feat: include authenticated user identity in HTTP access log (pgadmin-org#9991)

Set an X-Remote-User response header containing the authenticated username
on every request when the LOG_AUTHENTICATED_USER config option is enabled
(disabled by default). This allows the HTTP access log to be configured to
include user identity via standard log format directives
(%({x-remote-user}o)s in gunicorn, %{X-Remote-User}o in Apache) without
requiring any changes to pgAdmin's session or authentication behaviour. The
default gunicorn access log format is updated to surface the header.

The username is sanitised to a header-safe value: it is transliterated to
Latin-1 (HTTP headers are Latin-1 only) and any non-printable characters,
including CR/LF, are stripped, so unusual usernames cannot cause a 500 on
every response.

Author: ardentperf

pkg/docker/gunicorn_config.py

@@ -5,6 +5,14 @@
 
 gunicorn.SERVER_SOFTWARE = "Python"
 
+# Include the authenticated user identity in the access log.
+# %({x-remote-user}o)s reads the X-Remote-User response header set by pgAdmin
+# for authenticated requests; unauthenticated requests log '-'.
+access_log_format = (
+    '%(h)s %(l)s %({x-remote-user}o)s %(t)s "%(r)s" %(s)s %(b)s '
+    '"%(f)s" "%(a)s"'
+)
+
 if JSON_LOGGER:
     logconfig_dict = {
         "version": 1,

web/config.py

@@ -301,6 +301,9 @@
 LOG_ROTATION_SIZE = 10  # In MBs
 LOG_ROTATION_AGE = 1440  # In minutes
 LOG_ROTATION_MAX_LOG_FILES = 90  # Maximum number of backups to retain
+# Include the authenticated username in the X-Remote-User response header so
+# it can be captured in the HTTP access log. Disabled by default.
+LOG_AUTHENTICATED_USER = False
 ##########################################################################
 # Server Connection Driver Settings
 ##########################################################################

web/pgadmin/__init__.py

@@ -873,6 +873,20 @@ def before_request():
 
     @app.after_request
     def after_request(response):
+        if config.LOG_AUTHENTICATED_USER:
+            if current_user.is_authenticated and current_user.username:
+                # HTTP headers are latin-1 only, so transliterate anything
+                # outside that range to avoid gunicorn 500s for unicode names.
+                safe = current_user.username.encode(
+                    'latin-1', 'replace').decode('latin-1')
+                # CR/LF and other control chars are valid latin-1 but Werkzeug
+                # rejects them in header values (would 500 every request for
+                # that user), so drop any non-printable characters too.
+                safe = ''.join(c for c in safe if c.isprintable())
+                response.headers['X-Remote-User'] = safe
+            else:
+                response.headers.pop('X-Remote-User', None)
+
         if 'key' in request.args:
             domain = dict()
             if config.COOKIE_DEFAULT_DOMAIN and \