openzoo 0.48.47 → 0.48.48

package/lib/proxy.js

@@ -863,6 +863,10 @@ export async function startProxy({ silent = false, requireToken = null, sessionM
     // answer back on the way out. See lib/anthropic.js.
     let anthropicMode = false;
     let anthropicModel = null;
+    // The CLIENT's streaming intent, kept separate from the body we send
+    // upstream. The Anthropic lane asks the gateway for a complete message (we
+    // can only translate a finished one) while still owing the caller SSE.
+    let clientWantsStream = false;
     let responsesMode = false;
     let responsesModel = null;
     let responsesCustom = null;   // names of freeform tools needing custom_tool_call on the way back
@@ -912,7 +916,24 @@ export async function startProxy({ silent = false, requireToken = null, sessionM
       try {
         const inbound = JSON.parse(bodyBuf.toString('utf8'));
         anthropicModel = inbound.model;
-        bodyBuf = Buffer.from(JSON.stringify(anthropicToOpenAI(inbound)));
+        // ANTHROPIC CLIENTS CANNOT READ AN OPENAI STREAM.
+        //
+        // The gateway now streams for real, and `relay()` pipes those frames
+        // through untouched — which is correct for an OpenAI client and
+        // unreadable to Claude Code, which speaks the Anthropic SSE grammar
+        // (message_start / content_block_delta / message_stop). It surfaced as
+        // "API returned an empty or malformed response (HTTP 200)": a 200 whose
+        // body the client cannot parse.
+        //
+        // The translation we have (openAIToAnthropic + writeAnthropicSse) works
+        // on a COMPLETE message, so this lane asks the gateway not to stream and
+        // keeps the buffered translation. That costs Claude Code the
+        // time-to-first-byte win until an incremental OpenAI->Anthropic frame
+        // translator exists; a readable answer late beats an unreadable one now.
+        const converted = anthropicToOpenAI(inbound);
+        clientWantsStream = converted.stream === true || inbound.stream === true;
+        converted.stream = false;
+        bodyBuf = Buffer.from(JSON.stringify(converted));
         anthropicMode = true;
         req.url = '/v1/chat/completions';
         url = `${config.apiBase}${req.url}`;
@@ -939,7 +960,7 @@ export async function startProxy({ silent = false, requireToken = null, sessionM
       }
       try {
         const parsed = JSON.parse(bodyBuf.toString('utf8'));
-        wantsStream = parsed?.stream === true;
+        wantsStream = parsed?.stream === true || clientWantsStream;
         // REASONING MODELS SPEND max_tokens ON THINKING FIRST.
         //
         // The budget covers hidden reasoning AND the visible answer, so a

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openzoo",
-  "version": "0.48.47",
+  "version": "0.48.48",
   "description": "Local x402-paying proxy + MCP server for openzoo.fun — point any OpenAI-compatible harness (Cursor, Claude Code, aider, SDKs) at localhost and it pays per call from a local burner wallet. Solana and Base rails live; Robinhood experimental.",
   "license": "MIT",
   "type": "module",