- 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- Removed outdated test documents related to compression functionality.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.
- Introduced `requirements.docker.txt` for Docker-specific dependencies.
- Updated `requirements.txt` to include `psycopg[binary]` and `python-multipart`.
- Enhanced test suite in `test_main_endpoints.py` to cover document CRUD operations.
- Modified `docker-compose.yml` to include PostgreSQL and frontend services.
- Added Nginx configuration for reverse proxying API requests.
- Refactored file handling in Vue components to support new document storage backend.
- Created new utility functions in `docsApi.js` for document management.
- Updated configuration to support new API endpoints for document operations.
- Adjusted Vite configuration to proxy API requests to the local backend.
- Added support for PRO mode in LLM with specific instruction handling and context awareness.
- Updated prompt building functions to include prefill options for better context management.
- Introduced new inline examples for PRO mode in JSON format.
- Enhanced system prompts to reflect PRO mode capabilities and rules.
- Modified API endpoints to accommodate new parameters and ensure backward compatibility.
- Improved test cases to validate new functionality and ensure comprehensive coverage.
The workspace now carries the pro editing flow, streaming completion path, and lighter Office preview state as one checkpoint so the remote has the current runnable project shape.
Constraint: Preserve the current workspace as a single reviewable project commit while excluding local agent state and verification artifacts. Removed stale Univer runtime dependencies from the lockfile so installs match package.json.
Rejected: Commit runtime screenshots, .omx state, and coverage files | they are local artifacts rather than source state.
Confidence: medium
Scope-risk: broad
Directive: Keep package.json and package-lock.json synchronized when changing frontend dependencies.
Tested: npm run build; C:\Users\ydy\.conda\envs\llmwebsite\python.exe -m pytest backend/tests/test_main_endpoints.py backend/tests/test_main_cancel.py backend/tests/test_llm.py backend/tests/test_llm_extended.py -v -o addopts= (44 passed).
Not-tested: Full pytest with repository coverage addopts currently reports 0% coverage because pytest-cov watches backend.* module names while tests import top-level backend modules.
Co-authored-by: OmX <omx@oh-my-codex.dev>
- Normalize line endings in Markdown export for DOCX files.
- Improve selection serialization to Markdown with better handling of empty documents.
- Add a new `updateFile` function to the file system for updating file properties.
- Introduce video transcoding capabilities using FFmpeg, supporting various video formats.
- Update AGENTS.md for clearer plugin structure and responsibilities.
- Add scoped styles for TreeNodeItem component to improve UI consistency.
- Implement cross-origin isolation headers in Vite configuration for enhanced security.
- Remove obsolete test_cross.py file.
- Add AGENTS.md knowledge base with project documentation
- Move UserPreferences model to separate models.py file
- Extract API_KEY to environment variable for security
- Enhance Univer Editor with PPTX support and improved UI
- Improve file system handling with binary file detection
- Add HF_ENDPOINT mirror for better China connectivity
- Clean up unused imports and code structure
Added a new `.coveragerc` file configuring coverage thresholds and exclusions.
Included `pytest.ini` to enable coverage reporting for multiple backend modules (`main`, `llm`, `prompt`, `geoip`, `tts_asr`) with a 90 % fail‑under requirement and detailed HTML output.
Implemented a suite of unit tests:
* `test_geoip.py` – validates geo‑location lookup logic.
* `test_llm_extended.py` – tests LLm response extraction and Ollama interactions.
* `test_main_endpoints.py` – covers API endpoints for completions, OCR, and TTS.
* `test_prompt_extended.py` – verifies language sanitization, timestamp generation, and prompt building.
* `test_tts_asr_coverage.py` – checks device detection, cache clearing, and model loading under various environment configurations.
* `test_tts_asr_extended.py` – further tests TTS/ASR device selection and time‑outs.
Updated `backend/requirements.txt` to use newer, compatible packages, removed obsolete testing dependencies, and added `qwen-tts`.
Modified `backend/tts_asr.py` to work with the new `Qwen3TTSModel`, simplified imports, and adjusted device mapping logic.
Additionally, frontend changes added a new `TreeNodeItem` component, updated Markdown rendering, added TTS instruction fields, and reworked context menu handling.
No breaking changes were introduced.
Introduce a comprehensive TTS/ASR module that:
- Adds /v1/tts-asr/config, /status, /warmup, /tts, /asr endpoints with detailed JSON responses
- Implements Apple‑Silicon detection, device selection (MPS/CUDA/CPU), and memory limiting logic
- Supports selectable model size, quantization, and offline mode via environment variables
- Adds robust audio validation and multi‑path resampling fallback
- Provides new README sections for API usage, device detection, and performance benchmarking
- Includes a full testing suite: unit tests, integration tests, macOS simulation and performance reports
- Updates backend dependencies and CI scripts
- Adds new front‑end views and components for Univer editor integration
All changes are backward compatible; new features are exposed through environment variables and new API routes.
Add support for cancelling in-progress LLM completion requests via new /v1/completions/cancel endpoint with task tracking. Implement mermaid diagram rendering in the Milkdown editor with a new mermaidPlugin. Update copilotPlugin to properly abort requests with descriptive reasons. Refactor settings panel to handle system theme changes reactively. Add camera capture support for image uploads.
Separate prompt generation into system and user prompts for better LLM instruction following. Backend now builds a detailed system prompt with constraints for math formatting, code block handling, boundary newlines, and OCR safety, while user prompt contains context and completion state flags. Added corresponding tests for both modules.
“ydy0615”
ydy0615