Repository navigation
fix: model mentions name a model in the prompt instead of switching - #17
Open
ScriptedAlchemy wants to merge 3 commits into
Open
ScriptedAlchemy wants to merge 3 commits into
ScriptedAlchemy wants to merge 3 commits into
Conversation
Picking a model from the @ menu switched the thread's provider and model. Mentions are meant to tell the agent which model to use, for example when delegating, so they now insert `model:<instance>/<model>` into the prompt and leave the thread's model alone. Since nothing switches, mentions offer every ready provider's models, not only those the thread could switch to. The text has no `@` because the editor turns `@` tokens into file chips. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
…model state Remove the obsolete model-switch gate from web mentions, including question answers, while keeping the model picker gate intact. Drop the dead mobile selection prop, resolve model insertion through the pure command resolver, and reuse unlocked model options when possible. Add the mobile text-and-cursor regression, assert the exact web prompt, and correct the composer guide to describe model references for delegation without changing the thread model. Implemented with GPT-6.1 via the Codex harness. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
…sert-text # Conflicts: # apps/mobile/src/features/threads/ThreadComposer.tsx
This branch has not been deployed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Picking a model from the composer's
@menu switched the thread's provider and model. Mentions are meant to tell the agent which model you're talking about (for example "delegate this to …"), not to change the current chat.Selecting a model mention now inserts
model:<provider-instance>/<model>(e.g.model:codex/gpt-5.4) into the prompt on web and mobile, and the thread's model stays put. Because nothing switches anymore:onSelectModel/onUpdateModelSelectionwiring that only existed for mention switching.The inserted text avoids a leading
@, since the editor renders any@tokenas a file chip.Tests:
formatComposerModelMentionunit test, matcher test updated, and the web browser test now asserts the text is inserted andonProviderModelSelectis never called.🤖 Generated with Claude Code (Claude Opus 5.5)