docs: update project documentation to reflect current architecture#60
Open
hidetoshi-oya wants to merge 16 commits intoPrat011:masterfrom
Open
docs: update project documentation to reflect current architecture#60hidetoshi-oya wants to merge 16 commits intoPrat011:masterfrom
hidetoshi-oya wants to merge 16 commits intoPrat011:masterfrom
Conversation
- Replace all `npm run` / `npm rebuild` references in scripts with pnpm equivalents - Remove package-lock.json in favor of existing pnpm-lock.yaml - Add pnpm.onlyBuiltDependencies for native packages (electron, esbuild, sharp, tesseract.js) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Replace all npm commands with pnpm equivalents in README - Update CLAUDE.md command table to use pnpm - Resolve merge conflict in README.md Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Change liquid-glass effects from white-based (rgba 255,255,255) to black-based (rgba 0,0,0) with ~55% opacity. Update chat bubbles, inputs, and ModelSelector to use dark theme colors. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Implement real-time dual transcription using Web Speech API for microphone and Gemini Live API for system audio. Add React hooks, AudioWorklet PCM processor, TranscriptionDisplay component, and IPC integration. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…, remove tesseract.js - U2: Replace deprecated @google/generative-ai with @google/genai v1.42.0 - U3: Update model string from gemini-2.0-flash to gemini-2.5-flash - U5: Remove unused tesseract.js dependency (15MB+) - Add 13 unit tests for LLMHelper (TDD Green) - Exclude test files from electron tsconfig Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Upgrade electron from ^33.2.0 to ^40.6.0 (7 major versions) - Fix transparent+resizable bug: set resizable: false (#48421) - Fix setContentProtection cleared by hide(): re-apply after show (#45844) - sharp rebuilt successfully with new Node ABI Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Create types.ts with LLMProvider interface and capabilities - Extract GeminiProvider from LLMHelper (Gemini SDK wrapper) - Extract OllamaProvider from LLMHelper (REST API wrapper) - Create ProviderRegistry with switching and auto-fallback - Refactor LLMHelper as facade over ProviderRegistry - Add 13 ProviderRegistry unit tests (registration, switching, fallback) - All 40 existing tests still pass Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- OpenAIProvider: GPT-4o chat + vision (openai v6.23.0) - ClaudeProvider: Claude Sonnet 4.6 chat + vision (@anthropic-ai/sdk v0.78.0) - 15 new unit tests (8 OpenAI + 7 Claude) - All 55 tests pass Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Persistent settings storage in {userData}/settings.json
- API key encryption via Electron safeStorage (OS Keychain)
- Per-provider configuration (gemini/openai/claude/ollama)
- 13 unit tests covering CRUD, encryption, persistence
- Fix: use factory function for defaults to prevent shared mutation
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Phase 1.3 - New IPC endpoints: - get-settings / update-settings - get-available-providers / get-provider-models - set-active-provider / set-provider-api-key - test-provider-connection - SettingsHelper integrated into AppState Phase 1.4 - ModelSelector UI: - 4-provider card grid (Gemini/OpenAI/Claude/Ollama) - BYOK API key input per provider - Capability badges (Vision/Audio) - Connection test button Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- StorageHelper: meeting CRUD with JSON persistence (20 tests) - MeetingHelper: session management + Map-Reduce chunked summarization (16 tests) - Prompt templates: summary, action items, coaching, quick response (8 tests) - 10 new IPC endpoints for meeting lifecycle - MeetingPanel UI with real-time status, summary, action items - useMeeting hook for frontend state management - Meeting button added to QueueCommands toolbar Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…e 3) - PlaybookHelper: 6 built-in playbooks + custom CRUD (15 tests) - CoachingHelper: statement evaluation with cooldown + quick responses (8 tests) - 7 new IPC endpoints (playbook CRUD, coaching, quick responses) - PlaybookSelector UI: 3-column grid with active highlight - QuickResponses UI: click-to-copy response cards - MeetingPanel: integrated coaching advice + playbook selection - Built-in playbooks: technical-interview, sales-call, team-standup, vc-pitch, customer-success, general Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…nitor (Phase 4) - ConversationHelper: persistent chat history with 50-message cap (11 tests) - Click-through overlay: Cmd+Shift+T toggle, setIgnoreMouseEvents - Multi-monitor: getAvailableDisplays, moveToDisplay, snapTo (6 positions) - 8 new IPC endpoints for conversation, window management - Keyboard shortcut Cmd+Shift+T registered in ShortcutsHelper Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- ExportHelper: Markdown export, clipboard copy, JSON export (6 tests) - WebhookHelper: meeting.ended event POST, URL config, test hook (6 tests) - 6 new IPC endpoints for export and webhook management - Full type safety across all IPC boundaries Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…alendar integration Phase 4.1: Screen region capture (Cmd+Shift+H) with sharp cropping and fullscreen selection overlay. Phase 4.5: OpenAI Whisper API multi-language transcription (50+ languages, auto-detect). Phase 5.1: Calendar helper with ICS parsing, playbook auto-suggestion, and imminent event detection. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
CLAUDE.md, README.md, and rule files were outdated — still referencing Electron 33, Gemini/Ollama-only setup, and missing all new helpers added in Phases 1-5 (ProviderRegistry, Meeting, Coaching, Whisper, Calendar, Region Capture, etc.). Updated architecture diagram, tech stack versions, AI provider docs, keyboard shortcuts, feature descriptions, comparison table, security rules, and Electron coding guidelines. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Test plan
pnpm test:runstill passes (184 tests)🤖 Generated with Claude Code