fix: LLM_MODEL default to openrouter/deepseek/deepseek-v4-flash

LiteLLM requires openrouter/ prefix to route through openrouter API.
Without it, deepseek/* models route to Deepseek native API and fail
with the openrouter API key.

.env.example

@@ -6,7 +6,7 @@ LOG_LEVEL=info
 # --- LLM (LiteLLM provider/model) ---
 LLM_PROVIDER=openrouter
 LLM_API_KEY=sk-or-v1-PLACEHOLDER-replace-before-deploy
-LLM_MODEL=anthropic/claude-3.5-sonnet
+LLM_MODEL=openrouter/deepseek/deepseek-v4-flash
 LLM_API_BASE=
 
 # --- MCP Tool Server ---

docker-compose.yml

@@ -15,7 +15,7 @@ services:
       - PORT=${PORT:-8000}
       - LLM_PROVIDER=${LLM_PROVIDER:-openrouter}
       - LLM_API_KEY=${LLM_API_KEY}
-      - LLM_MODEL=${LLM_MODEL:-anthropic/claude-3.5-sonnet}
+      - LLM_MODEL=${LLM_MODEL:-openrouter/deepseek/deepseek-v4-flash}
       - LLM_API_BASE=${LLM_API_BASE:-}
       - MCP_SERVER_URL=${MCP_SERVER_URL:-http://mcp-tools:8501/mcp}
       - MCP_TIMEOUT=${MCP_TIMEOUT:-10}