open-webui/Fu-Jie_openwebui-extensions
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: ensure empty summary model skips compression

Browse Source 
Co-authored-by: Fu-Jie <33599649+Fu-Jie@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2026-01-11 08:25:33 +00:00
parent d2f35ce396
commit 4b8515f682
1 changed files with 1 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
plugins/filters/async-context-compression/async_context_compression.py
View File

@@ -914,11 +914,7 @@ class Filter:
# 3. Check Token limit and truncate (Max Context Truncation) # 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 # [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 # This allows using a long-window model (like gemini-flash) to compress history exceeding the current model's window
summary_model_id = ( summary_model_id = self.valves.summary_model or body.get("model")
self.valves.summary_model
or body.get("model")
or "gpt-3.5-turbo"
)
if not summary_model_id: if not summary_model_id:
await self._log( await self._log(