feat: add OLLAMA_NUM_CTX config to cap context window (#83)

- Add ollama_num_ctx setting (default 4096) to config.py
- Pass num_ctx option to Ollama in agent.py and agents/base.py
- Add OLLAMA_NUM_CTX to .env.example with usage docs
- Add context_window note in providers.yaml
- Fix mock_settings in test_agent.py for new attribute
- qwen3:30b with 4096 ctx uses ~19GB vs 45GB default

config/providers.yaml

@@ -28,6 +28,7 @@ providers:
       - name: qwen3.5:latest
         default: true
         context_window: 128000
+        # Note: actual context is capped by OLLAMA_NUM_CTX (default 4096) to save RAM
         capabilities: [text, tools, json, streaming]
       - name: llama3.1:8b-instruct
         context_window: 128000