Better handling of LLM request failures

2025-09-10 15:39:01 -07:00
parent 914b981072
commit 9a9a7268cd
10 changed files with 84 additions and 25 deletions
@@ -106,10 +106,13 @@ def _summarize_messages(
        completion_args = {
            "model": model,
            "messages": [{"role": "user", "content": prompt}],
+            "timeout": 180,
        }

        response = litellm.completion(**completion_args)
-        summary = response.choices[0].message.content
+        summary = response.choices[0].message.content or ""
+        if not summary.strip():
+            return messages[0]
        summary_msg = "<context_summary message_count='{count}'>{text}</context_summary>"
        return {
            "role": "assistant",