Kimi Code Updates & Release Notes

Open a new Desktop chat from the terminal

The new kimi app [path] command opens Kimi Code Desktop with a new draft in the current or specified directory, making it easy to move from the CLI into the graphical interface. →

Experimental progress updates

NotifyUser lets the Agent post short progress updates mid-turn. It is off by default and can be enabled in the TUI /experiments panel or in the Web / Desktop settings Lab, applying only to sessions created afterward. →

Interruptible background waits

WaitFor is capped at 90 seconds. While it waits, pressing Enter or Ctrl-S steers your message into the current turn and ends the wait early, while background tasks keep running. →

Also in this release

Fullscreen mode keeps a one-line summary of each user message and lets you jump back to it; user skill cards are now highlighted prompts that can be sent with Ctrl-S.

Linux support

Desktop is now available for x86_64 Linux, with AppImage, deb, and RPM packages. →

Remote Control

Enable it under Settings → Remote Control, then use a link or QR code to control the local Agent from a phone, tablet, or another computer. Tasks and local tools still run on the computer running Desktop. →

File Tree panel

The new File Tree in the right sidebar browses, searches, and refreshes workspace files, with click-to-preview. Toggle it with Cmd + Shift + E on macOS or Ctrl + Shift + E on Windows and Linux.

Also in this release: experimental progress updates can be enabled under Settings → Lab for newly created sessions; the new kimi app command opens a new Desktop session in the current or a specified directory. → ·

Minor Changes

• #4159 0a3a2fb 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.
• #4145 242ac23 Thanks @wbxl2000! - Add kimi app [path] to open a new desktop chat in the current or specified directory.
• #4061 20a2cea 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.
• #3998 09af3b4 Thanks @tpoisonooo! - Tower mode: a message sent while the agent is running aborts the in-progress turn and runs as its own turn.
• #4031 33e368a Thanks @Grapedge! - Add sticky user message summaries in fullscreen mode; click a summary to jump to the original message.
• #4074 c9f01f0 Thanks @tpoisonooo! - Tower mode: deterministic orchestration with TowerRebase and LLM-free status, goal/tower mutual exclusion, and workspace protection.
• #4059 1f6f0b1 Thanks @7Sageer! - Add the KIMI_CODE_TRUST_WORKSPACE environment variable to mark the workspace as trusted.
• #4165 afd95f6 Thanks @Grapedge! - Replace user skill cards with highlighted prompts and support Ctrl-S for skill prompts.

Patch Changes

• #4183 c15638b Thanks @RealKai42! - Cancel in-flight video uploads when a media read is interrupted.
• #4081 06ebfc8 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.
• #4154 419aced Thanks @7Sageer! - Fix media file reading on the first turn after resuming a session.
• #4083 f409caa Thanks @sailist! - Cron tasks from the source session no longer fire inside a forked session.
• #4152 f0bc988 Thanks @7Sageer! - Forked subagents now inherit the parent's available agent types, including custom agents.
• #4057 a940f2f Thanks @huangzheng2016! - Fix the permission mode switch in the goal-start approval prompt not taking effect on the v2 engine.
• #4081 06ebfc8 Thanks @sailist! - Fix messages rendering out of place in sessions with a UserPromptSubmit hook.
• #4153 7091138 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.
• #4054 4fbe065 Thanks @RealKai42! - Stop prompting the agent to send NotifyUser updates when a session is opened in a host that does not display them.
• #4091 21406fb 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.
• #4184 cbd7540 Thanks @7Sageer! - Remove the never-implemented executor = "kaos" option from MCP stdio server configuration; configs using it now fail validation at load time.
• #2919 0f052fe Thanks @duyphan154! - Sanitize foreground Bash tool output so captured terminal escape sequences no longer change the host terminal state.
• #4164 3395f5b 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.
• #4033 eec9bbd Thanks @Grapedge! - Feedback surveys now appear less often.
• #4160 72fc1d0 Thanks @kimi-agent-bot! - Show "Working…" in the status spinner while thinking.
• #4056 395d537 Thanks @7Sageer! - Replace inline MCP commands in the workspace trust prompt with activation summaries and configuration paths for manual inspection.
• #4076 e3bf50c Thanks @7Sageer! - Remove interruption reminders from the conversation when their interrupted turns are undone.
• #4031 33e368a Thanks @Grapedge! - Replace the user message bullet ✨ with ❯.
• #4221 2e6821d Thanks @kimi-agent-bot! - web: Improved interactions and fixed known bugs.

Fullscreen mode (experimental)

A new experimental fullscreen interface: the transcript scrolls independently, text can be selected with the mouse, fold blocks expand or collapse on click, and a clickable "Jump to bottom" indicator sits at the bottom. Enable it under /settings → TUI mode, or set tui_mode = "fullscreen" in ~/.kimi-code/tui.toml, then restart Kimi Code. →

Faster startup, lower memory

Shorter CLI startup time and reduced memory usage — first paint arrives noticeably sooner in large projects.

File watching is now off by default

Filesystem watching for config and workspace files no longer runs by default; to hot-reload AGENTS.md, skills, or MCP config, set [watch] enabled = true or KIMI_CODE_WATCH=1. →

Also in this release: hardened workspace trust boundaries — file tools can no longer reach outside the working directory through symbolic links, and project-local config only takes effect after the workspace is trusted; new auto_session_title config to turn off automatic session title generation by clients. →

Minor Changes

• #3990 32000d0 Thanks @Grapedge! - In fullscreen, click a folded block to open or close it.
• #4004 e17ff67 Thanks @Grapedge! - Add a TUI mode setting to /settings with an experimental fullscreen layout; switching modes takes effect after restarting Kimi Code. You can also set tui_mode in ~/.kimi-code/tui.toml directly: "regular" renders into the terminal scrollback, while "fullscreen" makes parts of the UI mouse-interactive for a smoother experience.

Patch Changes

• #3964 6451f1e Thanks @7Sageer! - Block file tools from accessing files outside the working directory through symlinks.
• #3975 bb96d80 Thanks @RealKai42! - Reduce the CLI's startup time and memory usage.
• #3957 6a214b8 Thanks @huangzheng2016! - Fix a "Maximum call stack size exceeded" error when opening large sessions.
• #3974 994287a Thanks @liruifengv! - Fix forked sessions getting their titles overwritten by auto-generated titles.
• #3964 6451f1e Thanks @7Sageer! - Apply project-local configuration only after the workspace is trusted.
• #3964 6451f1e Thanks @7Sageer! - Block repository git configuration from executing commands during background git operations.
• #3969 b3212fd Thanks @sailist! - Skip cloud telemetry on the global login until its collector is live, and keep shutdown from aborting TUI exit.
• #3979 e796bb5 Thanks @sailist! - Fix MCP OAuth not requesting the offline_access scope, which caused hourly browser re-authorization with providers like Vercel.
• #3969 b3212fd Thanks @sailist! - Fix Remote Control failing to start after kimi login --region global.
• #3964 6451f1e Thanks @7Sageer! - Reject additional directories that resolve to the home directory or filesystem root.
• #3995 a54e6f6 Thanks @7Sageer! - Turn off repeat reminders and forced stops with KIMI_CODE_REPEAT_BREAKER=0.
• #3970 895e9d9 Thanks @chengluyu! - Fix missing Swarm members after reopening an interrupted conversation.
• #3989 a268ad7 Thanks @Grapedge! - Show a Thinking… spinner and keep the status row height steady during streaming.
• #3989 a268ad7 Thanks @Grapedge! - Add a clickable "Jump to bottom" indicator to the fullscreen TUI.
• #3976 f7012aa Thanks @tpoisonooo! - Tower mode: smaller missions, stricter completion and review checks, and review history in rework briefings.
• #3847 65ae3e3 Thanks @tpoisonooo! - Tower mode: mission titles must be ASCII, and task cards show the mission id.
• #3931 f17a22e Thanks @sailist! - Turn off filesystem watchers for config and workspace files by default. Set [watch] enabled to true or KIMI_CODE_WATCH=1 to turn them back on.
• #4005 ba41d07 Thanks @liruifengv! - web: Improved interactions and fixed known bugs.

Patch Changes

• #3922 9df7a9c Thanks @sailist! - Fix new messages occasionally landing at an old position in the conversation after resuming a session.
• #3911 88a7d93 Thanks @Grapedge! - Fix compaction failing after switching to a model with a smaller context window.
• #3929 6ffdf0d Thanks @7Hanrui! - The agent no longer assumes the current working directory is the project root.
• #3933 9721259 Thanks @liruifengv! - Fix a message sent while the agent was running sometimes appearing twice in the chat.
• #3934 2e605b1 Thanks @liruifengv! - web: Improved interactions and fixed known bugs.

Patch Changes

• #3878 f233f9d Thanks @7Sageer! - Stop listing unavailable media tools in subagent menus and clarify Read errors for images and videos.
• #3762 c5ad17f Thanks @7Sageer! - Providers can read their API key from a named environment variable (api_key_env in config.toml or the provider API).
• #3896 73ebe9a Thanks @sailist! - Keep follow-up messages sent during a turn from appearing twice after a session reload.
• #3889 5108cad Thanks @huangzheng2016! - Compact the session index on startup when many entries point to deleted sessions.
• #3889 5108cad Thanks @huangzheng2016! - Start the CLI faster by removing a duplicate skills directory scan.
• #3889 5108cad Thanks @huangzheng2016! - Open the session list and resume sessions faster on workspaces with many sessions.
• #3889 5108cad Thanks @huangzheng2016! - Resume long sessions faster.
• #3889 5108cad Thanks @huangzheng2016! - Index sessions for search in capped, incremental background passes, tunable via the [database] searchSyncSessionCap and searchSyncDebounceMs settings.
• #3864 25dd4ce Thanks @wbxl2000! - Rename the kimi install-app subcommand to kimi install-desktop; the old name keeps working as a hidden alias.
• #3910 7dc253c Thanks @sailist! - Restore thinking display for OpenAI-compatible providers that send a reasoning string next to an unrecognized reasoning_details array.
• #3875 c1047a6 Thanks @7Sageer! - Fix kimi -p exiting early and cancelling the active turn when a cron task fires.
• #3894 910aba2 Thanks @7Sageer! - Drop literal decision clauses from the system prompt and the auto permission mode reminder.
• #3889 5108cad Thanks @huangzheng2016! - Restore sessions with large file-edit histories faster.
• #3889 5108cad Thanks @huangzheng2016! - Serve session transcript APIs faster on repeated calls.
• #3885 5acc863 Thanks @starquakee! - select_tools now points out already-available tools to call directly and suggests announced names for near-miss selections.
• #3887 e3f48a2 Thanks @RealKai42! - Fix deleting or archiving a session sometimes never finishing.
• #3891 53e5e3f Thanks @sailist! - Keep follow-up messages sent during a turn attached to that turn in the conversation history.
• #3906 60f2a63 Thanks @sailist! - Keep a follow-up sent during a turn as one message, and undo the host turn instead of the follow-up alone.
• #3879 1fddc16 Thanks @7Sageer! - Remove the system-prompt rule that forbade all file access outside the working directory.
• #3892 a80fe31 Thanks @sailist! - Stop workspace file watchers from scanning an unbounded project root, and add [watch] enabled / KIMI_CODE_WATCH to disable watching entirely.
• #3869 86e0820 Thanks @sailist! - Stop asking for approval of bash commands that cannot be statically analyzed in Ask When Needed permission mode.

The Kimi Code desktop client is officially available: it carries the Agent core of Kimi Code CLI into a graphical interface, where you open a project, talk to the Agent, and ship changes in one window. Available now for macOS (Apple Silicon / Intel) and Windows. →

Every step stays visible

Tool calls, thinking, and the files changed in each turn are all presented in the interface; sensitive operations raise approval prompts, and three permission modes (Always Ask / Ask When Needed / Never Ask) keep you in control. →

A complete workflow from conversation to delivery

Goal mode keeps long-running objectives moving and can be paused, resumed, or cancelled; plan mode proposes an approach before touching files, and the plan can be reviewed and refined; long tasks can move to the background, where you can check progress or stop them at any time. →

Built-in browser and visual annotation

The browser lives in the right panel, with tabs that stay with the session and page context shared with the Agent; screenshot annotation, text selection comments, @ file mentions, and element picking on web pages tell the Agent exactly what to change. →

Download:

macOS · Apple Silicon · macOS · Intel · Windows

New /desktop command

The new /desktop slash command (alias /install-desktop) and the kimi install-desktop subcommand open the desktop app page in your browser, so you can download and install the desktop client without leaving the terminal. →

Mermaid diagrams in the terminal

Mermaid code blocks now render as diagrams in the terminal; turn this off under /settings → Mermaid diagrams, or set mermaid = "off" in the [markdown] section of tui.toml.

Also in this release: the built-in browser plugin is renamed to Kimi Browser Extension; when accumulated media in a session exceeds 20 MB, the oldest images and videos are omitted from requests with a warning → Paste images and videos. Since v2.0.1, a provider's API key can be read from a named environment variable via api_key_env instead of being written into the config file → Config files.

Features

• Add native clipboard support on Linux X11, so copying from the TUI no longer depends on the terminal's OSC 52 support.

Polish

• Reduce event-loop stalls and GC churn in sessions with many concurrent subagents.

Bug Fixes

• Fix pressing Ctrl+C while subagents are running exiting the whole CLI instead of just interrupting the subagents.
• Fix progressively slower rendering on each round of large agent swarm runs.
• Fix memory not being released when subagent scopes are disposed.
• Fix tower mode mistaking newly spawned agents for previous sessions' roster entries.
• Stop returning deleted sessions from global search before the search index catches up.
• Fix link colors in wrapped markdown tables and @file-completion ordering.

Patch Changes

#3780 486dcd2 Thanks @Grapedge! - Update the terminal UI engine, fixing link colors in wrapped markdown tables and @ file-completion ordering, and adding native clipboard support on Linux X11.

#3776 48fad6e Thanks @huangzheng2016! - Fix memory not being released when subagent scopes are disposed.

#3777 dc76b0c Thanks @huangzheng2016! - Fix progressively slower rendering on each round of large agent swarm runs.

#3631 1336be3 Thanks @wbxl2000! - Stop returning deleted sessions from global search before the search index catches up.

#3775 f248624 Thanks @huangzheng2016! - Reduce event-loop stalls and GC churn in sessions with many concurrent subagents.

#3779 82ec469 Thanks @huangzheng2016! - Fix pressing Ctrl+C while subagents are running exiting the whole CLI instead of just interrupting the subagents.

#3752 0725ef1 Thanks @tpoisonooo! - Fix tower mode mistaking newly spawned agents for previous sessions' roster entries.

Minor Changes

• #3749 6126472 Thanks @liruifengv! - web: AI session titles are now always on — a title is generated after the first turn and can be regenerated from the rename field, with no experimental flag required.
• #3670 a9efbe0 Thanks @Grapedge! - Delete sessions from the session picker: press Ctrl+X on a session, then y to confirm.

Patch Changes

• #3763 dd6a411 Thanks @liruifengv! - web: add user agreement and privacy policy entries to the Settings → About page.
• #3750 775a6c3 Thanks @7Sageer! - Add the loop_control.compaction_max_attempts config option to set the maximum total attempts for a failing compaction request (default 5).
• #3667 9296e68 Thanks @sailist! - Add the dynamically_loaded_tools capability to official Kimi Code models when the service declares support for message-level tool declarations.
• #3763 dd6a411 Thanks @liruifengv! - web: fix sessions containing many brackets or backslashes getting stuck while loading.
• #3734 ee2cac1 Thanks @kimi-agent-bot! - Fix a crash that killed the process when a retried LLM request had streamed a partial tool call before disconnecting.
• #3763 dd6a411 Thanks @liruifengv! - web: fix persistent UI stuttering while streaming in long sessions.
• #3763 dd6a411 Thanks @liruifengv! - web: fix certain formulas, links, tool results, and log contents causing the UI to stutter or become unresponsive.
• #3763 dd6a411 Thanks @liruifengv! - web: fix the send button staying disabled when starting a new session.
• #3763 dd6a411 Thanks @liruifengv! - web: fix previous sessions being wrongly marked as unread and triggering "turn complete" notifications after starting a new conversation.
• #3763 dd6a411 Thanks @liruifengv! - web: render Markdown frontmatter metadata as key-value cards and tag lists.
• #3688 9f7e68e Thanks @RealKai42! - Preserve MCP attachments that cannot be delivered directly to the model.
• #3667 9296e68 Thanks @sailist! - Add a per-server deferred field to MCP server configuration: when the model supports dynamic tool loading (experimental tool-select flag), set deferred: true to keep a server's tools out of the top-level tool list and load them on demand via select_tools; servers are exposed inline by default.
• #3763 dd6a411 Thanks @liruifengv! - web: drop the Changes entry from the panel new-tab menu while a diff tab is open.
• #3657 5b3b5b6 Thanks @chengluyu! - Exclude time spent with the session closed from goal time budgets.
• #3728 b180725 Thanks @kimi-agent-bot! - Add the KIMI_CODE_PERMISSION_MODE_REMINDER environment variable: set it to 0 to stop injecting the auto permission-mode reminders into the model context.
• #3696 d3dc594 Thanks @sailist! - Include the server token in the Remote Control Local UI link so it opens already signed in.
• #3709 306f6f6 Thanks @sailist! - Fix Remote Control uploads larger than ~3.5MB always failing with a 400 error.
• #3718 ab9e688 Thanks @sailist! - Reuse unchanged Remote Control assets across page loads instead of retransferring them.
• #3657 5b3b5b6 Thanks @chengluyu! - Remove the 24-hour limit on goal time budgets.
• #3714 565093f Thanks @sailist! - Skip the confirmation prompt for rm -rf commands that target only /tmp or /temp paths.
• #3667 9296e68 Thanks @sailist! - Fix the select_tools tool never being registered because agent profiles do not list it in their tool allowlists.
• #3763 dd6a411 Thanks @liruifengv! - web: restructure the Settings pages — Account moves right after General, Agent is renamed to Agents & Sessions and now includes message folding, Advanced is renamed to About, and data & privacy settings move into General.
• #3763 dd6a411 Thanks @liruifengv! - web: fix the selected segment background flashing and shifting while the Settings segmented control loads.
• #3697 5e452fc Thanks @RealKai42! - Allow steering messages to interrupt waits for background tasks.
• #3763 dd6a411 Thanks @liruifengv! - web: fix the switch thumb deforming at both ends when stretched on hover.
• #3763 dd6a411 Thanks @liruifengv! - web: fix tooltips popping up even when the mouse has not moved.
• #3648 2da4aa2 Thanks @tpoisonooo! - Tower mode reliability fixes across messaging, worktrees, and the review-to-merge gate.
• #3707 e409bc8 Thanks @sailist! - Compress Remote Control tunnel responses with gzip.
• #3702 42998cf Thanks @sailist! - Add -y, --yes to kimi upgrade (alias kimi update) to skip the confirmation prompt and install the update directly.
• #3681 1306a9a Thanks @7Sageer! - Warn at startup when a [models] entry in config.toml is missing the model field and cannot be used.

Features

• web: AI session titles are now always on — a title is generated after the first turn and can be regenerated from the rename field, with no experimental flag required.
• Delete sessions from the session picker: press Ctrl+X on a session, then y to confirm.
• Add -y, --yes to kimi upgrade (alias kimi update) to skip the confirmation prompt and install the update directly.
• Add the loop_control.compaction_max_attempts config option to set the maximum total attempts for a failing compaction request (default 5). See loop_control for details.

Polish

• Skip the confirmation prompt for rm -rf commands that target only /tmp or /temp paths.
• Allow steering messages to interrupt waits for background tasks.
• Goal time budgets no longer count time spent with the session closed, and the 24-hour limit is removed.
• Add the KIMI_CODE_PERMISSION_MODE_REMINDER environment variable: set it to 0 to stop injecting the auto permission-mode reminders into the model context.

Bug Fixes

• Fix several known issues and make various refinements. See the changelog on GitHub for more technical entries.

AI session titles in Web, on by default

A title is generated automatically after the first turn, and you can regenerate it from the rename box — no more naming sessions by hand.

Delete sessions from the session selector

Select a session in the session selector, press Ctrl-X, then y to confirm — cleaning up old sessions is much easier.

Fairer time budgets in Goal Mode

Time budgets no longer count the time while a session is closed, and the 24-hour cap is gone, so long-running goals no longer burn budget while you are away. →

Goal mode

Also in this release: kimi upgrade (alias kimi update) gains a -y, --yes flag to skip the confirmation prompt; the new KIMI_CODE_PERMISSION_MODE_REMINDER environment variable (set to 0) stops injecting auto-permission-mode reminders into the model context. v0.43.1 fixes pressing Ctrl-C while a subagent is running quitting the entire CLI — it now only interrupts the running subagent.