Skip to content

feat: per-agent model selection and UI refinements#217

Merged
chriswritescode-dev merged 2 commits intodevfrom
feat/per-agent-model-selection
May 5, 2026
Merged

feat: per-agent model selection and UI refinements#217
chriswritescode-dev merged 2 commits intodevfrom
feat/per-agent-model-selection

Conversation

@chriswritescode-dev
Copy link
Copy Markdown
Owner

Summary

Allow per-session model selection in the prompt input, simplify model resolution logic, and improve task tool call status indicators (pending/running/completed/error) with better visual feedback. Adds z-index to side drawer for proper overlay.

Type of Change

  • Bug fix
  • New feature
  • Refactor
  • Documentation

Checklist

  • Code follows project style (no comments, named imports)
  • TypeScript types are properly defined
  • Tests added/updated (80% coverage target)
  • pnpm lint passes locally

- Add agentModels store with setAgentModel/getAgentModel
- PromptInput uses session model priority and stores agent model on change
- useContextUsage derives model from assistant message instead of global
- Migrate sub-agent/subtask badges from purple to blue with refined styling
- Fix MoreDrawer sentinel to skip history-back on navigation
@chriswritescode-dev chriswritescode-dev merged commit 93fe4d6 into dev May 5, 2026
3 checks passed
@chriswritescode-dev chriswritescode-dev deleted the feat/per-agent-model-selection branch May 5, 2026 01:35
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant