feat(video): add xai and alibaba providers

This commit is contained in:
Peter Steinberger
2026-04-05 23:06:18 +01:00
parent 5e0b58fbc6
commit a62193c09e
19 changed files with 1193 additions and 11 deletions

View File

@@ -16,6 +16,7 @@ import { isModernXaiModel, resolveXaiForwardCompatModel } from "./provider-model
import { resolveFallbackXaiAuth } from "./src/tool-auth-shared.js";
import { resolveEffectiveXSearchConfig } from "./src/x-search-config.js";
import { wrapXaiProviderStream } from "./stream.js";
import { buildXaiVideoGenerationProvider } from "./video-generation-provider.js";
import { createXaiWebSearchProvider } from "./web-search.js";
const PROVIDER_ID = "xai";
@@ -230,6 +231,7 @@ export default defineSingleProviderPluginEntry({
},
register(api) {
api.registerWebSearchProvider(createXaiWebSearchProvider());
api.registerVideoGenerationProvider(buildXaiVideoGenerationProvider());
api.registerTool((ctx) => createLazyCodeExecutionTool(ctx), { name: "code_execution" });
api.registerTool((ctx) => createLazyXSearchTool(ctx), { name: "x_search" });
},

View File

@@ -77,6 +77,7 @@
},
"contracts": {
"webSearchProviders": ["grok"],
"videoGenerationProviders": ["xai"],
"tools": ["code_execution", "x_search"]
},
"configSchema": {

View File

@@ -0,0 +1,10 @@
import { describePluginRegistrationContract } from "../../test/helpers/plugins/plugin-registration-contract.js";
describePluginRegistrationContract({
pluginId: "xai",
providerIds: ["xai"],
webSearchProviderIds: ["grok"],
videoGenerationProviderIds: ["xai"],
toolNames: ["code_execution", "x_search"],
requireGenerateVideo: true,
});

View File

@@ -0,0 +1,146 @@
import { afterEach, describe, expect, it, vi } from "vitest";
import { buildXaiVideoGenerationProvider } from "./video-generation-provider.js";
const {
resolveApiKeyForProviderMock,
postJsonRequestMock,
fetchWithTimeoutMock,
assertOkOrThrowHttpErrorMock,
resolveProviderHttpRequestConfigMock,
} = vi.hoisted(() => ({
resolveApiKeyForProviderMock: vi.fn(async () => ({ apiKey: "xai-key" })),
postJsonRequestMock: vi.fn(),
fetchWithTimeoutMock: vi.fn(),
assertOkOrThrowHttpErrorMock: vi.fn(async () => {}),
resolveProviderHttpRequestConfigMock: vi.fn((params) => ({
baseUrl: params.baseUrl ?? params.defaultBaseUrl,
allowPrivateNetwork: false,
headers: new Headers(params.defaultHeaders),
dispatcherPolicy: undefined,
})),
}));
vi.mock("openclaw/plugin-sdk/provider-auth-runtime", () => ({
resolveApiKeyForProvider: resolveApiKeyForProviderMock,
}));
vi.mock("openclaw/plugin-sdk/provider-http", () => ({
assertOkOrThrowHttpError: assertOkOrThrowHttpErrorMock,
fetchWithTimeout: fetchWithTimeoutMock,
postJsonRequest: postJsonRequestMock,
resolveProviderHttpRequestConfig: resolveProviderHttpRequestConfigMock,
}));
describe("xai video generation provider", () => {
afterEach(() => {
resolveApiKeyForProviderMock.mockClear();
postJsonRequestMock.mockReset();
fetchWithTimeoutMock.mockReset();
assertOkOrThrowHttpErrorMock.mockClear();
resolveProviderHttpRequestConfigMock.mockClear();
});
it("creates, polls, and downloads a generated video", async () => {
postJsonRequestMock.mockResolvedValue({
response: {
json: async () => ({
request_id: "req_123",
}),
},
release: vi.fn(async () => {}),
});
fetchWithTimeoutMock
.mockResolvedValueOnce({
json: async () => ({
request_id: "req_123",
status: "done",
video: { url: "https://cdn.x.ai/video.mp4" },
}),
})
.mockResolvedValueOnce({
headers: new Headers({ "content-type": "video/mp4" }),
arrayBuffer: async () => Buffer.from("mp4-bytes"),
});
const provider = buildXaiVideoGenerationProvider();
const result = await provider.generateVideo({
provider: "xai",
model: "grok-imagine-video",
prompt: "A tiny robot crab crossing a moonlit tide pool",
cfg: {},
durationSeconds: 6,
aspectRatio: "16:9",
resolution: "720P",
});
expect(postJsonRequestMock).toHaveBeenCalledWith(
expect.objectContaining({
url: "https://api.x.ai/v1/videos/generations",
body: expect.objectContaining({
model: "grok-imagine-video",
prompt: "A tiny robot crab crossing a moonlit tide pool",
duration: 6,
aspect_ratio: "16:9",
resolution: "720p",
}),
}),
);
expect(fetchWithTimeoutMock).toHaveBeenNthCalledWith(
1,
"https://api.x.ai/v1/videos/req_123",
expect.objectContaining({ method: "GET" }),
120000,
fetch,
);
expect(result.videos[0]?.mimeType).toBe("video/mp4");
expect(result.metadata).toEqual(
expect.objectContaining({
requestId: "req_123",
mode: "generate",
}),
);
});
it("routes video inputs to the extension endpoint when duration is set", async () => {
postJsonRequestMock.mockResolvedValue({
response: {
json: async () => ({
request_id: "req_extend",
}),
},
release: vi.fn(async () => {}),
});
fetchWithTimeoutMock
.mockResolvedValueOnce({
json: async () => ({
request_id: "req_extend",
status: "done",
video: { url: "https://cdn.x.ai/extended.mp4" },
}),
})
.mockResolvedValueOnce({
headers: new Headers({ "content-type": "video/mp4" }),
arrayBuffer: async () => Buffer.from("extended-bytes"),
});
const provider = buildXaiVideoGenerationProvider();
await provider.generateVideo({
provider: "xai",
model: "grok-imagine-video",
prompt: "Continue the shot into a neon alleyway",
cfg: {},
durationSeconds: 8,
inputVideos: [{ url: "https://example.com/input.mp4" }],
});
expect(postJsonRequestMock).toHaveBeenCalledWith(
expect.objectContaining({
url: "https://api.x.ai/v1/videos/extensions",
body: expect.objectContaining({
video: { url: "https://example.com/input.mp4" },
duration: 8,
}),
}),
);
});
});

View File

@@ -0,0 +1,338 @@
import { isProviderApiKeyConfigured } from "openclaw/plugin-sdk/provider-auth";
import { resolveApiKeyForProvider } from "openclaw/plugin-sdk/provider-auth-runtime";
import {
assertOkOrThrowHttpError,
fetchWithTimeout,
postJsonRequest,
resolveProviderHttpRequestConfig,
} from "openclaw/plugin-sdk/provider-http";
import type {
GeneratedVideoAsset,
VideoGenerationProvider,
VideoGenerationRequest,
VideoGenerationSourceAsset,
} from "openclaw/plugin-sdk/video-generation";
const DEFAULT_XAI_VIDEO_BASE_URL = "https://api.x.ai/v1";
const DEFAULT_XAI_VIDEO_MODEL = "grok-imagine-video";
const DEFAULT_TIMEOUT_MS = 120_000;
const POLL_INTERVAL_MS = 5_000;
const MAX_POLL_ATTEMPTS = 120;
const XAI_VIDEO_ASPECT_RATIOS = new Set(["1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3"]);
type XaiVideoCreateResponse = {
request_id?: string;
error?: {
code?: string;
message?: string;
} | null;
};
type XaiVideoStatusResponse = {
request_id?: string;
status?: "queued" | "processing" | "done" | "failed" | "expired";
video?: {
url?: string;
} | null;
error?: {
code?: string;
message?: string;
} | null;
};
function resolveXaiVideoBaseUrl(req: VideoGenerationRequest): string {
return req.cfg?.models?.providers?.xai?.baseUrl?.trim() || DEFAULT_XAI_VIDEO_BASE_URL;
}
function toDataUrl(buffer: Buffer, mimeType: string): string {
return `data:${mimeType};base64,${buffer.toString("base64")}`;
}
function resolveImageUrl(input: VideoGenerationSourceAsset | undefined): string | undefined {
if (!input) {
return undefined;
}
if (input.url?.trim()) {
return input.url.trim();
}
if (!input.buffer) {
throw new Error("xAI image-to-video input is missing image data.");
}
return toDataUrl(input.buffer, input.mimeType?.trim() || "image/png");
}
function resolveInputVideoUrl(input: VideoGenerationSourceAsset | undefined): string | undefined {
if (!input) {
return undefined;
}
const url = input.url?.trim();
if (url) {
return url;
}
if (input.buffer) {
throw new Error("xAI video editing currently requires a remote mp4 URL input.");
}
throw new Error("xAI video editing input is missing video data.");
}
function resolveDurationSeconds(params: {
durationSeconds?: number;
min?: number;
max?: number;
}): number | undefined {
if (typeof params.durationSeconds !== "number" || !Number.isFinite(params.durationSeconds)) {
return undefined;
}
const rounded = Math.round(params.durationSeconds);
return Math.max(params.min ?? 1, Math.min(params.max ?? 15, rounded));
}
function resolveAspectRatio(value: string | undefined): string | undefined {
const trimmed = value?.trim();
if (!trimmed || !XAI_VIDEO_ASPECT_RATIOS.has(trimmed)) {
return undefined;
}
return trimmed;
}
function resolveResolution(value: string | undefined): "480p" | "720p" | undefined {
if (value === "480P") {
return "480p";
}
if (value === "720P" || value === "1080P") {
return "720p";
}
return undefined;
}
function resolveXaiVideoMode(req: VideoGenerationRequest): "generate" | "edit" | "extend" {
const hasVideoInput = (req.inputVideos?.length ?? 0) > 0;
if (!hasVideoInput) {
return "generate";
}
return typeof resolveDurationSeconds({
durationSeconds: req.durationSeconds,
min: 2,
max: 10,
}) === "number"
? "extend"
: "edit";
}
function buildCreateBody(req: VideoGenerationRequest): Record<string, unknown> {
if ((req.inputImages?.length ?? 0) > 1) {
throw new Error("xAI video generation supports at most one reference image.");
}
if ((req.inputVideos?.length ?? 0) > 1) {
throw new Error("xAI video generation supports at most one input video.");
}
if ((req.inputImages?.length ?? 0) > 0 && (req.inputVideos?.length ?? 0) > 0) {
throw new Error("xAI video generation does not support image and video inputs together.");
}
const mode = resolveXaiVideoMode(req);
const body: Record<string, unknown> = {
model: req.model?.trim() || DEFAULT_XAI_VIDEO_MODEL,
prompt: req.prompt,
};
if (mode === "generate") {
const imageUrl = resolveImageUrl(req.inputImages?.[0]);
if (imageUrl) {
body.image = { url: imageUrl };
}
const duration = resolveDurationSeconds({
durationSeconds: req.durationSeconds,
min: 1,
max: 15,
});
if (typeof duration === "number") {
body.duration = duration;
}
const aspectRatio = resolveAspectRatio(req.aspectRatio);
if (aspectRatio) {
body.aspect_ratio = aspectRatio;
}
const resolution = resolveResolution(req.resolution);
if (resolution) {
body.resolution = resolution;
}
return body;
}
body.video = { url: resolveInputVideoUrl(req.inputVideos?.[0]) };
if (mode === "extend") {
const duration = resolveDurationSeconds({
durationSeconds: req.durationSeconds,
min: 2,
max: 10,
});
if (typeof duration === "number") {
body.duration = duration;
}
}
return body;
}
function resolveCreateEndpoint(req: VideoGenerationRequest): string {
switch (resolveXaiVideoMode(req)) {
case "edit":
return "/videos/edits";
case "extend":
return "/videos/extensions";
case "generate":
default:
return "/videos/generations";
}
}
async function pollXaiVideo(params: {
requestId: string;
headers: Headers;
timeoutMs?: number;
baseUrl: string;
fetchFn: typeof fetch;
}): Promise<XaiVideoStatusResponse> {
for (let attempt = 0; attempt < MAX_POLL_ATTEMPTS; attempt += 1) {
const response = await fetchWithTimeout(
`${params.baseUrl}/videos/${params.requestId}`,
{
method: "GET",
headers: params.headers,
},
params.timeoutMs ?? DEFAULT_TIMEOUT_MS,
params.fetchFn,
);
await assertOkOrThrowHttpError(response, "xAI video status request failed");
const payload = (await response.json()) as XaiVideoStatusResponse;
switch (payload.status) {
case "done":
return payload;
case "failed":
case "expired":
throw new Error(payload.error?.message?.trim() || `xAI video generation ${payload.status}`);
case "queued":
case "processing":
default:
await new Promise((resolve) => setTimeout(resolve, POLL_INTERVAL_MS));
break;
}
}
throw new Error(`xAI video generation task ${params.requestId} did not finish in time`);
}
async function downloadXaiVideo(params: {
url: string;
timeoutMs?: number;
fetchFn: typeof fetch;
}): Promise<GeneratedVideoAsset> {
const response = await fetchWithTimeout(
params.url,
{ method: "GET" },
params.timeoutMs ?? DEFAULT_TIMEOUT_MS,
params.fetchFn,
);
await assertOkOrThrowHttpError(response, "xAI generated video download failed");
const mimeType = response.headers.get("content-type")?.trim() || "video/mp4";
const arrayBuffer = await response.arrayBuffer();
return {
buffer: Buffer.from(arrayBuffer),
mimeType,
fileName: `video-1.${mimeType.includes("webm") ? "webm" : "mp4"}`,
};
}
export function buildXaiVideoGenerationProvider(): VideoGenerationProvider {
return {
id: "xai",
label: "xAI",
defaultModel: DEFAULT_XAI_VIDEO_MODEL,
models: [DEFAULT_XAI_VIDEO_MODEL],
isConfigured: ({ agentDir }) =>
isProviderApiKeyConfigured({
provider: "xai",
agentDir,
}),
capabilities: {
maxVideos: 1,
maxInputImages: 1,
maxInputVideos: 1,
maxDurationSeconds: 15,
supportsAspectRatio: true,
supportsResolution: true,
},
async generateVideo(req) {
const auth = await resolveApiKeyForProvider({
provider: "xai",
cfg: req.cfg,
agentDir: req.agentDir,
store: req.authStore,
});
if (!auth.apiKey) {
throw new Error("xAI API key missing");
}
const fetchFn = fetch;
const { baseUrl, allowPrivateNetwork, headers, dispatcherPolicy } =
resolveProviderHttpRequestConfig({
baseUrl: resolveXaiVideoBaseUrl(req),
defaultBaseUrl: DEFAULT_XAI_VIDEO_BASE_URL,
allowPrivateNetwork: false,
defaultHeaders: {
Authorization: `Bearer ${auth.apiKey}`,
"Content-Type": "application/json",
},
provider: "xai",
capability: "video",
transport: "http",
});
const { response, release } = await postJsonRequest({
url: `${baseUrl}${resolveCreateEndpoint(req)}`,
headers,
body: buildCreateBody(req),
timeoutMs: req.timeoutMs,
fetchFn,
allowPrivateNetwork,
dispatcherPolicy,
});
try {
await assertOkOrThrowHttpError(response, "xAI video generation failed");
const submitted = (await response.json()) as XaiVideoCreateResponse;
const requestId = submitted.request_id?.trim();
if (!requestId) {
throw new Error(
submitted.error?.message?.trim() || "xAI video generation response missing request_id",
);
}
const completed = await pollXaiVideo({
requestId,
headers,
timeoutMs: req.timeoutMs,
baseUrl,
fetchFn,
});
const videoUrl = completed.video?.url?.trim();
if (!videoUrl) {
throw new Error("xAI video generation completed without an output URL");
}
const video = await downloadXaiVideo({
url: videoUrl,
timeoutMs: req.timeoutMs,
fetchFn,
});
return {
videos: [video],
model: req.model?.trim() || DEFAULT_XAI_VIDEO_MODEL,
metadata: {
requestId,
status: completed.status,
videoUrl,
mode: resolveXaiVideoMode(req),
},
};
} finally {
await release();
}
},
};
}