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/executors/antigravity.js

@@ -5,7 +5,7 @@ import { OAUTH_ENDPOINTS, ANTIGRAVITY_HEADERS, INTERNAL_REQUEST_HEADER, AG_DEFAU
 import { HTTP_STATUS } from "../config/runtimeConfig.js";
 import { deriveSessionId } from "../utils/sessionManager.js";
 import { proxyAwareFetch } from "../utils/proxyFetch.js";
-import { cleanJSONSchemaForAntigravity } from "../translator/helpers/geminiHelper.js";
+import { cleanJSONSchemaForAntigravity } from "../translator/formats/gemini.js";
 
 // Sanitize function name: Gemini requires [a-zA-Z_][a-zA-Z0-9_.:\-]{0,63}
 function sanitizeFunctionName(name) {

open-sse/executors/codex.js

@@ -6,8 +6,8 @@ import {
   refreshProviderCredentials,
   shouldRefreshCredentials,
 } from "../services/oauthCredentialManager.js";
-import { normalizeResponsesInput } from "../translator/helpers/responsesApiHelper.js";
-import { fetchImageAsBase64 } from "../translator/helpers/imageHelper.js";
+import { normalizeResponsesInput } from "../translator/formats/responsesApi.js";
+import { fetchImageAsBase64 } from "../translator/concerns/image.js";
 import { getModelUpstreamId } from "../config/providerModels.js";
 import { getConsistentMachineId } from "../shared/machineId.js";
 import { DEFAULT_RETRY_CONFIG, resolveRetryEntry } from "../config/runtimeConfig.js";

open-sse/executors/commandcode.js

@@ -1,7 +1,7 @@
 import { randomUUID } from "crypto";
 import { BaseExecutor } from "./base.js";
 import { PROVIDERS } from "../config/providers.js";
-import { convertCommandCodeToOpenAI } from "../translator/response/commandcode-to-openai.js";
+import { commandCodeToOpenAIResponse } from "../translator/response/commandcode-to-openai.js";
 import { SSE_DONE } from "../utils/sseConstants.js";
 
 /**
@@ -71,13 +71,13 @@ function wrapNdjsonAsOpenAISse(originalResponse, model) {
         const trimmed = line.trim();
         if (!trimmed) continue;
         // Translate AI SDK v5 NDJSON line to one or more OpenAI chunks
-        emitChunks(convertCommandCodeToOpenAI(trimmed, state), controller);
+        emitChunks(commandCodeToOpenAIResponse(trimmed, state), controller);
       }
     },
     flush(controller) {
       const trimmed = buffer.trim();
       if (trimmed) {
-        emitChunks(convertCommandCodeToOpenAI(trimmed, state), controller);
+        emitChunks(commandCodeToOpenAIResponse(trimmed, state), controller);
       }
       controller.enqueue(encoder.encode(SSE_DONE));
     },

open-sse/executors/cursor.js

@@ -142,7 +142,7 @@ export class CursorExecutor extends BaseExecutor {
 
   transformRequest(model, body, stream, credentials) {
     // Messages are already translated by chatCore (claude→openai→cursor)
-    // Do NOT call buildCursorRequest again — double-translation drops tool_results
+    // Do NOT call openaiToCursorRequest again — double-translation drops tool_results
     const messages = body.messages || [];
     const tools = body.tools || [];
     const reasoningEffort = body.reasoning_effort || null;