modelbeast/server/db.py
John King 8e3085466d feat(reporting): per-node job attribution + real fleet occupancy
- jobs.node column (migration) written at dispatch: placement was held only
  in runner memory, so every job rendered as the primary and busy remotes
  showed idle in fluxgod
- sysinfo.nodes_detail() joins running jobs on jobs.node; legacy NULL rows
  still credit the primary. gpu_pool() now derives busy from the inflight
  counters instead of the dead busy key (set once at load, never updated)
- /api/nodes endpoint exposing the per-machine view
- local pool node named after its host (m3ultra), not "local"
- /api/assets?parent_job= filter actually filters now (was accepted and
  silently ignored; callers got the whole table)
- tests/test_node_reporting.py: 8 framework-free checks incl. the captured
  /api/nodes contract fluxgod consumes

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-24 11:51:35 +10:00

106 lines
3.1 KiB
Python

import json
import os
import sqlite3
import time
import uuid
from pathlib import Path
ROOT = Path(__file__).resolve().parent.parent
# Tests / alternate roots can override the data dir.
DATA = Path(os.environ.get("MODELBEAST_DATA", str(ROOT / "data")))
DB_PATH = DATA / "modelbeast.db"
SCHEMA = """
CREATE TABLE IF NOT EXISTS assets (
id TEXT PRIMARY KEY,
name TEXT NOT NULL,
kind TEXT NOT NULL,
path TEXT NOT NULL,
size INTEGER NOT NULL DEFAULT 0,
meta TEXT NOT NULL DEFAULT '{}',
parent_job TEXT,
created_at REAL NOT NULL
);
CREATE TABLE IF NOT EXISTS jobs (
id TEXT PRIMARY KEY,
operator TEXT NOT NULL,
status TEXT NOT NULL DEFAULT 'queued',
asset_id TEXT,
asset_ids TEXT NOT NULL DEFAULT '[]',
params TEXT NOT NULL DEFAULT '{}',
outdir TEXT,
log TEXT NOT NULL DEFAULT '',
error TEXT,
created_at REAL NOT NULL,
started_at REAL,
finished_at REAL
);
CREATE TABLE IF NOT EXISTS settings (
key TEXT PRIMARY KEY,
value TEXT NOT NULL DEFAULT ''
);
CREATE TABLE IF NOT EXISTS users (
id TEXT PRIMARY KEY,
username TEXT UNIQUE NOT NULL,
pw_hash TEXT NOT NULL,
role TEXT NOT NULL DEFAULT 'guest', -- 'owner' | 'guest'; guests are LOCAL-ONLY
max_active_jobs INTEGER NOT NULL DEFAULT 4,
created_at REAL NOT NULL
);
CREATE TABLE IF NOT EXISTS api_tokens (
token_hash TEXT PRIMARY KEY, -- sha256 hex of the raw token
user_id TEXT NOT NULL,
name TEXT NOT NULL DEFAULT '',
created_at REAL NOT NULL
);
"""
# Columns added after the original Phase 0 schema; applied idempotently so an
# existing data/modelbeast.db upgrades in place.
MIGRATIONS = [
("jobs", "asset_ids", "TEXT NOT NULL DEFAULT '[]'"),
("jobs", "user_id", "TEXT"), # nullable; legacy rows = owner-era
("assets", "user_id", "TEXT"),
("users", "session_epoch", "INTEGER NOT NULL DEFAULT 0"), # bump to revoke sessions
("jobs", "node", "TEXT"), # which pool node ran it; NULL = pre-2026-08-05 rows
]
def connect() -> sqlite3.Connection:
DATA.mkdir(parents=True, exist_ok=True)
# FastAPI sync endpoints run in a threadpool; python sqlite3 is built in
# serialized threading mode, so sharing one connection across threads is safe.
con = sqlite3.connect(DB_PATH, check_same_thread=False)
con.row_factory = sqlite3.Row
con.execute("PRAGMA journal_mode=WAL")
con.executescript(SCHEMA)
_migrate(con)
return con
def _migrate(con: sqlite3.Connection) -> None:
for table, column, decl in MIGRATIONS:
cols = {r["name"] for r in con.execute(f"PRAGMA table_info({table})")}
if column not in cols:
con.execute(f"ALTER TABLE {table} ADD COLUMN {column} {decl}")
con.commit()
def new_id() -> str:
return uuid.uuid4().hex[:12]
def now() -> float:
return time.time()
def row_to_dict(row: sqlite3.Row) -> dict:
d = dict(row)
for key in ("meta", "params", "asset_ids"):
if key in d and isinstance(d[key], str):
try:
d[key] = json.loads(d[key])
except ValueError:
pass
return d