bugfix: Write JSON formatted string #3994

ftnext · 2025-12-21T15:07:17Z

Please ensure you have read the contribution guide before creating a pull request.

Link to Issue or Description of Change

1. Link to an existing issue (if applicable):

Closes: LocalEvalSetResultsManager writes double-encoded JSON files #3993
Related: #issue_number

2. Or, if no issue exists, describe the change:

If applicable, please follow the issue templates to provide as much detail as
possible.

Problem:
A clear and concise description of what the problem is.

Solution:
A clear and concise description of what you want to happen and why you choose
this solution.

Testing Plan

Please describe the tests that you ran to verify your changes. This is required
for all PRs that are not small documentation or typo fixes.

Unit Tests:

I have added or updated unit tests for my change.
All unit tests pass locally.

Please include a summary of passed pytest results.

Manual End-to-End (E2E) Tests:

Please provide instructions on how to manually test your changes, including any
necessary setup or configuration. Please provide logs or screenshots to help
reviewers better understand the fix.

Checklist

I have read the CONTRIBUTING.md document.
I have performed a self-review of my own code.
I have commented my code, particularly in hard-to-understand areas.
I have added tests that prove my fix is effective or that my feature works.
New and existing unit tests pass locally with my changes.
I have manually tested my changes end-to-end.
Any dependent changes have been merged and published in downstream modules.

Additional context

EvalStatus Enum is serialized to int
https://docs.pydantic.dev/latest/api/base_model/#pydantic.BaseModel.model_dump

If mode is 'json', the output will only contain JSON serializable types.

Fix google#3993

gemini-code-assist · 2025-12-21T15:07:27Z

Summary of Changes

Hello @ftnext, 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 a bug related to writing evaluation results to a file. Previously, data that was already a JSON formatted string was being passed through json.dumps() again, which could lead to incorrect output. The change ensures that the pre-formatted JSON string is written directly to the file, streamlining the process and preventing potential serialization errors.

Highlights

Bug Fix: Corrected an issue where JSON formatted strings were being double-encoded when written to a file, ensuring proper data serialization.
Code Simplification: Removed a redundant call to json.dumps() in the save_eval_set_result function, as the data was already in a JSON string format.

🧠 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.

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. ↩

adk-bot · 2025-12-21T15:08:11Z

Response from ADK Triaging Agent

Hello @ftnext, thank you for creating this PR!

Could you please provide a testing plan for your changes? This should include details on the unit tests you've added or updated, as well as instructions for manual end-to-end testing.

This information will help reviewers to review your PR more efficiently. Thanks!

gemini-code-assist

Code Review

This pull request aims to fix a bug where a JSON string was being double-encoded before being written to a file. The change correctly removes the double encoding. However, this is an incomplete fix that introduces breaking changes in other parts of the codebase that read this file, such as get_eval_set_result and related unit tests. My review includes a critical comment explaining the issue and outlining the necessary changes to make this a complete and safe fix.

gemini-code-assist · 2025-12-21T15:08:46Z

src/google/adk/evaluation/local_eval_set_results_manager.py

    logger.info("Writing eval result to file: %s", eval_set_result_file_path)
    with open(eval_set_result_file_path, "w", encoding="utf-8") as f:
-      f.write(json.dumps(eval_set_result_json, indent=2))
+      f.write(eval_set_result_json)


This change correctly fixes the double JSON encoding. However, this is an incomplete fix that breaks other parts of the code that consume this file.

Breaks get_eval_set_result: This method will now fail with a TypeError. It uses json.load() which now returns a dict, but then passes it to EvalSetResult.model_validate_json(), which expects a string.

Breaks Unit Tests: The test test_save_eval_set_result will fail as it now incorrectly compares a string with a dictionary.

To complete this fix, get_eval_set_result and its tests must be updated. For example, get_eval_set_result should use EvalSetResult.model_validate(json.load(file)).

Additionally, this change removes the indent=2 pretty-printing. To restore this for readability, the recommended approach is to modify line 57 to eval_set_result.model_dump_json(indent=2), which is outside the current diff.

Updated JSON serialization method for eval set results. EvalStatus Enum is serialized to int https://docs.pydantic.dev/latest/api/base_model/#pydantic.BaseModel.model_dump >If mode is 'json', the output will only contain JSON serializable types.

ryanaiagent · 2025-12-23T23:27:34Z

/gemini review

gemini-code-assist

Code Review

This pull request correctly fixes a bug related to JSON serialization and deserialization of Pydantic models. The changes address an issue where JSON data was being double-encoded upon saving and an incorrect validation method was used upon loading. The switch to model_dump(mode="json") and model_validate() is appropriate and resolves the problem. My review includes a couple of suggestions to improve variable naming for better code clarity and maintainability.

gemini-code-assist · 2025-12-23T23:28:56Z

src/google/adk/evaluation/local_eval_set_results_manager.py

      os.makedirs(app_eval_history_dir)
    # Convert to json and write to file.
-    eval_set_result_json = eval_set_result.model_dump_json()
+    eval_set_result_json = eval_set_result.model_dump(mode="json")


While this change correctly fixes the serialization bug, the variable eval_set_result_json now holds a Python dictionary rather than a JSON string, making the name misleading. For improved code clarity, I recommend renaming it to something like eval_set_result_data or eval_set_result_dict. Note that this would also require updating the variable name on line 64.

gemini-code-assist · 2025-12-23T23:28:56Z

tests/unittests/evaluation/test_local_eval_set_results_manager.py


    # need to convert eval_set_result to json
-    expected_eval_set_result_json = self.eval_set_result.model_dump_json()
+    expected_eval_set_result_json = self.eval_set_result.model_dump(mode="json")


This change correctly aligns the test with the fix in the application code. However, similar to the main code, the variable expected_eval_set_result_json now contains a dictionary. To improve readability and consistency, consider renaming it to expected_eval_set_result_data. This naming suggestion also applies to actual_eval_set_result_json on line 88.

ryanaiagent · 2025-12-23T23:30:54Z

Hi @ftnext ,Thank you for your contribution! We appreciate you taking the time to submit this pull request. Your PR has been received by the team and is currently under review. We will provide feedback as soon as we have an update to share.

ryanaiagent · 2025-12-23T23:31:17Z

Hi @wyf7107 , can you please review this.

bugfix: Write JSON formatted string

bb7e82a

Fix google#3993

adk-bot added the eval [Component] This issue is related to evaluation label Dec 21, 2025

gemini-code-assist bot reviewed Dec 21, 2025

View reviewed changes

ftnext added 2 commits December 22, 2025 00:31

test: Use model_dump(mode="json")

3e83554

bugfix: Use model_dump(mode="json")

7575627

Updated JSON serialization method for eval set results. EvalStatus Enum is serialized to int https://docs.pydantic.dev/latest/api/base_model/#pydantic.BaseModel.model_dump >If mode is 'json', the output will only contain JSON serializable types.

ftnext marked this pull request as ready for review December 21, 2025 15:35

Fix get_eval_set_result

f2b9bdd

rahuldevikar approved these changes Dec 22, 2025

View reviewed changes

Merge branch 'main' into fix-double-encoded-json

acb35ba

ryanaiagent self-assigned this Dec 22, 2025

ryanaiagent added the request clarification [Status] The maintainer need clarification or more information from the author label Dec 23, 2025

ryanaiagent removed the request clarification [Status] The maintainer need clarification or more information from the author label Dec 23, 2025

gemini-code-assist bot reviewed Dec 23, 2025

View reviewed changes

ryanaiagent added the needs-review [Status] The PR is awaiting review from the maintainer label Dec 23, 2025

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

bugfix: Write JSON formatted string #3994

bugfix: Write JSON formatted string #3994

ftnext commented Dec 21, 2025 •

edited

Loading

Uh oh!

gemini-code-assist bot commented Dec 21, 2025

Uh oh!

adk-bot commented Dec 21, 2025

Uh oh!

gemini-code-assist bot left a comment

Uh oh!

gemini-code-assist bot Dec 21, 2025

Uh oh!

ryanaiagent commented Dec 23, 2025

Uh oh!

gemini-code-assist bot left a comment

Uh oh!

gemini-code-assist bot Dec 23, 2025

Uh oh!

gemini-code-assist bot Dec 23, 2025

Uh oh!

ryanaiagent commented Dec 23, 2025

Uh oh!

ryanaiagent commented Dec 23, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

bugfix: Write JSON formatted string #3994

Are you sure you want to change the base?

bugfix: Write JSON formatted string #3994

Conversation

ftnext commented Dec 21, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Link to Issue or Description of Change

Testing Plan

Checklist

Additional context

Uh oh!

gemini-code-assist bot commented Dec 21, 2025

Summary of Changes

Highlights

Footnotes

Uh oh!

adk-bot commented Dec 21, 2025

Uh oh!

gemini-code-assist bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

gemini-code-assist bot Dec 21, 2025

Choose a reason for hiding this comment

Uh oh!

ryanaiagent commented Dec 23, 2025

Uh oh!

gemini-code-assist bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

gemini-code-assist bot Dec 23, 2025

Choose a reason for hiding this comment

Uh oh!

gemini-code-assist bot Dec 23, 2025

Choose a reason for hiding this comment

Uh oh!

ryanaiagent commented Dec 23, 2025

Uh oh!

ryanaiagent commented Dec 23, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

ftnext commented Dec 21, 2025 •

edited

Loading