openzoo 0.48.35 → 0.48.36

package/lib/proxy.js

@@ -385,12 +385,23 @@ async function spillTranscript(body, log) {
   let bind;
   if (prior && corpus.startsWith(prior.corpus) && corpus.length > prior.corpus.length) {
     const delta = corpus.slice(prior.corpus.length);
-    await bindCorpus(delta, {
+    // FIRE AND FORGET. This delta is history for FUTURE turns — the answer
+    // being generated right now is served from the tail plus what is already
+    // bound, so waiting on the upload buys nothing and costs the user the
+    // round trip on every single turn. The context id is already known, so
+    // nothing is lost by not waiting for it.
+    //
+    // The FIRST bind is deliberately NOT async: the request must carry
+    // x-hrr-context, and that id does not exist until the bind returns. Firing
+    // that one off would send the opening turn with no context at all — a
+    // silently worse answer traded for a shorter pause, which is the wrong way
+    // round.
+    void bindCorpus(delta, {
       appendTo: prior.contextId,
       onStage: (stage, info) => {
-        if (stage === 'binding') log(`appending ${mb(info.bytes)}MB to ${prior.contextId} (delta only)`);
+        if (stage === 'binding') log(`appending ${mb(info.bytes)}MB to ${prior.contextId} (delta, background)`);
       },
-    });
+    }).catch((e) => log(`append failed (history may lag one turn): ${e.message}`));
     bind = { contextId: prior.contextId, hash: prior.hash, reused: true, bytes: delta.length };
   } else {
     bind = await bindCorpus(corpus, {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openzoo",
-  "version": "0.48.35",
+  "version": "0.48.36",
   "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",