fix: defer background processing until all upload batches complete (race condition fix)

Add finalize_upload endpoint that starts _background_process only after
all file batches have been saved to disk. Fixes race where glob(*.csv)
captured only first batch's files.

- upload_csv: no longer starts thread, sets status='pending'
- finalize_upload: validates dir, starts processing thread
- upload.html: calls finalize after batch upload loop completes

analysis/urls.py

@@ -20,6 +20,7 @@ urlpatterns = [
     path('config/', views.config_view, name='config'),
     path('api/llm/test/', views.llm_test, name='llm_test'),
     path('runs/<int:display_id>/retry/', views.retry_run, name='retry_run'),
+    path('runs/<int:display_id>/finalize/', views.finalize_upload, name='finalize_upload'),
     path('runs/<int:display_id>/delete/', views.delete_upload, name='delete_upload'),
     path('logs/', views.log_viewer, name='log_viewer'),
     path('globe/', views.globe_view, name='globe'),

analysis/views.py

@@ -331,15 +331,14 @@ def upload_csv(request):
             for chunk in f.chunks():
                 dst.write(chunk)
         saved.append(str(path))
-    # Auto-process in background
+    # Create run with status='pending' — background processing deferred to finalize endpoint
     run = AnalysisRun.objects.create(
         csv_glob=str(upload_dir / '*.csv'),
-        status='loading',
+        status='pending',
         run_type='upload',
     )
-    t = threading.Thread(target=_background_process, args=(run.id, upload_dir), daemon=True)
-    t.start()
-    return JsonResponse({'run_id': run.display_id, 'files': saved, 'status': 'loading'})
+    # Deferred: _background_process will be started by finalize_upload endpoint
+    return JsonResponse({'run_id': run.display_id, 'files': saved, 'status': 'pending'})
 
 
 @csrf_exempt
@@ -367,6 +366,24 @@ def upload_csv_batch(request, display_id):
     return JsonResponse({'run_id': run.display_id, 'files': len(saved), 'status': 'ok'})
 
 
+@csrf_exempt
+def finalize_upload(request, display_id):
+    """Finalize batch upload: validate upload_dir, set status='loading', start background processing."""
+    if request.method != 'POST':
+        return JsonResponse({'error': 'POST required'}, status=405)
+    run = get_object_or_404(AnalysisRun, display_id=display_id)
+    if run.status != 'pending':
+        return JsonResponse({'error': f'Run status is {run.status}, expected pending'}, status=400)
+    upload_dir = Path(run.csv_glob).parent if run.csv_glob else None
+    if not upload_dir or not upload_dir.exists():
+        return JsonResponse({'error': 'Upload directory not found'}, status=400)
+    run.status = 'loading'
+    run.save(update_fields=['status'])
+    t = threading.Thread(target=_background_process, args=(run.id, upload_dir), daemon=True)
+    t.start()
+    return JsonResponse({'run_id': run.display_id, 'status': 'loading'})
+
+
 @csrf_exempt
 def delete_upload(request, display_id):
     """Delete uploaded files, SQLite data table, and AnalysisRun.

templates/tianxuan/upload.html

@@ -126,6 +126,24 @@ document.getElementById('uploadForm').addEventListener('submit', async (e) => {
             return;
         }
     }
+    // All batches uploaded — finalize to trigger background processing
+    document.getElementById('progressText').textContent = '正在初始化后台处理...';
+    try {
+        const finResp = await fetch(`/runs/${runId}/finalize/`, {
+            method: 'POST',
+            headers: { 'X-CSRFToken': csrfToken }
+        });
+        const finData = await finResp.json();
+        if (finData.error) {
+            document.getElementById('progressText').textContent = '初始化失败: ' + finData.error;
+            submitBtn.disabled = false;
+            return;
+        }
+    } catch (err) {
+        document.getElementById('progressText').textContent = '初始化失败: ' + err.message;
+        submitBtn.disabled = false;
+        return;
+    }
     // Upload complete — poll for background processing
     document.getElementById('progressText').textContent = '上传完成，后台处理中...';
     const poll = setInterval(async () => {