fix: enhance agent node convert_template by recursive render all str fields

[hoffermei]

fixes #30527

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

When agent node tool reference a variable which is a multiple line string, run agent node with 'str' object has no attribute 'get', this pr fix the variable render problem by scan and render str value only

Screenshots

Before	After

|

|

|

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 @hoffermei, 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 significantly enhances the template rendering capabilities within the workflow's variable pool. By introducing a recursive rendering mechanism, it allows for seamless variable substitution across complex and nested data structures, including Pydantic models. This change streamlines how agent nodes process their inputs, making the system more flexible and robust in handling diverse data types that contain template strings.

Highlights

• Recursive Template Rendering: Introduced a new render_template method in VariablePool that recursively processes templates within various data structures, including lists, tuples, dictionaries, sets, and Pydantic BaseModels. This ensures all string fields within these structures are properly rendered.
• Agent Node Input Handling Improvement: The _generate_agent_parameters function in AgentNode now utilizes the new render_template method, simplifying the logic for handling 'mixed' and 'constant' agent inputs and making template substitution more consistent across complex data types. Error logging has been added for TypeError during rendering.
• Comprehensive Unit Tests: Extensive unit tests have been added for the render_template method, covering a wide range of scenarios including primitive types, nested collections, Pydantic models, and edge cases like None values and unsupported types, ensuring robustness and correctness.

🧠 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 introduces a significant enhancement to template rendering by adding a render_template method to the VariablePool. This new method recursively processes nested data structures like lists, dictionaries, and Pydantic models, rendering any string template variables it finds. This is a much cleaner approach than the previous method of JSON-stringifying objects before rendering.

The changes in agent_node.py correctly adopt this new method within a try...except block, ensuring a safe fallback to the old logic, which is a good practice for this kind of refactoring. The accompanying unit tests for render_template are comprehensive and cover a wide range of scenarios, which is excellent.

My review includes a couple of suggestions for improvement: one regarding adding type hints for better code clarity and another to strengthen a test assertion to make the behavior of a related function more explicit.