From 97ecae4e77abdb53bd3ef95b60efc532752c1463 Mon Sep 17 00:00:00 2001 From: pyr0ball Date: Tue, 12 May 2026 18:27:52 -0700 Subject: [PATCH] fix: increase LLM summarize timeout to 120s for remote cf-orch routing 20s was too tight for first-request model swaps in Ollama (model cold load can take 30-60s). 120s matches coordinator inference timeout. --- app/services/llm.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/app/services/llm.py b/app/services/llm.py index 4fd13c9..fc92c70 100644 --- a/app/services/llm.py +++ b/app/services/llm.py @@ -38,7 +38,7 @@ def summarize( llm_url: str, llm_model: str, api_key: str | None = None, - timeout: float = 20.0, + timeout: float = 120.0, ) -> str | None: if not entries: return None