Merge pull request 'Agent: bound video GPU work (early-exit frame loop at max_regions)' (#172) 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 = "2026-06-30.9 · region-caps + active-reset"
+VERSION = "2026-06-30.10 · video region early-exit"
 
 logbuf.install()
 cfg = Config.from_env()

agent/fc_agent/worker.py

@@ -559,6 +559,12 @@ class Worker:
                         tmpl["siglip_embedding"] = vec
                         tmpl["embedding_version"] = embed_version
                         regions.append(tmpl)
+                # Stop once we have enough: a long video (image 81602 = a 156 MB
+                # mp4, 64 sampled frames × ~32 regions) would otherwise burn ~38s
+                # of GPU across every frame before the submit is even truncated.
+                # Bounds the WORK, not just the POST body.
+                if len(regions) >= self.cfg.max_regions:
+                    break
             self._record("gpu", time.monotonic() - _t_gpu)
             # Backstop: never submit an unbounded pile of regions (a pathological
             # image / long video). Keep the highest-scoring max_regions so the