Files
node-26/drb-edge-node/app/internal/credentials.py
Logan CusanoandClaude Opus 5.5 c2c349043b Node self-heals its API key; one-stop install.sh; real host-level OTA updater (#14, #15)
install.sh (#14): after enrolling it now BLOCKS until an admin approves,
printing "Please have an admin approve node '<id>' at <app>/settings/nodes
to continue", polling GET /nodes/{id}/credentials with the pickup secret
(no default timeout; Ctrl-C safe; re-run resumes from configs/pickup_secret).
A re-run with a key on disk re-checks it against C2 and replaces a stale
(reissued) key. credentials.json is merged atomically so the dashboard auth
salt/secret survive. edge-node is ALWAYS force-recreated at the end, so a key
written after the container started is loaded. --wait-approval N caps the
wait; 0 = don't wait. git fetch uses --force so a re-cut v1 tag is accepted.

edge-node (#14): with no key at startup, or on a broker auth refusal
(CONNACK 4/5/134/135), mqtt_manager re-reads credentials.json, else fetches
the key over HTTPS (key_pickup.py, pickup secret from /configs), persists it
and rebuilds the paho client in place. Single-flight, 30s..15min backoff.
A key pushed over MQTT while connected is applied for the next reconnect.

OTA (#15): node_update no longer os._exit()s. It drops
configs/update-requested; install.sh installs scripts/install-updater.sh's
drb-update.{service,timer,path}. The path unit fires on the sentinel, the
timer (~15 min) does an HTTPS check-in (POST /nodes/{id}/update-check,
server-26 PR) so offline/locked-out nodes still update. drb-update.sh only
installs the repo/ref/registry in root-owned /etc/drb/updater.conf; C2's
answer is just a timestamp; origin and registry mismatches abort; creds go
to curl via a 0600 header file.

Tests: test_credential_recovery.py, test_host_updater.py (runs the real
updater script with stub git/docker/curl).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-04 01:09:39 -04:00

135 lines
4.7 KiB
Python

"""
Manages the persisted node API key, plus the local-auth signing material used
by app/internal/auth.py.
The API key is provisioned by the C2 server after an admin approves the node.
install.sh fetches it over HTTPS (GET /nodes/{id}/credentials + the pickup
secret it saved to /configs/pickup_secret) and writes /configs/credentials.json;
the running app can also fetch it itself (app/internal/key_pickup.py) and
re-read the file at any time (reload_api_key), so a key written after startup
is picked up without a container restart (node-26#14). The legacy MQTT
delivery (nodes/{id}/api_key) still saves here too.
The scrypt salt and session-signing secret are generated locally on first boot
(never provisioned externally) and persisted the same way, so dashboard
sessions survive a container restart instead of forcing every operator to
re-login whenever the node restarts.
"""
import json
import os
import secrets
from pathlib import Path
from app.config import settings
from app.internal.logger import logger
_CREDS_FILE = Path(settings.config_path) / "credentials.json"
_PICKUP_FILE = Path(settings.config_path) / "pickup_secret"
_api_key: str | None = None
_auth_salt: bytes | None = None
_session_secret: bytes | None = None
def load() -> None:
"""Load persisted credentials from disk on startup."""
global _api_key, _auth_salt, _session_secret
if _CREDS_FILE.exists():
try:
data = json.loads(_CREDS_FILE.read_text())
_api_key = data.get("api_key")
if data.get("auth_salt"):
_auth_salt = bytes.fromhex(data["auth_salt"])
if data.get("session_secret"):
_session_secret = bytes.fromhex(data["session_secret"])
if _api_key:
logger.info("Node credentials loaded from disk.")
except Exception as e:
logger.warning(f"Could not read credentials file: {e}")
_ensure_auth_material()
def _ensure_auth_material() -> None:
"""Generate (once) and persist the local-auth salt + session secret."""
global _auth_salt, _session_secret
changed = False
if _auth_salt is None:
_auth_salt = secrets.token_bytes(16)
changed = True
if _session_secret is None:
_session_secret = secrets.token_bytes(32)
changed = True
if changed:
_write()
logger.info("Generated local-auth signing material (first boot).")
def get_auth_salt() -> bytes:
"""Scrypt salt for dashboard password hashing — generated once, persisted."""
if _auth_salt is None:
_ensure_auth_material()
return _auth_salt # type: ignore[return-value]
def get_session_secret() -> bytes:
"""HMAC key used to sign dashboard session cookies — generated once, persisted."""
if _session_secret is None:
_ensure_auth_material()
return _session_secret # type: ignore[return-value]
def get_api_key() -> str | None:
return _api_key
def reload_api_key() -> str | None:
"""Re-read the api_key from disk (install.sh, or an operator, may have
written it after startup). Returns the key now in effect. Only the api_key
is taken from the file — the auth material already in memory stays."""
global _api_key
try:
data = json.loads(_CREDS_FILE.read_text())
except FileNotFoundError:
return _api_key
except Exception as e:
logger.warning(f"Could not re-read credentials file: {e}")
return _api_key
key = data.get("api_key")
if key and key != _api_key:
_api_key = key
logger.info("Node API key re-read from disk (changed since it was last loaded).")
return _api_key
def get_pickup_secret() -> str | None:
"""The one-time pickup secret install.sh saved at enrollment, if any."""
try:
secret = _PICKUP_FILE.read_text().strip()
except FileNotFoundError:
return None
except Exception as e:
logger.warning(f"Could not read pickup secret: {e}")
return None
return secret or None
def save_api_key(key: str) -> None:
global _api_key
_api_key = key
_write()
logger.info("Node API key saved to disk.")
def _write() -> None:
_CREDS_FILE.parent.mkdir(parents=True, exist_ok=True)
data: dict = {"api_key": _api_key}
if _auth_salt is not None:
data["auth_salt"] = _auth_salt.hex()
if _session_secret is not None:
data["session_secret"] = _session_secret.hex()
# Atomic replace with 0600: install.sh on the host writes this same file,
# and a torn half-written JSON would lose the key AND the auth material.
tmp = _CREDS_FILE.with_name(_CREDS_FILE.name + ".tmp")
fd = os.open(tmp, os.O_WRONLY | os.O_CREAT | os.O_TRUNC, 0o600)
with os.fdopen(fd, "w") as f:
f.write(json.dumps(data))
os.replace(tmp, _CREDS_FILE)