video-gen: drop duration param, restrict image_url to a single URL

The cogvideox-flash API does not accept a duration field — passing
one gets rejected upstream. Remove DEFAULT_DURATION, the
X-Video-Gen-Duration header parser, and the field forwarded to
Zhipu, both in code and README.

image_url was documented as accepting up to 2 URLs for first/last
frame, but the upstream schema only accepts a single string. Tighten
the zod schema to z.string().url().optional() and update README /
FAQ to make the single-URL constraint explicit.
This commit is contained in:
2026-09-04 22:28:39 +08:00
parent daaa01878d
commit 88120d61c1
2 changed files with 28 additions and 33 deletions
+4 -5
View File
@@ -152,7 +152,7 @@ curl -F "file=@/tmp/cat.png" https://video-gen.ai.foresh.com/upload
| 名称 | 类型 | 必填 | 说明 |
|---|---|---|---|
| `prompt` | string | ❌ | 视频文本描述,最大 512 字符 |
| `image_url` | string | ❌ | 参考图 URL(也支持 base64)。最多两张,首张为首帧、第二张为尾帧。图片 ≤ 5MB,格式 png/jpeg/jpg |
| `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` |
@@ -163,7 +163,6 @@ curl -F "file=@/tmp/cat.png" https://video-gen.ai.foresh.com/upload
| `X-Video-Gen-Model` / `X-Mcp-Model` / `X-Model` | string | `cogvideox-flash` | 覆盖模型 |
| `X-Video-Gen-Quality` | string | `speed` | `speed`(速度优先)或 `quality`(质量优先) |
| `X-Video-Gen-Fps` | int | `30` | `30` 或 `60` |
| `X-Video-Gen-Duration` | int | `5` | `5` 或 `10` 秒 |
| `X-Video-Gen-Watermark` | bool | `true` | 是否添加 AI 水印;关闭需先在智谱后台签署免责声明 |
模型名串识别顺序(首个非空值生效):`X-Video-Gen-Model` → `X-Mcp-Model` → `X-Model` → 默认。
@@ -360,7 +359,7 @@ package.json # @modelcontextprotocol/sdk + express + multer
- **Token 闭包注入**:在 Express 入口处从 header 提取 token,闭包传给 tool 回调;不依赖 SDK 内部字段
- **AI 可见 vs AI 不可见**:
- AI 只看到 `prompt / image_url / size / with_audio`
- `model / quality / fps / duration / watermark_enabled` 全部由 HTTP header 注入,避免 AI 误传或被诱导调高价档
- `model / quality / fps / watermark_enabled` 全部由 HTTP header 注入,避免 AI 误传或被诱导调高价档
- **异步语义暴露给 AI**:服务端不做轮询,`generate_video` 只提交、`query_video` 只查一次。AI 自主决定节奏
- **服务端自动 `request_id`**:每次提交服务端生成一个 UUID 作为智谱 `request_id`,便于日志关联,但不暴露给 AI
- **上传接口与 MCP 走同一进程**:额外 `POST /upload` + `GET /uploads/*` 不走 MCP、不鉴权,靠内网隔离;`PUBLIC_BASE_URL` 环境变量控制返回 URL 的拼接 host,AI 看到的 tool description 启动时拼接进真实地址,避免 AI 自由发挥
@@ -385,8 +384,8 @@ A: AI 自己 sleep 几秒再调(建议 2~5 秒间隔)。这是设计取舍
**Q: 视频 URL 多久过期?**
A: 智谱签发 URL 默认 24h 左右。需要在收到后及时转存到自己的 OSS/S3。
**Q: 为什么 quality / fps / duration 不让 AI 直接传?**
A: 这些是技术档位,与成本/单价挂钩。让 AI 自主挑 `quality=quality + fps=60 + duration=10` 会爆账号预算。改成 header 由部署方注入更可控。
**Q: 为什么 quality / fps 不让 AI 直接传?**
A: 这些是技术档位,与成本/单价挂钩。让 AI 自主挑 `quality=quality + fps=60` 会爆账号预算。改成 header 由部署方注入更可控。
**Q: 能否限制 `size` 白名单?**
A: 当前透传给智谱 API,不做强制校验。如需加白名单,修改 `src/mcp-server.js` 中 `generate_video` 的 `size` schema 即可。
+24 -28
View File
@@ -20,7 +20,6 @@ const DEFAULT_MODEL = "cogvideox-flash";
// AI 不可见的服务端默认(可被同名 header 覆盖)
const DEFAULT_QUALITY = "speed"; // speed | quality
const DEFAULT_FPS = 30; // 30 | 60
const DEFAULT_DURATION = 5; // 5 | 10
const DEFAULT_WATERMARK_ENABLED = true; // 平台政策默认 true
// ===== 上传文件相关 =====
@@ -197,7 +196,6 @@ async function submitVideo({
quality,
with_audio,
fps,
duration,
watermark_enabled,
}) {
// 平台要求 image_url 和 prompt 至少传一个
@@ -207,7 +205,6 @@ async function submitVideo({
with_audio: Boolean(with_audio),
watermark_enabled: Boolean(watermark_enabled),
fps,
duration,
// 由服务端生成唯一 request_id,便于日志关联;不暴露给 AI
request_id: randomUUID(),
};
@@ -270,11 +267,12 @@ Uploaded files live in container temp storage and are discarded on restart — d
"Video text description (max 512 chars). At least one of prompt / image_url is required."
),
image_url: z
.string()
.optional()
.describe(
"Reference image source for image-to-video. String or Array of up to 2 URLs for first/last frame. Image <= 5MB, .png/.jpeg/.jpg."
),
.string()
.url()
.optional()
.describe(
"Reference image URL for image-to-video. Single URL only. Image <= 5MB, .png/.jpeg/.jpg. Use the /upload endpoint to get a URL from a local file."
),
size: z
.string()
.optional()
@@ -297,15 +295,14 @@ Uploaded files live in container temp storage and are discarded on restart — d
}
// AI 不可见:全部走 header
const model = pickModel(headers) || DEFAULT_MODEL;
const quality = pickHeaderString(headers, "x-video-gen-quality", DEFAULT_QUALITY);
const fps = pickHeaderInt(headers, "x-video-gen-fps", DEFAULT_FPS);
const duration = pickHeaderInt(headers, "x-video-gen-duration", DEFAULT_DURATION);
const watermark_enabled = pickHeaderBool(
headers,
"x-video-gen-watermark",
DEFAULT_WATERMARK_ENABLED
);
const model = pickModel(headers) || DEFAULT_MODEL;
const quality = pickHeaderString(headers, "x-video-gen-quality", DEFAULT_QUALITY);
const fps = pickHeaderInt(headers, "x-video-gen-fps", DEFAULT_FPS);
const watermark_enabled = pickHeaderBool(
headers,
"x-video-gen-watermark",
DEFAULT_WATERMARK_ENABLED
);
if (!args.prompt && !args.image_url) {
return {
@@ -321,17 +318,16 @@ Uploaded files live in container temp storage and are discarded on restart — d
try {
const data = await submitVideo({
token,
model,
prompt: args.prompt,
image_url: args.image_url,
size: args.size,
quality,
with_audio: args.with_audio ?? false,
fps,
duration,
watermark_enabled,
});
token,
model,
prompt: args.prompt,
image_url: args.image_url,
size: args.size,
quality,
with_audio: args.with_audio ?? false,
fps,
watermark_enabled,
});
const summary =
`Model: ${model}\n` +