291,7 +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
|
||||||
@@ -326,10 +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.
|
||||||
@@ -372,12 +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),
|
||||||
@@ -386,7 +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,
|
||||||
@@ -409,13 +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",
|
||||||
@@ -438,6 +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."""
|
||||||
@@ -445,7 +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.
|
||||||
@@ -499,6 +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
|
||||||
@@ -509,7 +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")
|
||||||
|
|||||||
@@ -3,7 +3,7 @@
|
|||||||
Split out of `egress_addon.py` so the host's unit tests can
|
Split out of `egress_addon.py` so the host's unit tests can
|
||||||
exercise the parse + decision functions without depending on the
|
exercise the parse + decision functions without depending on the
|
||||||
`mitmproxy` package. The companion module wraps these with 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.
|
container.
|
||||||
|
|
||||||
Imports: stdlib + `yaml_subset` (which is itself stdlib-only and
|
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
|
from .yaml_subset import YamlSubsetError, parse_yaml_subset
|
||||||
|
|
||||||
# DLP detector-config parsing lives in a sibling module (also flat-bundled
|
# 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.
|
# `from egress_addon_core import ON_MATCH_*` callers keep working.
|
||||||
try:
|
try:
|
||||||
from egress_dlp_config import ( # type: ignore[import-not-found]
|
from egress_dlp_config import ( # type: ignore[import-not-found]
|
||||||
@@ -120,7 +120,7 @@ class ScanResult:
|
|||||||
reason: str
|
reason: str
|
||||||
location: str = "" # where the match was found, e.g. "body", "authorization header"
|
location: str = "" # where the match was found, e.g. "body", "authorization header"
|
||||||
context: str = "" # surrounding text with the match replaced by REDACT
|
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
|
# supervisor-approved "safe tokens" set (PRD 0062); never logged or written
|
||||||
# to a proposal file. Empty for structural detectors (CRLF) that carry no
|
# to a proposal file. Empty for structural detectors (CRLF) that carry no
|
||||||
# safelist-able value.
|
# safelist-able value.
|
||||||
@@ -413,6 +413,67 @@ def load_config(text: str) -> "Config":
|
|||||||
return parse_config(payload)
|
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
|
# Match evaluation
|
||||||
# ---------------------------------------------------------------------------
|
# ---------------------------------------------------------------------------
|
||||||
@@ -613,7 +674,7 @@ def outbound_scan_headers(
|
|||||||
) -> dict[str, str]:
|
) -> dict[str, str]:
|
||||||
"""Return request headers that should be included in outbound DLP.
|
"""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
|
Authorization header before forwarding. Scanning that header first
|
||||||
creates false positives for provider clients that insist on sending
|
creates false positives for provider clients that insist on sending
|
||||||
their own bearer-shaped placeholder, while still not changing what
|
their own bearer-shaped placeholder, while still not changing what
|
||||||
@@ -664,7 +725,7 @@ def scan_outbound(
|
|||||||
crlf_text: str | None = None,
|
crlf_text: str | None = None,
|
||||||
) -> ScanResult | None:
|
) -> ScanResult | None:
|
||||||
# Lazy import to avoid circular deps and keep dlp_detectors optional
|
# 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:
|
try:
|
||||||
from dlp_detectors import ( # type: ignore[import-not-found]
|
from dlp_detectors import ( # type: ignore[import-not-found]
|
||||||
scan_crlf_injection,
|
scan_crlf_injection,
|
||||||
@@ -804,6 +865,10 @@ __all__ = [
|
|||||||
"is_git_push_request",
|
"is_git_push_request",
|
||||||
"is_git_fetch_request",
|
"is_git_fetch_request",
|
||||||
"load_config",
|
"load_config",
|
||||||
|
"resolve_client_config",
|
||||||
|
"resolve_client_context",
|
||||||
|
"PolicyResolverLike",
|
||||||
|
"ContextResolverLike",
|
||||||
"match_route",
|
"match_route",
|
||||||
"outbound_scan_headers",
|
"outbound_scan_headers",
|
||||||
"parse_config",
|
"parse_config",
|
||||||
|
|||||||
@@ -46,6 +46,7 @@ from .git_gate_render import (
|
|||||||
git_gate_known_hosts_line,
|
git_gate_known_hosts_line,
|
||||||
git_gate_render_access_hook,
|
git_gate_render_access_hook,
|
||||||
git_gate_render_entrypoint,
|
git_gate_render_entrypoint,
|
||||||
|
git_gate_render_provision,
|
||||||
git_gate_render_gitconfig,
|
git_gate_render_gitconfig,
|
||||||
git_gate_render_hook,
|
git_gate_render_hook,
|
||||||
git_gate_upstreams_for_bottle,
|
git_gate_upstreams_for_bottle,
|
||||||
@@ -155,6 +156,7 @@ __all__ = [
|
|||||||
"git_gate_render_gitconfig",
|
"git_gate_render_gitconfig",
|
||||||
"git_gate_known_hosts_line",
|
"git_gate_known_hosts_line",
|
||||||
"git_gate_render_entrypoint",
|
"git_gate_render_entrypoint",
|
||||||
|
"git_gate_render_provision",
|
||||||
"git_gate_render_hook",
|
"git_gate_render_hook",
|
||||||
"git_gate_render_access_hook",
|
"git_gate_render_access_hook",
|
||||||
"provision_git_gate_dynamic_keys",
|
"provision_git_gate_dynamic_keys",
|
||||||
|
|||||||
@@ -9,6 +9,7 @@ own; `git_gate` re-exports these names for API stability."""
|
|||||||
|
|
||||||
from __future__ import annotations
|
from __future__ import annotations
|
||||||
|
|
||||||
|
import re
|
||||||
import shlex
|
import shlex
|
||||||
from dataclasses import dataclass
|
from dataclasses import dataclass
|
||||||
from pathlib import Path
|
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"
|
return f"{target} {key}\n"
|
||||||
|
|
||||||
|
|
||||||
def git_gate_render_entrypoint(upstreams: tuple[GitGateUpstream, ...]) -> str:
|
def _git_gate_init_repo_fn(repo_root: str, creds_dir: str) -> list[str]:
|
||||||
"""Posix-sh entrypoint. One `init_repo` call per upstream, then
|
"""The `init_repo` shell function, parameterized by the bare-repo root
|
||||||
`exec git daemon`. The function reads
|
and the per-bottle creds dir. Single source of the credential-wiring
|
||||||
`/git-gate/creds/<name>-{key,known_hosts}` (bind-mounted into
|
logic, shared by the single-tenant daemon entrypoint (`/git`,
|
||||||
the bundle by the renderer) and wires them into each bare repo's
|
`/git-gate/creds`) and the consolidated per-bottle provisioning
|
||||||
config; the access-hook + pre-receive hook pick those paths up
|
(`/git/<bottle_id>`, `/git-gate/creds/<bottle_id>`)."""
|
||||||
at fetch / push time."""
|
return [
|
||||||
lines = [
|
|
||||||
"#!/bin/sh",
|
|
||||||
"set -eu",
|
|
||||||
"",
|
|
||||||
"init_repo() {",
|
"init_repo() {",
|
||||||
" name=$1",
|
" name=$1",
|
||||||
" upstream_url=$2",
|
" upstream_url=$2",
|
||||||
" keyfile=/git-gate/creds/${name}-key",
|
f" keyfile={creds_dir}/${{name}}-key",
|
||||||
" hostsfile=/git-gate/creds/${name}-known_hosts",
|
f" hostsfile={creds_dir}/${{name}}-known_hosts",
|
||||||
"",
|
"",
|
||||||
# `|| true`: PRD 0018 chunk 3+ bind-mounts these RO from the
|
# `|| true`: PRD 0018 chunk 3+ bind-mounts these RO from the
|
||||||
# host, so chmod-syscalls fail with EROFS. The files already
|
# host, so chmod-syscalls fail with EROFS. The files already
|
||||||
@@ -153,14 +150,14 @@ def git_gate_render_entrypoint(upstreams: tuple[GitGateUpstream, ...]) -> str:
|
|||||||
" chmod 600 \"$hostsfile\" 2>/dev/null || true",
|
" chmod 600 \"$hostsfile\" 2>/dev/null || true",
|
||||||
" fi",
|
" fi",
|
||||||
"",
|
"",
|
||||||
" repo=/git/${name}.git",
|
f" repo={repo_root}/${{name}}.git",
|
||||||
" if [ ! -d \"$repo\" ]; then",
|
" if [ ! -d \"$repo\" ]; then",
|
||||||
" git init --bare \"$repo\" >/dev/null",
|
" git init --bare \"$repo\" >/dev/null",
|
||||||
# --mirror=fetch sets remote.origin.fetch = +refs/*:refs/* so",
|
# --mirror=fetch sets remote.origin.fetch = +refs/*:refs/* so a later
|
||||||
# a later `git fetch origin` mirrors the upstream's full ref",
|
# `git fetch origin` mirrors the upstream's full ref graph (heads,
|
||||||
# graph (heads, tags, notes) into the bare repo at canonical",
|
# tags, notes) into the bare repo at canonical paths. It does NOT set
|
||||||
# paths. It does NOT set remote.origin.mirror=true, so an",
|
# remote.origin.mirror=true, so an explicit `git push origin
|
||||||
# explicit `git push origin <ref>:<ref>` still pushes one ref.",
|
# <ref>:<ref>` still pushes one ref.
|
||||||
" git -C \"$repo\" remote add --mirror=fetch origin \"$upstream_url\"",
|
" git -C \"$repo\" remote add --mirror=fetch origin \"$upstream_url\"",
|
||||||
" fi",
|
" fi",
|
||||||
" git -C \"$repo\" config git-gate.identityFile \"$keyfile\"",
|
" git -C \"$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",
|
" git -C \"$repo\" config http.receivepack true",
|
||||||
" install -m 755 /etc/git-gate/pre-receive \"$repo/hooks/pre-receive\"",
|
" 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:
|
for u in upstreams:
|
||||||
lines.append(f"init_repo {shlex.quote(u.name)} {shlex.quote(u.upstream_url)}")
|
lines.append(f"init_repo {shlex.quote(u.name)} {shlex.quote(u.upstream_url)}")
|
||||||
lines.extend([
|
lines.extend([
|
||||||
@@ -190,6 +197,35 @@ def git_gate_render_entrypoint(upstreams: tuple[GitGateUpstream, ...]) -> str:
|
|||||||
return "\n".join(lines) + "\n"
|
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:
|
def git_gate_render_hook() -> str:
|
||||||
"""The shared pre-receive hook: gitleaks-scan all incoming refs,
|
"""The shared pre-receive hook: gitleaks-scan all incoming refs,
|
||||||
then forward each accepted ref to the real upstream (`origin`)
|
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
|
wrapper serves the same `/git/*.git` bare repos through
|
||||||
`git http-backend`, so pre-receive and upstream forwarding remain the
|
`git http-backend`, so pre-receive and upstream forwarding remain the
|
||||||
git-gate enforcement point.
|
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
|
from __future__ import annotations
|
||||||
@@ -13,13 +22,86 @@ from __future__ import annotations
|
|||||||
import os
|
import os
|
||||||
import subprocess
|
import subprocess
|
||||||
import sys
|
import sys
|
||||||
|
import typing
|
||||||
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
from urllib.parse import urlsplit
|
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
|
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
|
# Mirrors git_gate_render.GIT_GATE_TIMEOUT_SECS. Duplicated rather than
|
||||||
# imported: this module ships as a flat top-level sibling in the sidecar
|
# 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
|
# bundle image (see Dockerfile.sidecars), not as part of the bot_bottle
|
||||||
@@ -40,10 +122,25 @@ class GitHttpHandler(BaseHTTPRequestHandler):
|
|||||||
def do_POST(self) -> None:
|
def do_POST(self) -> None:
|
||||||
self._run_backend()
|
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:
|
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)
|
parsed = urlsplit(self.path)
|
||||||
if self._is_upload_pack(parsed.path, parsed.query):
|
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:
|
if repo_dir is None:
|
||||||
self.send_error(404)
|
self.send_error(404)
|
||||||
return
|
return
|
||||||
@@ -77,7 +174,7 @@ class GitHttpHandler(BaseHTTPRequestHandler):
|
|||||||
return
|
return
|
||||||
env = os.environ.copy()
|
env = os.environ.copy()
|
||||||
env.update({
|
env.update({
|
||||||
"GIT_PROJECT_ROOT": os.environ.get("GIT_PROJECT_ROOT", "/git"),
|
"GIT_PROJECT_ROOT": str(sandbox_root),
|
||||||
"GIT_HTTP_EXPORT_ALL": "1",
|
"GIT_HTTP_EXPORT_ALL": "1",
|
||||||
"REQUEST_METHOD": self.command,
|
"REQUEST_METHOD": self.command,
|
||||||
"PATH_INFO": parsed.path,
|
"PATH_INFO": parsed.path,
|
||||||
@@ -91,6 +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"),
|
||||||
@@ -123,8 +228,8 @@ class GitHttpHandler(BaseHTTPRequestHandler):
|
|||||||
)
|
)
|
||||||
self._write_cgi_response(proc.stdout)
|
self._write_cgi_response(proc.stdout)
|
||||||
|
|
||||||
def _repo_dir(self, path: str) -> Path | None:
|
def _repo_dir(self, sandbox_root: Path, path: str) -> Path | None:
|
||||||
root = Path(os.environ.get("GIT_PROJECT_ROOT", "/git")).resolve()
|
root = sandbox_root.resolve()
|
||||||
relative = path.lstrip("/").split(".git", 1)[0] + ".git"
|
relative = path.lstrip("/").split(".git", 1)[0] + ".git"
|
||||||
candidate = (root / relative).resolve()
|
candidate = (root / relative).resolve()
|
||||||
if root not in (candidate, *candidate.parents):
|
if root not in (candidate, *candidate.parents):
|
||||||
@@ -181,7 +286,13 @@ class GitHttpHandler(BaseHTTPRequestHandler):
|
|||||||
def main() -> int:
|
def main() -> int:
|
||||||
port = int(os.environ.get("GIT_HTTP_PORT", str(DEFAULT_PORT)))
|
port = int(os.environ.get("GIT_HTTP_PORT", str(DEFAULT_PORT)))
|
||||||
server = ThreadingHTTPServer(("0.0.0.0", port), GitHttpHandler)
|
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()
|
sys.stdout.flush()
|
||||||
server.serve_forever()
|
server.serve_forever()
|
||||||
return 0
|
return 0
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
"""Per-host orchestrator service (PRD 0070).
|
"""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
|
(egress / git-gate / supervise), coordinate with the console, and broker
|
||||||
agent launches. This package is being built bottom-up, starting with the
|
agent launches. This package is being built bottom-up, starting with the
|
||||||
backend-neutral "consolidation core" that needs no VM packaging:
|
backend-neutral "consolidation core" that needs no VM packaging:
|
||||||
@@ -10,15 +10,15 @@ backend-neutral "consolidation core" that needs no VM packaging:
|
|||||||
* `broker` — the signed, structured launch-request contract + a
|
* `broker` — the signed, structured launch-request contract + a
|
||||||
`LaunchBroker` (stub for the harness) that verifies
|
`LaunchBroker` (stub for the harness) that verifies
|
||||||
provenance before acting.
|
provenance before acting.
|
||||||
* `sidecar` — the consolidated per-host sidecar: a `Sidecar`
|
* `gateway` — the consolidated per-host gateway: a `Gateway`
|
||||||
lifecycle contract (idempotent singleton) + a
|
lifecycle contract (idempotent singleton) + a
|
||||||
`DockerSidecar` impl. One sidecar shared by all
|
`DockerGateway` impl. One gateway shared by all
|
||||||
bottles instead of one per bottle.
|
bottles instead of one per bottle.
|
||||||
* `service` — the `Orchestrator`: owns the registry, brokers the
|
* `service` — the `Orchestrator`: owns the registry, brokers the
|
||||||
launch lifecycle (launch/teardown), manages the
|
launch lifecycle (launch/teardown), manages the
|
||||||
shared sidecar, attributes.
|
shared gateway, attributes.
|
||||||
* `control_plane` — the HTTP control-plane RPC (launch / teardown /
|
* `control_plane` — the HTTP control-plane RPC (launch / teardown /
|
||||||
list / attribute / sidecar / health).
|
list / attribute / gateway / health).
|
||||||
|
|
||||||
The actual backend-native launch (a real docker/firecracker broker) and
|
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
|
the egress/git/supervise data plane land in later slices once this core is
|
||||||
@@ -38,7 +38,7 @@ from .broker import (
|
|||||||
verify_request,
|
verify_request,
|
||||||
)
|
)
|
||||||
from .docker_broker import DockerBroker, DockerBrokerError
|
from .docker_broker import DockerBroker, DockerBrokerError
|
||||||
from .sidecar import DockerSidecar, Sidecar, SidecarError
|
from .gateway import DockerGateway, Gateway, GatewayError
|
||||||
from .service import Orchestrator
|
from .service import Orchestrator
|
||||||
from .control_plane import ControlPlaneServer, dispatch, make_server
|
from .control_plane import ControlPlaneServer, dispatch, make_server
|
||||||
|
|
||||||
@@ -52,9 +52,9 @@ __all__ = [
|
|||||||
"StubBroker",
|
"StubBroker",
|
||||||
"DockerBroker",
|
"DockerBroker",
|
||||||
"DockerBrokerError",
|
"DockerBrokerError",
|
||||||
"Sidecar",
|
"Gateway",
|
||||||
"DockerSidecar",
|
"DockerGateway",
|
||||||
"SidecarError",
|
"GatewayError",
|
||||||
"sign_request",
|
"sign_request",
|
||||||
"verify_request",
|
"verify_request",
|
||||||
"Orchestrator",
|
"Orchestrator",
|
||||||
|
|||||||
@@ -21,7 +21,7 @@ from .control_plane import make_server
|
|||||||
from .docker_broker import DockerBroker
|
from .docker_broker import DockerBroker
|
||||||
from .registry import RegistryStore, default_db_path
|
from .registry import RegistryStore, default_db_path
|
||||||
from .service import Orchestrator
|
from .service import Orchestrator
|
||||||
from .sidecar import DockerSidecar, Sidecar
|
from .gateway import DockerGateway, Gateway
|
||||||
|
|
||||||
|
|
||||||
def main(argv: list[str] | None = None) -> int:
|
def main(argv: list[str] | None = None) -> int:
|
||||||
@@ -38,7 +38,7 @@ def main(argv: list[str] | None = None) -> int:
|
|||||||
help="launch broker: 'stub' records requests; 'docker' runs containers",
|
help="launch broker: 'stub' records requests; 'docker' runs containers",
|
||||||
)
|
)
|
||||||
parser.add_argument(
|
parser.add_argument(
|
||||||
"--sidecar", action="store_true",
|
"--gateway", action="store_true",
|
||||||
help="run one consolidated per-host sidecar bundle (build-if-missing)",
|
help="run one consolidated per-host sidecar bundle (build-if-missing)",
|
||||||
)
|
)
|
||||||
args = parser.parse_args(argv)
|
args = parser.parse_args(argv)
|
||||||
@@ -51,14 +51,14 @@ def main(argv: list[str] | None = None) -> int:
|
|||||||
# anything; 'docker' runs real containers (firecracker drops in later).
|
# anything; 'docker' runs real containers (firecracker drops in later).
|
||||||
secret = secrets.token_bytes(32)
|
secret = secrets.token_bytes(32)
|
||||||
broker: LaunchBroker = DockerBroker(secret) if args.broker == "docker" else StubBroker(secret)
|
broker: LaunchBroker = DockerBroker(secret) if args.broker == "docker" else StubBroker(secret)
|
||||||
sidecar: Sidecar | None = DockerSidecar() if args.sidecar else None
|
gateway: Gateway | None = DockerGateway() if args.gateway else None
|
||||||
orchestrator = Orchestrator(registry, broker, secret, sidecar)
|
orchestrator = Orchestrator(registry, broker, secret, gateway)
|
||||||
|
|
||||||
# One persistent per-host sidecar, shared by every bottle: build the
|
# One persistent per-host gateway, shared by every bottle: build the
|
||||||
# bundle image if missing, then bring the singleton up (idempotent).
|
# bundle image if missing, then bring the singleton up (idempotent).
|
||||||
if sidecar is not None:
|
if gateway is not None:
|
||||||
orchestrator.ensure_sidecar()
|
orchestrator.ensure_gateway()
|
||||||
log.info("consolidated sidecar ensured", context={"name": sidecar.name})
|
log.info("consolidated gateway ensured", context={"name": gateway.name})
|
||||||
|
|
||||||
server = make_server(orchestrator, host=args.host, port=args.port)
|
server = make_server(orchestrator, host=args.host, port=args.port)
|
||||||
bound_host, bound_port = server.server_address[0], server.server_address[1]
|
bound_host, bound_port = server.server_address[0], server.server_address[1]
|
||||||
|
|||||||
@@ -9,7 +9,7 @@ The request it sends is:
|
|||||||
request can't be coerced into launching an arbitrary payload; and
|
request can't be coerced into launching an arbitrary payload; and
|
||||||
* **signed** — wrapped as a compact JWS/JWT the broker verifies before
|
* **signed** — wrapped as a compact JWS/JWT the broker verifies before
|
||||||
acting, so a *compromised co-located component* (an agent-facing
|
acting, so a *compromised co-located component* (an agent-facing
|
||||||
sidecar, say) can't forge a launch. This is the concrete form of the
|
gateway, say) can't forge a launch. This is the concrete form of the
|
||||||
"structured requests only" rule in the PRD security review.
|
"structured requests only" rule in the PRD security review.
|
||||||
|
|
||||||
Signing is **HS256** over a secret shared by the orchestrator (signer) and
|
Signing is **HS256** over a secret shared by the orchestrator (signer) and
|
||||||
|
|||||||
@@ -5,7 +5,7 @@ The backend-agnostic control-plane RPC (CLI / console -> orchestrator) over
|
|||||||
vsock / unix-socket portability caveats):
|
vsock / unix-socket portability caveats):
|
||||||
|
|
||||||
GET /health -> 200 {"status": "ok"}
|
GET /health -> 200 {"status": "ok"}
|
||||||
GET /sidecar -> 200 {"configured", ["name","running"]}
|
GET /gateway -> 200 {"configured", ["name","running"]}
|
||||||
GET /bottles -> 200 {"bottles": [ <redacted record>, ...]}
|
GET /bottles -> 200 {"bottles": [ <redacted record>, ...]}
|
||||||
POST /bottles -> 201 {"bottle_id","identity_token"} (launch)
|
POST /bottles -> 201 {"bottle_id","identity_token"} (launch)
|
||||||
body: {"source_ip", ["image_ref"],
|
body: {"source_ip", ["image_ref"],
|
||||||
@@ -63,8 +63,8 @@ def dispatch( # pylint: disable=too-many-return-statements,too-many-branches
|
|||||||
if method == "GET" and route == "/health":
|
if method == "GET" and route == "/health":
|
||||||
return 200, {"status": "ok"}
|
return 200, {"status": "ok"}
|
||||||
|
|
||||||
if method == "GET" and route == "/sidecar":
|
if method == "GET" and route == "/gateway":
|
||||||
return 200, orch.sidecar_status()
|
return 200, orch.gateway_status()
|
||||||
|
|
||||||
if method == "GET" and route == "/bottles":
|
if method == "GET" and route == "/bottles":
|
||||||
return 200, {"bottles": [r.redacted() for r in orch.registry.all()]}
|
return 200, {"bottles": [r.redacted() for r in orch.registry.all()]}
|
||||||
@@ -107,7 +107,7 @@ def dispatch( # pylint: disable=too-many-return-statements,too-many-branches
|
|||||||
return 200, {"torn_down": True}
|
return 200, {"torn_down": True}
|
||||||
return 404, {"error": "no such bottle"}
|
return 404, {"error": "no such bottle"}
|
||||||
|
|
||||||
if method == "POST" and route in ("/attribute", "/resolve"):
|
if method == "POST" and route == "/attribute":
|
||||||
try:
|
try:
|
||||||
data = _parse_json_object(body)
|
data = _parse_json_object(body)
|
||||||
except ValueError as e:
|
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)
|
rec = orch.attribute(source_ip, token)
|
||||||
if rec is None:
|
if rec is None:
|
||||||
return 403, {"error": "unattributed"}
|
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}
|
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"}
|
return 404, {"error": "not found"}
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
@@ -1,18 +1,18 @@
|
|||||||
"""The consolidated per-host sidecar (PRD 0070).
|
"""The consolidated per-host gateway (PRD 0070).
|
||||||
|
|
||||||
The core consolidation win: **one** persistent sidecar per host, shared by
|
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
|
every bottle, instead of a sidecar bundle per bottle. It's safe to share
|
||||||
because the attribution invariant (source IP + identity token, see
|
because the attribution invariant (source IP + identity token, see
|
||||||
`registry`) lets the sidecar attribute each request to the right bottle —
|
`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.
|
so per-bottle policy lives in one long-lived process keyed on who's calling.
|
||||||
|
|
||||||
`Sidecar` is the backend-neutral lifecycle contract (mirrors `LaunchBroker`):
|
`Gateway` is the backend-neutral lifecycle contract (mirrors `LaunchBroker`):
|
||||||
ensure the single instance is up, report it, tear it down. `DockerSidecar`
|
ensure the single instance is up, report it, tear it down. `DockerGateway`
|
||||||
is the docker implementation; a firecracker sidecar VM slots in later.
|
is the docker implementation; a firecracker gateway VM slots in later.
|
||||||
|
|
||||||
The defining behaviour is **idempotent singleton**: `ensure_running` starts
|
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
|
the instance if absent and is a no-op if it's already up, so N bottle
|
||||||
launches never spawn N sidecars.
|
launches never spawn N gateways.
|
||||||
"""
|
"""
|
||||||
|
|
||||||
from __future__ import annotations
|
from __future__ import annotations
|
||||||
@@ -23,49 +23,49 @@ from pathlib import Path
|
|||||||
|
|
||||||
from ..docker_cmd import run_docker
|
from ..docker_cmd import run_docker
|
||||||
|
|
||||||
SIDECAR_NAME = "bot-bottle-orch-sidecar"
|
GATEWAY_NAME = "bot-bottle-orch-gateway"
|
||||||
SIDECAR_LABEL = "bot-bottle-orch-sidecar=1"
|
GATEWAY_LABEL = "bot-bottle-orch-gateway=1"
|
||||||
|
|
||||||
# The real sidecar-bundle image + its Dockerfile. Kept as a local constant
|
# The real sidecar-bundle image + its Dockerfile. Kept as a local constant
|
||||||
# rather than imported from backend.docker.sidecar_bundle, which would drag
|
# rather than imported from backend.docker.sidecar_bundle, which would drag
|
||||||
# the whole backend layer into the lean orchestrator (see #359); unify when
|
# the whole backend layer into the lean orchestrator (see #359); unify when
|
||||||
# that lands. Env override matches the backend's BOT_BOTTLE_SIDECAR_IMAGE.
|
# that lands. Env override matches the backend's BOT_BOTTLE_SIDECAR_IMAGE.
|
||||||
SIDECAR_BUNDLE_IMAGE = os.environ.get("BOT_BOTTLE_SIDECAR_IMAGE", "bot-bottle-sidecars:latest")
|
GATEWAY_IMAGE = os.environ.get("BOT_BOTTLE_SIDECAR_IMAGE", "bot-bottle-sidecars:latest")
|
||||||
SIDECAR_DOCKERFILE = "Dockerfile.sidecars"
|
GATEWAY_DOCKERFILE = "Dockerfile.sidecars"
|
||||||
_REPO_ROOT = Path(__file__).resolve().parents[2]
|
_REPO_ROOT = Path(__file__).resolve().parents[2]
|
||||||
|
|
||||||
|
|
||||||
class SidecarError(Exception):
|
class GatewayError(Exception):
|
||||||
"""The shared sidecar failed to build/start/stop (non-zero `docker` exit)."""
|
"""The shared gateway failed to build/start/stop (non-zero `docker` exit)."""
|
||||||
|
|
||||||
|
|
||||||
class Sidecar(abc.ABC):
|
class Gateway(abc.ABC):
|
||||||
"""Lifecycle of the single per-host sidecar. Backend-neutral."""
|
"""Lifecycle of the single per-host gateway. Backend-neutral."""
|
||||||
|
|
||||||
name: str
|
name: str
|
||||||
|
|
||||||
def ensure_built(self) -> None:
|
def ensure_built(self) -> None:
|
||||||
"""Ensure the sidecar's image / rootfs exists, building it if needed.
|
"""Ensure the gateway's image / rootfs exists, building it if needed.
|
||||||
Default: nothing to build (e.g. a stub or a pre-pulled image)."""
|
Default: nothing to build (e.g. a stub or a pre-pulled image)."""
|
||||||
return
|
return
|
||||||
|
|
||||||
@abc.abstractmethod
|
@abc.abstractmethod
|
||||||
def ensure_running(self) -> None:
|
def ensure_running(self) -> None:
|
||||||
"""Start the sidecar if it isn't already up. Idempotent: a no-op
|
"""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).
|
when it's already running (that's the whole point — one per host).
|
||||||
Assumes the image exists — call `ensure_built()` first."""
|
Assumes the image exists — call `ensure_built()` first."""
|
||||||
|
|
||||||
@abc.abstractmethod
|
@abc.abstractmethod
|
||||||
def is_running(self) -> bool:
|
def is_running(self) -> bool:
|
||||||
"""True iff the sidecar instance is currently up."""
|
"""True iff the gateway instance is currently up."""
|
||||||
|
|
||||||
@abc.abstractmethod
|
@abc.abstractmethod
|
||||||
def stop(self) -> None:
|
def stop(self) -> None:
|
||||||
"""Remove the sidecar. Idempotent — absent is success."""
|
"""Remove the gateway. Idempotent — absent is success."""
|
||||||
|
|
||||||
|
|
||||||
class DockerSidecar(Sidecar):
|
class DockerGateway(Gateway):
|
||||||
"""The consolidated sidecar as a single, fixed-name Docker container.
|
"""The consolidated gateway as a single, fixed-name Docker container.
|
||||||
|
|
||||||
`image_ref` defaults to the real sidecar-bundle image; `ensure_built`
|
`image_ref` defaults to the real sidecar-bundle image; `ensure_built`
|
||||||
builds it from `Dockerfile.sidecars` when it's missing. (Note: slice 5
|
builds it from `Dockerfile.sidecars` when it's missing. (Note: slice 5
|
||||||
@@ -74,11 +74,11 @@ class DockerSidecar(Sidecar):
|
|||||||
|
|
||||||
def __init__(
|
def __init__(
|
||||||
self,
|
self,
|
||||||
image_ref: str = SIDECAR_BUNDLE_IMAGE,
|
image_ref: str = GATEWAY_IMAGE,
|
||||||
*,
|
*,
|
||||||
name: str = SIDECAR_NAME,
|
name: str = GATEWAY_NAME,
|
||||||
build_context: Path | None = None,
|
build_context: Path | None = None,
|
||||||
dockerfile: str | None = SIDECAR_DOCKERFILE,
|
dockerfile: str | None = GATEWAY_DOCKERFILE,
|
||||||
) -> None:
|
) -> None:
|
||||||
self.image_ref = image_ref
|
self.image_ref = image_ref
|
||||||
self.name = name
|
self.name = name
|
||||||
@@ -101,7 +101,7 @@ class DockerSidecar(Sidecar):
|
|||||||
str(self._build_context),
|
str(self._build_context),
|
||||||
])
|
])
|
||||||
if proc.returncode != 0:
|
if proc.returncode != 0:
|
||||||
raise SidecarError(f"sidecar image build failed: {proc.stderr.strip()}")
|
raise GatewayError(f"gateway image build failed: {proc.stderr.strip()}")
|
||||||
|
|
||||||
def is_running(self) -> bool:
|
def is_running(self) -> bool:
|
||||||
proc = run_docker([
|
proc = run_docker([
|
||||||
@@ -121,19 +121,19 @@ class DockerSidecar(Sidecar):
|
|||||||
proc = run_docker([
|
proc = run_docker([
|
||||||
"docker", "run", "--detach",
|
"docker", "run", "--detach",
|
||||||
"--name", self.name,
|
"--name", self.name,
|
||||||
"--label", SIDECAR_LABEL,
|
"--label", GATEWAY_LABEL,
|
||||||
self.image_ref,
|
self.image_ref,
|
||||||
])
|
])
|
||||||
if proc.returncode != 0:
|
if proc.returncode != 0:
|
||||||
raise SidecarError(f"sidecar failed to start: {proc.stderr.strip()}")
|
raise GatewayError(f"gateway failed to start: {proc.stderr.strip()}")
|
||||||
|
|
||||||
def stop(self) -> None:
|
def stop(self) -> None:
|
||||||
proc = run_docker(["docker", "rm", "--force", self.name])
|
proc = run_docker(["docker", "rm", "--force", self.name])
|
||||||
if proc.returncode != 0 and "No such container" not in proc.stderr:
|
if proc.returncode != 0 and "No such container" not in proc.stderr:
|
||||||
raise SidecarError(f"sidecar failed to stop: {proc.stderr.strip()}")
|
raise GatewayError(f"gateway failed to stop: {proc.stderr.strip()}")
|
||||||
|
|
||||||
|
|
||||||
__all__ = [
|
__all__ = [
|
||||||
"Sidecar", "DockerSidecar", "SidecarError",
|
"Gateway", "DockerGateway", "GatewayError",
|
||||||
"SIDECAR_NAME", "SIDECAR_LABEL", "SIDECAR_BUNDLE_IMAGE",
|
"GATEWAY_NAME", "GATEWAY_LABEL", "GATEWAY_IMAGE",
|
||||||
]
|
]
|
||||||
@@ -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"]
|
||||||
@@ -67,9 +67,9 @@ class BottleRecord:
|
|||||||
# Opaque JSON blob for forward-compat (pool slot, ...) — the registry
|
# Opaque JSON blob for forward-compat (pool slot, ...) — the registry
|
||||||
# doesn't interpret it, so new fields need no migration.
|
# doesn't interpret it, so new fields need no migration.
|
||||||
metadata: str = ""
|
metadata: str = ""
|
||||||
# The bottle's sidecar policy (opaque JSON — egress allowlist / routes /
|
# The bottle's gateway policy (opaque JSON — egress allowlist / routes /
|
||||||
# git config). The registry stores and serves it verbatim, keyed by
|
# git config). The registry stores and serves it verbatim, keyed by
|
||||||
# source IP; the multi-tenant sidecar interprets it.
|
# source IP; the multi-tenant gateway interprets it.
|
||||||
policy: str = ""
|
policy: str = ""
|
||||||
|
|
||||||
def redacted(self) -> dict[str, object]:
|
def redacted(self) -> dict[str, object]:
|
||||||
@@ -102,9 +102,9 @@ _MIGRATIONS = TableMigrations(
|
|||||||
# the "one active bottle per source IP" check cheap.
|
# the "one active bottle per source IP" check cheap.
|
||||||
"CREATE INDEX IF NOT EXISTS idx_orchestrator_bottles_source_ip "
|
"CREATE INDEX IF NOT EXISTS idx_orchestrator_bottles_source_ip "
|
||||||
"ON orchestrator_bottles (source_ip)",
|
"ON orchestrator_bottles (source_ip)",
|
||||||
# v3 — per-bottle policy (opaque JSON the sidecar interprets): the
|
# v3 — per-bottle policy (opaque JSON the gateway interprets): the
|
||||||
# egress allowlist / routes / git config selected by source IP. The
|
# egress allowlist / routes / git config selected by source IP. The
|
||||||
# multi-tenant sidecar resolves it per request via `attribute`.
|
# multi-tenant gateway resolves it per request via `attribute`.
|
||||||
"ALTER TABLE orchestrator_bottles ADD COLUMN policy TEXT NOT NULL DEFAULT ''",
|
"ALTER TABLE orchestrator_bottles ADD COLUMN policy TEXT NOT NULL DEFAULT ''",
|
||||||
],
|
],
|
||||||
)
|
)
|
||||||
@@ -212,14 +212,13 @@ class RegistryStore(DbStore):
|
|||||||
).fetchall()
|
).fetchall()
|
||||||
return [_row_to_record(r) for r in rows]
|
return [_row_to_record(r) for r in rows]
|
||||||
|
|
||||||
def attribute(self, source_ip: str, identity_token: str) -> BottleRecord | None:
|
def by_source_ip(self, source_ip: str) -> BottleRecord | None:
|
||||||
"""Fail-closed attribution. Returns the bottle only when exactly one
|
"""Network-layer attribution: the single active bottle at this source
|
||||||
active record has this source IP AND its identity token matches
|
IP, or None if unknown or ambiguous (more than one — a
|
||||||
(constant-time). Either signal alone is insufficient: an unknown IP,
|
misconfiguration). Safe as the *sole* attributor only where the
|
||||||
an ambiguous IP (more than one active bottle — a misconfiguration),
|
source IP is unspoofable (Firecracker `/31` + nft) and the control
|
||||||
an empty token, or a token mismatch all deny."""
|
plane is reachable only by the trusted gateway; pair with the
|
||||||
if not identity_token:
|
identity token (`attribute`) elsewhere."""
|
||||||
return None
|
|
||||||
with self._connect() as conn:
|
with self._connect() as conn:
|
||||||
rows = conn.execute(
|
rows = conn.execute(
|
||||||
"SELECT * FROM orchestrator_bottles "
|
"SELECT * FROM orchestrator_bottles "
|
||||||
@@ -228,7 +227,17 @@ class RegistryStore(DbStore):
|
|||||||
).fetchall()
|
).fetchall()
|
||||||
if len(rows) != 1:
|
if len(rows) != 1:
|
||||||
return None
|
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):
|
if not hmac.compare_digest(rec.identity_token, identity_token):
|
||||||
return None
|
return None
|
||||||
return rec
|
return rec
|
||||||
|
|||||||
@@ -19,12 +19,12 @@ from __future__ import annotations
|
|||||||
|
|
||||||
from .broker import LaunchBroker, LaunchRequest, sign_request
|
from .broker import LaunchBroker, LaunchRequest, sign_request
|
||||||
from .registry import BottleRecord, RegistryStore
|
from .registry import BottleRecord, RegistryStore
|
||||||
from .sidecar import Sidecar
|
from .gateway import Gateway
|
||||||
|
|
||||||
|
|
||||||
class Orchestrator:
|
class Orchestrator:
|
||||||
"""Owns the registry + brokers launches, and manages the single
|
"""Owns the registry + brokers launches, and manages the single
|
||||||
consolidated per-host sidecar. Backend-neutral (broker and sidecar
|
consolidated per-host gateway. Backend-neutral (broker and gateway
|
||||||
abstract the backend-native pieces)."""
|
abstract the backend-native pieces)."""
|
||||||
|
|
||||||
def __init__(
|
def __init__(
|
||||||
@@ -32,12 +32,12 @@ class Orchestrator:
|
|||||||
registry: RegistryStore,
|
registry: RegistryStore,
|
||||||
broker: LaunchBroker,
|
broker: LaunchBroker,
|
||||||
sign_secret: bytes,
|
sign_secret: bytes,
|
||||||
sidecar: Sidecar | None = None,
|
gateway: Gateway | None = None,
|
||||||
) -> None:
|
) -> None:
|
||||||
self.registry = registry
|
self.registry = registry
|
||||||
self._broker = broker
|
self._broker = broker
|
||||||
self._secret = sign_secret
|
self._secret = sign_secret
|
||||||
self._sidecar = sidecar
|
self._gateway = gateway
|
||||||
|
|
||||||
def launch_bottle(
|
def launch_bottle(
|
||||||
self,
|
self,
|
||||||
@@ -48,7 +48,7 @@ class Orchestrator:
|
|||||||
metadata: str = "",
|
metadata: str = "",
|
||||||
policy: str = "",
|
policy: str = "",
|
||||||
) -> BottleRecord:
|
) -> BottleRecord:
|
||||||
"""Register a bottle (with its sidecar policy) and broker its launch.
|
"""Register a bottle (with its gateway policy) and broker its launch.
|
||||||
Rolls the registry entry back if the launch doesn't take, so a
|
Rolls the registry entry back if the launch doesn't take, so a
|
||||||
failure leaves no orphan."""
|
failure leaves no orphan."""
|
||||||
rec = self.registry.register(source_ip, metadata=metadata, policy=policy)
|
rec = self.registry.register(source_ip, metadata=metadata, policy=policy)
|
||||||
@@ -79,33 +79,42 @@ class Orchestrator:
|
|||||||
return True
|
return True
|
||||||
|
|
||||||
def attribute(self, source_ip: str, identity_token: str) -> BottleRecord | None:
|
def attribute(self, source_ip: str, identity_token: str) -> BottleRecord | None:
|
||||||
"""Fail-closed attribution (delegates to the registry). The returned
|
"""Fail-closed attribution (delegates to the registry)."""
|
||||||
record carries the bottle's `policy` — this is the source-IP-keyed
|
|
||||||
resolution the multi-tenant sidecar makes per request."""
|
|
||||||
return self.registry.attribute(source_ip, identity_token)
|
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:
|
def set_policy(self, bottle_id: str, policy: str) -> bool:
|
||||||
"""Update a bottle's sidecar policy in place (live reload). False if
|
"""Update a bottle's gateway policy in place (live reload). False if
|
||||||
the bottle is unknown."""
|
the bottle is unknown."""
|
||||||
return self.registry.set_policy(bottle_id, policy)
|
return self.registry.set_policy(bottle_id, policy)
|
||||||
|
|
||||||
# --- consolidated sidecar ----------------------------------------------
|
# --- consolidated gateway ----------------------------------------------
|
||||||
|
|
||||||
def ensure_sidecar(self) -> None:
|
def ensure_gateway(self) -> None:
|
||||||
"""Ensure the single per-host sidecar is built and up (idempotent).
|
"""Ensure the single per-host gateway is built and up (idempotent).
|
||||||
No-op when no sidecar is configured."""
|
No-op when no gateway is configured."""
|
||||||
if self._sidecar is not None:
|
if self._gateway is not None:
|
||||||
self._sidecar.ensure_built()
|
self._gateway.ensure_built()
|
||||||
self._sidecar.ensure_running()
|
self._gateway.ensure_running()
|
||||||
|
|
||||||
def sidecar_status(self) -> dict[str, object]:
|
def gateway_status(self) -> dict[str, object]:
|
||||||
"""Report the shared sidecar for the control plane / console."""
|
"""Report the shared gateway for the control plane / console."""
|
||||||
if self._sidecar is None:
|
if self._gateway is None:
|
||||||
return {"configured": False}
|
return {"configured": False}
|
||||||
return {
|
return {
|
||||||
"configured": True,
|
"configured": True,
|
||||||
"name": self._sidecar.name,
|
"name": self._gateway.name,
|
||||||
"running": self._sidecar.is_running(),
|
"running": self._gateway.is_running(),
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
@@ -1,6 +1,6 @@
|
|||||||
"""Sidecar-side per-client policy resolver (PRD 0070).
|
"""Gateway-side per-client policy resolver (PRD 0070).
|
||||||
|
|
||||||
The consolidated sidecar serves every bottle from one process, so for each
|
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
|
request it must apply the *calling* bottle's policy, selected by the source
|
||||||
IP the attribution invariant makes unspoofable. This resolves that policy
|
IP the attribution invariant makes unspoofable. This resolves that policy
|
||||||
from the orchestrator's control plane (`POST /resolve`), keyed on the
|
from the orchestrator's control plane (`POST /resolve`), keyed on the
|
||||||
@@ -47,11 +47,11 @@ class PolicyResolver:
|
|||||||
self._base = base_url.rstrip("/")
|
self._base = base_url.rstrip("/")
|
||||||
self._timeout = timeout
|
self._timeout = timeout
|
||||||
|
|
||||||
def resolve(self, source_ip: str, identity_token: str) -> str | None:
|
def _post_resolve(self, source_ip: str, identity_token: str) -> dict[str, object] | None:
|
||||||
"""The calling bottle's policy blob, or None if unattributed. Always
|
"""The orchestrator's `/resolve` payload for this client, or None if
|
||||||
fetches from the orchestrator so revocations / changes / teardowns
|
unattributed (a clean `403`). Raises `PolicyResolveError` on an
|
||||||
are honored immediately. Raises `PolicyResolveError` if the
|
unreachable / unexpected-status / malformed response so every caller
|
||||||
orchestrator can't be reached / errors."""
|
can fail closed. Shared by `resolve` and `resolve_bottle_id`."""
|
||||||
body = json.dumps(
|
body = json.dumps(
|
||||||
{"source_ip": source_ip, "identity_token": identity_token}
|
{"source_ip": source_ip, "identity_token": identity_token}
|
||||||
).encode()
|
).encode()
|
||||||
@@ -68,8 +68,56 @@ class PolicyResolver:
|
|||||||
raise PolicyResolveError(f"/resolve returned HTTP {e.code}") from e
|
raise PolicyResolveError(f"/resolve returned HTTP {e.code}") from e
|
||||||
except (urllib.error.URLError, TimeoutError, OSError, ValueError) as e:
|
except (urllib.error.URLError, TimeoutError, OSError, ValueError) as e:
|
||||||
raise PolicyResolveError(f"/resolve unreachable or malformed: {e}") from e
|
raise PolicyResolveError(f"/resolve unreachable or malformed: {e}") from e
|
||||||
policy = payload.get("policy") if isinstance(payload, dict) else None
|
return payload if isinstance(payload, dict) else {}
|
||||||
|
|
||||||
|
def resolve(self, source_ip: str, identity_token: str = "") -> str | None:
|
||||||
|
"""The calling bottle's policy blob, or None if unattributed. Always
|
||||||
|
fetches from the orchestrator so revocations / changes / teardowns
|
||||||
|
are honored immediately.
|
||||||
|
|
||||||
|
`identity_token` is optional *transitionally* — omitting it resolves
|
||||||
|
by source IP alone (the network-layer attribution, sound by
|
||||||
|
construction on Firecracker's `/31`+nft, weaker elsewhere). The
|
||||||
|
consolidated end state makes the token mandatory so the app-layer
|
||||||
|
defense is always enforced, not silently degraded; that flips at the
|
||||||
|
`/resolve` boundary once identity-token *delivery* lands (a PRD 0070
|
||||||
|
open question — we can't require what the agent can't yet present).
|
||||||
|
Raises `PolicyResolveError` if the orchestrator can't be reached."""
|
||||||
|
payload = self._post_resolve(source_ip, identity_token)
|
||||||
|
if payload is None:
|
||||||
|
return None
|
||||||
|
policy = payload.get("policy")
|
||||||
return policy if isinstance(policy, str) else ""
|
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"]
|
__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
|
||||||
|
|
||||||
|
|||||||
@@ -10,8 +10,8 @@
|
|||||||
|
|
||||||
## Summary
|
## Summary
|
||||||
|
|
||||||
Replace the **per-bottle sidecar bundle** with a single **persistent,
|
Replace the **per-bottle gateway bundle** with a single **persistent,
|
||||||
per-host orchestrator**: one long-lived service that runs the sidecar
|
per-host orchestrator**: one long-lived service that runs the gateway
|
||||||
functions (egress / git-gate / supervise), coordinates with the console,
|
functions (egress / git-gate / supervise), coordinates with the console,
|
||||||
and brokers agent launches and teardown. It is **virtualized from the
|
and brokers agent launches and teardown. It is **virtualized from the
|
||||||
start** using each backend's native isolation primitive — a Firecracker
|
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
|
## 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:
|
git-gate + supervise). That costs:
|
||||||
|
|
||||||
- **Resources.** N bottles → N heavy bundles booting and idling.
|
- **Resources.** N bottles → N heavy bundles booting and idling.
|
||||||
- **Operational churn.** Per-launch container/VM lifecycle for the
|
- **Operational churn.** Per-launch container/VM lifecycle for the
|
||||||
sidecars, a control path baked at launch and torn down at exit.
|
gateways, a control path baked at launch and torn down at exit.
|
||||||
- **A blurry contract.** "How a bottle talks to its sidecar" is
|
- **A blurry contract.** "How a bottle talks to its gateway" is
|
||||||
re-implemented per backend instead of being one agreed interface.
|
re-implemented per backend instead of being one agreed interface.
|
||||||
|
|
||||||
A per-host orchestrator collapses the first two and forces the third to
|
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.
|
structured, auditable privileged core instead of a fat socket.
|
||||||
- **Attribution is enforced, not assumed.** Making source-IP identity a
|
- **Attribution is enforced, not assumed.** Making source-IP identity a
|
||||||
first-class contract invariant (below) means each backend must *prove*
|
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
|
### 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
|
process boundary — each holds only its bottle's tokens/keys. A host
|
||||||
orchestrator concentrates **every bottle's** egress tokens, git deploy
|
orchestrator concentrates **every bottle's** egress tokens, git deploy
|
||||||
keys, and the console credential in one long-lived process. A single
|
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.
|
fleet, plus launch authority, plus the console token.
|
||||||
- *Mitigation:* the orchestrator is itself confined (its own VM/container
|
- *Mitigation:* the orchestrator is itself confined (its own VM/container
|
||||||
with its own fail-closed egress); make it **restartable without killing
|
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
|
connectivity until it's back); persist state to a host volume so a
|
||||||
restart re-adopts live bottles rather than losing them.
|
restart re-adopts live bottles rather than losing them.
|
||||||
|
|
||||||
@@ -114,13 +114,13 @@ responsibility** and part of the contract:
|
|||||||
- **Apple** — the host-only network.
|
- **Apple** — the host-only network.
|
||||||
|
|
||||||
If a backend can't honor the invariant, source-IP consolidation is not
|
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.
|
hard precondition, not an aspiration.
|
||||||
|
|
||||||
**Defense-in-depth — a per-bottle identity token.** On top of the
|
**Defense-in-depth — a per-bottle identity token.** On top of the
|
||||||
network-layer invariant, inject a per-bottle secret token into every
|
network-layer invariant, inject a per-bottle secret token into every
|
||||||
request the agent makes to the orchestrator (the agent already egresses
|
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:
|
**application-layer** proof of identity independent of the network layer:
|
||||||
|
|
||||||
- On **Firecracker** the `/31` + nft already make source IP unspoofable
|
- 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
|
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
|
can't learn another bottle's token, given bottle isolation), so a hostile
|
||||||
agent gains nothing by presenting it. The orchestrator provisions the
|
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
|
Note this hardens *attribution*, not *secret exposure*: it's app-layer, so
|
||||||
a compromised orchestrator still sees every token (that's the
|
a compromised orchestrator still sees every token (that's the
|
||||||
concentration problem, addressed separately under Secret handling).
|
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
|
`AgentProvider`s are — because maintaining every forge/cloud/OAuth
|
||||||
provider in-tree is untenable. The orchestrator's vault mints via these
|
provider in-tree is untenable. The orchestrator's vault mints via these
|
||||||
providers; but the abstraction is shippable independently and today's
|
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
|
## Design
|
||||||
|
|
||||||
@@ -195,7 +195,7 @@ Three surfaces; only one is per-backend.
|
|||||||
every host (no vsock/unix-socket portability caveats); a local unix
|
every host (no vsock/unix-socket portability caveats); a local unix
|
||||||
socket is a fine optimization, but HTTP is the wire contract.
|
socket is a fine optimization, but HTTP is the wire contract.
|
||||||
2. **Data plane (agent → orchestrator)** — the egress / git / supervise
|
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.
|
only the *address* and *how packets get there* are per-backend.
|
||||||
3. **Launch / wire (orchestrator → backend)** — the irreducibly
|
3. **Launch / wire (orchestrator → backend)** — the irreducibly
|
||||||
backend-specific part; lives on `BottleBackend`.
|
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
|
the broker verifies with the orchestrator's public key (provisioned at
|
||||||
broker install). This is the concrete form of security #3's "structured
|
broker install). This is the concrete form of security #3's "structured
|
||||||
requests only." Same JSON-with-ids + JWT shape for all
|
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.
|
handled as they arise, with this as the default.
|
||||||
|
|
||||||
If `BottleBackend` bloats, the pressure valve is composition one level
|
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,
|
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
|
never a direct file handle.** No agent-facing component gets the file, so
|
||||||
none can forge attribution. (This supersedes the earlier `ro`-mount idea.)
|
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
|
rw-bind-mounts `bot-bottle.db`** to write proposals — exactly the
|
||||||
pattern the orchestrator removes (supervise consolidates into 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.
|
put the attribution registry behind a data-plane-writable mount.
|
||||||
|
|
||||||
Implementation note for the VM slices: SQLite **WAL** over a guest share
|
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):
|
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
|
containers; collapse N bundles into one persistent container). Proves
|
||||||
consolidation + the `BottleBackend` seam with the least moving parts.
|
consolidation + the `BottleBackend` seam with the least moving parts.
|
||||||
2. **Firecracker orchestrator** — the real work: the shim + VM-to-VM
|
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.
|
the dev-harness so the app logic is already proven.
|
||||||
3. **macOS (Apple container)** — last (container-to-container networking).
|
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
|
## Non-goals
|
||||||
|
|
||||||
- Removing OCI/Dockerfile support for agent images (0069's concern).
|
- Removing OCI/Dockerfile support for agent images (0069's concern).
|
||||||
- A single database for *all* config (see the three-tier table).
|
- 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.
|
is consolidated; agents stay one-VM/container-each.
|
||||||
|
|
||||||
## Relationship to other work
|
## 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
|
`BottleBackend.wire()` (DNAT+forward for fc, shared-net for
|
||||||
docker/apple), not orchestrator logic. **Not a blocker** — resolvable at
|
docker/apple), not orchestrator logic. **Not a blocker** — resolvable at
|
||||||
implementation time (may require a bit of host modification, as the pool
|
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.
|
it's feasible.
|
||||||
- **Live-reload protocol** for per-bottle policy over the HTTP control
|
- **Live-reload protocol** for per-bottle policy over the HTTP control
|
||||||
plane (add/remove routes/keys/proposals without a restart).
|
plane (add/remove routes/keys/proposals without a restart).
|
||||||
|
|||||||
+6
-6
@@ -1,7 +1,7 @@
|
|||||||
"""Integration: the consolidated Docker sidecar is an idempotent singleton.
|
"""Integration: the consolidated Docker gateway is an idempotent singleton.
|
||||||
|
|
||||||
Gated on a reachable Docker daemon. Uses a unique name so it never
|
Gated on a reachable Docker daemon. Uses a unique name so it never
|
||||||
collides with a real per-host sidecar or a leftover from another run.
|
collides with a real per-host gateway or a leftover from another run.
|
||||||
"""
|
"""
|
||||||
|
|
||||||
from __future__ import annotations
|
from __future__ import annotations
|
||||||
@@ -10,17 +10,17 @@ import secrets
|
|||||||
import subprocess
|
import subprocess
|
||||||
import unittest
|
import unittest
|
||||||
|
|
||||||
from bot_bottle.orchestrator.sidecar import DockerSidecar
|
from bot_bottle.orchestrator.gateway import DockerGateway
|
||||||
from tests._docker import skip_unless_docker
|
from tests._docker import skip_unless_docker
|
||||||
|
|
||||||
IMAGE = "busybox"
|
IMAGE = "busybox"
|
||||||
|
|
||||||
|
|
||||||
@skip_unless_docker()
|
@skip_unless_docker()
|
||||||
class TestDockerSidecarIntegration(unittest.TestCase):
|
class TestDockerGatewayIntegration(unittest.TestCase):
|
||||||
def setUp(self) -> None:
|
def setUp(self) -> None:
|
||||||
self.name = "bot-bottle-orch-sidecar-itest-" + secrets.token_hex(4)
|
self.name = "bot-bottle-orch-gateway-itest-" + secrets.token_hex(4)
|
||||||
self.sc = DockerSidecar(IMAGE, name=self.name)
|
self.sc = DockerGateway(IMAGE, name=self.name)
|
||||||
self.addCleanup(self.sc.stop)
|
self.addCleanup(self.sc.stop)
|
||||||
|
|
||||||
def _count(self) -> int:
|
def _count(self) -> int:
|
||||||
+5
-5
@@ -1,4 +1,4 @@
|
|||||||
"""Integration: DockerSidecar.image_exists reflects real docker state.
|
"""Integration: DockerGateway.image_exists reflects real docker state.
|
||||||
|
|
||||||
Gated on a reachable Docker daemon. Deliberately does NOT build the full
|
Gated on a reachable Docker daemon. Deliberately does NOT build the full
|
||||||
sidecar bundle (a heavy, slow image build) — it exercises the `image_exists`
|
sidecar bundle (a heavy, slow image build) — it exercises the `image_exists`
|
||||||
@@ -11,14 +11,14 @@ from __future__ import annotations
|
|||||||
import subprocess
|
import subprocess
|
||||||
import unittest
|
import unittest
|
||||||
|
|
||||||
from bot_bottle.orchestrator.sidecar import DockerSidecar
|
from bot_bottle.orchestrator.gateway import DockerGateway
|
||||||
from tests._docker import skip_unless_docker
|
from tests._docker import skip_unless_docker
|
||||||
|
|
||||||
IMAGE = "busybox"
|
IMAGE = "busybox"
|
||||||
|
|
||||||
|
|
||||||
@skip_unless_docker()
|
@skip_unless_docker()
|
||||||
class TestDockerSidecarImageExists(unittest.TestCase):
|
class TestDockerGatewayImageExists(unittest.TestCase):
|
||||||
def test_image_exists_true_for_present_false_for_absent(self) -> None:
|
def test_image_exists_true_for_present_false_for_absent(self) -> None:
|
||||||
# Ensure the tiny image is present (build_if_missing is disabled here
|
# Ensure the tiny image is present (build_if_missing is disabled here
|
||||||
# so this never triggers a Dockerfile.sidecars build).
|
# so this never triggers a Dockerfile.sidecars build).
|
||||||
@@ -26,9 +26,9 @@ class TestDockerSidecarImageExists(unittest.TestCase):
|
|||||||
["docker", "pull", IMAGE],
|
["docker", "pull", IMAGE],
|
||||||
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
|
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL, check=False,
|
||||||
)
|
)
|
||||||
self.assertTrue(DockerSidecar(IMAGE, dockerfile=None).image_exists())
|
self.assertTrue(DockerGateway(IMAGE, dockerfile=None).image_exists())
|
||||||
self.assertFalse(
|
self.assertFalse(
|
||||||
DockerSidecar("bot-bottle-nonexistent:doesnotexist", dockerfile=None).image_exists()
|
DockerGateway("bot-bottle-nonexistent:doesnotexist", dockerfile=None).image_exists()
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
@@ -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()
|
||||||
|
|||||||
@@ -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 +1,67 @@
|
|||||||
|
"""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
|
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 +1,65 @@
|
|||||||
|
"""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()
|
||||||
@@ -118,8 +118,8 @@ class TestDispatch(unittest.TestCase):
|
|||||||
status, _ = dispatch(self.orch, "GET", "/health/", b"")
|
status, _ = dispatch(self.orch, "GET", "/health/", b"")
|
||||||
self.assertEqual(200, status)
|
self.assertEqual(200, status)
|
||||||
|
|
||||||
def test_sidecar_status_unconfigured(self) -> None:
|
def test_gateway_status_unconfigured(self) -> None:
|
||||||
status, payload = dispatch(self.orch, "GET", "/sidecar", b"")
|
status, payload = dispatch(self.orch, "GET", "/gateway", b"")
|
||||||
self.assertEqual(200, status)
|
self.assertEqual(200, status)
|
||||||
self.assertEqual(False, payload["configured"])
|
self.assertEqual(False, payload["configured"])
|
||||||
|
|
||||||
@@ -171,6 +171,22 @@ class TestDispatch(unittest.TestCase):
|
|||||||
)
|
)
|
||||||
self.assertEqual(400, status)
|
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):
|
class TestServerRoundTrip(unittest.TestCase):
|
||||||
def test_http_register_health_attribute(self) -> None:
|
def test_http_register_health_attribute(self) -> None:
|
||||||
|
|||||||
@@ -1,29 +1,29 @@
|
|||||||
"""Unit tests for the consolidated Docker sidecar (PRD 0070). Docker mocked."""
|
"""Unit tests for the consolidated Docker gateway (PRD 0070). Docker mocked."""
|
||||||
|
|
||||||
from __future__ import annotations
|
from __future__ import annotations
|
||||||
|
|
||||||
import unittest
|
import unittest
|
||||||
from unittest.mock import Mock, patch
|
from unittest.mock import Mock, patch
|
||||||
|
|
||||||
from bot_bottle.orchestrator.sidecar import (
|
from bot_bottle.orchestrator.gateway import (
|
||||||
SIDECAR_NAME,
|
GATEWAY_NAME,
|
||||||
DockerSidecar,
|
DockerGateway,
|
||||||
SidecarError,
|
GatewayError,
|
||||||
)
|
)
|
||||||
|
|
||||||
_RUN_DOCKER = "bot_bottle.orchestrator.sidecar.run_docker"
|
_RUN_DOCKER = "bot_bottle.orchestrator.gateway.run_docker"
|
||||||
|
|
||||||
|
|
||||||
def _proc(returncode: int = 0, stdout: str = "", stderr: str = "") -> Mock:
|
def _proc(returncode: int = 0, stdout: str = "", stderr: str = "") -> Mock:
|
||||||
return Mock(returncode=returncode, stdout=stdout, stderr=stderr)
|
return Mock(returncode=returncode, stdout=stdout, stderr=stderr)
|
||||||
|
|
||||||
|
|
||||||
class TestDockerSidecar(unittest.TestCase):
|
class TestDockerGateway(unittest.TestCase):
|
||||||
def setUp(self) -> None:
|
def setUp(self) -> None:
|
||||||
self.sc = DockerSidecar("bot-bottle-sidecars:latest")
|
self.sc = DockerGateway("bot-bottle-sidecars:latest")
|
||||||
|
|
||||||
def test_default_name(self) -> None:
|
def test_default_name(self) -> None:
|
||||||
self.assertEqual(SIDECAR_NAME, self.sc.name)
|
self.assertEqual(GATEWAY_NAME, self.sc.name)
|
||||||
|
|
||||||
def test_is_running_reads_docker_ps(self) -> None:
|
def test_is_running_reads_docker_ps(self) -> None:
|
||||||
with patch(_RUN_DOCKER, return_value=_proc(stdout=self.sc.name + "\n")):
|
with patch(_RUN_DOCKER, return_value=_proc(stdout=self.sc.name + "\n")):
|
||||||
@@ -61,7 +61,7 @@ class TestDockerSidecar(unittest.TestCase):
|
|||||||
return _proc()
|
return _proc()
|
||||||
|
|
||||||
with patch(_RUN_DOCKER, side_effect=fake):
|
with patch(_RUN_DOCKER, side_effect=fake):
|
||||||
with self.assertRaises(SidecarError):
|
with self.assertRaises(GatewayError):
|
||||||
self.sc.ensure_running()
|
self.sc.ensure_running()
|
||||||
|
|
||||||
def test_stop_is_idempotent_on_missing(self) -> None:
|
def test_stop_is_idempotent_on_missing(self) -> None:
|
||||||
@@ -71,13 +71,13 @@ class TestDockerSidecar(unittest.TestCase):
|
|||||||
|
|
||||||
def test_stop_raises_on_other_failure(self) -> None:
|
def test_stop_raises_on_other_failure(self) -> None:
|
||||||
with patch(_RUN_DOCKER, return_value=_proc(returncode=1, stderr="daemon down")):
|
with patch(_RUN_DOCKER, return_value=_proc(returncode=1, stderr="daemon down")):
|
||||||
with self.assertRaises(SidecarError):
|
with self.assertRaises(GatewayError):
|
||||||
self.sc.stop()
|
self.sc.stop()
|
||||||
|
|
||||||
|
|
||||||
class TestDockerSidecarBuild(unittest.TestCase):
|
class TestDockerGatewayBuild(unittest.TestCase):
|
||||||
def setUp(self) -> None:
|
def setUp(self) -> None:
|
||||||
self.sc = DockerSidecar() # defaults to the real bundle image + dockerfile
|
self.sc = DockerGateway() # defaults to the real bundle image + dockerfile
|
||||||
|
|
||||||
def test_image_exists_reads_docker_inspect(self) -> None:
|
def test_image_exists_reads_docker_inspect(self) -> None:
|
||||||
with patch(_RUN_DOCKER, return_value=_proc(returncode=0)):
|
with patch(_RUN_DOCKER, return_value=_proc(returncode=0)):
|
||||||
@@ -109,7 +109,7 @@ class TestDockerSidecarBuild(unittest.TestCase):
|
|||||||
self.assertTrue(any(a.endswith("Dockerfile.sidecars") for a in builds[0]))
|
self.assertTrue(any(a.endswith("Dockerfile.sidecars") for a in builds[0]))
|
||||||
|
|
||||||
def test_ensure_built_noop_when_no_dockerfile(self) -> None:
|
def test_ensure_built_noop_when_no_dockerfile(self) -> None:
|
||||||
sc = DockerSidecar("busybox", dockerfile=None)
|
sc = DockerGateway("busybox", dockerfile=None)
|
||||||
with patch(_RUN_DOCKER) as m:
|
with patch(_RUN_DOCKER) as m:
|
||||||
sc.ensure_built()
|
sc.ensure_built()
|
||||||
m.assert_not_called()
|
m.assert_not_called()
|
||||||
@@ -121,7 +121,7 @@ class TestDockerSidecarBuild(unittest.TestCase):
|
|||||||
return _proc(returncode=1, stderr="build boom")
|
return _proc(returncode=1, stderr="build boom")
|
||||||
|
|
||||||
with patch(_RUN_DOCKER, side_effect=fake):
|
with patch(_RUN_DOCKER, side_effect=fake):
|
||||||
with self.assertRaises(SidecarError):
|
with self.assertRaises(GatewayError):
|
||||||
self.sc.ensure_built()
|
self.sc.ensure_built()
|
||||||
|
|
||||||
|
|
||||||
@@ -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()
|
||||||
@@ -121,6 +121,18 @@ class TestRegistryStore(unittest.TestCase):
|
|||||||
assert got is not None
|
assert got is not None
|
||||||
self.assertEqual("", got.policy)
|
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__":
|
if __name__ == "__main__":
|
||||||
unittest.main()
|
unittest.main()
|
||||||
|
|||||||
@@ -10,7 +10,7 @@ from pathlib import Path
|
|||||||
from bot_bottle.orchestrator.broker import LaunchBroker, LaunchRequest, StubBroker
|
from bot_bottle.orchestrator.broker import LaunchBroker, LaunchRequest, StubBroker
|
||||||
from bot_bottle.orchestrator.registry import RegistryStore
|
from bot_bottle.orchestrator.registry import RegistryStore
|
||||||
from bot_bottle.orchestrator.service import Orchestrator
|
from bot_bottle.orchestrator.service import Orchestrator
|
||||||
from bot_bottle.orchestrator.sidecar import Sidecar
|
from bot_bottle.orchestrator.gateway import Gateway
|
||||||
|
|
||||||
|
|
||||||
class _FailingBroker(LaunchBroker):
|
class _FailingBroker(LaunchBroker):
|
||||||
@@ -24,11 +24,11 @@ class _FailingBroker(LaunchBroker):
|
|||||||
pass
|
pass
|
||||||
|
|
||||||
|
|
||||||
class _FakeSidecar(Sidecar):
|
class _FakeGateway(Gateway):
|
||||||
"""In-memory sidecar for wiring tests."""
|
"""In-memory gateway for wiring tests."""
|
||||||
|
|
||||||
def __init__(self) -> None:
|
def __init__(self) -> None:
|
||||||
self.name = "fake-sidecar"
|
self.name = "fake-gateway"
|
||||||
self.ensured = 0
|
self.ensured = 0
|
||||||
self.built = 0
|
self.built = 0
|
||||||
self._running = False
|
self._running = False
|
||||||
@@ -102,29 +102,41 @@ class TestOrchestrator(unittest.TestCase):
|
|||||||
def test_set_policy_unknown_is_false(self) -> None:
|
def test_set_policy_unknown_is_false(self) -> None:
|
||||||
self.assertFalse(self.orch.set_policy("ghost", "{}"))
|
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:
|
def test_launch_rolls_back_registry_on_broker_failure(self) -> None:
|
||||||
orch = Orchestrator(self.store, _FailingBroker(self.secret), self.secret)
|
orch = Orchestrator(self.store, _FailingBroker(self.secret), self.secret)
|
||||||
with self.assertRaises(RuntimeError):
|
with self.assertRaises(RuntimeError):
|
||||||
orch.launch_bottle("10.243.0.9")
|
orch.launch_bottle("10.243.0.9")
|
||||||
self.assertEqual([], self.store.all()) # no orphan
|
self.assertEqual([], self.store.all()) # no orphan
|
||||||
|
|
||||||
def test_sidecar_unconfigured_by_default(self) -> None:
|
def test_gateway_unconfigured_by_default(self) -> None:
|
||||||
self.assertEqual({"configured": False}, self.orch.sidecar_status())
|
self.assertEqual({"configured": False}, self.orch.gateway_status())
|
||||||
self.orch.ensure_sidecar() # no-op, must not raise
|
self.orch.ensure_gateway() # no-op, must not raise
|
||||||
|
|
||||||
def test_sidecar_wired_and_ensured(self) -> None:
|
def test_gateway_wired_and_ensured(self) -> None:
|
||||||
sc = _FakeSidecar()
|
sc = _FakeGateway()
|
||||||
orch = Orchestrator(self.store, self.broker, self.secret, sidecar=sc)
|
orch = Orchestrator(self.store, self.broker, self.secret, gateway=sc)
|
||||||
self.assertEqual(
|
self.assertEqual(
|
||||||
{"configured": True, "name": "fake-sidecar", "running": False},
|
{"configured": True, "name": "fake-gateway", "running": False},
|
||||||
orch.sidecar_status(),
|
orch.gateway_status(),
|
||||||
)
|
)
|
||||||
orch.ensure_sidecar()
|
orch.ensure_gateway()
|
||||||
self.assertEqual(1, sc.built) # ensure_sidecar builds first,
|
self.assertEqual(1, sc.built) # ensure_gateway builds first,
|
||||||
self.assertEqual(1, sc.ensured) # then runs
|
self.assertEqual(1, sc.ensured) # then runs
|
||||||
self.assertEqual(
|
self.assertEqual(
|
||||||
{"configured": True, "name": "fake-sidecar", "running": True},
|
{"configured": True, "name": "fake-gateway", "running": True},
|
||||||
orch.sidecar_status(),
|
orch.gateway_status(),
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
|
|||||||
@@ -1,4 +1,4 @@
|
|||||||
"""Unit tests for the sidecar-side PolicyResolver (PRD 0070). HTTP mocked."""
|
"""Unit tests for the gateway-side PolicyResolver (PRD 0070). HTTP mocked."""
|
||||||
|
|
||||||
from __future__ import annotations
|
from __future__ import annotations
|
||||||
|
|
||||||
@@ -66,6 +66,42 @@ class TestPolicyResolver(unittest.TestCase):
|
|||||||
self.assertEqual("10.243.0.7", sent["source_ip"])
|
self.assertEqual("10.243.0.7", sent["source_ip"])
|
||||||
self.assertEqual("the-token", sent["identity_token"])
|
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__":
|
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