seahi/baoyu-skills
1
0
Fork 0
mirror of https://github.com/JimLiu/baoyu-skills.git synced 2026-07-28 12:49:48 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat(baoyu-imagine): add Z.AI GLM-Image provider

Browse Source 
Adds the Z.AI (智谱) provider supporting glm-image and cogview-4-250304
models via the Z.AI sync image API. Configure with ZAI_API_KEY (or
BIGMODEL_API_KEY for backward compat). Reference images are not supported yet.
This commit is contained in:
Jim Liu 宝玉
2026-04-12 00:30:49 -05:00
parent ec5f4ffcc9
commit eaa0f1aa11
10 changed files with 683 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skills/baoyu-imagine/scripts/main.test.ts
+41 -2
View File
@@ -78,7 +78,7 @@ test("parseArgs parses the main baoyu-imagine CLI flags", () => {
"--image",
"out/hero",
"--provider",
"openai",
"zai",
"--quality",
"2k",
"--imageSize",
@@ -95,7 +95,7 @@ test("parseArgs parses the main baoyu-imagine CLI flags", () => {
assert.deepEqual(args.promptFiles, ["prompts/system.md", "prompts/content.md"]);
assert.equal(args.imagePath, "out/hero");
assert.equal(args.provider, "openai");
assert.equal(args.provider, "zai");
assert.equal(args.quality, "2k");
assert.equal(args.imageSize, "4K");
assert.deepEqual(args.referenceImages, ["ref/one.png", "ref/two.jpg"]);
@@ -124,6 +124,7 @@ default_image_size: 2K
default_model:
google: gemini-3-pro-image-preview
openai: gpt-image-1.5
zai: glm-image
azure: image-prod
minimax: image-01
batch:
@@ -134,6 +135,9 @@ batch:
start_interval_ms: 900
openai:
concurrency: 4
zai:
concurrency: 2
start_interval_ms: 1000
minimax:
concurrency: 2
start_interval_ms: 1400
@@ -151,6 +155,7 @@ batch:
assert.equal(config.default_image_size, "2K");
assert.equal(config.default_model?.google, "gemini-3-pro-image-preview");
assert.equal(config.default_model?.openai, "gpt-image-1.5");
assert.equal(config.default_model?.zai, "glm-image");
assert.equal(config.default_model?.azure, "image-prod");
assert.equal(config.default_model?.minimax, "image-01");
assert.equal(config.batch?.max_workers, 8);
@@ -161,6 +166,10 @@ batch:
assert.deepEqual(config.batch?.provider_limits?.openai, {
concurrency: 4,
});
assert.deepEqual(config.batch?.provider_limits?.zai, {
concurrency: 2,
start_interval_ms: 1000,
});
assert.deepEqual(config.batch?.provider_limits?.minimax, {
concurrency: 2,
start_interval_ms: 1400,
@@ -316,6 +325,27 @@ test("detectProvider selects Azure when only Azure credentials are configured",
);
});
test("detectProvider selects Z.AI when credentials are present or the model id matches", (t) => {
useEnv(t, {
GOOGLE_API_KEY: null,
OPENAI_API_KEY: null,
AZURE_OPENAI_API_KEY: null,
AZURE_OPENAI_BASE_URL: null,
OPENROUTER_API_KEY: null,
DASHSCOPE_API_KEY: null,
ZAI_API_KEY: "zai-key",
BIGMODEL_API_KEY: null,
MINIMAX_API_KEY: null,
REPLICATE_API_TOKEN: null,
JIMENG_ACCESS_KEY_ID: null,
JIMENG_SECRET_ACCESS_KEY: null,
ARK_API_KEY: null,
});
assert.equal(detectProvider(makeArgs()), "zai");
assert.equal(detectProvider(makeArgs({ model: "glm-image" })), "zai");
});
test("detectProvider infers Seedream from model id and allows Seedream reference-image workflows", (t) => {
useEnv(t, {
GOOGLE_API_KEY: null,
@@ -375,6 +405,7 @@ test("batch worker and provider-rate-limit configuration prefer env over EXTEND
BAOYU_IMAGE_GEN_MAX_WORKERS: "12",
BAOYU_IMAGE_GEN_GOOGLE_CONCURRENCY: "5",
BAOYU_IMAGE_GEN_GOOGLE_START_INTERVAL_MS: "450",
BAOYU_IMAGE_GEN_ZAI_CONCURRENCY: "4",
});
const extendConfig: Partial<ExtendConfig> = {
@@ -385,6 +416,10 @@ test("batch worker and provider-rate-limit configuration prefer env over EXTEND
concurrency: 2,
start_interval_ms: 900,
},
zai: {
concurrency: 1,
start_interval_ms: 1200,
},
minimax: {
concurrency: 1,
start_interval_ms: 1500,
@@ -398,6 +433,10 @@ test("batch worker and provider-rate-limit configuration prefer env over EXTEND
concurrency: 5,
startIntervalMs: 450,
});
assert.deepEqual(getConfiguredProviderRateLimits(extendConfig).zai, {
concurrency: 4,
startIntervalMs: 1200,
});
assert.deepEqual(getConfiguredProviderRateLimits(extendConfig).minimax, {
concurrency: 1,
startIntervalMs: 1500,
skills/baoyu-imagine/scripts/main.ts
+28 -4
View File
@@ -58,6 +58,7 @@ const DEFAULT_PROVIDER_RATE_LIMITS: Record<Provider, ProviderRateLimit> = {
openai: { concurrency: 3, startIntervalMs: 1100 },
openrouter: { concurrency: 3, startIntervalMs: 1100 },
dashscope: { concurrency: 3, startIntervalMs: 1100 },
zai: { concurrency: 3, startIntervalMs: 1100 },
minimax: { concurrency: 3, startIntervalMs: 1100 },
jimeng: { concurrency: 3, startIntervalMs: 1100 },
seedream: { concurrency: 3, startIntervalMs: 1100 },
@@ -76,7 +77,7 @@ Options:
--image <path> Output image path (required in single-image mode)
--batchfile <path> JSON batch file for multi-image generation
--jobs <count> Worker count for batch mode (default: auto, max from config, built-in default 10)
--provider google|openai|openrouter|dashscope|minimax|replicate|jimeng|seedream|azure Force provider (auto-detect by default)
--provider google|openai|openrouter|dashscope|zai|minimax|replicate|jimeng|seedream|azure Force provider (auto-detect by default)
-m, --model <id> Model ID
--ar <ratio> Aspect ratio (e.g., 16:9, 1:1, 4:3)
--size <WxH> Size (e.g., 1024x1024)
@@ -113,6 +114,8 @@ Environment variables:
GOOGLE_API_KEY Google API key
GEMINI_API_KEY Gemini API key (alias for GOOGLE_API_KEY)
DASHSCOPE_API_KEY DashScope API key
ZAI_API_KEY Z.AI API key
BIGMODEL_API_KEY Backward-compatible alias for Z.AI API key
MINIMAX_API_KEY MiniMax API key
REPLICATE_API_TOKEN Replicate API token
JIMENG_ACCESS_KEY_ID Jimeng Access Key ID
@@ -122,6 +125,8 @@ Environment variables:
OPENROUTER_IMAGE_MODEL Default OpenRouter model (google/gemini-3.1-flash-image-preview)
GOOGLE_IMAGE_MODEL Default Google model (gemini-3-pro-image-preview)
DASHSCOPE_IMAGE_MODEL Default DashScope model (qwen-image-2.0-pro)
ZAI_IMAGE_MODEL Default Z.AI model (glm-image)
BIGMODEL_IMAGE_MODEL Backward-compatible alias for Z.AI model (glm-image)
MINIMAX_IMAGE_MODEL Default MiniMax model (image-01)
REPLICATE_IMAGE_MODEL Default Replicate model (google/nano-banana-pro)
JIMENG_IMAGE_MODEL Default Jimeng model (jimeng_t2i_v40)
@@ -133,6 +138,8 @@ Environment variables:
OPENROUTER_TITLE Optional app name for OpenRouter attribution
GOOGLE_BASE_URL Custom Google endpoint
DASHSCOPE_BASE_URL Custom DashScope endpoint
ZAI_BASE_URL Custom Z.AI endpoint
BIGMODEL_BASE_URL Backward-compatible alias for Z.AI endpoint
MINIMAX_BASE_URL Custom MiniMax endpoint
REPLICATE_BASE_URL Custom Replicate endpoint
JIMENG_BASE_URL Custom Jimeng endpoint
@@ -239,6 +246,7 @@ export function parseArgs(argv: string[]): CliArgs {
v !== "openai" &&
v !== "openrouter" &&
v !== "dashscope" &&
v !== "zai" &&
v !== "minimax" &&
v !== "replicate" &&
v !== "jimeng" &&
@@ -395,6 +403,7 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
openai: null,
openrouter: null,
dashscope: null,
zai: null,
minimax: null,
replicate: null,
jimeng: null,
@@ -423,6 +432,7 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
key === "openai" ||
key === "openrouter" ||
key === "dashscope" ||
key === "zai" ||
key === "minimax" ||
key === "replicate" ||
key === "jimeng" ||
@@ -441,6 +451,7 @@ export function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
key === "openai" ||
key === "openrouter" ||
key === "dashscope" ||
key === "zai" ||
key === "minimax" ||
key === "replicate" ||
key === "jimeng" ||
@@ -571,13 +582,14 @@ export function getConfiguredProviderRateLimits(
openai: { ...DEFAULT_PROVIDER_RATE_LIMITS.openai },
openrouter: { ...DEFAULT_PROVIDER_RATE_LIMITS.openrouter },
dashscope: { ...DEFAULT_PROVIDER_RATE_LIMITS.dashscope },
zai: { ...DEFAULT_PROVIDER_RATE_LIMITS.zai },
minimax: { ...DEFAULT_PROVIDER_RATE_LIMITS.minimax },
jimeng: { ...DEFAULT_PROVIDER_RATE_LIMITS.jimeng },
seedream: { ...DEFAULT_PROVIDER_RATE_LIMITS.seedream },
azure: { ...DEFAULT_PROVIDER_RATE_LIMITS.azure },
};
for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope", "minimax", "jimeng", "seedream", "azure"] as Provider[]) {
for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope", "zai", "minimax", "jimeng", "seedream", "azure"] as Provider[]) {
const envPrefix = `BAOYU_IMAGE_GEN_${provider.toUpperCase()}`;
const extendLimit = extendConfig.batch?.provider_limits?.[provider];
configured[provider] = {
@@ -629,6 +641,7 @@ function inferProviderFromModel(model: string | null): Provider | null {
const normalized = model.trim();
if (normalized.includes("seedream") || normalized.includes("seededit")) return "seedream";
if (normalized === "image-01" || normalized === "image-01-live") return "minimax";
if (normalized === "glm-image" || normalized === "cogview-4-250304") return "zai";
return null;
}
@@ -656,6 +669,7 @@ export function detectProvider(args: CliArgs): Provider {
const hasOpenai = !!process.env.OPENAI_API_KEY;
const hasOpenrouter = !!process.env.OPENROUTER_API_KEY;
const hasDashscope = !!process.env.DASHSCOPE_API_KEY;
const hasZai = !!(process.env.ZAI_API_KEY || process.env.BIGMODEL_API_KEY);
const hasMinimax = !!process.env.MINIMAX_API_KEY;
const hasReplicate = !!process.env.REPLICATE_API_TOKEN;
const hasJimeng = !!(process.env.JIMENG_ACCESS_KEY_ID && process.env.JIMENG_SECRET_ACCESS_KEY);
@@ -676,6 +690,13 @@ export function detectProvider(args: CliArgs): Provider {
return "minimax";
}
if (modelProvider === "zai") {
if (!hasZai) {
throw new Error("Model looks like a Z.AI image model, but ZAI_API_KEY is not set.");
}
return "zai";
}
if (args.referenceImages.length > 0) {
if (hasGoogle) return "google";
if (hasOpenai) return "openai";
@@ -695,6 +716,7 @@ export function detectProvider(args: CliArgs): Provider {
hasAzure && "azure",
hasOpenrouter && "openrouter",
hasDashscope && "dashscope",
hasZai && "zai",
hasMinimax && "minimax",
hasReplicate && "replicate",
hasJimeng && "jimeng",
@@ -705,7 +727,7 @@ export function detectProvider(args: CliArgs): Provider {
if (available.length > 1) return available[0]!;
throw new Error(
"No API key found. Set GOOGLE_API_KEY, GEMINI_API_KEY, OPENAI_API_KEY, AZURE_OPENAI_API_KEY+AZURE_OPENAI_BASE_URL, OPENROUTER_API_KEY, DASHSCOPE_API_KEY, MINIMAX_API_KEY, REPLICATE_API_TOKEN, JIMENG keys, or ARK_API_KEY.\n" +
"No API key found. Set GOOGLE_API_KEY, GEMINI_API_KEY, OPENAI_API_KEY, AZURE_OPENAI_API_KEY+AZURE_OPENAI_BASE_URL, OPENROUTER_API_KEY, DASHSCOPE_API_KEY, ZAI_API_KEY, MINIMAX_API_KEY, REPLICATE_API_TOKEN, JIMENG keys, or ARK_API_KEY.\n" +
"Create ~/.baoyu-skills/.env or <cwd>/.baoyu-skills/.env with your keys."
);
}
@@ -744,6 +766,7 @@ export function isRetryableGenerationError(error: unknown): boolean {
async function loadProviderModule(provider: Provider): Promise<ProviderModule> {
if (provider === "google") return (await import("./providers/google")) as ProviderModule;
if (provider === "dashscope") return (await import("./providers/dashscope")) as ProviderModule;
if (provider === "zai") return (await import("./providers/zai")) as ProviderModule;
if (provider === "minimax") return (await import("./providers/minimax")) as ProviderModule;
if (provider === "replicate") return (await import("./providers/replicate")) as ProviderModule;
if (provider === "openrouter") return (await import("./providers/openrouter")) as ProviderModule;
@@ -775,6 +798,7 @@ function getModelForProvider(
return extendConfig.default_model.openrouter;
}
if (provider === "dashscope" && extendConfig.default_model.dashscope) return extendConfig.default_model.dashscope;
if (provider === "zai" && extendConfig.default_model.zai) return extendConfig.default_model.zai;
if (provider === "minimax" && extendConfig.default_model.minimax) return extendConfig.default_model.minimax;
if (provider === "replicate" && extendConfig.default_model.replicate) return extendConfig.default_model.replicate;
if (provider === "jimeng" && extendConfig.default_model.jimeng) return extendConfig.default_model.jimeng;
@@ -999,7 +1023,7 @@ async function runBatchTasks(
const acquireProvider = createProviderGate(providerRateLimits);
const workerCount = getWorkerCount(tasks.length, jobs, maxWorkers);
console.error(`Batch mode: ${tasks.length} tasks, ${workerCount} workers, parallel mode enabled.`);
for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope", "jimeng", "seedream", "azure"] as Provider[]) {
for (const provider of ["replicate", "google", "openai", "openrouter", "dashscope", "zai", "minimax", "jimeng", "seedream", "azure"] as Provider[]) {
const limit = providerRateLimits[provider];
console.error(`- ${provider}: concurrency=${limit.concurrency}, startIntervalMs=${limit.startIntervalMs}`);
}
skills/baoyu-imagine/scripts/providers/zai.test.ts
+180
View File
@@ -0,0 +1,180 @@
import assert from "node:assert/strict";
import test, { type TestContext } from "node:test";
import type { CliArgs } from "../types.ts";
import {
buildRequestBody,
buildZaiUrl,
extractImageFromResponse,
getDefaultModel,
getModelFamily,
parseAspectRatio,
parseSize,
resolveSizeForModel,
validateArgs,
} from "./zai.ts";
function makeArgs(overrides: Partial<CliArgs> = {}): CliArgs {
return {
prompt: null,
promptFiles: [],
imagePath: null,
provider: null,
model: null,
aspectRatio: null,
size: null,
quality: null,
imageSize: null,
referenceImages: [],
n: 1,
batchFile: null,
jobs: null,
json: false,
help: false,
...overrides,
};
}
function useEnv(
t: TestContext,
values: Record<string, string | null>,
): void {
const previous = new Map<string, string | undefined>();
for (const [key, value] of Object.entries(values)) {
previous.set(key, process.env[key]);
if (value == null) {
delete process.env[key];
} else {
process.env[key] = value;
}
}
t.after(() => {
for (const [key, value] of previous.entries()) {
if (value == null) {
delete process.env[key];
} else {
process.env[key] = value;
}
}
});
}
test("Z.AI default model prefers env override and otherwise uses glm-image", (t) => {
useEnv(t, {
ZAI_IMAGE_MODEL: null,
BIGMODEL_IMAGE_MODEL: null,
});
assert.equal(getDefaultModel(), "glm-image");
process.env.BIGMODEL_IMAGE_MODEL = "cogview-4-250304";
assert.equal(getDefaultModel(), "cogview-4-250304");
});
test("Z.AI URL builder normalizes host, v4 base, and full endpoint inputs", (t) => {
useEnv(t, { ZAI_BASE_URL: "https://api.z.ai" });
assert.equal(buildZaiUrl(), "https://api.z.ai/api/paas/v4/images/generations");
process.env.ZAI_BASE_URL = "https://proxy.example.com/api/paas/v4/";
assert.equal(buildZaiUrl(), "https://proxy.example.com/api/paas/v4/images/generations");
process.env.ZAI_BASE_URL = "https://proxy.example.com/custom/images/generations";
assert.equal(buildZaiUrl(), "https://proxy.example.com/custom/images/generations");
});
test("Z.AI model family and parsing helpers recognize documented formats", () => {
assert.equal(getModelFamily("glm-image"), "glm");
assert.equal(getModelFamily("cogview-4-250304"), "legacy");
assert.deepEqual(parseAspectRatio("16:9"), { width: 16, height: 9 });
assert.equal(parseAspectRatio("wide"), null);
assert.deepEqual(parseSize("1280x1280"), { width: 1280, height: 1280 });
assert.deepEqual(parseSize("1472*1088"), { width: 1472, height: 1088 });
assert.equal(parseSize("big"), null);
});
test("Z.AI size resolution follows documented recommended ratios and validates custom sizes", () => {
assert.equal(
resolveSizeForModel("glm-image", makeArgs({ aspectRatio: "16:9", quality: "2k" })),
"1728x960",
);
assert.equal(
resolveSizeForModel("cogview-4-250304", makeArgs({ aspectRatio: "4:3", quality: "normal" })),
"1152x864",
);
assert.equal(
resolveSizeForModel("glm-image", makeArgs({ size: "1568x1056", quality: "2k" })),
"1568x1056",
);
const uncommon = resolveSizeForModel(
"glm-image",
makeArgs({ aspectRatio: "5:2", quality: "normal" }),
);
const parsed = parseSize(uncommon);
assert.ok(parsed);
assert.ok(parsed.width % 32 === 0);
assert.ok(parsed.height % 32 === 0);
assert.ok(parsed.width * parsed.height <= 2 ** 22);
assert.throws(
() => resolveSizeForModel("glm-image", makeArgs({ size: "1000x1000", quality: "2k" })),
/between 1024 and 2048/,
);
assert.throws(
() => resolveSizeForModel("glm-image", makeArgs({ size: "1280x1260", quality: "2k" })),
/divisible by 32/,
);
assert.throws(
() => resolveSizeForModel("cogview-4-250304", makeArgs({ size: "2048x2048", quality: "2k" })),
/must not exceed 2\^21 total pixels/,
);
});
test("Z.AI validation rejects unsupported refs and multi-image requests", () => {
assert.throws(
() => validateArgs("glm-image", makeArgs({ referenceImages: ["ref.png"] })),
/text-to-image only/,
);
assert.throws(
() => validateArgs("glm-image", makeArgs({ n: 2 })),
/single image per request/,
);
});
test("Z.AI request body maps skill quality and resolved size into provider fields", () => {
const body = buildRequestBody(
"A cinematic science poster",
"glm-image",
makeArgs({ aspectRatio: "4:3", quality: "normal" }),
);
assert.deepEqual(body, {
model: "glm-image",
prompt: "A cinematic science poster",
quality: "standard",
size: "1472x1088",
});
});
test("Z.AI response extraction downloads the returned image URL", async (t) => {
const originalFetch = globalThis.fetch;
t.after(() => {
globalThis.fetch = originalFetch;
});
globalThis.fetch = async () =>
new Response(Uint8Array.from([1, 2, 3]), {
status: 200,
headers: { "Content-Type": "image/png" },
});
const image = await extractImageFromResponse({
data: [{ url: "https://cdn.example.com/glm-image.png" }],
});
assert.deepEqual([...image], [1, 2, 3]);
await assert.rejects(
() => extractImageFromResponse({ data: [{}] }),
/No image URL/,
);
});
skills/baoyu-imagine/scripts/providers/zai.ts
+306
View File
@@ -0,0 +1,306 @@
import type { CliArgs, Quality } from "../types";
type ZaiModelFamily = "glm" | "legacy";
type ZaiRequestBody = {
model: string;
prompt: string;
quality: "hd" | "standard";
size: string;
};
type ZaiResponse = {
data?: Array<{ url?: string }>;
};
const DEFAULT_MODEL = "glm-image";
const GLM_MAX_PIXELS = 2 ** 22;
const LEGACY_MAX_PIXELS = 2 ** 21;
const GLM_SIZE_STEP = 32;
const LEGACY_SIZE_STEP = 16;
const GLM_RECOMMENDED_SIZES: Record<string, string> = {
"1:1": "1280x1280",
"3:2": "1568x1056",
"2:3": "1056x1568",
"4:3": "1472x1088",
"3:4": "1088x1472",
"16:9": "1728x960",
"9:16": "960x1728",
};
const LEGACY_RECOMMENDED_SIZES: Record<string, string> = {
"1:1": "1024x1024",
"9:16": "768x1344",
"3:4": "864x1152",
"16:9": "1344x768",
"4:3": "1152x864",
"2:1": "1440x720",
"1:2": "720x1440",
};
export function getDefaultModel(): string {
return process.env.ZAI_IMAGE_MODEL || process.env.BIGMODEL_IMAGE_MODEL || DEFAULT_MODEL;
}
function getApiKey(): string | null {
return process.env.ZAI_API_KEY || process.env.BIGMODEL_API_KEY || null;
}
export function buildZaiUrl(): string {
const base = (process.env.ZAI_BASE_URL || process.env.BIGMODEL_BASE_URL || "https://api.z.ai/api/paas/v4")
.replace(/\/+$/g, "");
if (base.endsWith("/images/generations")) return base;
if (base.endsWith("/api/paas/v4")) return `${base}/images/generations`;
if (base.endsWith("/v4")) return `${base}/images/generations`;
return `${base}/api/paas/v4/images/generations`;
}
export function getModelFamily(model: string): ZaiModelFamily {
return model.trim().toLowerCase() === "glm-image" ? "glm" : "legacy";
}
export function parseAspectRatio(ar: string): { width: number; height: number } | null {
const match = ar.match(/^(\d+(?:\.\d+)?):(\d+(?:\.\d+)?)$/);
if (!match) return null;
const width = Number(match[1]);
const height = Number(match[2]);
if (!Number.isFinite(width) || !Number.isFinite(height) || width <= 0 || height <= 0) {
return null;
}
return { width, height };
}
export function parseSize(size: string): { width: number; height: number } | null {
const match = size.trim().match(/^(\d+)\s*[xX*]\s*(\d+)$/);
if (!match) return null;
const width = parseInt(match[1]!, 10);
const height = parseInt(match[2]!, 10);
if (!Number.isFinite(width) || !Number.isFinite(height) || width <= 0 || height <= 0) {
return null;
}
return { width, height };
}
function formatSize(width: number, height: number): string {
return `${width}x${height}`;
}
function roundToStep(value: number, step: number): number {
return Math.max(step, Math.round(value / step) * step);
}
function getRatioValue(ar: string): number | null {
const parsed = parseAspectRatio(ar);
if (!parsed) return null;
return parsed.width / parsed.height;
}
function findClosestRatioKey(ar: string, candidates: string[]): string | null {
const targetRatio = getRatioValue(ar);
if (targetRatio == null) return null;
let bestKey: string | null = null;
let bestDiff = Infinity;
for (const candidate of candidates) {
const candidateRatio = getRatioValue(candidate);
if (candidateRatio == null) continue;
const diff = Math.abs(candidateRatio - targetRatio);
if (diff < bestDiff) {
bestDiff = diff;
bestKey = candidate;
}
}
return bestDiff <= 0.05 ? bestKey : null;
}
function getTargetPixels(quality: Quality): number {
return quality === "normal" ? 1024 * 1024 : 1536 * 1536;
}
function fitToPixelBudget(
width: number,
height: number,
targetPixels: number,
maxPixels: number,
step: number,
): { width: number; height: number } {
let nextWidth = width;
let nextHeight = height;
const pixels = nextWidth * nextHeight;
if (pixels > maxPixels) {
const scale = Math.sqrt(maxPixels / pixels);
nextWidth *= scale;
nextHeight *= scale;
} else {
const scale = Math.sqrt(targetPixels / pixels);
nextWidth *= scale;
nextHeight *= scale;
}
let roundedWidth = roundToStep(nextWidth, step);
let roundedHeight = roundToStep(nextHeight, step);
let roundedPixels = roundedWidth * roundedHeight;
while (roundedPixels > maxPixels && (roundedWidth > step || roundedHeight > step)) {
if (roundedWidth >= roundedHeight && roundedWidth > step) {
roundedWidth -= step;
} else if (roundedHeight > step) {
roundedHeight -= step;
} else {
break;
}
roundedPixels = roundedWidth * roundedHeight;
}
return { width: roundedWidth, height: roundedHeight };
}
function validateCustomSize(
size: string,
family: ZaiModelFamily,
): string {
const parsed = parseSize(size);
if (!parsed) {
throw new Error("Z.AI --size must be in WxH format, for example 1280x1280.");
}
const widthStep = family === "glm" ? GLM_SIZE_STEP : LEGACY_SIZE_STEP;
const minEdge = family === "glm" ? 1024 : 512;
const maxPixels = family === "glm" ? GLM_MAX_PIXELS : LEGACY_MAX_PIXELS;
if (parsed.width < minEdge || parsed.width > 2048 || parsed.height < minEdge || parsed.height > 2048) {
throw new Error(
family === "glm"
? "GLM-image custom size requires width and height between 1024 and 2048."
: "Z.AI legacy image models require width and height between 512 and 2048."
);
}
if (parsed.width % widthStep !== 0 || parsed.height % widthStep !== 0) {
throw new Error(
family === "glm"
? "GLM-image custom size requires width and height divisible by 32."
: "Z.AI legacy image models require width and height divisible by 16."
);
}
if (parsed.width * parsed.height > maxPixels) {
throw new Error(
family === "glm"
? "GLM-image custom size must not exceed 2^22 total pixels."
: "Z.AI legacy image size must not exceed 2^21 total pixels."
);
}
return formatSize(parsed.width, parsed.height);
}
export function resolveSizeForModel(
model: string,
args: Pick<CliArgs, "size" | "aspectRatio" | "quality">,
): string {
const family = getModelFamily(model);
const quality = args.quality === "normal" ? "normal" : "2k";
if (args.size) {
return validateCustomSize(args.size, family);
}
const recommended = family === "glm" ? GLM_RECOMMENDED_SIZES : LEGACY_RECOMMENDED_SIZES;
const defaultSize = family === "glm" ? "1280x1280" : "1024x1024";
if (!args.aspectRatio) return defaultSize;
const recommendedRatio = findClosestRatioKey(args.aspectRatio, Object.keys(recommended));
if (recommendedRatio) {
return recommended[recommendedRatio]!;
}
const parsedRatio = parseAspectRatio(args.aspectRatio);
if (!parsedRatio) return defaultSize;
const targetPixels = getTargetPixels(quality);
const maxPixels = family === "glm" ? GLM_MAX_PIXELS : LEGACY_MAX_PIXELS;
const step = family === "glm" ? GLM_SIZE_STEP : LEGACY_SIZE_STEP;
const fit = fitToPixelBudget(
parsedRatio.width,
parsedRatio.height,
targetPixels,
maxPixels,
step,
);
return formatSize(fit.width, fit.height);
}
function getZaiQuality(quality: CliArgs["quality"]): "hd" | "standard" {
return quality === "normal" ? "standard" : "hd";
}
export function validateArgs(_model: string, args: CliArgs): void {
if (args.referenceImages.length > 0) {
throw new Error("Z.AI GLM-image currently supports text-to-image only in baoyu-imagine. Remove --ref or choose another provider.");
}
if (args.n > 1) {
throw new Error("Z.AI image generation currently returns a single image per request in baoyu-imagine.");
}
}
export function buildRequestBody(
prompt: string,
model: string,
args: CliArgs,
): ZaiRequestBody {
validateArgs(model, args);
return {
model,
prompt,
quality: getZaiQuality(args.quality),
size: resolveSizeForModel(model, args),
};
}
export async function extractImageFromResponse(result: ZaiResponse): Promise<Uint8Array> {
const url = result.data?.[0]?.url;
if (!url) {
throw new Error("No image URL in Z.AI response");
}
const imageResponse = await fetch(url);
if (!imageResponse.ok) {
throw new Error(`Failed to download image from Z.AI: ${imageResponse.status}`);
}
return new Uint8Array(await imageResponse.arrayBuffer());
}
export async function generateImage(
prompt: string,
model: string,
args: CliArgs,
): Promise<Uint8Array> {
const apiKey = getApiKey();
if (!apiKey) {
throw new Error("ZAI_API_KEY is required. Get one from https://docs.z.ai/.");
}
const response = await fetch(buildZaiUrl(), {
method: "POST",
headers: {
"Content-Type": "application/json",
Authorization: `Bearer ${apiKey}`,
},
body: JSON.stringify(buildRequestBody(prompt, model, args)),
});
if (!response.ok) {
const err = await response.text();
throw new Error(`Z.AI API error (${response.status}): ${err}`);
}
const result = (await response.json()) as ZaiResponse;
return extractImageFromResponse(result);
}
skills/baoyu-imagine/scripts/types.ts
+2
View File
@@ -3,6 +3,7 @@ export type Provider =
| "openai"
| "openrouter"
| "dashscope"
| "zai"
| "minimax"
| "replicate"
| "jimeng"
@@ -61,6 +62,7 @@ export type ExtendConfig = {
openai: string | null;
openrouter: string | null;
dashscope: string | null;
zai: string | null;
minimax: string | null;
replicate: string | null;
jimeng: string | null;