Skip to content

refactor(session): non-radiant player convos saved automatically#23

Merged
canefe merged 3 commits intomainfrom
refactor/session/auto-accept-player-convo
Mar 7, 2026
Merged

refactor(session): non-radiant player convos saved automatically#23
canefe merged 3 commits intomainfrom
refactor/session/auto-accept-player-convo

Conversation

@canefe
Copy link
Owner

@canefe canefe commented Mar 7, 2026

No description provided.

@gemini-code-assist
Copy link

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 refactors the conversation system to introduce a distinction between 'radiant' and 'non-radiant' conversations. The primary impact is that non-radiant conversations involving players will now have their summaries automatically saved to the session history, ensuring that important player interactions are always recorded without requiring explicit user confirmation. This enhances the continuity and completeness of the narrative by consistently capturing relevant conversation data.

Highlights

  • New 'radiant' property for conversations: A new boolean property radiant has been added to the Conversation class, defaulting to false, to distinguish between different types of conversations.
  • Conditional session history saving: The SessionManager.feed method now accepts a force parameter, allowing certain conversations (specifically non-radiant ones involving players) to automatically save their summaries to session history without requiring user permission.
  • Radiant conversation initialization: New conversations initiated through RadiantConversationService or NPCManager are now explicitly marked as radiant.
  • Updated test cases: The ConversationManagerTest has been updated to reflect the changes in the SessionManager.feed method signature and the logic related to the radiant flag.

🧠 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.

Changelog
  • src/main/kotlin/com/canefe/story/conversation/Conversation.kt
    • Added a radiant boolean property with a default value of false.
  • src/main/kotlin/com/canefe/story/conversation/ConversationManager.kt
    • Modified the call to plugin.sessionManager.feed to include a force parameter, which is set based on the radiant status of the conversation and whether players are involved.
    • Explicitly set the radiant property to true for conversations started via startConversation.
  • src/main/kotlin/com/canefe/story/conversation/radiant/RadiantConversationService.kt
    • Updated the npcManager.eventGoToPlayerAndTalk method call to pass radiant = true.
  • src/main/kotlin/com/canefe/story/npc/NPCManager.kt
    • Added a radiant boolean parameter with a default value of false to the eventGoToPlayerAndTalk method.
    • Used the new radiant parameter to set the radiant property of the created conversation.
  • src/main/kotlin/com/canefe/story/session/SessionManager.kt
    • Modified the feed method signature to accept an optional force boolean parameter.
    • Implemented conditional logic within the feed method to bypass the user permission prompt for adding narrative responses to session history if force is true.
  • src/test/kotlin/com/canefe/story/ConversationManagerTest.kt
    • Updated mock definitions for plugin.sessionManager.feed to match the new method signature, including the force parameter.
    • Adjusted verification calls for plugin.sessionManager.feed to account for the new force parameter, specifically verifying eq(true) when appropriate.
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

@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 radiant flag for conversations and automatically adds summaries of non-radiant player conversations to the session history via a force parameter in SessionManager.feed, bypassing the permission prompt. This change, however, introduces a critical security vulnerability by bypassing a safety check, allowing untrusted player input to influence AI output rendered to other players. This creates a vector for AI output injection attacks, potentially leading to chat spoofing or the execution of malicious commands. It is recommended to re-introduce a manual review step or implement strict sanitization of AI-generated content before broadcasting. Additionally, there is a suggestion regarding the long-term growth of the session history.

@canefe canefe merged commit 4a00641 into main Mar 7, 2026
3 checks passed
@canefe canefe deleted the refactor/session/auto-accept-player-convo branch March 7, 2026 12:45
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant