fix: set Google thinking config by Gemini model version

Uses thinkingLevel for Gemini 3 Flash models
Keeps older Gemini Flash models on thinkingBudget: 0
Updates docs and tests for the new Google request payload

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

@@ -45,7 +45,8 @@ other runtime API.
     `ChatGPT-Account-Id`; expired tokens are refreshed against
     `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`.
+  - **Google** (`type: api`): `generateContent` with `x-goog-api-key`; Gemini 3
+    uses `thinkingLevel` while older Flash models use `thinkingBudget: 0`.
   - 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

@@ -213,6 +213,9 @@ const callAnthropic = async ({ apiKey, modelID, prompt, system, maxOutputTokens
 
 const callGoogle = async ({ apiKey, modelID, prompt, system, maxOutputTokens }) => {
   const url = `https://generativelanguage.googleapis.com/v1beta/models/${encodeURIComponent(modelID)}:generateContent`;
+  const thinkingConfig = modelID.toLowerCase().startsWith('gemini-3')
+    ? { thinkingLevel: modelID.toLowerCase().includes('flash') ? 'minimal' : 'low' }
+    : { thinkingBudget: 0 };
   const response = await fetch(url, {
     method: 'POST',
     headers: {
@@ -223,9 +226,7 @@ const callGoogle = async ({ apiKey, modelID, prompt, system, maxOutputTokens })
     body: JSON.stringify({
       contents: [{ role: 'user', parts: [{ text: prompt }] }],
       ...(system ? { systemInstruction: { parts: [{ text: system }] } } : {}),
-      // thinkingBudget 0 switches Gemini Flash thinking off; Flash is the only
+      generationConfig: { maxOutputTokens, thinkingConfig },
-      // family the small-model resolver picks for Google.
-      generationConfig: { maxOutputTokens, thinkingConfig: { thinkingBudget: 0 } },
     }),
     signal: AbortSignal.timeout(REQUEST_TIMEOUT_MS),
   });

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

@@ -336,3 +336,59 @@ describe('callSmallModel — custom provider config', () => {
     });
   });
 });
+
+describe('callSmallModel — Google thinking configuration', () => {
+  let fetchMock;
+  let originalFetch;
+
+  beforeEach(() => {
+    fetchMock = vi.fn();
+    originalFetch = globalThis.fetch;
+    globalThis.fetch = fetchMock;
+    readConfig.mockReset();
+    readConfig.mockReturnValue({});
+  });
+
+  afterEach(() => {
+    globalThis.fetch = originalFetch;
+  });
+
+  const googleResponse = (text) => ({
+    ok: true,
+    status: 200,
+    json: async () => ({ candidates: [{ content: { parts: [{ text }] } }] }),
+  });
+
+  it('uses thinkingLevel for Gemini 3 Flash models', async () => {
+    fetchMock.mockResolvedValue(googleResponse('generated commit'));
+
+    const text = await callSmallModel({
+      auth: { google: { type: 'api', key: 'google-key' } },
+      catalog: {},
+      workingDirectory: '/proj',
+      providerID: 'google',
+      modelID: 'gemini-3.1-flash-lite-preview',
+      prompt: 'generate',
+    });
+
+    expect(text).toBe('generated commit');
+    const body = JSON.parse(lastCall(fetchMock).init.body);
+    expect(body.generationConfig.thinkingConfig).toEqual({ thinkingLevel: 'minimal' });
+  });
+
+  it('keeps thinkingBudget disabled for Gemini 2.5 Flash models', async () => {
+    fetchMock.mockResolvedValue(googleResponse('generated commit'));
+
+    await callSmallModel({
+      auth: { google: { type: 'api', key: 'google-key' } },
+      catalog: {},
+      workingDirectory: '/proj',
+      providerID: 'google',
+      modelID: 'gemini-2.5-flash-lite',
+      prompt: 'generate',
+    });
+
+    const body = JSON.parse(lastCall(fetchMock).init.body);
+    expect(body.generationConfig.thinkingConfig).toEqual({ thinkingBudget: 0 });
+  });
+});