feat: make Ollama model configurable via OLLAMA_MODEL env var

- Add OLLAMA_MODEL setting to shared config (default: qwen3:32b)
- LLM router reads from settings instead of hardcoded model name
- Create .env file with all configurable settings documented
- docker-compose passes OLLAMA_MODEL to llm-pool container

To change the model: edit OLLAMA_MODEL in .env and restart llm-pool.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

packages/shared/shared/config.py

@@ -112,6 +112,10 @@ class Settings(BaseSettings):
         default="http://localhost:11434",
         description="Ollama inference server base URL",
     )
+    ollama_model: str = Field(
+        default="qwen3:32b",
+        description="Ollama model to use for local inference (e.g., qwen3:32b, llama3.1:70b)",
+    )
 
     # -------------------------------------------------------------------------
     # Auth / Security