Merge pull request #101 from cwandev/fix/openrouter
fix(baoyu-image-gen): align `OpenRouter` image generation with current API
This commit is contained in:
Jim Liu 宝玉
GitHub
commit
e7f9764a49
|
|
@ -0,0 +1,131 @@
|
|||
import assert from "node:assert/strict";
|
||||
import test from "node:test";
|
||||
|
||||
import type { CliArgs } from "../types.ts";
|
||||
import {
|
||||
buildContent,
|
||||
buildRequestBody,
|
||||
extractImageFromResponse,
|
||||
getAspectRatio,
|
||||
getImageSize,
|
||||
validateArgs,
|
||||
} from "./openrouter.ts";
|
||||
|
||||
const GEMINI_MODEL = "google/gemini-3.1-flash-image-preview";
|
||||
const GEMINI_25_MODEL = "google/gemini-2.5-flash-image-preview";
|
||||
const FLUX_MODEL = "black-forest-labs/flux.2-pro";
|
||||
|
||||
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,
|
||||
};
|
||||
}
|
||||
|
||||
test("OpenRouter request body uses image_config and string content for text-only prompts", () => {
|
||||
const args = makeArgs({ aspectRatio: "16:9", quality: "2k" });
|
||||
const body = buildRequestBody("hello", GEMINI_MODEL, args, []);
|
||||
|
||||
assert.deepEqual(body.image_config, {
|
||||
image_size: "2K",
|
||||
aspect_ratio: "16:9",
|
||||
});
|
||||
assert.deepEqual(body.provider, {
|
||||
require_parameters: true,
|
||||
});
|
||||
assert.deepEqual(body.modalities, ["image", "text"]);
|
||||
assert.equal(body.stream, false);
|
||||
assert.equal(body.messages[0].content, "hello");
|
||||
});
|
||||
|
||||
test("OpenRouter request body omits image_config and provider guard when no image options are requested", () => {
|
||||
const body = buildRequestBody("hello", FLUX_MODEL, makeArgs(), []);
|
||||
|
||||
assert.equal(body.image_config, undefined);
|
||||
assert.equal(body.provider, undefined);
|
||||
assert.deepEqual(body.modalities, ["image"]);
|
||||
assert.equal(body.stream, false);
|
||||
assert.equal(body.messages[0].content, "hello");
|
||||
});
|
||||
|
||||
test("OpenRouter request body keeps multimodal array content when references are provided", () => {
|
||||
const content = buildContent("hello", ["data:image/png;base64,abc"]);
|
||||
assert.ok(Array.isArray(content));
|
||||
assert.deepEqual(content[0], { type: "text", text: "hello" });
|
||||
assert.deepEqual(content[1], {
|
||||
type: "image_url",
|
||||
image_url: { url: "data:image/png;base64,abc" },
|
||||
});
|
||||
});
|
||||
|
||||
test("OpenRouter size and aspect helpers infer expected defaults", () => {
|
||||
assert.equal(getImageSize(makeArgs()), null);
|
||||
assert.equal(getImageSize(makeArgs({ quality: "normal" })), "1K");
|
||||
assert.equal(getImageSize(makeArgs({ size: "2048x1024" })), "2K");
|
||||
assert.equal(getAspectRatio(GEMINI_MODEL, makeArgs({ size: "2048x1024" })), null);
|
||||
assert.equal(getAspectRatio(GEMINI_MODEL, makeArgs({ size: "1600x900" })), "16:9");
|
||||
assert.equal(getAspectRatio(GEMINI_MODEL, makeArgs({ size: "1024x4096" })), "1:4");
|
||||
assert.equal(getAspectRatio(GEMINI_25_MODEL, makeArgs({ size: "1024x4096" })), null);
|
||||
assert.equal(getAspectRatio(FLUX_MODEL, makeArgs({ size: "1024x4096" })), null);
|
||||
});
|
||||
|
||||
test("OpenRouter validates explicit aspect ratios against model support", () => {
|
||||
assert.doesNotThrow(() =>
|
||||
validateArgs(GEMINI_MODEL, makeArgs({ aspectRatio: "1:4" })),
|
||||
);
|
||||
assert.throws(
|
||||
() => validateArgs(GEMINI_25_MODEL, makeArgs({ aspectRatio: "1:4" })),
|
||||
/does not support aspect ratio 1:4/,
|
||||
);
|
||||
assert.throws(
|
||||
() => validateArgs(FLUX_MODEL, makeArgs({ aspectRatio: "1:4" })),
|
||||
/does not support aspect ratio 1:4/,
|
||||
);
|
||||
});
|
||||
|
||||
test("OpenRouter response extraction supports inline image data and finish_reason errors", async () => {
|
||||
const bytes = await extractImageFromResponse({
|
||||
choices: [
|
||||
{
|
||||
message: {
|
||||
images: [
|
||||
{
|
||||
image_url: {
|
||||
url: `data:image/png;base64,${Buffer.from("hello").toString("base64")}`,
|
||||
},
|
||||
},
|
||||
],
|
||||
},
|
||||
},
|
||||
],
|
||||
});
|
||||
assert.equal(Buffer.from(bytes).toString("utf8"), "hello");
|
||||
|
||||
await assert.rejects(
|
||||
() =>
|
||||
extractImageFromResponse({
|
||||
choices: [
|
||||
{
|
||||
finish_reason: "error",
|
||||
native_finish_reason: "MALFORMED_FUNCTION_CALL",
|
||||
message: { content: null },
|
||||
},
|
||||
],
|
||||
}),
|
||||
/finish_reason=MALFORMED_FUNCTION_CALL/,
|
||||
);
|
||||
});
|
||||
|
|
@ -3,6 +3,19 @@ import { readFile } from "node:fs/promises";
|
|||
import type { CliArgs } from "../types";
|
||||
|
||||
const DEFAULT_MODEL = "google/gemini-3.1-flash-image-preview";
|
||||
const COMMON_ASPECT_RATIOS = [
|
||||
"1:1",
|
||||
"2:3",
|
||||
"3:2",
|
||||
"3:4",
|
||||
"4:3",
|
||||
"4:5",
|
||||
"5:4",
|
||||
"9:16",
|
||||
"16:9",
|
||||
"21:9",
|
||||
];
|
||||
const GEMINI_EXTENDED_ASPECT_RATIOS = ["1:4", "4:1", "1:8", "8:1"];
|
||||
|
||||
type OpenRouterImageEntry = {
|
||||
image_url?: string | { url?: string | null } | null;
|
||||
|
|
@ -18,9 +31,11 @@ type OpenRouterMessagePart = {
|
|||
|
||||
type OpenRouterResponse = {
|
||||
choices?: Array<{
|
||||
finish_reason?: string | null;
|
||||
native_finish_reason?: string | null;
|
||||
message?: {
|
||||
images?: OpenRouterImageEntry[];
|
||||
content?: string | OpenRouterMessagePart[];
|
||||
content?: string | OpenRouterMessagePart[] | null;
|
||||
};
|
||||
}>;
|
||||
};
|
||||
|
|
@ -29,6 +44,24 @@ export function getDefaultModel(): string {
|
|||
return process.env.OPENROUTER_IMAGE_MODEL || DEFAULT_MODEL;
|
||||
}
|
||||
|
||||
function normalizeModelId(model: string): string {
|
||||
return model.trim().toLowerCase().split(":")[0]!;
|
||||
}
|
||||
|
||||
export function isGeminiImageModel(model: string): boolean {
|
||||
const normalized = normalizeModelId(model);
|
||||
return normalized.startsWith("google/gemini-") && normalized.includes("image-preview");
|
||||
}
|
||||
|
||||
function getSupportedAspectRatios(model: string): Set<string> {
|
||||
const normalized = normalizeModelId(model);
|
||||
if (normalized !== "google/gemini-3.1-flash-image-preview") {
|
||||
return new Set(COMMON_ASPECT_RATIOS);
|
||||
}
|
||||
|
||||
return new Set([...COMMON_ASPECT_RATIOS, ...GEMINI_EXTENDED_ASPECT_RATIOS]);
|
||||
}
|
||||
|
||||
function getApiKey(): string | null {
|
||||
return process.env.OPENROUTER_API_KEY || null;
|
||||
}
|
||||
|
|
@ -103,17 +136,45 @@ function inferImageSize(size: string | null): "1K" | "2K" | "4K" | null {
|
|||
return "4K";
|
||||
}
|
||||
|
||||
function getImageSize(args: CliArgs): "1K" | "2K" | "4K" {
|
||||
export function getImageSize(args: CliArgs): "1K" | "2K" | "4K" | null {
|
||||
if (args.imageSize) return args.imageSize as "1K" | "2K" | "4K";
|
||||
|
||||
const inferredFromSize = inferImageSize(args.size);
|
||||
if (inferredFromSize) return inferredFromSize;
|
||||
|
||||
return args.quality === "normal" ? "1K" : "2K";
|
||||
if (args.quality === "normal") return "1K";
|
||||
if (args.quality === "2k") return "2K";
|
||||
return null;
|
||||
}
|
||||
|
||||
function getAspectRatio(args: CliArgs): string | null {
|
||||
return args.aspectRatio || inferAspectRatio(args.size);
|
||||
export function getAspectRatio(model: string, args: CliArgs): string | null {
|
||||
if (args.aspectRatio) return args.aspectRatio;
|
||||
|
||||
const inferred = inferAspectRatio(args.size);
|
||||
if (!inferred || !getSupportedAspectRatios(model).has(inferred)) {
|
||||
return null;
|
||||
}
|
||||
|
||||
return inferred;
|
||||
}
|
||||
|
||||
function getModalities(model: string): string[] {
|
||||
return isGeminiImageModel(model) ? ["image", "text"] : ["image"];
|
||||
}
|
||||
|
||||
export function validateArgs(model: string, args: CliArgs): void {
|
||||
if (!args.aspectRatio) {
|
||||
return;
|
||||
}
|
||||
|
||||
const supported = getSupportedAspectRatios(model);
|
||||
if (supported.has(args.aspectRatio)) {
|
||||
return;
|
||||
}
|
||||
|
||||
throw new Error(
|
||||
`OpenRouter model ${model} does not support aspect ratio ${args.aspectRatio}. Supported values: ${Array.from(supported).join(", ")}`
|
||||
);
|
||||
}
|
||||
|
||||
function getMimeType(filename: string): string {
|
||||
|
|
@ -129,7 +190,14 @@ async function readImageAsDataUrl(filePath: string): Promise<string> {
|
|||
return `data:${getMimeType(filePath)};base64,${bytes.toString("base64")}`;
|
||||
}
|
||||
|
||||
function buildContent(prompt: string, referenceImages: string[]): Array<Record<string, unknown>> {
|
||||
export function buildContent(
|
||||
prompt: string,
|
||||
referenceImages: string[],
|
||||
): string | Array<Record<string, unknown>> {
|
||||
if (referenceImages.length === 0) {
|
||||
return prompt;
|
||||
}
|
||||
|
||||
const content: Array<Record<string, unknown>> = [{ type: "text", text: prompt }];
|
||||
|
||||
for (const imageUrl of referenceImages) {
|
||||
|
|
@ -171,8 +239,9 @@ async function downloadImage(value: string): Promise<Uint8Array> {
|
|||
return Uint8Array.from(Buffer.from(value, "base64"));
|
||||
}
|
||||
|
||||
async function extractImageFromResponse(result: OpenRouterResponse): Promise<Uint8Array> {
|
||||
const message = result.choices?.[0]?.message;
|
||||
export async function extractImageFromResponse(result: OpenRouterResponse): Promise<Uint8Array> {
|
||||
const choice = result.choices?.[0];
|
||||
const message = choice?.message;
|
||||
|
||||
for (const image of message?.images ?? []) {
|
||||
const imageUrl = extractImageUrl(image);
|
||||
|
|
@ -194,7 +263,50 @@ async function extractImageFromResponse(result: OpenRouterResponse): Promise<Uin
|
|||
if (inline) return inline;
|
||||
}
|
||||
|
||||
throw new Error("No image in OpenRouter response");
|
||||
const finishReason =
|
||||
choice?.native_finish_reason || choice?.finish_reason || "unknown";
|
||||
throw new Error(
|
||||
`No image in OpenRouter response (finish_reason=${finishReason})`,
|
||||
);
|
||||
}
|
||||
|
||||
export function buildRequestBody(
|
||||
prompt: string,
|
||||
model: string,
|
||||
args: CliArgs,
|
||||
referenceImages: string[],
|
||||
): Record<string, unknown> {
|
||||
const imageConfig: Record<string, string> = {};
|
||||
|
||||
const imageSize = getImageSize(args);
|
||||
if (imageSize) {
|
||||
imageConfig.image_size = imageSize;
|
||||
}
|
||||
|
||||
const aspectRatio = getAspectRatio(model, args);
|
||||
if (aspectRatio) {
|
||||
imageConfig.aspect_ratio = aspectRatio;
|
||||
}
|
||||
|
||||
const body: Record<string, unknown> = {
|
||||
messages: [
|
||||
{
|
||||
role: "user",
|
||||
content: buildContent(prompt, referenceImages),
|
||||
},
|
||||
],
|
||||
modalities: getModalities(model),
|
||||
stream: false,
|
||||
};
|
||||
|
||||
if (Object.keys(imageConfig).length > 0) {
|
||||
body.image_config = imageConfig;
|
||||
body.provider = {
|
||||
require_parameters: true,
|
||||
};
|
||||
}
|
||||
|
||||
return body;
|
||||
}
|
||||
|
||||
export async function generateImage(
|
||||
|
|
@ -212,32 +324,15 @@ export async function generateImage(
|
|||
referenceImages.push(await readImageAsDataUrl(refPath));
|
||||
}
|
||||
|
||||
const imageGenerationOptions: Record<string, string> = {
|
||||
size: getImageSize(args),
|
||||
};
|
||||
|
||||
const aspectRatio = getAspectRatio(args);
|
||||
if (aspectRatio) {
|
||||
imageGenerationOptions.aspect_ratio = aspectRatio;
|
||||
}
|
||||
|
||||
const body = {
|
||||
model,
|
||||
messages: [
|
||||
{
|
||||
role: "user",
|
||||
content: buildContent(prompt, referenceImages),
|
||||
},
|
||||
],
|
||||
modalities: ["image", "text"],
|
||||
max_tokens: 256,
|
||||
imageGenerationOptions,
|
||||
providerPreferences: {
|
||||
require_parameters: true,
|
||||
},
|
||||
...buildRequestBody(prompt, model, args, referenceImages),
|
||||
};
|
||||
|
||||
console.log(`Generating image with OpenRouter (${model})...`, imageGenerationOptions);
|
||||
console.log(
|
||||
`Generating image with OpenRouter (${model})...`,
|
||||
(body.image_config as Record<string, string>),
|
||||
);
|
||||
|
||||
const response = await fetch(`${getBaseUrl()}/chat/completions`, {
|
||||
method: "POST",
|
||||
|
|
|
|||
Loading…
Reference in New Issue