fix: use Gemini v1 API endpoint instead of v1beta (#1082)

v1beta does not support newer models like gemini-3-flash, causing
silent 404 errors that back up the observation queue indefinitely.
Users with CLAUDE_MEM_GEMINI_MODEL=gemini-3-flash get zero observations
stored, with no visible error — the queue just grows silently.

Changes:
- Switch API URL from v1beta/models to v1/models (generateContent
  works identically on both endpoints)
- Add gemini-3-flash to GeminiModel type and RPM limits
- Update test to match new endpoint

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

tests/gemini_agent.test.ts

@@ -168,7 +168,7 @@ describe('GeminiAgent', () => {
 
     expect(global.fetch).toHaveBeenCalledTimes(1);
     const url = (global.fetch as any).mock.calls[0][0];
-    expect(url).toContain('https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-lite:generateContent');
+    expect(url).toContain('https://generativelanguage.googleapis.com/v1/models/gemini-2.5-flash-lite:generateContent');
     expect(url).toContain('key=test-api-key');
   });