Reorganize third-party env integrations (TA, RG, etc.)

[willccbb]

Description

Adds an integrations folder for third-party environment bridges (currently just TextArena and ReasoningGym). Removes the envs extra in favor

Type of Change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation update
• Test improvement

Testing

• All existing tests pass when running uv run pytest locally.
• New tests have been added to cover the changes

Checklist

• My code follows the style guidelines of this project as outlined in AGENTS.md
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• Any dependent changes have been merged and published

---

Note

Reorganize third‑party environment integrations

• Move TextArenaEnv and ReasoningGymEnv to verifiers/envs/integrations/ with lazy imports updated in verifiers/__init__.py
• Replace bespoke Wordle environment with TextArenaEnv(game="Wordle-v0"); environments/wordle/wordle.py now wires rewards/feedback only
• Add optional extras: rg (reasoning-gym) and ta (textarena+nltk); remove previous envs extra; add mcp to core deps
• Improve integration classes: clearer ImportError messages, quiet NLTK downloads, proper setup_state/cleanup and done-handling in TextArenaEnv
• Docs: rewrite verifiers/envs/AGENTS.md to explain Core/Integrations/Experimental; add verifiers/envs/integrations/README.md
• Bump environments/reasoning_gym_env to version 0.1.4 and require verifiers>=0.1.8.post0

^{Written by Cursor Bugbot for commit 8c27e1d. This will update automatically on new commits. Configure here.}