refactor(open-sse): D1c — forceStream hardcode → PROVIDERS schema (#5)

chatCore providerRequiresStreaming: switch provider-name →
PROVIDERS[provider].forceStream. Thêm forceStream:true vào registry
openai/codex/commandcode. verify-providers allowlist added-fields
(forceStream/urlSuffix verified bằng golden + runtime test riêng).

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

open-sse/handlers/chatCore.js

@@ -7,6 +7,7 @@ import { createStreamController } from "../utils/streamHandler.js";
 import { refreshWithRetry } from "../services/tokenRefresh.js";
 import { createRequestLogger } from "../utils/requestLogger.js";
 import { getModelTargetFormat, getModelStrip, getModelUpstreamId, getModelType, PROVIDER_ID_TO_ALIAS } from "../config/providerModels.js";
+import { PROVIDERS } from "../config/providers.js";
 import { createErrorResult, parseUpstreamError, formatProviderError } from "../utils/error.js";
 import { HTTP_STATUS } from "../config/runtimeConfig.js";
 import { handleBypassRequest } from "../utils/bypassHandler.js";
@@ -59,7 +60,7 @@ export async function handleChatCore({ body, modelInfo, credentials, log, onCred
   }
 
   const clientRequestedStreaming = body.stream === true || sourceFormat === FORMATS.ANTIGRAVITY || sourceFormat === FORMATS.GEMINI || sourceFormat === FORMATS.GEMINI_CLI;
-  const providerRequiresStreaming = provider === "openai" || provider === "codex" || provider === "commandcode";
+  const providerRequiresStreaming = PROVIDERS[provider]?.forceStream === true;
   let stream = providerRequiresStreaming ? true : (body.stream !== false);
 
   // DeepSeek-TUI: interactive TUI panel sends stream:true and needs SSE.

open-sse/providers/registry/codex.js

@@ -6,6 +6,7 @@ export default {
   transport: {
     baseUrl: "https://chatgpt.com/backend-api/codex/responses",
     format: "openai-responses",
+    forceStream: true,
     headers: {
       "originator": "codex_cli_rs",
       "User-Agent": "codex_cli_rs/0.136.0"

open-sse/providers/registry/commandcode.js

@@ -4,6 +4,7 @@ export default {
   "transport": {
     "baseUrl": "https://api.commandcode.ai/alpha/generate",
     "format": "commandcode",
+    "forceStream": true,
     "headers": {
       "x-command-code-version": "0.25.7",
       "x-cli-environment": "cli"

open-sse/providers/registry/openai.js

@@ -2,7 +2,8 @@ export default {
   "id": "openai",
   "alias": "openai",
   "transport": {
-    "baseUrl": "https://api.openai.com/v1/chat/completions"
+    "baseUrl": "https://api.openai.com/v1/chat/completions",
+    "forceStream": true
   },
   "models": [
     {