copilot-delegate

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Copilot Delegate

Copilot 委托工作流程

You are the orchestrator. Delegate a bounded coding task to a separate implementer — the GitHub Copilot CLI — then review what it produced and land it yourself. You write the brief and own the judgment; the implementer makes changes in its own session in a clean working tree; 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，将一个边界清晰的编码任务委托给独立的实现工具——GitHub Copilot CLI，之后审核其产出内容并自行完成提交。你撰写任务简报并负责最终判断；实现工具会在干净的工作目录中独立会话进行修改；你负责验证并提交代码。

该流程仅需要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

请勿使用此流程的场景

The task is small enough to do inline; delegation overhead is not worth it.
The
```
copilot
```
CLI is not installed or authenticated.
You need a hard sandbox. Copilot exposes sandbox controls, but they are upstream-experimental (MXC-based, controlled via the
```
/sandbox
```
command and settings, disabled by default) — this relay does not configure them.
```
--read-only
```
only disables edit tools (
```
--mode plan
```
); shell commands still run. If project files must not change at all, dispatch against a clean or isolated worktree.

任务足够简单可直接完成；委托带来的额外开销得不偿失。
未安装或未认证
```
copilot
```
CLI。
需要严格的沙箱环境。Copilot提供沙箱控制功能，但属于上游实验性特性（基于MXC，通过
```
/sandbox
```
命令和设置控制，默认禁用）——本中继工具不会配置这些特性。
```
--read-only
```
仅会禁用编辑工具（
```
--mode plan
```
模式）；Shell命令仍可运行。如果项目文件绝对不能被修改，请在干净或隔离的工作目录中执行任务。

Prerequisites (check once)

前置条件（只需检查一次）

Install
```
copilot
```
(
```
npm install -g @github/copilot
```
; the CLI requires Node 22+, the relay itself runs on Node 18+ — the relay probes
```
copilot version
```
).
Authenticate: run
```
copilot login
```
(interactive web/device flow), or set
```
COPILOT_GITHUB_TOKEN
```
/
```
GH_TOKEN
```
/
```
GITHUB_TOKEN
```
in the environment.
Confirm
```
copilot version
```
succeeds.
Work in, or point
```
--cd
```
at, the target git repository.

安装
```
copilot
```
（执行
```
npm install -g @github/copilot
```
；CLI需要Node 22+版本，中继工具本身可在Node 18+版本运行——中继工具会检测
```
copilot version
```
）。
认证：执行
```
copilot login
```
（交互式网页/设备验证流程），或在环境变量中设置
```
COPILOT_GITHUB_TOKEN
```
/
```
GH_TOKEN
```
/
```
GITHUB_TOKEN
```
。
确认
```
copilot version
```
命令可成功执行。
在目标git仓库中工作，或通过
```
--cd
```
参数指定目标仓库路径。

Choose the model (optional)

选择模型（可选）

Copilot picks a default model (

auto

). To choose another, pass

--model <name>

. The relay accepts letters, digits, and

. _ : / -

only (the value reaches a shell on Windows).

Copilot会选择默认模型（

auto

）。如需选择其他模型，传递

--model <name>

参数。中继工具仅接受字母、数字以及

. _ : / -

字符（该参数值会传递给Windows系统的Shell）。

Choose the effort (optional)

选择推理强度（可选）

Copilot supports a reasoning effort dial:

--effort <level>

with values

low

medium

high

xhigh

, or

max

. The relay rejects any other value before dispatch.

Copilot支持推理强度调节：使用

--effort <level>

参数，可选值为

low

、

medium

、

high

、

xhigh

或

max

。中继工具在执行前会拒绝其他任何值。

The loop

工作循环

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

每个任务执行以下五个步骤。步骤1、4、5需要人工判断；步骤2、3为机械操作。

1. Write a brief

1. 撰写任务简报

Copilot sees only the text you send. It cannot read your conversation: the brief must stand alone with the goal, current state, what to change, what to leave untouched, the project's real gates, and a report contract. Keep each brief to a single task. Write it to a file and pass it as the relay's

--brief

. See references/writing-the-brief.md.

Copilot只能看到你发送的文本内容，无法读取你的对话记录：任务简报必须独立包含目标、当前状态、需要修改的内容、需要保留的内容、项目的实际校验规则，以及报告要求。每份简报对应单个任务。将简报写入文件并通过中继工具的

--brief

参数传递。详见references/writing-the-brief.md。

2. Dispatch

2. 任务分发

Use the bundled relay. It runs

copilot -p

with

--output-format json --no-color --stream off

, captures the JSONL event stream, and writes

result.json

bash

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

使用内置的中继工具。它会运行

copilot -p

并附带

--output-format json --no-color --stream off

参数，捕获JSONL事件流并写入

result.json

文件。

bash

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

choose a model: add --model <name>

选择模型: 添加 --model <name>

set reasoning effort: add --effort <level>

设置推理强度: 添加 --effort <level>

read-only planning pass: add --read-only (forces --mode plan)

只读规划模式: 添加 --read-only （强制使用--mode plan模式）

full tool autonomy: add --allow-all-tools

完全工具自主权: 添加 --allow-all-tools

hard time limit (watchdog): add --timeout 2h (the 30m default suits brief runs)

强制时间限制（监控）: 添加 --timeout 2h （默认30分钟适合短任务）

resume a session: add --session <id> or --resume-last

恢复会话: 添加 --session <id> 或 --resume-last

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

查看所有选项: node .../relay.mjs --help


The child's cwd pins the workspace. 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会固定为目标工作区。中继工具默认将产物写入系统临时目录，且绝不会自动提交代码。详见[references/dispatch-and-poll.md](references/dispatch-and-poll.md)。

3. Wait for completion

3. 等待任务完成

The relay blocks until copilot 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

copilot

exits 127 and writes

status: "copilot_unavailable"

Completion means the process exited and

result.json

exists — trust process state and the working tree, not the progress display. Copilot's final assistant message is the

finalMessage

field of

result.json

中继工具会阻塞直到copilot完成任务。可通过协调工具的后台命令功能运行它，或在Shell中后台运行并轮询

result.json

文件。预运行时的使用错误会以退出码2结束且不会写入结果；若

copilot

未安装则以退出码127结束并写入

status: "copilot_unavailable"

。

任务完成意味着进程已退出且

result.json

文件存在——请以进程状态和工作目录为准，而非进度显示。Copilot的最终助手消息会存储在

result.json

的

finalMessage

字段中。

4. Review — do not trust the self-report

4. 审核——不要依赖自我报告

Re-run the project's gates yourself.
Read the diff against the brief, starting with
```
touchedFiles
```
.
Run relevant guard skills if installed.

See references/review-and-land.md.

自行重新运行项目的校验规则。
对照任务简报查看代码差异，从
```
touchedFiles
```
开始检查。
如果已安装相关校验工具，运行它们。

详见references/review-and-land.md。

5. Land it

5. 完成提交

If the work is good, commit it. The relay never commits — the diff and

result.json

are the record; run

git status

and

git diff

first to confirm exactly what changed. If the group has a PR flow, make the commit and push a branch; let human review happen. If the diff is wrong or incomplete, re-dispatch a corrected brief in a fresh run and review again.

如果工作成果符合要求，提交代码。中继工具绝不会自动提交——代码差异和

result.json

是记录；提交前请先运行

git status

和

git diff

确认具体修改内容。如果团队采用PR流程，请提交代码并推送分支，交由人工审核。如果代码差异有误或不完整，请在新的运行中重新分发修正后的任务简报并再次审核。

Autonomy and permissions

自主权与权限

Without

--allow-all-tools

, copilot auto-denies tool calls in headless mode: the process exits 0 but the relay detects the denial events and reports

status: "failed"

with the CLI's own error message and a hint to pass

--allow-all-tools

. This is the honest default — the orchestrator sees the failure rather than a silent no-op.

--allow-all-tools

explicitly grants full tool autonomy.

--read-only

selects

--mode plan

, which disables edit tools so project files can't be changed by direct edits; it works without

--allow-all-tools

. Shell commands still run in plan mode, so it guards against edits, not against everything. The two flags are mutually exclusive.

Copilot also exposes sandbox controls, but they are upstream-experimental (MXC-based, controlled via the

/sandbox

command and settings, disabled by default). This relay does not configure them.

如果未添加

--allow-all-tools

参数，copilot在无头模式下会自动拒绝工具调用：进程会以退出码0结束，但中继工具会检测到拒绝事件并报告

status: "failed"

，同时附带CLI自身的错误消息和添加

--allow-all-tools

参数的提示。这是默认的安全设置——协调工具会看到失败信息而非静默无操作。

--allow-all-tools

参数会明确授予完全的工具自主权。

--read-only

参数会选择

--mode plan

模式，该模式会禁用编辑工具，避免项目文件被直接修改；无需

--allow-all-tools

参数即可生效。规划模式下Shell命令仍可运行，因此该参数仅能防止文件编辑，而非所有操作。这两个参数互斥。

Copilot还提供沙箱控制功能，但属于上游实验性特性（基于MXC，通过

/sandbox

命令和设置控制，默认禁用）。本中继工具不会配置这些特性。

Authorization model

授权模型

Delegation is something the human opts into. Once briefed, copilot works as a tool you approved use of. The boundary is: do not accept conclusions from the self-report; verify everything on disk. For anything touching credentials, production data, or irreversible operations, stop and ask the human first instead of encoding it in a brief.

委托操作是由人工主动选择的。任务简报确认后，copilot作为你批准使用的工具开展工作。边界原则是：不要接受自我报告的结论；请验证磁盘上的所有内容。对于任何涉及凭证、生产数据或不可逆操作的任务，请先询问人工而非将其写入任务简报。

References

参考文档

references/writing-the-brief.md — structure, scope, gates, brief delivery.
references/dispatch-and-poll.md — flags, artifacts,
```
result.json
```
, and failure recovery.
references/review-and-land.md — what to verify before calling the diff done, at the end of a run.
references/multi-task-queues.md — sequential queues, constraint carry-forward, progress tracking, and the final coherence pass.

references/writing-the-brief.md — 结构、范围、校验规则、简报交付方式。
references/dispatch-and-poll.md — 参数、产物、
```
result.json
```
以及故障恢复。
references/review-and-land.md — 运行结束时，确认代码差异完成前需要验证的内容。
references/multi-task-queues.md — 顺序任务队列、约束传递、进度跟踪以及最终一致性检查。