refactor(open-sse): translator DRY + schema enums, bug fixes, dead code cleanup

- Bug B1-B7: media UI m.kind||m.type, serviceKinds, gemini mediaPriority, schema kind, models/info lookup by kind
- Dead code D1-D6: safeParseJSON, drop PROVIDER_ENDPOINTS, orphan fetcher, GITHUB_CONFIG derive, getProviderConfig internal, legacy kiro file
- Translator concerns: toOpenAIUsage, toOpenAIFinish (gemini/kiro/ollama + fix kiro tool finish), thinking effort maps
- Reorg helpers/ → concerns/ (logic) + formats/ (per-format) + schema/ (pure enums: roles/blocks/finishReasons/defaults)
- Wire ~280 hardcoded role/block/finish/default literals to schema enums across 20+ files
- collapseTextParts + extractTextContent dedup
- Normalize translator fn names to openaiToXRequest / xToOpenAIResponse
- Golden tests lock behavior; 0 regression (byte-for-byte providers/alias, 26=26 known fails)

Co-authored-by: Cursor <cursoragent@cursor.com>

src/app/(dashboard)/dashboard/providers/components/ModelsCard.js

@@ -206,14 +206,14 @@ export default function ModelsCard({ providerId, kindFilter, providerAliasOverri
   const builtInModels = kindFilter
     ? allBuiltIn.filter((m) => {
         if (m.kinds) return m.kinds.includes(kindFilter);
-        return (m.type || "llm") === kindFilter;
+        return (m.kind || m.type || "llm") === kindFilter;
       })
     : allBuiltIn;
 
   // Custom models for this provider + kind, dedupe vs built-in
   const myCustomModels = customModels.filter(
     (m) => m.providerAlias === providerAlias
-      && (m.type || "llm") === effectiveType
+      && (m.kind || m.type || "llm") === effectiveType
       && !builtInModels.some((b) => b.id === m.id)
   );