feat(xiaomi-tokenplan): add Claude-native MiMo V2.5 Pro alias via dedicated executor

Add mimo-v2.5-pro-claude alias routing to the Xiaomi TokenPlan Anthropic-compatible
/anthropic/v1/messages endpoint. Logic lives in a dedicated XiaomiTokenplanExecutor
(config-driven via targetFormat) instead of the shared DefaultExecutor.

Co-authored-by: Cursor <cursoragent@cursor.com>

open-sse/config/providerModels.js

@@ -549,6 +549,7 @@ export const PROVIDER_MODELS = {
   ],
   "xiaomi-tokenplan": [
     { id: "mimo-v2.5-pro", name: "MiMo V2.5 Pro" },
+    { id: "mimo-v2.5-pro-claude", name: "MiMo V2.5 Pro (Claude Native)", targetFormat: "claude", upstreamModelId: "mimo-v2.5-pro" },
     { id: "mimo-v2.5", name: "MiMo V2.5" },
     { id: "mimo-v2-pro", name: "MiMo V2 Pro" },
     { id: "mimo-v2-omni", name: "MiMo V2 Omni" },

open-sse/executors/default.js

@@ -1,5 +1,5 @@
 import { BaseExecutor } from "./base.js";
-import { PROVIDERS, resolveXiaomiTokenplanBaseUrl } from "../config/providers.js";
+import { PROVIDERS } from "../config/providers.js";
 import { OAUTH_ENDPOINTS, buildKimiHeaders } from "../config/appConstants.js";
 import { buildClineHeaders } from "../../src/shared/utils/clineAuth.js";
 import { getCachedClaudeHeaders } from "../utils/claudeHeaderCache.js";
@@ -60,9 +60,6 @@ export class DefaultExecutor extends BaseExecutor {
       case "gemini":
         return `${this.config.baseUrl}/${model}:${stream ? "streamGenerateContent?alt=sse" : "generateContent"}`;
       default: {
-        if (this.provider === "xiaomi-tokenplan") {
-          return `${resolveXiaomiTokenplanBaseUrl(credentials)}/chat/completions`;
-        }
         const url = this.config.baseUrl;
         if (url?.includes("{accountId}")) {
           const accountId = credentials?.providerSpecificData?.accountId;

open-sse/executors/index.js

@@ -15,6 +15,7 @@ import { GrokWebExecutor } from "./grok-web.js";
 import { PerplexityWebExecutor } from "./perplexity-web.js";
 import { OllamaLocalExecutor } from "./ollama-local.js";
 import { CommandCodeExecutor } from "./commandcode.js";
+import { XiaomiTokenplanExecutor } from "./xiaomi-tokenplan.js";
 import { DefaultExecutor } from "./default.js";
 
 const executors = {
@@ -37,6 +38,7 @@ const executors = {
   "perplexity-web": new PerplexityWebExecutor(),
   "ollama-local": new OllamaLocalExecutor(),
   commandcode: new CommandCodeExecutor(),
+  "xiaomi-tokenplan": new XiaomiTokenplanExecutor(),
 };
 
 const defaultCache = new Map();
@@ -70,3 +72,4 @@ export { GrokWebExecutor } from "./grok-web.js";
 export { PerplexityWebExecutor } from "./perplexity-web.js";
 export { OllamaLocalExecutor } from "./ollama-local.js";
 export { CommandCodeExecutor } from "./commandcode.js";
+export { XiaomiTokenplanExecutor } from "./xiaomi-tokenplan.js";

open-sse/executors/xiaomi-tokenplan.js

@@ -0,0 +1,19 @@
+import { DefaultExecutor } from "./default.js";
+import { resolveXiaomiTokenplanBaseUrl } from "../config/providers.js";
+import { getModelTargetFormat } from "../config/providerModels.js";
+import { FORMATS } from "../translator/formats.js";
+
+export class XiaomiTokenplanExecutor extends DefaultExecutor {
+  constructor() {
+    super("xiaomi-tokenplan");
+  }
+
+  // Claude-native aliases route to the Anthropic-compatible messages endpoint
+  buildUrl(model, stream, urlIndex = 0, credentials = null) {
+    const baseUrl = resolveXiaomiTokenplanBaseUrl(credentials);
+    if (getModelTargetFormat(model, model) === FORMATS.CLAUDE) {
+      return `${baseUrl.replace(/\/v1\/?$/, "/anthropic/v1")}/messages`;
+    }
+    return `${baseUrl}/chat/completions`;
+  }
+}

open-sse/handlers/chatCore.js

@@ -5,7 +5,7 @@ import { COLORS } from "../utils/stream.js";
 import { createStreamController } from "../utils/streamHandler.js";
 import { refreshWithRetry } from "../services/tokenRefresh.js";
 import { createRequestLogger } from "../utils/requestLogger.js";
-import { getModelTargetFormat, getModelStrip, PROVIDER_ID_TO_ALIAS } from "../config/providerModels.js";
+import { getModelTargetFormat, getModelStrip, getModelUpstreamId, PROVIDER_ID_TO_ALIAS } from "../config/providerModels.js";
 import { createErrorResult, parseUpstreamError, formatProviderError } from "../utils/error.js";
 import { HTTP_STATUS } from "../config/runtimeConfig.js";
 import { handleBypassRequest } from "../utils/bypassHandler.js";
@@ -41,6 +41,7 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
   const modelTargetFormat = getModelTargetFormat(alias, model);
   const targetFormat = modelTargetFormat || getTargetFormat(provider);
   const stripList = getModelStrip(alias, model);
+  const upstreamModel = getModelUpstreamId(alias, model);
 
   // Inject provider-level thinking config override (only if client hasn't set)
   // on/off → extended type (body.thinking), none/low/medium/high → effort type (body.reasoning_effort)
@@ -89,16 +90,16 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
   let toolNameMap;
   if (passthrough) {
     log?.debug?.("PASSTHROUGH", `${clientTool} → ${provider} | native lossless`);
-    translatedBody = { ...body, model };
+    translatedBody = { ...body, model: upstreamModel };
   } else {
-    translatedBody = translateRequest(sourceFormat, targetFormat, model, body, stream, credentials, provider, reqLogger, stripList, connectionId, clientTool);
+    translatedBody = translateRequest(sourceFormat, targetFormat, upstreamModel, body, stream, credentials, provider, reqLogger, stripList, connectionId, clientTool);
     if (!translatedBody) {
       trackPendingRequest(model, provider, connectionId, false, true);
       return createErrorResult(HTTP_STATUS.BAD_REQUEST, `Failed to translate request for ${sourceFormat} → ${targetFormat}`);
     }
     toolNameMap = translatedBody._toolNameMap;
     delete translatedBody._toolNameMap;
-    translatedBody.model = model;
+    translatedBody.model = upstreamModel;
   }
 
   // Dedupe duplicate built-in tools when equivalent MCP tools are present (Claude clients only).