video-gen: make prompt a required parameter in tool schema

This commit is contained in:
2026-09-05 19:22:29 +08:00
parent dab3732b50
commit 4264ed0e39
2 changed files with 4 additions and 5 deletions
+2 -2
View File
@@ -145,13 +145,13 @@ curl -F "file=@/tmp/cat.png" https://video-gen.ai.foresh.com/upload
## 工具:generate_video
提交一个视频生成任务,支持**文生视频**和**图生视频**。**至少**需要传 `prompt` 或 `image_url` 其中之一;两者都传也行(image-to-video 时 prompt 会被附加为运动/动作描述)。
提交一个视频生成任务,支持**文生视频**和**图生视频**。`prompt` 为**必填**;图生视频另传 `image_url`(两者都传也行,此时 prompt 会附加为运动/动作描述)。
### 参数(AI 可见)
| 名称 | 类型 | 必填 | 说明 |
|---|---|---|---|
| `prompt` | string | ❌ | 视频文本描述,最大 512 字符 |
| `prompt` | string | ✅ | 视频文本描述,最大 512 字符 |
| `image_url` | string (URL) | ❌ | 参考图 URL(**单张**,不支持数组 / 多张 / 首尾帧)。图片 ≤ 5MB,格式 png/jpeg/jpg。本地文件请走 `/upload` |
| `size` | string | ❌ | 视频尺寸,例如 `1920x1080`、`1080x1920`、`1024x1024`、`1280x960` 等 |
| `with_audio` | boolean | ❌ | 是否生成 AI 音效,默认 `false` |
+2 -3
View File
@@ -250,7 +250,7 @@ function buildServer({ publicBaseUrl }) {
"video-gen",
`Submit a video generation task (text-to-video or image-to-video).
Returns the task_id immediately; poll the result later with query_video.
Provide prompt and/or image_url (at least one is required).
prompt is required. Add image_url for image-to-video.
If you need to use a LOCAL image file as image_url, upload it FIRST with this exact command (replace the path):
@@ -262,9 +262,8 @@ Uploaded files live in container temp storage and are discarded on restart — d
{
prompt: z
.string()
.optional()
.describe(
"Video text description (max 512 chars). At least one of prompt / image_url is required."
"Video text description (max 512 chars). Required; when combined with image_url it serves as the motion/action description."
),
image_url: z
.string()