pyproject.toml

# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the BSD-style license found in the
# LICENSE file in the root directory of this source tree.

[build-system]
requires = ["setuptools>=45", "wheel"]
build-backend = "setuptools.build_meta"

[project]
name = "sql_drift_env"
version = "0.1.0"
description = "SQLDrift: OpenEnv gym for repairing and optimizing SQL under live schema/business-rule drift"
requires-python = ">=3.12,<3.14"
dependencies = [
    "duckdb>=1.5.2,<2.0",
    # huggingface-hub: floor must satisfy `transformers>=5.2.0` (which
    # needs hub>=1.3.0) — and the highest transformers we allow
    # (5.4.x–5.5.0) needs hub>=1.5.0. Pin the floor at 1.5.0 to match
    # the worst case so the [train] extra resolves cleanly. Cap <2.0
    # because the `run_job` / `fetch_job_logs` / `inspect_job` API we
    # call in utilities/run_training_job.py landed in the 1.x line.
    "huggingface-hub>=1.5.0,<2.0",
    "openenv-core[core]>=0.2.2,<0.4",
    "sqlglot>=30.6.0,<40.0",
    "pydantic>=2.8.0,<3.0",
    "python-dotenv>=1.2.2,<2.0",
    "openai>=2.32.0,<3.0",
]

[project.optional-dependencies]
evidence = [
    "matplotlib>=3.8.0,<4.0",
    "pandas>=2.0.0,<3.0",
]
dev = [
    "mypy>=1.20.1",
    "pytest>=9.0.3",
    "pytest-asyncio>=1.3.0",
    "pytest-cov>=7.0.0",
    "ruff>=0.15.11",
    "httpx>=0.28.0",
]
train = [
    # TRL-only stack — mirrors Hugging Face's reference notebooks for
    # GRPO with QLoRA (`grpo_trl_lora_qlora.ipynb`) and the OpenEnv
    # multi-turn tool-calling examples (`openenv_wordle_grpo.ipynb`).
    # No Unsloth: AutoModelForCausalLM + BitsAndBytesConfig is the
    # canonical path the TRL examples use, and it resolves cleanly
    # on a free Colab T4.
    "trl[peft]>=1.2.0,<2.0",
    "datasets>=3.0.0,<5.0",
    # TRL 1.2 floors transformers at >=5.0. Keep the ceiling open so
    # we follow the TRL release cadence.
    "transformers>=5.5.0",
    "accelerate>=1.13.0",
    "peft>=0.19",
    "bitsandbytes>=0.46.1,!=0.48.0",
    # jmespath: required by TRL's GRPOTrainer whenever `tools` or
    # `environment_factory` is used (parses tool-call responses from
    # the model). TRL raises ImportError at GRPOTrainer.__init__
    # otherwise. Pure-Python, no transitive deps.
    # https://github.com/huggingface/trl/blob/main/trl/trainer/grpo_trainer.py
    "jmespath>=1.0,<2.0",
    "tensorboard>=2.20,<3.0",
]

[project.scripts]
# Flat package layout; see _cli.py. Runtime path: site-packages/sql_drift_env/
server = "sql_drift_env._cli:main"

[tool.setuptools]
include-package-data = true
packages = [
    "sql_drift_env",
    "sql_drift_env.scenarios",
    "sql_drift_env.engine",
    "sql_drift_env.skill_library",
    "sql_drift_env.actors",
    "sql_drift_env.training",
    "sql_drift_env.server",
    "sql_drift_env.utilities",
]

[tool.setuptools.package-dir]
"sql_drift_env" = "."
"sql_drift_env.scenarios" = "scenarios"
"sql_drift_env.engine" = "engine"
"sql_drift_env.skill_library" = "skill_library"
"sql_drift_env.actors" = "actors"
"sql_drift_env.training" = "training"
"sql_drift_env.server" = "server"
"sql_drift_env.utilities" = "utilities"

[tool.pytest.ini_options]
testpaths = ["tests"]
asyncio_mode = "auto"
markers = [
    "slow: marks tests as slow (excluded by default; run via `pytest -m slow`)",
]
# Default excludes slow tests so CI stays on a fast path; run `pytest -m slow` for full suite.
addopts = "-ra --strict-markers -m 'not slow'"

[tool.ruff]
line-length = 100
target-version = "py312"
extend-exclude = [".venv", "design", "*.egg-info", "*.ipynb"]

[tool.ruff.lint]
select = ["E", "F", "I", "B", "UP", "SIM"]
ignore = ["E501"]

# Prefer fixing structure over scattered inline suppressions. See each rule in Ruff docs.
[tool.ruff.lint.per-file-ignores]
"_cli.py" = ["PLC0415"]
"training/grpo_train.py" = ["PLC0415"]
"engine/profiler.py" = ["BLE001"]
"scenarios/__init__.py" = ["F401"]
"tests/unit/test_p0_smoke.py" = ["F401"]
"utilities/verbose_api_rollout.py" = ["E402"]
"utilities/demo_rollout.py" = ["E402"]
"tests/unit/test_drift_scenarios.py" = ["E402"]
"tests/unit/test_profiler.py" = ["E402"]
"tests/unit/test_drift.py" = ["E402"]
"tests/unit/test_runtime.py" = ["E402"]

[tool.mypy]
python_version = "3.12"
strict = true
ignore_missing_imports = true
explicit_package_bases = true
mypy_path = "."
files = [
    "_cli.py",
    "actors",
    "client.py",
    "engine",
    "models.py",
    "scenarios",
    "utilities",
    "server",
    "skill_library",
    "training",
]
exclude = [
    "\\.venv",
    "design",
    ".*\\.egg-info",
    "tests",
    "build",
    "dist",
]

# Subclasses in these modules call into openenv-core (no stubs). Relax only here.
[[tool.mypy.overrides]]
module = [
    "client",
    "models",
    "engine.reward",
    "server.app",
    "server.sql_drift_env_environment",
    "training.grpo_train",
]
disallow_subclassing_any = false
warn_return_any = false

[tool.coverage.run]
# pytest-cov can hit upstream issues with beartype when tracing; run plain pytest for CI.
source = ["engine", "scenarios", "skill_library", "actors", "models.py"]
omit = ["tests/*", ".venv/*"]

[tool.coverage.report]
skip_empty = true
exclude_lines = [
    "pragma: no cover",
    "if __name__ == \"__main__\":",
    "if TYPE_CHECKING:",
    "raise NotImplementedError",
    "if 0:",
    "if False:",
    "\\.\\.\\.",
]