openzoo 0.48.52 → 0.48.53

package/lib/proxy.js

@@ -463,7 +463,15 @@ async function spillTranscript(body, log, req) {
   //
   // Claude Code identifies its session, so use that when it is offered and fall
   // back to the content anchor when it is not. Same memo, better key.
-  const sessionId = req?.headers?.['x-session-id']
+  // CAPTURED FROM A LIVE claude-cli/2.1.232 REQUEST, not guessed. The first
+  // version of this checked x-session-id / x-claude-session-id /
+  // metadata.user_id — none of which Claude Code sends, so it silently fell
+  // back to the content anchor on every request and the feature did nothing.
+  // The real header list is:
+  //   anthropic-beta, anthropic-version, x-app, x-claude-code-session-id,
+  //   x-stainless-*
+  const sessionId = req?.headers?.['x-claude-code-session-id']
+    || req?.headers?.['x-session-id']
     || req?.headers?.['x-claude-session-id']
     || (typeof body?.metadata?.user_id === 'string' ? body.metadata.user_id : null);
   const anchor = sessionId ? `sid:${sessionId}` : corpus.slice(0, 2048);
@@ -499,9 +507,12 @@ async function spillTranscript(body, log, req) {
   spillMemo.set(anchor, { corpus, contextId: bind.contextId, hash: bind.hash });
   if (spillMemo.size > 32) spillMemo.delete(spillMemo.keys().next().value);
   const sent = msgs.length - cut;
+  // NAME THE KEY. A memo keyed on the wrong thing fails silently — it just
+  // re-binds forever and collides sessions — so the log says which key was used.
+  const keyKind = sessionId ? `sid ${String(sessionId).slice(0, 8)}` : 'content-anchor';
   log(bind.reused
-    ? `transcript prefix already bound (${bind.contextId}) — sending ${sent}/${msgs.length} turns`
-    : `transcript prefix bound (${mb(bind.bytes)}MB → ${bind.contextId}) — sending ${sent}/${msgs.length} turns`);
+    ? `transcript prefix already bound (${bind.contextId}, ${keyKind}) — sending ${sent}/${msgs.length} turns`
+    : `transcript prefix bound (${mb(bind.bytes)}MB → ${bind.contextId}, ${keyKind}) — sending ${sent}/${msgs.length} turns`);
 
   // ADAPTIVE TOP-K. A fixed 32 chunks is what was actually eating the saving:
   // MEASURED on a 56,265-token corpus, top_k 32 handed 9,990 tokens back and
@@ -1018,6 +1029,12 @@ export async function startProxy({ silent = false, requireToken = null, sessionM
       if ((req.url || '').includes('/chat/completions') && req.method === 'POST') {
         servedRequests += 1;
         say(`\n<- request #${servedRequests} from ${(req.headers['user-agent'] || 'unknown').slice(0, 40)}`);
+        // TEMPORARY: name the headers (not values) so we can see whether the
+        // client offers a session id at all. Values are never logged — several
+        // of these carry auth.
+        if (process.env.OPENZOO_LOG_HEADERS === '1') {
+          log(`  headers: ${Object.keys(req.headers).sort().join(', ')}`);
+        }
       }
     if (rewritablePath(req.method, req.url)) {
       const rw = await maybeRewriteModel(bodyBuf);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "openzoo",
-  "version": "0.48.52",
+  "version": "0.48.53",
   "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",