langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-21 20:15:31 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

Agent mode cannot output streaming #19487

New Issue
Closed
opened 2026-02-21 20:00:22 -05:00 by yindo · 0 comments
yindo commented 2026-02-21 20:00:22 -05:00
Owner
Copy Link
Copy Source

Originally created by @NieRonghua on GitHub (Oct 16, 2025).

Self Checks

  • I have read the Contributing Guide and Language Policy.
  • This is only for bug report, if you would like to ask a question, please head to Discussions.
  • I have searched for existing issues search for existing issues, including closed ones.
  • I confirm that I am using English to submit this report, otherwise it will be closed.
  • 【中文用户 & Non English User】请使用英语提交，否则会被关闭 ：）
  • Please do not modify this template :) and fill in all the required fields.

Dify version

1.8.1

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

This is my app, the mode is Agent, no tool is called, and the model is a privately deployed LLM

When I issue a query, the Agent's thinking process is streamed out, but the time result of the request model is not returned in a streamed manner.

API Response：

data: {"event":"agent_thought","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"e1439e03-b6a0-42a7-a3ef-f7ef74e84617","position":1,"thought":"","observation":"","tool":"","tool_labels":{},"tool_input":"","message_files":[]}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":" "}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"I"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":" "}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"k"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"n"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"o"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"w"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":" "}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"w"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"h"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"a"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"t"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":" "}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"t"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"o"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":" "}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"r"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"e"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"s"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"p"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"o"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"n"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"d"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"\n"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"\n"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"\n"}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":""}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":""}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":""}

data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"要在Python中连接MySQL数据库，可以使用`mysql-connector-python`库。以下是一个简单的示例，展示如何建立连接、执行查询和关闭连接：\n\n首先，确保安装了`mysql-connector-python`库：\n```bash\npip install mysql-connector-python\n```\n\n然后，可以使用以下代码连接到MySQL数据库：\n```python\nimport mysql.connector\nfrom mysql.connector import Error\n\ntry:\n    # 建立连接\n    connection = mysql.connector.connect(\n        host='localhost',\n        database='your_database',\n        user='your_username',\n        password='your_password'\n    )\n\n    if connection.is_connected():\n        db_info = connection.get_server_info()\n        print(f'已成功连接到MySQL服务器，版本为 {db_info}')\n        \n        # 创建游标\n        cursor = connection.cursor()\n        \n        # 执行查询\n        query = 'SELECT * FROM your_table'\n        cursor.execute(query)\n        \n        # 获取查询结果\n        records = cursor.fetchall()\n        for row in records:\n            print(row)\n        \nexcept Error as e:\n    print(f'连接MySQL时发生错误: {e}')\nfinally:\n    if connection.is_connected():\n        cursor.close()\n        connection.close()\n        print('MySQL连接已关闭')\n```\n\n请根据实际情况修改`host`、`database`、`user`和`password`参数。"}

data: {"event":"message_end","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","metadata":{"annotation_reply":null,"retriever_resources":[],"usage":{"prompt_tokens":1192,"prompt_unit_price":"0.004","prompt_price_unit":"0.001","prompt_price":"0.004768","completion_tokens":312,"completion_unit_price":"0.012","completion_price_unit":"0.001","completion_price":"0.003744","total_tokens":1504,"total_price":"0.008512","currency":"RMB","latency":7.794083629269153}},"files":null}

The body of the request for the private deployment llm model

{
  "model": "qwen2.5-72b-instruct",
  "stream": true,
  "messages": [
    {
      "role": "system",
      "content": "Respond to the human as helpfully and accurately as possible.\n\n​​# Role: 多格式测试内容生成专家​​\n​​author​​: TestEngineer\n​​version​​: 2.1\n​​description​​: 专为UI及格式验证而设计，能根据用户指令动态生成纯文本或富含Markdown样式的测试内容。\n​​核心能力与格式判断逻辑​​\n你的核心任务是生成用于测试的不同长度文章。关键在于​​根据用户指令动态选择输出格式​​：\n​​格式触发​​：当用户指令中明确包含 ​​markdown​​、​​md​​ 或 ​​格式​​、​​样式​​ 等关键词时，必须启用Markdown格式输出。\n​​默认格式​​：若用户指令未明确提及上述格式要求（例如，仅要求生成一篇XX字的文章），则​​默认使用纯文本（Plain Text）格式​​输出。\n​​主动确认（可选）​​：在复杂或模糊指令下，可主动询问用户期望的输出格式，以确保理解一致。\n​​输出内容规范​​\n​​内容长度控制​​：\n​​短内容（50-200字）​​：用于测试标题、列表、按钮等小组件布局。\n​​中内容（200-500字）​​：用于测试卡片、段落等标准容器的渲染。\n​​长内容（500-1500字）​​：用于测试长文阅读、滚动、导航等整体页面布局。\n​​Markdown样式库（当且仅当要求Markdown格式时启用）​​：\n必须系统化应用以下元素，确保均匀分布，避免堆积：\n​​标题​​：从 # H1到 ###### H6的全部六级标题。\n​​强调​​：​​粗体​​、斜体、​​粗斜体​​、~~删除线~~。\n​​列表​​：有序列表（1. 2. 3.）、无序列表（-, *, +）、任务列表（- [ ], - [x]）。\n​​代码​​：行内代码 code和代码块（需指定语言，如 ```python）。\n​​引用​​：> 块引用。\n​​表格​​：创建包含对齐方式（左、中、右）的表格。\n​​链接与图片​​：[链接文本](URL)和 ![图片描述](图片URL)。\n​​分隔线​​：使用 ***或 ---。\n​​纯文本规范（默认格式）​​：\n内容结构清晰，逻辑通顺，语义连贯。\n仅通过换行和空格实现基本段落划分，​​不使用任何Markdown标记符号​​。\n确保内容本身具备可读性和测试价值。\n​​工作流程​​\n​​解析指令​​：识别用户指令中的关键词，判断输出格式要求。\n​​确认需求​​：明确文章主题、目标长度及特殊要求。\n​​结构化生成​​：生成包含引言、正文（至少两个主要部分）和结论的结构化文章。\n​​应用样式​​：根据判断结果，系统化应用Markdown样式或保持纯文本格式。\n​​输出与验证​​：\n输出最终内容，不添加额外解释。\n若为Markdown格式，在文末附上\"​​本文应用的Markdown元素清单​​\"（表格形式），列所使用的元素及示例。\n​​约束条件​​\n​​内容真实性​​：文章内容需逻辑通顺，语义连贯。主题可为技术、科普或生活类。\n​​格式准确性​​：Markdown语法需严格符合CommonMark标准；纯文本需整洁无标记符号。\n​​禁止冗余​​：输出内容除指定的Markdown样式或纯文本外，不添加任何引导语或总结。\n​​安全边界​​：只生成公开、中立、无争议的测试内容。\n💡 如何使用（示例）\n您可以通过以下指令模式灵活驱动智能体：\n测试场景\n示例指令\n​​全面Markdown测试​​\n\"生成一篇约800字的长文，主题为'人工智能的未来'，​​使用markdown格式​​，并要求文章必须包含所有Markdown样式元素。\"\n​​纯文本专项测试​​\n\"生成一篇300字的中等长度文章，主题为'季度数据报告'，​​无需任何格式​​。\"\n​​模糊指令（触发默认）​​\n\"写一段150字左右的短文，介绍一下云计算。\" （智能体将默认输出纯文本）\n​​主动确认（复杂情况）​​\n用户指令：\"生成一份开发计划，内容要详细。\" -> 智能体可回复：\"请问您希望的输出格式是纯文本还是Markdown格式？Markdown格式可以使计划的结构更清晰。\"\n\nYou have access to the following tools:\n\n[]\n\nUse a json blob to specify a tool by providing an action key (tool name) and an action_input key (tool input).\nValid \"action\" values: \"Final Answer\" or \n\nProvide only ONE action per $JSON_BLOB, as shown:\n\n```\n{\n  \"action\": $TOOL_NAME,\n  \"action_input\": $ACTION_INPUT\n}\n```\n\nFollow this format:\n\nQuestion: input question to answer\nThought: consider previous and subsequent steps\nAction:\n```\n$JSON_BLOB\n```\nObservation: action result\n... (repeat Thought/Action/Observation N times)\nThought: I know what to respond\nAction:\n```\n{\n  \"action\": \"Final Answer\",\n  \"action_input\": \"Final response to human\"\n}\n```\n\nBegin! Reminder to ALWAYS respond with a valid json blob of a single action. Use tools if necessary. Respond directly if appropriate. Format is Action:```$JSON_BLOB```then Observation:."
    },
    {
      "role": "user",
      "content": "python 链接MySQL"
    }
  ],
  "stop": [
    "Observation"
  ],
  "user": "daf6d8aa-4d06-4416-ab71-c16d64499c6c"
}

✔️ Expected Behavior

My version is 1.8.1. It seems that this problem only occurred after the upgrade, and it did not occur before.

❌ Actual Behavior

No response

Originally created by @NieRonghua on GitHub (Oct 16, 2025). ### Self Checks - [x] I have read the [Contributing Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) and [Language Policy](https://github.com/langgenius/dify/issues/1542). - [x] This is only for bug report, if you would like to ask a question, please head to [Discussions](https://github.com/langgenius/dify/discussions/categories/general). - [x] I have searched for existing issues [search for existing issues](https://github.com/langgenius/dify/issues), including closed ones. - [x] I confirm that I am using English to submit this report, otherwise it will be closed. - [x] 【中文用户 & Non English User】请使用英语提交，否则会被关闭 ：） - [x] Please do not modify this template :) and fill in all the required fields. ### Dify version 1.8.1 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce This is my app, the mode is Agent, no tool is called, and the model is a privately deployed LLM When I issue a query, the Agent's thinking process is streamed out, but the time result of the request model is not returned in a streamed manner. API Response： ``` data: {"event":"agent_thought","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"e1439e03-b6a0-42a7-a3ef-f7ef74e84617","position":1,"thought":"","observation":"","tool":"","tool_labels":{},"tool_input":"","message_files":[]} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":" "} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"I"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":" "} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"k"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"n"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"o"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"w"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":" "} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"w"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"h"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"a"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"t"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":" "} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"t"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"o"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":" "} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"r"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"e"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"s"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"p"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"o"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"n"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"d"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"\n"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"\n"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"\n"} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":""} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":""} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":""} data: {"event":"agent_message","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","answer":"要在Python中连接MySQL数据库，可以使用`mysql-connector-python`库。以下是一个简单的示例，展示如何建立连接、执行查询和关闭连接：\n\n首先，确保安装了`mysql-connector-python`库：\n```bash\npip install mysql-connector-python\n```\n\n然后，可以使用以下代码连接到MySQL数据库：\n```python\nimport mysql.connector\nfrom mysql.connector import Error\n\ntry:\n # 建立连接\n connection = mysql.connector.connect(\n host='localhost',\n database='your_database',\n user='your_username',\n password='your_password'\n )\n\n if connection.is_connected():\n db_info = connection.get_server_info()\n print(f'已成功连接到MySQL服务器，版本为 {db_info}')\n \n # 创建游标\n cursor = connection.cursor()\n \n # 执行查询\n query = 'SELECT * FROM your_table'\n cursor.execute(query)\n \n # 获取查询结果\n records = cursor.fetchall()\n for row in records:\n print(row)\n \nexcept Error as e:\n print(f'连接MySQL时发生错误: {e}')\nfinally:\n if connection.is_connected():\n cursor.close()\n connection.close()\n print('MySQL连接已关闭')\n```\n\n请根据实际情况修改`host`、`database`、`user`和`password`参数。"} data: {"event":"message_end","conversation_id":"cef49eaa-f578-4efd-a79b-258c5cf88bf1","message_id":"fcfee593-a095-4180-90af-da948df792a2","created_at":1760699167,"task_id":"aa876a74-3f3a-443c-9ad3-f618ea698f74","id":"fcfee593-a095-4180-90af-da948df792a2","metadata":{"annotation_reply":null,"retriever_resources":[],"usage":{"prompt_tokens":1192,"prompt_unit_price":"0.004","prompt_price_unit":"0.001","prompt_price":"0.004768","completion_tokens":312,"completion_unit_price":"0.012","completion_price_unit":"0.001","completion_price":"0.003744","total_tokens":1504,"total_price":"0.008512","currency":"RMB","latency":7.794083629269153}},"files":null} ``` The body of the request for the private deployment llm model ``` { "model": "qwen2.5-72b-instruct", "stream": true, "messages": [ { "role": "system", "content": "Respond to the human as helpfully and accurately as possible.\n\n​​# Role: 多格式测试内容生成专家​​\n​​author​​: TestEngineer\n​​version​​: 2.1\n​​description​​: 专为UI及格式验证而设计，能根据用户指令动态生成纯文本或富含Markdown样式的测试内容。\n​​核心能力与格式判断逻辑​​\n你的核心任务是生成用于测试的不同长度文章。关键在于​​根据用户指令动态选择输出格式​​：\n​​格式触发​​：当用户指令中明确包含 ​​markdown​​、​​md​​ 或 ​​格式​​、​​样式​​ 等关键词时，必须启用Markdown格式输出。\n​​默认格式​​：若用户指令未明确提及上述格式要求（例如，仅要求生成一篇XX字的文章），则​​默认使用纯文本（Plain Text）格式​​输出。\n​​主动确认（可选）​​：在复杂或模糊指令下，可主动询问用户期望的输出格式，以确保理解一致。\n​​输出内容规范​​\n​​内容长度控制​​：\n​​短内容（50-200字）​​：用于测试标题、列表、按钮等小组件布局。\n​​中内容（200-500字）​​：用于测试卡片、段落等标准容器的渲染。\n​​长内容（500-1500字）​​：用于测试长文阅读、滚动、导航等整体页面布局。\n​​Markdown样式库（当且仅当要求Markdown格式时启用）​​：\n必须系统化应用以下元素，确保均匀分布，避免堆积：\n​​标题​​：从 # H1到 ###### H6的全部六级标题。\n​​强调​​：​​粗体​​、斜体、​​粗斜体​​、~~删除线~~。\n​​列表​​：有序列表（1. 2. 3.）、无序列表（-, *, +）、任务列表（- [ ], - [x]）。\n​​代码​​：行内代码 code和代码块（需指定语言，如 ```python）。\n​​引用​​：> 块引用。\n​​表格​​：创建包含对齐方式（左、中、右）的表格。\n​​链接与图片​​：[链接文本](URL)和 ![图片描述](图片URL)。\n​​分隔线​​：使用 ***或 ---。\n​​纯文本规范（默认格式）​​：\n内容结构清晰，逻辑通顺，语义连贯。\n仅通过换行和空格实现基本段落划分，​​不使用任何Markdown标记符号​​。\n确保内容本身具备可读性和测试价值。\n​​工作流程​​\n​​解析指令​​：识别用户指令中的关键词，判断输出格式要求。\n​​确认需求​​：明确文章主题、目标长度及特殊要求。\n​​结构化生成​​：生成包含引言、正文（至少两个主要部分）和结论的结构化文章。\n​​应用样式​​：根据判断结果，系统化应用Markdown样式或保持纯文本格式。\n​​输出与验证​​：\n输出最终内容，不添加额外解释。\n若为Markdown格式，在文末附上\"​​本文应用的Markdown元素清单​​\"（表格形式），列所使用的元素及示例。\n​​约束条件​​\n​​内容真实性​​：文章内容需逻辑通顺，语义连贯。主题可为技术、科普或生活类。\n​​格式准确性​​：Markdown语法需严格符合CommonMark标准；纯文本需整洁无标记符号。\n​​禁止冗余​​：输出内容除指定的Markdown样式或纯文本外，不添加任何引导语或总结。\n​​安全边界​​：只生成公开、中立、无争议的测试内容。\n💡 如何使用（示例）\n您可以通过以下指令模式灵活驱动智能体：\n测试场景\n示例指令\n​​全面Markdown测试​​\n\"生成一篇约800字的长文，主题为'人工智能的未来'，​​使用markdown格式​​，并要求文章必须包含所有Markdown样式元素。\"\n​​纯文本专项测试​​\n\"生成一篇300字的中等长度文章，主题为'季度数据报告'，​​无需任何格式​​。\"\n​​模糊指令（触发默认）​​\n\"写一段150字左右的短文，介绍一下云计算。\" （智能体将默认输出纯文本）\n​​主动确认（复杂情况）​​\n用户指令：\"生成一份开发计划，内容要详细。\" -> 智能体可回复：\"请问您希望的输出格式是纯文本还是Markdown格式？Markdown格式可以使计划的结构更清晰。\"\n\nYou have access to the following tools:\n\n[]\n\nUse a json blob to specify a tool by providing an action key (tool name) and an action_input key (tool input).\nValid \"action\" values: \"Final Answer\" or \n\nProvide only ONE action per $JSON_BLOB, as shown:\n\n```\n{\n \"action\": $TOOL_NAME,\n \"action_input\": $ACTION_INPUT\n}\n```\n\nFollow this format:\n\nQuestion: input question to answer\nThought: consider previous and subsequent steps\nAction:\n```\n$JSON_BLOB\n```\nObservation: action result\n... (repeat Thought/Action/Observation N times)\nThought: I know what to respond\nAction:\n```\n{\n \"action\": \"Final Answer\",\n \"action_input\": \"Final response to human\"\n}\n```\n\nBegin! Reminder to ALWAYS respond with a valid json blob of a single action. Use tools if necessary. Respond directly if appropriate. Format is Action:```$JSON_BLOB```then Observation:." }, { "role": "user", "content": "python 链接MySQL" } ], "stop": [ "Observation" ], "user": "daf6d8aa-4d06-4416-ab71-c16d64499c6c" } ``` ### ✔️ Expected Behavior My version is 1.8.1. It seems that this problem only occurred after the upgrade, and it did not occur before. ### ❌ Actual Behavior _No response_
yindo added the 🐞 bug label 2026-02-21 20:00:22 -05:00
yindo closed this issue 2026-02-21 20:00:22 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Knowledge Pipeline
Proposal
WIP
cloud
dependencies
feat:webapp
good first issue
outdated
performance
pull-request
Mirrored from GitHub Pull Request
 python:uv
refactor
size:L
stale
status: accepting prs
status: blocked
status: in discussion
stt & tts
vulnerablity
web
wont-fix
🌊 feat:workflow
🌚 invalid
🐞 bug
👻 feat:rag
💪 enhancement
📚 documentation
🔨 feat:tools
🙋‍♂️ question
🙏 help wanted
🤔 cant-reproduce
🤖 feat:agent
No Label 🐞 bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#19487
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?