"""FastAPI control surface for the agent (served on localhost).
Start / stop the worker pool, tune the worker count live (trades desktop
responsiveness for throughput), and watch GPU load + progress + the server-side
queue. Config is env-seeded; the worker count is adjustable here on the fly.
"""
from fastapi import FastAPI, Request
from fastapi.responses import HTMLResponse, JSONResponse
from .config import Config
from .gpu import read_gpu
from .worker import Worker
cfg = Config.from_env()
worker = Worker(cfg)
app = FastAPI(title="FabledCurator GPU agent")
@app.get("/", response_class=HTMLResponse)
def index() -> str:
return _PAGE
@app.post("/start")
def start():
worker.start()
return JSONResponse(worker.status())
@app.post("/stop")
def stop():
worker.stop()
return JSONResponse(worker.status())
@app.post("/concurrency")
async def concurrency(request: Request):
body = await request.json()
worker.set_concurrency(int(body.get("value", 1)))
return JSONResponse(worker.status())
@app.get("/status")
def status():
s = worker.status()
s["fc_url"] = cfg.fc_url
s["configured"] = bool(cfg.token)
s["gpu"] = read_gpu()
try:
s["queue"] = worker.client.queue_status()
except Exception:
s["queue"] = None
return JSONResponse(s)
_PAGE = """
FabledCurator GPU agent
FabledCurator GPU agent
FC: — · token —
workers
(more = overlap I/O, fill the GPU) max 8
stopped
state
0
active now
0
processed
0
errors
GPU — …
"""