Merge pull request 'Release: agent perf (batched crop embeds) + UI (full-width, copy logs, quiet noise) + truncated-image fix' (#160) from dev into main

2026-06-30 18:47:55 -04:00
parent 92494ec4ed 2713c3f773
commit 76b6af4903
5 changed files with 68 additions and 35 deletions
@@ -86,7 +86,7 @@ _PAGE = """<!doctype html><html><head><meta charset=utf-8>
 *{box-sizing:border-box}
 body{font:14px/1.5 system-ui,-apple-system,Segoe UI,Roboto,sans-serif;margin:0;
  background:radial-gradient(1200px 600px at 50% -10%,#1a2029,#0f1216);color:var(--fg)}
- .wrap{max-width:780px;margin:0 auto;padding:28px 20px 48px}
+ .wrap{max-width:none;margin:0;padding:28px 28px 48px}
 header{display:flex;align-items:center;justify-content:space-between;margin-bottom:4px}
 .brand{display:flex;align-items:center;gap:10px;font-size:19px;font-weight:700;letter-spacing:.2px}
 .logo{color:var(--acc);font-size:20px}
@@ -137,6 +137,11 @@ _PAGE = """<!doctype html><html><head><meta charset=utf-8>
 .queue{font:13px ui-monospace,monospace;color:var(--mut)}
 .banner{margin:0 0 14px;padding:.7rem .9rem;border-radius:10px;background:#3a2f12;
  border:1px solid #5a4a17;color:#ffd98a;font-size:13px}
 .logs-h{display:flex;align-items:center;justify-content:space-between}
 .copybtn{font:600 11px system-ui;letter-spacing:.04em;text-transform:uppercase;
  background:#262c34;color:var(--fg);border:1px solid var(--bd);border-radius:7px;
  padding:5px 11px;cursor:pointer}
 .copybtn:hover{border-color:var(--acc)}
 .logs{margin:0;background:#0b0e12;border:1px solid var(--bd);border-radius:10px;padding:12px;
  height:230px;overflow:auto;font:12px/1.55 ui-monospace,SFMono-Regular,Menlo,monospace;
  color:#b9c4d0;white-space:pre-wrap;word-break:break-word}
@@ -187,7 +192,9 @@ _PAGE = """<!doctype html><html><head><meta charset=utf-8>
 </section>
 <section class=card>
-  <div class=card-h>Logs</div>
+  <div class="card-h logs-h">Logs
   <button class=copybtn id=copybtn onclick=copyLogs()>Copy</button>
  </div>
  <pre class=logs id=logs>waiting for activity…</pre>
 </section>
 </div>
@@ -238,6 +245,13 @@ _PAGE = """<!doctype html><html><head><meta charset=utf-8>
   if(atBottom) el.scrollTop=el.scrollHeight
  }catch{}
 }
 async function copyLogs(){
  const txt=logs.textContent||''
  try{ await navigator.clipboard.writeText(txt) }
  catch{ const t=document.createElement('textarea'); t.value=txt; document.body.appendChild(t);
   t.select(); try{document.execCommand('copy')}catch{}; t.remove() }
  copybtn.textContent='Copied'; setTimeout(()=>{copybtn.textContent='Copy'},1200)
 }
 refresh(); refreshLogs()
 setInterval(refresh,3000); setInterval(refreshLogs,2500)
 </script></body></html>"""
@@ -58,12 +58,20 @@ class CropEmbedder:
    def embed(self, image: Image.Image) -> list[float]:
        """A crop → its embedding as a plain float list, ready to POST."""
        return self.embed_batch([image])[0]
    def embed_batch(self, images: list) -> list[list[float]]:
        """Embed many crops in ONE forward pass — far better GPU utilisation +
        only one lock acquisition than embedding each crop separately (which
        starved the GPU and serialised the whole pool)."""
        if not images:
            return []
        self.load()
        torch = self._torch
-        enc = self._processor(images=image, return_tensors="pt")
+        enc = self._processor(images=images, return_tensors="pt")
        pixel_values = enc["pixel_values"].to(self._device, self._dt)
        with self._infer_lock, torch.no_grad():
            out = self._model.get_image_features(pixel_values=pixel_values)
        pooled = out.pooler_output if hasattr(out, "pooler_output") else out
-        vec = pooled[0].float().cpu().numpy().astype(np.float32).reshape(-1)
+        arr = pooled.float().cpu().numpy().astype(np.float32)
-        return vec.tolist()
+        return [row.reshape(-1).tolist() for row in arr]
@@ -34,7 +34,11 @@ def install(level: int = logging.INFO) -> None:
    root.addHandler(h)
    if root.level == logging.NOTSET or root.level > level:
        root.setLevel(level)
-    # Keep the buffer signal-rich: drop the per-request access spam + ultralytics
+    # Keep the buffer signal-rich: silence the chatty HTTP/download libs (every
-    # banner noise to WARNING.
+    # HF model fetch logs per-request) so the console shows agent activity —
-    logging.getLogger("uvicorn.access").setLevel(logging.WARNING)
+    # detector loads, job errors, autoscale moves — not request spam.
-    logging.getLogger("ultralytics").setLevel(logging.WARNING)
+    for noisy in (
        "uvicorn.access", "ultralytics", "httpx", "httpcore",
        "huggingface_hub", "urllib3", "filelock",
    ):
        logging.getLogger(noisy).setLevel(logging.WARNING)
@@ -6,7 +6,12 @@ import os
 import subprocess
 import tempfile
-from PIL import Image
+from PIL import Image, ImageFile
 # Load slightly-truncated images (a few missing trailing bytes) instead of
 # raising — matches the server embedder. These are common in scraped libraries
 # and would otherwise fail the job 3× then error (operator-flagged 2026-06-30).
 ImageFile.LOAD_TRUNCATED_IMAGES = True
 def is_video(mime: str) -> bool:
@@ -348,17 +348,6 @@ class Worker:
            ccip_ev = self.cfg.ccip_model or "ccip-default"
            dv = f"person-{self.cfg.detector_level}"
            def _concept(frame, bbox, t, score, detver, kind="concept"):
                """A SigLIP region for one crop (None if below the size floor)."""
                crop = crop_region(frame, bbox)
                if crop is None:
                    return None
                return {
                    "kind": kind, "bbox": list(bbox), "frame_time": t,
                    "score": score, "siglip_embedding": embedder.embed(crop),
                    "embedding_version": embed_version, "detector_version": detver,
                }
            for t, frame in frames:
                # FIGURE boxes: imgutils detect_person ∪ general COCO person,
                # NMS-merged → CCIP identity (+ a concept crop). Covers anime +
@@ -367,6 +356,11 @@ class Worker:
                figs = proposers.figures(frame, base)
                if not figs:
                    figs = [((0.0, 0.0, 1.0, 1.0), 1.0, "whole")]  # whole-frame fallback
                # Collect every crop that needs a SigLIP embedding, then embed
                # them in ONE batched forward pass (huge GPU-util + throughput
                # win vs one forward per crop). CCIP runs per figure inline.
                pending = []   # (crop, region-template-without-embedding)
                for bbox, score, _label in figs:
                    crop = crop_region(frame, bbox)
                    if crop is None:
@@ -381,25 +375,33 @@ class Worker:
                            "embedding_version": ccip_ev, "detector_version": dv,
                        })
                    if want_siglip:
-                        regions.append({
+                        pending.append((crop, {
                            "kind": "concept", "bbox": list(bbox), "frame_time": t,
-                            "score": score,
+                            "score": score, "detector_version": dv,
-                            "siglip_embedding": embedder.embed(crop),
+                        }))
                            "embedding_version": embed_version, "detector_version": dv,
                        })
                if not want_siglip:
                    continue
-                # ANATOMY components (booru_yolo: head/cat-head/anatomy/…) →
+                # ANATOMY components (booru_yolo) + PANELS → concept/panel crops.
                # concept crops only (not full characters, so no CCIP).
                for bbox, score, label in proposers.components(frame):
-                    r = _concept(frame, bbox, t, score, f"booru:{label}")
+                    crop = crop_region(frame, bbox)
-                    if r is not None:
+                    if crop is not None:
-                        regions.append(r)
+                        pending.append((crop, {
-                # PANEL crops (comic page → panels) → kind='panel' (still SigLIP).
+                            "kind": "concept", "bbox": list(bbox), "frame_time": t,
                            "score": score, "detector_version": f"booru:{label}",
                        }))
                for bbox, score, _label in proposers.panels(frame):
-                    r = _concept(frame, bbox, t, score, "panel", kind="panel")
+                    crop = crop_region(frame, bbox)
-                    if r is not None:
+                    if crop is not None:
-                        regions.append(r)
+                        pending.append((crop, {
                            "kind": "panel", "bbox": list(bbox), "frame_time": t,
                            "score": score, "detector_version": "panel",
                        }))
                if pending:
                    vecs = embedder.embed_batch([c for c, _ in pending])
                    for (_c, tmpl), vec in zip(pending, vecs):
                        tmpl["siglip_embedding"] = vec
                        tmpl["embedding_version"] = embed_version
                        regions.append(tmpl)
            self.client.submit(job["job_id"], regions, replace_kinds)
            self._bump(processed=1)
            return True