Changelog

This page documents the changes in each Kimi Code CLI release.

2.0.2 (2026-09-19)

Polish

• The agent no longer assumes the current working directory is the project root.

Bug Fixes

• Fix compaction failing after switching to a model with a smaller context window.
• Fix new messages occasionally landing at an old position in the conversation after resuming a session.
• Fix a message sent while the agent was running sometimes appearing twice in the chat.
• web: Improved interactions and fixed known bugs.

2.0.1 (2026-09-18)

Polish

• Remove the system-prompt rule that forbade all file access outside the working directory.
• Providers can read their API key from a named environment variable via api_key_env in config.toml.
• Stop workspace file watchers from scanning an unbounded project root, and add [watch] enabled / KIMI_CODE_WATCH to disable watching entirely. See watch for details.
• Stop asking for approval of bash commands that cannot be statically analyzed in Ask When Needed permission mode.
• Rename the kimi install-app subcommand to kimi install-desktop; the old name keeps working as a hidden alias.

Bug Fixes

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

2.0.0 (2026-09-17)

Features

• Add the /desktop slash command (alias /install-desktop) and the kimi install-app subcommand.
• Render mermaid code blocks as diagrams in the terminal; turn it off under /settings → Mermaid diagrams, or set mermaid = "off" in the [markdown] section of tui.toml.

Polish

• The built-in browser plugin now appears as "Kimi Browser Extension" in the plugins panel, marketplace catalog, and docs, matching the product rename.

Bug Fixes

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

0.43.1 (2026-09-15)

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.

0.43.0 (2026-09-14)

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.

0.42.0 (2026-09-09)

Features

• Remote Control is now always on; the experimental KIMI_CODE_EXPERIMENTAL_REMOTE_CONTROL flag has been removed. See Remote Control for details.
• web: Support permanently deleting sessions from the session row context menu, with a confirmation prompt.
• Add read-only tools to the /btw side agent.
• web: Preview images and videos in a reorderable media rail in the composer, mention them in the text on demand, and keep the previews after queueing and sending.
• Accept HEIC, HEIF, and BMP images in prompt attachments and ReadMediaFile when the model is served by Kimi.

Polish

• Collapse finished tool calls in the transcript to a header plus one marked outcome row: short output is shown whole, hidden output is counted (N more lines, +N more) and revealed by Ctrl-O, which the footer advertises while it is available.
• Upgrade the default thinking effort to the recommended level for eligible users.
• The subagent model pool ([secondary_model]) is now always on; the experimental secondary-model flag and the KIMI_CODE_EXPERIMENTAL_SECONDARY_MODEL opt-out have been removed.
• Add configurable character limits and resumable long-line file reads without repeated output truncation; see read for details.
• The minidb session-index read model and global search worker are now always on; the experimental flags have been replaced by the [database] config section and the KIMI_CODE_PERSISTENCE_MINIDB_READMODEL / KIMI_CODE_SEARCH_WORKER env vars; see database for details.

Bug Fixes

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

0.41.0 (2026-09-04)

Features

• web: Add tower multi-agent collaboration mode (experimental), enabled via the /tower command or the composer plus menu; /tower supports specifying a base branch (e.g. /tower add-new-feature).
• web: Add selection annotation — select text in messages, file previews, the diff and per-turn changes panels, or the terminal to add a comment or quote it into the chat.
• CLI: Add a session rating prompt that invites you to rate the session at appropriate times above the input box.

Polish

• Auto permission mode no longer blocks dangerous commands and commands that cannot be statically analyzed.
• Remind the model of its context budget before automatic compaction, and after compaction point it at the session's event log for exact details.
• web: Rename the three permission modes to Always Ask / Ask When Needed / Never Ask and update their descriptions; switching to Ask When Needed or Never Ask permission mode now warns that files may be modified or deleted directly in that mode.
• web: Esc no longer closes the right detail panel.
• web: Restyle Bash commands in the right-side panel in terminal style.
• Deliver background question answers to the agent directly instead of via a saved output file.
• Subagent final messages under 200 characters are no longer bounced back for expansion.

Bug Fixes

• Fix print mode (kimi -p) losing session records when the run exits on an error or a termination signal.
• Fix print mode (kimi -p) ignoring the KIMI_DISABLE_TELEMETRY environment variable.
• Tower mode (experimental): fix tower mode never starting when enabled through [experimental] tower = true in config.toml instead of the environment variable, and make /tower work in directories that are not git repositories; enablement errors now name the actual blocker.
• Fix background questions being cancelled as soon as the agent finishes its turn.
• Fix resuming a subagent by its agent id after the session is reopened in a new process; the resumed subagent follows the current permission mode and is matched by its own profile in permission rules.
• web: Fix per-turn file change previews showing added/removed lines that never existed and inaccurate line counts when the same file is edited multiple times in one turn; change cards now show only exact line statistics.
• web: Fix the default thinking effort in settings not being settable to the highest level (Max).
• Fix several known issues and make various refinements. See the changelog on GitHub for more technical entries.

0.40.1 (2026-09-02)

Bug Fixes

• Fix the condition for showing the kimi-cli migration prompt.

0.40.0 (2026-09-02)

Features

• web: Add a Plugins panel to Settings for browsing the plugin marketplace and installing, enabling, disabling, and removing plugins.
• web: Support activating multiple skills from a single message.
• Add the kimi session list command to list sessions from the command line.
• Tower mode (experimental, KIMI_CODE_EXPERIMENTAL_TOWER=1): the agent no longer enters tower mode on its own — turn it on with /tower on or /tower <base-branch>.
• The subagent model setting ([secondary_model]) graduates from experimental to stable.
• Block dangerous shell commands such as shutdown, reboot, or rm -rf in Auto mode, and always ask before running them in Manual and YOLO modes; disable the guard with [permission] dangerous_command_guard = false or KIMI_CODE_DANGEROUS_COMMAND_GUARD=false.

Polish

• Preserve comments, key order, and formatting in config.toml when configuration values are updated.
• Remove the workspace restriction on the Bash tool's cwd parameter.
• Default the workspace trust prompt selection to "Trust this folder" instead of "Don't trust".
• The kimi acp subcommand no longer honors KIMI_CODE_LEGACY_FLAG; it always runs on the default agent engine.
• web: Add a code wrap toggle to the diff panel and streamline its header.

Bug Fixes

• Honor explicit [experimental] config entries over the KIMI_CODE_EXPERIMENTAL_FLAG master switch, so a flag set to false in config.toml stays off; per-feature KIMI_CODE_EXPERIMENTAL_<NAME> variables still override both.
• Fix several known issues and make various refinements. See the changelog on GitHub for more technical entries.

0.39.1 (2026-08-28)

Bug Fixes

• web: Fix switching the permission mode in one session changing it for every session; the permission mode is now scoped per session.
• web: Fix signed-in users without a usable model being wrongly asked to sign in (and getting stuck there on web); the send gate now offers picking or configuring a model instead.
• web: Fix the first IME (or keyboard) character being silently swallowed after clicking the composer placeholder.
• web: Fix attachments in a newly created session still showing as uploading after the upload has finished.
• Fix several known issues and make various refinements. See the changelog on GitHub for more technical entries.

0.39.0 (2026-08-27)

Features

• Add Remote Control as an experimental feature for accessing a local web session remotely. Enable it with KIMI_CODE_EXPERIMENTAL_REMOTE_CONTROL=1, then run kimi rc, kimi web --remote-control, or /remote-control to start it.
• Add experimental tower mode for multi-agent orchestration; set KIMI_CODE_EXPERIMENTAL_TOWER=1, then run /tower on and /tower <objective> to start.
• Add an optional fork parameter to subagent and swarm tools that starts the subagent with a snapshot of the calling agent's conversation history; set KIMI_CODE_EXPERIMENTAL_SUBAGENT_FORK=1 or subagent_fork = true under [experimental] in config.toml to enable it.
• web: Allow moving a running foreground Bash command or subagent to the background via the "Move to background" button on the running card.
• web: Add a flat/by-workspace tab to the mobile session list.
• Add the Tencent CloudBase plugin to the curated marketplace.
• Add a dedicated [swarm] timeout_ms config option (or the KIMI_CODE_SWARM_TIMEOUT_MS env var) for AgentSwarm subagent timeouts, which no longer follow [subagent] timeout_ms.

Polish

• web: Revamp the right sidebar as a multi-tab panel.
• web: Improve composer interaction, including the presentation of file, folder, and media attachments.
• web: Improve mobile UI styling.

Bug Fixes

• Fix file tools and shell working directories failing to resolve Git Bash paths such as /c/Users or /tmp on Windows.
• Fix several known issues and make various refinements. See the changelog on GitHub for more technical entries.

0.38.0 (2026-08-20)

Features

• Support two OAuth login methods — kimi.ai and kimi.com.
• Add the WaitFor tool: the agent can now wait for a background task to finish within the current turn instead of ending the turn and being re-invoked.
• Add 13 data sources to the official Kimi Datasource plugin — Chinese government data (NDA/NBS) and standards (GB/HB/DB/TT), eight international organization datasets (WHO, FAO, UNSD, ECB, Eurostat, UNICEF, OECD, FRED), Xinhua Finance, and Caixin. Update the plugin from the Official tab in /plugins.
• web: Add a Pin action to the chat header more-menu.

Polish

• Edit and Write now require reading an existing file before modifying it.

• Collapse long ! shell command output instead of flooding the transcript. Press ctrl+o to expand or collapse it together with tool output.

Bug Fixes

• Fix config.toml entries being lost when the file had a syntax error or was edited outside the app.
• Fix several known issues and make various refinements. See the changelog on GitHub for more technical entries.

0.37.2 (2026-08-19)

Polish

• web: Settings gains a Lab tab with a new multi-tab sidebar toggle; when enabled, the sidebar shows the Open / Done / Workspaces tabs.
• Make several refinements and internal improvements. See the changelog on GitHub for more technical entries.

0.37.1 (2026-08-18)

Bug Fixes

• Fix pasted images and videos failing to reach the model.

0.37.0 (2026-08-18)

Features

• Activate multiple skills in a single prompt. Type / after whitespace to insert a skill token.
• The Windows native (single-binary) CLI now supports automatic updates.
• web: The sidebar gains Open / Done / Workspaces tabs, and sessions can be marked as done.
• web: Add a session management page.

Polish

• Queue slash skill commands entered while the agent is busy instead of rejecting them.
• web: @-mentioned files, folders, and skills in chat messages now render as icon pills.
• web: The browser tab title now shows the current workspace directory name.
• web: The search dialog now finds workspaces too, and picking a workspace or session result expands the sidebar and scrolls the item into view.
• web: Renamed the Subagent panel to "Background Agent".
• Warn when a typed /goal objective exceeds the 4000-character limit, and keep the input if it is rejected.

Bug Fixes

• Fix Gemini tool-calling sessions failing on follow-up requests.
• web: Fix Ctrl+K in the composer opening session search on macOS — session search now only answers to Cmd+K.
• web: Fix the Background Agent panel showing incorrect task counts and statuses.
• web: Fix pasting a copied folder into the composer failing the upload with a connection error — folders are now skipped instead.
• Fix several known issues and make various refinements. See the changelog on GitHub for more technical entries.

0.36.1 (2026-08-14)

Features

• web: Generate session titles with AI (experimental). Off by default — set KIMI_CODE_EXPERIMENTAL_AUTO_SESSION_TITLE=1 (or the master flag KIMI_CODE_EXPERIMENTAL_FLAG=1) to turn it on.

Polish

• web: Polish the Plan, Goal, and Swarm toggles in the composer, which now live in the + menu next to the input box.

Bug Fixes

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

0.36.0 (2026-08-13)

Features

• Upgrade the experimental subagent model setting to a model pool: the [secondary_model] section can now hold a set of candidate models with descriptions, and the main agent picks from them per spawn based on the task.

  Set KIMI_CODE_EXPERIMENTAL_SECONDARY_MODEL=1 (or the master flag KIMI_CODE_EXPERIMENTAL_FLAG=1) before starting Kimi to enable it.

  Recommended setups:

  • Minimal: run /secondary-model in the TUI, or write a single default_model line in config.toml, to make every subagent run the same model by default; add force = true to pin that choice so the main agent cannot override it.

  • Declare a named pool with a one-line scenario description for each alias — the descriptions are what the main agent sees when choosing:

    [secondary_model]
    default_model = "kimi-code/kimi-for-coding-highspeed"
    [secondary_model.models]
    "kimi-code/kimi-for-coding-highspeed" = "Fast and cheap — good for daily refactoring, code explanation, and small edits."
    "kimi-code/k3" = "Strong at complex reasoning and deep debugging — pick it for hard problems."

  See the subagent model pool docs for details.

• Add an experimental fullscreen TUI mode. Set the KIMI_CODE_TUI_FULL_SCREEN=1 environment variable to enable it.

• Support rendering LaTeX math formulas ($…$ / $$…$$) in TUI messages as Unicode formulas.

Bug Fixes

• Show project MCP launch targets in the workspace trust prompt, default to declining trust, and resolve fd and stty binaries to absolute paths so untrusted workspaces cannot plant bare-name executables before confirmation.
• Fix sessions failing with a provider 400 error on every follow-up request after a turn is interrupted while the model is still thinking, on strict OpenAI-compatible providers (e.g. DeepSeek).
• Fix Ctrl+C being ignored during automatic retries of failed API requests.
• Fix several known issues and make various refinements. See the changelog on GitHub for more technical entries.

0.35.0 (2026-08-12)

Features

• Add the Modern Web Guidance plugin to the bundled plugin marketplace. Run /plugins and select Modern Web Guidance to install it.
• Show the live work progress of background subagents in the /tasks panel.

Bug Fixes

• Fix coder subagents spawning further subagents by default.
• Fix the token counts reported after compaction reading far below the real context size; they now match the numbers shown while the session runs.
• Fix two binary-planting risks on Windows.
• Fix several known issues and make various refinements. See the changelog on GitHub for more technical entries.

0.34.0 (2026-08-06)

Features

• web: Add a flat view to the sidebar session list.
• The Kimi Computer Use plugin now supports Windows x64 — install it from /plugins.
• Show a cache-expiry reminder when resuming or sending after a long idle. Set cache_expiry_hint to false to disable it.

Polish

• web: Subagent tasks show their model and thinking level.
• web: Show a failure card with one-click resume when a model request fails.
• web: Show retry progress (attempt N of M) in the working status during automatic retries.
• Show browser extension links and activation steps after installing Kimi WebBridge.

Bug Fixes

• Fix UTF-16 LE/BE text files (with or without a BOM) failing to load.
• web: Fix attachments being dropped when sent with a skill command.
• web: Fix the model picker overflowing the screen when many models are available.
• web: Fix a file path with spaces opening the Documents folder instead of the file on Windows.
• web: Fix the thinking level resetting to the model default when a new session starts with a skill command.
• web: Fix manually cancelled sessions showing an error marker in the sidebar; it now appears only when the last turn failed.
• web: Fix IME composition while renaming a session — Enter and Esc no longer act mid-composition.
• web: Fix dragging to select text while renaming moving the whole list item.
• web: Fix the background-tasks and todos pills jumping to the top when the plan approval dialog expands.
• web: Fix the chevron direction on the "show less" button of the changed-files summary card.
• Fix kimi -p exiting before background tasks and subagents finish.
• /feedback now works for signed-in users on any model; signed-out users see the sign-up page and GitHub Issues links.
• Fix removing an MCP server breaking open sessions: its tools stay visible but calls fail with a removal notice.
• Fix the last turn's outcome being lost across server restarts — failed turns now stay flagged in session lists and resumed sessions.
• Fix resumed sessions showing background-task completion as raw protocol text instead of a status card.

0.33.0 (2026-08-05)

Features

• Add Kimi Computer Use and Kimi WebBridge as built-in official marketplace entries in the v2 CLI. Installing from /plugins sets up the latest managed runtime and plugin together, reports incomplete manual steps, and supports retrying interrupted setup.
• web: Add and manage custom providers in settings.
• web: Pin sessions to the top of the sidebar.
• web: Set an emoji for the session title.
• web: Show the signed-in account and plan usage.
• Add /bug as an alias for the /feedback slash command. Type /bug to submit feedback.

Polish

• Ask whether to trust the current folder on startup.
• /fork no longer switches to the forked session: the current session stays active and its background tasks keep running. Find the fork in /sessions.
• web: Overhaul the UI/UX and fix known issues.
• Start the interactive TUI without creating a session.
• Rename the partner plugin marketplace tab to Curated and clarify that it contains third-party plugins from Kimi partners.

Bug Fixes

• Fix all tool calls failing with spawn EBADF on macOS when a skill folder contains a very large file tree.
• Fix MCP OAuth re-authorization always failing with "Invalid redirect URI"; the stale client registration is now dropped and re-created with the current callback URI.
• Ensure the first request waits for MCP startup to finish while the interface still opens immediately.
• MCP tool results now surface the spec-defined structuredContent field and _meta server metadata to the model instead of silently dropping them, so servers that return their machine-readable contract in these fields work the same as on other MCP hosts.
• Fix built-in capability availability and installed status in /plugins, preserve legacy WebBridge skills as backups during updates, and prevent Computer Use updates from duplicating or disconnecting MCP servers.

Refactors

• Run the CLI surfaces (interactive TUI, kimi -p, kimi acp, kimi export, kimi provider) on the agent-core-v2 engine by default. Set KIMI_CODE_LEGACY_FLAG=1 to fall back to the legacy engine.

0.32.0 (2026-08-04)

Features

• Add four hook events: TurnStarted, UserPromptQueued, TaskStarted, and SessionHeartbeat. Configure them under [[hooks]] in config.toml — see Hooks for details.

Polish

• Rename two [loop_control] keys: max_retries_per_step → max_attempts_per_step and max_steps_per_run → max_steps_per_turn; the old keys stop working with a rename warning at startup — see loop_control.
• Add a [token_counting] config section: when a provider doesn't report token usage, switch the context-size display to local estimates — see token_counting.

Bug Fixes

• Fix answers to interactive question prompts being rejected when the model provider returns tool call IDs containing colons (some OpenAI-compatible gateways).
• Fix automatic context compaction getting stuck retrying an oversized request until it fails.
• Fall back to the built-in models.dev catalog snapshot when the public catalog is unreachable, so importing a known provider still works offline or in blocked networks.
• Fix the context window limit showing as 0 when no model is configured; it now falls back to the default model.
• web: Fix dark-mode monochrome controls and align the chat composer corner radius with the design system.
• Fix the /login already-logged-in confirmation being hard to read; it now uses the success color.

0.31.1 (2026-07-31)

Polish

• Reduce frequent full-screen redraws in the TUI.
• Preserve the assistant's partial output when a turn is interrupted with Esc, and remind the model that the previous turn was deliberately interrupted.
• web: Order permission modes from safest to most permissive across settings surfaces, and fix the swapped yolo/auto risk colors in the status panel and mobile settings.
• web: Enable Monaco-based highlighting for code blocks, and fix line numbers overlapping or drifting out of alignment in fallback-rendered code blocks.

Bug Fixes

• Fix sporadic "model is not configured" errors when starting kimi web, caused by the background provider-model refresh transiently clearing the model catalog while the first session was being created.
• web: Fix new sessions showing the thinking level (e.g. Max) while the first message actually ran with thinking off.
• web: Make the @ file mention work in a new-session draft, before the first prompt creates the session.
• web: Fix chat code blocks rendering in the proportional UI font at the wrong size after the markdown renderer upgrade, and align the loading fallback with the highlighted block.

0.31.0 (2026-07-30)

Features

• Support Markdown-defined custom agents on agent-core.
• Add the /secondary_model slash command to configure the secondary model used by subagents (experimental; enable it in /experiments first).
• Plugins can contribute custom agents, discovered automatically and available for sub-agent delegation.
• Plugins can contribute system prompt instructions through systemPrompt or systemPromptPath in kimi.plugin.json.

Bug Fixes

• Remove the blocking block/timeout wait from the TaskOutput tool so checking a background task can no longer stall the conversation; it now always returns an immediate snapshot, and completion still arrives via automatic notification.
• Fix sessions missing from the session picker when their cached metadata predates the archived flag.
• Fix request headers not being passed correctly on some requests.

0.30.0 (2026-07-29)

Features

• Add a customizable footer status line, configured via [status_line] in tui.toml.

Polish

• Show a quota note after installing official plugins that bill against plan quota (such as Kimi Datasource).
• Show a notice when an official plugin used in the session has an update available — run /plugins to update.
• Remove the 50 MB size limit on file uploads to the built-in server.

Bug Fixes

• Fail fast when account quota or balance is exhausted instead of silently retrying for ~3 minutes.
• Stop the turn after repeated invalid tool calls instead of retrying indefinitely.
• web: Fix garbled line numbers in code blocks.

0.29.2 (2026-07-27)

Bug Fixes

• Fix goal pursuit pausing when a goal turn hits the per-turn step limit (loop_control.max_steps_per_turn).
• Fix messages sent during goal pursuit being rejected.
• Fix /undo to restore conversation history, todo lists, plan mode, and task notifications consistently.
• web: Fix copying selected chat text over plain HTTP overwriting the clipboard with an event placeholder.

0.29.1 (2026-07-24)

Features

• Add global default MCP server timeouts in config.toml and env vars.
• Add environment variables to configure the web search and web fetch services without OAuth login.
• Add experimental secondary-model bindings for newly spawned subagents, including per-agent model preferences and subagent-only model overrides.

Bug Fixes

• Fix loss of thinking content with OpenAI-compatible endpoints that return reasoning under a different field name (e.g. newer vLLM).

0.29.0 (2026-07-22)

Features

• web: Support defining agents in Markdown files, declaring system prompt, name, description, and tool permissions. Details
• web: Permanently override the main agent's system prompt with SYSTEM.md. Details
• web: Globally enable or disable tools across all sessions via config.toml. Details
• Videos attached to a prompt now reach the model together with the prompt, with no extra tool round trip.
• Support selecting a thinking effort level from ACP clients.
• Add environment variable overrides for agent loop and background task limits.

Polish

• Import many more providers from the models.dev catalog.
• Improve TUI performance and resume speed for long-running sessions.
• Reconnect a dropped MCP server connection automatically when one of its tools is called, and retry the call once.
• Remove red coloring from syntax highlighting in code previews and markdown code blocks.
• Add a reminder for third-party install sources to use the official installer in the update prompt.

Bug Fixes

• Fix sessions getting stuck with a provider "message must not be empty" error after a content-filtered response.
• Fix cancelled model requests being wrapped as retryable provider errors.
• Fix thinking levels being offered for models that do not support them.
• Fix config environment overrides being persisted into config.toml while the env var is set.
• Send the session prompt cache key to OpenAI and OpenAI Responses providers.
• Fix ReadMediaFile failing on videos when the provider has no file upload channel.
• Fix goal mode continuation prompts leaking into the transcript when resuming a session.
• web: Show transparent images over a checkerboard canvas.
• Remove references to the non-existent kimi resume command from the scheduled-task tool descriptions.

0.28.1 (2026-07-20)

Features

• Allow ACP sessions to start with configured non-OAuth model credentials instead of requiring terminal login.

Polish

• Run web servers foreground-only end to end: the /web slash command now always starts a new server, and the kimi web kill / kimi web ps subcommands are removed — foreground servers stop with Ctrl+C. kimi server kill remains as a deprecated fallback that only stops servers started by a version before 0.28.0.

Bug Fixes

• Fix running subagents not observing permission mode switches made after they started.

0.28.0 (2026-07-20)

Features

• Breaking:
  • The kimi server command tree is deprecated; use kimi web instead.
  • kimi web now runs in the foreground of the current terminal and opens the browser; stop it with Ctrl+C.

Polish

• Thinking effort persists only levels below the model's top tier (max).
• web: Add a note in the model switcher that switching models or thinking effort invalidates the existing prompt cache.

Bug Fixes

• Correct the YOLO and Auto permission mode descriptions: YOLO auto-approves tool actions but the agent may still ask questions, while Auto is fully autonomous and never asks.
• Fix the web backend ignoring symbolic links when loading AGENTS.md files and reading files.

0.27.0 (2026-07-17)

Features

• Add the /copy slash command to copy the last assistant message to the clipboard.
• Using an API key for Kimi coding models now also fetches the latest model list automatically.

Polish

• OAuth connection errors now include the underlying network cause (DNS, refused connection, TLS, or timeout) instead of a bare "fetch failed".

Bug Fixes

• Fix repeated request rejections after an interrupted model response.
• Fix the built-in URL fetch tool's network safeguards: crafted domains and redirect chains can no longer reach loopback or internal network services.
• web: Fix LaTeX formulas