fix: pause downshift on manual thinking level changes - #23
Merged
Conversation
Register the current thinking_level_select event and share manual model-state pause handling so external thinking changes cannot leave stale handoff state or target tracking. Guard both model and thinking-level updates initiated by Downshift, update the adapter and core tests, and align Pi development dependencies so agent_settled can use the typed ExtensionAPI directly. Tests: npm run check Packaging: npm pack --dry-run
Apply the repository Prettier formatting to the Downshift core and adapter files.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
thinking_level_selectevent changes the active thinking level.agent_settledthrough the typedExtensionAPI.Tests
npm cinpm run checknpm pack --dry-runAll checks pass. The test suite reports 36 passing tests.
Compatibility
No configuration or persisted state format changes were made. Manual thinking-level changes now follow the existing safety behavior for manual model changes by pausing instead of guessing the intended Downshift target.