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/concerns/chunk.js

@@ -0,0 +1,11 @@
+// Build OpenAI chat.completion.chunk. Caller supplies id/created/model so each
+// translator keeps its exact id-generation + created semantics (no Date.now here).
+export function buildChunk({ id, created, model }, delta, finishReason = null) {
+  return {
+    id,
+    object: "chat.completion.chunk",
+    created,
+    model,
+    choices: [{ index: 0, delta, finish_reason: finishReason }],
+  };
+}