9f43dc70228339deda54218eca9ee277df683fdc
Every TUI config-editor save regenerates the TOML through CorrexConfigWriter, whose [router.narration] section never wrote model_id — one save and narration silently fell back to the main model, queueing every narration behind slow 9B inferences (live QA: approval narrations arrived minutes late, after the workflow had already failed). The writer now persists it and the field is editable in the TUI (blank clears it).
fix: workflow inference chain — surface llama-server errors, user-turn-last, bundle-relative prompts
Description
No description provided
Languages
Kotlin
88.4%
Go
11.4%
Python
0.2%