fix: In parallel mode, the assignment of session variables by the iteration node through the assignment node may fail.

[Chenyl-Sai]

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>.

Fixes #29989

Summary

As is known, when there is an assigner node inside an iteration node and the iteration runs in parallel, the final value produced by the assigner is nondeterministic. It will be overwritten by the loop that finishes last.

However, if the assigner is executed only once, the final value should be deterministic.

Currently, before each loop execution, the parent variable pool is copied into the loop context. After the loop finishes, all values from the loop are written back to the parent variable pool, even if the loop did not perform any assignment operations.

This PR tracks the keys that are actually updated within each loop and replaces only those values in the parent variable pool that were truly modified.

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 dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods

[gemini-code-assist]

Summary of Changes

Hello @Chenyl-Sai, 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 addresses a critical bug in the parallel execution of iteration nodes, specifically concerning the assignment of session variables. The previous implementation could lead to race conditions and non-deterministic outcomes when an assigner node was present within a parallel loop, as the entire variable pool was merged back, potentially overwriting values from other parallel branches. The fix ensures that only the variables explicitly modified within an iteration are merged back, guaranteeing correct and predictable state management in parallel workflows.

Highlights

• Deterministic Variable Assignment: This pull request resolves an issue where session variable assignments within parallel iteration nodes could become non-deterministic. Previously, the entire parent variable pool was copied back after each loop, leading to potential overwrites by the last finishing iteration.
• Selective Variable Merging: The core change introduces a mechanism to track only the specific conversation variables that are actually modified within each parallel loop iteration. Instead of merging the entire snapshot, only these 'touched' variables are merged back into the parent variable pool, ensuring that unrelated variables are not inadvertently overwritten.
• New Helper Function: A new helper function, get_updated_variables, is imported and utilized to identify which variables have been updated during a node's execution, specifically focusing on conversation variables within the iteration context.

🧠 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. ↩

[gemini-code-assist]

Code Review

This pull request effectively addresses a race condition in parallel iterations where session variables could be overwritten incorrectly. The approach of tracking touched variables within each iteration and only merging those back to the parent variable pool is sound and should resolve the non-deterministic behavior. The implementation is clear and follows the described logic. I have one suggestion regarding code duplication to improve long-term maintainability.