>>> from datasets import load_dataset
>>> dataset = load_dataset("harborframework/terminal-bench")
>>> dataset
DatasetDict({
    test: Dataset({
        features: ['name', 'instruction', 'description', 'keywords', 'schema_version', 'config', 'metadata', 'files', 'location'],
        num_rows: 66
    })
})

my-harbor-dataset/
├── README.md
└── tasks/
    ├── task-a/
    │   ├── task.toml          # configuration: metadata, resources, timeouts...
    │   ├── instruction.md     # what the agent is asked to do
    │   ├── README.md          # optional human-readable description
    │   ├── environment/       # Dockerfile / docker-compose.yaml + files of the sandbox
    │   ├── tests/             # verifier
    │   └── solution/          # oracle solution
    └── task-b/
        └── ...

>>> from datasets import load_dataset

>>> # a dataset repository on the Hub
>>> dataset = load_dataset("harborframework/terminal-bench")
>>> # a local directory of tasks
>>> dataset = load_dataset("/path/to/my-harbor-dataset")
>>> # the tasks of a repository that are in a sub-directory
>>> dataset = load_dataset("harborframework/terminal-bench", data_dir="tasks")

>>> dataset = load_dataset(
...     "/path/to/my-harbor-dataset",
...     data_files={"test": ["my-tasks-dir/*/task.toml", "my-tasks-dir/*/instruction.md"]},
... )

>>> dataset = load_dataset("harborframework/terminal-bench", split="test")
>>> dataset[0]["name"]
'terminal-bench/atrx-vep-crispr'
>>> dataset[0]["instruction"][:90]
'You are provided with a region of genomic DNA representing the human ATRX locus plus sequence'
>>> dataset[0]["config"]["task"]["authors"]
[{'name': 'ScaleAI', 'email': 'tbench@scale.com'}]
>>> dataset[0]["metadata"]["category"]
'Science'
>>> dataset[0]["config"]["environment"]
{'build_timeout_sec': 1800.0, 'cpus': 2, 'memory_mb': 4096, 'storage_mb': 10240, 'gpus': 0}
>>> dataset[0]["files"][:4]
['LICENSE.md', 'README.md', 'environment/Dockerfile', 'environment/data/CDS-information.txt']
>>> dataset[0]["location"]
'tasks/atrx-vep-crispr'

>>> dataset = dataset.map(lambda task: {"timeout_min": task["config"]["verifier"]["timeout_sec"] / 60})
>>> sorted(set(dataset["timeout_min"]))[:6]
[1.0, 2.0, 3.0, 4.0, 5.0, 7.0]

>>> security_tasks = dataset.filter(lambda task: task["metadata"].get("category") == "Security")
>>> [task["name"] for task in security_tasks]
['terminal-bench/formal-crypto', 'terminal-bench/html-js-filter', 'terminal-bench/interleaved-vigenere', 'terminal-bench/shadow-relay', 'terminal-bench/uefi-bootkit']

>>> pytest_verifiers = dataset.filter(lambda task: any(f.startswith("tests/") and f.endswith(".py") for f in task["files"]))
>>> pytest_verifiers.num_rows
63

>>> from huggingface_hub import hffs
>>> dataset_path = "hf://datasets/harborframework/terminal-bench"
>>> with hffs.open(f"{dataset_path}/tasks/cumulative-layout-shift/environment/Dockerfile", "r") as f:
...     print(f.read()[:20])
'# harbor-canary GUID

>>> from datasets import load_dataset
>>> dataset = load_dataset("harborframework/terminal-bench", streaming=True)
>>> for task in dataset["test"]:
...     print(task["name"])