"""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 from requests.adapters import HTTPAdapter from urllib3.util.retry import Retry class FcClient: def __init__(self, base_url: str, token: str, agent_id: str): self.base = base_url.rstrip("/") self.agent_id = agent_id # Main session: NO in-request retry — lease/fetch are cheap to redo and # the worker loop already backs off + re-leases on failure. (Auto-retrying # a lease could double-claim a batch if a response is lost.) self.s = self._session(token) # Submit session: retry in-place, because by submit time the GPU work is # already DONE — a momentary blip (dropped connection, gateway 5xx during # a curator redeploy) must not throw that work away and force a full # re-download + recompute on another agent. A duplicate submit after a # lost response is harmless: the job is already closed, so it just returns # 409 lease_invalid (a no-op). Idempotent enough to retry POST safely. retry = Retry( total=3, connect=3, read=3, status=3, backoff_factor=0.5, # ~0.5s, 1s, 2s between tries status_forcelist=(500, 502, 503, 504), # transient server/gateway allowed_methods=frozenset({"POST"}), raise_on_status=False, # let raise_for_status decide ) self._submit_s = self._session(token, retry) @staticmethod def _session(token: str, retry: Retry | None = None) -> requests.Session: s = requests.Session() s.headers["Authorization"] = f"Bearer {token}" # Many worker threads share a Session; the default pool (10) would # throttle them + spam "connection pool is full". Size it for the cap. adapter = HTTPAdapter( pool_connections=64, pool_maxsize=64, max_retries=retry or 0 ) s.mount("http://", adapter) s.mount("https://", adapter) return s 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._submit_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 submit_embedding(self, job_id: int, embedding: list, version: str) -> dict: """Post a whole-image SigLIP embedding (the 'embed' task) → image_record.""" r = self._submit_s.post( f"{self.base}/api/gpu/jobs/submit_embedding", json={ "agent_id": self.agent_id, "job_id": job_id, "embedding": embedding, "embedding_version": version, }, 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: # Short timeout: this backs the UI /status poll, so a busy curator must # not hang the page for long (the GPU meters poll /gpu separately). r = self.s.get(f"{self.base}/api/gpu/status", timeout=5) r.raise_for_status() return r.json()