{"data":{"kind":"file","path":"README.md","version_id":"gas2t5nijw8jv9vmyhjzwfhw","entry":{"name":"README.md","path":"README.md","is_directory":false,"size":1805,"modified_at":"2026-02-14T11:26:51.789000","content_hash":"a3e47719c973f3fa2b702d71bd839a569a36f4fa3af2bb22be44aa10a5ab3bf1"},"entries":[],"content":"# openenv-textarena\n\n<a href=\"https://github.com/PrimeIntellect-ai/verifiers/tree/main/environments/openenv_textarena\">\n<img src=\"https://img.shields.io/badge/GitHub-181717?style=for-the-badge&logo=github&logoColor=white\" alt=\"Source Code\">\n</a>\n\n### Overview\n\n- **Environment ID**: `openenv-textarena`\n- **Short description**: OpenEnv TextArena gym integration (default game: `Wordle-v0`) via `OpenEnvEnv`.\n- **Tags**: openenv, gym, textarena, wordle, example\n\n### Datasets\n\n- **Primary dataset(s)**: Seed-generated episodes (one seed per rollout).\n- **Source links**: Bundled OpenEnv TextArena project in `proj/` (copied from OpenEnv).\n- **Split sizes**: 100 train / 50 eval by default (configurable).\n\n### Task\n\n- **Type**: Multi-turn gym interaction.\n- **Parser**: Default `Parser` (no special formatting).\n- **Rubric overview**: `OpenEnvEpisodicSumRubric` sums per-step rewards; `MultiTurnMonitorRubric` tracks turn count.\n\n### Quickstart\n\nBuild and register the bundled OpenEnv Docker image in the Prime registry:\n\n```bash\nuv run vf-build openenv-textarena\n```\n\nRun an evaluation with default settings:\n\n```bash\nprime eval run openenv-textarena\n```\n\n### Environment Arguments\n\n| Arg | Type | Default | Description |\n| --- | ---- | ------- | ----------- |\n| `num_train_examples` | int | `100` | Number of training seeds to generate. |\n| `num_eval_examples` | int | `50` | Number of eval seeds to generate. |\n| `seed` | int | `0` | Base seed for episode generation. |\n\n### Notes\n\n- Upstream TextArena app defaults to `TEXTARENA_ENV_ID=Wordle-v0`.\n- To use another game, set environment variables in the OpenEnv project/server config before building.\n- `openenv_textarena.py` defines `render_textarena_prompt()` and passes it via\n`prompt_renderer` so observations are rendered as useful game messages.\n","encoding":"utf-8","truncated":false,"total_bytes":1805},"status":null}