Merge pull request #518 from diegosouzapw/fix/issue-517-515-prompt-cache-key-tagcontent

fix: preserve prompt_cache_key in Responses API, escape \n in tagContent (#517, #515)

open-sse/services/combo.ts

@@ -472,7 +472,7 @@ export async function handleComboChat({
         // SDKs close the connection on finish_reason, so anything sent after
         // that marker is silently dropped.
         if (!res.body) return res;
-        const tagContent = `\n<omniModel>${modelStr}</omniModel>\n`;
+        const tagContent = `\\n<omniModel>${modelStr}</omniModel>\\n`;
         const encoder = new TextEncoder();
         const decoder = new TextDecoder();
         let tagInjected = false;

open-sse/translator/helpers/responsesApiHelper.ts

@@ -93,10 +93,11 @@ export function convertResponsesApiFormat(body) {
   }
 
   // Cleanup Responses API specific fields
+  // Note: prompt_cache_key is intentionally preserved — it is used by Codex and other
+  // providers as a cache-affinity signal. Stripping it breaks prompt caching (#517).
   delete result.input;
   delete result.instructions;
   delete result.include;
-  delete result.prompt_cache_key;
   delete result.store;
   delete result.reasoning;
 

open-sse/translator/request/openai-responses.ts

@@ -227,10 +227,11 @@ export function openaiResponsesToOpenAIRequest(
   });
 
   // Cleanup Responses API specific fields
+  // Note: prompt_cache_key is intentionally preserved — it is used by Codex and other
+  // providers as a cache-affinity signal. Stripping it breaks prompt caching (#517).
   delete result.input;
   delete result.instructions;
   delete result.include;
-  delete result.prompt_cache_key;
   delete result.store;
   delete result.reasoning;