Two layered changes shipped in this branch: == 1.0.0-22: app-level authentication == The dashboard previously had only an IP allowlist. Adds username + bcrypt password auth, signed-cookie sessions, and a "first user setup" flow. * New app/auth.py: User dataclass, bcrypt hash/verify, get_user_by_id/ username, create_user, touch_last_login, FastAPI `get_current_user` dependency. Session secret loaded from SESSION_SECRET env or persisted to /data/session_secret. * New app/auth_cli.py: `python -m app.auth_cli list|reset|add` for out-of-band user management. Passwords always read from a TTY prompt. * Schema: idempotent ALTER for `users` table (id, username unique, password_hash, full_name, is_admin, created_at, last_login_at). * main.py: SessionMiddleware (HMAC-signed cookie, max-age 7 days, SameSite=strict — see hardening section) + _AuthGateMiddleware that populates request.state.current_user and bounces unauth'd HTML GETs to /login while returning 401 JSON for everything else. * Routes: GET /login renders first-user-setup form when users table is empty otherwise sign-in form; POST /login; POST /api/v1/auth/setup (only works while empty); GET|POST /logout. * Bootstrap: env vars INITIAL_ADMIN_USERNAME + INITIAL_ADMIN_PASSWORD create the first admin on startup if both set AND users table empty. Ignored thereafter — change passwords via UI or CLI. * Layout: header shows current_user.full_name|username + Logout link. Modal operator field auto-fills from the logged-in user via <meta name="default-operator"> rendered in layout (replaces the localStorage-only previous behaviour). * requirements.txt: pinned bcrypt>=4.0,<5.0, itsdangerous>=2.1, python-multipart>=0.0.7. First step toward addressing the unpinned-deps gotcha. * New app/templates/login.html with first-user-setup variant. == 1.0.0-23: hardening sweep == Closes the eight-item gap audit: * DB retention + automated backup. New app/retention.py runs daily at 03:00 local. Nulls burnin_stages.log_text on stages older than retention_log_days (default 35), VACUUMs to reclaim pages, then runs `sqlite3 .backup` to /data/backups/app-YYYY-MM-DD.db keeping the retention_backup_keep most recent (default 14). Wired into the lifespan supervisor next to mailer/poller. * CSRF mitigation. SessionMiddleware bumped to SameSite=strict so the browser refuses to send the session cookie on cross-site POSTs — removes the actual CSRF vector. Trade-off: external links into the app require re-auth. * Login rate limiting. In-memory per-username AND per-source-IP failure counters in auth.py. 10 failures within 10 min trips a 15-min lockout for both keys. Returns HTTP 429 with a clear "try again in N min" message. Cleared on successful login. * Login audit events. New event types in audit_events: user_login, user_login_failed, user_login_locked_out, user_logout, user_password_changed. All include source IP. Recorded via auth.audit_auth_event(). * Password change UI. Header link "Change password" opens templates/components/modal_password.html (current/new/confirm). Posts to POST /api/v1/auth/change-password — bcrypt-verifies current, requires >=8 char new pw, writes audit event. * NVMe burn-in path. _stage_surface_validate now detects nvme* devnames and routes to _stage_surface_validate_nvme() which runs `nvme format -s 1 --force` (cryptographic erase). Seconds vs hours of badblocks, exercises the controller's secure-erase. Falls back to badblocks if nvme-cli isn't installed. Post-format SMART check. * Mounted-FS detection. ssh_client.get_mounted_drives() runs `findmnt -no SOURCE`, parses non-ZFS sources back to base devnames. Poller treats them as pool_name='(mounted)', pool_role='mounted'. Confirm token DESTROY MOUNTED FILESYSTEM, distinct purple styling, audit event mounted_drive_unlocked, daily-report banner picks it up. * Deeper /health. Real readiness check — DB write probe (PRAGMA journal_mode), poller freshness (age <= 3x stale_threshold), SSH test_connection() when configured. Returns 503 when any check fails so a proxy/orchestrator can take the container out of rotation. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
170 lines
6.4 KiB
Python
170 lines
6.4 KiB
Python
import aiosqlite
|
|
from pathlib import Path
|
|
|
|
from app.config import settings
|
|
|
|
SCHEMA = """
|
|
CREATE TABLE IF NOT EXISTS drives (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
truenas_disk_id TEXT UNIQUE NOT NULL,
|
|
devname TEXT NOT NULL,
|
|
serial TEXT,
|
|
model TEXT,
|
|
size_bytes INTEGER,
|
|
temperature_c INTEGER,
|
|
smart_health TEXT DEFAULT 'UNKNOWN',
|
|
last_seen_at TEXT NOT NULL,
|
|
last_polled_at TEXT NOT NULL,
|
|
notes TEXT,
|
|
location TEXT
|
|
);
|
|
|
|
CREATE TABLE IF NOT EXISTS smart_tests (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
drive_id INTEGER NOT NULL REFERENCES drives(id) ON DELETE CASCADE,
|
|
test_type TEXT NOT NULL CHECK(test_type IN ('short', 'long')),
|
|
state TEXT NOT NULL DEFAULT 'idle',
|
|
percent INTEGER DEFAULT 0,
|
|
truenas_job_id INTEGER,
|
|
started_at TEXT,
|
|
eta_at TEXT,
|
|
finished_at TEXT,
|
|
error_text TEXT,
|
|
UNIQUE(drive_id, test_type)
|
|
);
|
|
|
|
CREATE TABLE IF NOT EXISTS burnin_jobs (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
drive_id INTEGER NOT NULL REFERENCES drives(id),
|
|
profile TEXT NOT NULL,
|
|
state TEXT NOT NULL DEFAULT 'queued',
|
|
percent INTEGER DEFAULT 0,
|
|
stage_name TEXT,
|
|
operator TEXT NOT NULL,
|
|
created_at TEXT NOT NULL,
|
|
started_at TEXT,
|
|
finished_at TEXT,
|
|
error_text TEXT
|
|
);
|
|
|
|
CREATE TABLE IF NOT EXISTS burnin_stages (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
burnin_job_id INTEGER NOT NULL REFERENCES burnin_jobs(id) ON DELETE CASCADE,
|
|
stage_name TEXT NOT NULL,
|
|
state TEXT NOT NULL DEFAULT 'pending',
|
|
percent INTEGER DEFAULT 0,
|
|
started_at TEXT,
|
|
finished_at TEXT,
|
|
duration_seconds REAL,
|
|
error_text TEXT
|
|
);
|
|
|
|
CREATE TABLE IF NOT EXISTS audit_events (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
event_type TEXT NOT NULL,
|
|
drive_id INTEGER REFERENCES drives(id),
|
|
burnin_job_id INTEGER REFERENCES burnin_jobs(id),
|
|
operator TEXT,
|
|
message TEXT NOT NULL,
|
|
created_at TEXT NOT NULL DEFAULT (strftime('%Y-%m-%dT%H:%M:%fZ', 'now'))
|
|
);
|
|
|
|
CREATE INDEX IF NOT EXISTS idx_smart_drive_type ON smart_tests(drive_id, test_type);
|
|
CREATE INDEX IF NOT EXISTS idx_burnin_jobs_drive ON burnin_jobs(drive_id, state);
|
|
CREATE INDEX IF NOT EXISTS idx_burnin_stages_job ON burnin_stages(burnin_job_id);
|
|
CREATE INDEX IF NOT EXISTS idx_audit_events_job ON audit_events(burnin_job_id);
|
|
"""
|
|
|
|
|
|
# Migrations for existing databases that predate schema additions.
|
|
# Each entry is tried with try/except — SQLite raises OperationalError
|
|
# ("duplicate column name") if the column already exists, which is safe to ignore.
|
|
_MIGRATIONS = [
|
|
"ALTER TABLE drives ADD COLUMN notes TEXT",
|
|
"ALTER TABLE drives ADD COLUMN location TEXT",
|
|
# Stage 7: SSH command output + SMART attribute storage
|
|
"ALTER TABLE burnin_stages ADD COLUMN log_text TEXT",
|
|
"ALTER TABLE burnin_stages ADD COLUMN bad_blocks INTEGER DEFAULT 0",
|
|
"ALTER TABLE drives ADD COLUMN smart_attrs TEXT",
|
|
"ALTER TABLE smart_tests ADD COLUMN raw_output TEXT",
|
|
# Stage 8: track last reset time so dashboard burn-in col clears after reset
|
|
"ALTER TABLE drives ADD COLUMN last_reset_at TEXT",
|
|
# 1.0.0-15: pool-membership lock
|
|
"ALTER TABLE drives ADD COLUMN pool_name TEXT",
|
|
"ALTER TABLE drives ADD COLUMN pool_role TEXT",
|
|
"ALTER TABLE drives ADD COLUMN pool_seen_at TEXT",
|
|
# 1.0.0-19: enforce one active burn-in per drive at the storage layer.
|
|
# Closes the read-then-insert race in burnin.start_job — without this,
|
|
# two concurrent /api/v1/burnin/start requests for the same drive could
|
|
# both observe zero active jobs and both insert queued rows.
|
|
"""CREATE UNIQUE INDEX IF NOT EXISTS uniq_active_burnin_per_drive
|
|
ON burnin_jobs (drive_id) WHERE state IN ('queued', 'running')""",
|
|
# 1.0.0-22: app-level login (username + bcrypt password)
|
|
"""CREATE TABLE IF NOT EXISTS users (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
username TEXT UNIQUE NOT NULL,
|
|
password_hash TEXT NOT NULL,
|
|
full_name TEXT,
|
|
is_admin INTEGER NOT NULL DEFAULT 0,
|
|
created_at TEXT NOT NULL,
|
|
last_login_at TEXT
|
|
)""",
|
|
]
|
|
|
|
|
|
async def _run_migrations(db: aiosqlite.Connection) -> None:
|
|
for sql in _MIGRATIONS:
|
|
try:
|
|
await db.execute(sql)
|
|
except Exception:
|
|
pass # Column already exists — harmless
|
|
|
|
# Remove the old CHECK(profile IN ('quick','full')) constraint if present.
|
|
# SQLite can't ALTER a CHECK — requires a full table rebuild.
|
|
cur = await db.execute(
|
|
"SELECT sql FROM sqlite_master WHERE type='table' AND name='burnin_jobs'"
|
|
)
|
|
row = await cur.fetchone()
|
|
if row and "CHECK" in (row[0] or ""):
|
|
await db.executescript("""
|
|
PRAGMA foreign_keys=OFF;
|
|
CREATE TABLE burnin_jobs_new (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
drive_id INTEGER NOT NULL REFERENCES drives(id),
|
|
profile TEXT NOT NULL,
|
|
state TEXT NOT NULL DEFAULT 'queued',
|
|
percent INTEGER DEFAULT 0,
|
|
stage_name TEXT,
|
|
operator TEXT NOT NULL,
|
|
created_at TEXT NOT NULL,
|
|
started_at TEXT,
|
|
finished_at TEXT,
|
|
error_text TEXT
|
|
);
|
|
INSERT INTO burnin_jobs_new SELECT * FROM burnin_jobs;
|
|
DROP TABLE burnin_jobs;
|
|
ALTER TABLE burnin_jobs_new RENAME TO burnin_jobs;
|
|
CREATE INDEX IF NOT EXISTS idx_burnin_jobs_drive ON burnin_jobs(drive_id, state);
|
|
PRAGMA foreign_keys=ON;
|
|
""")
|
|
|
|
|
|
async def init_db() -> None:
|
|
Path(settings.db_path).parent.mkdir(parents=True, exist_ok=True)
|
|
async with aiosqlite.connect(settings.db_path) as db:
|
|
await db.execute("PRAGMA journal_mode=WAL")
|
|
await db.execute("PRAGMA foreign_keys=ON")
|
|
await db.executescript(SCHEMA)
|
|
await _run_migrations(db)
|
|
await db.commit()
|
|
|
|
|
|
async def get_db():
|
|
db = await aiosqlite.connect(settings.db_path)
|
|
db.row_factory = aiosqlite.Row
|
|
try:
|
|
await db.execute("PRAGMA journal_mode=WAL")
|
|
await db.execute("PRAGMA foreign_keys=ON")
|
|
yield db
|
|
finally:
|
|
await db.close()
|