From 4b8515f68209c46ff4a8af9d3111332ca05ab69b Mon Sep 17 00:00:00 2001 From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com> Date: Sun, 11 Jan 2026 08:25:33 +0000 Subject: [PATCH] fix: ensure empty summary model skips compression Co-authored-by: Fu-Jie <33599649+Fu-Jie@users.noreply.github.com> --- .../async-context-compression/async_context_compression.py | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/plugins/filters/async-context-compression/async_context_compression.py b/plugins/filters/async-context-compression/async_context_compression.py index 3e09a29..0ec2323 100644 --- a/plugins/filters/async-context-compression/async_context_compression.py +++ b/plugins/filters/async-context-compression/async_context_compression.py @@ -914,11 +914,7 @@ class Filter: # 3. Check Token limit and truncate (Max Context Truncation) # [Optimization] Use the summary model's (if any) threshold to decide how many middle messages can be processed # This allows using a long-window model (like gemini-flash) to compress history exceeding the current model's window - summary_model_id = ( - self.valves.summary_model - or body.get("model") - or "gpt-3.5-turbo" - ) + summary_model_id = self.valves.summary_model or body.get("model") if not summary_model_id: await self._log(