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/schema/roles.js

@@ -0,0 +1,16 @@
+// Role enums — fixed per format. Pure data (no logic).
+// OpenAI chat / Claude share these; mapping between them stays in translators.
+
+export const ROLE = {
+  USER: "user",
+  ASSISTANT: "assistant",
+  TOOL: "tool",
+  SYSTEM: "system",
+  DEVELOPER: "developer",
+};
+
+// Gemini / Antigravity use "model" instead of "assistant".
+export const GEMINI_ROLE = {
+  USER: "user",
+  MODEL: "model",
+};