- Redefine keep_first to count only non-system messages, protecting
the first N user/assistant exchanges plus all interleaved system messages
- System messages in the compression gap are now extracted and preserved
as original messages instead of being summarized
- System messages dropped during forced trimming are re-inserted into
the final output
- Change keep_first default from 1 to 0
- Update docstring, README, README_CN, WORKFLOW_GUIDE_CN, and docs mirrors
Fixes#62
- Updated README files for the following plugins to include installation instructions using Batch Install Plugins:
- deep-dive
- export_to_docx
- export_to_excel
- flash-card
- infographic
- smart-mind-map
- async-context-compression
- chat-session-mapping-filter
- folder-memory
- github_copilot_sdk_files_filter
- markdown_normalizer
- github-copilot-sdk
- iflow-sdk-pipe
- openwebui-skills-manager
- smart-mind-map-tool
- Added important notes regarding the removal of the official OpenWebUI Community version before installation.
- update plugin README badges to use Top <1% and a clearer contribution icon
- reorder badge rows across mirrored docs and templates
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
- Add comprehensive error logging for LLM response validation failures
- Thread __request__ context through entire summary generation pipeline
- Load and merge previous_summary from DB when not in outlet payload
- Use real request object instead of minimal synthetic context
- Add comprehensive error logging for LLM response validation failures
- Thread __request__ context through entire summary generation pipeline
- Load and merge previous_summary from DB when not in outlet payload
- Use real request object instead of minimal synthetic context
- Set 'enable_escape_fix' to False by default to prevent accidental corruption
- Improve LaTeX display math identification using regex protection
- Update documentation to reflect opt-in recommendation for escape fixes
- Fix Issue #57 remaining aggressive escaping bugs
- Fix error fallback mechanism to guarantee 100% rollback to original text on failure
- Improve escape character cleanup to protect inline code blocks from unwanted modification
- Fix 'enable_escape_fix_in_code_blocks' configuration to correctly apply to code blocks when enabled
- Change 'show_debug_log' default to False to reduce console noise and improve privacy
- Update READMEs and docs, bumped version to 1.2.8
- Enable default overwrite installation policy for overlapping skills
- Support deep recursive GitHub trees discovery mechanism to resolve#58
- Refactor internal architecture to fully decouple stateless helper logic
- READMEs and docs synced (v0.3.0)
* Initial plan
* docs: add OpenWebUI official newsletter featured recognition
- Add newsletter featured callout to Smart Mind Map README.md, README_CN.md, and docs
- Add newsletter featured callout to Markdown Normalizer README.md, README_CN.md, and docs
- Add newsletter featured badge to Prompt Plus in root README.md and README_CN.md
- Reference both newsletters: Jan 28, 2026 and Feb 3, 2026
Co-authored-by: Fu-Jie <33599649+Fu-Jie@users.noreply.github.com>
* docs: fix newsletter links to match actual featured issue per plugin
- Smart Mind Map: link only to Feb 3, 2026 (second newsletter)
- Markdown Normalizer: link only to Jan 28, 2026 (first newsletter)
- Prompt Plus (root READMEs): already correct, no change needed
Co-authored-by: Fu-Jie <33599649+Fu-Jie@users.noreply.github.com>
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: Fu-Jie <33599649+Fu-Jie@users.noreply.github.com>
- Fix Issue #49: resolve greedy regex matching in consecutive emphasis
- Add LaTeX formula protection to prevent corruption of \times, \nu, etc.
- Expand i18n support to 12 languages with strict alignment
- Fix NameError in Request import during testing
- Add native i18n support across 9 languages
- Implement non-blocking frontend log emission for zero TTFB delay
- Add token_usage_status_threshold to intelligently control status notifications
- Automatically detect and skip compression for copilot_sdk models
- Set debug_mode default to false for a quieter production environment
- Update documentation and remove legacy bilingual code
- Updated README.md and README_CN.md for the infographic plugin to reflect new features and bug fixes in version 1.5.0, including context-aware generation and language synchronization.
- Revised README.md and README_CN.md for the smart mind map plugin to include support for user feedback and a changelog.
- Enhanced README.md and README_CN.md for the async context compression filter with critical fixes and improved compatibility details.
- Introduced initial release notes for the folder memory filter, detailing its core features and installation instructions.
- Updated markdown normalizer documentation to synchronize version numbers and improve clarity on configuration options.
- Revised GitHub Copilot SDK documentation to enhance installation instructions and troubleshooting sections, including a new changelog.
- Add 'Prerequisites' section to folder-memory README files clarifying that conversations must occur inside a folder
- Update docs/plugins/filters/folder-memory.md and folder-memory.zh.md with same prerequisites
- Enhance extract_plugin_versions.py to auto-generate GitHub README URLs in release notes
- Update plugin-development workflow to document README link requirements for publishing
- Rename plugin from `folder-rule-collector` to `folder-memory` for better clarity.
- Refactor code to focus on "Project Rules" collection, removing "Knowledge" collection for V1.
- Add `PRIORITY` valve (default: 20) to ensure execution after context compression.
- Update all parameter names to uppercase for consistency.
- Update documentation (README, global docs) with GitHub raw URL for demo image.
- Remove `STATUS` valve as it's redundant with OpenWebUI's built-in function toggle.
- Add `ROADMAP.md` to track future "Project Knowledge" features.
- Update `.github/copilot-instructions.md` with detailed commit message guidelines.
This release introduces significant improvements to configuration flexibility, performance, and stability.
**Key Changes:**
* **Smart Configuration:**
* Added `summary_model_max_context` to allow independent context limits for the summary model (e.g., using `gemini-flash` with 1M context to summarize `gpt-4` history).
* Implemented auto-detection of base model settings for custom models, ensuring correct threshold application.
* **Performance & Refactoring:**
* Optimized `model_thresholds` parsing with caching to reduce overhead.
* Refactored `inlet` and `outlet` logic to remove redundant code and improve maintainability.
* Replaced all `print` statements with proper `logging` calls for better production monitoring.
* **Bug Fixes & Modernization:**
* Fixed `datetime.utcnow()` deprecation warnings by switching to timezone-aware `datetime.now(timezone.utc)`.
* Corrected type annotations and improved error handling for `JSONResponse` objects from LLM backends.
* Removed hard truncation in summary generation to allow full context usage.
**Files Updated:**
* Plugin source code (English & Chinese)
* Documentation and READMEs
* Version bumped to 1.2.1
