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>

docker-compose.yml

@@ -66,9 +66,10 @@ services:
     environment:
       - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY:-}
       - OPENAI_API_KEY=${OPENAI_API_KEY:-}
-      - OLLAMA_BASE_URL=http://host.docker.internal:11434
+      - OLLAMA_BASE_URL=${OLLAMA_BASE_URL:-http://host.docker.internal:11434}
+      - OLLAMA_MODEL=${OLLAMA_MODEL:-qwen3:32b}
       - REDIS_URL=redis://redis:6379/0
-      - LOG_LEVEL=INFO
+      - LOG_LEVEL=${LOG_LEVEL:-INFO}
     restart: unless-stopped
     healthcheck:
       test: ["CMD-SHELL", "curl -sf http://localhost:8004/health || exit 1"]

packages/llm-pool/llm_pool/router.py

@@ -32,7 +32,7 @@ _model_list: list[dict] = [
     {
         "model_name": "local",
         "litellm_params": {
-            "model": "ollama/qwen3:32b",
+            "model": f"ollama/{settings.ollama_model}",
             "api_base": settings.ollama_base_url,
         },
     },
@@ -40,7 +40,7 @@ _model_list: list[dict] = [
     {
         "model_name": "fast",
         "litellm_params": {
-            "model": "ollama/qwen3:32b",
+            "model": f"ollama/{settings.ollama_model}",
             "api_base": settings.ollama_base_url,
         },
     },
@@ -48,7 +48,7 @@ _model_list: list[dict] = [
     {
         "model_name": "economy",
         "litellm_params": {
-            "model": "ollama/qwen3:32b",
+            "model": f"ollama/{settings.ollama_model}",
             "api_base": settings.ollama_base_url,
         },
     },
@@ -56,7 +56,7 @@ _model_list: list[dict] = [
     {
         "model_name": "balanced",
         "litellm_params": {
-            "model": "ollama/qwen3:32b",
+            "model": f"ollama/{settings.ollama_model}",
             "api_base": settings.ollama_base_url,
         },
     },

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