🤖 feat: persist per-model thinking via backend settings #1238
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
Restore the per-model thinking behavior that was changed in #1203. While that PR added valuable backend persistence for AI settings, it also changed thinking levels from per-model to per-workspace scoping. This was an unintended UX regression - users expect different models to remember their individual thinking preferences. ### Changes - **ThinkingContext**: Use per-model localStorage keys (`thinkingLevel:model:{model}`) instead of workspace-scoped keys - **WorkspaceContext**: Seed per-model thinking from backend metadata - **Storage**: Remove workspace-scoped thinking key from persistent keys (thinking is global per-model, not workspace-specific) - **sendOptions**: Simplify to read per-model thinking directly - **useCreationWorkspace**: Remove workspace-scoped thinking sync - **ThinkingSlider**: Update tooltip to "Saved per model" ### Backend persistence preserved Backend still stores `aiSettings.thinkingLevel` per workspace (the last-used value) and seeds it to new devices via the per-model key. This maintains cross-device sync while restoring the expected per-model UX. ### Tests - Updated ThinkingContext tests to verify per-model behavior - Updated WorkspaceContext test to seed per-model key - Updated useCreationWorkspace test to remove migration assertion
ammar-agent
changed the title
Collaborator
Author
|
Heads up: we’re not planning to merge this approach. We’re abandoning the backend Leaving notes here because there were a few useful lessons worth carrying forward:
Generated with |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Eliminate localStorage↔backend duplication for thinking levels by making per-model thinking backend-authoritative.
What changed
persistedSettingsto config (~/.mux/config.json) storingai.thinkingLevelByModelpersistedSettings.get,persistedSettings.setAIThinkingLevel,persistedSettings.onChangedPersistedSettingsStorekeeps an in-memory snapshot, refreshes + subscribes, and provides a localStorage fallback + one-time seed to migrate existingthinkingLevel:model:*keysThinkingContext, command palette thinking actions, andgetSendOptionsFromStoragenow read from the store; no longer write thinking to localStorageWorkspaceContextonly seeds workspace model; thinking is handled via persistedSettingsTests
Generated with
mux• Model:openai:gpt-5.2• Thinking:xhigh