#41590a3a2fb Thanks @RealKai42! - Add an opt-in NotifyUser progress update feature (off by default): new sessions can show the agent's mid-turn progress with an optional one-line title, enabled in the TUI /experiments or the web/Desktop settings' Lab section; set [experimental] notify_user = true or KIMI_CODE_EXPERIMENTAL_NOTIFY_USER=1 to turn it on.
#4145242ac23 Thanks @wbxl2000! - Add kimi app [path] to open a new desktop chat in the current or specified directory.
#406120a2cea Thanks @chengluyu! - Cap the agent's in-turn wait for background tasks at 90 seconds (longer timeouts are no longer accepted), discourage repeated waits, and let a new message end the wait immediately.
#399809af3b4 Thanks @tpoisonooo! - Tower mode: a message sent while the agent is running aborts the in-progress turn and runs as its own turn.
#403133e368a Thanks @Grapedge! - Add sticky user message summaries in fullscreen mode; click a summary to jump to the original message.
#4074c9f01f0 Thanks @tpoisonooo! - Tower mode: deterministic orchestration with TowerRebase and LLM-free status, goal/tower mutual exclusion, and workspace protection.
#40591f6f0b1 Thanks @7Sageer! - Add the KIMI_CODE_TRUST_WORKSPACE environment variable to mark the workspace as trusted.
#4165afd95f6 Thanks @Grapedge! - Replace user skill cards with highlighted prompts and support Ctrl-S for skill prompts.
Patch Changes
#4183c15638b Thanks @RealKai42! - Cancel in-flight video uploads when a media read is interrupted.
#408106ebfc8 Thanks @sailist! - Fix shifted turns and lost replies when a UserPromptSubmit hook injects text; hook JSON output without a "message" field is no longer added to the conversation.
#4154419aced Thanks @7Sageer! - Fix media file reading on the first turn after resuming a session.
#4083f409caa Thanks @sailist! - Cron tasks from the source session no longer fire inside a forked session.
#4152f0bc988 Thanks @7Sageer! - Forked subagents now inherit the parent's available agent types, including custom agents.
#4057a940f2f Thanks @huangzheng2016! - Fix the permission mode switch in the goal-start approval prompt not taking effect on the v2 engine.
#408106ebfc8 Thanks @sailist! - Fix messages rendering out of place in sessions with a UserPromptSubmit hook.
#41537091138 Thanks @RealKai42! - Let the agent write one- or two-sentence progress notes between tool calls instead of bare status lines; in the experimental Updates panel (KIMI_CODE_EXPERIMENTAL_NOTIFY_USER=1), stop asking the agent to repost its mid-turn text as an update and remind it to post updates less often.
#40544fbe065 Thanks @RealKai42! - Stop prompting the agent to send NotifyUser updates when a session is opened in a host that does not display them.
#409121406fb Thanks @sailist! - Omit max_tokens for models without an explicit output limit, fixing repeated 400 errors on strict serving stacks (e.g. bare vLLM) when the model's max output size is unknown.
#4184cbd7540 Thanks @7Sageer! - Remove the never-implemented executor = "kaos" option from MCP stdio server configuration; configs using it now fail validation at load time.
#29190f052fe Thanks @duyphan154! - Sanitize foreground Bash tool output so captured terminal escape sequences no longer change the host terminal state.
#41643395f5b Thanks @huangzheng2016! - Show a "Shutting down" status hint while shutdown hooks run during exit, and let a Ctrl+C during that window force an immediate exit instead of waiting for the hook timeout.
#4056395d537 Thanks @7Sageer! - Replace inline MCP commands in the workspace trust prompt with activation summaries and configuration paths for manual inspection.
#4076e3bf50c Thanks @7Sageer! - Remove interruption reminders from the conversation when their interrupted turns are undone.
