feat(text): default to MiniMax-M3 with 8192 max-tokens

- Default model MiniMax-M2.7 → MiniMax-M3 (frontier reasoning model, launched 2026-06-01)
- Default max_tokens 4096 → 8192 (M3 thinking phase consumes tokens; 4096 too tight)
- Update help text, examples, and the one test that asserts default model

Built on top of MiniMax-AI#168. Users can still override with --model flag for M2.7/M2.7-highspeed.

Author: raylanlin

src/commands/text/chat.ts

@@ -159,11 +159,11 @@ export default defineCommand({
   apiDocs: '/docs/api-reference/text-post',
   usage: 'mmx text chat --message <text> [flags]',
   options: [
-    { flag: '--model <model>', description: 'Model ID (default: MiniMax-M2.7)' },
+    { flag: '--model <model>', description: 'Model ID (default: MiniMax-M3)' },
     { flag: '--message <text>',        description: 'Message text (repeatable, prefix role: to set role)', required: true, type: 'array' },
     { flag: '--messages-file <path>',  description: 'JSON file with messages array (use - for stdin)' },
     { flag: '--system <text>',         description: 'System prompt' },
-    { flag: '--max-tokens <n>',        description: 'Maximum tokens to generate (default: 4096)', type: 'number' },
+    { flag: '--max-tokens <n>',        description: 'Maximum tokens to generate (default: 8192)', type: 'number' },
     { flag: '--temperature <n>',       description: 'Sampling temperature (0.0, 1.0]', type: 'number' },
     { flag: '--top-p <n>',             description: 'Nucleus sampling threshold', type: 'number' },
     { flag: '--stream',                description: 'Stream response tokens (default: on in TTY)' },
@@ -197,7 +197,7 @@ export default defineCommand({
 
     const model = (flags.model as string)
       || config.defaultTextModel
-      || 'MiniMax-M2.7';
+      || 'MiniMax-M3';
     const format = detectOutputFormat(config.output);
     const shouldStream = flags.stream === true || (
       flags.stream === undefined
@@ -208,7 +208,7 @@ export default defineCommand({
     const body: ChatRequest = {
       model,
       messages,
-      max_tokens: (flags.maxTokens as number) ?? 4096,
+      max_tokens: (flags.maxTokens as number) ?? 8192,
       stream: shouldStream,
     };
 

src/commands/text/repl.ts

@@ -294,9 +294,9 @@ export default defineCommand({
   description: 'Start an interactive multi-turn chat session',
   usage: 'mmx text repl [flags]',
   options: [
-    { flag: '--model <model>',     description: 'Model ID (default: MiniMax-M2.7)' },
+    { flag: '--model <model>',     description: 'Model ID (default: MiniMax-M3)' },
     { flag: '--system <text>',     description: 'System prompt' },
-    { flag: '--max-tokens <n>',    description: 'Maximum tokens per response (default: 4096)', type: 'number' },
+    { flag: '--max-tokens <n>',    description: 'Maximum tokens per response (default: 8192)', type: 'number' },
     { flag: '--temperature <n>',   description: 'Sampling temperature (0.0, 1.0]', type: 'number' },
     { flag: '--top-p <n>',         description: 'Nucleus sampling threshold', type: 'number' },
   ],
@@ -325,8 +325,8 @@ export default defineCommand({
     const state: ReplState = {
       messages: [],
       system: flags.system as string | undefined,
-      model: (flags.model as string) || config.defaultTextModel || 'MiniMax-M2.7',
-      maxTokens: (flags.maxTokens as number) ?? 4096,
+      model: (flags.model as string) || config.defaultTextModel || 'MiniMax-M3',
+      maxTokens: (flags.maxTokens as number) ?? 8192,
       temperature: flags.temperature !== undefined ? flags.temperature as number : undefined,
       topP: flags.topP !== undefined ? flags.topP as number : undefined,
     };

src/sdk/text/index.ts

@@ -56,8 +56,8 @@ export class TextSDK extends Client {
 
     return {
       ...params,
-      model: params.model ?? 'MiniMax-M2.7',
-      max_tokens: params.max_tokens ?? 4096,
+      model: params.model ?? 'MiniMax-M3',
+      max_tokens: params.max_tokens ?? 8192,
     } as ChatRequest;
   }
 }

test/commands/text/chat.test.ts

@@ -96,7 +96,7 @@ describe('text chat command', () => {
       });
 
       const parsed = JSON.parse(output);
-      expect(parsed.request.model).toBe('MiniMax-M2.7');
+      expect(parsed.request.model).toBe('MiniMax-M3');
       expect(parsed.request.messages).toHaveLength(1);
     } finally {
       console.log = originalLog;