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>
Add support to download and load TTS model from ModelScope, with a fallback to the HuggingFace mirror.
Implement a `documentLoadStatus` property and helper functions in `office.js` to track file loading state.
Improve request cancellation logic in `api.js`, ensuring proper cancel URL resolution and request‑id handling.
These changes enhance robustness, reduce external dependencies, and provide better UX for office file handling.
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.
Add a file tree UI and corresponding composable for local file management.
Introduce TTS menu and player components for voice synthesis integration.
Add new EditorView and DocsView routes and update SettingsPanel view switching.
Enhance Mermaid plugin with improved styling and action buttons.
Add LANGUAGE_SYNONYMS dictionary to map language aliases to canonical IDs,
_canonical_language_id() to normalize language identifiers, and
_language_guidance() to provide language-specific instructions for LLM
code generation. This improves language detection and ensures consistent
prompt context across different language format variations.
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.
Add API key security using fastapi.security.APIKeyHeader to protect /v1/completions and /v1/ocr endpoints. Updated frontend to include X-API-Key header in API requests. Also changed default API base URL from http://149.104.29.239:8001 to https://api.learnteach.tech:8002.
- Add privacy mode to hide IP and user preferences from AI requests
- Add model thinking levels (low/medium/high) for context analysis depth
- Add PWA support with service worker, manifest, and app icons
- Add SettingsPanel for user preferences (theme, background, language)
- Add i18n translations for en/zh/ja/ko/de/fr
- Add Pinia store for centralized settings management
- Update backend to support user preferences and thinking levels
- Update config to use absolute API URLs
- Add GeoLite2-City.mmdb database for IP lookup
- Create geoip.py module for IP location services
- Extract client IP from requests and log location info
- Pass location context to LLM prompts for enhanced responses
- Implement SHA-256 image hashing to cache OCR results and avoid re-processing identical images
- Add 100MB file size limit for image uploads with user-friendly error messages
- Clear ghost suggestions when uploading new images to prevent interference
- Optimize size limit calculation in copilot plugin to include OCR context
- Remove debug logging from production code
- Add image processing optimization plan document
BREAKING CHANGE: Image upload size limit is now enforced at 100MB (previously unlimited)
- Replace overlay-based GhostTextOverlay.vue with ProseMirror Mark system
- Add AI toggle button with enable/disable functionality
- Implement new copilotPlugin.ts using copilotGhostMark for inline suggestions
- Fix cursor position offset in prompt.py by moving first suffix char to prefix
- Improve API error handling with abort signal support and debug logging
- Update model configuration from gpt-oss:120b to gpt-oss:20b
- Add button tooltips and improve editor styling
- Remove deprecated inlineSuggestionPlugin.ts
- Update README with new architecture diagram and feature documentation
This commit refactors the LLM integration to use Ollama's native Python client instead of OpenAI-compatible API, while fixing critical template syntax errors and improving project structure.
Key changes:
- Replace openai package with ollama package in backend requirements
- Rewrite llm.py to use ollama.AsyncClient for direct Ollama API calls
- Update main.py to use non-streaming Ollama responses with thinking extraction
- Fix template syntax error in MilkdownEditor.vue (GhostTextOverlay component tags)
- Fix string截取错误 by using slice() instead of substring()
- Add src/utils/api.js and src/utils/config.js for shared configuration
- Add CORS middleware to FastAPI backend
- Update prompt.py with clearer instructions for continuation generation
- Add comprehensive README.md documentation
BREAKING CHANGE: Environment variables OLLAMA_BASE_URL changed to OLLAMA_HOST (remove /v1/ suffix)
“ydy0615”
ydy0615