- Manage instances with kimi web kill [server-id|all], kimi web ps, and kimi web rotate-token
- Add a note in the model switcher that switching models or thinking effort invalidates the existing prompt cache
- Replace the kimi server command tree with kimi web: the server runs in the foreground (the background daemon and OS-service lifecycle commands are removed), and multiple servers can now share one home directory, each taking the next free port
- Thinking effort persists only levels below the model's top tier (max)
- Rename the stale afk reference to auto in the built-in MCP config skill guidance
- Correct the YOLO and Auto permission mode descriptions in CLI --help output and in the ACP session mode selector shown by IDE clients
- Correct the YOLO and Auto permission mode descriptions in the slash command list and the mobile permission sheet
- Fix the YOLO and Auto permission mode descriptions to match their actual behavior: YOLO auto-approves tool actions but the agent may still ask questions, while Auto is fully autonomous and never asks
- Correct the YOLO mode notice shown when replaying a session: tool actions are auto-approved, but the agent may still ask questions
- Fix the web backend ignoring symbolic links when loading AGENTS.md files and reading files
- Any kimi server invocation prints a deprecation notice and exits 1
Minor Changes
-
#1826
a41a09cThanks @sailist! - Replace thekimi servercommand tree withkimi web: the server runs in the foreground (the background daemon and OS-service lifecycle commands are removed), and multiple servers can now share one home directory, each taking the next free port. Manage instances withkimi web kill [server-id|all],kimi web ps, andkimi web rotate-token; anykimi server …invocation prints a deprecation notice and exits 1. -
#1933
11c1683Thanks @liruifengv! - Thinking effort persists only levels below the model's top tier (max).
Patch Changes
-
#1867
3086e47Thanks @RealKai42! - Rename the stale "afk" reference to "auto" in the built-in MCP config skill guidance. -
#1867
3086e47Thanks @RealKai42! - Correct the YOLO and Auto permission mode descriptions in CLI --help output and in the ACP session mode selector shown by IDE clients. -
#1867
3086e47Thanks @RealKai42! - web: Correct the YOLO and Auto permission mode descriptions in the slash command list and the mobile permission sheet. -
#1867
3086e47Thanks @RealKai42! - Fix the YOLO and Auto permission mode descriptions to match their actual behavior: YOLO auto-approves tool actions but the agent may still ask questions, while Auto is fully autonomous and never asks. -
#1867
3086e47Thanks @RealKai42! - Correct the YOLO mode notice shown when replaying a session: tool actions are auto-approved, but the agent may still ask questions. -
#1843
a3e773fThanks @7Sageer! - Fix the web backend ignoring symbolic links when loading AGENTS.md files and reading files. -
#1940
d71bf9eThanks @wbxl2000! - web: Add a note in the model switcher that switching models or thinking effort invalidates the existing prompt cache.