Merge pull request 'Agent: huge-image load + figure/region caps + stale-active fix' (#171) 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 = "2026-06-30.7 · ubuntu24.04-py312-cuda12.9"
+VERSION = "2026-06-30.9 · region-caps + active-reset"
 
 logbuf.install()
 cfg = Config.from_env()

agent/fc_agent/config.py

@@ -34,6 +34,8 @@ class Config:
     panel_conf: float
     max_components: int   # cap anatomy component crops per frame
     max_panels: int       # cap panel crops per frame
+    max_figures: int      # cap figure boxes per frame (each = a CCIP call + crop)
+    max_regions: int      # hard cap on total regions per JOB (submit-size backstop)
 
     @classmethod
     def from_env(cls) -> Config:
@@ -58,4 +60,6 @@ class Config:
             panel_conf=float(os.environ.get("PANEL_CONF", "0.30")),
             max_components=int(os.environ.get("MAX_COMPONENTS", "8")),
             max_panels=int(os.environ.get("MAX_PANELS", "8")),
+            max_figures=int(os.environ.get("MAX_FIGURES", "8")),
+            max_regions=int(os.environ.get("MAX_REGIONS", "128")),
         )

agent/fc_agent/detectors.py

@@ -144,11 +144,14 @@ class Proposers:
 
     def figures(self, image, base_boxes):
         """Merge imgutils person boxes (base_boxes: [(bbox, score)]) with the
-        general COCO person detector → NMS'd figure boxes [(bbox, score, label)]."""
+        general COCO person detector → NMS'd figure boxes [(bbox, score, label)],
+        capped to the highest-scoring max_figures. Uncapped, a busy/huge image
+        (many characters) yields hundreds of boxes → hundreds of per-figure CCIP
+        calls + crops → a 30s+ job and an oversized submit (operator-flagged)."""
         boxes = [(bb, sc if sc is not None else 1.0, "person") for bb, sc in base_boxes]
         if self._person is not None:
             boxes += self._person.detect(image)
-        return nms_merge(boxes)
+        return nms_merge(boxes)[: self.cfg.max_figures]   # nms_merge is score-desc
 
     def components(self, image):
         if self._anatomy is None:

agent/fc_agent/media.py

@@ -13,6 +13,13 @@ from PIL import Image, ImageFile
 # and would otherwise fail the job 3× then error (operator-flagged 2026-06-30).
 ImageFile.LOAD_TRUNCATED_IMAGES = True
 
+# Disable PIL's decompression-bomb guard: this is a TRUSTED local library, not an
+# untrusted upload surface, so a legitimately huge image (high-res scans/prints,
+# 90M+ pixels) must load. The default 89M-pixel limit only WARNS, but PIL raises
+# DecompressionBombError at 2× (~179M px) — which would fail those jobs outright
+# (operator-flagged 2026-06-30, images of 90–95M px).
+Image.MAX_IMAGE_PIXELS = None
+
 
 def is_video(mime: str) -> bool:
     return bool(mime) and (mime.startswith("video/") or mime in {"image/gif"})

agent/fc_agent/worker.py

@@ -210,6 +210,8 @@ class Worker:
         self._ctrl_stop.set()
         with self._lock:
             slots, self._slots = self._slots, []
+            self._active = 0      # no slots left → the meter reads 0 at once; any
+            #                       lagging decrement is clamped (see _bump)
         for s in slots:
             s.stop.set()          # each slot releases its inflight on exit
 
@@ -265,7 +267,9 @@ class Worker:
             self.processed += processed
             self.errors += errors
             self.transient += transient
-            self._active += active
+            # Clamp at 0: a Stop resets _active to 0, so a slot that was mid-image
+            # decrements afterwards — that must not drive the meter negative.
+            self._active = max(0, self._active + active)
 
     # --- per-slot loop -----------------------------------------------------
     def _loop(self, slot: _Slot):
@@ -556,6 +560,17 @@ class Worker:
                         tmpl["embedding_version"] = embed_version
                         regions.append(tmpl)
             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
+            # POST body stays sane — curator rejects an oversized one with 413
+            # (operator-flagged: image 81602 looped on 413).
+            if len(regions) > self.cfg.max_regions:
+                regions.sort(key=lambda r: r.get("score", 0.0) or 0.0, reverse=True)
+                dropped = len(regions) - self.cfg.max_regions
+                regions = regions[: self.cfg.max_regions]
+                log.info("job %s: capped regions %d→%d (dropped %d)",
+                         job.get("job_id"), len(regions) + dropped,
+                         len(regions), dropped)
             _t = time.monotonic()
             self.client.submit(job["job_id"], regions, replace_kinds)
             self._record("submit", time.monotonic() - _t)