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>

open-sse/translator/response/cursor-to-openai.js

@@ -10,7 +10,7 @@ import { FORMATS } from "../formats.js";
  * Since CursorExecutor.transformProtobufToSSE/JSON already emits OpenAI chunks,
  * this is a passthrough translator (similar to Kiro pattern)
  */
-export function convertCursorToOpenAI(chunk, state) {
+export function cursorToOpenAIResponse(chunk, state) {
   if (!chunk) return null;
 
   // If chunk is already in OpenAI format (from executor transform), return as-is
@@ -27,4 +27,4 @@ export function convertCursorToOpenAI(chunk, state) {
   return chunk;
 }
 
-register(FORMATS.CURSOR, FORMATS.OPENAI, null, convertCursorToOpenAI);
+register(FORMATS.CURSOR, FORMATS.OPENAI, null, cursorToOpenAIResponse);