- Thumbs down now increases the similarity threshold by +0.15 for the
notes involved, making it harder for irrelevant connections to reappear
- Thumbs up slightly lowers the threshold by -0.05, boosting similar
future connections
- Remove duplicate close button in ComparisonModal (kept only the
native Dialog close button)
- Normalize all embeddings to same model/dimension (2560) to fix
random similarity scores caused by mixed embedding models
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Fix critical bug: used prisma.systemConfig.findFirst() which returned
a single {key,value} record instead of the full config object needed
by getAIProvider(). Replaced with getSystemConfig() that returns all
config as a proper Record<string,string>.
- Add ensureEmbeddings() to auto-generate embeddings for notes that
lack them before searching for connections. This fixes the case where
notes created without an AI provider configured never got embeddings,
making Memory Echo silently return zero connections.
- Restore demo mode polling (15s interval after dismiss) in the
notification component.
- Integrate ComparisonModal and FusionModal in the notification card
with merge button for direct note fusion from the notification.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Ajout de la table de relation 1-1 NoteEmbedding pour alléger Model Note
- Refactor complet des actions IA sémantique et Memory Echo pour utiliser la jointure
- Migration propre des 85 embeddings locaux existants
- Ajout PRAGMA journal_mode=WAL pour la concurrence au sein de lib/prisma
- Ajout npm run db:switch pour configuration auto SQLite / PostgreSQL
- Fix du compilateur Turbopack et Next-PWA
- RTL: force dir=rtl on LabelFilter, NotesViewToggle, LabelManagementDialog
- i18n: add missing keys (notifications, privacy, edit/preview, AI translate/undo)
- Settings pages: convert to Server Components (general, appearance) + loading skeleton
- AI menu: add Translate option (10 languages) + Undo AI button in toolbar
- Fix: saveInline uses REST API instead of Server Action → eliminates all implicit refreshes in list mode
- Fix: NotesTabsView notes sync effect preserves selected note on content changes
- Fix: auto-tag suggestions now filter already-assigned labels
- Fix: color change in card view uses local state (no refresh)
- Fix: nav links use <Link> for prefetching (Settings, Admin)
- Fix: suppress duplicate label suggestions already on note
- Route: add /api/ai/translate endpoint
- Add reminders page with navigation support
- Upgrade BMad builder module to skills-based architecture
- Refactor MCP server: extract tools and auth into separate modules
- Add connections cache, custom AI provider support
- Update prisma schema and generated client
- Various UI/UX improvements and i18n updates
- Add service worker for PWA support
Made-with: Cursor
- Fix LanguageProvider: add RTL support (ar/fa), translation caching,
prevent blank flash during load, browser language detection
- Fix detect-user-language: extend whitelist from 5 to all 15 languages
- Remove hardcoded initialLanguage="fr" from auth layout
- Complete fr.json translation (all sections translated from English)
- Add missing admin.ai keys to all 13 non-English locales
- Translate ai.autoLabels, ai.batchOrganization, memoryEcho sections
for all locales
- Remove duplicate top-level autoLabels/batchOrganization from en.json
- Fix notebook creation: replace window.location.reload() with
createNotebookOptimistic + router.refresh()
- Fix notebook name truncation in sidebar with min-w-0
- Remove redundant router.refresh() after note creation in page.tsx
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Unified localStorage key to 'theme-preference' across all components
- Fixed header.tsx using wrong localStorage key ('theme' instead of 'theme-preference')
- Added localStorage hybrid persistence for instant theme changes
- Removed router.refresh() which was causing stale data revert
- Replaced Blue theme with Sepia
- Consolidated auth() calls to prevent race conditions
- Updated UserSettingsData types to include all themes
CRITICAL FIX: Auto-labels, notebook summaries, and other AI features
were not working because 8 services were calling getAIProvider() WITHOUT
passing the config parameter.
This caused them to use the default 'ollama' provider instead of
the configured OpenAI provider from the database.
ROOT CAUSE ANALYSIS:
Working features (titles):
- title-suggestions/route.ts: getAIProvider(config) ✓
Broken features (auto-labels, summaries):
- contextual-auto-tag.service.ts: getAIProvider() ✗ (2x)
- notebook-summary.service.ts: getAIProvider() ✗
- auto-label-creation.service.ts: getAIProvider() ✗
- notebook-suggestion.service.ts: getAIProvider() ✗
- batch-organization.service.ts: getAIProvider() ✗
- embedding.service.ts: getAIProvider() ✗ (2x)
FIXED: All 8 services now properly call:
const config = await getSystemConfig()
const provider = getAIProvider(config)
This ensures ALL AI features use the provider configured in the admin
interface (OpenAI) instead of defaulting to Ollama.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
ROOT CAUSE: The factory was defaulting to 'ollama' when no provider
was configured, and docker-compose.yml was always setting OLLAMA_BASE_URL
even when using OpenAI. This caused the app to try connecting to Ollama
even when OpenAI was configured in the admin.
CRITICAL CHANGES:
1. lib/ai/factory.ts - Removed 'ollama' default fallback
- getTagsProvider() now throws error if AI_PROVIDER_TAGS not set
- getEmbeddingsProvider() now throws error if AI_PROVIDER_EMBEDDING not set
- Forces explicit configuration instead of silent fallback to Ollama
2. docker-compose.yml - Removed default OLLAMA_BASE_URL
- Changed: OLLAMA_BASE_URL=${OLLAMA_BASE_URL:-http://ollama:11434}
- To: OLLAMA_BASE_URL=${OLLAMA_BASE_URL}
- Only set if explicitly defined in .env.docker
3. Application name: Mento → Memento (correct spelling)
- Updated in: sidebar, README, deploy.sh, DOCKER_DEPLOYMENT.md
4. app/api/ai/config/route.ts - Return 'not set' instead of 'ollama'
- Makes it clear when provider is not configured
IMPACT: The app will now properly use OpenAI when configured in the
admin interface, instead of silently falling back to Ollama.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
The paragraph-refactor service was using OLLAMA_BASE_URL directly from
environment variables instead of using the configured AI provider from
the database. This caused "OLLAMA error" even when OpenAI was configured
in the admin interface.
Changes:
- paragraph-refactor.service.ts: Now uses getSystemConfig() and
getTagsProvider() from factory instead of direct Ollama calls
- factory.ts: Added proper error messages when API keys are missing
- .env.docker.example: Updated with new provider configuration
variables (AI_PROVIDER_TAGS, AI_PROVIDER_EMBEDDING)
This fixes the issue where AI reformulation features (Clarify, Shorten,
Improve Style) would fail with OLLAMA errors even when OpenAI was
properly configured in the admin settings.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Critical fix for Docker deployment where AI features were trying to connect
to localhost:11434 instead of using configured provider (Ollama Docker service
or OpenAI).
Problems fixed:
1. Reformulation (clarify/shorten/improve) failing with ECONNREFUSED 127.0.0.1:11434
2. Auto-labels failing with same error
3. Notebook summaries failing
4. Could not switch from Ollama to OpenAI in admin
Root cause:
- Code had hardcoded fallback to 'http://localhost:11434' in multiple places
- .env.docker file not created on server (gitignore'd)
- No validation that required environment variables were set
Changes:
1. lib/ai/factory.ts:
- Remove hardcoded 'http://localhost:11434' fallback
- Only use localhost for local development (NODE_ENV !== 'production')
- Throw error if OLLAMA_BASE_URL not set in production
2. lib/ai/providers/ollama.ts:
- Remove default parameter 'http://localhost:11434' from constructor
- Require baseUrl to be explicitly passed
- Throw error if baseUrl is missing
3. lib/ai/services/paragraph-refactor.service.ts:
- Remove 'http://localhost:11434' fallback (2 locations)
- Require OLLAMA_BASE_URL to be set
- Throw clear error if not configured
4. app/(main)/admin/settings/admin-settings-form.tsx:
- Add debug info showing current provider state
- Display database config value for transparency
- Help troubleshoot provider selection issues
5. DOCKER-SETUP.md:
- Complete guide for Docker configuration
- Instructions for .env.docker setup
- Examples for Ollama Docker, OpenAI, and external Ollama
- Troubleshooting common issues
Usage:
On server, create .env.docker with proper provider configuration:
- Ollama in Docker: OLLAMA_BASE_URL="http://ollama:11434"
- OpenAI: OPENAI_API_KEY="sk-..."
- External Ollama: OLLAMA_BASE_URL="http://SERVER_IP:11434"
Then in admin interface, users can independently configure:
- Tags Provider (for auto-labels, AI features)
- Embeddings Provider (for semantic search)
Result:
✓ Clear errors if Ollama not configured
✓ Can switch to OpenAI freely in admin
✓ No more hardcoded localhost in production
✓ Proper separation between local dev and Docker production
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Fixes issue where interface always defaulted to English for new users.
Now automatically detects and applies browser language on first visit.
Changes:
- lib/i18n/LanguageProvider.tsx:
- Add browser language detection using navigator.language
- Check if detected language is in supported languages list
- Auto-save detected language to localStorage
- Update HTML lang attribute for proper font rendering
Behavior:
- First visit: Detects browser language (e.g., fr-FR → fr)
- Returning visits: Uses saved language from localStorage
- Fallback: Defaults to English if language not supported
Result:
✓ French users see French interface automatically
✓ All supported languages work (en, fr, es, de, fa, it, pt, ru, zh, ja, ko, ar, hi, nl, pl)
✓ Better UX for international users
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Add AI Provider Testing page (/admin/ai-test) with Tags and Embeddings tests
- Add new AI providers: CustomOpenAI, DeepSeek, OpenRouter
- Add API routes for AI config, models listing, and testing endpoints
- Add UX Design Specification document for Phase 1 MVP AI
- Add PRD Phase 1 MVP AI planning document
- Update admin settings and sidebar navigation
- Fix AI factory for multi-provider support
## Bug Fixes
### Note Card Actions
- Fix broken size change functionality (missing state declaration)
- Implement React 19 useOptimistic for instant UI feedback
- Add startTransition for non-blocking updates
- Ensure smooth animations without page refresh
- All note actions now work: pin, archive, color, size, checklist
### Markdown LaTeX Rendering
- Add remark-math and rehype-katex plugins
- Support inline equations with dollar sign syntax
- Support block equations with double dollar sign syntax
- Import KaTeX CSS for proper styling
- Equations now render correctly instead of showing raw LaTeX
## Technical Details
- Replace undefined currentNote references with optimistic state
- Add optimistic updates before server actions for instant feedback
- Use router.refresh() in transitions for smart cache invalidation
- Install remark-math, rehype-katex, and katex packages
## Testing
- Build passes successfully with no TypeScript errors
- Dev server hot-reloads changes correctly
- Added multi-provider AI infrastructure (OpenAI/Ollama)
- Implemented real-time tag suggestions with debounced analysis
- Created AI diagnostics and database maintenance tools in Settings
- Added automated garbage collection for orphan labels
- Refined UX with deterministic color hashing and interactive ghost tags
- Add debounced state updates for title and content (500ms delay)
- Immediate UI updates with delayed history saving
- Prevent one-letter-per-undo issue
- Add cleanup for debounce timers on unmount
