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`