You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
processor.ts: merge multiple reasoning-start/end cycles into one part #27987
Some API providers (e.g. chenbei proxy) send reasoning_content split across multiple reasoning-start/reasoning-end cycles, each containing only 1-2 characters.
This causes the TUI to display dozens of tiny ▶ Thought for 2ms blocks instead of one complete reasoning block.
Root Cause
In processor.ts, each reasoning-start creates a new ReasoningPart. When the provider emits multiple reasoning cycles for the same reasoning content, each cycle
gets its own part, fragmenting the display.
Fix
Save the last ended reasoning part and reuse it when a new reasoning-start arrives, instead of creating a new part each time.
Activity
github-actions commentedon May 17, 2026
This issue might be a duplicate of existing issues. Please check:
processor.ts— models that emit a separatereasoning-start/reasoning-endcycle per token or per character result in many tiny reasoning blocks instead of one continuous block. The issue describes the same symptom and the same fix area.github-actions commentedon Jul 17, 2026
To stay organized issues are automatically closed after 60 days of no activity. If the issue is still relevant please open a new one.