Compare commits

...
8 changed files with 2163 additions and 0 deletions
+456
View File
@@ -0,0 +1,456 @@
#!/usr/bin/env python3
"""Disabled-by-default TLS edge for the read-only GPT Online Task ingress.
The internal AIOS ingress remains loopback-only. This service is a separate edge
that may bind non-loopback only when the owner explicitly approves it. It
forwards only the tiny read-only ingress API and never proxies the canonical
Bridge or Task API.
"""
from __future__ import annotations
from collections import defaultdict, deque
from dataclasses import dataclass
import hashlib
import hmac
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
import json
import os
from pathlib import Path
import re
import secrets
import ssl
import sys
import threading
import time
import urllib.error
import urllib.request
from typing import Any, Mapping
from urllib.parse import urlsplit
UPSTREAM = "http://127.0.0.1:18945"
MAX_BODY = 64 * 1024
MAX_RESPONSE = 256 * 1024
MAX_CONCURRENT_REQUESTS = 32
REQUEST_TIMEOUT_SECONDS = 20
RATE_WINDOW_SECONDS = 60
RATE_LIMIT_REQUESTS = 60
RATE_BURST_REQUESTS = 15
RATE_MAX_CLIENTS = 4096
_AUDIT_SALT = secrets.token_bytes(32)
PUBLIC_APPROVAL_ENV = "AIOS_GPT_EDGE_PUBLIC_BIND_APPROVED"
PUBLIC_DOMAIN_ENV = "AIOS_GPT_EDGE_PUBLIC_DOMAIN"
TASK_PATH_RE = re.compile(r"^/v1/read-only-tasks(?:/[A-Za-z0-9][A-Za-z0-9._:-]{7,127})?$")
def _client_pseudonym(value: str) -> str:
return hashlib.sha256(_AUDIT_SALT + value.encode("utf-8", "replace")).hexdigest()[:16]
def audit(event: str, **fields: object) -> None:
safe = {
"event": event,
"ts_unix_ms": int(time.time() * 1000),
}
for key, value in fields.items():
if key in {"authorization", "body", "token", "cookie", "client_ip"}:
continue
safe[key] = value
print(
json.dumps(safe, sort_keys=True, separators=(",", ":")),
file=sys.stderr,
flush=True,
)
class EdgeError(RuntimeError):
def __init__(self, code: str, status: int = 400) -> None:
super().__init__(code)
self.code = code
self.status = status
def canonical(value: object) -> bytes:
return json.dumps(
value,
ensure_ascii=False,
sort_keys=True,
separators=(",", ":"),
).encode("utf-8")
def public_bind_allowed(host: str, approval: str) -> str:
value = host.strip()
if value in {"127.0.0.1", "::1", "localhost"}:
return value
if approval != "1":
raise RuntimeError("GPT_EDGE_PUBLIC_BIND_OWNER_APPROVAL_REQUIRED")
if value not in {"0.0.0.0", "::"}:
raise RuntimeError("GPT_EDGE_BIND_ADDRESS_INVALID")
return value
def validated_public_domain(value: str) -> str:
domain = value.strip().lower()
if not domain:
return ""
if len(domain) > 253 or re.fullmatch(
r"(?=.{1,253}\Z)(?:[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?\.)+[a-z0-9](?:[a-z0-9-]{0,61}[a-z0-9])?",
domain,
) is None:
raise RuntimeError("GPT_EDGE_PUBLIC_DOMAIN_INVALID")
return domain
def validated_edge_identity(host: str, approval: str, domain: str) -> tuple[str, str]:
bind_host = public_bind_allowed(host, approval)
public_domain = validated_public_domain(domain)
if bind_host not in {"127.0.0.1", "::1", "localhost"} and not public_domain:
raise RuntimeError("GPT_EDGE_PUBLIC_DOMAIN_REQUIRED")
return bind_host, public_domain
def validate_tls_file(path: Path, *, key: bool) -> Path:
if path.is_symlink() or not path.is_file():
raise RuntimeError("GPT_EDGE_TLS_FILE_INVALID")
size = path.stat().st_size
if size < 16 or size > 256 * 1024:
raise RuntimeError("GPT_EDGE_TLS_FILE_INVALID")
if key and (path.stat().st_mode & 0o077):
raise RuntimeError("GPT_EDGE_TLS_KEY_MODE_INVALID")
return path
def build_tls_context(cert_path: Path, key_path: Path) -> ssl.SSLContext:
cert = validate_tls_file(cert_path, key=False)
key = validate_tls_file(key_path, key=True)
context = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
context.minimum_version = ssl.TLSVersion.TLSv1_2
context.options |= ssl.OP_NO_COMPRESSION
context.load_cert_chain(certfile=str(cert), keyfile=str(key))
return context
def allowed_route(method: str, raw_path: str) -> str:
parsed = urlsplit(raw_path)
if parsed.query or parsed.fragment:
raise EdgeError("QUERY_OR_FRAGMENT_DENY", 400)
path = parsed.path
if method == "GET" and path in {"/health", "/openapi.json"}:
return path
if method == "POST" and path == "/v1/read-only-tasks":
return path
if method == "GET" and TASK_PATH_RE.fullmatch(path):
return path
raise EdgeError("ROUTE_DENY", 404)
def route_label(method: str, path: str) -> str:
if method == "GET" and path == "/health":
return "health"
if method == "GET" and path == "/openapi.json":
return "openapi"
if method == "POST" and path == "/v1/read-only-tasks":
return "task_create"
if method == "GET" and path.startswith("/v1/read-only-tasks/"):
return "task_status"
return "unknown"
def forwarded_headers(headers: Mapping[str, str], *, body: bool) -> dict[str, str]:
result = {"Accept": "application/json"}
authorization = headers.get("Authorization")
if not isinstance(authorization, str) or not authorization.startswith("Bearer "):
raise EdgeError("AUTHORIZATION_REQUIRED", 401)
token = authorization[7:]
if len(token) < 32 or len(token) > 4096 or any(ch.isspace() for ch in token):
raise EdgeError("AUTHORIZATION_INVALID", 401)
result["Authorization"] = authorization
if body:
content_type = headers.get("Content-Type", "")
if content_type.split(";", 1)[0].strip().lower() != "application/json":
raise EdgeError("CONTENT_TYPE_INVALID", 415)
result["Content-Type"] = "application/json"
return result
class RateLimiter:
def __init__(
self,
*,
window_seconds: int = RATE_WINDOW_SECONDS,
limit: int = RATE_LIMIT_REQUESTS,
burst: int = RATE_BURST_REQUESTS,
max_clients: int = RATE_MAX_CLIENTS,
now_fn=time.monotonic,
) -> None:
self.window_seconds = window_seconds
self.limit = limit
self.burst = burst
self.max_clients = max_clients
self.now_fn = now_fn
self._lock = threading.Lock()
self._events: dict[str, deque[float]] = defaultdict(deque)
def _prune_stale(self, cutoff: float) -> None:
stale = [
key
for key, events in self._events.items()
if not events or events[-1] <= cutoff
]
for key in stale:
self._events.pop(key, None)
def allowed(self, key: str) -> bool:
now = self.now_fn()
cutoff = now - self.window_seconds
with self._lock:
if key not in self._events and len(self._events) >= self.max_clients:
self._prune_stale(cutoff)
if len(self._events) >= self.max_clients:
return False
events = self._events[key]
while events and events[0] <= cutoff:
events.popleft()
if len(events) >= self.limit + self.burst:
return False
events.append(now)
return True
@dataclass(frozen=True)
class Proxy:
upstream: str = UPSTREAM
timeout: int = REQUEST_TIMEOUT_SECONDS
def request(
self,
method: str,
path: str,
headers: Mapping[str, str],
body: bytes | None,
) -> tuple[int, bytes, str]:
if self.upstream != UPSTREAM:
raise EdgeError("UPSTREAM_DRIFT_DENY", 503)
req = urllib.request.Request(
self.upstream + path,
method=method,
data=body,
headers=dict(headers),
)
try:
with urllib.request.urlopen(req, timeout=self.timeout) as response:
raw = response.read(MAX_RESPONSE + 1)
status = response.status
content_type = response.headers.get("Content-Type", "application/json")
except urllib.error.HTTPError as exc:
raw = exc.read(MAX_RESPONSE + 1)
status = exc.code
content_type = exc.headers.get("Content-Type", "application/json")
except Exception as exc:
raise EdgeError("UPSTREAM_UNAVAILABLE", 502) from exc
if len(raw) > MAX_RESPONSE:
raise EdgeError("UPSTREAM_RESPONSE_TOO_LARGE", 502)
if content_type.split(";", 1)[0].strip().lower() != "application/json":
raise EdgeError("UPSTREAM_CONTENT_TYPE_INVALID", 502)
return status, raw, "application/json"
class EdgeServer(ThreadingHTTPServer):
daemon_threads = True
request_queue_size = 64
allow_reuse_address = True
class Handler(BaseHTTPRequestHandler):
proxy = Proxy()
limiter = RateLimiter()
concurrency = threading.BoundedSemaphore(MAX_CONCURRENT_REQUESTS)
expected_domain = ""
server_version = "AIOSGPTIngressEdge/1.0"
sys_version = ""
def log_message(self, *_args: Any) -> None:
return
def respond_json(self, value: Mapping[str, Any], status: int) -> None:
raw = canonical(value)
self.send_response(status)
self.send_header("Content-Type", "application/json")
self.send_header("Cache-Control", "no-store")
self.send_header("X-Content-Type-Options", "nosniff")
self.send_header("Referrer-Policy", "no-referrer")
self.send_header("Content-Security-Policy", "default-src 'none'")
self.send_header("Strict-Transport-Security", "max-age=31536000")
self.send_header("Content-Length", str(len(raw)))
self.end_headers()
self.wfile.write(raw)
def send_proxy_response(self, status: int, raw: bytes, content_type: str) -> None:
self.send_response(status)
self.send_header("Content-Type", content_type)
self.send_header("Cache-Control", "no-store")
self.send_header("X-Content-Type-Options", "nosniff")
self.send_header("Referrer-Policy", "no-referrer")
self.send_header("Content-Security-Policy", "default-src 'none'")
self.send_header("Strict-Transport-Security", "max-age=31536000")
self.send_header("Content-Length", str(len(raw)))
self.end_headers()
self.wfile.write(raw)
def client_key(self) -> str:
return str(self.client_address[0])
def validate_host(self) -> None:
if not self.expected_domain:
return
host = self.headers.get("Host", "").split(":", 1)[0].lower()
if not hmac.compare_digest(host, self.expected_domain):
raise EdgeError("HOST_HEADER_DENY", 421)
def body(self) -> bytes:
try:
length = int(self.headers.get("Content-Length", "-1"))
except ValueError as exc:
raise EdgeError("CONTENT_LENGTH_INVALID") from exc
if length < 1 or length > MAX_BODY:
raise EdgeError("REQUEST_SIZE_INVALID", 413)
raw = self.rfile.read(length)
if len(raw) != length:
raise EdgeError("REQUEST_BODY_TRUNCATED", 400)
# Validate JSON at the edge so malformed bodies do not consume upstream work.
try:
value = json.loads(raw.decode("utf-8"))
except Exception as exc:
raise EdgeError("REQUEST_JSON_INVALID", 400) from exc
if not isinstance(value, Mapping):
raise EdgeError("REQUEST_JSON_OBJECT_REQUIRED", 400)
return canonical(value)
def handle_proxy(self, method: str) -> None:
client_id = _client_pseudonym(self.client_key())
started = time.monotonic()
acquired = self.concurrency.acquire(blocking=False)
if not acquired:
audit("EDGE_BUSY", client_id=client_id, method=method)
self.respond_json({"error": "EDGE_BUSY"}, 503)
return
label = "unknown"
try:
self.validate_host()
path = allowed_route(method, self.path)
label = route_label(method, path)
if path == "/health" and method == "GET":
self.respond_json(
{
"status": "ok",
"service": "aios-gpt-https-edge",
"upstream": "loopback-readonly-ingress",
},
200,
)
audit(
"EDGE_REQUEST",
client_id=client_id,
method=method,
route=label,
status=200,
duration_ms=int((time.monotonic() - started) * 1000),
)
return
if not self.limiter.allowed(self.client_key()):
audit(
"EDGE_RATE_LIMIT",
client_id=client_id,
method=method,
route=label,
)
self.respond_json({"error": "RATE_LIMITED"}, 429)
return
has_body = method == "POST"
headers = forwarded_headers(self.headers, body=has_body)
body = self.body() if has_body else None
status, raw, content_type = self.proxy.request(
method,
path,
headers,
body,
)
self.send_proxy_response(status, raw, content_type)
audit(
"EDGE_REQUEST",
client_id=client_id,
method=method,
route=label,
status=status,
duration_ms=int((time.monotonic() - started) * 1000),
)
except EdgeError as exc:
audit(
"EDGE_REJECT",
client_id=client_id,
method=method,
route=label,
status=exc.status,
error=exc.code,
)
self.respond_json({"error": exc.code}, exc.status)
finally:
self.concurrency.release()
def do_GET(self) -> None:
self.handle_proxy("GET")
def do_POST(self) -> None:
self.handle_proxy("POST")
def do_PUT(self) -> None:
self.respond_json({"error": "METHOD_DENY"}, 405)
def do_PATCH(self) -> None:
self.respond_json({"error": "METHOD_DENY"}, 405)
def do_DELETE(self) -> None:
self.respond_json({"error": "METHOD_DENY"}, 405)
def do_CONNECT(self) -> None:
self.respond_json({"error": "METHOD_DENY"}, 405)
def do_OPTIONS(self) -> None:
self.respond_json({"error": "METHOD_DENY"}, 405)
def serve() -> None:
host, public_domain = validated_edge_identity(
os.environ.get("AIOS_GPT_EDGE_HOST", "127.0.0.1"),
os.environ.get(PUBLIC_APPROVAL_ENV, "0"),
os.environ.get(PUBLIC_DOMAIN_ENV, ""),
)
port = int(os.environ.get("AIOS_GPT_EDGE_PORT", "18443"))
if not 1024 <= port <= 65535:
raise RuntimeError("GPT_EDGE_PORT_INVALID")
Handler.expected_domain = public_domain
credentials = Path(os.environ.get("CREDENTIALS_DIRECTORY", "/run/credentials"))
cert_path = Path(
os.environ.get(
"AIOS_GPT_EDGE_TLS_CERT_FILE",
str(credentials / "tls_cert"),
)
)
key_path = Path(
os.environ.get(
"AIOS_GPT_EDGE_TLS_KEY_FILE",
str(credentials / "tls_key"),
)
)
context = build_tls_context(cert_path, key_path)
server = EdgeServer((host, port), Handler)
server.socket = context.wrap_socket(server.socket, server_side=True)
server.serve_forever()
if __name__ == "__main__":
serve()
@@ -0,0 +1,816 @@
#!/usr/bin/env python3
"""Credential-isolated host-side ingress for externally scheduled read-only Online Tasks.
This service is intentionally not a public AIOS control plane. It accepts a tiny,
authenticated external intent and translates it to the canonical loopback Bridge.
Callers cannot select repository coordinates, capabilities, execution action,
worker, branch policy, credentials, verification decisions, or write permissions.
"""
from __future__ import annotations
from dataclasses import dataclass
from datetime import datetime, timezone
import hashlib
import hmac
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
import json
import os
from pathlib import Path
import re
import sqlite3
import threading
import urllib.error
import urllib.request
from typing import Any, Mapping
SCHEMA = "aios.gpt-online-task-ingress.request.v1"
RESPONSE_SCHEMA = "aios.gpt-online-task-ingress.response.v1"
OPENAPI_VERSION = "3.1.0"
REQUEST_ID_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{7,127}$")
TASK_ID_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:-]{2,179}$")
JOB_ID_RE = re.compile(r"^job-[0-9a-f]{32}$")
OID_RE = re.compile(r"^[0-9a-f]{40}$")
MAX_BODY = 64 * 1024
MAX_GOAL = 12_000
MAX_INSTRUCTIONS = 24_000
MAX_CRITERIA = 16
MAX_CRITERION_TEXT = 1_000
READONLY_CAPABILITIES = ("git.read", "git.test")
REPOSITORY = "aios/aios"
class IngressError(RuntimeError):
def __init__(self, code: str, status: int = 400) -> None:
super().__init__(code)
self.code = code
self.status = status
def canonical(value: object) -> bytes:
return json.dumps(
value,
ensure_ascii=False,
sort_keys=True,
separators=(",", ":"),
).encode("utf-8")
def digest(value: object) -> str:
return hashlib.sha256(canonical(value)).hexdigest()
def now() -> str:
return datetime.now(timezone.utc).isoformat()
def load_secret(path: Path, *, code: str) -> str:
if path.is_symlink() or not path.is_file():
raise RuntimeError(code + "_UNAVAILABLE")
value = path.read_text(encoding="utf-8").strip()
if len(value) < 32 or "\n" in value or "\r" in value:
raise RuntimeError(code + "_INVALID")
return value
def normalized_request(value: Mapping[str, Any]) -> dict[str, Any]:
allowed = {
"schema",
"request_id",
"goal",
"instructions",
"success_criteria",
"constraints",
}
if set(value) - allowed:
raise IngressError("UNKNOWN_FIELDS")
if value.get("schema") != SCHEMA:
raise IngressError("SCHEMA_INVALID")
request_id = value.get("request_id")
if not isinstance(request_id, str) or REQUEST_ID_RE.fullmatch(request_id) is None:
raise IngressError("REQUEST_ID_INVALID")
goal = value.get("goal")
if not isinstance(goal, str) or not goal.strip() or len(goal) > MAX_GOAL:
raise IngressError("GOAL_INVALID")
instructions = value.get("instructions", "")
if not isinstance(instructions, str) or len(instructions) > MAX_INSTRUCTIONS:
raise IngressError("INSTRUCTIONS_INVALID")
criteria = value.get("success_criteria") or []
if not isinstance(criteria, list) or len(criteria) > MAX_CRITERIA:
raise IngressError("SUCCESS_CRITERIA_INVALID")
normalized_criteria = []
for item in criteria:
if not isinstance(item, Mapping) or set(item) != {"id", "description"}:
raise IngressError("SUCCESS_CRITERIA_INVALID")
criterion_id = item.get("id")
description = item.get("description")
if (
not isinstance(criterion_id, str)
or not criterion_id.strip()
or len(criterion_id) > 120
or not isinstance(description, str)
or not description.strip()
or len(description) > MAX_CRITERION_TEXT
):
raise IngressError("SUCCESS_CRITERIA_INVALID")
normalized_criteria.append(
{"id": criterion_id.strip(), "description": description.strip()}
)
constraints = value.get("constraints") or {}
if not isinstance(constraints, Mapping):
raise IngressError("CONSTRAINTS_INVALID")
allowed_constraints = {
"max_files",
"focus_paths",
"notes",
}
if set(constraints) - allowed_constraints:
raise IngressError("CONSTRAINTS_FIELDS_INVALID")
normalized_constraints: dict[str, Any] = {}
if "max_files" in constraints:
max_files = constraints["max_files"]
if (
not isinstance(max_files, int)
or isinstance(max_files, bool)
or not 1 <= max_files <= 500
):
raise IngressError("MAX_FILES_INVALID")
normalized_constraints["max_files"] = max_files
if "focus_paths" in constraints:
paths = constraints["focus_paths"]
if (
not isinstance(paths, list)
or len(paths) > 32
or not all(
isinstance(path, str)
and path
and len(path) <= 512
and not path.startswith("/")
and ".." not in Path(path).parts
for path in paths
)
):
raise IngressError("FOCUS_PATHS_INVALID")
normalized_constraints["focus_paths"] = paths
if "notes" in constraints:
notes = constraints["notes"]
if not isinstance(notes, str) or len(notes) > 4_000:
raise IngressError("CONSTRAINT_NOTES_INVALID")
normalized_constraints["notes"] = notes
return {
"schema": SCHEMA,
"request_id": request_id,
"goal": goal.strip(),
"instructions": instructions,
"success_criteria": normalized_criteria,
"constraints": normalized_constraints,
}
def validated_bind_host(value: str) -> str:
host = value.strip()
if host not in {"127.0.0.1", "::1", "localhost"}:
raise RuntimeError("GPT_INGRESS_NON_LOOPBACK_BIND_DENY")
return host
def task_id_for(request_id: str) -> str:
suffix = hashlib.sha256(request_id.encode("utf-8")).hexdigest()[:24]
return "gpt-readonly-" + suffix
def branch_for(task_id: str) -> str:
return "agent/external-gpt-readonly/" + task_id[-24:]
@dataclass(frozen=True)
class Upstream:
bridge_base: str
task_base: str
control_token: str
timeout: int = 20
def _request(
self,
base: str,
method: str,
path: str,
body: Mapping[str, Any] | None = None,
) -> tuple[int, dict[str, Any]]:
raw_body = None if body is None else canonical(body)
headers = {
"Authorization": "Bearer " + self.control_token,
"Accept": "application/json",
}
if raw_body is not None:
headers["Content-Type"] = "application/json"
req = urllib.request.Request(
base.rstrip("/") + path,
method=method,
data=raw_body,
headers=headers,
)
try:
with urllib.request.urlopen(req, timeout=self.timeout) as response:
raw = response.read()
status = response.status
except urllib.error.HTTPError as exc:
raw = exc.read()
status = exc.code
except Exception as exc:
raise IngressError("UPSTREAM_TRANSPORT_FAILED", 503) from exc
try:
value = json.loads(raw.decode("utf-8"))
except Exception as exc:
raise IngressError("UPSTREAM_RESPONSE_INVALID", 502) from exc
if not isinstance(value, Mapping):
raise IngressError("UPSTREAM_RESPONSE_INVALID", 502)
return status, dict(value)
def control_snapshot(self) -> dict[str, Any]:
status, value = self._request(
self.bridge_base,
"GET",
"/v2/control-plane-snapshot",
)
if status != 200:
raise IngressError("CONTROL_SNAPSHOT_UNAVAILABLE", 503)
return value
def create_governed_task(
self,
body: Mapping[str, Any],
) -> tuple[int, dict[str, Any]]:
return self._request(
self.bridge_base,
"POST",
"/v2/governed-task",
body,
)
def execution_envelope(
self,
body: Mapping[str, Any],
) -> tuple[int, dict[str, Any]]:
return self._request(
self.bridge_base,
"POST",
"/v2/execution-envelope",
body,
)
def get_task(self, task_id: str) -> tuple[int, dict[str, Any]]:
return self._request(
self.task_base,
"GET",
"/v1/tasks/" + task_id,
)
class Store:
def __init__(self, path: Path) -> None:
self.path = Path(path)
self._lock = threading.RLock()
self.path.parent.mkdir(parents=True, exist_ok=True)
with self._connect() as con:
con.execute(
"""
CREATE TABLE IF NOT EXISTS external_task_requests(
request_id TEXT PRIMARY KEY,
request_sha256 TEXT NOT NULL,
task_id TEXT NOT NULL UNIQUE,
job_id TEXT,
base_oid TEXT,
state TEXT NOT NULL,
created_at TEXT NOT NULL,
updated_at TEXT NOT NULL,
response_json TEXT
)
"""
)
con.commit()
def _connect(self) -> sqlite3.Connection:
con = sqlite3.connect(self.path, timeout=30)
con.row_factory = sqlite3.Row
con.execute("PRAGMA busy_timeout=30000")
return con
def get(self, request_id: str) -> sqlite3.Row | None:
with self._connect() as con:
return con.execute(
"SELECT * FROM external_task_requests WHERE request_id=?",
(request_id,),
).fetchone()
def reserve(self, request: Mapping[str, Any], task_id: str) -> sqlite3.Row:
request_sha = digest(request)
timestamp = now()
with self._lock, self._connect() as con:
con.execute("BEGIN IMMEDIATE")
row = con.execute(
"SELECT * FROM external_task_requests WHERE request_id=?",
(request["request_id"],),
).fetchone()
if row is not None:
if row["request_sha256"] != request_sha:
raise IngressError("IDEMPOTENCY_CONFLICT", 409)
con.commit()
return row
con.execute(
"""
INSERT INTO external_task_requests(
request_id,request_sha256,task_id,state,created_at,updated_at
) VALUES(?,?,?,?,?,?)
""",
(
request["request_id"],
request_sha,
task_id,
"PENDING",
timestamp,
timestamp,
),
)
con.commit()
row = self.get(request["request_id"])
assert row is not None
return row
def bound(
self,
request_id: str,
*,
job_id: str,
base_oid: str,
response: Mapping[str, Any],
) -> None:
with self._lock, self._connect() as con:
con.execute(
"""
UPDATE external_task_requests
SET job_id=?,base_oid=?,state='BOUND',response_json=?,updated_at=?
WHERE request_id=?
""",
(
job_id,
base_oid,
json.dumps(response, sort_keys=True, separators=(",", ":")),
now(),
request_id,
),
)
con.commit()
class IngressService:
def __init__(self, upstream: Upstream, store: Store) -> None:
self.upstream = upstream
self.store = store
@staticmethod
def _main_oid(snapshot: Mapping[str, Any]) -> str:
candidates = [
snapshot.get("authoritative_head_oid"),
snapshot.get("head"),
(snapshot.get("aggregate") or {}).get("authoritative_head_oid")
if isinstance(snapshot.get("aggregate"), Mapping)
else None,
]
for candidate in candidates:
if isinstance(candidate, str) and OID_RE.fullmatch(candidate):
return candidate
raise IngressError("AUTHORITATIVE_HEAD_UNAVAILABLE", 503)
@staticmethod
def _public_response(
request_id: str,
task_id: str,
job_id: str,
state: str,
) -> dict[str, Any]:
return {
"schema": RESPONSE_SCHEMA,
"request_id": request_id,
"task_id": task_id,
"job_id": job_id,
"state": state,
"execution_mode": "source_capture",
"capabilities": list(READONLY_CAPABILITIES),
"write_access": False,
"official_verification_required": True,
}
def _recover_existing(
self,
request: Mapping[str, Any],
row: sqlite3.Row,
) -> dict[str, Any] | None:
task_id = str(row["task_id"])
status, task = self.upstream.get_task(task_id)
if status == 404:
return None
if status != 200:
raise IngressError("TASK_RECOVERY_FAILED", 503)
metadata = task.get("metadata")
execution = (
metadata.get("execution")
if isinstance(metadata, Mapping)
and isinstance(metadata.get("execution"), Mapping)
else {}
)
job_id = str(execution.get("job_id") or row["job_id"] or "")
base_oid = str(execution.get("base_oid") or row["base_oid"] or "")
if (
task.get("task_id") != task_id
or not JOB_ID_RE.fullmatch(job_id)
or not OID_RE.fullmatch(base_oid)
or execution.get("action") != "source_capture"
or sorted(execution.get("capability_scope") or [])
!= sorted(READONLY_CAPABILITIES)
or (execution.get("governance") or {}).get("writer_lease") is not False
):
raise IngressError("TASK_RECOVERY_BINDING_INVALID", 409)
response = self._public_response(
request["request_id"],
task_id,
job_id,
str(task.get("status") or "BOUND"),
)
self.store.bound(
request["request_id"],
job_id=job_id,
base_oid=base_oid,
response=response,
)
return response
def create(self, raw: Mapping[str, Any]) -> dict[str, Any]:
request = normalized_request(raw)
task_id = task_id_for(request["request_id"])
row = self.store.reserve(request, task_id)
if row["state"] == "BOUND" and row["response_json"]:
return json.loads(row["response_json"])
recovered = self._recover_existing(request, row)
if recovered is not None:
return recovered
snapshot = self.upstream.control_snapshot()
base_oid = self._main_oid(snapshot)
target_branch = branch_for(task_id)
binding_key = "gpt-readonly-binding-" + digest(
{"request_id": request["request_id"], "base_oid": base_oid}
)[:24]
constraints = {
**request["constraints"],
"repository_mutation": "forbidden",
"control_plane_side_effects": "forbidden",
"credential_access": "forbidden",
}
body = {
"task_id": task_id,
"repository": REPOSITORY,
"base_oid": base_oid,
"expected_branch_oid": base_oid,
"target_branch": target_branch,
"branch_mode": "CREATE_NEW",
"generation": 1,
"risk": "low",
"description": "Externally requested read-only governed Online Task.",
"idempotency_key": binding_key,
"priority": 0,
"max_attempts": 3,
"require_online_task_projection": True,
"online_task": {
"goal": request["goal"],
"instructions": request["instructions"],
"success_criteria": request["success_criteria"],
"constraints": constraints,
"required_capabilities": list(READONLY_CAPABILITIES),
"priority": 0,
"max_attempts": 3,
},
"execution": {
"action": "source_capture",
"adapter": "source_capture",
"capability_scope": list(READONLY_CAPABILITIES),
"source_signals": [
"external read-only source analysis request",
"no repository mutation no credential access no control-plane side effects",
],
},
}
status, value = self.upstream.create_governed_task(body)
if status not in {200, 201, 202}:
if status == 409:
recovered = self._recover_existing(request, row)
if recovered is not None:
return recovered
raise IngressError(
"GOVERNED_TASK_CREATE_FAILED",
409 if status == 409 else 503,
)
job_id = str(value.get("job_id") or "")
if value.get("task_id") != task_id or JOB_ID_RE.fullmatch(job_id) is None:
raise IngressError("GOVERNED_TASK_RESPONSE_INVALID", 502)
envelope_status, envelope = self.upstream.execution_envelope(
{
"task_id": task_id,
"job_id": job_id,
"required_capabilities": list(READONLY_CAPABILITIES),
"execution": body["execution"],
}
)
if envelope_status != 200:
raise IngressError("EXECUTION_PROJECTION_FAILED", 503)
if (
envelope.get("task_id") != task_id
or envelope.get("job_id") != job_id
or envelope.get("base_oid") != base_oid
or envelope.get("action") != "source_capture"
or sorted(envelope.get("capability_scope") or [])
!= sorted(READONLY_CAPABILITIES)
or (envelope.get("governance") or {}).get("writer_lease") is not False
):
raise IngressError("EXECUTION_PROJECTION_INVALID", 502)
response = self._public_response(
request["request_id"],
task_id,
job_id,
"BOUND",
)
self.store.bound(
request["request_id"],
job_id=job_id,
base_oid=base_oid,
response=response,
)
return response
def status(self, request_id: str) -> dict[str, Any]:
if REQUEST_ID_RE.fullmatch(request_id) is None:
raise IngressError("REQUEST_ID_INVALID")
row = self.store.get(request_id)
if row is None:
raise IngressError("REQUEST_NOT_FOUND", 404)
task_id = str(row["task_id"])
status, task = self.upstream.get_task(task_id)
if status == 200 and not row["job_id"]:
metadata = task.get("metadata")
execution = (
metadata.get("execution")
if isinstance(metadata, Mapping)
and isinstance(metadata.get("execution"), Mapping)
else {}
)
job_id = str(execution.get("job_id") or "")
base_oid = str(execution.get("base_oid") or "")
if (
JOB_ID_RE.fullmatch(job_id)
and OID_RE.fullmatch(base_oid)
and execution.get("action") == "source_capture"
and sorted(execution.get("capability_scope") or [])
== sorted(READONLY_CAPABILITIES)
and (execution.get("governance") or {}).get("writer_lease") is False
):
recovered = self._public_response(
request_id,
task_id,
job_id,
str(task.get("status") or "BOUND"),
)
self.store.bound(
request_id,
job_id=job_id,
base_oid=base_oid,
response=recovered,
)
row = self.store.get(request_id) or row
if status == 404:
return {
"schema": RESPONSE_SCHEMA,
"request_id": request_id,
"task_id": task_id,
"state": "PENDING",
"official_verification_required": True,
}
if status != 200:
raise IngressError("TASK_STATUS_UNAVAILABLE", 503)
result = task.get("result") if isinstance(task.get("result"), Mapping) else {}
verification = (
task.get("verification")
if isinstance(task.get("verification"), Mapping)
else {}
)
safe = {
"schema": RESPONSE_SCHEMA,
"request_id": request_id,
"task_id": task_id,
"job_id": str(row["job_id"] or ""),
"state": str(task.get("status") or "UNKNOWN"),
"attempt": int(task.get("attempt") or 0),
"claimed": bool(task.get("claimed_by")),
"result_status": result.get("status"),
"result_classification": result.get("classification"),
"official_verification": verification.get("decision"),
"official_classification": verification.get("classification"),
"write_access": False,
}
if result.get("execution_mode") == "source_capture":
snapshot = result.get("source_snapshot")
if isinstance(snapshot, Mapping):
safe["source_snapshot_sha256"] = snapshot.get("payload_sha256")
safe["source_snapshot_file_count"] = snapshot.get("file_count")
return safe
def openapi_document() -> dict[str, Any]:
return {
"openapi": OPENAPI_VERSION,
"info": {
"title": "AIOS Read-Only Online Task Ingress",
"version": "1.0.0",
},
"paths": {
"/v1/read-only-tasks": {
"post": {
"operationId": "createReadOnlyOnlineTask",
"security": [{"bearerAuth": []}],
"requestBody": {"required": True},
"responses": {"200": {"description": "Task accepted"}},
}
},
"/v1/read-only-tasks/{request_id}": {
"get": {
"operationId": "getReadOnlyOnlineTaskStatus",
"security": [{"bearerAuth": []}],
"responses": {"200": {"description": "Sanitized task status"}},
}
},
},
"components": {
"securitySchemes": {
"bearerAuth": {
"type": "http",
"scheme": "bearer",
}
}
},
}
class Handler(BaseHTTPRequestHandler):
service: IngressService | None = None
ingress_token: str = ""
def log_message(self, *_args: Any) -> None:
return
def respond(self, value: Mapping[str, Any], status: int) -> None:
raw = canonical(value)
self.send_response(status)
self.send_header("Content-Type", "application/json")
self.send_header("Cache-Control", "no-store")
self.send_header("Content-Length", str(len(raw)))
self.end_headers()
self.wfile.write(raw)
def authorized(self) -> bool:
header = self.headers.get("Authorization", "")
return (
header.startswith("Bearer ")
and bool(self.ingress_token)
and hmac.compare_digest(header[7:], self.ingress_token)
)
def body(self) -> dict[str, Any]:
try:
length = int(self.headers.get("Content-Length", "-1"))
except ValueError as exc:
raise IngressError("CONTENT_LENGTH_INVALID") from exc
if length < 1 or length > MAX_BODY:
raise IngressError("REQUEST_SIZE_INVALID", 413)
try:
value = json.loads(self.rfile.read(length).decode("utf-8"))
except Exception as exc:
raise IngressError("REQUEST_JSON_INVALID") from exc
if not isinstance(value, Mapping):
raise IngressError("REQUEST_OBJECT_REQUIRED")
return dict(value)
def do_GET(self) -> None:
if self.path == "/health":
self.respond(
{
"status": "ok",
"service": "aios-gpt-online-task-ingress",
"mode": "read-only",
},
200,
)
return
if self.path == "/openapi.json":
self.respond(openapi_document(), 200)
return
if not self.authorized():
self.respond({"error": "UNAUTHORIZED"}, 401)
return
match = re.fullmatch(r"/v1/read-only-tasks/([^/?#]+)", self.path)
if match is None:
self.respond({"error": "NOT_FOUND"}, 404)
return
try:
if self.service is None:
raise IngressError("RUNTIME_UNAVAILABLE", 503)
self.respond(self.service.status(match.group(1)), 200)
except IngressError as exc:
self.respond({"error": exc.code}, exc.status)
def do_POST(self) -> None:
if self.path != "/v1/read-only-tasks":
self.respond({"error": "NOT_FOUND"}, 404)
return
if not self.authorized():
self.respond({"error": "UNAUTHORIZED"}, 401)
return
try:
if self.service is None:
raise IngressError("RUNTIME_UNAVAILABLE", 503)
value = self.service.create(self.body())
self.respond(value, 200)
except IngressError as exc:
self.respond({"error": exc.code}, exc.status)
def serve() -> None:
ingress_token_path = Path(
os.environ.get(
"AIOS_GPT_INGRESS_TOKEN_FILE",
str(
Path(os.environ.get("CREDENTIALS_DIRECTORY", "/run/credentials"))
/ "gpt_ingress_token"
),
)
)
control_token_path = Path(
os.environ.get(
"AIOS_AGENT_TASK_CONTROL_TOKEN_FILE",
str(
Path(os.environ.get("CREDENTIALS_DIRECTORY", "/run/credentials"))
/ "agent_task_control_token"
),
)
)
ingress_token = load_secret(
ingress_token_path,
code="GPT_INGRESS_CREDENTIAL",
)
control_token = load_secret(
control_token_path,
code="CONTROL_PLANE_CREDENTIAL",
)
state_root = Path(
os.environ.get(
"AIOS_GPT_INGRESS_STATE_ROOT",
"/var/lib/aios-gpt-online-task-ingress",
)
)
host = validated_bind_host(
os.environ.get("AIOS_GPT_INGRESS_HOST", "127.0.0.1")
)
port = int(os.environ.get("AIOS_GPT_INGRESS_PORT", "18945"))
if not 1024 <= port <= 65535:
raise RuntimeError("GPT_INGRESS_PORT_INVALID")
Handler.service = IngressService(
Upstream(
bridge_base=os.environ.get(
"AIOS_GOVERNED_WRITE_API_URL",
"http://127.0.0.1:18892",
),
task_base=os.environ.get(
"AIOS_AGENT_TASK_API_URL",
"http://127.0.0.1:18940",
),
control_token=control_token,
),
Store(state_root / "state.sqlite3"),
)
Handler.ingress_token = ingress_token
ThreadingHTTPServer((host, port), Handler).serve_forever()
if __name__ == "__main__":
serve()
@@ -0,0 +1,41 @@
[Unit]
Description=AIOS disabled-by-default HTTPS edge for GPT read-only Online Task ingress
After=network-online.target aios-gpt-online-task-ingress.service
Wants=network-online.target aios-gpt-online-task-ingress.service
ConditionPathExists=/etc/aios-gitops/gpt-https-edge.approved
[Service]
Type=simple
DynamicUser=yes
LoadCredential=tls_cert:/etc/aios-gitops/gpt-https-edge-tls.crt
LoadCredential=tls_key:/etc/aios-gitops/gpt-https-edge-tls.key
Environment=AIOS_GPT_EDGE_TLS_CERT_FILE=%d/tls_cert
Environment=AIOS_GPT_EDGE_TLS_KEY_FILE=%d/tls_key
Environment=AIOS_GPT_EDGE_HOST=127.0.0.1
Environment=AIOS_GPT_EDGE_PORT=18443
Environment=AIOS_GPT_EDGE_PUBLIC_BIND_APPROVED=0
Environment=AIOS_GPT_EDGE_PUBLIC_DOMAIN=
ExecStart=/usr/bin/python3 -B /opt/aios/current/active-runtime/app/aios_gpt_https_edge.py
Restart=on-failure
RestartSec=2
NoNewPrivileges=yes
PrivateTmp=yes
PrivateDevices=yes
ProtectSystem=strict
ProtectHome=yes
ProtectKernelTunables=yes
ProtectKernelModules=yes
ProtectControlGroups=yes
ProtectKernelLogs=yes
ProtectClock=yes
LockPersonality=yes
RestrictSUIDSGID=yes
RestrictRealtime=yes
RestrictNamespaces=yes
MemoryDenyWriteExecute=yes
RestrictAddressFamilies=AF_INET AF_INET6
InaccessiblePaths=/data/aios-gitops /etc/aios-gitops /home /var/lib/aios-agent-task
UMask=0077
[Install]
WantedBy=multi-user.target
@@ -0,0 +1,45 @@
[Unit]
Description=AIOS external GPT read-only Online Task ingress
After=network.target aios-chatgpt-bridge-v2-staging.service aios-agent-task-api.service
Wants=aios-chatgpt-bridge-v2-staging.service aios-agent-task-api.service
[Service]
Type=simple
DynamicUser=yes
StateDirectory=aios-gpt-online-task-ingress
StateDirectoryMode=0750
LoadCredential=gpt_ingress_token:/etc/aios-gitops/gpt-online-task-ingress.token
LoadCredential=agent_task_control_token:/etc/aios-gitops/agent-task-control.token
Environment=AIOS_GPT_INGRESS_TOKEN_FILE=%d/gpt_ingress_token
Environment=AIOS_AGENT_TASK_CONTROL_TOKEN_FILE=%d/agent_task_control_token
Environment=AIOS_GPT_INGRESS_STATE_ROOT=%S/aios-gpt-online-task-ingress
Environment=AIOS_GPT_INGRESS_HOST=127.0.0.1
Environment=AIOS_GPT_INGRESS_PORT=18945
Environment=AIOS_GOVERNED_WRITE_API_URL=http://127.0.0.1:18892
Environment=AIOS_AGENT_TASK_API_URL=http://127.0.0.1:18940
ExecStart=/usr/bin/python3 -B /opt/aios/current/active-runtime/app/aios_gpt_online_task_ingress.py
Restart=on-failure
RestartSec=2
NoNewPrivileges=yes
PrivateTmp=yes
PrivateDevices=yes
ProtectSystem=strict
ProtectHome=yes
ProtectKernelTunables=yes
ProtectKernelModules=yes
ProtectControlGroups=yes
ProtectKernelLogs=yes
ProtectClock=yes
LockPersonality=yes
RestrictSUIDSGID=yes
RestrictRealtime=yes
RestrictNamespaces=yes
MemoryDenyWriteExecute=yes
RestrictAddressFamilies=AF_UNIX AF_INET
IPAddressDeny=any
IPAddressAllow=127.0.0.0/8
InaccessiblePaths=/data/aios-gitops /etc/aios-gitops /home
UMask=0077
[Install]
WantedBy=multi-user.target
@@ -0,0 +1,120 @@
# Disabled-by-default HTTPS edge for external GPT Online Task access
## Purpose
The internal ingress (`127.0.0.1:18945`) remains loopback-only. This edge is the only component
allowed to become Internet-facing, and only after a separate owner approval.
It forwards only:
```text
POST /v1/read-only-tasks
GET /v1/read-only-tasks/{request_id}
GET /openapi.json
GET /health
```
It never proxies:
```text
18892 canonical Bridge
18940 Task API
WriterLease
commit
verification
release
tag
baseline
arbitrary URLs
```
## Default state
The systemd unit is disabled by policy unless the owner creates:
```text
/etc/aios-gitops/gpt-https-edge.approved
```
The base unit still binds only to:
```text
127.0.0.1:18443
AIOS_GPT_EDGE_PUBLIC_BIND_APPROVED=0
```
Non-loopback bind is rejected by code unless an owner-controlled drop-in sets:
```text
AIOS_GPT_EDGE_PUBLIC_BIND_APPROVED=1
AIOS_GPT_EDGE_HOST=0.0.0.0
AIOS_GPT_EDGE_PUBLIC_DOMAIN=<approved hostname>
```
This repository candidate does not create that drop-in or approval marker.
## TLS
TLS certificate/key are owner-managed systemd credentials:
```text
/etc/aios-gitops/gpt-https-edge-tls.crt
/etc/aios-gitops/gpt-https-edge-tls.key
```
The service requires TLS 1.2 or newer, disables TLS compression, and never logs or returns key
material.
Certificate/key issuance and renewal are external owner responsibilities until a separately
governed ACME workflow is implemented.
## Request protections
The edge provides:
- 64 KiB request cap;
- 256 KiB upstream response cap;
- JSON validation before proxying;
- fixed upstream `http://127.0.0.1:18945`;
- Authorization-only header forwarding;
- no Cookie/X-Forwarded-* trust;
- route/method allowlist;
- per-source-IP in-memory rate limiting;
- bounded concurrent request handling;
- optional exact Host-header enforcement;
- HSTS / no-store / nosniff / no-referrer response headers.
The rate limiter is intentionally simple and local. Multi-node/global abuse protection is outside
the current one-host architecture.
## Authentication
The HTTPS edge does not create a new authentication scheme. It forwards the external Bearer
credential to the loopback GPT ingress, which verifies `gpt_ingress_token`.
The edge never receives the AIOS control-plane token.
## Deployment boundary
Public activation is a high-risk network operation and requires explicit owner approval. Before
activation verify:
```text
host-side GPT ingress E2E=VERIFIED
owner ingress token provisioned
TLS certificate/key provisioned
public hostname owned and DNS configured
firewall/network exposure reviewed
explicit public-bind approval recorded
rollback plan available
```
Only after those gates may an owner-authorized runtime drop-in bind this service publicly.
Until then:
```text
GPT_HTTPS_EDGE_IMPLEMENTATION=candidate
PUBLIC_NETWORK_EXPOSURE=NONE
PUBLIC_CUSTOM_GPT_DIRECT_AI0S_ACCESS=NOT_VERIFIED
```
@@ -0,0 +1,138 @@
# External GPT → Online Task ingress
## Scope
This component closes the current architectural gap between an external Custom GPT and AIOS
without exposing the internal Task API (`18940`) or canonical Bridge (`18892`) directly.
The first supported public-facing capability is intentionally read-only:
```text
authenticated external intent
→ host-side ingress
→ canonical /v2/governed-task
→ canonical /v2/execution-envelope
→ persistent generic worker
→ source_capture result
→ official control-plane verification
```
The ingress itself never claims, heartbeats, verifies, commits, acquires WriterLease, or writes
protected refs.
## Security boundary
The service binds only to loopback (`127.0.0.1:18945`). A future owner-approved TLS reverse proxy
or tunnel may expose this service externally. Direct non-loopback binding is denied by code.
Two independent credentials are projected by systemd:
- `gpt_ingress_token`: authenticates the external caller to this ingress.
- `agent_task_control_token`: lets the ingress call the loopback AIOS control plane.
Neither credential is stored in Git, SQLite, task payloads, results, logs, or API responses.
The ingress has no repository filesystem access.
## Caller-controlled fields
Allowed:
```text
request_id
goal
instructions
success_criteria
constraints.max_files
constraints.focus_paths
constraints.notes
```
Not caller-controlled:
```text
repository
base_oid
expected_branch_oid
target_branch
branch_mode
generation
risk
priority
max_attempts
capabilities
action/adapter
WriterLease
worker identity
credentials
verification decision
main/production/tag/baseline permissions
```
All external tasks are hard-bound to:
```text
repository=aios/aios
capabilities=[git.read, git.test]
action=source_capture
writer_lease=false
repository_mutation=forbidden
control_plane_side_effects=forbidden
credential_access=forbidden
```
## Idempotency
`request_id` is the durable external idempotency boundary.
The ingress stores only:
```text
request hash
derived AIOS task id
canonical job id
base oid
sanitized receipt
state
```
An exact retry returns the same receipt. Reusing a `request_id` with different content returns
`IDEMPOTENCY_CONFLICT`.
A crash after canonical task creation can recover the same binding from the Task API rather than
creating a replacement Task.
## Status
`GET /v1/read-only-tasks/{request_id}` returns only sanitized state:
```text
task/job ids
status
attempt
whether claimed
result classification
official verification decision/classification
source snapshot hash/count when available
```
It does not proxy raw Task metadata, execution envelopes, result text, credentials, or source files.
## Public exposure
This candidate does **not** make AIOS publicly reachable. Public exposure requires a separately
approved HTTPS ingress/reverse proxy with:
- TLS;
- external authentication lifecycle;
- rate limiting / abuse controls;
- request size limits;
- observability;
- explicit owner approval for the network exposure.
Until that step is verified:
```text
HOST_SIDE_EXTERNAL_GPT_ADAPTER=implemented/staging-candidate
PUBLIC_CUSTOM_GPT_DIRECT_AI0S_ACCESS=not verified
```
+205
View File
@@ -0,0 +1,205 @@
from __future__ import annotations
from email.message import Message
import json
from pathlib import Path
import stat
import sys
import pytest
ROOT=Path(__file__).resolve().parents[1]
APP=ROOT/"active-runtime/app"
sys.path.insert(0,str(APP))
import aios_gpt_https_edge as edge
class Headers(dict):
def get(self,key,default=None):
return super().get(key,default)
def test_default_and_public_bind_require_explicit_owner_approval():
assert edge.public_bind_allowed("127.0.0.1","0")=="127.0.0.1"
assert edge.public_bind_allowed("::1","0")=="::1"
with pytest.raises(RuntimeError,match="OWNER_APPROVAL_REQUIRED"):
edge.public_bind_allowed("0.0.0.0","0")
with pytest.raises(RuntimeError,match="OWNER_APPROVAL_REQUIRED"):
edge.public_bind_allowed("::","")
assert edge.public_bind_allowed("0.0.0.0","1")=="0.0.0.0"
def test_arbitrary_public_bind_address_is_denied_even_with_approval():
with pytest.raises(RuntimeError,match="BIND_ADDRESS_INVALID"):
edge.public_bind_allowed("192.0.2.10","1")
def test_public_domain_validation():
assert edge.validated_public_domain("tasks.example.com")=="tasks.example.com"
assert edge.validated_public_domain("")==""
with pytest.raises(RuntimeError,match="PUBLIC_DOMAIN_INVALID"):
edge.validated_public_domain("https://example.com")
with pytest.raises(RuntimeError,match="PUBLIC_DOMAIN_INVALID"):
edge.validated_public_domain("localhost")
def test_route_allowlist_accepts_only_readonly_api():
assert edge.allowed_route("POST","/v1/read-only-tasks")=="/v1/read-only-tasks"
assert edge.allowed_route("GET","/v1/read-only-tasks/external-request-0001")==(
"/v1/read-only-tasks/external-request-0001"
)
assert edge.allowed_route("GET","/health")=="/health"
assert edge.allowed_route("GET","/openapi.json")=="/openapi.json"
for method,path in [
("POST","/v2/governed-task"),
("GET","/v1/tasks/x"),
("POST","/v1/read-only-tasks/x"),
("DELETE","/v1/read-only-tasks/x"),
]:
with pytest.raises(edge.EdgeError,match="ROUTE_DENY"):
edge.allowed_route(method,path)
def test_query_and_fragment_are_denied():
with pytest.raises(edge.EdgeError,match="QUERY_OR_FRAGMENT_DENY"):
edge.allowed_route("GET","/health?x=1")
with pytest.raises(edge.EdgeError,match="QUERY_OR_FRAGMENT_DENY"):
edge.allowed_route("GET","/openapi.json#x")
def test_forwarded_headers_are_minimal_and_require_bearer():
incoming=Headers({
"Authorization":"Bearer "+"a"*40,
"Content-Type":"application/json; charset=utf-8",
"Cookie":"secret=1",
"X-Forwarded-For":"203.0.113.10",
"X-Api-Key":"do-not-forward",
})
forwarded=edge.forwarded_headers(incoming,body=True)
assert forwarded=={
"Accept":"application/json",
"Authorization":"Bearer "+"a"*40,
"Content-Type":"application/json",
}
with pytest.raises(edge.EdgeError,match="AUTHORIZATION_REQUIRED"):
edge.forwarded_headers(Headers({}),body=False)
def test_invalid_content_type_is_denied():
with pytest.raises(edge.EdgeError,match="CONTENT_TYPE_INVALID"):
edge.forwarded_headers(
Headers({
"Authorization":"Bearer "+"a"*40,
"Content-Type":"text/plain",
}),
body=True,
)
def test_rate_limiter_caps_window_and_allows_expiry():
now=[100.0]
limiter=edge.RateLimiter(window_seconds=60,limit=2,burst=1,now_fn=lambda:now[0])
assert limiter.allowed("client")
assert limiter.allowed("client")
assert limiter.allowed("client")
assert not limiter.allowed("client")
now[0]=161.0
assert limiter.allowed("client")
def test_rate_limiter_client_table_is_bounded():
now=[100.0]
limiter=edge.RateLimiter(
window_seconds=60,
limit=10,
burst=0,
max_clients=2,
now_fn=lambda:now[0],
)
assert limiter.allowed("a")
assert limiter.allowed("b")
assert not limiter.allowed("c")
now[0]=161.0
assert limiter.allowed("c")
assert len(limiter._events) <= 2
def test_audit_source_does_not_log_sensitive_request_material():
source=(ROOT/"active-runtime/app/aios_gpt_https_edge.py").read_text()
assert '"authorization", "body", "token", "cookie", "client_ip"' in source
assert "_client_pseudonym" in source
def test_proxy_upstream_is_fixed():
proxy=edge.Proxy()
assert proxy.upstream=="http://127.0.0.1:18945"
bad=edge.Proxy(upstream="http://127.0.0.1:18892")
with pytest.raises(edge.EdgeError,match="UPSTREAM_DRIFT_DENY"):
bad.request("GET","/health",{"Authorization":"Bearer "+"a"*40},None)
def test_public_bind_requires_approved_domain():
assert edge.validated_edge_identity("127.0.0.1","0","")==("127.0.0.1","")
with pytest.raises(RuntimeError,match="PUBLIC_DOMAIN_REQUIRED"):
edge.validated_edge_identity("0.0.0.0","1","")
assert edge.validated_edge_identity(
"0.0.0.0","1","tasks.example.com"
)==("0.0.0.0","tasks.example.com")
def test_tls_key_requires_no_group_or_other_permissions(tmp_path):
key=tmp_path/"key.pem"
key.write_text("x"*64,encoding="utf-8")
key.chmod(0o600)
assert edge.validate_tls_file(key,key=True)==key
key.chmod(0o644)
with pytest.raises(RuntimeError,match="TLS_KEY_MODE_INVALID"):
edge.validate_tls_file(key,key=True)
def test_tls_symlink_is_denied(tmp_path):
real=tmp_path/"cert.pem"
real.write_text("x"*64,encoding="utf-8")
link=tmp_path/"link.pem"
link.symlink_to(real)
with pytest.raises(RuntimeError,match="TLS_FILE_INVALID"):
edge.validate_tls_file(link,key=False)
def test_systemd_unit_is_disabled_by_owner_approval_condition_and_loopback_default():
unit=(ROOT/"deploy/systemd/aios-gpt-https-edge.service").read_text()
assert "ConditionPathExists=/etc/aios-gitops/gpt-https-edge.approved" in unit
assert "AIOS_GPT_EDGE_HOST=127.0.0.1" in unit
assert "AIOS_GPT_EDGE_PUBLIC_BIND_APPROVED=0" in unit
assert "AIOS_GPT_EDGE_PORT=18443" in unit
assert "LoadCredential=tls_cert:" in unit
assert "LoadCredential=tls_key:" in unit
assert "InaccessiblePaths=/data/aios-gitops" in unit
assert "InaccessiblePaths=" in unit and "/var/lib/aios-agent-task" in unit
assert "NoNewPrivileges=yes" in unit
assert "ProtectSystem=strict" in unit
def test_systemd_unit_does_not_reference_internal_control_credentials():
unit=(ROOT/"deploy/systemd/aios-gpt-https-edge.service").read_text()
assert "agent_task_control" not in unit
assert "gitea" not in unit.lower()
assert "18892" not in unit
assert "18940" not in unit
def test_edge_source_does_not_proxy_internal_bridge_or_task_api():
source=(ROOT/"active-runtime/app/aios_gpt_https_edge.py").read_text()
assert 'UPSTREAM = "http://127.0.0.1:18945"' in source
assert "18892" not in source
assert "18940" not in source
assert "/v2/governed-task" not in source
assert "/v1/tasks/" not in source
def test_docs_keep_public_activation_separately_approved():
doc=(ROOT/"docs/superpowers/specs/2026-08-19-gpt-https-edge.md").read_text()
assert "explicit owner approval" in doc.lower()
assert "PUBLIC_NETWORK_EXPOSURE=NONE" in doc
assert "PUBLIC_CUSTOM_GPT_DIRECT_AI0S_ACCESS=NOT_VERIFIED" in doc
+342
View File
@@ -0,0 +1,342 @@
from __future__ import annotations
import json
from pathlib import Path
import sqlite3
import sys
import pytest
ROOT=Path(__file__).resolve().parents[1]
APP=ROOT/"active-runtime/app"
sys.path.insert(0,str(APP))
from aios_gpt_online_task_ingress import (
IngressError,
IngressService,
Store,
READONLY_CAPABILITIES,
branch_for,
normalized_request,
openapi_document,
task_id_for,
validated_bind_host,
)
MAIN="3244f0f17f8845592ac94d585f5ebd65693c9f29"
JOB="job-0123456789abcdef0123456789abcdef"
def request(request_id="external-request-0001", **overrides):
value={
"schema":"aios.gpt-online-task-ingress.request.v1",
"request_id":request_id,
"goal":"Inspect the repository for durable worker state.",
"instructions":"Read only. Return a concise source analysis.",
"success_criteria":[
{"id":"analysis","description":"Return a source-backed analysis."}
],
"constraints":{
"max_files":50,
"focus_paths":["active-runtime/app","tests"],
"notes":"Do not mutate repository state.",
},
}
value.update(overrides)
return value
class FakeUpstream:
def __init__(self):
self.created=[]
self.projected=[]
self.tasks={}
self.snapshot={"authoritative_head_oid":MAIN}
def control_snapshot(self):
return dict(self.snapshot)
def create_governed_task(self, body):
self.created.append(dict(body))
task_id=body["task_id"]
job_id=JOB
self.tasks[task_id]={
"task_id":task_id,
"status":"PROJECTED",
"attempt":0,
"metadata":{
"execution":{
"task_id":task_id,
"job_id":job_id,
"base_oid":body["base_oid"],
"action":"source_capture",
"capability_scope":list(READONLY_CAPABILITIES),
"governance":{"writer_lease":False},
}
},
}
return 201,{"task_id":task_id,"job_id":job_id,"state":"BOUND"}
def execution_envelope(self, body):
self.projected.append(dict(body))
task_id=body["task_id"]
return 200,{
"schema":"aios.online-agent.execution.v2",
"task_id":task_id,
"job_id":body["job_id"],
"repository":"aios/aios",
"base_oid":MAIN,
"action":"source_capture",
"capability_scope":list(READONLY_CAPABILITIES),
"governance":{"writer_lease":False},
}
def get_task(self, task_id):
value=self.tasks.get(task_id)
return (404,{}) if value is None else (200,dict(value))
def service(tmp_path):
upstream=FakeUpstream()
store=Store(tmp_path/"state.sqlite3")
return IngressService(upstream,store),upstream,store
def test_request_schema_is_narrow_and_rejects_capability_or_execution_control():
value=normalized_request(request())
assert value["goal"].startswith("Inspect")
for field in ("capability_scope","required_capabilities","action","adapter","repository","base_oid"):
bad=request()
bad[field]="evil"
with pytest.raises(IngressError,match="UNKNOWN_FIELDS"):
normalized_request(bad)
def test_constraints_are_bounded_and_path_traversal_is_denied():
bad=request(constraints={"focus_paths":["../etc/passwd"]})
with pytest.raises(IngressError,match="FOCUS_PATHS_INVALID"):
normalized_request(bad)
bad=request(constraints={"max_files":1000})
with pytest.raises(IngressError,match="MAX_FILES_INVALID"):
normalized_request(bad)
def test_non_loopback_bind_is_denied():
assert validated_bind_host("127.0.0.1")=="127.0.0.1"
with pytest.raises(RuntimeError,match="GPT_INGRESS_NON_LOOPBACK_BIND_DENY"):
validated_bind_host("0.0.0.0")
with pytest.raises(RuntimeError,match="GPT_INGRESS_NON_LOOPBACK_BIND_DENY"):
validated_bind_host("192.0.2.10")
def test_task_and_branch_ids_are_deterministic_and_bounded():
a=task_id_for("external-request-0001")
b=task_id_for("external-request-0001")
c=task_id_for("external-request-0002")
assert a==b
assert a!=c
assert a.startswith("gpt-readonly-")
branch=branch_for(a)
assert branch.startswith("agent/external-gpt-readonly/")
assert len(a)<180
def test_create_translates_to_canonical_readonly_governed_task(tmp_path):
svc,upstream,store=service(tmp_path)
response=svc.create(request())
assert response["state"]=="BOUND"
assert response["write_access"] is False
assert response["official_verification_required"] is True
assert response["capabilities"]==list(READONLY_CAPABILITIES)
assert len(upstream.created)==1
body=upstream.created[0]
assert body["repository"]=="aios/aios"
assert body["base_oid"]==MAIN
assert body["expected_branch_oid"]==MAIN
assert body["branch_mode"]=="CREATE_NEW"
assert body["risk"]=="low"
assert body["priority"]==0
assert body["max_attempts"]==3
assert body["require_online_task_projection"] is True
assert body["online_task"]["required_capabilities"]==list(READONLY_CAPABILITIES)
assert body["online_task"]["constraints"]["repository_mutation"]=="forbidden"
assert body["online_task"]["constraints"]["credential_access"]=="forbidden"
assert body["execution"]["action"]=="source_capture"
assert body["execution"]["adapter"]=="source_capture"
assert body["execution"]["capability_scope"]==list(READONLY_CAPABILITIES)
assert "writer_lease" not in body["execution"]
assert len(upstream.projected)==1
projection=upstream.projected[0]
assert projection["task_id"]==response["task_id"]
assert projection["job_id"]==JOB
assert projection["required_capabilities"]==list(READONLY_CAPABILITIES)
row=store.get("external-request-0001")
assert row is not None
assert row["state"]=="BOUND"
assert row["job_id"]==JOB
assert row["base_oid"]==MAIN
def test_exact_retry_is_idempotent_without_duplicate_bridge_call(tmp_path):
svc,upstream,_=service(tmp_path)
first=svc.create(request())
second=svc.create(request())
assert second==first
assert len(upstream.created)==1
assert len(upstream.projected)==1
def test_same_request_id_with_different_content_is_conflict(tmp_path):
svc,upstream,_=service(tmp_path)
svc.create(request())
with pytest.raises(IngressError,match="IDEMPOTENCY_CONFLICT"):
svc.create(request(goal="Different goal."))
assert len(upstream.created)==1
def test_pending_request_recovers_existing_canonical_task_after_crash(tmp_path):
svc,upstream,store=service(tmp_path)
raw=normalized_request(request())
task_id=task_id_for(raw["request_id"])
store.reserve(raw,task_id)
upstream.tasks[task_id]={
"task_id":task_id,
"status":"PROJECTED",
"attempt":0,
"metadata":{
"execution":{
"task_id":task_id,
"job_id":JOB,
"base_oid":MAIN,
"action":"source_capture",
"capability_scope":list(READONLY_CAPABILITIES),
"governance":{"writer_lease":False},
}
},
}
result=svc.create(request())
assert result["job_id"]==JOB
assert result["task_id"]==task_id
assert len(upstream.created)==0
row=store.get(raw["request_id"])
assert row["state"]=="BOUND"
def test_status_is_sanitized_and_never_proxies_raw_execution_or_result_text(tmp_path):
svc,upstream,store=service(tmp_path)
created=svc.create(request())
task_id=created["task_id"]
upstream.tasks[task_id]={
"task_id":task_id,
"status":"SUCCEEDED",
"attempt":1,
"claimed_by":"online-engineering-worker-cn-network-mkt-generic-20260815",
"metadata":{
"execution":{
"job_id":JOB,
"base_oid":MAIN,
"action":"source_capture",
"capability_scope":list(READONLY_CAPABILITIES),
"governance":{"writer_lease":False},
"secret_marker":"do-not-return",
}
},
"result":{
"status":"SUCCEEDED",
"classification":"NEEDS_REWORK_SOURCE_CAPTURE",
"execution_mode":"source_capture",
"output_text":"raw source text that must not be proxied",
"source_snapshot":{
"payload_sha256":"a"*64,
"file_count":42,
"files":["secret/path"],
},
},
"verification":{
"decision":"SUCCEEDED",
"classification":"GENERIC_ONLINE_TASK_AUTO_CONSUMPTION_VERIFIED",
"private":"do-not-return",
},
}
status=svc.status("external-request-0001")
assert status["state"]=="SUCCEEDED"
assert status["attempt"]==1
assert status["claimed"] is True
assert status["official_verification"]=="SUCCEEDED"
assert status["source_snapshot_sha256"]=="a"*64
assert status["source_snapshot_file_count"]==42
serialized=json.dumps(status)
assert "raw source text" not in serialized
assert "secret_marker" not in serialized
assert "secret/path" not in serialized
assert "do-not-return" not in serialized
def test_pending_status_can_recover_job_binding(tmp_path):
svc,upstream,store=service(tmp_path)
raw=normalized_request(request())
task_id=task_id_for(raw["request_id"])
store.reserve(raw,task_id)
upstream.tasks[task_id]={
"task_id":task_id,
"status":"PROJECTED",
"attempt":0,
"metadata":{
"execution":{
"job_id":JOB,
"base_oid":MAIN,
"action":"source_capture",
"capability_scope":list(READONLY_CAPABILITIES),
"governance":{"writer_lease":False},
}
},
}
value=svc.status(raw["request_id"])
assert value["job_id"]==JOB
assert store.get(raw["request_id"])["state"]=="BOUND"
def test_openapi_exposes_only_create_readonly_and_status_operations():
doc=openapi_document()
assert doc["openapi"]=="3.1.0"
paths=doc["paths"]
assert set(paths)=={
"/v1/read-only-tasks",
"/v1/read-only-tasks/{request_id}",
}
rendered=json.dumps(doc)
for forbidden in ("writer-lease","commit","verify","production","tag","baseline"):
assert forbidden not in rendered.lower()
def test_systemd_unit_is_loopback_credential_isolated_and_has_no_repository_access():
unit=(ROOT/"deploy/systemd/aios-gpt-online-task-ingress.service").read_text()
assert "DynamicUser=yes" in unit
assert "LoadCredential=gpt_ingress_token:" in unit
assert "LoadCredential=agent_task_control_token:" in unit
assert "AIOS_GPT_INGRESS_HOST=127.0.0.1" in unit
assert "AIOS_GOVERNED_WRITE_API_URL=http://127.0.0.1:18892" in unit
assert "AIOS_AGENT_TASK_API_URL=http://127.0.0.1:18940" in unit
assert "IPAddressDeny=any" in unit
assert "IPAddressAllow=127.0.0.0/8" in unit
assert "InaccessiblePaths=/data/aios-gitops /etc/aios-gitops /home" in unit
assert "ProtectSystem=strict" in unit
assert "NoNewPrivileges=yes" in unit
assert "MemoryDenyWriteExecute=yes" in unit
assert "0.0.0.0" not in unit
def test_ingress_sqlite_contains_no_request_body_or_credentials(tmp_path):
svc,upstream,store=service(tmp_path)
svc.create(request(instructions="sensitive-looking but non-secret user text"))
con=sqlite3.connect(store.path)
columns=[row[1] for row in con.execute("pragma table_info(external_task_requests)")]
assert "request_json" not in columns
assert "goal" not in columns
assert "instructions" not in columns
assert "token" not in " ".join(columns).lower()