Add 'None' personality option to completely disable personality #10687
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Implements the feature requested in OpenAI Codex issue openai#10582. Users can now select 'None' personality to completely disable personality-driven responses, making Codex behave as a purely functional tool without any conversational personality layer. Changes: - Add 'None' variant to Personality enum - Add personality_none field to ModelInstructionsVariables - Return None (not empty string) when Personality::None is selected - Update TUI to show 'None' option in personality popup - Update tests and snapshots Generated with [Claude Code](https://claude.ai/code) via [Happy](https://happy.engineering) Co-Authored-By: Claude <noreply@anthropic.com> Co-Authored-By: Happy <yesreply@happy.engineering>
The `personality_none` field in `ModelInstructionsVariables` was never used: - Required by `is_complete()` to be `Some` - But never read by `get_personality_message()` (returns hardcoded `None`) - Always set to `None` in production code Removing this dead code since `Personality::None` correctly returns `None` via the hardcoded return in `get_personality_message()`. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Contributor
|
All contributors have signed the CLA ✍️ ✅ |
Author
|
I have read the CLA Document and I hereby sign the CLA |
The field was removed from ModelInstructionsVariables but these assignments weren't cleaned up. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Collaborator
|
We've updated our contribution guidelines to indicate that we're no longer accepting unsolicited code contributions. All code contributions are by invitation only. To read more about why we've taken this step, please refer to this announcement. |
Author
|
LOL WTF. |
Collaborator
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Add 'None' Personality Option
Summary
This PR adds a new "None" personality option that completely disables personality injection in AI responses. When selected, the model provides purely functional responses without any personality formatting or conversational styling.
Changes
Protocol Layer
protocol/src/config_types.rs: AddedNonevariant to thePersonalityenumprotocol/src/openai_models.rs: Updated personality matching logic to returnNone(no personality injection) whenPersonality::Noneis selectedUI Layer
tui/src/app.rs: Added display label for the None personality optiontui/src/chatwidget.rs:Personality::Noneto the personality selection popupBug Fix
core/src/models_manager/model_info.rs: Removed leftoverpersonality_nonefield assignments that were causing compilation errors after the struct field was removedUser Impact
Users can now select "None" as a personality option, which will:
Testing
Fixes #10582