Merge pull request 'fix(search): expect the seven engines that actually contribute, not the five that don't' (#149) from fix/search-stack-multiprovider-20261003 into master

scripts/search-stack-check.py

@@ -61,11 +61,23 @@ EXTRACT_URL = os.environ.get(
 # engines (images, videos, translate, currency, arxiv, npm, ...) are excluded on
 # purpose -- contributing nothing to a general query is correct for them.
 DEFAULT_EXPECTED_ENGINES = [
+    # Multi-engine expansion 2026-10-03.  The stack had fallen to Bing-only:
+    # brave and google cse are suspended upstream, duckduckgo CAPTCHAs both
+    # egresses and yandex flaps.  The seven below all returned real results
+    # from this network and are the engines a general query must draw on.
     "bing",
-    "brave",
-    "google cse",
     "yandex",
+    "yep",
+    "mwmbl",
+    "naver",
+    "seznam",
+    "yahoo",
+    # Best-effort canaries: intentionally left enabled so a recovery shows up
+    # as a contribution and a failure stays visible in unresponsive_engines.
+    # All three are blocked upstream today.
+    "brave",
     "duckduckgo",
+    "google cse",
 ]
 EXPECTED_ENGINES = [
     e.strip()

search-stack-visibility.prose.md

@@ -17,11 +17,16 @@ description: >
     * reports every silent-zero engine explicitly (enabled, not in
       unresponsive_engines, contributed no results).
 
-  Multi-engine state (2026-09-25): bing, google cse, brave and yandex
-  contribute on every query. duckduckgo is NOT working: the house egress IP
-  and the VPS fallback egress are both flagged by DuckDuckGo and it reports
-  CAPTCHA. It is left enabled as best-effort coverage so that a recovery shows
-  up as a contribution.
+  Multi-engine state (2026-10-03): the stack had fallen to Bing-only -- brave
+  and google cse are suspended upstream, duckduckgo CAPTCHAs both egresses and
+  yandex flaps. Every no-credential free general engine this build ships was
+  enabled and probed. Seven now contribute real results on a general query:
+  bing, yandex, yep, mwmbl, naver, seznam and yahoo. brave, duckduckgo and
+  google cse are left enabled as best-effort canaries so a recovery shows up as
+  a contribution and their failure stays visible in unresponsive_engines.
+  mojeek, startpage and dogpile are `inactive: true` in the build (proof-of-work
+  CAPTCHA), marginalia needs an API key, and qwant and fireball were tested and
+  dropped (CAPTCHA and access-denied).
 
   google cse is a third party's public search-engine id hardcoded in the
   SearXNG build. Quota and availability are outside our control.
@@ -29,7 +34,7 @@ description: >
   SCHEDULED: /etc/cron.d/contract-runner on CT 100 (abiba), hourly at :15,
   via scripts/contract-run.sh search-stack-visibility. Logs land in
   /var/log/contract-runs/. A failure also raises a firstmate inbox note.
-version: 1.1.0
+version: 1.2.0
 ---
 
 ## Purpose
@@ -54,11 +59,12 @@ firstmate inbox note through `bin/fm-inbox.sh`.
 
 ```
 $ bash scripts/contract-run.sh search-stack-visibility
-Expected engines, enabled (5): ['bing', 'brave', 'duckduckgo', 'google cse', 'yandex']
-queries: 'proxmox backup server' -> contributing: bing, brave, google cse, yandex
-                                    unresponsive: duckduckgo=CAPTCHA
-         'python asyncio tutorial' -> contributing: bing, brave, google cse, yandex
-EXTRACTION: 71016 chars of markdown returned
+Expected engines, enabled (10): ['bing', 'brave', 'duckduckgo', 'google cse',
+                                'mwmbl', 'naver', 'seznam', 'yahoo', 'yandex', 'yep']
+queries: 'proxmox backup server'  -> contributing: bing, mwmbl, naver, seznam, yahoo, yandex, yep
+                                     unresponsive: brave, duckduckgo, google cse
+         'python asyncio tutorial' -> contributing: bing, mwmbl, naver, seznam, yandex, yep
+EXTRACTION: 71532 chars of markdown returned
 VERDICT: PASS -- multiple engines contributing, extraction healthy
 ```