fix(core): strip thoughts from scrubbed history turns and resolve thought leakage

[amelidev]

Summary

This PR resolves a Thought Leakage issue where the Gemini model's internal monologues/reasoning thoughts leak into plain-text history turns, confusing the model in subsequent turns and causing it to emulate scratchpad thoughts or enter infinite loop monologues.

Details

• Surgical Thought Stripping: Updated scrubContents inside packages/core/src/utils/historyHardening.ts to actively filter out any parts where part.thought is truthy, before map-scrubbing the remaining fields. This ensures nested executions (e.g. subagents) do not leak raw thoughts as plain conversational text.
• Alternation Preservation: Updated scrubHistory to run coalesce on the scrubbed turns. This safely discards any turns made empty by thought stripping while maintaining the Gemini API's strict role-alternation invariant.
• Robust Thought Detection: Unified the thought checks in stripThoughts to check for truthy p.thought properties rather than strictly p.thought === true, matching how thoughts are represented.
• Comprehensive Unit Testing: Created a new robust unit test suite (thought leakage in getHistoryTurns) in packages/core/src/core/geminiChat.test.ts to reproduce and confirm the fix.

Related Issues

Resolves the issue documented in issue.md.

How to Validate

Run the targeted and whole history hardening test suites using Vitest:

npx vitest run packages/core/src/core/geminiChat.test.ts -t "thought leakage in getHistoryTurns"
npx vitest run packages/core/src/utils/historyHardening.test.ts

All tests pass perfectly in under 15 seconds.

Pre-Merge Checklist

• Updated relevant documentation and README (if needed)
• Added/updated tests (if needed)
• Noted breaking changes (if any)
• Validated on required platforms/methods:
  • Linux (npm run)

[gemini-code-assist]

Summary of Changes

Hello, 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 issue where the Gemini model's internal reasoning thoughts were leaking into the plain-text conversation history. By introducing a preprocessing step to strip these thoughts and subsequently coalescing the remaining turns, the changes ensure that the model history remains clean and compliant with API requirements, preventing the model from confusing its own scratchpad with user-facing dialogue.

Highlights

• Thought Leakage Prevention: Implemented a surgical stripping mechanism in scrubContents to filter out internal model thoughts, preventing them from leaking into conversational history.
• History Hardening Improvements: Updated hardenHistory and scrubHistory to coalesce turns after thought removal, ensuring strict role-alternation invariants are maintained.
• Robust Thought Detection: Unified logic to identify thought parts by checking for truthy thought properties, improving reliability across different model outputs.
• Testing: Added comprehensive unit tests in geminiChat.test.ts and historyHardening.test.ts to reproduce and verify the fix for thought leakage.

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 the 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 counterproductive. 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.

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. ↩

[github-actions]

📊 PR Size: size/M

• Lines changed: 191
• Additions: +154
• Deletions: -37
• Files changed: 4

[gemini-code-assist]

Code Review

This pull request introduces changes to filter out internal model thoughts from the chat history during history hardening and scrubbing, preventing thought leakage. It adds a stripThoughts helper function in historyHardening.ts and updates scrubContents to exclude thought parts, accompanied by comprehensive unit tests. The reviewer noted an inconsistency in how thoughts are detected between stripThoughts (strict boolean check) and scrubContents (truthy check), suggesting a unified truthy check to ensure robust thought detection.

[luisfelipe-alt]

/gemini review

[gemini-code-assist]

Code Review

This pull request removes peer dependency flags from package-lock.json and implements logic to strip internal model thoughts from the conversation history in packages/core. This includes adding a stripThoughts step in hardenHistory, filtering out thought parts in scrubContents, and adding corresponding unit tests. The review feedback suggests adding defensive checks to ensure that parts are valid objects before using the 'in' operator to prevent runtime TypeErrors, and using the nullish coalescing operator (??) instead of logical OR (||) when providing default values for optional properties.

[amelidev]

/gemini review

[gemini-code-assist]

Code Review

This pull request removes "peer": true from several dependencies in package-lock.json and implements a mechanism to strip internal model thoughts (where part.thought === true) from conversational history in packages/core. This includes adding a stripThoughts pass in hardenHistory and filtering out thought parts in scrubContents, along with corresponding unit tests. The feedback suggests extracting the inline thought check into a reusable type guard isThoughtPart with a local interface and a detailed comment, in accordance with repository guidelines for using undocumented SDK properties, and using this helper consistently across the codebase.

[amelidev]

/gemini review

[gemini-code-assist]

Code Review

This pull request removes peer dependency flags from several packages in package-lock.json and implements a mechanism to strip internal model thoughts (where part.thought === true) from chat history in packages/core. Specifically, a new stripThoughts helper has been introduced in historyHardening.ts to filter out thought parts and discard any resulting empty turns during history hardening and scrubbing. Corresponding unit tests have been added to verify this behavior and prevent thought leakage. There are no review comments to address, and I have no additional feedback to provide.