✨ Agent duplicate name handling logic improvement #1622

[Specification Details] 1.Add test cases.

Author: YehongPan

backend/prompts/utils/prompt_generate.yaml

@@ -52,16 +52,16 @@ FEW_SHOTS_SYSTEM_PROMPT: |-
      - 用简单的Python编写代码
      - 遵循python代码规范和python语法
      - 根据格式规范正确调用工具/助手
-     - 考虑到代码执行与展示用户代码的区别，使用'代码：\n```<RUN>\n'开头，并以'```<END_CODE>'表达运行代码，使用'代码：\n```<DISPLAY:语言类型>\n'开头，并以'```<END_CODE>'表达展示代码
-     - 注意运行的代码不会被用户看到，所以如果用户需要看到代码，你需要使用'代码：\n```<DISPLAY:语言类型>\n'开头，并以'```<END_CODE>'表达展示代码。
+     - 考虑到代码执行与展示用户代码的区别，使用'代码：\n```<RUN>\n'开头，并以'```<END_CODE>'表达运行代码，使用'代码：\n```<DISPLAY:语言类型>\n'开头，并以'```<END_DISPLAY_CODE>'表达展示代码
+     - 注意运行的代码不会被用户看到，所以如果用户需要看到代码，你需要使用'代码：\n```<DISPLAY:语言类型>\n'开头，并以'```<END_DISPLAY_CODE>'表达展示代码。
 
   3. 观察结果：
      - 查看代码执行结果
   
   在思考结束后，当Agent认为可以回答用户问题，那么可以不生成代码，直接生成最终回答给到用户并停止循环。
 
   ### python代码规范
-  1. 如果认为是需要执行的代码，代码内容以'代码：\n```<RUN>\n'开头，并以'```<END_CODE>'标识符结尾。如果是不需要执行仅用于展示的代码，代码内容以'代码：\n```<DISPLAY:语言类型>\n'开头，并以'```<END_CODE>'标识符结尾，其中语言类型例如python、java、javascript等；
+  1. 如果认为是需要执行的代码，代码内容以'代码：\n```<RUN>\n'开头，并以'```<END_CODE>'标识符结尾。如果是不需要执行仅用于展示的代码，代码内容以'代码：\n```<DISPLAY:语言类型>\n'开头，并以'```<END_DISPLAY_CODE>'标识符结尾，其中语言类型例如python、java、javascript等；
   2. 只使用已定义的变量，变量将在多次调用之间持续保持；
   3. 使用“print()”函数让下一次的模型调用看到对应变量信息；
   4. 正确使用工具/助手的入参，使用关键字参数，不要用字典形式；
@@ -160,7 +160,7 @@ FEW_SHOTS_SYSTEM_PROMPT: |-
     middle = [x for x in arr if x == pivot]
     right = [x for x in arr if x > pivot]
     return quick_sort(left) + middle + quick_sort(right)
-  ```<END_CODE>
+  ```<END_DISPLAY_CODE>
   观察结果：快速排序的python代码。
   
   思考：我已经获得了快速排序的python代码，现在我将生成最终回答。
@@ -174,7 +174,7 @@ FEW_SHOTS_SYSTEM_PROMPT: |-
     middle = [x for x in arr if x == pivot]
     right = [x for x in arr if x > pivot]
     return quick_sort(left) + middle + quick_sort(right)
-  ```<END_CODE>
+  ```<END_DISPLAY_CODE>
 
   ---
 

backend/prompts/utils/prompt_generate_en.yaml

@@ -53,16 +53,16 @@ FEW_SHOTS_SYSTEM_PROMPT: |-
      - Write code in simple Python
      - Follow Python coding standards and Python syntax
      - Call tools/assistants correctly according to format specifications
-     - To distinguish between code execution and displaying user code, use 'Code: \n```<RUN>\n' to start executing code and '```<END_CODE>' to indicate its completion. Use 'Code: \n```<DISPLAY:language_type>\n' to start displaying code and '```<END_CODE>' to indicate its completion.
-     - Note that executed code is not visible to users. If users need to see the code, use 'Code: \n```<DISPLAY:language_type>\n' as the start and '```<END_CODE>' to denote displayed code.
+     - To distinguish between code execution and displaying user code, use 'Code: \n```<RUN>\n' to start executing code and '```<END_CODE>' to indicate its completion. Use 'Code: \n```<DISPLAY:language_type>\n' to start displaying code and '```<END_DISPLAY_CODE>' to indicate its completion.
+     - Note that executed code is not visible to users. If users need to see the code, use 'Code: \n```<DISPLAY:language_type>\n' as the start and '```<END_DISPLAY_CODE>' to denote displayed code.
 
   3. Observe Results:
      - View code execution results
   
   After thinking, when you believe you can answer the user's question, you can generate a final answer directly to the user without generating code and stop the loop.
   
   ### Python Code Specifications
-  1. If it is considered to be code that needs to be executed, the code content begins with 'Code:\n```<RUN>\n' and ends with '```<END_CODE>'. If the code does not need to be executed for display only, the code content begins with 'Code:\n```<DISPLAY:language_type>\n', and ends with '```<END_CODE>', where language_type can be python, java, javascript, etc.;
+  1. If it is considered to be code that needs to be executed, the code content begins with 'Code:\n```<RUN>\n' and ends with '```<END_CODE>'. If the code does not need to be executed for display only, the code content begins with 'Code:\n```<DISPLAY:language_type>\n', and ends with '```<END_DISPLAY_CODE>', where language_type can be python, java, javascript, etc.;
   2. Only use defined variables, variables will persist between multiple calls;
   3. Use "print()" function to let the next model call see corresponding variable information;
   4. Use tool/assistant input parameters correctly, use keyword arguments, not dictionary format;
@@ -158,7 +158,7 @@ FEW_SHOTS_SYSTEM_PROMPT: |-
     middle = [x for x in arr if x == pivot]
     right = [x for x in arr if x > pivot]
     return quick_sort(left) + middle + quick_sort(right)
-  ```<END_CODE>
+  ```<END_DISPLAY_CODE>
   Observe Results: The Python quick sort code.
 
   Think: I have obtained the Python quick sort code, now I will generate the final answer.
@@ -172,7 +172,7 @@ FEW_SHOTS_SYSTEM_PROMPT: |-
     middle = [x for x in arr if x == pivot]
     right = [x for x in arr if x > pivot]
     return quick_sort(left) + middle + quick_sort(right)
-  ```<END_CODE>
+  ```<END_DISPLAY_CODE>
 
   ---
 

test/backend/services/test_agent_service.py

@@ -5302,6 +5302,49 @@ def test_check_agent_value_duplicate_with_and_without_exclude():
     )
 
 
+@patch('backend.services.agent_service.query_all_agent_info_by_tenant_id')
+def test_check_agent_value_duplicate_empty_value(mock_query_all):
+    """_check_agent_value_duplicate should return False when value is empty."""
+    # Test empty string
+    assert not agent_service._check_agent_value_duplicate(
+        "name", "", tenant_id="t", agents_cache=[]
+    )
+    # Test None value
+    assert not agent_service._check_agent_value_duplicate(
+        "name", None, tenant_id="t", agents_cache=[]
+    )
+    # Should not call query_all_agent_info_by_tenant_id when value is empty
+    mock_query_all.assert_not_called()
+
+
+@patch('backend.services.agent_service.query_all_agent_info_by_tenant_id')
+def test_check_agent_value_duplicate_cache_none(mock_query_all):
+    """_check_agent_value_duplicate should query database when agents_cache is None."""
+    mock_query_all.return_value = [
+        {"agent_id": 1, "name": "agent_one"},
+        {"agent_id": 2, "name": "agent_two"},
+    ]
+
+    # Should query database when cache is None
+    assert agent_service._check_agent_value_duplicate(
+        "name", "agent_one", tenant_id="t", agents_cache=None
+    )
+    mock_query_all.assert_called_once_with("t")
+
+    # Reset mock
+    mock_query_all.reset_mock()
+    mock_query_all.return_value = [
+        {"agent_id": 1, "name": "agent_one"},
+        {"agent_id": 2, "name": "agent_two"},
+    ]
+
+    # Should query database when cache is None and no duplicate found
+    assert not agent_service._check_agent_value_duplicate(
+        "name", "agent_three", tenant_id="t", agents_cache=None
+    )
+    mock_query_all.assert_called_once_with("t")
+
+
 def test_generate_unique_value_with_suffix_success():
     """_generate_unique_value_with_suffix should find first available suffix."""
 
@@ -5448,6 +5491,203 @@ def fallback(base):
     assert used.get("called") is True
 
 
+def test_regenerate_agent_value_with_llm_empty_system_prompt(monkeypatch):
+    """_regenerate_agent_value_with_llm should use default_system_prompt when system_prompt is empty."""
+
+    monkeypatch.setattr(
+        agent_service,
+        "get_prompt_generate_prompt_template",
+        lambda lang: {},
+        raising=False,
+    )
+    monkeypatch.setattr(
+        agent_service,
+        "_render_prompt_template",
+        lambda template_str, **kwargs: "",  # Return empty string
+        raising=False,
+    )
+
+    def fake_call_llm(model_id, user_prompt, system_prompt, callback, tenant_id):
+        # Verify that default_system_prompt was used
+        assert system_prompt == "default_system"
+        return "new_name"
+
+    fake_prompt_module = MagicMock()
+    fake_prompt_module.call_llm_for_system_prompt = fake_call_llm
+    sys.modules["services.prompt_service"] = fake_prompt_module
+
+    result = _regenerate_agent_value_with_llm(
+        original_value="old",
+        existing_values=["existing"],
+        task_description="task",
+        model_id=1,
+        tenant_id="tenant",
+        language="en",
+        system_prompt_key="SYS_KEY",
+        user_prompt_key="USER_KEY",
+        default_system_prompt="default_system",
+        default_user_prompt_builder=lambda ctx: "user",
+        fallback_fn=lambda base: f"fallback_{base}",
+    )
+    assert result == "new_name"
+
+
+def test_regenerate_agent_value_with_llm_empty_user_prompt(monkeypatch):
+    """_regenerate_agent_value_with_llm should use default_user_prompt_builder when user_prompt is empty."""
+
+    monkeypatch.setattr(
+        agent_service,
+        "get_prompt_generate_prompt_template",
+        lambda lang: {},
+        raising=False,
+    )
+
+    call_count = {"render_count": 0}
+
+    def mock_render(template_str, **kwargs):
+        call_count["render_count"] += 1
+        # First call is for system_prompt, return non-empty
+        if call_count["render_count"] == 1:
+            return "system_prompt"
+        # Second call is for user_prompt, return empty
+        return ""
+
+    monkeypatch.setattr(
+        agent_service,
+        "_render_prompt_template",
+        mock_render,
+        raising=False,
+    )
+
+    def fake_call_llm(model_id, user_prompt, system_prompt, callback, tenant_id):
+        # Verify that default_user_prompt_builder was used
+        assert user_prompt == "default_user"
+        return "new_name"
+
+    fake_prompt_module = MagicMock()
+    fake_prompt_module.call_llm_for_system_prompt = fake_call_llm
+    sys.modules["services.prompt_service"] = fake_prompt_module
+
+    result = _regenerate_agent_value_with_llm(
+        original_value="old",
+        existing_values=["existing"],
+        task_description="task",
+        model_id=1,
+        tenant_id="tenant",
+        language="en",
+        system_prompt_key="SYS_KEY",
+        user_prompt_key="USER_KEY",
+        default_system_prompt="system_prompt",
+        default_user_prompt_builder=lambda ctx: "default_user",
+        fallback_fn=lambda base: f"fallback_{base}",
+    )
+    assert result == "new_name"
+
+
+def test_regenerate_agent_value_with_llm_duplicate_candidate(monkeypatch):
+    """_regenerate_agent_value_with_llm should raise ValueError when generated candidate is duplicate."""
+
+    monkeypatch.setattr(
+        agent_service,
+        "get_prompt_generate_prompt_template",
+        lambda lang: {},
+        raising=False,
+    )
+
+    attempt_count = {"count": 0}
+
+    def fake_call_llm(model_id, user_prompt, system_prompt, callback, tenant_id):
+        attempt_count["count"] += 1
+        # Return a value that exists in existing_values
+        if attempt_count["count"] == 1:
+            return "existing"  # This is a duplicate
+        # On retry, return a unique value
+        return "new_unique_name"
+
+    fake_prompt_module = MagicMock()
+    fake_prompt_module.call_llm_for_system_prompt = fake_call_llm
+    sys.modules["services.prompt_service"] = fake_prompt_module
+
+    result = _regenerate_agent_value_with_llm(
+        original_value="old",
+        existing_values=["existing", "another"],
+        task_description="task",
+        model_id=1,
+        tenant_id="tenant",
+        language="en",
+        system_prompt_key="SYS_KEY",
+        user_prompt_key="USER_KEY",
+        default_system_prompt="sys",
+        default_user_prompt_builder=lambda ctx: "user",
+        fallback_fn=lambda base: f"fallback_{base}",
+    )
+    # Should retry and eventually return a unique value
+    assert result == "new_unique_name"
+    assert attempt_count["count"] == 2
+
+
+def test_regenerate_agent_name_with_llm(monkeypatch):
+    """_regenerate_agent_name_with_llm should call _regenerate_agent_value_with_llm with correct parameters."""
+
+    monkeypatch.setattr(
+        agent_service,
+        "get_prompt_generate_prompt_template",
+        lambda lang: {},
+        raising=False,
+    )
+
+    def fake_call_llm(model_id, user_prompt, system_prompt, callback, tenant_id):
+        return "new_agent_name"
+
+    fake_prompt_module = MagicMock()
+    fake_prompt_module.call_llm_for_system_prompt = fake_call_llm
+    sys.modules["services.prompt_service"] = fake_prompt_module
+
+    result = agent_service._regenerate_agent_name_with_llm(
+        original_name="old_name",
+        existing_names=["existing1", "existing2"],
+        task_description="task desc",
+        model_id=1,
+        tenant_id="tenant",
+        language="en",
+        agents_cache=[],
+        exclude_agent_id=None
+    )
+
+    assert result == "new_agent_name"
+
+
+def test_regenerate_agent_display_name_with_llm(monkeypatch):
+    """_regenerate_agent_display_name_with_llm should call _regenerate_agent_value_with_llm with correct parameters."""
+
+    monkeypatch.setattr(
+        agent_service,
+        "get_prompt_generate_prompt_template",
+        lambda lang: {},
+        raising=False,
+    )
+
+    def fake_call_llm(model_id, user_prompt, system_prompt, callback, tenant_id):
+        return "New Display Name"
+
+    fake_prompt_module = MagicMock()
+    fake_prompt_module.call_llm_for_system_prompt = fake_call_llm
+    sys.modules["services.prompt_service"] = fake_prompt_module
+
+    result = agent_service._regenerate_agent_display_name_with_llm(
+        original_display_name="Old Display Name",
+        existing_display_names=["Display1", "Display2"],
+        task_description="task desc",
+        model_id=1,
+        tenant_id="tenant",
+        language="en",
+        agents_cache=[],
+        exclude_agent_id=None
+    )
+
+    assert result == "New Display Name"
+
+
 @pytest.mark.asyncio
 async def test_import_agent_impl_dfs_import_order(monkeypatch):
     """