Prototypes

8 actions. Each is callable by the agent as a tool, over HTTP via /api/invoke, and (usually) from a UI page.

`prototypes.list`

GET

List website prototypes generated with v0.

AI tool: prototypes_list
API: GET /api/invoke/prototypes.list

Input

Field	Type	Required
`subjectId`	string	—
`limit`	integer	—
`offset`	integer	—
`orderBy`	string	—
`orderDir`	"asc" \| "desc"	—
`q`	string	—

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "subjectId": {
      "type": "string",
      "minLength": 1
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 500
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    },
    "orderBy": {
      "type": "string"
    },
    "orderDir": {
      "type": "string",
      "enum": [
        "asc",
        "desc"
      ]
    },
    "q": {
      "type": "string"
    }
  }
}

`prototypes.get`

GET

Get one prototype with its mirrored v0 files.

AI tool: prototypes_get
API: GET /api/invoke/prototypes.get

Input

Field	Type	Required	Description
`id`	string	yes

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "minLength": 1
    }
  },
  "required": [
    "id"
  ]
}

`prototypes.create`

POST · mutating

Create a website prototype from a prompt via v0 (or labelled simulated mode if no v0 key is configured).

AI tool: prototypes_create
API: POST /api/invoke/prototypes.create

Input

Field	Type	Required
`name`	string	yes
`prompt`	string	yes
`subjectId`	string	—

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "minLength": 1
    },
    "prompt": {
      "type": "string",
      "minLength": 1
    },
    "subjectId": {
      "type": "string",
      "minLength": 1
    }
  },
  "required": [
    "name",
    "prompt"
  ]
}

`prototypes.iterate`

POST · mutating

Refine a prototype by sending v0 a follow-up message; pulls the new version files back.

AI tool: prototypes_iterate
API: POST /api/invoke/prototypes.iterate

Input

Field	Type	Required	Description
`id`	string	yes
`message`	string	yes

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "minLength": 1
    },
    "message": {
      "type": "string",
      "minLength": 1
    }
  },
  "required": [
    "id",
    "message"
  ]
}

`prototypes.save_files`

POST · mutating

Persist locally-edited prototype files (no v0 call). Push to v0 with prototypes.push.

AI tool: prototypes_save_files
API: POST /api/invoke/prototypes.save_files

Input

Field	Type	Required	Description
`id`	string	yes
`files`	object[]	yes

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "minLength": 1
    },
    "files": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string"
          },
          "content": {
            "type": "string"
          },
          "locked": {
            "type": "boolean"
          }
        },
        "required": [
          "name",
          "content"
        ]
      }
    }
  },
  "required": [
    "id",
    "files"
  ]
}

`prototypes.push`

POST · mutating

Push locally-edited files back to v0. v0 has no per-file update, so this seeds a NEW v0 chat/version from the current files and relinks the prototype to it.

AI tool: prototypes_push
API: POST /api/invoke/prototypes.push

Input

Field	Type	Required	Description
`id`	string	yes

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "minLength": 1
    }
  },
  "required": [
    "id"
  ]
}

`prototypes.deploy`

POST · mutating

Deploy the latest prototype version to Vercel via v0. Returns the live URL.

AI tool: prototypes_deploy
API: POST /api/invoke/prototypes.deploy

Input

Field	Type	Required	Description
`id`	string	yes

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "minLength": 1
    }
  },
  "required": [
    "id"
  ]
}

`prototypes.delete`

POST · mutating

Soft-delete a prototype.

AI tool: prototypes_delete
API: POST /api/invoke/prototypes.delete

Input

Field	Type	Required	Description
`id`	string	yes

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "minLength": 1
    }
  },
  "required": [
    "id"
  ]
}