platoon-textcraft 0.1.0__tar.gz

platoon_textcraft-0.1.0/.gitignore

@@ -0,0 +1,232 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+.tmp
+
+results_*/
+
+logs.md
+
+*.code-workspace
+
+**.pt
+logs*.md
+.vscode/
+countdown*.md
+
+nohup*.out
+logs/
+
+.claude/
+inference_results/
+*.deb
+slurm*.out
+external/
+# Run outputs of the tutorials and examples
+runs/
+wandb/

platoon_textcraft-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Apurva Gandhi
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

platoon_textcraft-0.1.0/PKG-INFO

@@ -0,0 +1,229 @@
+Metadata-Version: 2.5
+Name: platoon-textcraft
+Version: 0.1.0
+Summary: TextCraft and TextCraft-Synth: crafting environments for LLM agents (ORS), with platoon's named environments and a Harbor export.
+Project-URL: Source, https://github.com/ApGa/platoon/tree/main/extensions/textcraft
+Author-email: Apurva Gandhi <apurvag@cs.cmu.edu>
+License-Expression: MIT
+License-File: LICENSE
+Requires-Python: >=3.12
+Requires-Dist: openreward>=0.1.125
+Requires-Dist: pydantic>=2
+Provides-Extra: platoon
+Requires-Dist: platoon[ors]<0.3,>=0.2; extra == 'platoon'
+Description-Content-Type: text/markdown
+
+# TextCraft for platoon
+
+`platoon-textcraft` is platoon's first-party TextCraft extension: crafting environments for training tool-using and
+recursive LLM agents, served as [OpenReward](https://openreward.ai) (ORS) environments, with platoon's named
+environments, the CodeAct prompts of platoon's TextCraft agents, and an export of TextCraft-Synth as a
+[Harbor](https://github.com/harbor-framework/harbor) dataset.
+
+- **TextCraft** comes from [ADaPT](https://arxiv.org/abs/2311.05772) (Prasad et al., Findings of NAACL 2024): craft
+  Minecraft items by their recipes, with shallow crafting trees.
+- **TextCraft-Synth** is platoon's synthetic variant: generated recipes with deeper crafting trees (up to 12
+  levels), abstract item names and difficulty tags. The [RAO recipe](https://github.com/ApGa/platoon/blob/platoon-textcraft-v0.1.0/recipes/rao/README.md) trains on it.
+
+## Install
+
+```bash
+pip install 'platoon-textcraft[platoon]'
+```
+
+The `platoon` extra installs platoon 0.2 with its `ors` extra (`platoon[ors]>=0.2,<0.3`), for what imports platoon:
+the prompt builders, the named environments and the task generators. To train or evaluate with platoon, add its
+`tinker` extra: `pip install 'platoon[tinker,ors]' 'platoon-textcraft[platoon]'`. The environments themselves need
+only openreward and pydantic: `platoon_textcraft.env` imports neither platoon nor IPython, so any ORS client can serve
+them after `pip install platoon-textcraft`.
+
+The configs below and the tests are in platoon's repository, not in the package. From a checkout of platoon, in its
+uv workspace:
+
+```bash
+uv sync --package platoon-textcraft --extra platoon     # the extension, platoon and the test tools
+```
+
+or into an environment of your own: `uv pip install -e "extensions/textcraft[platoon]"`.
+
+## Environments
+
+| Service | Recipes | Splits |
+|---|---|---|
+| `python://platoon_textcraft.env:TextCraftEnvironment` | Minecraft | `train` (1,000), `val` (100) |
+| `python://platoon_textcraft.env:TextCraftSynthEnvironment` | synthetic | `train` (2,522), `val` (632), and `<split>-<difficulty>`: `train-medium` holds the 852 RAO training tasks |
+
+Task ids are `<split>:<index>`. The tools are `craft(ingredients, target)`, `get_info(items)`, `view_inventory()` and
+the terminal `finish(message)`, which grades the episode: success (reward 1) when every target was crafted on top
+of the starting inventory and the message is not empty.
+
+Subagents share their parent's inventory: the environment's `platoon_fork(task_spec)` gives a child its own targets
+(parsed from its goal, `Craft the following items: 2x stick, ...`) on the same inventory, and the child's `finish`
+grades its own targets (`agents.child_grading: env`).
+
+## Named environments
+
+Installed, the extension registers `textcraft@1` and `textcraft-synth@1` in the `platoon.environments` entry-point
+group (`entries.py`). Each stands for the environment, the TextCraft prompts for `platoon-codeact`
+(`platoon_textcraft.prompts:TextCraftPromptBuilder`) and the `val` split for evaluation; `textcraft-synth@1` also
+scores with platoon's RAO reward processor, `platoon-delegation`. A config names one with `env:`, picks the arm of
+the prompts with `prompt_builder_options.variant` (`linear`, `recursive` or `depth_aware`) and adds the rest:
+
+```yaml
+environments:
+  - env: textcraft-synth@1
+    harness: platoon-codeact
+    harness_options:
+      prompt_builder_options: {variant: recursive}
+    agents: {max_depth: null, budget: linear, child_grading: env}
+    dataset_kwargs: {split_name: train-medium}
+```
+
+`platoon env show textcraft-synth` prints what it stands for, and `platoon extensions check platoon-textcraft`
+checks the extension's metadata. The default episode program, `single`, applies the rollout config's
+`skip_subagent_reward_computation` and `propagate_root_success`, in that order.
+
+## Configs
+
+| Config | What it runs |
+|---|---|
+| `configs/textcraft_train.yaml` | Trains the recursive agent on original TextCraft: the first 1,000 training tasks, 50 steps per episode |
+| `configs/textcraft_eval.yaml` | Evaluates the recursive agent on the first 100 validation tasks of original TextCraft |
+| `configs/textcraft_synth_eval.yaml` | Evaluates the linear agent on TextCraft-Synth, greedy, up to 800 steps: the easy, medium and hard validation tasks, shuffled with seed 42, first 100 |
+
+```bash
+platoon train extensions/textcraft/configs/textcraft_train.yaml
+platoon eval extensions/textcraft/configs/textcraft_synth_eval.yaml inference.model_path=tinker://...
+```
+
+The RAO paper's TextCraft-Synth experiments, its single agent against its recursive agent and its ablation of the
+subagents' rewards, are a recipe of their own: [`recipes/rao/`](https://github.com/ApGa/platoon/blob/platoon-textcraft-v0.1.0/recipes/rao/README.md).
+
+## Data
+
+The task files ship in the package, under `src/platoon_textcraft/data/`, and `data/SHA256SUMS` pins them:
+
+| File | Tasks |
+|---|---|
+| `textcraft_train.jsonl`, `textcraft_val.jsonl` | 1,000 and 100 original TextCraft tasks |
+| `textcraft_synth_train.jsonl`, `textcraft_synth_val.jsonl` | 2,522 and 632 TextCraft-Synth tasks, the source of the published Harbor dataset |
+
+`data/recipes/` holds the 860 recipes of original TextCraft: the recipe files of Minecraft: Java Edition 1.16.5 (the
+game's `data/minecraft/recipes/`), unmodified, as
+[InventivetalentDev/minecraft-assets](https://github.com/InventivetalentDev/minecraft-assets/tree/1b7a1d48b0343c0b8da80604598707df428dc32a/data/minecraft/recipes)
+extracted them from the game. ADaPT's README sends TextCraft's users there for them; ADaPT's repository does not
+include them. TextCraft-Synth needs no recipe files: the environment builds its world in memory (seed 42, 25 items
+per domain and tier, 1,452 items).
+
+Every task keeps its gold trajectory (`misc.gold_trajectory`), a sequence of crafts that reaches the goal. The
+environments never read it; the Harbor export builds each task's reference solution from it.
+
+The task generators are not deterministic across runs: they draw each task's unrelated base materials from a Python
+set, so running them again gives the same goals in another order and with other starting inventories, unless they
+run under the same string-hash seed. The shipped files are the source of truth. To generate others, write them
+outside the package:
+
+```bash
+python -m platoon_textcraft.tasks --num_samples 10000 --eval_size 1000 --out /tmp/textcraft-tasks
+python -m platoon_textcraft.synth_tasks --num_samples 10000 --eval_size 1000 --seed 42 --out /tmp/textcraft-synth-tasks
+python -m platoon_textcraft.synth_recipe_generator --output-dir /tmp/textcraft-synth-recipes --seed 42 --items-per-tier 25
+```
+
+The last command writes the TextCraft-Synth world the environment builds as JSON files, to read.
+
+## Export as a Harbor dataset
+
+`platoon_textcraft.harbor` writes TextCraft-Synth as a Harbor dataset: one task directory per task of the `train`
+and `val` splits, which runners that take Harbor tasks (Harbor itself, platoon's `service: harbor`) play in a
+container through a `textcraft` command:
+
+```bash
+python -m platoon_textcraft.harbor export --variant synth --out /data/textcraft-synth --version 1.0 \
+  --source-revision "$(git rev-parse HEAD)"
+```
+
+| Option | Default | Meaning |
+|---|---|---|
+| `--variant` | `synth` | `synth` (TextCraft-Synth) or `original` (Minecraft recipes) |
+| `--out` | | a new directory (`--force` replaces one) |
+| `--version` | `1.0` | the version of the registry's datasets, `<world>-<split>@<version>` |
+| `--splits`, `--limit` | every split, every task | export only these splits, or the first N tasks of each |
+| `--repo-id` | `apurvaga/textcraft-synth` | the Hugging Face repository the dataset card's commands name |
+| `--source-revision` | none | the platoon commit the card names as the dataset's source |
+
+The same inputs give the same bytes. The dataset published as
+[`apurvaga/textcraft-synth`](https://huggingface.co/datasets/apurvaga/textcraft-synth) was exported before
+TextCraft moved here, so its card names the earlier command, `python -m platoon.textcraft.harbor export`; an export
+from this package gives the same tasks, byte for byte, and a card that differs only in where the tasks came from.
+The extension's tests check the first tasks of each split against the published content hashes.
+
+Each task holds:
+
+- `instruction.md`: the game description the linear agent's prompt opens with (without its strategy tips), the
+  goal, and the four commands, which print what the environment's tools return;
+- `environment/`: a Dockerfile whose build (`python:3.12-slim`, tmux and the `textcraft` command) is the same in
+  every task, then copies of the game (`harbor/game.py`, standard library only), the recipes and the task's
+  `task.json`;
+- `tests/test.sh`: the verifier. It replays the game's action log (`/app/textcraft/actions.jsonl`) with its own
+  copies of the game, the recipes and the task, and scores 1 only for an episode the rules allow that ends with
+  `finish` with every target crafted. It reads the log only as a regular file of at most 32 MiB, reached without
+  symbolic links. `task.toml` runs it in a separate verifier container (`environment_mode = "separate"`), which
+  receives the log as an artifact; it also runs in the agent's container.
+- `solution/solve.sh`: the gold trajectory as commands. The export plays every one with the game and fails unless
+  it reaches the goal.
+
+The dataset's root holds `registry.json` (`textcraft-synth-train@1.0`, `textcraft-synth-val@1.0`), `task-index.json`
+(each task's split, difficulty, crafting depth, source ids and Harbor content hash, which platoon's `select:`
+filters on), `splits.json` (the environment's split names, such as `train-medium`, to task names, for platoon's
+`splits:`), `LICENSE` and the dataset card `README.md`, which says how to run the tasks with Harbor and with
+platoon. The tasks have no network, so an agent cannot fetch the published solutions.
+
+## Modules
+
+- `env.py`: the ORS environments (`TextCraftEnvironment`, `TextCraftSynthEnvironment`); `recipe_loader.py`,
+  `synth_recipe_generator.py`, `synth_recipe_loader.py`: their recipes.
+- `prompts.py`: the system prompts and action spaces of the linear, recursive and depth-aware agents.
+- `entries.py`: the named environments.
+- `tasks.py`, `synth_tasks.py`: task generation and loading.
+- `harbor/`: the Harbor export (`export.py`, `card.py`, `templates/`) and the in-container game and verifier
+  (`game.py`).
+
+## Test
+
+```bash
+uv sync --package platoon-textcraft --extra platoon
+uv run --package platoon-textcraft pytest extensions/textcraft/tests -n auto --dist loadfile
+```
+
+The tests run on CPU and share platoon's test helpers (`tests/`). The golden replays of recursive CodeAct rollouts
+need the `Qwen/Qwen3-4B-Instruct-2507` tokenizer in the Hugging Face cache, and skip without it.
+
+## License
+
+MIT (`LICENSE`), platoon's license, for the code and the data: the task files, which platoon generated, and the
+recipe files in `data/recipes/`, which are Minecraft's (see [Data](#data)). Minecraft is a trademark of Mojang;
+platoon is not affiliated with Mojang or Microsoft.
+
+## Citation
+
+TextCraft comes from ADaPT; platoon generated TextCraft-Synth for
+[Recursive Agent Optimization](https://arxiv.org/abs/2605.06639) (RAO):
+
+```bibtex
+@inproceedings{prasad2024adapt,
+  title     = {{ADaPT}: As-Needed Decomposition and Planning with Language Models},
+  author    = {Prasad, Archiki and Koller, Alexander and Hartmann, Mareike and Clark, Peter and Sabharwal, Ashish
+               and Bansal, Mohit and Khot, Tushar},
+  booktitle = {Findings of the Association for Computational Linguistics: NAACL 2024},
+  pages     = {4226--4252},
+  year      = {2024},
+  url       = {https://aclanthology.org/2024.findings-naacl.264/}
+}
+
+@article{gandhi2026rao,
+  title   = {Recursive Agent Optimization},
+  author  = {Gandhi, Apurva and Chakraborty, Satyaki and Wang, Xiangjun and Kumar, Aviral and Neubig, Graham},
+  journal = {arXiv preprint arXiv:2605.06639},
+  year    = {2026}
+}
+```