endpoint: https://llm-gateway.example.com/v1
api_key: ""            # optional; env LLMTB_API_KEY wins
models:
  - uni/deepseek-v4-flash-0731
  - uni/qwen3.6-27b
  - uni/btl-4
concurrency: 8         # default when omitted; matches internal/config's default
request_timeout: 900s  # default when omitted
max_tokens_default: 12000  # default when omitted; a reasoning model can spend
                            # thousands of tokens on reasoning_content before
                            # writing an answer, so this must stay generous