feat: Add Qwen3-VL-Plus token limits (256K input, 32K output) (QwenLM#720)

- Added 256K input context window limit for Qwen3-VL-Plus model
- Updated output token limit from 8K to 32K for Qwen3-VL-Plus
- Added comprehensive tests for both input and output limits

As requested by Qwen maintainers for proper model support.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-authored-by: Claude <[email protected]>

Author: brandomagnani

packages/core/src/core/tokenLimits.test.ts

@@ -278,6 +278,11 @@ describe('tokenLimit with output type', () => {
       expect(tokenLimit('qwen-vl-max-latest', 'output')).toBe(8192); // 8K output
     });
 
+    it('should return different limits for input vs output for qwen3-vl-plus', () => {
+      expect(tokenLimit('qwen3-vl-plus', 'input')).toBe(262144); // 256K input
+      expect(tokenLimit('qwen3-vl-plus', 'output')).toBe(32768); // 32K output
+    });
+
     it('should return same default limits for unknown models', () => {
       expect(tokenLimit('unknown-model', 'input')).toBe(DEFAULT_TOKEN_LIMIT); // 128K input
       expect(tokenLimit('unknown-model', 'output')).toBe(

packages/core/src/core/tokenLimits.ts

@@ -135,6 +135,7 @@ const PATTERNS: Array<[RegExp, TokenCount]> = [
   [/^qwen-turbo.*$/, LIMITS['128k']],
 
   // Qwen Vision Models
+  [/^qwen3-vl-plus$/, LIMITS['256k']], // Qwen3-VL-Plus: 256K input
   [/^qwen-vl-max.*$/, LIMITS['128k']],
 
   // Generic vision-model: same as qwen-vl-max (128K token context)
@@ -187,8 +188,8 @@ const OUTPUT_PATTERNS: Array<[RegExp, TokenCount]> = [
   // Generic vision-model: same as qwen-vl-max-latest (8K max output tokens)
   [/^vision-model$/, LIMITS['8k']],
 
-  // Qwen3-VL-Plus: 8,192 max output tokens
-  [/^qwen3-vl-plus$/, LIMITS['8k']],
+  // Qwen3-VL-Plus: 32K max output tokens
+  [/^qwen3-vl-plus$/, LIMITS['32k']],
 ];
 
 /**