Files
openclaw/extensions/minimax/image-generation-provider.ts
liyuan97 e2e9f979ca feat(minimax): add image generation provider and trim model catalog to M2.7 (#54487)
* feat(minimax): add image generation and TTS providers, trim TUI model list

Register MiniMax image-01 and speech-2.8 models as plugin providers for
the image_generate and TTS tools. Both resolve CN/global base URLs from
the configured model endpoint origin.

- Image generation: base64 response, aspect-ratio support, image-to-image
  via subject_reference, registered for minimax and minimax-portal
- TTS: speech-2.8-turbo (default) and speech-2.8-hd, hex-encoded audio,
  voice listing via get_voice API, telephony PCM support
- Add MiniMax to TTS auto-detection cascade (after ElevenLabs, before
  Microsoft) and TTS config section
- Remove MiniMax-VL-01, M2, M2.1, M2.5 and variants from TUI picker;
  keep M2.7 and M2.7-highspeed only (backend routing unchanged)

* feat(minimax): trim legacy model catalog to M2.7 only

Cherry-picked from temp/feat/minimax-trim-legacy-models (949ed28).
Removes MiniMax-VL-01, M2, M2.1, M2.5 and variants from the model
catalog, model order, modern model matchers, OAuth config, docs, and
tests. Keeps only M2.7 and M2.7-highspeed.

Conflicts resolved:
- provider-catalog.ts: removed MINIMAX_TUI_MODELS filter (no longer
  needed since source array is now M2.7-only)
- index.ts: kept image generation + speech provider registrations
  (added by this branch), moved media understanding registrations
  earlier (as intended by the cherry-picked commit)

* fix(minimax): update discovery contract test to reflect M2.7-only catalog

Cherry-picked from temp/feat/minimax-trim-legacy-models (2c750cb).

* feat(minimax): add web search provider and register in plugin entry

* fix(minimax): resolve OAuth credentials for TTS speech provider

* MiniMax: remove web search and TTS providers

* fix(minimax): throw on empty images array after generation failure

* feat(minimax): add image generation provider and trim catalog to M2.7 (#54487) (thanks @liyuan97)

---------

Co-authored-by: tars90percent <tars@minimaxi.com>
Co-authored-by: George Zhang <georgezhangtj97@gmail.com>
2026-03-25 09:29:35 -07:00

177 lines
5.1 KiB
TypeScript

import type { ImageGenerationProvider } from "openclaw/plugin-sdk/image-generation";
import { resolveApiKeyForProvider } from "openclaw/plugin-sdk/provider-auth";
const DEFAULT_MINIMAX_IMAGE_BASE_URL = "https://api.minimax.io";
const DEFAULT_MODEL = "image-01";
const DEFAULT_OUTPUT_MIME = "image/png";
const MINIMAX_SUPPORTED_ASPECT_RATIOS = [
"1:1",
"16:9",
"4:3",
"3:2",
"2:3",
"3:4",
"9:16",
"21:9",
] as const;
type MinimaxImageApiResponse = {
data?: {
image_base64?: string[];
};
metadata?: {
success_count?: number;
failed_count?: number;
};
id?: string;
base_resp?: {
status_code?: number;
status_msg?: string;
};
};
function resolveMinimaxImageBaseUrl(
cfg: Parameters<typeof resolveApiKeyForProvider>[0]["cfg"],
providerId: string,
): string {
const direct = cfg?.models?.providers?.[providerId]?.baseUrl?.trim();
if (!direct) {
return DEFAULT_MINIMAX_IMAGE_BASE_URL;
}
// Extract origin from the configured base URL (which may include path like /anthropic)
try {
return new URL(direct).origin;
} catch {
return DEFAULT_MINIMAX_IMAGE_BASE_URL;
}
}
function buildMinimaxImageProvider(providerId: string): ImageGenerationProvider {
return {
id: providerId,
label: "MiniMax",
defaultModel: DEFAULT_MODEL,
models: [DEFAULT_MODEL],
capabilities: {
generate: {
maxCount: 9,
supportsSize: false,
supportsAspectRatio: true,
supportsResolution: false,
},
edit: {
enabled: true,
maxCount: 9,
maxInputImages: 1,
supportsSize: false,
supportsAspectRatio: true,
supportsResolution: false,
},
geometry: {
aspectRatios: [...MINIMAX_SUPPORTED_ASPECT_RATIOS],
},
},
async generateImage(req) {
const auth = await resolveApiKeyForProvider({
provider: providerId,
cfg: req.cfg,
agentDir: req.agentDir,
store: req.authStore,
});
if (!auth.apiKey) {
throw new Error("MiniMax API key missing");
}
const baseUrl = resolveMinimaxImageBaseUrl(req.cfg, providerId);
const body: Record<string, unknown> = {
model: req.model || DEFAULT_MODEL,
prompt: req.prompt,
response_format: "base64",
n: req.count ?? 1,
};
if (req.aspectRatio?.trim()) {
body.aspect_ratio = req.aspectRatio.trim();
}
// Map input images to subject_reference for image-to-image generation
if (req.inputImages && req.inputImages.length > 0) {
const ref = req.inputImages[0];
const mime = ref.mimeType || "image/jpeg";
const dataUrl = `data:${mime};base64,${ref.buffer.toString("base64")}`;
body.subject_reference = [{ type: "character", image_file: dataUrl }];
}
const controller = new AbortController();
const timeoutMs = req.timeoutMs;
const timeout =
typeof timeoutMs === "number" && Number.isFinite(timeoutMs) && timeoutMs > 0
? setTimeout(() => controller.abort(), timeoutMs)
: undefined;
const response = await fetch(`${baseUrl}/v1/image_generation`, {
method: "POST",
headers: {
Authorization: `Bearer ${auth.apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify(body),
signal: controller.signal,
}).finally(() => {
clearTimeout(timeout);
});
if (!response.ok) {
const text = await response.text().catch(() => "");
throw new Error(
`MiniMax image generation failed (${response.status}): ${text || response.statusText}`,
);
}
const data = (await response.json()) as MinimaxImageApiResponse;
const baseResp = data.base_resp;
if (baseResp && typeof baseResp.status_code === "number" && baseResp.status_code !== 0) {
const msg = baseResp.status_msg ?? "";
throw new Error(`MiniMax image generation API error (${baseResp.status_code}): ${msg}`);
}
const base64Images = data.data?.image_base64 ?? [];
const failedCount = data.metadata?.failed_count ?? 0;
if (base64Images.length === 0) {
const reason =
failedCount > 0 ? `${failedCount} image(s) failed to generate` : "no images returned";
throw new Error(`MiniMax image generation returned no images: ${reason}`);
}
const images = base64Images
.map((b64, index) => {
if (!b64) {
return null;
}
return {
buffer: Buffer.from(b64, "base64"),
mimeType: DEFAULT_OUTPUT_MIME,
fileName: `image-${index + 1}.png`,
};
})
.filter((entry): entry is NonNullable<typeof entry> => entry !== null);
return {
images,
model: req.model || DEFAULT_MODEL,
};
},
};
}
export function buildMinimaxImageGenerationProvider(): ImageGenerationProvider {
return buildMinimaxImageProvider("minimax");
}
export function buildMinimaxPortalImageGenerationProvider(): ImageGenerationProvider {
return buildMinimaxImageProvider("minimax-portal");
}