Overview
This patch release broadens summary-response parsing so the filter can accept both classic chat-completions payloads and Responses-style output payloads. It also improves empty-summary diagnostics without persisting reasoning-only fields. Polish (pl-PL) translations are also added.
What's Changed
- fix: robust summary response parsing for multi-provider shapes by @NexZhu in #73
- feat: add Polish (pl-PL) translations by @mhajder in #77
Bug Fixes
- Alternate summary payload support:
_call_summary_llm()now accepts summary text fromchoices[].message.content,output_textcontent parts, and Responses-styleoutputmessage items. - Stale choices-only gate removed: The summary call path no longer rejects valid provider payloads just because they omit
choices. - Clearer empty-summary errors: When no final summary text is present, the filter now reports a compact response-shape summary instead of a misleading generic format error.
New Features
- Polish language support: Full
pl-PLtranslation set added toTRANSLATIONS, covering all status messages, prompts, and UI strings.
Behavior Notes
- Reasoning-only output is ignored:
reasoning_content,thinking, and reasoning output items are not treated as summary text, so private chain-of-thought is not written into chat memory. - No change to 1.6.3 fail-mode behavior:
SUMMARY_FAIL_MODEcontinues to control whether upstream summary-call errors are silent or raised.
Migration Notes
No breaking changes. If a provider returns only reasoning fields and no final answer text, the filter will skip saving a summary for that turn and log the response shape for debugging.
Version Changes
Plugin Updates
- Async Context Compression: v1.6.3 → v1.6.4 | 📖 README
New Contributors
📚 Documentation Portal
🐛 Report Issues
Full Changelog: openwebui-skills-manager-v0.3.3...async-context-compression-v1.6.4