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

Incorrect order of steps in parallel branches #13182

New Issue
Closed
opened 2026-02-21 19:10:56 -05:00 by yindo · 4 comments
yindo commented 2026-02-21 19:10:56 -05:00
Owner
Copy Link
Copy Source

Originally created by @Sergey-Engel on GitHub (Apr 21, 2025).

Originally assigned to: @Nov1c444 on GitHub.

Self Checks

  • 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 (我已阅读并同意 Language Policy).
  • [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:)
  • Please do not modify this template :) and fill in all the required fields.

Dify version

1.2.0

Cloud or Self Hosted

Self Hosted (Source)

Steps to reproduce

In Dify v1.2.0, the workflow engine appears to incorrectly handle dependencies during parallel execution. A node (DIALOG HISTORY VARS) that has a single dependency on a preceding node (DIALOG HISTORY CALC) is being executed in a different parallel branch, after a node (ANSWER) it has no direct dependency on. This violates the explicit dependencies defined in the workflow diagram.

Steps to Reproduce:

Create a workflow with a structure similar to the attached diagram [Link to Workflow Diagram Screenshot]:

  • A starting node (e.g., LLM MAIN).
  • The output of LLM MAIN connects to two nodes, initiating parallel branches:
  • Branch 1 -> ANSWER node.
  • Branch 2 -> DIALOG HISTORY CALC (Code node).
  • The output of DIALOG HISTORY CALC is the only input connected to DIALOG HISTORY VARS (Variable Assignment node).

Run the workflow with some input.

Observe the execution details/logs.

The same problem is seen elsewhere in the script.

✔️ Expected Behavior

Expected Behavior:

Based on the workflow graph dependencies:

  • LLM MAIN completes.
  • ANSWER and DIALOG HISTORY CALC start executing in parallel.
  • DIALOG HISTORY VARS should execute only after DIALOG HISTORY CALC has successfully completed. It should follow DIALOG HISTORY CALC in the logical execution flow, regardless of when ANSWER finishes.

❌ Actual Behavior

Actual Behavior:

  • The execution log [Link to Execution Log Screenshot] shows a different behavior:
    LLM MAIN completes.
  • The engine creates two parallel execution containers (e.g., PARALLEL-1D and PARALLEL-1E).
  • PARALLEL-1D contains only DIALOG HISTORY CALC.
  • PARALLEL-1E contains the ANSWER node, and sequentially after it, the DIALOG HISTORY VARS node.

This means DIALOG HISTORY VARS executes after ANSWER and is placed in a separate parallel branch from its sole dependency, DIALOG HISTORY CALC.

Image
Originally created by @Sergey-Engel on GitHub (Apr 21, 2025). Originally assigned to: @Nov1c444 on GitHub. ### Self Checks - [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 (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)). - [x] [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:) - [x] Please do not modify this template :) and fill in all the required fields. ### Dify version 1.2.0 ### Cloud or Self Hosted Self Hosted (Source) ### Steps to reproduce In Dify v1.2.0, the workflow engine appears to incorrectly handle dependencies during parallel execution. A node (DIALOG HISTORY VARS) that has a single dependency on a preceding node (DIALOG HISTORY CALC) is being executed in a different parallel branch, after a node (ANSWER) it has no direct dependency on. This violates the explicit dependencies defined in the workflow diagram. Steps to Reproduce: Create a workflow with a structure similar to the attached diagram [Link to Workflow Diagram Screenshot]: - A starting node (e.g., LLM MAIN). - The output of LLM MAIN connects to two nodes, initiating parallel branches: - Branch 1 -> ANSWER node. - Branch 2 -> DIALOG HISTORY CALC (Code node). - The output of DIALOG HISTORY CALC is the only input connected to DIALOG HISTORY VARS (Variable Assignment node). Run the workflow with some input. Observe the execution details/logs. The same problem is seen elsewhere in the script. ### ✔️ Expected Behavior Expected Behavior: Based on the workflow graph dependencies: - LLM MAIN completes. - ANSWER and DIALOG HISTORY CALC start executing in parallel. - DIALOG HISTORY VARS should execute only after DIALOG HISTORY CALC has successfully completed. It should follow DIALOG HISTORY CALC in the logical execution flow, regardless of when ANSWER finishes. ### ❌ Actual Behavior Actual Behavior: - The execution log [Link to Execution Log Screenshot] shows a different behavior: LLM MAIN completes. - The engine creates two parallel execution containers (e.g., PARALLEL-1D and PARALLEL-1E). - PARALLEL-1D contains only DIALOG HISTORY CALC. - PARALLEL-1E contains the ANSWER node, and sequentially after it, the DIALOG HISTORY VARS node. This means DIALOG HISTORY VARS executes after ANSWER and is placed in a separate parallel branch from its sole dependency, DIALOG HISTORY CALC. <img width="1058" alt="Image" src="https://github.com/user-attachments/assets/c4a5b9a3-8517-43aa-898d-07a1c526fb4a" />
yindo added the 🌊 feat:workflow label 2026-02-21 19:10:56 -05:00
yindo closed this issue 2026-02-21 19:10:56 -05:00
yindo commented 2026-02-21 19:10:56 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Apr 21, 2025):

Hello @Sergey-Engel! I'm Dosu, your friendly bot here to help you tackle bugs, answer questions, and guide you on your journey to becoming a contributor. I'm here to assist you while you wait for a human maintainer. Let's dive into your issue!

The issue you're experiencing with the Dify workflow engine in version 1.2.0 seems to be related to how the engine handles dependencies in parallel branches. Specifically, the node DIALOG HISTORY VARS is executing in a different parallel branch than its dependency DIALOG HISTORY CALC, which is not the expected behavior.

In Dify, the workflow engine should respect the explicit dependencies defined in the workflow diagram. The expected behavior is that DIALOG HISTORY VARS should execute only after DIALOG HISTORY CALC has completed, regardless of the execution status of the ANSWER node in a separate parallel branch.

This issue might be related to how the workflow engine manages parallel execution and dependencies. The engine uses a thread pool and queue system to handle parallel branches, and it should ensure that nodes execute in the correct order based on their dependencies [1][2]. However, there might be a bug or misconfiguration causing the nodes to be placed incorrectly in parallel execution containers.

To address this, you might want to:

  1. Double-check the workflow configuration to ensure that dependencies are correctly defined.
  2. Review the execution logs to see if there are any errors or warnings that might indicate why the nodes are being placed in the wrong parallel branches.
  3. Consider updating to a newer version of Dify if available, as this might be a known issue that has been resolved in later releases.

If the problem persists, it might require a deeper investigation into the workflow engine's handling of parallel branches and dependencies.

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 (Apr 21, 2025): <!-- Greeting --> Hello @Sergey-Engel! I'm [Dosu](https://dosu.dev), your friendly bot here to help you tackle bugs, answer questions, and guide you on your journey to becoming a contributor. I'm here to assist you while you wait for a human maintainer. Let's dive into your issue! <!-- Answer --> The issue you're experiencing with the Dify workflow engine in version 1.2.0 seems to be related to how the engine handles dependencies in parallel branches. Specifically, the node `DIALOG HISTORY VARS` is executing in a different parallel branch than its dependency `DIALOG HISTORY CALC`, which is not the expected behavior. In Dify, the workflow engine should respect the explicit dependencies defined in the workflow diagram. The expected behavior is that `DIALOG HISTORY VARS` should execute only after `DIALOG HISTORY CALC` has completed, regardless of the execution status of the `ANSWER` node in a separate parallel branch. This issue might be related to how the workflow engine manages parallel execution and dependencies. The engine uses a thread pool and queue system to handle parallel branches, and it should ensure that nodes execute in the correct order based on their dependencies <sup>[[1]](https://github.com/langgenius/dify/blob/main/api/core/workflow/graph_engine/graph_engine.py)</sup><sup>[[2]](https://github.com/langgenius/dify/blob/main/api/tests/unit_tests/core/workflow/graph_engine/test_graph_engine.py)</sup>. However, there might be a bug or misconfiguration causing the nodes to be placed incorrectly in parallel execution containers. To address this, you might want to: 1. Double-check the workflow configuration to ensure that dependencies are correctly defined. 2. Review the execution logs to see if there are any errors or warnings that might indicate why the nodes are being placed in the wrong parallel branches. 3. Consider updating to a newer version of Dify if available, as this might be a known issue that has been resolved in later releases. If the problem persists, it might require a deeper investigation into the workflow engine's handling of parallel branches and dependencies. <!-- 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/0f01e30e-0c17-449f-90b5-dc29a0009807?feedback_type=great_response) | [Irrelevant Answer](https://app.dosu.dev/response-feedback/0f01e30e-0c17-449f-90b5-dc29a0009807?feedback_type=irrelevant_answer) | [Incorrect Sources](https://app.dosu.dev/response-feedback/0f01e30e-0c17-449f-90b5-dc29a0009807?feedback_type=incorrect_sources) | [Too Verbose](https://app.dosu.dev/response-feedback/0f01e30e-0c17-449f-90b5-dc29a0009807?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/0f01e30e-0c17-449f-90b5-dc29a0009807?feedback_type=hallucination) | [Bug Report](https://app.dosu.dev/response-feedback/0f01e30e-0c17-449f-90b5-dc29a0009807?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/0f01e30e-0c17-449f-90b5-dc29a0009807?feedback_type=other)</sup>
yindo commented 2026-02-21 19:10:56 -05:00
Author
Owner
Copy Link
Copy Source

@Sergey-Engel commented on GitHub (Apr 22, 2025):

Thank you for the acknowledgement and the initial analysis.

To provide further information for the human maintainers who will look into this:

Reproducibility: I have confirmed that this exact issue is also reproducible on the Dify Cloud environment running version 1.2.0. This suggests the problem is not specific to my local deployment setup.

Workflow for Reproduction: I have attached a workflow

Image Image Image

that reliably reproduces the incorrect execution order described in this issue.

Execution Comparison: For clarity and to demonstrate the regression, I am also providing examples of the execution sequence:

Correct Execution (v0.15.2): A log/screenshot showing the expected and correct execution order from Dify version 0.15.2, where the DIALOG HISTORY VARS node correctly waits for DIALOG HISTORY CALC.

Incorrect Execution (v1.2.0): The log/screenshot (similar to the one originally provided) showing the incorrect execution order in Dify version 1.2.0, where DIALOG HISTORY VARS runs in the wrong parallel branch after ANSWER.

This comparison strongly suggests a regression or change in the parallel execution logic between version 0.15.2 and 1.2.0 that leads to the incorrect handling of dependencies in this specific scenario.

Hopefully, this additional information, especially the reproducible workflow file and the version comparison, will help the maintainers pinpoint the cause of this bug.

app:
description: ''
icon: 🤖
icon_background: '#FFEAD5'
mode: advanced-chat
name: Test Parallelism
use_icon_as_answer_icon: false
dependencies:

  • current_identifier: null
    type: marketplace
    value:
    marketplace_plugin_unique_identifier: langgenius/openai:0.0.19@6b2b2e115b1b9d34a63eb26fadcc33d74330fd2ec06071bb30b8a24b1fab107a
    kind: app
    version: 0.1.5
    workflow:
    conversation_variables:
    • description: ''
      id: bfbb2e68-fbea-4397-9abc-1c57a14dc2fd
      name: chinese
      selector:
      • conversation
      • chinese
        value: ''
        value_type: string
    • description: ''
      id: fd8569db-06e5-4c03-b57c-9744e034a9b4
      name: arabic
      selector:
      • conversation
      • arabic
        value: ''
        value_type: string
    • description: ''
      id: d62841ab-7a9c-4b43-b2d1-119ae31f160c
      name: english
      selector:

      • conversation

      • english
        value: ''
        value_type: string
        environment_variables: []
        features:
        file_upload:
        allowed_file_extensions:

        • .JPG
        • .JPEG
        • .PNG
        • .GIF
        • .WEBP
        • .SVG
          allowed_file_types:
        • image
          allowed_file_upload_methods:
        • local_file
        • remote_url
          enabled: false
          fileUploadConfig:
          audio_file_size_limit: 50
          batch_count_limit: 5
          file_size_limit: 15
          image_file_size_limit: 10
          video_file_size_limit: 100
          workflow_file_upload_limit: 10
          image:
          enabled: false
          number_limits: 3
          transfer_methods:
          • local_file
          • remote_url
            number_limits: 3
            opening_statement: ''
            retriever_resource:
            enabled: true
            sensitive_word_avoidance:
            enabled: false
            speech_to_text:
            enabled: false
            suggested_questions: []
            suggested_questions_after_answer:
            enabled: false
            text_to_speech:
            enabled: false
            language: ''
            voice: ''
            graph:
            edges:

      • data:
        sourceType: start
        targetType: llm
        id: 1745310425592-llm
        source: '1745310425592'
        sourceHandle: source
        target: llm
        targetHandle: target
        type: custom

      • data:
        isInLoop: false
        sourceType: start
        targetType: llm
        id: 1745310425592-source-17453106168860-target
        source: '1745310425592'
        sourceHandle: source
        target: '17453106168860'
        targetHandle: target
        type: custom
        zIndex: 0

      • data:
        isInLoop: false
        sourceType: start
        targetType: llm
        id: 1745310425592-source-17453106944400-target
        source: '1745310425592'
        sourceHandle: source
        target: '17453106944400'
        targetHandle: target
        type: custom
        zIndex: 0

      • data:
        isInIteration: false
        isInLoop: false
        sourceType: llm
        targetType: assigner
        id: llm-source-1745310888263-target
        source: llm
        sourceHandle: source
        target: '1745310888263'
        targetHandle: target
        type: custom
        zIndex: 0

      • data:
        isInIteration: false
        isInLoop: false
        sourceType: assigner
        targetType: answer
        id: 1745310888263-source-answer-target
        source: '1745310888263'
        sourceHandle: source
        target: answer
        targetHandle: target
        type: custom
        zIndex: 0

      • data:
        isInIteration: false
        isInLoop: false
        sourceType: llm
        targetType: assigner
        id: 17453106168860-source-1745310922846-target
        source: '17453106168860'
        sourceHandle: source
        target: '1745310922846'
        targetHandle: target
        type: custom
        zIndex: 0

      • data:
        isInIteration: false
        isInLoop: false
        sourceType: assigner
        targetType: answer
        id: 1745310922846-source-answer-target
        source: '1745310922846'
        sourceHandle: source
        target: answer
        targetHandle: target
        type: custom
        zIndex: 0

      • data:
        isInIteration: false
        isInLoop: false
        sourceType: llm
        targetType: assigner
        id: 17453106944400-source-1745310951095-target
        source: '17453106944400'
        sourceHandle: source
        target: '1745310951095'
        targetHandle: target
        type: custom
        zIndex: 0

      • data:
        isInIteration: false
        isInLoop: false
        sourceType: assigner
        targetType: answer
        id: 1745310951095-source-answer-target
        source: '1745310951095'
        sourceHandle: source
        target: answer
        targetHandle: target
        type: custom
        zIndex: 0
        nodes:

      • data:
        desc: ''
        selected: false
        title: Start
        type: start
        variables: []
        height: 54
        id: '1745310425592'
        position:
        x: 56.960000000000036
        y: 399.5
        positionAbsolute:
        x: 56.960000000000036
        y: 399.5
        selected: false
        sourcePosition: right
        targetPosition: left
        type: custom
        width: 244

      • data:
        context:
        enabled: false
        variable_selector: []
        desc: ''
        model:
        completion_params:
        temperature: 1
        mode: chat
        name: gpt-4.1-nano
        provider: langgenius/openai/openai
        prompt_template:

        • id: a49f3d5e-fd60-4af0-95bb-09dc3abb8235
          role: system
          text: Translate to English
        • id: 0a877697-3ecb-4fc9-8529-a5b48616860a
          role: user
          text: '{{#sys.query#}}'
          selected: false
          title: LLM ENG
          type: llm
          variables: []
          vision:
          enabled: false
          height: 90
          id: llm
          position:
          x: 380
          y: 282
          positionAbsolute:
          x: 380
          y: 282
          selected: false
          sourcePosition: right
          targetPosition: left
          type: custom
          width: 244

      • data:
        answer: '{{#sys.query#}}:

        {{#conversation.english#}}

{{#conversation.chinese#}}

{{#conversation.arabic#}}

'

        desc: ''
        selected: false
        title: Answer
        type: answer
        variables: []
        height: 142
        id: answer
        position:
        x: 1339.24
        y: 399.5
        positionAbsolute:
        x: 1339.24
        y: 399.5
        selected: true
        sourcePosition: right
        targetPosition: left
        type: custom
        width: 244

      • data:
        context:
        enabled: false
        variable_selector: []
        desc: ''
        model:
        completion_params:
        temperature: 1
        mode: chat
        name: gpt-4.1-nano
        provider: langgenius/openai/openai
        prompt_template:

        • id: a49f3d5e-fd60-4af0-95bb-09dc3abb8235
          role: system
          text: Translate to Chinese
        • id: 0a877697-3ecb-4fc9-8529-a5b48616860a
          role: user
          text: '{{#sys.query#}}'
          selected: false
          title: LLM CHI
          type: llm
          variables: []
          vision:
          enabled: false
          height: 90
          id: '17453106168860'
          position:
          x: 380
          y: 399.5
          positionAbsolute:
          x: 380
          y: 399.5
          selected: false
          sourcePosition: right
          targetPosition: left
          type: custom
          width: 244

      • data:
        context:
        enabled: false
        variable_selector: []
        desc: ''
        model:
        completion_params:
        temperature: 1
        mode: chat
        name: gpt-4.1-nano
        provider: langgenius/openai/openai
        prompt_template:

        • id: a49f3d5e-fd60-4af0-95bb-09dc3abb8235
          role: system
          text: Translate to Arabic
        • id: 0a877697-3ecb-4fc9-8529-a5b48616860a
          role: user
          text: '{{#sys.query#}}'
          selected: false
          title: LLM ARB
          type: llm
          variables: []
          vision:
          enabled: false
          height: 90
          id: '17453106944400'
          position:
          x: 380
          y: 523.5
          positionAbsolute:
          x: 380
          y: 523.5
          selected: false
          sourcePosition: right
          targetPosition: left
          type: custom
          width: 244

      • data:
        desc: ''
        items:

        • input_type: variable
          operation: over-write
          value:
          • llm
          • text
            variable_selector:
          • conversation
          • english
            write_mode: over-write
            selected: false
            title: Variable Assigner
            type: assigner
            version: '2'
            height: 88
            id: '1745310888263'
            position:
            x: 740
            y: 282
            positionAbsolute:
            x: 740
            y: 282
            selected: false
            sourcePosition: right
            targetPosition: left
            type: custom
            width: 244

      • data:
        desc: ''
        items:

        • input_type: variable
          operation: over-write
          value:
          • '17453106168860'
          • text
            variable_selector:
          • conversation
          • chinese
            write_mode: over-write
            selected: false
            title: Variable Assigner 2
            type: assigner
            version: '2'
            height: 88
            id: '1745310922846'
            position:
            x: 740
            y: 399.5
            positionAbsolute:
            x: 740
            y: 399.5
            selected: false
            sourcePosition: right
            targetPosition: left
            type: custom
            width: 244

      • data:
        desc: ''
        items:

        • input_type: variable
          operation: over-write
          value:
          • '17453106944400'
          • text
            variable_selector:
          • conversation
          • arabic
            write_mode: over-write
            selected: false
            title: Variable Assigner 3
            type: assigner
            version: '2'
            height: 88
            id: '1745310951095'
            position:
            x: 740
            y: 523.5
            positionAbsolute:
            x: 740
            y: 523.5
            selected: false
            sourcePosition: right
            targetPosition: left
            type: custom
            width: 244
            viewport:
            x: 170.08333333333326
            y: 284.66666666666663
            zoom: 0.6944444444444445
@Sergey-Engel commented on GitHub (Apr 22, 2025): Thank you for the acknowledgement and the initial analysis. To provide further information for the human maintainers who will look into this: Reproducibility: I have confirmed that this exact issue is also reproducible on the Dify Cloud environment running version 1.2.0. This suggests the problem is not specific to my local deployment setup. Workflow for Reproduction: I have attached a workflow <img width="1092" alt="Image" src="https://github.com/user-attachments/assets/6cb3dbb9-74e4-4e94-8301-1af4ce0948a1" /> <img width="393" alt="Image" src="https://github.com/user-attachments/assets/ee5983e8-f52f-4d07-a95b-12832eba0eb0" /> <img width="398" alt="Image" src="https://github.com/user-attachments/assets/be0bb802-4af0-42cf-9147-7f7b7844822c" /> that reliably reproduces the incorrect execution order described in this issue. Execution Comparison: For clarity and to demonstrate the regression, I am also providing examples of the execution sequence: Correct Execution (v0.15.2): A log/screenshot showing the expected and correct execution order from Dify version 0.15.2, where the DIALOG HISTORY VARS node correctly waits for DIALOG HISTORY CALC. Incorrect Execution (v1.2.0): The log/screenshot (similar to the one originally provided) showing the incorrect execution order in Dify version 1.2.0, where DIALOG HISTORY VARS runs in the wrong parallel branch after ANSWER. This comparison strongly suggests a regression or change in the parallel execution logic between version 0.15.2 and 1.2.0 that leads to the incorrect handling of dependencies in this specific scenario. Hopefully, this additional information, especially the reproducible workflow file and the version comparison, will help the maintainers pinpoint the cause of this bug. app: description: '' icon: 🤖 icon_background: '#FFEAD5' mode: advanced-chat name: Test Parallelism use_icon_as_answer_icon: false dependencies: - current_identifier: null type: marketplace value: marketplace_plugin_unique_identifier: langgenius/openai:0.0.19@6b2b2e115b1b9d34a63eb26fadcc33d74330fd2ec06071bb30b8a24b1fab107a kind: app version: 0.1.5 workflow: conversation_variables: - description: '' id: bfbb2e68-fbea-4397-9abc-1c57a14dc2fd name: chinese selector: - conversation - chinese value: '' value_type: string - description: '' id: fd8569db-06e5-4c03-b57c-9744e034a9b4 name: arabic selector: - conversation - arabic value: '' value_type: string - description: '' id: d62841ab-7a9c-4b43-b2d1-119ae31f160c name: english selector: - conversation - english value: '' value_type: string environment_variables: [] features: file_upload: allowed_file_extensions: - .JPG - .JPEG - .PNG - .GIF - .WEBP - .SVG allowed_file_types: - image allowed_file_upload_methods: - local_file - remote_url enabled: false fileUploadConfig: audio_file_size_limit: 50 batch_count_limit: 5 file_size_limit: 15 image_file_size_limit: 10 video_file_size_limit: 100 workflow_file_upload_limit: 10 image: enabled: false number_limits: 3 transfer_methods: - local_file - remote_url number_limits: 3 opening_statement: '' retriever_resource: enabled: true sensitive_word_avoidance: enabled: false speech_to_text: enabled: false suggested_questions: [] suggested_questions_after_answer: enabled: false text_to_speech: enabled: false language: '' voice: '' graph: edges: - data: sourceType: start targetType: llm id: 1745310425592-llm source: '1745310425592' sourceHandle: source target: llm targetHandle: target type: custom - data: isInLoop: false sourceType: start targetType: llm id: 1745310425592-source-17453106168860-target source: '1745310425592' sourceHandle: source target: '17453106168860' targetHandle: target type: custom zIndex: 0 - data: isInLoop: false sourceType: start targetType: llm id: 1745310425592-source-17453106944400-target source: '1745310425592' sourceHandle: source target: '17453106944400' targetHandle: target type: custom zIndex: 0 - data: isInIteration: false isInLoop: false sourceType: llm targetType: assigner id: llm-source-1745310888263-target source: llm sourceHandle: source target: '1745310888263' targetHandle: target type: custom zIndex: 0 - data: isInIteration: false isInLoop: false sourceType: assigner targetType: answer id: 1745310888263-source-answer-target source: '1745310888263' sourceHandle: source target: answer targetHandle: target type: custom zIndex: 0 - data: isInIteration: false isInLoop: false sourceType: llm targetType: assigner id: 17453106168860-source-1745310922846-target source: '17453106168860' sourceHandle: source target: '1745310922846' targetHandle: target type: custom zIndex: 0 - data: isInIteration: false isInLoop: false sourceType: assigner targetType: answer id: 1745310922846-source-answer-target source: '1745310922846' sourceHandle: source target: answer targetHandle: target type: custom zIndex: 0 - data: isInIteration: false isInLoop: false sourceType: llm targetType: assigner id: 17453106944400-source-1745310951095-target source: '17453106944400' sourceHandle: source target: '1745310951095' targetHandle: target type: custom zIndex: 0 - data: isInIteration: false isInLoop: false sourceType: assigner targetType: answer id: 1745310951095-source-answer-target source: '1745310951095' sourceHandle: source target: answer targetHandle: target type: custom zIndex: 0 nodes: - data: desc: '' selected: false title: Start type: start variables: [] height: 54 id: '1745310425592' position: x: 56.960000000000036 y: 399.5 positionAbsolute: x: 56.960000000000036 y: 399.5 selected: false sourcePosition: right targetPosition: left type: custom width: 244 - data: context: enabled: false variable_selector: [] desc: '' model: completion_params: temperature: 1 mode: chat name: gpt-4.1-nano provider: langgenius/openai/openai prompt_template: - id: a49f3d5e-fd60-4af0-95bb-09dc3abb8235 role: system text: Translate to English - id: 0a877697-3ecb-4fc9-8529-a5b48616860a role: user text: '{{#sys.query#}}' selected: false title: LLM ENG type: llm variables: [] vision: enabled: false height: 90 id: llm position: x: 380 y: 282 positionAbsolute: x: 380 y: 282 selected: false sourcePosition: right targetPosition: left type: custom width: 244 - data: answer: '{{#sys.query#}}: {{#conversation.english#}} {{#conversation.chinese#}} {{#conversation.arabic#}} ' desc: '' selected: false title: Answer type: answer variables: [] height: 142 id: answer position: x: 1339.24 y: 399.5 positionAbsolute: x: 1339.24 y: 399.5 selected: true sourcePosition: right targetPosition: left type: custom width: 244 - data: context: enabled: false variable_selector: [] desc: '' model: completion_params: temperature: 1 mode: chat name: gpt-4.1-nano provider: langgenius/openai/openai prompt_template: - id: a49f3d5e-fd60-4af0-95bb-09dc3abb8235 role: system text: Translate to Chinese - id: 0a877697-3ecb-4fc9-8529-a5b48616860a role: user text: '{{#sys.query#}}' selected: false title: LLM CHI type: llm variables: [] vision: enabled: false height: 90 id: '17453106168860' position: x: 380 y: 399.5 positionAbsolute: x: 380 y: 399.5 selected: false sourcePosition: right targetPosition: left type: custom width: 244 - data: context: enabled: false variable_selector: [] desc: '' model: completion_params: temperature: 1 mode: chat name: gpt-4.1-nano provider: langgenius/openai/openai prompt_template: - id: a49f3d5e-fd60-4af0-95bb-09dc3abb8235 role: system text: Translate to Arabic - id: 0a877697-3ecb-4fc9-8529-a5b48616860a role: user text: '{{#sys.query#}}' selected: false title: LLM ARB type: llm variables: [] vision: enabled: false height: 90 id: '17453106944400' position: x: 380 y: 523.5 positionAbsolute: x: 380 y: 523.5 selected: false sourcePosition: right targetPosition: left type: custom width: 244 - data: desc: '' items: - input_type: variable operation: over-write value: - llm - text variable_selector: - conversation - english write_mode: over-write selected: false title: Variable Assigner type: assigner version: '2' height: 88 id: '1745310888263' position: x: 740 y: 282 positionAbsolute: x: 740 y: 282 selected: false sourcePosition: right targetPosition: left type: custom width: 244 - data: desc: '' items: - input_type: variable operation: over-write value: - '17453106168860' - text variable_selector: - conversation - chinese write_mode: over-write selected: false title: Variable Assigner 2 type: assigner version: '2' height: 88 id: '1745310922846' position: x: 740 y: 399.5 positionAbsolute: x: 740 y: 399.5 selected: false sourcePosition: right targetPosition: left type: custom width: 244 - data: desc: '' items: - input_type: variable operation: over-write value: - '17453106944400' - text variable_selector: - conversation - arabic write_mode: over-write selected: false title: Variable Assigner 3 type: assigner version: '2' height: 88 id: '1745310951095' position: x: 740 y: 523.5 positionAbsolute: x: 740 y: 523.5 selected: false sourcePosition: right targetPosition: left type: custom width: 244 viewport: x: 170.08333333333326 y: 284.66666666666663 zoom: 0.6944444444444445
yindo commented 2026-02-21 19:10:56 -05:00
Author
Owner
Copy Link
Copy Source

@Nov1c444 commented on GitHub (May 12, 2025):

The execution appears to be correct on cloud 1.3.0. Is this result in line with your expectations?
Image

@Nov1c444 commented on GitHub (May 12, 2025): The execution appears to be correct on cloud 1.3.0. Is this result in line with your expectations? <img width="842" alt="Image" src="https://github.com/user-attachments/assets/f449a888-0427-40e7-80dd-9a2e75c2b390" />
yindo commented 2026-02-21 19:10:57 -05:00
Author
Owner
Copy Link
Copy Source

@Sergey-Engel commented on GitHub (May 13, 2025):

Yes, now it works correct. Thank you.

@Sergey-Engel commented on GitHub (May 13, 2025): Yes, now it works correct. Thank you.
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
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#13182
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?