bvandeusen
4a1a9ec5a7
Control UI gains what the operator asked for: - GPU load (nvidia-smi): util %, VRAM used/total + bar, temp — so you can see how hard the card is working while you're at the desktop. - Worker count is now a live − / + control (POST /concurrency), not just an env: the worker is a pool of independent slots (shared model, so slots add concurrent inference, not N× VRAM). Dial up for speed, down to free the card. Replaces pause/resume with Start/Stop + the worker dial. - Graceful release on stop / pool-shrink: a slot hands its still-leased jobs back via client.release() so they're re-picked immediately (pairs with the server recovery sweep). Not CI-tested (agent/ outside CI) — verified by running. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
80 lines
2.6 KiB
Python
80 lines
2.6 KiB
Python
"""HTTP client for the FabledCurator GPU-job API.
|
|
|
|
The agent's ONLY contact with FC — lease/submit/heartbeat/fail + fetch image
|
|
bytes, all over HTTP with the bearer token. No DB/Redis.
|
|
"""
|
|
import requests
|
|
|
|
|
|
class FcClient:
|
|
def __init__(self, base_url: str, token: str, agent_id: str):
|
|
self.base = base_url.rstrip("/")
|
|
self.agent_id = agent_id
|
|
self.s = requests.Session()
|
|
self.s.headers["Authorization"] = f"Bearer {token}"
|
|
|
|
def lease(self, batch_size: int) -> list[dict]:
|
|
r = self.s.post(
|
|
f"{self.base}/api/gpu/jobs/lease",
|
|
json={"agent_id": self.agent_id, "batch_size": batch_size},
|
|
timeout=30,
|
|
)
|
|
r.raise_for_status()
|
|
return r.json().get("jobs", [])
|
|
|
|
def submit(self, job_id: int, regions: list[dict], replace_kinds: list[str]) -> dict:
|
|
r = self.s.post(
|
|
f"{self.base}/api/gpu/jobs/submit",
|
|
json={
|
|
"agent_id": self.agent_id, "job_id": job_id,
|
|
"regions": regions, "replace_kinds": replace_kinds,
|
|
},
|
|
timeout=120,
|
|
)
|
|
r.raise_for_status()
|
|
return r.json()
|
|
|
|
def heartbeat(self, job_ids: list[int]) -> None:
|
|
try:
|
|
self.s.post(
|
|
f"{self.base}/api/gpu/jobs/heartbeat",
|
|
json={"agent_id": self.agent_id, "job_ids": job_ids},
|
|
timeout=30,
|
|
)
|
|
except requests.RequestException:
|
|
pass
|
|
|
|
def fail(self, job_id: int, error: str) -> None:
|
|
try:
|
|
self.s.post(
|
|
f"{self.base}/api/gpu/jobs/fail",
|
|
json={"agent_id": self.agent_id, "job_id": job_id, "error": error},
|
|
timeout=30,
|
|
)
|
|
except requests.RequestException:
|
|
pass
|
|
|
|
def release(self, job_ids: list[int]) -> None:
|
|
# Graceful hand-back on stop so orphaned work is re-leased at once.
|
|
if not job_ids:
|
|
return
|
|
try:
|
|
self.s.post(
|
|
f"{self.base}/api/gpu/jobs/release",
|
|
json={"agent_id": self.agent_id, "job_ids": job_ids},
|
|
timeout=30,
|
|
)
|
|
except requests.RequestException:
|
|
pass
|
|
|
|
def fetch_image(self, image_url: str) -> bytes:
|
|
# image_url is a server-relative path ("/images/...").
|
|
r = self.s.get(f"{self.base}{image_url}", timeout=180)
|
|
r.raise_for_status()
|
|
return r.content
|
|
|
|
def queue_status(self) -> dict:
|
|
r = self.s.get(f"{self.base}/api/gpu/status", timeout=15)
|
|
r.raise_for_status()
|
|
return r.json()
|