v1.1.3: row-level clustering + dataset selector with status filter

- Add cluster_mode toggle (raw row-level vs entity-aggregated) in manual.html
- manual_run_analysis supports cluster_mode='raw' skipping entity aggregation
- Replace simple dataset dropdown with selector showing status badges and filter tabs
- Filter tabs: 全部/待分析/已分析/错误, default 待分析
- E2E verified: raw mode entity_count=total_flows, entity mode regression OK

analysis/views.py

@@ -593,6 +593,46 @@ def manual_page(request):
     store = SessionStore()
     datasets = store.list_datasets() if hasattr(store, 'list_datasets') else []
 
+    # Get upload AnalysisRun statuses for dataset badges
+    from analysis.models import AnalysisRun
+    upload_runs = AnalysisRun.objects.filter(run_type='upload').order_by('-created_at')[:50]
+    run_status_map = {
+        f'upload_{r.display_id}': {
+            'status': r.status,
+            'total_flows': r.total_flows,
+            'display_id': r.display_id,
+        }
+        for r in upload_runs
+    }
+
+    # Build datasets_with_status: each dataset annotated with run status
+    datasets_with_status = []
+    for ds in datasets:
+        run_info = run_status_map.get(ds['dataset_id'])
+        if run_info:
+            datasets_with_status.append({
+                **ds,
+                'run_status': run_info['status'],
+                'total_flows': run_info['total_flows'],
+                'display_id': run_info['display_id'],
+            })
+        else:
+            datasets_with_status.append({**ds, 'run_status': 'ready', 'total_flows': None, 'display_id': None})
+
+    # Map statuses to user-facing labels for the filter tabs
+    # ready → 待分析, completed → 已分析, failed → 错误
+    # Everything else (pending/loading/profiling/aggregating/clustering/extracting) → analyzing → 分析中
+    for ds_info in datasets_with_status:
+        s = ds_info['run_status']
+        if s in ('completed',):
+            ds_info['status_label'] = '已分析'
+        elif s in ('failed',):
+            ds_info['status_label'] = '错误'
+        elif s in ('pending', 'loading', 'profiling', 'aggregating', 'clustering', 'extracting'):
+            ds_info['status_label'] = '分析中'
+        else:
+            ds_info['status_label'] = '待分析'
+
     return render(request, 'tianxuan/manual.html', {
         'core_tools': core_tools,
         'diag_tools': diag_tools,
@@ -600,6 +640,7 @@ def manual_page(request):
         'other_tools': other_tools,
         'tools_meta': _json.dumps(meta_list, ensure_ascii=False),
         'datasets': datasets,
+        'datasets_with_status_json': _json.dumps(datasets_with_status, ensure_ascii=False),
     })
 
 
@@ -858,6 +899,7 @@ def manual_run_analysis(request):
     algorithm = body.get('algorithm', 'hdbscan')
     min_cluster_size = int(body.get('min_cluster_size', 5))
     head = body.get('head')
+    cluster_mode = body.get('cluster_mode', 'entity')
 
     def _analysis_fn(run, ctx):
         from analysis.session_store import SessionStore
@@ -867,6 +909,7 @@ def manual_run_analysis(request):
         min_cluster_size = ctx['min_cluster_size']
         head = ctx.get('head')
         pk = ctx['pk']
+        cluster_mode = ctx.get('cluster_mode', 'entity')
 
         store = SessionStore()
         try:
@@ -888,6 +931,23 @@ def manual_run_analysis(request):
 
             ds_id = upload_ds_id if store.get_dataset(upload_ds_id) else f'upload_{pk}'
 
+            # ── Cluster mode: entity aggregation vs raw ──
+            if cluster_mode == 'entity':
+                # Build entity profiles first, then cluster on entity dataset
+                from analysis.tool_registry import _handle_build_entity_profiles
+                import asyncio
+                entity_result = asyncio.new_event_loop().run_until_complete(
+                    _handle_build_entity_profiles(dataset_id=ds_id, auto_detect=True)
+                )
+                if 'error' in entity_result:
+                    run.error_message = f'实体聚合失败: {entity_result["error"]}'
+                    run.status = 'failed'
+                    run.save(update_fields=['status', 'error_message'])
+                    return
+                ds_id = entity_result['dataset_id']
+                run.entity_count = entity_result.get('n_entities')
+                run.save(update_fields=['entity_count'])
+
             # Use the unified clustering pipeline (clustering → extraction → PCA)
             from analysis.views import _run_clustering_pipeline
             _run_clustering_pipeline(
@@ -910,7 +970,7 @@ def manual_run_analysis(request):
         args=(pk, _analysis_fn),
         kwargs=dict(feature_columns=feature_columns, algorithm=algorithm,
                      min_cluster_size=min_cluster_size, head=head, pk=pk,
-                     display_id=run.display_id),
+                     display_id=run.display_id, cluster_mode=cluster_mode),
         daemon=True,
     )
     t.start()