kimi-delegate

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Kimi Delegate

Kimi 任务委托

You are the orchestrator. Hand a bounded coding task to a separate implementer - the Kimi Code CLI - then review what it produced and land it yourself. You write the brief and own the judgment; Kimi does the typing in its own session; you verify and commit.

The loop needs only a shell command and file access, so any comparable orchestrator can drive it.

你作为协调者，将一个明确范围的编码任务交给独立的实现工具——Kimi Code CLI——之后审核其产出内容并自行完成提交。由你撰写任务简报并负责判断；Kimi在独立会话中完成代码编写；你进行验证并提交。

此流程仅需要shell命令和文件访问权限，因此任何类似的协调工具都可以驱动它。

When NOT to use this

何时不使用此方法

The task is small enough to do inline; delegation overhead is not worth it.
The
```
kimi
```
CLI is not installed or authenticated.
You need a CLI-enforced read-only implementer. Headless Kimi has no read-only mode.

任务规模小到足以直接完成；委托的开销得不偿失。
未安装或未认证
```
kimi
```
CLI。
你需要一个CLI强制的只读实现工具。无头模式的Kimi没有只读模式。

Prerequisites (check once)

前提条件（仅需检查一次）

Install Kimi Code with
```
brew install kimi-code
```
on macOS/Linux, or use the native installer from the official Kimi Code documentation.
Authenticate with
```
kimi login
```
(device-code flow, no TUI), or use
```
/login
```
in the TUI.
Confirm
```
kimi --version
```
succeeds.
Work in, or point
```
--cd
```
at, the target git repository.

在macOS/Linux上使用
```
brew install kimi-code
```
安装Kimi Code，或从Kimi Code官方文档下载原生安装包。
使用
```
kimi login
```
进行认证（设备码流程，无TUI），或在TUI中使用
```
/login
```
。
确认
```
kimi --version
```
命令执行成功。
在目标git仓库中工作，或使用
```
--cd
```
参数指定目标git仓库路径。

Choose the model alias

选择模型别名

Kimi uses

default_model

from its

config.toml

when

--model

is omitted. To choose another model alias, pass

--model <alias from your kimi config>

. Model aliases are user-defined config keys; use one the human has configured rather than inventing one.

当省略

--model

参数时，Kimi会使用其

config.toml

中的

default_model

。要选择其他模型别名，请传递

--model <你的kimi配置中的别名>

。模型别名是用户自定义的配置键；请使用人类已配置的别名，而非自行创建。

The loop

流程循环

Run these five steps per task. Steps 1, 4, and 5 require judgment; 2 and 3 are mechanical.

每个任务都需要执行以下五个步骤。步骤1、4和5需要判断；步骤2和3是机械操作。

1. Write the brief

1. 撰写任务简报

Kimi sees only the text you send plus what it can inspect in the workspace - no chat history or shared context. Include the goal, current state, what to change, what to leave untouched, the project's actual gates, and a report contract. Tell Kimi not to commit. Keep one task per brief. See references/writing-the-brief.md.

Kimi只能看到你发送的文本以及它可以在工作区中检查的内容——无聊天历史或共享上下文。请包含目标、当前状态、需要修改的内容、需要保留不变的内容、项目的实际准入标准，以及报告约定。告知Kimi不要提交。每个简报对应一个任务。详见references/writing-the-brief.md。

2. Dispatch

2. 分发任务

Use the bundled helper. It wraps Kimi's headless prompt mode, captures the structured event stream, and writes

result.json

. (

<skill-dir>

is the installed folder containing this

SKILL.md

bash

node "<skill-dir>/scripts/relay.mjs" --brief brief.txt --cd /path/to/repo

使用内置的辅助工具。它封装了Kimi的无头提示模式，捕获结构化事件流，并写入

result.json

。（

<skill-dir>

是包含此

SKILL.md

的安装文件夹。）

bash

node "<skill-dir>/scripts/relay.mjs" --brief brief.txt --cd /path/to/repo

choose a configured model alias: add --model <alias from your kimi config>

选择已配置的模型别名: 添加 --model <你的kimi配置中的别名>

resume the most recent session: add --resume-last (delta brief only)

恢复最近的会话: 添加 --resume-last （仅需增量简报）

resume a specific session: add --session <id> (delta brief only)

恢复特定会话: 添加 --session <id>（仅需增量简报）

hard time limit (watchdog): add --timeout 2h (the 30m default suits short runs; implementation briefs routinely need 1-2h)

硬时间限制（监控机制）: 添加 --timeout 2h （默认30分钟适合短任务；实现类简报通常需要1-2小时）

see all options: node .../relay.mjs --help

查看所有选项: node .../relay.mjs --help


The child process's cwd pins the workspace. Use repeatable `--add-dir` flags only for extra workspace
directories. The relay writes artifacts under the system temp dir by default and never commits. See
[references/dispatch-and-poll.md](references/dispatch-and-poll.md).


子进程的当前工作目录固定为工作区。仅当需要额外工作区目录时，使用可重复的`--add-dir`参数。默认情况下，中继工具会将产物写入系统临时目录，且绝不会提交。详见[references/dispatch-and-poll.md](references/dispatch-and-poll.md)。

3. Wait for completion

3. 等待完成

The helper blocks until Kimi finishes. Run it with the orchestrator's background-command facility, or background it in the shell and poll for

result.json

. A pre-run usage error exits 2 and writes no result; a missing

kimi

exits 127 and writes

status: "kimi_unavailable"

Trust process state and the working tree over a progress display. Completion means the process exited and

result.json

exists. Kimi's full report is the

finalMessage

field in

result.json

(also printed in full on stdout between the report markers).

辅助工具会阻塞直到Kimi完成任务。可以使用协调工具的后台命令功能运行它，或在shell中将其置于后台并轮询

result.json

。预运行时的使用错误会以状态码2退出且不写入结果；若缺少

kimi

则以状态码127退出并写入

status: "kimi_unavailable"

。

优先信任进程状态和工作树而非进度显示。完成意味着进程已退出且

result.json

已存在。Kimi的完整报告位于

result.json

的

finalMessage

字段中（也会在报告标记之间完整打印到标准输出）。

4. Review - do not trust the self-report

4. 审核——不要信任自我报告

Treat Kimi's final message and gate claims as claims:

Re-run the project's gates yourself.
Read the diff against the brief, starting with
```
touchedFiles
```
.
Run relevant guard skills if installed.
Round-trip migrations and grep for dangling references after removals or renames.

See references/review-and-land.md.

将Kimi的最终消息和准入标准声明视为待验证的主张：

自行重新运行项目的准入标准检查。
根据任务简报阅读代码差异，从
```
touchedFiles
```
开始。
若已安装相关防护工具，则运行它们。
在删除或重命名后，往返迁移并 grep 查找悬空引用。

详见references/review-and-land.md。

5. Land it

5. 完成提交

The implementer edits the working tree; the orchestrator commits. Commit only after the gates pass and the diff holds. If rework is needed, send a delta brief with

--resume-last

--session <id>

, then review again.

实现工具会编辑工作树；由协调者提交。仅当准入标准检查通过且代码差异符合要求时再提交。若需要返工，请使用

--resume-last

或

--session <id>

发送增量简报，之后再次审核。

Autonomy and permissions

自主性与权限

In headless

-p

mode, Kimi always runs in auto permission mode and never asks for approval. Kimi rejects

--prompt

combined with

--yolo

--auto

, or

--plan

, so the relay passes none of them and offers no

--read-only

--full-access

option. There is no CLI-enforced read-only mode: inspect

touchedFiles

and the diff after every run. That diff, not a flag, is the guarantee of what changed.

在无头

-p

模式下，Kimi始终运行在自动权限模式，绝不会请求批准。Kimi拒绝将

--prompt

与

--yolo

、

--auto

或

--plan

结合使用，因此中继工具不会传递这些参数，也不提供

--read-only

或

--full-access

选项。不存在CLI强制的只读模式：每次运行后检查

touchedFiles

和代码差异。该差异而非某个标志，才是变更内容的保障。

Authorization model

授权模型

Delegation is something the human opts into. Once they have ("run this queue", "proceed"), committing verified, gate-passing work is the agreed contract. Two limits remain: surface, don't absorb (report Kimi's design decisions, defensible-but-unasked turns, and non-blocking nitpicks) and stop for scope changes (if correct completion needs going beyond the brief, ask instead of expanding the mandate). See references/review-and-land.md.

委托是人类主动选择的操作。一旦他们选择（如“运行此队列”、“继续”），提交经过验证且符合准入标准的工作就是约定的契约。仍有两个限制：披露而非隐瞒（报告Kimi的设计决策、合理但未被要求的变更，以及不影响功能的小问题）和范围变更时停止（若正确完成任务需要超出简报范围，应先询问而非扩大任务权限）。详见references/review-and-land.md。

References

参考资料

references/writing-the-brief.md - structure, report contract, real gates, argv delivery, and delta briefs.
references/dispatch-and-poll.md - flags, artifacts,
```
result.json
```
, polling, and failure recovery.
references/review-and-land.md - review checklist, commit boundary, and rework through Kimi sessions.
references/multi-task-queues.md - sequential queues, constraint carry-forward, progress tracking, and the final coherence pass.

references/writing-the-brief.md - 结构、报告约定、实际准入标准、参数传递和增量简报。
references/dispatch-and-poll.md - 参数、产物、
```
result.json
```
、轮询和故障恢复。
references/review-and-land.md - 审核清单、提交边界，以及通过Kimi会话进行返工。
references/multi-task-queues.md - 顺序队列、约束传递、进度跟踪和最终一致性检查。