{"data":{"kind":"file","path":"README.md","version_id":"m8xlhe2gaarre0igqudv7p4w","entry":{"name":"README.md","path":"README.md","is_directory":false,"size":1395,"modified_at":"2025-10-30T03:03:45.260000","content_hash":"903cc85a6b7821ff0c21653f34dacee4c4fab73bb41037da910e3473c18cb947"},"entries":[],"content":"# connect-x\n\n### Overview\n- **Environment ID**: `connect-x`\n- **Short description**: Two LLMs playing connect-x against one another!\n- **Tags**: <comma-separated tags>\n\n### Datasets\n- **Primary dataset(s)**: <name(s) and brief description>\n- **Source links**: <links>\n- **Split sizes**: <train/eval counts>\n\n### Task\n- **Type**: multi-turn\n- **Rubric overview**: If the user wins then 1, loss is 0, and tie is 0.5.\n\n### Quickstart\nRun an evaluation with default settings:\n\n```bash\nuv run vf-eval connect-x\n```\n\nConfigure model and sampling:\n\n```bash\nuv run vf-eval connect-x   -m gpt-4.1-mini   -n 20 -r 3 -t 1024 -T 0.7   -a '{\"key\": \"value\"}'  # env-specific args as JSON\n```\n\nNotes:\n- Use `-a` / `--env-args` to pass environment-specific configuration as a JSON object.\n\n### Environment Arguments\nDocument any supported environment arguments and their meaning. Example:\n\n| Arg | Type | Default | Description |\n| --- | ---- | ------- | ----------- |\n| `adv_model` | str | `\"gpt-4.1-mini\"` | Model to use for the opponent player |\n| `adv_base_url` | str | `\"https://api.openai.com/v1\"` | Base URL for the opponent's API endpoint |\n| `adv_api_key_var` | str | `\"OPENAI_API_KEY\"` | Environment variable name for the opponent's API key |\n| `runs` | int | `1` | Number of games to run |\n\n### Metrics\n| Metric | Meaning |\n| ------ | ------- |\n| `reward` | 0 for loss, 1 for win, and 0.5 for a tie |\n","encoding":"utf-8","truncated":false,"total_bytes":1395},"status":null}