agnes-the-ai-analyst/Caddyfile

{$DOMAIN:localhost} {
	# Cert provisioning. Driven by env var CADDY_TLS:
	#   - unset (default) → cert-file mode for corporate PKI (rotated by
	#     scripts/ops/agnes-tls-rotate.sh into /data/state/certs/).
	#   - "tls <email>"   → Let's Encrypt auto-issue, e.g. "tls ops@example.com"
	#                       (used by public-internet deployments).
	#   - "tls internal"  → Caddy-managed self-signed cert (lab/dev only,
	#                       browser warning on every visit).
	#
	# The {$VAR:default} substitution lets one Caddyfile serve all three
	# regimes without per-deployment forks. Caddyfile parses the substituted
	# string as a directive, so the value MUST start with `tls `.
	{$CADDY_TLS:tls /certs/fullchain.pem /certs/privkey.pem} {
		# Modern TLS only. Caddy default already excludes 1.0/1.1 in
		# most builds, but pin explicitly so a future Caddy default
		# change can't silently weaken our posture.
		protocols tls1.2 tls1.3
	}

	# Security headers
	header {
		# HSTS: tell compliant browsers to refuse plain-HTTP for this host
		# for a year. Skipping `preload` so we keep an escape hatch (preload
		# submission is hard-bound and blocks rollback). Skipping
		# `includeSubDomains` because we don't control subdomains.
		Strict-Transport-Security "max-age=31536000"
		# Prevent clickjacking — dashboard is not embedded in iframes
		X-Frame-Options "DENY"
		# Prevent MIME-type sniffing — browser must honor declared Content-Type
		X-Content-Type-Options "nosniff"
		# Limit referrer leakage to origin on same-site navigations only
		Referrer-Policy "strict-origin-when-cross-origin"
		# Strip Server header to avoid fingerprinting the reverse proxy
		-Server
	}

	# Direct file_server for parquet downloads — bypasses uvicorn so a
	# multi-GB pull from one analyst can't starve the app workers and
	# block UI / health / API for everyone else. forward_auth calls the
	# app's lightweight ``/api/data/{id}/check-access`` (RBAC only,
	# ~1 ms) on every request; on 2xx Caddy serves the file directly
	# via sendfile/zero-copy from the data volume mounted read-only.
	#
	# Path layout matches `app/api/data.py`'s extract.duckdb v2 search:
	#   /data/extracts/<source_type>/data/<table_id>.parquet
	# try_files probes known source subdirs in order; first hit wins.
	# If a deployment adds a new connector and lands parquets at a fresh
	# subdir, extend the try_files list. Anything that misses falls
	# through to the app reverse_proxy below — so an unmapped source
	# degrades to "downloads work, just through uvicorn" — never 404.
	@download path_regexp tid ^/api/data/([^/]+)/download$
	handle @download {
		forward_auth app:8000 {
			uri /api/data/{re.tid.1}/check-access
			# Bearer PAT or session cookie travels in Authorization
			# / Cookie; copy_headers ensures the upstream sees them.
			copy_headers Authorization Cookie
		}
		# Caddy's own /data is occupied by the caddy_data volume, so the
		# agnes data dir is mounted at /srv (read-only) instead — see the
		# `data:/srv:ro` line in docker-compose.yml's caddy service. The
		# root + try_files combo therefore probes /srv/extracts/...
		#
		# Devin Review caught: `try_files A B C` rewrites the URI to its
		# LAST entry when no file matches (per Caddy docs). Without an
		# explicit "rewrite back to original URI" fallback, a parquet
		# missing from all three known paths would get rewritten to the
		# last static candidate (`/jira/data/<id>.parquet`), and the
		# reverse_proxy below would forward THAT rewritten URI to
		# app:8000 → app has no such route → 404. To make the documented
		# "missed → falls through to app handler" promise hold, append
		# the original `/api/data/<id>/download` path as the final
		# try_files entry: when no file matches, the URI is rewritten
		# back to the analyst-facing path and the app's `download_table`
		# handler picks it up via the reverse_proxy fallback below.
		root * /srv/extracts
		try_files /bigquery/data/{re.tid.1}.parquet /keboola/data/{re.tid.1}.parquet /jira/data/{re.tid.1}.parquet /api/data/{re.tid.1}/download
		@found file
		handle @found {
			header Content-Disposition "attachment; filename=\"{re.tid.1}.parquet\""
			file_server
		}
		# Fallback: parquet not at any known static path → defer to app
		# (handles legacy src_data/parquet layout + future connectors).
		reverse_proxy app:8000 {
			header_up X-Forwarded-Proto https
			header_up X-Forwarded-Host {host}
		}
	}

	reverse_proxy app:8000 {
		# App's uvicorn runs with --proxy-headers, so stamping these
		# ourselves makes OAuth callback URLs and Set-Cookie Secure
		# flags resolve to https consistently. X-Forwarded-Host is
		# also Caddy's default, but pinning it explicitly insures
		# against future default changes.
		header_up X-Forwarded-Proto https
		header_up X-Forwarded-Host {host}
	}
}