Skip to content

fix: fix assign value stand as default#30651

Merged
crazywoola merged 3 commits intolanggenius:mainfrom
fatelei:issue-30650
Jan 7, 2026
Merged

fix: fix assign value stand as default#30651
crazywoola merged 3 commits intolanggenius:mainfrom
fatelei:issue-30650

Conversation

@fatelei
Copy link
Contributor

@fatelei fatelei commented Jan 6, 2026

Important

  1. Make sure you have read our contribution guidelines
  2. Ensure there is an associated issue and you have been assigned to it
  3. Use the correct syntax to link this PR: Fixes #<issue number>.

Summary

fix #30650

  1. Workflow starts executing
  2. ResponseStreamCoordinator initializes
    - Register Answer node template: "{{#conversation.conv_var#}}"
    - Parse template into segments: [TextSegment, VariableSegment]
  3. Attempt to send streaming output (try_flush)
    - Iterate through template segments
    - Encounter VariableSegment: conversation.conv_var
    - Read current value from variable_pool → "default" (not yet updated at this point)
    - Send NodeRunStreamChunkEvent("default")
  4. Event flow
    - NodeRunStreamChunkEvent → QueueTextChunkEvent
    - Frontend receives TextChunkStreamResponse → message event
  5. Workflow continues execution
    - Variable Assigner node executes, updates conversation.conv_var = "123"
    - Answer node finishes execution, outputs "123"
  6. Problem
    - Frontend has already displayed "default"
    - Need to send message_replace event to update

Screenshots

Before After
... ...

before

Screen.Recording.2026-01-06.at.21.53.16.mov

after

Screen.Recording.2026-01-06.at.21.51.21.mov

Checklist

  • This change requires a documentation update, included: Dify Document
  • I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
  • I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
  • I've updated the documentation accordingly.
  • I ran make lint and make type-check (backend) and cd web && npx lint-staged (frontend) to appease the lint gods
@fatelei fatelei requested a review from QuantumGhost as a code owner January 6, 2026 13:12
@dosubot dosubot bot added the size:S This PR changes 10-29 lines, ignoring generated files. label Jan 6, 2026
@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @fatelei, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request resolves an issue in the advanced chat workflow where the 'Answer' node could display an incorrect initial value if its underlying variables were updated later in the execution pipeline. The changes introduce logic to detect such discrepancies and send a 'message_replace' event to the frontend, ensuring that the final, correct answer is always presented to the user, thereby improving the accuracy of streamed responses.

Highlights

  • Problem Identification: The pull request addresses a bug where the 'Answer' node in a workflow might initially stream a default or outdated value to the frontend.
  • Root Cause: This issue occurs because variables used in the 'Answer' node's template might be updated later in the workflow by a 'Variable Assigner' node, after the initial stream has already begun.
  • Solution Implementation: A new mechanism is introduced to detect when the final output of an 'Answer' node differs from the value already streamed.
  • Frontend Update: If a discrepancy is found, a 'message_replace' event is sent to the frontend, ensuring the user interface displays the correct, updated value.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request introduces a fix for an issue where the UI displays a default variable value that is later updated by a variable_assigner node. The proposed solution correctly identifies when the final output of an ANSWER node differs from the initially streamed content and sends a message_replace event to update the UI. The implementation is clean and directly addresses the problem. I have one suggestion to improve maintainability regarding the reason for the message replacement.

@dosubot dosubot bot added size:L This PR changes 100-499 lines, ignoring generated files. and removed size:S This PR changes 10-29 lines, ignoring generated files. labels Jan 7, 2026
QuantumGhost
QuantumGhost previously approved these changes Jan 7, 2026
@dosubot dosubot bot added the lgtm This PR has been approved by a maintainer label Jan 7, 2026
@crazywoola crazywoola merged commit 187bfaf into langgenius:main Jan 7, 2026
11 checks passed
@fatelei fatelei deleted the issue-30650 branch January 7, 2026 07:45
QuantumGhost added a commit that referenced this pull request Jan 8, 2026
QuantumGhost added a commit that referenced this pull request Jan 9, 2026
The original fix seems correct on its own. However, for chatflows with multiple answer nodes, the `message_replace` command only preserves the output of the last executed answer node.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

lgtm This PR has been approved by a maintainer size:L This PR changes 100-499 lines, ignoring generated files.

3 participants