Merge pull request 'Fix: agent py3.10 startup crash + submit-path retry + pin agent ruff to py310' (#169) from dev into main

agent/fc_agent/app.py

@@ -15,7 +15,7 @@ from .worker import Worker
 # Bump on every agent change. The page embeds this and /status reports it; the UI
 # warns to reload when they differ — so a stale browser-cached page can't be
 # mistaken for "the new image didn't deploy". (Belt-and-braces with no-store.)
-VERSION = "2026-06-30.5 · stop+poll+ci"
+VERSION = "2026-06-30.6 · submit-retry+py310"
 
 logbuf.install()
 cfg = Config.from_env()

agent/fc_agent/client.py

@@ -5,19 +5,44 @@ 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
-        self.s = requests.Session()
-        self.s.headers["Authorization"] = f"Bearer {token}"
-        # Many worker threads share this Session; the default pool (10) would
+        # 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)
-        self.s.mount("http://", adapter)
-        self.s.mount("https://", adapter)
+        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(
@@ -29,7 +54,7 @@ class FcClient:
         return r.json().get("jobs", [])
 
     def submit(self, job_id: int, regions: list[dict], replace_kinds: list[str]) -> dict:
-        r = self.s.post(
+        r = self._submit_s.post(
             f"{self.base}/api/gpu/jobs/submit",
             json={
                 "agent_id": self.agent_id, "job_id": job_id,
@@ -42,7 +67,7 @@ class FcClient:
 
     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.s.post(
+        r = self._submit_s.post(
             f"{self.base}/api/gpu/jobs/submit_embedding",
             json={
                 "agent_id": self.agent_id, "job_id": job_id,

agent/fc_agent/config.py

@@ -1,4 +1,9 @@
 """Agent config, all from env (the control container is configured at run)."""
+# Lazy annotations so the `from_env(cls) -> Config` self-reference is a string,
+# not evaluated at class-definition time — otherwise it NameErrors on the agent's
+# Python 3.10 (CI lints on 3.14, where PEP 649 hides this).
+from __future__ import annotations
+
 import os
 from dataclasses import dataclass
 

agent/ruff.toml

@@ -0,0 +1,7 @@
+# The agent runs on the CUDA base image's Python 3.10 — NOT the 3.14 that CI's
+# ci-python image and the repo-root ruff.toml target. Pin the agent to py310 so
+# ruff enforces 3.10 compatibility and never auto-applies a 3.11+/3.14-only fix
+# (e.g. unquoting a self-referential annotation, which PEP 649 makes safe on 3.14
+# but NameErrors on 3.10). Inherit the root lint rules.
+extend = "../ruff.toml"
+target-version = "py310"