# Research Site Configuration
# Generated: 2026-02-19
# This file intentionally has no extension to test crawler handling
# of extensionless files.

[server]
host = 0.0.0.0
port = 443
protocol = https
region = us-east-1
bucket = site4726837462198733423

[logging]
enabled = true
target_bucket = site4726837462198733423-logs
target_prefix = access-logs/
format = s3_server_access
fields = timestamp,remote_ip,operation,key,status,bytes,referrer,user_agent

[content]
index_document = index.html
error_document = error.html
default_cache_control = max-age=3600
enable_cors = false

[crawlers]
# Known crawler User-Agent patterns for identification
gptbot = GPTBot
claudebot = ClaudeBot
amazonbot = Amazonbot
bingbot = bingbot
googlebot = Googlebot
applebot = Applebot

[experiments]
redirect_chain_enabled = true
redirect_chain_max_depth = 100
large_file_test_enabled = true
pagination_enabled = true
pagination_max_pages = 10000
link_discovery_enabled = true
link_discovery_count = 100000

[rate_limiting]
enabled = false
max_requests_per_minute = 60
burst_size = 10

[monitoring]
health_check_path = /health
metrics_enabled = true
alert_threshold_5xx = 10
alert_threshold_bandwidth_gb = 50

[security]
block_public_access = false
enable_versioning = false
enable_encryption = false
cors_allowed_origins = *