Merge pull request 'Release: GPU re-process trigger (apply new crop detectors to the existing library)' (#156) from dev into main

backend/app/api/gpu.py

@@ -96,6 +96,19 @@ async def backfill():
     return jsonify({"celery_task_id": r.id, "task": task}), 202
 
 
+@gpu_bp.route("/reprocess", methods=["POST"])
+async def reprocess():
+    """Reset every done/error job of `task` back to pending so the agent re-runs
+    the WHOLE library under the current pipeline (e.g. after adding crop
+    detectors). Heavy — the back-catalogue is otherwise skipped by the backfills."""
+    body = await request.get_json(silent=True) or {}
+    task = str(body.get("task") or "ccip")
+    from ..tasks.ml import reprocess_gpu_jobs
+
+    r = reprocess_gpu_jobs.delay(task)
+    return jsonify({"celery_task_id": r.id, "task": task}), 202
+
+
 # --- Agent (bearer token): lease / submit / heartbeat / fail ------------
 
 @gpu_bp.route("/jobs/lease", methods=["POST"])

backend/app/tasks/ml.py

@@ -549,6 +549,37 @@ def recover_orphaned_gpu_jobs() -> int:
         return res.rowcount or 0
 
 
+@celery.task(name="backend.app.tasks.ml.reprocess_gpu_jobs")
+def reprocess_gpu_jobs(task_name: str = "ccip") -> int:
+    """Reset every done/error job of `task_name` back to pending so the agent
+    re-runs the WHOLE library under the CURRENT pipeline — e.g. after adding crop
+    detectors (#1202), re-cropping existing images. Heavy + operator-triggered;
+    the back-catalogue won't otherwise re-process (the backfills skip images that
+    already have current-version regions). Returns the number reset."""
+    from datetime import UTC, datetime
+
+    from sqlalchemy import update
+
+    from ..models import GpuJob
+
+    SessionLocal = _sync_session_factory()
+    with SessionLocal() as session:
+        now = datetime.now(UTC)
+        res = session.execute(
+            update(GpuJob)
+            .where(
+                GpuJob.task == task_name,
+                GpuJob.status.in_(["done", "error"]),
+            )
+            .values(
+                status="pending", attempts=0, lease_token=None, leased_at=None,
+                lease_expires_at=None, updated_at=now,
+            )
+        )
+        session.commit()
+        return res.rowcount or 0
+
+
 @celery.task(
     name="backend.app.tasks.ml.scheduled_ccip_auto_apply",
     soft_time_limit=1800, time_limit=2100,

frontend/src/components/settings/GpuAgentCard.vue

@@ -71,6 +71,16 @@
       images get these automatically; this catches the back-catalogue.
     </p>
 
+    <v-btn
+      class="mt-3" color="warning" variant="tonal" rounded="pill" size="small"
+      prepend-icon="mdi-backup-restore" :loading="reprocessing" @click="onReprocess"
+    >Re-process library (re-detect + re-crop)</v-btn>
+    <p class="fc-muted text-caption mt-2 mb-0">
+      Re-runs the FULL pipeline (figure detection + CCIP + concept/panel crops) on
+      <b>every</b> image — use after changing crop detectors so the back-catalogue
+      gets re-cropped, not just new images. Heavy: re-processes the whole library.
+    </p>
+
     <!-- Match strictness -->
     <div class="fc-section-h mt-5 mb-1">Character-match strictness</div>
     <div v-if="ml.settings" class="d-flex align-center" style="gap:12px">
@@ -157,6 +167,7 @@ const masked = ref(true)
 const rotating = ref(false)
 const backfilling = ref(false)
 const backfillingSiglip = ref(false)
+const reprocessing = ref(false)
 const threshold = ref(0.85)
 const savingThreshold = ref(false)
 const autoApply = ref(true)
@@ -307,6 +318,20 @@ async function onBackfillSiglip() {
     backfillingSiglip.value = false
   }
 }
+
+async function onReprocess() {
+  if (!window.confirm('Re-process the ENTIRE library (re-detect + re-crop every image)? This is heavy and runs on the GPU agent.')) return
+  reprocessing.value = true
+  try {
+    await store.reprocess('ccip')
+    toast({ text: 'Library queued for re-processing — run the agent to drain it', type: 'success' })
+    await refreshQueue()
+  } catch (e) {
+    toast({ text: `Could not start re-process: ${e.message}`, type: 'error' })
+  } finally {
+    reprocessing.value = false
+  }
+}
 </script>
 
 <style scoped>

frontend/src/stores/gpu.js

@@ -29,5 +29,11 @@ export const useGpuStore = defineStore('gpu', () => {
     return await api.post('/api/gpu/backfill', { body: { task } })
   }
 
-  return { token, rotateToken, status, backfill }
+  // Reset every done/error `task` job to pending → re-run the WHOLE library
+  // under the current pipeline (e.g. after adding crop detectors).
+  async function reprocess(task = 'ccip') {
+    return await api.post('/api/gpu/reprocess', { body: { task } })
+  }
+
+  return { token, rotateToken, status, backfill, reprocess }
 })

tests/test_gpu_jobs.py

@@ -91,6 +91,24 @@ async def test_enqueue_embed_backfill_selects_stale_and_unembedded(db):
     assert current.id not in queued
 
 
+@pytest.mark.asyncio
+async def test_reprocess_resets_done_jobs_to_pending(db):
+    # Re-process (#1202): done/error jobs of a task go back to pending so the
+    # agent re-runs the whole library under the current pipeline.
+    from backend.app.tasks.ml import reprocess_gpu_jobs
+
+    img = await _img(db, "r1" * 32)
+    job = await GpuJobService(db).enqueue(img.id, "ccip")
+    job.status = "done"
+    job.attempts = 2
+    await db.commit()
+
+    assert reprocess_gpu_jobs("ccip") >= 1
+    await db.refresh(job)
+    assert job.status == "pending"
+    assert job.attempts == 0
+
+
 @pytest.mark.asyncio
 async def test_enqueue_dedupes_same_pair(db):
     img = await _img(db, "a" * 64)