orchestration fixes

packages/orchestration-service/src/chat/index.js

@@ -87,7 +87,7 @@ async function chat(externalId, userMessage, options = {}) {
         tokenCount: (result.evalCount || 0 ) + (result.promptEvalCount || 0 ),
     };
 }
-
+/*
 async function chatStream(externalId, userMessage, onChunk, options = {} ) {
     // 1. Resolve or create session
     let session = await memory.getSessionByExternalId(externalId);
@@ -148,5 +148,70 @@ async function chatStream(externalId, userMessage, onChunk, options = {} ) {
     }
     return {model, tokenCount};        
 }
+*/
+async function chatStream(externalId, userMessage, onChunk, options = {}) {
+  let session = await memory.getSessionByExternalId(externalId);
+  if (!session) session = await memory.createSession(externalId);
 
+  const recentEpisodes = await memory.getRecentEpisodes(session.id, RECENT_EPISODE_LIMIT);
+  const recentIds = new Set(recentEpisodes.map(e => e.id));
+  const semanticEpisodes = await getSemanticEpisodes(userMessage, session.id, recentIds);
+
+  const prompt = buildPrompt(recentEpisodes, semanticEpisodes, userMessage);
+  const res = await inference.completeStream(prompt, options);
+
+  let fullText = '';
+  let model = '';
+  let tokenCount = 0;
+  let buffer = '';
+
+  for await (const chunk of res.body) {
+    buffer += Buffer.from(chunk).toString('utf8');
+
+    const events = buffer.split('\n\n');
+    buffer = events.pop() || '';
+
+    for (const event of events) {
+      const lines = event.split('\n');
+      const dataLines = lines
+        .filter(line => line.startsWith('data: '))
+        .map(line => line.slice(6));
+
+      if (dataLines.length === 0) continue;
+
+      const raw = dataLines.join('\n').trim();
+      if (raw === '[DONE]') continue;
+
+      try {
+        const data = JSON.parse(raw);
+
+        if (data.response) {
+          fullText += data.response;
+          onChunk(data.response);
+        }
+
+        if (data.model) model = data.model;
+        if (data.done && data.tokenCount !== undefined) {
+          tokenCount = data.tokenCount;
+        }
+
+        if (data.error) {
+          throw new Error(data.error);
+        }
+      } catch (err) {
+        console.error('[orchestration] Failed to parse inference SSE event:', raw, err.message);
+      }
+    }
+  }
+
+  console.log('[orchestration] final streamed text length:', fullText.length);
+
+  if (fullText.trim()) {
+    await memory.createEpisode(session.id, userMessage, fullText, tokenCount);
+  } else {
+    console.warn('[orchestration] Stream finished with no assistant text; episode not saved');
+  }
+
+  return { model, tokenCount };
+}
 module.exports = { chat, chatStream };