lychee.toml

# Lychee configuration for external link checking
# Documentation: https://github.com/lycheeverse/lychee

# Base URL to resolve root-relative links
base_url = "https://docs.sentry.io"

# Only check HTTP and HTTPS links
scheme = ["https", "http"]

# Exclude all private IP addresses automatically (localhost, 10.x, 172.16-31.x, 192.168.x, etc.)
exclude_all_private = true

# Exclude internal links (already handled by lint-404s script)
exclude = ['^https://docs\.sentry\.io']

# Maximum number of concurrent requests
max_concurrency = 32

# Maximum number of retries per request
max_retries = 2

# Request timeout in seconds
timeout = 30

# Retry wait time in seconds
retry_wait_time = 2

# User agent (some sites block default user agents)
user_agent = "Mozilla/5.0 (compatible; Sentry-Docs-Link-Checker; +https://github.com/getsentry/sentry-docs)"

# Accept common status codes that indicate the link works
# Include 403 (possibly bot blocking) and 418 (freedesktop teapot) to reduce noise
accept = [200, 201, 202, 203, 204, 206, 301, 302, 308, 403, 418]

# Don't validate URL fragments/anchors (e.g., #section-name)
# Fragment checking is unreliable: JS-rendered anchors appear broken, and many sites don't validate them
include_fragments = false

# Only check external links (our internal check handles internal ones)
include_mail = false
include_verbatim = false

# Follow redirects
max_redirects = 10

# Cache settings
#
# Strategy: Weekly scheduled runs populate the cache, PR checks consume it.
# - Successful responses (200, 301, 403, 404) are cached and skipped on subsequent runs
# - Transient errors (429 rate limits, 5xx server errors) are NOT cached, so they get retried
# - Cache lifetime is just under 2 weeks so it survives between weekly runs
#
# This means each weekly run only re-checks:
# 1. Links that failed with transient errors last time
# 2. New links not yet in cache
cache = true
max_cache_age = "335h"
cache_exclude_status = "429, 500.."