fix(alicode): preserve cache_control for DashScope providers (#2069)

Opt-in quirk preserveCacheControl keeps cache_control on content blocks
for alicode/alicode-intl, enabling DashScope prompt caching. signature
is always stripped; all other providers unchanged.

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

open-sse/providers/registry/alicode-intl.js

@@ -16,6 +16,7 @@ export default {
   transport: {
     baseUrl: "https://coding-intl.dashscope.aliyuncs.com/v1/chat/completions",
     headers: {},
+    quirks: { preserveCacheControl: true },
   },
   models: [
     { id: "qwen3.5-plus", name: "Qwen3.5 Plus" },

open-sse/providers/registry/alicode.js

@@ -16,6 +16,7 @@ export default {
   transport: {
     baseUrl: "https://coding.dashscope.aliyuncs.com/v1/chat/completions",
     headers: {},
+    quirks: { preserveCacheControl: true },
   },
   models: [
     { id: "qwen3.5-plus", name: "Qwen3.5 Plus" },

open-sse/translator/formats/openai.js

@@ -6,42 +6,46 @@ export { VALID_OPENAI_CONTENT_TYPES, VALID_OPENAI_MESSAGE_TYPES };
 
 // Filter messages to OpenAI standard format
 // Remove: thinking, redacted_thinking, signature, and other non-OpenAI blocks
-export function filterToOpenAIFormat(body) {
+// opts.preserveCacheControl: keep cache_control on content blocks (e.g. for DashScope/alicode)
+export function filterToOpenAIFormat(body, opts = {}) {
   if (!body.messages || !Array.isArray(body.messages)) return body;
-  
+  const keepCache = !!opts.preserveCacheControl;
+
+  function stripBlock(block) {
+    const { signature, cache_control, ...rest } = block;
+    return keepCache && cache_control ? { ...rest, cache_control } : rest;
+  }
+
   body.messages = body.messages.map(msg => {
     // Normalize developer role to system (many providers don't support developer)
     if (msg.role === ROLE.DEVELOPER) msg = { ...msg, role: ROLE.SYSTEM };
-    
+
     // Keep tool messages as-is (OpenAI format)
     if (msg.role === ROLE.TOOL) return msg;
-    
+
     // Keep assistant messages with tool_calls as-is
     if (msg.role === ROLE.ASSISTANT && msg.tool_calls) return msg;
-    
+
     // Handle string content
     if (typeof msg.content === "string") return msg;
-    
+
     // Handle array content
     if (Array.isArray(msg.content)) {
       const filteredContent = [];
-      
+
       for (const block of msg.content) {
         // Skip thinking blocks
         if (block.type === CLAUDE_BLOCK.THINKING || block.type === CLAUDE_BLOCK.REDACTED_THINKING) continue;
-        
+
         // Only keep valid OpenAI content types
         if (VALID_OPENAI_CONTENT_TYPES.includes(block.type)) {
-          // Remove signature field if exists
-          const { signature, cache_control, ...cleanBlock } = block;
-          filteredContent.push(cleanBlock);
+          filteredContent.push(stripBlock(block));
         } else if (block.type === CLAUDE_BLOCK.TOOL_USE) {
           // Convert tool_use to tool_calls format (handled separately)
           continue;
         } else if (block.type === CLAUDE_BLOCK.TOOL_RESULT) {
           // Keep tool_result but clean it
-          const { signature, cache_control, ...cleanBlock } = block;
-          filteredContent.push(cleanBlock);
+          filteredContent.push(stripBlock(block));
         }
       }
       

open-sse/translator/index.js

@@ -109,7 +109,9 @@ export function translateRequest(sourceFormat, targetFormat, model, body, stream
   // Always normalize to clean OpenAI format when target is OpenAI
   // This handles hybrid requests (e.g., OpenAI messages + Claude tools)
   if (targetFormat === FORMATS.OPENAI) {
-    result = filterToOpenAIFormat(result);
+    result = filterToOpenAIFormat(result, {
+      preserveCacheControl: !!PROVIDERS[provider]?.quirks?.preserveCacheControl,
+    });
   }
 
   // Final step: prepare request for Claude format endpoints