Merge pull request #532 from MaEscalanteHe/feature/update-openai-models

fix: update OpenAI models and send supported reasoning parameters

AppImage/config/verified_ai_models.json

@@ -38,31 +38,24 @@
   },
   "openai": {
     "models": [
-      "gpt-4.1-nano-2025-04-14",
-      "gpt-4.1-nano",
-      "gpt-4.1-2025-04-14",
-      "gpt-4.1",
-      "gpt-4o-2024-11-20",
-      "gpt-4o-2024-05-13",
-      "gpt-4o-mini",
-      "gpt-3.5-turbo-16k",
-      "gpt-4o-mini-2024-07-18",
-      "gpt-5-nano",
-      "gpt-3.5-turbo-1106",
-      "gpt-3.5-turbo-0125",
-      "gpt-5-nano-2025-08-07",
-      "gpt-4.1-mini",
-      "gpt-4.1-mini-2025-04-14",
-      "gpt-3.5-turbo",
-      "gpt-4o",
-      "gpt-4o-2024-08-06",
-      "gpt-4",
-      "gpt-4-turbo",
-      "gpt-4-turbo-2024-04-09",
-      "gpt-4-0613"
+      "gpt-6-luna",
+      "gpt-5.6-luna",
+      "gpt-5.4-mini",
+      "gpt-5.4-mini-2026-03-17",
+      "gpt-6-sol",
+      "gpt-6.1-sol",
+      "gpt-5.6-terra",
+      "gpt-5.2",
+      "gpt-5.2-2025-12-11",
+      "gpt-5.4",
+      "gpt-5.4-2026-03-05",
+      "gpt-5.6-sol",
+      "gpt-5.5",
+      "gpt-5.5-2026-04-23",
+      "gpt-6-astra"
     ],
-    "recommended": "gpt-4.1-nano",
-    "_note": "Verified 2026-09-02 with the OpenAI API — 22 of 74 tested pass. Includes stable aliases (gpt-4.1-nano, gpt-4o-mini, ...), dated snapshots for pinning (gpt-4o-2024-11-20, gpt-4.1-nano-2025-04-14) and legacy families (gpt-3.5-turbo, gpt-4) for cost-optimised use cases. Recommended kept as `gpt-4.1-nano` (stable alias, 1.39s)."
+    "recommended": "gpt-6-luna",
+    "_note": "Verified 2026-10-26 against the live API. Recommended `gpt-6-luna` (cheapest current model). Dropped every model that is retired (gpt-4.1-nano, gpt-3.5-turbo, gpt-4, gpt-4-turbo, ...) or has a shutdown date (gpt-4.1, gpt-4o, gpt-4o-mini, gpt-5-nano, gpt-5.1, gpt-5.4-nano)."
   },
   "anthropic": {
     "models": [