mirror of
https://github.com/MoonshotAI/kimi-code.git
synced 2026-07-10 01:39:25 +00:00
02da587795
* feat(agent-core): guide the model away from repeating denied or failed tool calls - system.md: add a diagnose-before-retrying paragraph next to the existing permission-denial guidance, covering failed tool calls - permission: when the user rejects an approval on the main agent, tell the model not to re-attempt the exact same call (sub agents already had an equivalent hint) * fix(agent-core): close abandoned tool exchanges and dedupe duplicate tool_use ids A turn that dies between a recorded tool.call and its paired tool.result (e.g. a transcript write failure mid-batch) used to leave pendingToolResultIds open forever: every later message was stranded in deferredMessages and user input was silently swallowed. - runOneTurn now defensively closes any dangling tool calls when a turn ends (completed, cancelled, or failed), synthesizing an error result that names the cause, with a warn log and a tool_exchange_abandoned telemetry event - the projector drops assistant tool calls whose id already appeared earlier (first occurrence wins): a duplicate id is wire-invalid on strict providers and not repairable by the strict resend; reported via the existing projection-repair log and telemetry - resume-side closePendingToolResults now logs what it closes (warn for a mid-history gap, info for the routine trailing interruption) * chore: add changesets for tool exchange fixes * fix(agent-core): scope duplicate tool_use id dedup to the strict resend Unconditional dedup regressed providers that emit per-response counter ids (e.g. call_0 in every step) and accept their own duplicates: later tool exchanges silently vanished from the projected history, and a duplicate call's own recorded result was left dangling. - the dedupe pass is now opt-in via dedupeDuplicateToolCalls and enabled only in strictMessages, so the normal projection keeps the history the provider produced - the pass also drops every tool result after the first for an id, so no dangling tool message survives; when the kept call has no result of its own, the surviving one is reattached by the adjacency repair - kosong now classifies the Anthropic "tool_use ids must be unique" 400 as a recoverable request-structure error so it triggers the strict resend * feat(cli): wait for background subagents before exiting kimi -p When `background.keep_alive_on_exit` is enabled, `kimi -p` now waits for all background subagents to reach a terminal state before exiting, bounded by `background.print_wait_ceiling_s` (default 3600s). This lets concurrent background subagents run to completion in single-turn runs instead of being torn down when the main agent's turn ends. |
||
|---|---|---|
| .. | ||
| scripts | ||
| src | ||
| test | ||
| .gitignore | ||
| AGENTS.md | ||
| CHANGELOG.md | ||
| package.json | ||
| README.md | ||
| tsconfig.dev.json | ||
| tsconfig.json | ||
| tsdown.config.ts | ||
| tsdown.native.config.ts | ||
| vitest.config.ts | ||
@moonshot-ai/kimi-code
The Starting Point for Next-Gen Agents
What is Kimi Code CLI
Kimi Code CLI is an AI coding agent that runs in your terminal. It can read and edit code, run shell commands, search files, fetch web pages, and choose the next step based on the feedback it receives. It works out of the box with Moonshot AI's Kimi models and can also be configured to use other compatible providers.
Install
The recommended install path is the official script. It does not require Node.js to be installed first.
- macOS / Linux:
curl -fsSL https://code.kimi.com/kimi-code/install.sh | bash
- Windows (PowerShell):
irm https://code.kimi.com/kimi-code/install.ps1 | iex
On Windows, install Git for Windows before first launch because Kimi Code CLI uses the bundled Git Bash as its shell environment. If Git Bash is installed in a custom location, set
KIMI_SHELL_PATHto the absolute path ofbash.exe.
Then run it with a new Terminal session:
kimi --version
Alternative: npm
If you prefer npm, use Node.js 22.19.0 or later:
npm install -g @moonshot-ai/kimi-code
Or with pnpm:
pnpm add -g @moonshot-ai/kimi-code
For upgrade and uninstall instructions, see the Getting Started guide.
Quick Start
Open a project and start the interactive UI:
cd your-project
kimi
On first launch, run /login inside Kimi Code CLI and choose either Kimi Code OAuth or a Kimi Platform API key. After login, try a first task:
Take a look at this project and explain the main directories.
Key Features
- Single-binary distribution. Install with one command — no Node.js setup, no PATH gymnastics, no global module conflicts.
- Blazing-fast startup. The TUI is ready in milliseconds, so opening a session never feels heavy.
- Polished TUI. A carefully tuned interface designed for long, focused agent sessions.
- Video input. Drop a screen recording or demo clip into the chat — let the agent watch instead of typing out what's hard to describe in words.
- AI-native MCP configuration. Add, edit, and authenticate Model Context Protocol servers conversationally via
/mcp-config— no hand-editing JSON. - Subagents for focused, parallel work. Dispatch built-in
coder,explore, andplansubagents in isolated context windows; the main conversation stays clean. - Lifecycle hooks. Run local commands at key points — gate risky tool calls, audit decisions, fire desktop notifications, wire into your own automation.
Documentation
- Full docs: https://moonshotai.github.io/kimi-code/en/
- 中文文档: https://moonshotai.github.io/kimi-code/zh/
- Getting Started: https://moonshotai.github.io/kimi-code/en/guides/getting-started
Repository & Issues
- Source: https://github.com/MoonshotAI/kimi-code
- Issues: https://github.com/MoonshotAI/kimi-code/issues
- Security: see SECURITY.md in the main repository
License
MIT