swarm

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Swarm

Fan out N parallel cloud workers. They may cover separate slices, race the same brief, or mix both. The parent waits, aggregates, and returns one report.

调度N个并行云工作者。它们可以处理不同的任务切片、针对同一任务进行竞速，或两者混合使用。父进程会等待所有工作者完成，汇总结果后返回一份报告。

Start

启动步骤

Open a todolist with one entry per phase before launching anything.

Frame
Fan out
Aggregate
Report

在启动任何操作前，先创建一个待办事项列表，每个阶段对应一项条目：

框架定义
调度分发
结果汇总
生成报告

Phase A: Frame

阶段A：框架定义

State the done predicate and the artifact or report the swarm must return.
Choose the shape. Partition into slices, race N workers on identical briefs, or mix both. For a race or mixed shape, declare
```
first pass
```
,
```
rank all
```
, or
```
best-of
```
before spawning.
Set N from the user or derive it from the shape. N is total workers, not the cloud concurrency limit.
Pick the worker model from
```
swarm workers
```
in
```
~/.cursor/rules/pstack-models.mdc
```
when present. Otherwise use
```
grok-4.6-fast-xhigh
```
. For a model race, name each arm's model up front.
Give each worker its own writable output when it writes. Use a worktree, branch, or
```
/tmp/swarm-<slug>/worker-<n>/
```
.

明确完成判定条件，以及Swarm必须返回的产物或报告内容。
选择任务模式：将任务划分为多个切片、让N个工作者针对相同任务竞速，或混合两种模式。如果是竞速或混合模式，在启动工作者前需声明采用“首次通过”“全部排名”或“最优选择”规则。
根据用户输入或任务模式确定N的值。N是工作者的总数，而非云并发限制。
若存在
```
~/.cursor/rules/pstack-models.mdc
```
文件，从其中的
```
swarm workers
```
中选择工作者模型。否则使用
```
grok-4.6-fast-xhigh
```
。如果是模型竞速，需提前指定每个分支使用的模型。
为每个工作者分配独立的可写输出路径，可使用工作树、分支或
```
/tmp/swarm-<slug>/worker-<n>/
```
路径。

Phase B: Fan out

阶段B：调度分发

Spawn all N workers in one message with

subagent_type: generalPurpose

environment: "cloud"

run_in_background: true

, and the configured model. Use

environment: "local"

only when the worker needs access to something on the user's computer.

When a worker must start from a non-default pushed branch, pass

cloud_base_branch

Every brief stands alone. Include the goal, scope, exact slice or race arm, how to verify, and what to report. Reports use

PASS

ISSUES

, or

BLOCKED

with evidence.

If a worker drops out, proceed with N-1 and note it.

通过一条消息启动所有N个工作者，配置参数包括

subagent_type: generalPurpose

、

environment: "cloud"

、

run_in_background: true

以及选定的模型。仅当工作者需要访问用户电脑上的内容时，才使用

environment: "local"

。

若工作者需要从非默认的已推送分支启动，需传入

cloud_base_branch

参数。

每个任务指令需独立完整，包含目标、范围、具体的任务切片或竞速分支、验证方式以及报告要求。报告需使用

PASS

、

ISSUES

或

BLOCKED

状态，并附上相关证据。

如果某个工作者退出，继续使用剩余的N-1个工作者，并记录该情况。

Phase C: Aggregate

阶段C：结果汇总

Read the terminal results. For coverage, every required slice needs a result. For a race, apply the selection rule declared up front. Use first pass, rank all, or best-of. Do not paste raw worker dumps.

Keep a compact result table, one-line evidenced issues, and explicit gaps or dropouts.

读取最终结果。对于覆盖测试模式，每个必填切片都需要有结果。对于竞速模式，应用之前声明的选择规则：首次通过、全部排名或最优选择。请勿直接粘贴工作者的原始输出。

整理出简洁的结果表格、单行的问题说明（附证据），以及明确的空白项或工作者退出记录。

Phase D: Report

阶段D：生成报告

Return one consolidated in-chat report with the table, issue one-liners, gaps or dropouts, and the race rule when used.

返回一份整合后的聊天内报告，包含结果表格、单行问题说明、空白项或退出记录，以及所使用的竞速规则（若适用）。",