智能体大模型接口全面切换 + 新增视觉智能体

- 全部 AI Worker 切换到 deepseek/deepseek-v4-flash（api.deepseek.com，实测757ms/次，成本降40倍）
- 团队模板默认 provider/model 同步改为 deepseek/deepseek-v4-flash
- 新增视觉智能体「视觉分析师」：autodl/qwen3.6-plus 多模态
- llm_gateway: chat_vision 多模态调用(URL/base64) + 空content自动重试 + 聚合后端路由容错
- engine: 任务描述支持 ![图](url) 图片注入（视觉任务直接派活）
- API: POST /api/workers/<id>/vision_test；前端 Worker 页新增🖼️视觉测试按钮
- 实测: 截图结构化分析 ✅ 雪羊图片识别 ✅ 辩论模式DeepSeek 55秒完成

app.py

@@ -263,6 +263,35 @@ def worker_test(wid):
         return jsonify({'ok': False, 'error': str(e)})
 
 
+@app.route('/api/workers/<int:wid>/vision_test', methods=['POST'])
+@require_auth
+def worker_vision_test(wid):
+    """视觉智能体能力测试：传入图片（URL 或 base64）与问题，验证多模态理解"""
+    w = db.q('SELECT * FROM workers WHERE id=?', (wid,), one=True)
+    if not w:
+        return jsonify({'ok': False, 'error': '不存在'}), 404
+    d = request.get_json(force=True)
+    image_url = (d.get('image_url') or '').strip()
+    image_b64 = (d.get('image_base64') or '').strip()
+    question = (d.get('question') or '请描述这张图片的内容').strip()
+    if not image_url and not image_b64:
+        return jsonify({'ok': False, 'error': '请提供图片 URL 或 base64 数据'}), 400
+    try:
+        if image_b64:
+            r = llm_gateway.chat_vision(
+                w['provider'], w['model'], question, image_url=f'data:image/png;base64,{image_b64}',
+                temperature=0.3, max_tokens=w['max_tokens'] or 2000,
+                base_url=w['base_url'] or None, api_key=w['api_key'] or None)
+        else:
+            r = llm_gateway.chat_vision(
+                w['provider'], w['model'], question, image_url=image_url,
+                temperature=0.3, max_tokens=w['max_tokens'] or 2000,
+                base_url=w['base_url'] or None, api_key=w['api_key'] or None)
+        return jsonify({'ok': True, 'data': r})
+    except Exception as e:
+        return jsonify({'ok': False, 'error': str(e)})
+
+
 @app.route('/api/providers')
 @require_auth
 def providers():
@@ -273,7 +302,7 @@ def providers():
             'has_key': bool(v['api_key']),
             'models': [m for m in config.MODEL_PRICING.keys() if m.startswith(
                 {'doubao': 'doubao', 'deepseek': 'deepseek', 'openai': 'gpt',
-                 'qwen': 'qwen', 'vllm': ''}.get(k, '__none__'))],
+                 'qwen': 'qwen', 'vllm': '', 'autodl': 'qwen3'}.get(k, '__none__'))],
         })
     return jsonify({'ok': True, 'data': data})
 
@@ -1119,8 +1148,8 @@ def template_apply(tid):
             pid, ids = tplmod.apply_project_template(t, variables, worker_id)
             return jsonify({'ok': True, 'kind': 'project', 'id': pid, 'task_ids': ids})
         if t['type'] == 'team':
-            ids = tplmod.apply_team_template(t, variables, provider=d.get('provider', 'doubao'),
-                                             model=d.get('model', 'doubao-seed-evolving'))
+            ids = tplmod.apply_team_template(t, variables, provider=d.get('provider', 'deepseek'),
+                                             model=d.get('model', 'deepseek-v4-flash'))
             return jsonify({'ok': True, 'kind': 'team', 'ids': ids})
         return jsonify({'ok': False, 'error': '未知模板类型'}), 400
     except Exception as e: