langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-21 12:05:30 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

AgentLogEvent类缺少parallel_id属性导致并行执行错误 #8867

New Issue
Closed
opened 2026-02-21 18:28:15 -05:00 by yindo · 2 comments
yindo commented 2026-02-21 18:28:15 -05:00
Owner
Copy Link
Copy Source

Originally created by @alleneee on GitHub (Mar 2, 2025).

问题描述

在使用Dify的工作流进行并行执行时，系统报错：'AgentLogEvent' object has no attribute 'parallel_id'。这表明AgentLogEvent类缺少parallel_id属性，导致在处理并行节点时出现错误。

复现步骤

  1. 使用Docker部署Dify应用
  2. 创建一个包含并行执行节点（parallel execution nodes）的工作流
  3. 运行该工作流
  4. 当工作流执行到并行节点时，系统报错：'AgentLogEvent' object has no attribute 'parallel_id'

代码分析

通过分析代码发现，在api/core/workflow/graph_engine/entities/event.py文件中，AgentLogEvent类的定义如下：

class AgentLogEvent(BaseEvent):
    def __init__(self, agent_chat_message: AgentChatMessage) -> None:
        super().__init__()
        self.agent_chat_message = agent_chat_message

而其他类如BaseParallelBranchEvent和BaseIterationEvent则包含parallel_id属性：

class BaseParallelBranchEvent(BaseEvent):
    def __init__(self, parallel_id: str, parallel_start_node_id: str) -> None:
        super().__init__()
        self.parallel_id = parallel_id
        self.parallel_start_node_id = parallel_start_node_id

在WorkflowBasedAppRunner._handle_event方法中处理事件时，系统尝试访问AgentLogEvent对象的parallel_id属性，但该属性不存在，从而导致错误。

建议修复

  1. 在AgentLogEvent类中添加parallel_id属性，可能也需要添加parallel_start_node_id属性：
class AgentLogEvent(BaseEvent):
    def __init__(self, agent_chat_message: AgentChatMessage, parallel_id: str = None, parallel_start_node_id: str = None) -> None:
        super().__init__()
        self.agent_chat_message = agent_chat_message
        self.parallel_id = parallel_id
        self.parallel_start_node_id = parallel_start_node_id
  1. 同时，需要检查api/core/app/entities/queue_entities.py中的QueueAgentLogEvent类，确保也添加了相应的属性：
class QueueAgentLogEvent(QueueEvent):
    def __init__(self, end_user_id: str, conversation_id: str, agent_chat_message: AgentChatMessage, 
                 parallel_id: str = None, parallel_start_node_id: str = None, task_id: str = None) -> None:
        super().__init__(end_user_id, conversation_id, task_id)
        self.agent_chat_message = agent_chat_message
        self.parallel_id = parallel_id
        self.parallel_start_node_id = parallel_start_node_id
  1. 确保在事件处理逻辑中正确传递parallel_id参数。

环境信息

  • 操作系统：macOS 24.3.0
  • 部署方式：Docker
  • Dify版本：最新版

感谢您的关注和解决这个问题！

Originally created by @alleneee on GitHub (Mar 2, 2025). ## 问题描述 在使用Dify的工作流进行并行执行时，系统报错：`'AgentLogEvent' object has no attribute 'parallel_id'`。这表明`AgentLogEvent`类缺少`parallel_id`属性，导致在处理并行节点时出现错误。 ## 复现步骤 1. 使用Docker部署Dify应用 2. 创建一个包含并行执行节点（parallel execution nodes）的工作流 3. 运行该工作流 4. 当工作流执行到并行节点时，系统报错：`'AgentLogEvent' object has no attribute 'parallel_id'` ## 代码分析 通过分析代码发现，在`api/core/workflow/graph_engine/entities/event.py`文件中，`AgentLogEvent`类的定义如下： ```python class AgentLogEvent(BaseEvent): def __init__(self, agent_chat_message: AgentChatMessage) -> None: super().__init__() self.agent_chat_message = agent_chat_message ``` 而其他类如`BaseParallelBranchEvent`和`BaseIterationEvent`则包含`parallel_id`属性： ```python class BaseParallelBranchEvent(BaseEvent): def __init__(self, parallel_id: str, parallel_start_node_id: str) -> None: super().__init__() self.parallel_id = parallel_id self.parallel_start_node_id = parallel_start_node_id ``` 在`WorkflowBasedAppRunner._handle_event`方法中处理事件时，系统尝试访问`AgentLogEvent`对象的`parallel_id`属性，但该属性不存在，从而导致错误。 ## 建议修复 1. 在`AgentLogEvent`类中添加`parallel_id`属性，可能也需要添加`parallel_start_node_id`属性： ```python class AgentLogEvent(BaseEvent): def __init__(self, agent_chat_message: AgentChatMessage, parallel_id: str = None, parallel_start_node_id: str = None) -> None: super().__init__() self.agent_chat_message = agent_chat_message self.parallel_id = parallel_id self.parallel_start_node_id = parallel_start_node_id ``` 2. 同时，需要检查`api/core/app/entities/queue_entities.py`中的`QueueAgentLogEvent`类，确保也添加了相应的属性： ```python class QueueAgentLogEvent(QueueEvent): def __init__(self, end_user_id: str, conversation_id: str, agent_chat_message: AgentChatMessage, parallel_id: str = None, parallel_start_node_id: str = None, task_id: str = None) -> None: super().__init__(end_user_id, conversation_id, task_id) self.agent_chat_message = agent_chat_message self.parallel_id = parallel_id self.parallel_start_node_id = parallel_start_node_id ``` 3. 确保在事件处理逻辑中正确传递`parallel_id`参数。 ## 环境信息 - 操作系统：macOS 24.3.0 - 部署方式：Docker - Dify版本：最新版 感谢您的关注和解决这个问题！
yindo added the 🐞 bug🌊 feat:workflow labels 2026-02-21 18:28:15 -05:00
yindo closed this issue 2026-02-21 18:28:15 -05:00
yindo commented 2026-02-21 18:28:16 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Mar 2, 2025):

Hey there, @alleneee! I'm here to help you with any bugs, questions, or contributions you have on Dify. Let's get this issue sorted out together.

要解决AgentLogEvent类缺少parallel_id属性导致的并行执行错误，可以按照以下步骤进行修改：

  1. 在AgentLogEvent类中添加parallel_id属性：

    在api/core/workflow/graph_engine/entities/event.py文件中，修改AgentLogEvent类以包含parallel_id属性：

    class AgentLogEvent(BaseAgentEvent):
    id: str = Field(..., description="id")
    label: str = Field(..., description="label")
    node_execution_id: str = Field(..., description="node execution id")
    parent_id: str | None = Field(..., description="parent id")
    error: str | None = Field(..., description="error")
    status: str = Field(..., description="status")
    data: Mapping[str, Any] = Field(..., description="data")
    metadata: Optional[Mapping[str, Any]] = Field(default=None, description="metadata")
    parallel_id: Optional[str] = None  # 添加此行

  2. 在QueueAgentLogEvent类中添加parallel_id属性：

    在api/core/app/entities/queue_entities.py文件中，确保QueueAgentLogEvent类也包含parallel_id属性：

    class QueueAgentLogEvent(QueueEvent):
    def __init__(self, end_user_id: str, conversation_id: str, agent_chat_message: AgentChatMessage, 
                 parallel_id: str = None, parallel_start_node_id: str = None, task_id: str = None) -> None:
        super().__init__(end_user_id, conversation_id, task_id)
        self.agent_chat_message = agent_chat_message
        self.parallel_id = parallel_id
        self.parallel_start_node_id = parallel_start_node_id

  3. 确保在事件处理逻辑中正确传递parallel_id参数：

    在WorkflowBasedAppRunner._handle_event方法中，确保在创建QueueAgentLogEvent对象时传递parallel_id参数。

通过这些修改，可以解决AgentLogEvent类缺少parallel_id属性导致的并行执行错误[1][2].

To continue talking to Dosu, mention @dosu.

Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other

@dosubot[bot] commented on GitHub (Mar 2, 2025): <!-- Greeting --> Hey there, @alleneee! I'm here to help you with any bugs, questions, or contributions you have on Dify. Let's get this issue sorted out together. <!-- Answer --> 要解决`AgentLogEvent`类缺少`parallel_id`属性导致的并行执行错误，可以按照以下步骤进行修改： 1. **在`AgentLogEvent`类中添加`parallel_id`属性**： 在`api/core/workflow/graph_engine/entities/event.py`文件中，修改`AgentLogEvent`类以包含`parallel_id`属性： ```python class AgentLogEvent(BaseAgentEvent): id: str = Field(..., description="id") label: str = Field(..., description="label") node_execution_id: str = Field(..., description="node execution id") parent_id: str | None = Field(..., description="parent id") error: str | None = Field(..., description="error") status: str = Field(..., description="status") data: Mapping[str, Any] = Field(..., description="data") metadata: Optional[Mapping[str, Any]] = Field(default=None, description="metadata") parallel_id: Optional[str] = None # 添加此行 ``` 2. **在`QueueAgentLogEvent`类中添加`parallel_id`属性**： 在`api/core/app/entities/queue_entities.py`文件中，确保`QueueAgentLogEvent`类也包含`parallel_id`属性： ```python class QueueAgentLogEvent(QueueEvent): def __init__(self, end_user_id: str, conversation_id: str, agent_chat_message: AgentChatMessage, parallel_id: str = None, parallel_start_node_id: str = None, task_id: str = None) -> None: super().__init__(end_user_id, conversation_id, task_id) self.agent_chat_message = agent_chat_message self.parallel_id = parallel_id self.parallel_start_node_id = parallel_start_node_id ``` 3. **确保在事件处理逻辑中正确传递`parallel_id`参数**： 在`WorkflowBasedAppRunner._handle_event`方法中，确保在创建`QueueAgentLogEvent`对象时传递`parallel_id`参数。 通过这些修改，可以解决`AgentLogEvent`类缺少`parallel_id`属性导致的并行执行错误<sup>[[1]](https://github.com/langgenius/dify/blob/main/api/core/workflow/graph_engine/entities/event.py)</sup><sup>[[2]](https://github.com/langgenius/dify/blob/main/api/core/app/entities/queue_entities.py)</sup>. <!-- Dosu Comment Footer --> *To continue talking to [Dosu](https://dosu.dev), mention @dosu.* --- <sup>Help Dosu learn! Give it feedback: [Great Response](https://app.dosu.dev/response-feedback/035a532e-33c2-4918-bb93-9177407797df?feedback_type=great_response) | [Irrelevant Answer](https://app.dosu.dev/response-feedback/035a532e-33c2-4918-bb93-9177407797df?feedback_type=irrelevant_answer) | [Incorrect Sources](https://app.dosu.dev/response-feedback/035a532e-33c2-4918-bb93-9177407797df?feedback_type=incorrect_sources) | [Too Verbose](https://app.dosu.dev/response-feedback/035a532e-33c2-4918-bb93-9177407797df?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/035a532e-33c2-4918-bb93-9177407797df?feedback_type=hallucination) | [Bug Report](https://app.dosu.dev/response-feedback/035a532e-33c2-4918-bb93-9177407797df?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/035a532e-33c2-4918-bb93-9177407797df?feedback_type=other)</sup>
yindo commented 2026-02-21 18:28:16 -05:00
Author
Owner
Copy Link
Copy Source

@crazywoola commented on GitHub (Mar 2, 2025):

Close due to #1542

@crazywoola commented on GitHub (Mar 2, 2025): Close due to #1542
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 🌊 feat:workflow 🐞 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#8867
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?