fix: wire modelstudio env discovery (#40634) (thanks @pomelo-nwu)

CHANGELOG.md

@@ -74,6 +74,7 @@ Docs: https://docs.openclaw.ai
 - Discord/Telegram outbound runtime config: thread runtime-resolved config through Discord and Telegram send paths so SecretRef-based credentials stay resolved during message delivery. (#42352) Thanks @joshavant.
 - Secrets/SecretRef: reject exec SecretRef traversal ids across schema, runtime, and gateway. (#42370) Thanks @joshavant.
 - Telegram/docs: clarify that `channels.telegram.groups` allowlists chats while `groupAllowFrom` allowlists users inside those chats, and point invalid negative chat IDs at the right config key. (#42451) Thanks @altaywtf.
+- Models/Alibaba Cloud Model Studio: wire `MODELSTUDIO_API_KEY` through shared env auth, implicit provider discovery, and shell-env fallback so onboarding works outside the wizard too. (#40634) Thanks @pomelo-nwu.
 
 ## 2026.3.8
 

src/agents/model-auth-env-vars.ts

@@ -32,6 +32,7 @@ export const PROVIDER_ENV_API_KEY_CANDIDATES: Record<string, string[]> = {
   mistral: ["MISTRAL_API_KEY"],
   together: ["TOGETHER_API_KEY"],
   qianfan: ["QIANFAN_API_KEY"],
+  modelstudio: ["MODELSTUDIO_API_KEY"],
   ollama: ["OLLAMA_API_KEY"],
   vllm: ["VLLM_API_KEY"],
   kilocode: ["KILOCODE_API_KEY"],

src/agents/model-auth.profiles.test.ts

@@ -230,6 +230,21 @@ describe("getApiKeyForModel", () => {
     });
   });
 
+  it("resolves Model Studio API key from env", async () => {
+    await withEnvAsync(
+      { [envVar("MODELSTUDIO", "API", "KEY")]: "modelstudio-test-key" },
+      async () => {
+        // pragma: allowlist secret
+        const resolved = await resolveApiKeyForProvider({
+          provider: "modelstudio",
+          store: { version: 1, profiles: {} },
+        });
+        expect(resolved.apiKey).toBe("modelstudio-test-key");
+        expect(resolved.source).toContain("MODELSTUDIO_API_KEY");
+      },
+    );
+  });
+
   it("resolves synthetic local auth key for configured ollama provider without apiKey", async () => {
     await withEnvAsync({ OLLAMA_API_KEY: undefined }, async () => {
       const resolved = await resolveApiKeyForProvider({

src/agents/models-config.e2e-harness.ts

@@ -101,6 +101,7 @@ export const MODELS_CONFIG_IMPLICIT_ENV_VARS = [
   "OPENROUTER_API_KEY",
   "PI_CODING_AGENT_DIR",
   "QIANFAN_API_KEY",
+  "MODELSTUDIO_API_KEY",
   "QWEN_OAUTH_TOKEN",
   "QWEN_PORTAL_API_KEY",
   "SYNTHETIC_API_KEY",

src/agents/models-config.providers.modelstudio.test.ts

@@ -0,0 +1,32 @@
+import { mkdtempSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { describe, expect, it } from "vitest";
+import { withEnvAsync } from "../test-utils/env.js";
+import { resolveImplicitProvidersForTest } from "./models-config.e2e-harness.js";
+import { buildModelStudioProvider } from "./models-config.providers.js";
+
+const modelStudioApiKeyEnv = ["MODELSTUDIO_API", "KEY"].join("_");
+
+describe("Model Studio implicit provider", () => {
+  it("should include modelstudio when MODELSTUDIO_API_KEY is configured", async () => {
+    const agentDir = mkdtempSync(join(tmpdir(), "openclaw-test-"));
+    const modelStudioApiKey = "test-key"; // pragma: allowlist secret
+    await withEnvAsync({ [modelStudioApiKeyEnv]: modelStudioApiKey }, async () => {
+      const providers = await resolveImplicitProvidersForTest({ agentDir });
+      expect(providers?.modelstudio).toBeDefined();
+      expect(providers?.modelstudio?.apiKey).toBe("MODELSTUDIO_API_KEY");
+      expect(providers?.modelstudio?.baseUrl).toBe("https://coding-intl.dashscope.aliyuncs.com/v1");
+    });
+  });
+
+  it("should build the static Model Studio provider catalog", () => {
+    const provider = buildModelStudioProvider();
+    const modelIds = provider.models.map((model) => model.id);
+    expect(provider.api).toBe("openai-completions");
+    expect(provider.baseUrl).toBe("https://coding-intl.dashscope.aliyuncs.com/v1");
+    expect(modelIds).toContain("qwen3.5-plus");
+    expect(modelIds).toContain("qwen3-coder-plus");
+    expect(modelIds).toContain("kimi-k2.5");
+  });
+});

src/agents/models-config.providers.static.ts

@@ -137,6 +137,90 @@ const QIANFAN_DEFAULT_COST = {
   cacheWrite: 0,
 };
 
+export const MODELSTUDIO_BASE_URL = "https://coding-intl.dashscope.aliyuncs.com/v1";
+export const MODELSTUDIO_DEFAULT_MODEL_ID = "qwen3.5-plus";
+const MODELSTUDIO_DEFAULT_COST = {
+  input: 0,
+  output: 0,
+  cacheRead: 0,
+  cacheWrite: 0,
+};
+
+const MODELSTUDIO_MODEL_CATALOG: ReadonlyArray<ProviderModelConfig> = [
+  {
+    id: "qwen3.5-plus",
+    name: "qwen3.5-plus",
+    reasoning: false,
+    input: ["text", "image"],
+    cost: MODELSTUDIO_DEFAULT_COST,
+    contextWindow: 1_000_000,
+    maxTokens: 65_536,
+  },
+  {
+    id: "qwen3-max-2026-01-23",
+    name: "qwen3-max-2026-01-23",
+    reasoning: false,
+    input: ["text"],
+    cost: MODELSTUDIO_DEFAULT_COST,
+    contextWindow: 262_144,
+    maxTokens: 65_536,
+  },
+  {
+    id: "qwen3-coder-next",
+    name: "qwen3-coder-next",
+    reasoning: false,
+    input: ["text"],
+    cost: MODELSTUDIO_DEFAULT_COST,
+    contextWindow: 262_144,
+    maxTokens: 65_536,
+  },
+  {
+    id: "qwen3-coder-plus",
+    name: "qwen3-coder-plus",
+    reasoning: false,
+    input: ["text"],
+    cost: MODELSTUDIO_DEFAULT_COST,
+    contextWindow: 1_000_000,
+    maxTokens: 65_536,
+  },
+  {
+    id: "MiniMax-M2.5",
+    name: "MiniMax-M2.5",
+    reasoning: false,
+    input: ["text"],
+    cost: MODELSTUDIO_DEFAULT_COST,
+    contextWindow: 1_000_000,
+    maxTokens: 65_536,
+  },
+  {
+    id: "glm-5",
+    name: "glm-5",
+    reasoning: false,
+    input: ["text"],
+    cost: MODELSTUDIO_DEFAULT_COST,
+    contextWindow: 202_752,
+    maxTokens: 16_384,
+  },
+  {
+    id: "glm-4.7",
+    name: "glm-4.7",
+    reasoning: false,
+    input: ["text"],
+    cost: MODELSTUDIO_DEFAULT_COST,
+    contextWindow: 202_752,
+    maxTokens: 16_384,
+  },
+  {
+    id: "kimi-k2.5",
+    name: "kimi-k2.5",
+    reasoning: false,
+    input: ["text", "image"],
+    cost: MODELSTUDIO_DEFAULT_COST,
+    contextWindow: 262_144,
+    maxTokens: 32_768,
+  },
+];
+
 const NVIDIA_BASE_URL = "https://integrate.api.nvidia.com/v1";
 const NVIDIA_DEFAULT_MODEL_ID = "nvidia/llama-3.1-nemotron-70b-instruct";
 const NVIDIA_DEFAULT_CONTEXT_WINDOW = 131072;
@@ -384,6 +468,14 @@ export function buildQianfanProvider(): ProviderConfig {
   };
 }
 
+export function buildModelStudioProvider(): ProviderConfig {
+  return {
+    baseUrl: MODELSTUDIO_BASE_URL,
+    api: "openai-completions",
+    models: MODELSTUDIO_MODEL_CATALOG.map((model) => ({ ...model })),
+  };
+}
+
 export function buildNvidiaProvider(): ProviderConfig {
   return {
     baseUrl: NVIDIA_BASE_URL,

src/agents/models-config.providers.ts

@@ -29,6 +29,7 @@ import {
   buildKilocodeProvider,
   buildMinimaxPortalProvider,
   buildMinimaxProvider,
+  buildModelStudioProvider,
   buildMoonshotProvider,
   buildNvidiaProvider,
   buildOpenAICodexProvider,
@@ -46,8 +47,11 @@ export {
   buildKimiCodingProvider,
   buildKilocodeProvider,
   buildNvidiaProvider,
+  buildModelStudioProvider,
   buildQianfanProvider,
   buildXiaomiProvider,
+  MODELSTUDIO_BASE_URL,
+  MODELSTUDIO_DEFAULT_MODEL_ID,
   QIANFAN_BASE_URL,
   QIANFAN_DEFAULT_MODEL_ID,
   XIAOMI_DEFAULT_MODEL_ID,
@@ -512,6 +516,7 @@ const SIMPLE_IMPLICIT_PROVIDER_LOADERS: ImplicitProviderLoader[] = [
     apiKey,
   })),
   withApiKey("qianfan", async ({ apiKey }) => ({ ...buildQianfanProvider(), apiKey })),
+  withApiKey("modelstudio", async ({ apiKey }) => ({ ...buildModelStudioProvider(), apiKey })),
   withApiKey("openrouter", async ({ apiKey }) => ({ ...buildOpenrouterProvider(), apiKey })),
   withApiKey("nvidia", async ({ apiKey }) => ({ ...buildNvidiaProvider(), apiKey })),
   withApiKey("kilocode", async ({ apiKey }) => ({

src/commands/onboard-non-interactive.provider-auth.test.ts

@@ -611,6 +611,26 @@ describe("onboard (non-interactive): provider auth", () => {
     });
   });
 
+  it("infers Model Studio auth choice from --modelstudio-api-key and sets default model", async () => {
+    await withOnboardEnv("openclaw-onboard-modelstudio-infer-", async (env) => {
+      const cfg = await runOnboardingAndReadConfig(env, {
+        modelstudioApiKey: "modelstudio-test-key", // pragma: allowlist secret
+      });
+
+      expect(cfg.auth?.profiles?.["modelstudio:default"]?.provider).toBe("modelstudio");
+      expect(cfg.auth?.profiles?.["modelstudio:default"]?.mode).toBe("api_key");
+      expect(cfg.models?.providers?.modelstudio?.baseUrl).toBe(
+        "https://coding-intl.dashscope.aliyuncs.com/v1",
+      );
+      expect(cfg.agents?.defaults?.model?.primary).toBe("modelstudio/qwen3.5-plus");
+      await expectApiKeyProfile({
+        profileId: "modelstudio:default",
+        provider: "modelstudio",
+        key: "modelstudio-test-key",
+      });
+    });
+  });
+
   it("configures a custom provider from non-interactive flags", async () => {
     await withOnboardEnv("openclaw-onboard-custom-provider-", async ({ configPath, runtime }) => {
       await runNonInteractiveOnboardingWithDefaults(runtime, {

src/config/io.ts

@@ -68,6 +68,7 @@ const SHELL_ENV_EXPECTED_KEYS = [
   "OPENROUTER_API_KEY",
   "AI_GATEWAY_API_KEY",
   "MINIMAX_API_KEY",
+  "MODELSTUDIO_API_KEY",
   "SYNTHETIC_API_KEY",
   "KILOCODE_API_KEY",
   "ELEVENLABS_API_KEY",