v1.1.3: default server 0.0.0.0:80 + row-level clustering + filter UI + dataset selector

analysis/views.py

@@ -899,7 +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')
+    cluster_mode = body.get('cluster_mode', 'raw')
 
     def _analysis_fn(run, ctx):
         from analysis.session_store import SessionStore
@@ -909,7 +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')
+        cluster_mode = ctx.get('cluster_mode', 'raw')
 
         store = SessionStore()
         try:
@@ -931,23 +931,6 @@ 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(

config/config.yaml

@@ -1,6 +1,6 @@
 server:
-  host: 127.0.0.1
+  host: 0.0.0.0
-  port: 8000
+  port: 80
   debug: false
 data:
   schema_strict: false

config/loader.py

@@ -10,8 +10,8 @@ class Config(BaseModel):
     """Typed configuration for TianXuan."""
 
     class Server(BaseModel):
-        host: str = '127.0.0.1'
+        host: str = '0.0.0.0'
-        port: int = 8000
+        port: int = 80
         debug: bool = False
 
     class Data(BaseModel):

templates/tianxuan/manual.html

@@ -111,19 +111,11 @@
     </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;">
+<div class="card" id="filterCard" style="background:#f0f4ff;border-color:#c8d6e5;">
     <h3>🔍 数据筛选</h3>
-    <div id="filterRows">
+    <div id="filterNoDataset" style="text-align:center;color:#999;padding:1rem;font-size:0.9rem;">选择数据集后可用</div>
+    <div id="filterRows" style="display:none;">
         <div class="filter-row" data-idx="0" style="display:flex;gap:0.5rem;align-items:center;margin-bottom:0.4rem;">
             <select class="filter-col" style="flex:1;padding:0.35rem;border:1px solid #ccc;border-radius:4px;"><option value="">-- 列 --</option></select>
             <select class="filter-op" style="width:130px;padding:0.35rem;border:1px solid #ccc;border-radius:4px;">
@@ -139,12 +131,13 @@
             <button class="btn" onclick="removeFilterRow(this)" style="background:#dc3545;color:#fff;font-size:0.8rem;padding:0.2rem 0.5rem;display:none;">✕</button>
         </div>
     </div>
-    <div style="margin:0.5rem 0;display:flex;gap:0.5rem;align-items:center;">
+    <div id="filterControls" style="display:none;margin:0.5rem 0;gap:0.5rem;align-items:center;">
         <label style="font-size:0.85rem;white-space:nowrap;">逻辑:</label>
         <select id="filterLogic" style="padding:0.35rem;border:1px solid #ccc;border-radius:4px;">
             <option value="and">AND</option><option value="or">OR</option>
         </select>
         <button class="btn" onclick="addFilterRow()" style="font-size:0.8rem;background:#e8f0fe;color:#4361ee;">+ 添加条件</button>
+        <button class="btn" onclick="resetFilter()" style="font-size:0.8rem;background:#fce4ec;color:#c62828;">重置</button>
         <button class="btn btn-primary" onclick="applyFilter()" style="margin-left:auto;">应用筛选</button>
     </div>
     <div id="filterResult" style="display:none;margin-top:0.5rem;padding:0.5rem;background:#e8f5e9;border-radius:4px;font-size:0.85rem;"></div>
@@ -181,7 +174,6 @@ 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 }};
@@ -362,16 +354,16 @@ async function executeStep(idx) {
     resultDiv.style.display = 'none';
     const params = collectParams(idx);
 
-    // Cluster mode: skip build_entity_profiles in raw mode
+    // Raw row-level clustering: skip entity aggregation entirely
-    if (clusterMode === 'raw' && step.tool.name === 'build_entity_profiles') {
+    if (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
+    // Always cluster raw rows directly
-    if (clusterMode === 'raw' && step.tool.name === 'run_clustering') {
+    if (step.tool.name === 'run_clustering') {
         params.cluster_mode = 'raw';
     }
 
@@ -578,9 +570,30 @@ const DATASET_COLUMNS = {
 // ── Filter builder ──
 function onDatasetChange() {
     const dsId = document.getElementById('datasetSelect').value;
-    const filterCard = document.getElementById('filterCard');
+    const noDatasetMsg = document.getElementById('filterNoDataset');
-    if (!dsId) { filterCard.style.display = 'none'; return; }
+    const filterRows = document.getElementById('filterRows');
-    filterCard.style.display = 'block';
+    const filterControls = document.getElementById('filterControls');
+    const filterResult = document.getElementById('filterResult');
+
+    if (!dsId) {
+        // No dataset selected: show placeholder, hide filter UI
+        noDatasetMsg.style.display = 'block';
+        filterRows.style.display = 'none';
+        filterControls.style.display = 'none';
+        filterResult.style.display = 'none';
+        // Clear column dropdowns
+        document.querySelectorAll('.filter-col').forEach(sel => {
+            sel.innerHTML = '<option value="">-- 请先选择数据集 --</option>';
+        });
+        return;
+    }
+
+    // Dataset selected: show filter UI, hide placeholder
+    noDatasetMsg.style.display = 'none';
+    filterRows.style.display = 'block';
+    filterControls.style.display = 'flex';
+
+    // Populate column dropdowns
     const cols = DATASET_COLUMNS[dsId] || [];
     document.querySelectorAll('.filter-col').forEach(sel => {
         const cur = sel.value;
@@ -591,7 +604,7 @@ function onDatasetChange() {
 
 function addFilterRow() {
     const rows = document.querySelectorAll('.filter-row');
-    if (rows.length >= 2) return; // MVP: max 2 rows
+    if (rows.length >= 5) return; // max 5 rows
     const template = rows[0].cloneNode(true);
     template.querySelector('.filter-val').value = '';
     template.querySelector('.filter-col').selectedIndex = 0;
@@ -608,6 +621,20 @@ function removeFilterRow(btn) {
     btn.closest('.filter-row').remove();
 }
 
+function resetFilter() {
+    // Remove all rows except the first, then reset the first row
+    const rows = document.querySelectorAll('.filter-row');
+    for (let i = rows.length - 1; i >= 1; i--) {
+        rows[i].remove();
+    }
+    const firstRow = rows[0];
+    firstRow.querySelector('.filter-val').value = '';
+    firstRow.querySelector('.filter-col').selectedIndex = 0;
+    firstRow.querySelector('.filter-op').selectedIndex = 0;
+    firstRow.querySelector('button').style.display = 'none';
+    document.getElementById('filterResult').style.display = 'none';
+}
+
 function collectFilters() {
     const filters = [];
     document.querySelectorAll('.filter-row').forEach(row => {
@@ -650,7 +677,7 @@ async function applyFilter() {
 
         const resultDiv = document.getElementById('filterResult');
         resultDiv.style.display = 'block';
-        resultDiv.textContent = '筛选完成: ' + data.dataset_id + ' (' + data.row_count + ' 行)';
+        resultDiv.innerHTML = '<strong>✅ 筛选完成</strong>: 数据集 <code>' + data.dataset_id + '</code>，共 <strong>' + data.row_count + '</strong> 行';
         showSuccess('筛选完成: ' + data.row_count + ' 行');
     } catch(e) {
         showError('筛选请求失败: ' + e.message);