feat(providers): add Cline free-tier models and sync Freebuff catalog

- Cline: 6 free models, cline-cli product headers, API-key auth,
  {data} envelope unwrap, workos: prefix handling
- Freebuff: muse-spark 1.3 → 1.2 (upstream withdrawal 2026-09-07),
  DeepSeek V4.1 Flash rename

open-sse/handlers/chatCore/nonStreamingHandler.js

@@ -138,6 +138,21 @@ function openAICompletionToResponses(responseBody, customToolNames = null) {
   };
 }
 
+/**
+ * Unwrap gateway envelopes around an OpenAI Chat Completions body.
+ * Some OpenAI-compatible gateways wrap the body in a `data` envelope
+ * (Cline: {data, success}) — without this, choices/usage don't resolve at
+ * top level downstream and surface as "no completion choices".
+ * Generic guard, no provider hardcode: only fires when the OpenAI body is
+ * nested under `data`.
+ */
+export function unwrapDataEnvelope(responseBody) {
+  if (responseBody && !responseBody.choices && responseBody.data?.choices) {
+    return responseBody.data;
+  }
+  return responseBody;
+}
+
 /**
  * Translate non-streaming response body from provider format → OpenAI format.
  */
@@ -305,6 +320,9 @@ export async function handleNonStreamingResponse({ providerResponse, provider, m
   }
 
   reqLogger.logProviderResponse(providerResponse.status, providerResponse.statusText, providerResponse.headers, responseBody);
+  // Unwrap AFTER logging (raw envelope stays in the log for forensics) but
+  // BEFORE usage extraction/translation so choices/usage resolve downstream.
+  responseBody = unwrapDataEnvelope(responseBody);
   if (onRequestSuccess) {
     Promise.resolve()
       .then(onRequestSuccess)