# 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
# DBOS system database (created during local dev/tests)
peak*.sqlite

# 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__/

# Terraform
*.tfvars
!*.tfvars.example
.terraform/
*.tfstate
*.tfstate.backup
tfplan
*.tfplan

# Neo-specific ignores

# AWS CLI installer (large binary)
awscliv2.zip

# Environment and secrets
.env*
!.env.dev
.secrets
/etc/secrets.conf

# MLflow
mlruns/
mlartifacts/
wandb/

# Data and models
data/models/
data/columns/
/aws/
thirdparty/
experimental/

# Temporary files
tmp/

# Git worktrees (should not be tracked)
tree-*/

# Temporary planning files (keep root clean)
*_PLAN.md

# IDEs
.DS_Store

# Legacy analysis directory (removed, but clones may remain on disk)
analysis/

embeddings_cache/
*.npy

# Harbor jobs directory (contains logs and intermediate files, too large for git)
jobs

# Invariant learning experiment data (clones, caches, large outputs)
data/invariants/.clones/
data/invariants/.archive/
data/invariants/.checkpoints/
data/invariants/.cache/
data/invariants/invariants.duckdb
data/invariants/invariants.duckdb.wal
data/invariants/*/collect/
# Repo-specific working directories (generated by pipeline runs)
data/invariants/*/
!data/invariants/evaluation/
# Evaluation data (large, stored in S3 at s3://neoteny-ai/invariants/v2/)
data/invariants/evaluation/*_results*.json
data/invariants/evaluation/analysis_report.md
data/invariants/evaluation/checkpoints/
data/invariants/evaluation/checkpoints/.backup_*/
data/invariants/evaluation/procedures_summary.json
data/invariants/evaluation/summary.json
data/invariants/evaluation/evaluation_report.txt
# Per-repo generated reports (stored in S3 at s3://neoteny-ai/invariants/v2/reports/)
docs/invariant_learning/*-rules-report.md
docs/invariant_learning/*-procedures-report.md

# PEAK data (DuckDB snapshots)
data/peak/*
!data/peak/pydantic_ai_sample.duckdb
!data/peak/grafana_prometheus_repo_list_full.jsonl
!data/peak/grafana_prometheus_repo_list_tiny.jsonl

# OSS data v3 analysis outputs (stored in S3, not git)
data/oss_data/

# Large local data, binaries, and generated reports (not for version control)
data/github/
torch
predictions/
sb-cli-reports/
swebench_reports/
*.pdf
