fix(small-model): omit thinkingConfig for non-reasoning Google models

packages/web/server/lib/small-model/DOCUMENTATION.md

@@ -96,7 +96,8 @@ other runtime API.
     `auth.openai.com` (single-flight) and written back to `auth.json`.
   - **Anthropic** (`type: api`): `/v1/messages` with `x-api-key`.
   - **Google** (`type: api`): `generateContent` with `x-goog-api-key`; Gemini 3
-    uses `thinkingLevel` while older Flash models use `thinkingBudget: 0`.
+    uses `thinkingLevel`, Gemini 2.x uses `thinkingBudget: 0`, and all other
+    models omit `thinkingConfig` entirely.
   - Everything else: OpenAI-compatible `/chat/completions` against the
     provider's base URL, resolved from (1) `provider.<id>.options.baseURL`
     in the OpenCode config, (2) the hardcoded `https://api.openai.com/v1`

packages/web/server/lib/small-model/call.js

@@ -402,9 +402,10 @@ const getCopilotEndpoint = async ({ baseURL, headers, modelID }) => {
 
 const callGoogle = async ({ apiKey, modelID, prompt, system, maxOutputTokens, responseSchema, timeoutMs, signal }) => {
   const url = `https://generativelanguage.googleapis.com/v1beta/models/${encodeURIComponent(modelID)}:generateContent`;
-  const thinkingConfig = modelID.toLowerCase().startsWith('gemini-3')
+  const lowerModelID = modelID.toLowerCase();
-    ? { thinkingLevel: modelID.toLowerCase().includes('flash') ? 'minimal' : 'low' }
+  const thinkingConfig = lowerModelID.startsWith('gemini-3')
-    : { thinkingBudget: 0 };
+    ? { thinkingLevel: lowerModelID.includes('flash') ? 'minimal' : 'low' }
+    : lowerModelID.startsWith('gemini-2') ? { thinkingBudget: 0 } : null;
   const response = await fetch(url, {
     method: 'POST',
     headers: {
@@ -414,13 +415,11 @@ const callGoogle = async ({ apiKey, modelID, prompt, system, maxOutputTokens, re
     },
     body: JSON.stringify({
       contents: [{ role: 'user', parts: [{ text: prompt }] }],
-      ...(system ? { systemInstruction: { parts: [{ text: system }] } } : {}),
+      ...(system && { systemInstruction: { parts: [{ text: system }] } }),
       generationConfig: {
         maxOutputTokens,
-        thinkingConfig,
+        ...(thinkingConfig && { thinkingConfig }),
-        ...(responseSchema
+        ...(responseSchema && { responseMimeType: 'application/json', responseSchema: toGoogleSchema(responseSchema) }),
-          ? { responseMimeType: 'application/json', responseSchema: toGoogleSchema(responseSchema) }
-          : {}),
       },
     }),
     signal: requestSignal(timeoutMs, signal),

packages/web/server/lib/small-model/call.test.js

@@ -457,6 +457,22 @@ describe('callSmallModel — Google thinking configuration', () => {
     const body = JSON.parse(lastCall(fetchMock).init.body);
     expect(body.generationConfig.thinkingConfig).toEqual({ thinkingBudget: 0 });
   });
+
+  it('omits thinkingConfig for other Google/Gemini models', async () => {
+    fetchMock.mockResolvedValue(googleResponse('generated commit'));
+
+    await callSmallModel({
+      auth: { google: { type: 'api', key: 'google-key' } },
+      catalog: {},
+      workingDirectory: '/proj',
+      providerID: 'google',
+      modelID: 'gemini-1.5-flash',
+      prompt: 'generate',
+    });
+
+    const body = JSON.parse(lastCall(fetchMock).init.body);
+    expect(body.generationConfig.thinkingConfig).toBeUndefined();
+  });
 });
 
 describe('callSmallModel — GitHub Copilot endpoint routing', () => {