fix: move model resolution from TUI handlers to runtime coordinator#663
Merged
fix: move model resolution from TUI handlers to runtime coordinator#663
Conversation
TUI handlers always filled in a default model before runtime started, causing all experts to run with claude-sonnet-4-5 regardless of their defaultModelTier. Now model is optional at the TUI boundary and the coordinator-executor resolves it after expert setup, respecting each expert's defaultModelTier from both local config and API-resolved experts. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Merged
FL4TLiN3
added a commit
that referenced
this pull request
Mar 2, 2026
Since #663 made `model` optional in RunSetting/RunParamsInput with tier-based auto-resolution, update all documentation and code examples to reflect this change. Remove hardcoded model values from run() calls, add comments explaining auto-resolution, and rewrite the default model documentation to explain the tier-based system. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
3 tasks
FL4TLiN3
added a commit
that referenced
this pull request
Mar 2, 2026
* docs: update model parameter as optional in docs and examples Since #663 made `model` optional in RunSetting/RunParamsInput with tier-based auto-resolution, update all documentation and code examples to reflect this change. Remove hardcoded model values from run() calls, add comments explaining auto-resolution, and rewrite the default model documentation to explain the tier-based system. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * docs: remove unnecessary optional model comments Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> --------- 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
perstack start create-expertexecuting all agents withclaude-sonnet-4-5instead of respecting each expert'sdefaultModelTierperstack.toml— API-resolved experts never got tier resolutionmodeloptional at the TUI boundary and moved resolution toCoordinatorExecutor.execute(), which resolves aftersetupExperts()using: explicit model > expert'sdefaultModelTier> middle tier fallbackTest plan
bun run typecheck— 23/23 packages passbun run test— all tests pass including 4 new coordinator-executor tests and 1 new delegation-executor testbun run build— 23/23 packages buildbun run format-and-lint— no new warnings🤖 Generated with Claude Code