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()

templates/tianxuan/manual.html

@@ -48,6 +48,21 @@
     .pin-btn.pinned { color:#f4a261; }
     .pin-btn.unpinned { color:#aaa; }
     #autoPlansList { max-height:180px; overflow-y:auto; margin-top:0.25rem; padding-top:0.25rem; border-top:1px dashed #eee; }
+    /* Dataset selector table */
+    .ds-table { width:100%; border-collapse:collapse; font-size:0.85rem; }
+    .ds-table th { background:#f5f5f5; padding:0.4rem 0.5rem; text-align:left; font-weight:600; border-bottom:2px solid #ddd; position:sticky; top:0; }
+    .ds-table td { padding:0.35rem 0.5rem; border-bottom:1px solid #eee; }
+    .ds-table tr { cursor:pointer; transition: background 0.15s; }
+    .ds-table tr:hover { background:#e8f0fe; }
+    .ds-table tr.selected { background:#d4e6ff; font-weight:600; }
+    .status-badge { display:inline-block; padding:0.15rem 0.5rem; border-radius:3px; font-size:0.75rem; font-weight:600; }
+    .status-badge.ready { background:#e8f5e9; color:#2e7d32; }
+    .status-badge.analyzing { background:#fff3e0; color:#e65100; }
+    .status-badge.completed { background:#e3f2fd; color:#1565c0; }
+    .status-badge.failed { background:#ffebee; color:#c62828; }
+    .filter-btn { padding:0.3rem 0.75rem; border:1px solid #ccc; border-radius:4px; background:#fafafa; cursor:pointer; font-size:0.8rem; transition: all 0.15s; }
+    .filter-btn.active { background:#4361ee; color:#fff; border-color:#4361ee; }
+    .filter-btn:hover:not(.active) { background:#e8e8e8; }
 </style>
 
 <div class="card">
@@ -66,12 +81,26 @@
     <div id="autoPlansList"></div>
 </div>
 
-<!-- Dataset selector + Run All -->
+<!-- Dataset selector with status badges -->
+<div class="card" id="datasetSelectorCard">
+    <h3>📁 选择数据集</h3>
+    <div style="display:flex;gap:0.5rem;margin-bottom:0.75rem;" id="statusFilter">
+        <button class="btn filter-btn" data-filter="all">全部</button>
+        <button class="btn filter-btn active" data-filter="ready">待分析</button>
+        <button class="btn filter-btn" data-filter="completed">已分析</button>
+        <button class="btn filter-btn" data-filter="failed">错误</button>
+    </div>
+    <div id="datasetTable" style="max-height:300px;overflow-y:auto;border:1px solid #e0e0e0;border-radius:4px;">
+        <p style="text-align:center;color:#999;padding:1rem;">加载中...</p>
+    </div>
+</div>
+
+<!-- Dataset selector + Run All (keeping dropdown hidden as data source) -->
 <div class="card">
     <div style="display:flex;align-items:center;gap:1rem;flex-wrap:wrap;">
         <div style="flex:1;min-width:200px;">
             <label style="font-weight:600;font-size:0.9rem;">📁 数据集</label>
-            <select id="datasetSelect" onchange="onDatasetChange()" style="width:100%;padding:0.4rem;border:1px solid #ccc;border-radius:4px;margin-top:0.25rem;">
+            <select id="datasetSelect" onchange="onDatasetChange()" style="display:none;">
                 <option value="">-- 选择 --</option>
         {% for ds in datasets %}
         <option value="{{ ds.dataset_id }}">{{ ds.dataset_id }} ({{ ds.row_count|default:"?" }} rows, {{ ds.file_count|default:"?" }} files)</option>
@@ -82,6 +111,15 @@
     </div>
 </div>
 
+<!-- Cluster Mode -->
+<div class="card" id="clusterModeCard">
+    <label style="font-weight:600;">聚类模式</label>
+    <div style="display:flex;gap:1.5rem;margin-top:0.5rem;">
+        <label><input type="radio" name="clusterMode" value="entity" checked onchange="clusterMode='entity'"> 实体聚合后聚类（默认）</label>
+        <label><input type="radio" name="clusterMode" value="raw" onchange="clusterMode='raw'"> 逐行直接聚类</label>
+    </div>
+</div>
+
 <!-- Filter builder card -->
 <div class="card" id="filterCard" style="display:none;">
     <h3>🔍 数据筛选</h3>
@@ -143,6 +181,81 @@ const CATEGORIES = {
 let stepCounter = 0;
 const workflow = [];
 let running = false;
+var clusterMode = 'entity';
+
+// ── Dataset selector with status badges ──
+const DATASETS_WITH_STATUS = {{ datasets_with_status_json|safe }};
+let activeFilter = 'ready';
+
+function buildDatasetTable(filter) {
+    const container = document.getElementById('datasetTable');
+    let rows = DATASETS_WITH_STATUS.filter(ds => {
+        if (filter === 'all') return true;
+        if (filter === 'ready') return ds.run_status === 'ready' || (!ds.run_status || ds.run_status === 'ready');
+        if (filter === 'completed') return ds.run_status === 'completed';
+        if (filter === 'failed') return ds.run_status === 'failed';
+        return true;
+    });
+
+    if (!rows.length) {
+        container.innerHTML = '<p style="text-align:center;color:#999;padding:1rem;">无匹配的数据集</p>';
+        return;
+    }
+
+    let html = '<table class="ds-table"><thead><tr><th>ID</th><th>状态</th><th>行数</th><th>文件</th><th></th></tr></thead><tbody>';
+    rows.forEach(ds => {
+        const label = ds.status_label || '待分析';
+        const badgeClass = (ds.run_status === 'completed') ? 'completed' :
+                          (ds.run_status === 'failed') ? 'failed' :
+                          (ds.run_status && ds.run_status !== 'ready') ? 'analyzing' : 'ready';
+        const dispId = ds.display_id || ds.dataset_id;
+        const rowCount = ds.row_count != null ? ds.row_count.toLocaleString() : '?';
+        const fileCount = ds.file_count != null ? ds.file_count : '?';
+        html += `<tr data-ds-id="${ds.dataset_id}" onclick="selectDataset('${ds.dataset_id}')">
+            <td style="font-weight:600;">${dispId}</td>
+            <td><span class="status-badge ${badgeClass}">${label}</span></td>
+            <td>${rowCount}</td>
+            <td>${fileCount}</td>
+            <td><button class="btn" onclick="event.stopPropagation();selectDataset('${ds.dataset_id}')" style="font-size:0.75rem;padding:0.2rem 0.5rem;">选择</button></td>
+        </tr>`;
+    });
+    html += '</tbody></table>';
+    container.innerHTML = html;
+}
+
+function selectDataset(dsId) {
+    const sel = document.getElementById('datasetSelect');
+    let opt = Array.from(sel.options).find(o => o.value === dsId);
+    if (!opt) {
+        opt = document.createElement('option');
+        opt.value = dsId;
+        opt.text = dsId;
+        sel.add(opt);
+    }
+    sel.value = dsId;
+    onDatasetChange();
+
+    // Highlight selected row
+    document.querySelectorAll('#datasetTable tr').forEach(tr => tr.classList.remove('selected'));
+    const row = document.querySelector(`#datasetTable tr[data-ds-id="${dsId}"]`);
+    if (row) row.classList.add('selected');
+}
+
+function setDatasetFilter(filter) {
+    activeFilter = filter;
+    document.querySelectorAll('#statusFilter .filter-btn').forEach(btn => {
+        btn.classList.toggle('active', btn.dataset.filter === filter);
+    });
+    buildDatasetTable(filter);
+}
+
+// Init filter tabs & build default table
+document.querySelectorAll('#statusFilter .filter-btn').forEach(btn => {
+    btn.addEventListener('click', function() {
+        setDatasetFilter(this.dataset.filter);
+    });
+});
+buildDatasetTable('ready');
 
 // ── Tool picker ──
 function showToolPicker() {
@@ -248,6 +361,20 @@ async function executeStep(idx) {
     const resultDiv = document.getElementById(`result-${idx}`);
     resultDiv.style.display = 'none';
     const params = collectParams(idx);
+
+    // Cluster mode: skip build_entity_profiles in raw mode
+    if (clusterMode === 'raw' && step.tool.name === 'build_entity_profiles') {
+        step.status = 'done';
+        resultDiv.textContent = '[已跳过] 逐行直接聚类模式，无需实体聚合';
+        resultDiv.style.display = 'block';
+        renderSteps();
+        return;
+    }
+    // Pass cluster_mode to run_clustering tool
+    if (clusterMode === 'raw' && step.tool.name === 'run_clustering') {
+        params.cluster_mode = 'raw';
+    }
+
     try {
         const resp = await fetch('/tools/run/', {
             method: 'POST',