Repository navigation
fix(app): group the default model list by provider, name the Dashboard's model, and start new channels on the last pick - #676
Merged
Conversation
…d's model, and start new channels on the last pick Settings → Default model groups models under Anthropic and OpenAI and shows a provider without a key as "OpenAI (no key)". The Dashboard composer gets a model picker that names what Automatic resolves to, and a new local channel starts on the latest pick from any composer in this client. Why: apps/app/src/composer.tsx#function lastModel | the stored last pick only seeds new local channels; a chat's composer always shows the chat's own model, never this copy
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Settings, the Dashboard and new channels now agree on which model a new channel starts on.
OpenAI (no key)with a disabled "Add a key in Providers to use OpenAI models" row ((unavailable)when its key can't be read).Automatic (claude-opus-5-5), from a newautomaticfield on host settings (defaultModelresolved on the settled catalog, so it never waits on a keychain prompt). Changing the default in Settings updates it without a reload. The picker is hidden for Run in cloud, which uses the service's models.modelwhen it creates a local channel (Dashboard send, New channel, palette, GitHub pages). Picking Automatic goes back to Automatic. A chat's composer still shows the chat's own model, never this copy.Smoke-tested on an isolated loopback host (own ACE_HOME, config, keychain service, port 4968) from a headless Chromium, with a real Anthropic key:
Automatic (claude-opus-5-5); picked claude-haiku-4-5, then New channel: the channel's composer showed claude-haiku-4-5 andace lslisted it asanthropic/claude-haiku-4-5.Automatic (claude-opus-5-5).Automatic,[Anthropic: 16 models],[OpenAI (no key): Add a key in Providers to use OpenAI models]. Saving claude-sonnet-5-5 there changed the Dashboard toAutomatic (claude-sonnet-5-5)without a reload.Map: ^46, ^378.
Fixes #618 (with #640).
Built in Ace
No. This was made from Claude Code as a fix-train worker, using a headless Chromium to drive an isolated source host. Ace has no way yet to run an agent-driven fix queue across several workers like this (#5).