MoonshotAI · RealKai42 · Mar 18, 2026 · Mar 18, 2026 · devin-ai-integration · Mar 18, 2026
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -11,8 +11,10 @@ Only write entries that are worth mentioning to users.
 
 ## Unreleased
 
+## 1.24.0 (2026-03-18)
+
 - Shell: Increase pasted text placeholder thresholds to 1000 characters or 15 lines (previously 300 characters or 3 lines), making voice/typeless workflows less disruptive
-- Core: Plan mode now supports multiple selectable approach options — when the agent's plan contains distinct alternative paths, `ExitPlanMode` can present 2–4 labeled choices for the user to pick which approach to execute; the chosen option is returned to the agent as the selected approach
+- Core: Plan mode now supports multiple selectable approach options — when the agent's plan contains distinct alternative paths, `ExitPlanMode` can present 2–3 labeled choices for the user to pick which approach to execute; the chosen option is returned to the agent as the selected approach
 - Core: Persist plan session ID and file path across process restarts — the plan session identifier and file slug are saved to `SessionState`, so restarting Kimi Code mid-plan resumes the same plan file in `~/.kimi/plans/` instead of creating a new one
 - Core: Plan mode now supports incremental plan edits — the agent can use `StrReplaceFile` to surgically update sections of the plan file instead of rewriting the entire file with `WriteFile`, and non-plan file edits are now hard-blocked rather than requiring approval
 - Core: Defer MCP startup and surface loading progress — MCP servers now initialize asynchronously after the shell UI starts, with live progress indicators showing connection status; Shell displays connecting and ready states in the status area, Web shows server connection status

diff --git a/docs/en/customization/mcp.md b/docs/en/customization/mcp.md
@@ -108,9 +108,9 @@ kimi --mcp-config '{"mcpServers": {"test": {"url": "https://..."}}}'
 
 ## Loading status
 
-When Kimi Code CLI starts and connects to MCP servers, shell mode displays a "Connecting to MCP servers..." loading indicator before the first response. The web interface also shows a corresponding status message. The indicator disappears automatically once connections are established.
+MCP servers initialize asynchronously after the shell UI starts, so the interface is usable immediately. The shell status bar shows live connection progress, automatically switching to a ready state once all servers are connected. The web interface also reflects each server's connection status in real time.
 
-If multiple MCP servers are configured, the loading time may be longer. The loading indicator helps you understand the current status.
+If multiple MCP servers are configured, loading may take a moment. The status bar progress indicator keeps you informed while connections are being established.
 
 ## Security
 

diff --git a/docs/en/guides/interaction.md b/docs/en/guides/interaction.md
@@ -81,6 +81,8 @@ While the AI is executing a task, you can type and send follow-up messages in th
 
 Steer messages are appended to the context after the current step completes, and the AI will see and respond to your message before the next step begins. Approval requests and question panels are also handled inline with keyboard navigation during agent execution.
 
+Any text you type in the input box during a turn but haven't yet submitted is preserved when the turn ends — it won't be lost. You can press `Enter` to send it as the next message, or continue editing.
+
 ::: tip
 Steer messages do not interrupt the AI's currently executing step — they are processed between steps. To interrupt immediately, use `Ctrl-C`.
 :::

diff --git a/docs/en/release-notes/changelog.md b/docs/en/release-notes/changelog.md
@@ -4,6 +4,8 @@ This page documents the changes in each Kimi Code CLI release.
 
 ## Unreleased
 
+## 1.24.0 (2026-03-18)
+
 - Shell: Increase pasted text placeholder thresholds to 1000 characters or 15 lines (previously 300 characters or 3 lines), making voice/typeless workflows less disruptive
 - Core: Plan mode now supports multiple selectable approach options — when the agent's plan contains distinct alternative paths, `ExitPlanMode` can present 2–3 labeled choices for the user to pick which approach to execute; the chosen option is returned to the agent as the selected approach
 - Core: Persist plan session ID and file path across process restarts — the plan session identifier and file slug are saved to `SessionState`, so restarting Kimi Code mid-plan resumes the same plan file in `~/.kimi/plans/` instead of creating a new one

diff --git a/docs/zh/customization/mcp.md b/docs/zh/customization/mcp.md
@@ -108,9 +108,9 @@ kimi --mcp-config '{"mcpServers": {"test": {"url": "https://..."}}}'
 
 ## 加载状态
 
-当 Kimi Code CLI 启动并连接 MCP 服务器时，Shell 模式会在首次响应前显示 "Connecting to MCP servers..." 加载指示器，Web 界面也会显示相应的加载状态提示。连接完成后指示器自动消失。
+MCP 服务器在 Shell UI 启动后异步初始化，不会阻塞界面的使用。Shell 底部状态栏会实时显示连接进度，连接完成后自动切换为就绪状态。Web 界面也会同步显示各服务器的连接状态。
 
-如果配置了多个 MCP 服务器，加载时间可能较长，此时加载指示器可以帮助你了解当前状态。
+如果配置了多个 MCP 服务器，加载时间可能较长，状态栏的进度指示可以帮助你了解当前连接情况。
 
 ## 安全性
 

diff --git a/docs/zh/release-notes/changelog.md b/docs/zh/release-notes/changelog.md
@@ -4,6 +4,8 @@
 
 ## 未发布
 
+## 1.24.0 (2026-03-18)
+
 - Shell：提高长文本粘贴自动折叠阈值至 1000 字符或 15 行（之前为 300 字符或 3 行），改善语音/无键盘输入等场景下的体验
 - Core：Plan 模式现在支持多选方案——当 Agent 的计划包含多个不同路径时，`ExitPlanMode` 可展示 2–3 个带标签的选项供用户选择执行哪一个方案；用户选择的方案会作为选定路径返回给 Agent
 - Core：跨进程重启持久化 Plan 会话 ID 和文件路径——Plan 会话标识符和文件 slug 保存到 `SessionState`，重启 Kimi Code 后会继续使用 `~/.kimi/plans/` 下的同一计划文件，而非创建新文件

diff --git a/packages/kimi-code/pyproject.toml b/packages/kimi-code/pyproject.toml
@@ -1,10 +1,10 @@
 [project]
 name = "kimi-code"
-version = "1.23.0"
+version = "1.24.0"
 description = "Kimi Code is a CLI agent that lives in your terminal."
 readme = "README.md"
 requires-python = ">=3.12"
-dependencies = ["kimi-cli==1.23.0"]
+dependencies = ["kimi-cli==1.24.0"]
 
 [project.scripts]
 kimi-code = "kimi_cli.__main__:main"

diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "kimi-cli"
-version = "1.23.0"
+version = "1.24.0"
 description = "Kimi Code CLI is your next CLI agent."
 readme = "README.md"
 requires-python = ">=3.12"

diff --git a/uv.lock b/uv.lock
-Original file line number
+Diff line change
@@ Expand Up @@
     Steer messages are appended to the context after the current step completes, and the AI will see and respond to your message before the next step begins. Approval requests and question panels are also handled inline with keyboard navigation during agent execution.
+    Any text you type in the input box during a turn but haven't yet submitted is preserved when the turn ends — it won't be lost. You can press `Enter` to send it as the next message, or continue editing.
     ::: tip
     Steer messages do not interrupt the AI's currently executing step — they are processed between steps. To interrupt immediately, use `Ctrl-C`.
     :::
@@ Expand Down @@