node_modules
environment
keys

# GA4 retrofit backups (see docs/specs/ga4/)
output/_backups/

# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class

# C extensions
*.so

# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
!**/src/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

# 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

# pdm
#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
#pdm.lock
#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
#   in version control.
#   https://pdm.fming.dev/#use-with-ide
.pdm.toml

# 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 / local secrets
.env
.env.local
.env.*.local
.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/



open-travel-guide.zip
# Qwen API key + tag cache (do not check in)
data/.qwen-key
data/search-tags-cache.json

# Playwright artefacts (when running the filter smoke tests)
/playwright-report/
/test-results/
.playwright/
scripts/assets/og-cache/

# Autopilot in-flight markers (transient state across /loop ticks)
.autopilot/in_flight/
.claude/worktrees/

# Agent fetch caches under data/work/. Research and QA agents cache raw
# fetched pages so they can re-read a source without refetching; a single
# city's cache ran to 100MB (Montpellier, 2026-08-22) and rode into a
# commit. The durable artifacts in data/work (notes, scripts, result JSON)
# stay tracked; the raw page dumps do not.
data/work/*/pages/
data/work/*/extra/

# Design-review screenshots (before/after comparisons from UI work).
# Working artifacts, not source: 28MB of PNGs had accumulated in git by
# 2026-09-04. They stay on disk for reference but are no longer tracked.
# Existing ones were untracked in the same commit; history is left alone
# rather than rewritten on a shared branch.
data/work/design/*.png

# GetYourGuide catalogue feed (scripts/gyg_catalogue.py). 40 MB of the
# marketplace's own listings, refreshed by re-running the script in about an
# hour; a regenerable cache, not source. The pages built from it are
# generated on this host, so git never needs the feed itself.
site-data/*/*/data/gyg-catalogue.json

# Musement affiliate catalogue export (27 MB, re-downloaded from affiliate.musement.com; see docs/GETYOURGUIDE_API.md)
data/work/musement/catalog.csv
site-data/*/*/data/musement-catalogue.json
site-data/*/*/data/viator-catalogue.json
# Partner data lives in the shared Postgres since 2026-09-17 (docs/PARTNER_DATABASE.md).
# These patterns stay so a stray export can never be committed back.
site-data/*/*/data/hotels-catalogue.json
data/partner-maps/
data/work/viator/destinations.json
.playwright-mcp/
data/search.sqlite
data/search.sqlite.tmp
data/work/design/*.ttf

# The site's data lives in Postgres (docs/SITE_DATABASE.md, 2026-09-18).
# site-data/ holds only a research handoff until it is imported and
# consumed; data/*.json are documents in the database except the two
# bootstrap config files below. Nothing here is tracked any more.
site-data/**/*.json
site-data/*.json
data/*.json
data/*.jsonl
data/*.log
!data/site_config.json
!data/field_types.json

# Regenerated diagnostic from geocode_entities.py, and a journal as far as
# load_sitedb is concerned. It changes on every geocoding run and was
# tracked by accident on 2026-09-25.
data/geocode-failures.txt

# Scratch screenshots at the repo root from UX passes. The audits
# themselves live in docs/UX_AUDIT_*.md.
/sticky*.png

# QA and research agents' fetch caches (2026-09-29): raw copies of third-party
# pages, PDFs and map tiles saved while checking facts. Their findings and
# fix plans in the same folders are committed; the cached pages are not.
data/work/*-qa/**/cache/
data/work/*-research/**/cache/
data/work/*-qa/**/maps/
data/work/*-research/**/maps/
data/work/*-qa/**/*.html
data/work/*-qa/**/*.pdf
data/work/*-research/**/*.html
data/work/*-research/**/*.pdf

# git crash dumps from the dashboard diff view on the network volume
/core.*

# Rendered weekly outputs (2026-10-03): the clips go to the downloads bar and the dataset to GitHub
/data/work/videos/
/data/work/festival_dataset/

# Open-data downloads for scripts/api_verify.py (2026-10-08): download caches only; the
# per-city snapshots and every result live in Postgres (kv stores src:<source>:<city>, api-verification).
data/work/data_sources/

# agents sometimes write their working files here instead of their own temp folder
/scratchpad/
