[feat] plugin: AI summary of search results via local Ollama server

Add an optional, disabled-by-default plugin that shows an AI generated
summary at the top of the result page, generated by a (local) Ollama
server:

- async: the result page is never delayed; a client plugin streams the
  answer (NDJSON over a new /ai_summary endpoint) into a placeholder
  answer with a typing indicator, collapsed behind a More button, with
  an inline follow-up chat
- trigger: first page of general searches only, skipped when an infobox
  or instant answer already answers the query
- grounding (per-user preference): send the top result snippets as
  context, the model answers from them instead of its own knowledge
- configuration: new AI Summary preferences tab (server URL, model,
  grounding) with instance defaults in a new ai_summary: settings
  section; all three preferences can be locked for public instances

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

searx/webapp.py

@@ -93,8 +93,10 @@ from searx.preferences import (
     ClientPref,
     ValidationException,
 )
+import searx.ai_summary
 import searx.answerers
 import searx.plugins
+import searx.plugins.ai_summary
 
 
 from searx.metrics import get_engines_stats, get_engine_errors, get_reliabilities, histogram, counter, openmetrics
@@ -328,6 +330,8 @@ def get_translations():
         'Source': gettext('Source'),
         # infinite scroll
         'error_loading_next_page': gettext('Error loading the next page'),
+        # AI summary
+        'error_loading_ai_summary': gettext('Error loading the AI summary'),
     }
 
 
@@ -981,11 +985,17 @@ def preferences():
         preferences_url_params = sxng_request.preferences.get_as_url_params(),
         locked_preferences = get_setting("preferences").lock,
         doi_resolvers = get_setting("doi_resolvers", {}),
+        ai_summary_models = searx.ai_summary.model_choices(),
+        ai_summary_default_model = get_setting("ai_summary").model,
+        ai_summary_default_server = get_setting("ai_summary").base_url,
         # fmt: on
     )
 
 
 app.add_url_rule('/favicon_proxy', methods=['GET'], endpoint="favicon_proxy", view_func=favicons.favicon_proxy)
+app.add_url_rule(
+    '/ai_summary', methods=['POST'], endpoint="ai_summary", view_func=searx.plugins.ai_summary.ai_summary_view
+)
 
 
 @app.route('/image_proxy', methods=['GET'])