feat(video_task): 上游从智谱换成 WorkBuddy 网关

智谱 cogvideox-flash 是免费模型,实测连续 429「访问量过大」,基本调不通。
改接 wb.ai 的 OpenAI 兼容视频接口(/v1/videos/generations + /v1/videos/{id}):
- 默认模型 cn:minimax-video-h3(4s 约 62 积分 / 128s),可切 cn:kling-video-v3
- 参数换成网关口径:seconds / aspect_ratio / resolution / negative_prompt / enable_audio
- 鉴权改为 wb.ai 的 API Key,服务端仍不存密钥
- presets.json 的视频预设同步改默认模型与说明

实测:提交→轮询→出片 2.1MB MP4 全链路通过,op=get 与错误路径均正常。
This commit is contained in:
2026-11-17 16:24:27 +08:00
parent 6a0aed2611
commit 6bd1fa48f8
4 changed files with 257 additions and 474 deletions
+145 -204
View File
@@ -1,4 +1,8 @@
#!/usr/bin/env node
// MCP 视频任务服务:对接 WorkBuddy 网关(wb.ai)的 OpenAI 兼容视频接口
// 提交 POST /v1/videos/generations(wait=false,立刻回 task_id)
// 查询 GET /v1/videos/{task_id}
// 只有一条工具 video_task,用 op 区分 create / get;服务端不轮询,AI 自己查。
import express from "express";
import { randomUUID } from "node:crypto";
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
@@ -6,26 +10,25 @@ import { StreamableHTTPServerTransport } from "@modelcontextprotocol/sdk/server/
import { isInitializeRequest } from "@modelcontextprotocol/sdk/types.js";
import { z } from "zod";
const ZHIPU_SUBMIT_URL =
"https://open.bigmodel.cn/api/paas/v4/videos/generations";
const ZHIPU_QUERY_URL = (id) =>
`https://open.bigmodel.cn/api/paas/v4/async-result/${encodeURIComponent(id)}`;
// 上游网关地址:容器内可用 WB_BASE_URL 覆盖
const WB_BASE = (process.env.WB_BASE_URL || "https://wb.ai.foresh.com").replace(/\/+$/, "");
const SUBMIT_URL = `${WB_BASE}/v1/videos/generations`;
const queryUrl = (id) => `${WB_BASE}/v1/videos/${encodeURIComponent(id)}`;
// 默认模型:cogvideox-flash
const DEFAULT_MODEL = "cogvideox-flash";
// 默认模型:minimax 出片约 2 分钟、扣 57 积分;kling 约 8 分钟、扣 103 积分
const DEFAULT_MODEL = "cn:minimax-video-h3";
const DEFAULT_SECONDS = 4;
// 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_WATERMARK_ENABLED = true; // 平台政策默认 true
// 提交/查询都是快接口(wait=false 立刻返回),卡住基本等于上游挂了
const UPSTREAM_TIMEOUT_MS = 60_000;
// submit/query 都是快接口,卡住基本等于上游挂了;限时避免工具调用被拖死
const UPSTREAM_TIMEOUT_MS = 30_000;
// 上游状态归一:命中终态才停轮询
const DONE = new Set(["completed", "succeeded", "success"]);
const FAILED = new Set(["failed", "error", "cancelled", "canceled"]);
// ── 优雅退出 ──────────────────────────────────────────────────────────────
// 容器里 node 以 PID 1 运行且未注册 SIGTERM 处理器时,内核不会对其执行默认
// 终止动作,docker stop/restart 会白等满 10s 宽限期才被 SIGKILL。
// 显式注册处理器,关闭 MCP session 与长连接后立即退出;3s 定时器为兜底。
let httpServer = null;
let closeAllSessions = () => {};
let shuttingDown = false;
@@ -35,7 +38,7 @@ function shutdown(sig) {
shuttingDown = true;
console.log(`[video] received ${sig}, shutting down`);
closeAllSessions();
if (!httpServer) process.exit(0); // stdio 模式无监听,直接退
if (!httpServer) process.exit(0);
httpServer.close(() => process.exit(0));
setTimeout(() => process.exit(0), 3000).unref();
}
@@ -43,11 +46,7 @@ process.on("SIGTERM", () => shutdown("SIGTERM"));
process.on("SIGINT", () => shutdown("SIGINT"));
function parseArgs(argv) {
const args = {
http: false,
port: 3000,
host: "0.0.0.0",
};
const args = { http: false, port: 3000, host: "0.0.0.0" };
for (let i = 0; i < argv.length; i++) {
const a = argv[i];
if (a === "--http") args.http = true;
@@ -57,6 +56,7 @@ function parseArgs(argv) {
return args;
}
// 鉴权:每个请求从 header 取 wb.ai 的 API Key,服务端不落盘
function pickToken(headers) {
if (!headers) return null;
const candidates = [
@@ -80,42 +80,13 @@ function pickToken(headers) {
function pickModel(headers) {
if (!headers) return null;
const v =
headers["x-video-task-model"] ||
headers["x-mcp-model"] ||
headers["x-model"];
const v = headers["x-video-task-model"] || headers["x-mcp-model"] || headers["x-model"];
if (!v) return null;
const s = String(v).trim();
return s || null;
}
function pickHeaderString(headers, name, fallback) {
if (!headers) return fallback;
const v = headers[name];
if (v === undefined || v === null) return fallback;
const s = String(v).trim();
return s ? s : fallback;
}
function pickHeaderInt(headers, name, fallback) {
if (!headers) return fallback;
const v = headers[name];
if (v === undefined || v === null) return fallback;
const n = parseInt(String(v).trim(), 10);
return Number.isFinite(n) ? n : fallback;
}
function pickHeaderBool(headers, name, fallback) {
if (!headers) return fallback;
const v = headers[name];
if (v === undefined || v === null) return fallback;
const s = String(v).trim().toLowerCase();
if (s === "true" || s === "1" || s === "yes") return true;
if (s === "false" || s === "0" || s === "no") return false;
return fallback;
}
async function callZhipu({ url, token, method = "POST", body }) {
async function callWb({ url, token, method = "POST", body }) {
const init = {
method,
headers: {
@@ -125,16 +96,17 @@ async function callZhipu({ url, token, method = "POST", body }) {
signal: AbortSignal.timeout(UPSTREAM_TIMEOUT_MS),
};
if (body !== undefined) init.body = JSON.stringify(body);
let resp;
try {
resp = await fetch(url, init);
} catch (e) {
// AbortSignal.timeout 中止时抛 TimeoutError/AbortError,转成明确的超时错误
if (e?.name === "TimeoutError" || e?.name === "AbortError") {
throw new Error(`Upstream request timed out after ${UPSTREAM_TIMEOUT_MS} ms`);
throw new Error(`上游 ${UPSTREAM_TIMEOUT_MS} ms 内没有响应`);
}
throw e;
}
const text = await resp.text();
let data;
try {
@@ -143,9 +115,9 @@ async function callZhipu({ url, token, method = "POST", body }) {
data = { raw: text };
}
if (!resp.ok) {
const err = new Error(
`Zhipu API error: ${resp.status} ${resp.statusText} - ${text}`
);
// 网关的错误体是 {error:{message}},取原话给模型看,便于自行纠错
const msg = data?.error?.message || data?.error?.code || text.slice(0, 300);
const err = new Error(`网关返回 ${resp.status}: ${msg}`);
err.status = resp.status;
err.detail = data;
throw err;
@@ -153,96 +125,62 @@ async function callZhipu({ url, token, method = "POST", body }) {
return data;
}
// ===== op=create:提交视频生成(同步只提交,立刻返回)=====
async function submitVideo({
token,
model,
prompt,
image_url,
quality,
with_audio,
fps,
watermark_enabled,
}) {
// 平台要求 image_url 和 prompt 至少传一个(handler 侧已校验)
const body = {
model,
quality,
with_audio: Boolean(with_audio),
watermark_enabled: Boolean(watermark_enabled),
fps,
// 由服务端生成唯一 request_id,便于日志关联;不暴露给 AI
request_id: randomUUID(),
};
if (prompt) body.prompt = prompt;
if (image_url) body.image_url = image_url;
return await callZhipu({ url: ZHIPU_SUBMIT_URL, token, body });
// { model, id, request_id, task_status }
// ===== op=create:提交任务,wait=false 立刻返回 task_id =====
async function submitVideo({ token, model, prompt, imageUrl, seconds, aspectRatio, resolution, negativePrompt, enableAudio }) {
const body = { model, prompt, wait: false };
if (imageUrl) body.image = imageUrl;
if (seconds) body.seconds = seconds;
if (aspectRatio) body.aspect_ratio = aspectRatio;
if (resolution) body.resolution = resolution;
if (negativePrompt) body.negative_prompt = negativePrompt;
if (enableAudio !== undefined && enableAudio !== null) body.enable_audio = Boolean(enableAudio);
return await callWb({ url: SUBMIT_URL, token, body });
}
// ===== op=get:查询异步结果(单次拉取,不内部轮询)=====
async function queryAsyncResult({ token, id }) {
return await callZhipu({
url: ZHIPU_QUERY_URL(id),
token,
method: "GET",
});
// { id, request_id, model, task_status, video_result?, ... }
// ===== op=get:查任务(单次拉取) =====
async function queryVideo({ token, taskId }) {
return await callWb({ url: queryUrl(taskId), token, method: "GET" });
}
function normStatus(s) {
return String(s || "").trim().toLowerCase();
}
// ---------- op=create 的业务处理 ----------
async function handleCreate({ args, headers, token }) {
// 纯空白 prompt 等同没给:schema 只校验类型/长度,不校验内容。
// 不 trim 的话,“ ”会被当成合法 prompt 提交(text-to-video 拿到空白提示词,
// image-to-video 则多传一个无意义字段)。
const prompt = typeof args.prompt === "string" ? args.prompt.trim() : "";
if (!prompt && !args.image_url) {
if (!prompt) {
return {
isError: true,
content: [
{
type: "text",
text: 'op=create requires at least one of "prompt" or "image_url".',
},
],
content: [{ type: "text", text: 'op=create 需要 "prompt"(视频描述,必填)。' }],
};
}
// AI 不可见:全部走 header
const model = pickModel(headers) || DEFAULT_MODEL;
const quality = pickHeaderString(
headers,
"x-video-task-quality",
DEFAULT_QUALITY
);
const fps = pickHeaderInt(headers, "x-video-task-fps", DEFAULT_FPS);
const watermark_enabled = pickHeaderBool(
headers,
"x-video-task-watermark",
DEFAULT_WATERMARK_ENABLED
);
const seconds = Number.isFinite(args.seconds) ? args.seconds : DEFAULT_SECONDS;
try {
const data = await submitVideo({
token,
model,
prompt,
image_url: args.image_url,
quality,
with_audio: args.with_audio ?? false,
fps,
watermark_enabled,
imageUrl: args.image_url,
seconds,
aspectRatio: args.aspect_ratio,
resolution: args.resolution,
negativePrompt: args.negative_prompt,
// 兼容旧字段名
enableAudio: args.enable_audio ?? args.with_audio,
});
const taskId = data.task_id || data.id;
const summary =
`Model: ${model}\n` +
`task_id: ${data.id}\n` +
`request_id: ${data.request_id}\n` +
`task_status: ${data.task_status}\n` +
`model: ${data.model || model}\n` +
`task_id: ${taskId}\n` +
`status: ${normStatus(data.status) || "queued"}\n` +
`\n` +
`Video generation is asynchronous. ` +
`Call this tool again with op="get" and task_id="${data.id}" to fetch the result.`;
`视频是异步生成(minimax 约 2 分钟,kling 约 8 分钟)。` +
`之后用 op="get" 加 task_id="${taskId}" 查询,直到 status 变成 completed 或 failed。` +
`不要重复提交同一个任务。`;
return { content: [{ type: "text", text: summary }] };
} catch (e) {
@@ -251,138 +189,157 @@ async function handleCreate({ args, headers, token }) {
content: [
{
type: "text",
text: `Failed to submit video task: ${e.message}${
e.detail ? `\nDetails: ${JSON.stringify(e.detail)}` : ""
}`,
text: `提交视频任务失败:${e.message}`,
},
],
};
}
}
// ---------- op=get 的业务处理 ----------
async function handleGet({ args, token }) {
// 与 handleCreate 同理:纯空白 task_id 不能直接拼进上游路径,
// 否则会得到一条含编码后空白的上游报错,既无从归因也误导模型。
const taskId = typeof args.task_id === "string" ? args.task_id.trim() : "";
if (!taskId) {
return {
isError: true,
content: [{ type: "text", text: 'op=get requires "task_id".' }],
content: [{ type: "text", text: 'op=get 需要 "task_id"。' }],
};
}
try {
const data = await queryAsyncResult({ token, id: taskId });
const status = data.task_status || "UNKNOWN";
const data = await queryVideo({ token, taskId });
const status = normStatus(data.status) || "unknown";
if (status === "SUCCESS") {
const v = (data.video_result || [])[0];
if (!v || !v.url) {
if (DONE.has(status)) {
const url = (data.videos || [])[0]?.url;
if (!url) {
return {
isError: true,
content: [
{
type: "text",
text: `Task succeeded but no video URL returned. Raw: ${JSON.stringify(
data
)}`,
text: `任务已完成但没有返回视频地址。原始响应:${JSON.stringify(data).slice(0, 500)}`,
},
],
};
}
const credit = data.usage?.credit;
const summary =
`task_id: ${data.id}\n` +
`model: ${data.model}\n` +
`task_status: SUCCESS\n` +
`Video URL: ${v.url}\n` +
(v.cover_image_url ? `Cover: ${v.cover_image_url}\n` : "");
// 单块输出:URL 已经写在摘要里,旧版额外回一个裸 URL 块会让模型
// (core 会把 text 块 join 成一段)看到同一个链接两遍。
`task_id: ${taskId}\n` +
`model: ${data.model || "-"}\n` +
`status: completed\n` +
`Video URL: ${url}\n` +
(credit !== undefined ? `credit: ${credit}\n` : "") +
`\n注意:视频是签名直链,约 12 小时失效;要长期保存请立刻下载到本地。`;
return { content: [{ type: "text", text: summary }] };
}
// PROCESSING / FAIL / 其他:原样返回关键字段
const errBlock = data.error ? `\nerror: ${JSON.stringify(data.error)}` : "";
if (FAILED.has(status)) {
return {
isError: true,
content: [
{
type: "text",
text:
`task_id: ${taskId}\n` +
`status: ${status}\n` +
(data.error ? `error: ${JSON.stringify(data.error)}\n` : "") +
`任务已失败,需要换提示词或模型重新提交。`,
},
],
};
}
// queued / in_progress:告诉模型继续等,别重复提交
const progress = data.progress;
return {
isError: status === "FAIL",
content: [
{
type: "text",
text:
`task_id: ${data.id}\n` +
`model: ${data.model}\n` +
`task_status: ${status}` +
errBlock,
`task_id: ${taskId}\n` +
`model: ${data.model || "-"}\n` +
`status: ${status}` +
(progress !== undefined && progress !== null ? `(进度 ${progress}%)` : "") +
`\n还没出片,稍后再用 op="get" 查一次。`,
},
],
};
} catch (e) {
return {
isError: true,
content: [
{
type: "text",
text: `Failed to query video task: ${e.message}${
e.detail ? `\nDetails: ${JSON.stringify(e.detail)}` : ""
}`,
},
],
content: [{ type: "text", text: `查询视频任务失败:${e.message}` }],
};
}
}
function buildServer() {
const server = new McpServer(
{ name: "video_task", version: "1.0.0" },
{ name: "video_task", version: "2.0.0" },
{ capabilities: { tools: {} } }
);
server.tool(
"video_task",
`AI video generation task.
`AI 视频生成任务(异步)。
Operations:
- \`create\`: Start a new video generation task. Requires at least one of \`prompt\` or \`image_url\`. Returns \`task_id\` immediately; generation runs in background.
- \`get\`: Check an existing task. Requires \`task_id\`. Returns status and, on SUCCESS, the video URL.
操作:
- \`create\`:提交视频生成,必须给 \`prompt\`。立刻返回 \`task_id\`,生成在后台跑。
- \`get\`:用 \`task_id\` 查进度,出片后返回视频直链。
Examples:
- Text-to-video → \`{"op":"create","prompt":"A cat running in a garden"}\`
- Image-to-video → \`{"op":"create","image_url":"https://example.com/cat.jpg","prompt":"The cat runs forward"}\`
- Check task → \`{"op":"get","task_id":"<task_id from create>"}\`
示例:
- 文生视频 → \`{"op":"create","prompt":"一只橘猫在阳光下的草地上奔跑,电影感"}\`
- 图生视频 → \`{"op":"create","prompt":"画面里的人缓缓转身","image_url":"https://..."}\`
- 查任务 → \`{"op":"get","task_id":"<create 返回的 task_id>"}\`
Workflow: call \`create\` once, then call \`get\` with the returned \`task_id\` until \`task_status\` is \`SUCCESS\` or \`FAIL\`. Never create duplicate tasks just to check status.`,
工作流:\`create\` 调一次,然后反复用 \`get\` 查同一个 \`task_id\`,直到 status 变成 completed 或 failed。**不要为了看进度重复提交任务。**
耗时参考:minimax 约 2 分钟(扣 57 积分),kling 约 8 分钟(扣 103 积分)。视频直链约 12 小时失效。`,
{
op: z
.enum(["create", "get"])
.describe(
"Use create to start video generation; use get to check a task by its task_id."
),
.describe("create 提交生成;get 按 task_id 查结果。"),
prompt: z
.string()
.max(512)
.max(2000)
.optional()
.describe(
"Video description, max 512 characters. Required for text-to-video; when combined with image_url it describes the motion."
),
.describe("视频描述,create 必填。图生视频时描述画面如何运动。"),
image_url: z
.string()
.url()
.optional()
.describe(
"Reference image for image-to-video: publicly reachable png/jpeg/jpg URL <= 5 MB. For local files, first use the built-in mint_public_link tool to get a public temporary URL."
"图生视频的参考图,公网可访问的 png/jpeg URL。本地文件先用 mint_public_link 换成公网短链。"
),
seconds: z
.number()
.min(4)
.max(15)
.optional()
.describe("视频时长(秒),默认 4。越长越慢越贵。"),
aspect_ratio: z
.string()
.optional()
.describe("画幅,如 16:9 / 9:16 / 1:1。上游不严格校验,写合法值即可。"),
resolution: z
.string()
.optional()
.describe("分辨率,如 768P / 1080P。留空用上游默认。"),
negative_prompt: z
.string()
.optional()
.describe("不希望出现的画面描述。"),
enable_audio: z
.boolean()
.optional()
.describe("是否生成音频,默认 false。"),
with_audio: z
.boolean()
.optional()
.describe(
"Whether to generate AI audio. Used with create; defaults to false."
),
.describe("旧字段名,等同 enable_audio。"),
task_id: z
.string()
.min(1)
.optional()
.describe("task_id returned by create. Required for get; omit for create."),
.describe("create 返回的 task_id,get 时必填。"),
},
async (args, extra) => {
const headers = extra?.requestInfo?.headers;
@@ -390,7 +347,7 @@ Workflow: call \`create\` once, then call \`get\` with the returned \`task_id\`
if (!token) {
return {
isError: true,
content: [{ type: "text", text: "Missing authentication token." }],
content: [{ type: "text", text: "缺少鉴权:header 里要带 Authorization: Bearer <API Key>。" }],
};
}
@@ -402,12 +359,7 @@ Workflow: call \`create\` once, then call \`get\` with the returned \`task_id\`
default:
return {
isError: true,
content: [
{
type: "text",
text: `Unknown op "${args.op}" (available: create, get).`,
},
],
content: [{ type: "text", text: `未知 op "${args.op}"(可用:create、get)。` }],
};
}
}
@@ -420,7 +372,6 @@ async function startHttp({ port, host }) {
const app = express();
app.use(express.json({ limit: "2mb" }));
// session -> { server, transport } 映射
const sessions = new Map();
closeAllSessions = () => {
@@ -433,32 +384,28 @@ async function startHttp({ port, host }) {
} catch {}
}
sessions.clear();
// 掰掉未关闭的 SSE / keep-alive 连接,否则 httpServer.close() 回调不会触发
httpServer?.closeAllConnections?.();
};
app.get("/health", (_req, res) => {
res.json({ status: "ok", service: "video_task", sessions: sessions.size });
res.json({ status: "ok", service: "video_task", upstream: WB_BASE, sessions: sessions.size });
});
async function handleSessionRequest(req, res) {
const sessionId = req.headers["mcp-session-id"];
// 已有 session:复用 transport
if (sessionId && sessions.has(sessionId)) {
const { transport } = sessions.get(sessionId);
await transport.handleRequest(req, res, req.body);
return;
}
// 新 session:必须是 initialize 请求
if (!isInitializeRequest(req.body)) {
res.status(400).json({
jsonrpc: "2.0",
error: {
code: -32000,
message:
"Bad Request: missing valid Mcp-Session-Id for non-initialize request",
message: "Bad Request: missing valid Mcp-Session-Id for non-initialize request",
},
id: req.body?.id ?? null,
});
@@ -484,10 +431,8 @@ async function startHttp({ port, host }) {
await transport.handleRequest(req, res, req.body);
}
// POST /mcp: 主入口
app.post("/mcp", handleSessionRequest);
// GET /mcp & DELETE /mcp: 用于 SSE 流 / 会话关闭
const handleOther = async (req, res) => {
const sessionId = req.headers["mcp-session-id"];
if (!sessionId || !sessions.has(sessionId)) {
@@ -501,17 +446,13 @@ async function startHttp({ port, host }) {
app.delete("/mcp", handleOther);
httpServer = app.listen(port, host, () => {
console.log(
`[video] MCP HTTP server listening on http://${host}:${port}/mcp`
);
console.log(`[video] MCP HTTP server listening on http://${host}:${port}/mcp → ${WB_BASE}`);
});
}
async function startStdio() {
const server = buildServer();
const { StdioServerTransport } = await import(
"@modelcontextprotocol/sdk/server/stdio.js"
);
const { StdioServerTransport } = await import("@modelcontextprotocol/sdk/server/stdio.js");
const transport = new StdioServerTransport();
await server.connect(transport);
console.error("[video] MCP stdio server started");