Serve Hesychia crawler files as static text #44

Merged
westfarn merged 3 commits from feat/43-static-crawler-files into master 2026-10-19 08:07:47 -07:00
2 changed files with 43 additions and 0 deletions
Showing only changes of commit 5e9878632e - Show all commits

No files matched your search

+13
View File
@@ -125,6 +125,19 @@ app_catalog:
api_proxy_prefix: /api/finance/webhooks/
# /robots.txt, /sitemap.xml, and /llms.txt must not fall through to index.html.
exact_root_files: true
# Homepage was missing these. Enforcing CSP stays loose so Tianji, the API,
# websockets, and inline styles keep working. Report-Only is the strict policy.
security_headers: true
# Unknown URLs are HTTP 404 with public/404.html, not 200 + the SPA shell.
# Slash routes are directory index.html files from scripts/stampCanonicals.js.
# These extensionless routes are the matching files (keep in sync with
# llm-fe/src/llm-fe/utils/canonicals.js paths that do not end in /).
error_page_404: /404.html
html_exact_paths:
- /legal/terms-of-service
- /billing/success
- /billing/cancel
- /document_storage
chat_backend:
type: django
repo: "{{ git_base_url }}/ai_ml_operations/chat_backend.git"
+30
View File
@@ -17,6 +17,14 @@ log_format observability escape=json
'"user_agent":"$http_user_agent"'
'}';
{% macro security_headers() %}
add_header X-Content-Type-Options "nosniff" always;
add_header X-Frame-Options "DENY" always;
add_header Referrer-Policy "strict-origin-when-cross-origin" always;
add_header Content-Security-Policy "default-src 'self' https: wss: data: blob: 'unsafe-inline'; frame-ancestors 'none'; base-uri 'self'; object-src 'none'" always;
add_header Content-Security-Policy-Report-Only "default-src 'self'; style-src 'self' 'unsafe-inline'; img-src 'self' data: blob:; font-src 'self' data:; connect-src 'self'; frame-ancestors 'none'; base-uri 'self'; object-src 'none'; form-action 'self'" always;
{% endmacro %}
{% for a in _static_apps %}
server {
listen {{ a.port }};
@@ -29,6 +37,9 @@ server {
root {{ (app_catalog[a.name].webroot_pattern | default(web_static_root ~ '/{env}_' ~ a.name)) | replace('{env}', a.env) }};
index index.html;
{% if app_catalog[a.name].security_headers | default(false) %}
{{ security_headers() }}
{% endif %}
{%- set api_backend_name = app_catalog[a.name].api_backend | default('') %}
{%- if api_backend_name %}
@@ -74,6 +85,22 @@ server {
}
{% endif %}
{% if app_catalog[a.name].html_exact_paths | default([]) %}
{% for p in app_catalog[a.name].html_exact_paths %}
location = {{ p }} {
default_type text/html;
try_files {{ p }} =404;
}
{% endfor %}
{% endif %}
{% if a.name == 'chat_web_app' and a.env == 'prod' %}
# HeyCatch short links. Unknown paths 404, so the SDK never sees /x.
location ~ ^/([a-z0-9])$ {
return 302 /?utm_source=heycatch&utm_campaign=$1;
}
{% endif %}
{% if app_catalog[a.name].error_page_404 | default('') %}
error_page 404 {{ app_catalog[a.name].error_page_404 }};
@@ -89,6 +116,9 @@ server {
location ~* \.(?:js|css|woff2?|png|jpg|jpeg|gif|svg|ico)$ {
expires 7d;
add_header Cache-Control "public";
{% if app_catalog[a.name].security_headers | default(false) %}
{{ security_headers() }}
{% endif %}
}
}
{% endfor %}