feat(extract): allow changing LLM model before rerunning extraction#560
Merged
feat(extract): allow changing LLM model before rerunning extraction#560
Conversation
Pressing r on a completed LLM step now opens an inline model picker instead of immediately rerunning. Users can fuzzy-filter, navigate with arrow keys, and select a model -- the extraction client is switched and the LLM step reruns with the chosen model. Non-local models trigger a pull before rerunning. Refactors renderModelCompleter and refilterCompleter into reusable functions shared between chat and extraction overlays. closes #510 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
cpcloud
force-pushed
the
worktree-shimmying-coalescing-tulip
branch
from
7239016 to
3b7c6ab
Compare
cpcloud
added a commit
that referenced
this pull request
Mar 19, 2026
…560) ## Summary - Pressing `r` on a completed LLM step opens an inline model picker instead of immediately rerunning - Fuzzy filter by typing, navigate with arrow keys, select with Enter, dismiss with Esc - Selecting a local model switches the extraction client and reruns; non-local models trigger a pull first - Auto-reruns extraction after pull completes when the overlay is still open - Filter prompt shows typed text with a blinking block cursor - Hint text updated from "r to rerun" to "r model" - Refactors `renderModelCompleter` and `refilterCompleter` into reusable functions shared between chat and extraction - Adds `BlinkCursor` style to the styles singleton - 10 user-flow tests covering picker activation, dismissal, selection, filtering, navigation, step preservation, and guard rails closes #510 Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
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
ron a completed LLM step opens an inline model picker instead of immediately rerunningrenderModelCompleterandrefilterCompleterinto reusable functions shared between chat and extractionBlinkCursorstyle to the styles singletoncloses #510