- Video pipeline: video file OCR via VLM plus audio track ASR, integrated
into job_handlers with progress emit per phase. New media_utils.py for
audio extraction from video files.
- Document export: richExport.js replaces inline docx builder; DOCX and PDF
export buttons are now enabled in MilkdownEditor. File size limit raised to
100 MB.
- Input block: new InputBlockCrepe.vue component with inputBlockPlugin.ts
and inputBlock.js for custom user-input nodes in the editor.
- Risk config: added Vite dev server ports (5173) to CORS allowlist and
increased OCR max input from 10 MB to 100 MB.
- TTS/ASR refactor: simplified tts_asr.py model loading and warmup logic.
- Test coverage: updated tests for llm, main endpoints, pro completions and
web search modules.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Removed obsolete unit tests for TTS/ASR module.
- Deleted unused sample video file.
- Introduced OCRImageWrapper component for better OCR image handling with loading, success, and failure states.
- Updated copilot plugin to improve transaction handling and added new types for better type safety.
- Enhanced web search block plugin to support streaming content updates.
- Refactored API utility functions for better error handling and consistency across requests.
- Added new configuration for OCR API endpoint.
- Consolidated SSE event parsing into a shared utility.
- Created string utility functions to reduce code duplication.
- Removed outdated test documents related to compression functionality.
- Introduced a new web search block plugin to handle web search queries and results.
- Updated copilot, doc block, and pro block plugins to include web search context in AI completions.
- Implemented utility functions for parsing and building web search markdown.
- Enhanced API to support web search requests and responses.
- Added configuration for web search URL and timeout settings.
- Updated size limit checks to account for web search content.
“ydy0615”