- Align thinking-level handling in web with the CLI: submit the selected level verbatim instead of silently downgrading it, pin the model's catalog default when nothing was chosen, pre-select the target model's default on model switches, and persist explicit picks as the daemon-wide default so new sessions inherit them
- Show just the level name (e.g. Max) in the model pill instead of "thinking: max"
- Preserve goal completion summaries and show untyped LLM errors without an internal error-code prefix in step interruption events
- Fix built-in tools being unavailable when the model provider becomes ready after the session starts
- Fix Kimi sessions getting stuck when preserved-thinking history contains an empty reasoning step
- Fix Thinking effort routing so non-Kimi providers preserve configured values for upstream validation, while Kimi models validate runtime selections, fall back safely during model resolution, and synchronize the effective effort back to clients
Patch Changes
-
#1678
ec1c974Thanks @chengluyu! - Preserve goal completion summaries and show untyped LLM errors without an internal error-code prefix in step interruption events. -
#1688
94c0ef8Thanks @sailist! - Fix built-in tools being unavailable when the model provider becomes ready after the session starts. -
#1684
e417ee7Thanks @RealKai42! - Fix Kimi sessions getting stuck when preserved-thinking history contains an empty reasoning step. -
#1673
0f64b4dThanks @wbxl2000! - web: Align thinking-level handling with the CLI: submit the selected level verbatim instead of silently downgrading it, pin the model's catalog default when nothing was chosen, pre-select the target model's default on model switches, and persist explicit picks as the daemon-wide default so new sessions inherit them. -
#1689
ab22a2aThanks @wbxl2000! - web: Show just the level name (e.g. Max) in the model pill instead of "thinking: max". -
#1625
d158e0aThanks @RealKai42! - Fix Thinking effort routing so non-Kimi providers preserve configured values for upstream validation, while Kimi models validate runtime selections, fall back safely during model resolution, and synchronize the effective effort back to clients.