extraction error logging

packages/orchestration-service/src/services/summarization.js

@@ -9,34 +9,37 @@ const MAX_SUMMARY_TOKENS = parseInt(getEnv('SUMMARY_MAX_TOKENS', SUMMARIES.MAX_S
 const MIN_EPISODES_SINCE = parseInt(getEnv('SUMMARY_MIN_EPISODES', SUMMARIES.MIN_EPISODES_SINCE));
 
 function buildSummaryPrompt(episodes, existingSummary = null) {
-    const MAX_CHARS = 3000; // truncate input to keep Phi3 focused
+    const MAX_CHARS = 3000;
     let context = episodes
         .map(ep => `User: ${ep.user_message}\nAssistant: ${ep.ai_response}`)
         .join('\n\n');
 
-    // Truncate from the start if too long — keep the most recent exchanges
     if (context.length > MAX_CHARS) {
         context = context.slice(-MAX_CHARS);
     }
 
     const instruction = existingSummary
-        ? `Update the summary below to include the new exchanges. Write 3-5 sentences in third person. Output only the updated summary text, nothing else.
+        ? `Update the summary below to incorporate the new exchanges.
+Write 3-5 sentences in third person. Do not quote directly — paraphrase only.
+Do not include greetings, sign-offs, or filler. Output only the updated summary text.
 
 Previous summary:
 ${existingSummary}
 
 New exchanges:
 ${context}`
-        : `Summarize the conversation below in 3-5 sentences. Write in third person. Output only the summary text, nothing else.
+        : `Summarize the conversation below in 3-5 sentences.
+Write in third person. Do not quote directly — paraphrase only.
+Do not include greetings, sign-offs, or filler. Output only the summary text.
 
 Conversation:
 ${context}`;
 
     return [
-        '<|user|>',
+        '<|im_start|>user',   // ChatML for qwen2.5
         instruction,
-        '<|end|>',
+        '<|im_end|>',
-        '<|assistant|>',
+        '<|im_start|>assistant',
     ].join('\n');
 }
 
@@ -52,7 +55,7 @@ async function generateSummary(episodes, existingSummary = null) {
             stream: false,
             options: {
                 temperature: 0.2,   // slightly higher than entities — summaries benefit from some fluency
-                num_predict: 200,   // generous but bounded — keeps summaries from running long
+                num_predict: 500,   // generous but bounded — keeps summaries from running long
             },
         }),
     });