cawcut-workflow

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

CawCut Workflow

CawCut 工作流

One canvas. Follow-ups, missing inputs and re-runs go into the active

workflow_id

; an unrelated goal starts a new one. Solid edge, fixed asset. A canvas output reaches its consumer through an edge; an

asset_id

input is outside media or a result the user picked.

cawcut

cawcut asset upload <path|url|asset_id>… --json
cawcut workflow nodes [--capability <c>] [--asset <asset_id>…] [--model <id> --schema | --has-port <selector>] --json
cawcut workflow quick "<prompt>" --capability <c> --model <id> [--workflow <id>] [--param k=v] [--image|--video|--audio <asset_id>] --estimate --json
cawcut workflow create --file - --json
cawcut workflow edit <id> --file - --json
cawcut workflow set <id> --node <n> key=value --json
cawcut workflow connect <id> <from> <to> --json
cawcut workflow upscale <id> --node <draft_node> --json
cawcut workflow prepare <id> [--target <n>] --json
cawcut workflow run <id> [--target <n>] --wait --json
cawcut workflow results <id> --node <n> --download --json

--json

replies

{v,ok,data}

{ok:false,error}

; follow

error.next

. Ask with the host question tool, recommended option first; independent settings may share one call up to its question limit. Questions never arrive as a block of numbered prose; a numbered list is for a choice longer than the tool allows, or when no tool exists.

一个 Canvas。 后续操作、缺失输入和重跑操作都进入当前

workflow_id

；无关目标则启动一个新工作流。 Solid edge，固定 asset。 Canvas 输出通过 edge 到达其下游使用方；

asset_id

输入来自外部媒体或用户选择的结果。

cawcut

cawcut asset upload <path|url|asset_id>… --json
cawcut workflow nodes [--capability <c>] [--asset <asset_id>…] [--model <id> --schema | --has-port <selector>] --json
cawcut workflow quick "<prompt>" --capability <c> --model <id> [--workflow <id>] [--param k=v] [--image|--video|--audio <asset_id>] --estimate --json
cawcut workflow create --file - --json
cawcut workflow edit <id> --file - --json
cawcut workflow set <id> --node <n> key=value --json
cawcut workflow connect <id> <from> <to> --json
cawcut workflow upscale <id> --node <draft_node> --json
cawcut workflow prepare <id> [--target <n>] --json
cawcut workflow run <id> [--target <n>] --wait --json
cawcut workflow results <id> --node <n> --download --json

--json

{v,ok,data}

或

{ok:false,error}

；遵循

error.next

。使用宿主 question tool 提问，并优先列出推荐选项；相互独立的 settings 可以在一次调用中合并提问，但不得超过该工具的问题数量上限。问题绝不会以编号段落的形式出现；只有当选项数量超过工具限制或没有可用工具时，才使用编号列表。

0. Bootstrap

0. 启动准备

Silent guardrail, once per AI session: a session that already ran a

cawcut

command successfully starts at step 1. Otherwise run

cawcut upgrade check --json

```
"update_available": true
```
→ run
```
cawcut upgrade
```
yourself; the user never types it. Then continue.
```
"ahead_of_registry": true
```
→ a local build; continue.
Command missing, or any other check failure → failures. Done: the check ran, any update is installed, and no bootstrap text reaches the user.

静默检查规则，每个 AI 会话仅执行一次：如果会话中已成功运行过

cawcut

命令，则直接从第 1 步开始。否则运行

cawcut upgrade check --json

。

```
"update_available": true
```
→ 由你自行运行
```
cawcut upgrade
```
，用户无需输入。然后继续。
```
"ahead_of_registry": true
```
→ 本地构建版本；继续。
命令不存在或检查出现其他失败 → 失败处理。完成：检查已执行、所有可用更新均已安装，并且不会向用户显示任何启动准备文本。

1. Route

1. 路由

Request	Owner
Named App, "what apps exist"	`cawcut-app-run`
Running or named Ad Video, Story Video or avatar project	that skill
Story: multi-shot narrative or dialogue video	story on a canvas; `/cawcut-story-video` on request
Script, storyboard or shot list only (ad scripts too)	script-writing
Ad or ad video, or a product-page URL alone	`cawcut-ad-video` ; an ad asked for on a canvas → product
Product URL to scrape or extract	ask once: Ad Video wizard or canvas with a Product node → product
Cut, join, trim, timeline	`cawcut-vn`
Anything else new	`cawcut app list --schema --json` ; offer an App scoring ≥70 (the rubric is in `cawcut-app-run` ) beside "Build a canvas"; else canvas

Done: the user agreed to an App, a pipeline or a canvas.

请求	处理方
指定 App、“有哪些 Apps”	`cawcut-app-run`
运行或指定 Ad Video、Story Video 或 avatar 项目	对应的 skill
故事：多镜头叙事或对话视频	Canvas 上的 story；用户明确要求时使用 `/cawcut-story-video`
只需脚本、分镜或镜头清单（包括广告脚本）	script-writing
广告或广告视频，或仅提供商品页面 URL	`cawcut-ad-video` ；在 Canvas 上制作广告 → product
需要抓取或提取的商品 URL	询问一次：使用 Ad Video 向导，或使用包含 Product 节点的 Canvas → product
剪切、拼接、裁剪、时间线	`cawcut-vn`
其他所有新需求	`cawcut app list --schema --json` ；同时提供评分 ≥70 的 App（评分规则见 `cawcut-app-run` ）和“构建 Canvas”选项；否则使用 Canvas

完成：用户已同意采用 App、pipeline 或 Canvas。

2. Prepare media

2. 准备媒体

Outside media (file, URL, asset id):

cawcut asset upload

; relay its

notice

once. A canvas output ("the video above") is a solid edge, never an upload. Done: outside inputs have an

asset_id

; canvas outputs have edges.

外部媒体（文件、URL、asset id）：

cawcut asset upload

；将其

notice

传达一次。Canvas 输出（“上面的视频”）属于 solid edge，绝不能进行上传。完成：外部输入均具有

asset_id

；Canvas 输出均具有 edge。

3. Plan nodes

3. 规划节点

nodes

→ capabilities;

--capability

→ models;

--model --schema

→ ports and parameters. Offer

motion-transfer

and

object-swap

only when the user names them. Scripts are

text_input

text, never a

script

node.

Audio or video references, sound, frames, edits of existing media,
```
{{Image N}}
```
→ plan-rules.
Video or audio input → add
```
--asset <asset_id>…
```
to every
```
nodes --capability
```
call; a model whose duration limit rejects it → plan-rules.
Story → story.
Change an existing canvas, or "what next" → edit.

nodes

→ capabilities；

--capability

→ models；

--model --schema

→ ports 和 parameters。仅当用户明确提到

motion-transfer

和

object-swap

时才提供这些选项。脚本使用

text_input

文本，绝不使用

script

节点。

音频或视频参考、声音、帧、对现有媒体的编辑、
```
{{Image N}}
```
→ plan-rules。
视频或音频输入 → 在每个
```
nodes --capability
```
调用中添加
```
--asset <asset_id>…
```
；如果某个 model 因时长限制拒绝该输入 → plan-rules。
故事 → story。
修改现有 Canvas，或询问“下一步” → edit。

Model and settings (each paid node, before pricing)

Model 与 settings（每个付费节点，在定价之前）

Model: the first one
```
nodes
```
returns (the default sits there), or the one the user named.
Read
```
nodes --capability <c> --model <id> --schema
```
for that exact model, again after every model change. Settings, defaults and
```
options
```
come only from that reply; one model's options never carry to another (Seedance 2.5 Draft allows
```
480p
```
only, Seedance 2.5 allows more). Settings menu, one question: the model and its key settings by
```
label
```
(ratio or aspect, resolution or quality, duration, count, audio; only those in its schema). Options: Use current settings (recommended) · Adjust settings · Change model.
Adjust settings: one question per key setting in a single call, options from the parameter's labelled
```
options
```
, the default marked recommended. Other parameters keep their defaults. Write the answer under the parameter's key (
```
quick --param key=value
```
, or
```
set
```
on a canvas).
Change model (the schema read in step 2 repeats for the new model; settings the new model lacks or no longer allows reset to its defaults): one question with the first three models
```
nodes
```
returns (name, price) and More models; More models → every model as a numbered list (name, price), the turn's final reply, answered by number. Both keep the CLI's order. Then back to 2.

Done: each node has an input source, and each paid node a model and settings the user accepted.

Model：
```
nodes
```
返回的第一个 model（默认 model 位于其中），或用户指定的 model。
针对该确切 model 执行
```
nodes --capability <c> --model <id> --schema
```
，每次变更 model 后都要再次读取。仅可从该回复获取 settings、defaults 和
```
options
```
；一个 model 的 options 绝不能沿用至另一个 model（Seedance 2.5 Draft 仅允许
```
480p
```
，Seedance 2.5 支持更多选项）。 Settings 菜单只问一个问题：按
```
label
```
列出 model 及其关键 settings（ratio 或 aspect、resolution 或 quality、duration、count、audio；仅包含其 schema 中存在的项）。选项：使用当前设置（推荐）· 调整设置 · 更换 model。
调整 settings：在一次调用中针对每个关键 setting 提一个问题，选项来自参数中带标签的
```
options
```
，并将默认值标为推荐。其他参数保持默认值。将回答写入参数对应的 key（
```
quick --param key=value
```
，或在 Canvas 上使用
```
set
```
）。
更换 model（为新 model 重复执行第 2 步中的 schema 读取；新 model 不具备或不再允许的 settings 会重置为其默认值）：用一个问题展示
```
nodes
```
返回的前三个 model（名称、价格）以及更多 model；选择“更多 model”→ 将所有 model 以编号列表展示（名称、价格），作为该轮最后一条回复，并由用户按编号作答。两种列表均保持 CLI 的返回顺序。然后返回第 2 步。

完成：每个节点都有输入来源，每个付费节点都有用户接受的 model 和 settings。

4. Build, confirm, run

4. 构建、确认、运行

Build and price:
- Active
```
workflow_id
```
  (this AI session ran
```
quick
```
  or
```
create
```
  ; a script, an image or a video already sits on it): edit adds the new nodes and edges to it, then
```
prepare <id> --target <n>
```
  . Stages of one goal share one canvas: image → script → video.
- No canvas yet, several nodes:
```
create
```
  →
```
set
```
  /
```
connect
```
  →
```
prepare <id>
```
  (runs
```
check
```
  , returns credits).
- No canvas yet, one node:
```
quick … --estimate
```
  (runs
```
check
```
  ; returns
```
workflow_id
```
  ,
```
node_id
```
  , credits).
Ask one question: model, settings by label, scope, credits. Options: Confirm · Change model · Modify settings · Cancel. Each later paid run gets its own. Change model or Modify settings → the step 3 menus, then
```
switch-model <id> --node <n> --model <m>
```
or
```
set
```
, and
```
prepare --target
```
.
After Confirm:
```
run <id> --target <n> --wait
```
on the same workflow.

Done: Confirm for this scope,

check

passed,

task_id

read to its end state. Other cases → failures.

构建并核算价格：
- 当前
```
workflow_id
```
  （本 AI 会话运行过
```
quick
```
  或
```
create
```
  ，且其上已有脚本、图片或视频）：edit 将新节点和 edge 添加到其中，然后执行
```
prepare <id> --target <n>
```
  。同一目标的各阶段共享一个 Canvas：图片 → 脚本 → 视频。
- 尚无 Canvas，但有多个节点：
```
create
```
  →
```
set
```
  /
```
connect
```
  →
```
prepare <id>
```
  （会运行
```
check
```
  并返回 credits）。
- 尚无 Canvas，但只有一个节点：
```
quick … --estimate
```
  （会运行
```
check
```
  ；返回
```
workflow_id
```
  、
```
node_id
```
  、credits）。
询问一个问题：model、按
```
label
```
展示的 settings、范围和 credits。选项：确认 · 更换 model · 修改 settings · 取消。之后每次付费运行都需要单独确认。选择“更换 model”或“修改 settings”→ 进入第 3 步的菜单，然后执行
```
switch-model <id> --node <n> --model <m>
```
或
```
set
```
，并执行
```
prepare --target
```
。
确认后：在同一 workflow 上执行
```
run <id> --target <n> --wait
```
。

完成：本次范围已确认，

check

已通过，并持续读取

task_id

直至到达最终状态。其他情况 → 失败处理。

5. Deliver

5. 交付

delivery. Done: outputs, actual cost, Portal link reach the user;

cawcut-vn

gets every path, images too.

delivery。完成：输出内容、实际费用和 Portal 链接均已传达给用户；

cawcut-vn

必须获得每一个路径，包括图片路径。