allow proxy auto model selection

src/test/llm.test.js

@@ -4,7 +4,7 @@ import axios from 'axios';
 import { extractBalancedJSON, extractJSONText, extractMeaningfulError, mapWithConcurrency } from '../llm.js';
 
 const ENV_KEYS = [
-  'CLI_PROXY_API', 'CLI_PROXY_API_KEY', 'MODEL', 'INPUT_MODEL', 'OPENCODE_MODEL',
+  'CLI_PROXY_API', 'CLI_PROXY_API_KEY', 'CLI_PROXY_API_MODEL', 'MODEL', 'INPUT_MODEL', 'OPENCODE_MODEL',
   'AI_ASSISTANT_TIMEOUT_MS', 'AI_ASSISTANT_MAX_BUFFER',
 ];
 
@@ -57,6 +57,25 @@ describe('chat - CLIProxyAPI', async () => {
     assert.equal(capturedOpts.headers.Authorization, 'Bearer secret');
   });
 
+  it('omits model from the request body when auto selection is allowed', async () => {
+    process.env.CLI_PROXY_API = 'https://proxy.example';
+    process.env.CLI_PROXY_API_KEY = 'secret';
+
+    let capturedBody;
+    mock.method(axios, 'post', async (url, body) => {
+      capturedBody = body;
+      return {
+        data: { choices: [{ message: { content: 'cli response' } }] },
+        headers: {},
+      };
+    });
+
+    const result = await chat('sys', 'user');
+
+    assert.equal(result, 'cli response');
+    assert.equal(Object.hasOwn(capturedBody, 'model'), false);
+  });
+
   it('throws an error when the API fails', async () => {
     process.env.CLI_PROXY_API = 'https://proxy.example';
     process.env.MODEL = 'gpt-5-mini';