feat: Ollama adapter + chat rate limiter (30 req/hour)

Ollama adapter (internal/chat/ollama.go):
- Implements model.LLM interface for ADK Go
- Talks to Ollama's OpenAI-compatible API (/v1/chat/completions)
- Full tool/function calling support (tested with Mistral Small 3.2)
- Converts ADK types to OpenAI format (messages, tools, tool_calls)
- Configurable via OLLAMA_HOST and OLLAMA_MODEL env vars

Multi-provider handler:
- MODEL_PROVIDER env: "gemini" (default) or "ollama"
- Gemini: requires GOOGLE_API_KEY (pay-as-you-go recommended)
- Ollama: connects to local or Tailscale-remote instance

Rate limiter:
- 30 requests/hour per IP on /api/chat endpoint
- Uses existing middleware.NewRateLimiter pattern

Tested: Ollama + Mistral Small 3.2 on M4 Pro 64GB — correct answers

.env.example

@@ -80,6 +80,19 @@ SMTP_PASSWORD=your-password
 SMTP_FROM_EMAIL=your-email@yourdomain.com
 CONTACT_EMAIL=recipient@example.com
 
+# Chat AI Configuration
+#
+# MODEL_PROVIDER: "gemini" (default) or "ollama"
+# MODEL_PROVIDER=gemini
+#
+# Gemini settings (when MODEL_PROVIDER=gemini):
+# GOOGLE_API_KEY=your-google-api-key
+# MODEL_NAME=gemini-2.5-flash
+#
+# Ollama settings (when MODEL_PROVIDER=ollama):
+# OLLAMA_HOST=http://localhost:11434
+# OLLAMA_MODEL=mistral-small3.2
+
 # Production Settings
 # Uncomment for production:
 # GO_ENV=production