- Les agents créés par run-for-note ont frequency:'one-shot' et sont
filtrés de la page /agents (NOT frequency:'one-shot' dans getAgents)
- Panneau slides : sélecteurs Thème (11 palettes) + Style (sharp/soft/rounded/pill)
- Panneau diagramme : sélecteurs Type (auto/flowchart/mindmap/timeline/
org-chart/architecture/process-map) + Style (sketchy/austere/sketch+)
- Les valeurs sélectionnées sont transmises à l'API et injectées dans le prompt
Co-authored-by: Cursor <cursoragent@cursor.com>
Le problème : la route POST /api/agents/run-for-note bloquait le thread
HTTP pendant toute la durée de génération (2-5 min), provoquant un
spinner infini sans résultat.
Solution :
- POST retourne immédiatement avec { agentId } et lance executeAgent
en arrière-plan (fire-and-forget, sans await)
- GET /api/agents/run-for-note?agentId= retourne le statut de la
dernière agentAction (running | success | failure) + canvasId/noteId
- Le client poll le statut toutes les 3 secondes jusqu'au résultat,
le toast persistant Sonner se met à jour automatiquement
- Cleanup du polling au démontage du composant
Co-authored-by: Cursor <cursoragent@cursor.com>
- Nouveau endpoint POST /api/agents/run-for-note : crée un agent one-shot
(slide-generator ou excalidraw-generator) avec la note courante comme source
et l'exécute immédiatement
- ContextualAIChat : prop noteId + section "Générer depuis cette note" avec
deux boutons gradient (violet=slides, cyan=diagramme), spinner pendant la
génération, bouton de téléchargement .pptx ou lien "Ouvrir dans le Lab"
après succès
- note-editor.tsx : passage de note.id à ContextualAIChat
- i18n fr/en : nouvelles clés ai.generate.*
Co-authored-by: Cursor <cursoragent@cursor.com>
Slide generator (generate_pptx):
- Pivot vers génération PowerPoint natif (pptxgenjs) au lieu de Reveal.js HTML
- 4 nouveaux layouts diagramme : timeline, process, comparison, metrics
- 2 nouveaux layouts image : image-content (texte + image), image-full (plein cadre)
- Redesign visuel de tous les layouts (cover split, section full-bleed, header band)
- Palettes corrigées : bg blanc sur toutes les palettes, contrastes réels
- fit:shrink systématique sur tous les textes pour éviter les débordements
- Extraction automatique des images des notes (Markdown/HTML) et injection dans le prompt IA
- Prompt IA renforcé : impose "style" et "theme" explicitement dans le JSON, impose ≥2 layouts diagramme
- Fix overlap timeline : zones de texte calculées sans collision avec les cercles
- Notification agent mise à jour : bouton download .pptx au lieu d'ouvrir HTML
Excalidraw generator:
- Layout Dagre/ELK pour graphes auto-positionnés
- Styles visuels : coloré, austère, sketch-plus (Virgil font)
- Zones/containers pour architecture-cloud
- Sanitisation du graphe et métriques de qualité de layout
Co-authored-by: Cursor <cursoragent@cursor.com>
- Agent-created notes are now type 'markdown' by default (raw markdown content)
- Switching note type from markdown → richtext auto-converts content to HTML
via /api/ai/convert-markdown endpoint using the existing markdownToHtml utility
- Users can freely switch between markdown and richtext in the note type selector
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add DeepSeek, OpenRouter, Mistral, Z.AI, LM Studio as AI providers
with editable model names via Combobox in admin settings
- Fix OpenRouter broken by normalizeProvider bug in config.ts
- Convert agent-created notes from Markdown to HTML (TipTap rich text)
- Add Notification model + in-app notifications for agent results
- Agent notification click opens the created note directly
- Add note count display on notebook and inbox headers
- Fix checklist toggle in card view (persist state via localCheckItems)
- Add checklist creation option in tabs/list view (dropdown on + button)
- Fix image description ENOENT error with HTTP fallback
- Improve UI contrast across all themes (input, border, checkbox visibility)
- Add font family setting (Inter vs System Default) in Appearance settings
- Fix CSS font-sans variable conflict (removed dead Geist references)
- Update README with new features and 8 providers
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Same fix as reformulate — raise limit from 500 to 2000 and use i18n
error keys instead of hardcoded English messages.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Raise MAX_WORDS from 500 to 2000 for text reformulation
- Error messages now use i18n keys (ai.wordCountMin/Max) instead of
hardcoded English strings
- Client translates server errors using the user's UI language
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
When chatScope is "this note", the AI had access to note_search and note_read
tools which let it pull content from any note. Now these tools are excluded via
a webOnly flag in buildToolsForChat — only web_search/web_scrape remain if
the user toggled web search.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- When chat scope is "this note" (noteContext present), skip RAG/semantic
search entirely. Previously the AI received all user notes as context
even when scoped to a single note, causing irrelevant responses.
- Replace 3 native <select> elements for Ollama models with searchable
Combobox component (tags, embeddings, chat providers).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Add image description service + API route for AI-powered image analysis
- Image title generation returns 3 selectable suggestions via TitleSuggestions component
- Add "Describe images" action in AI assistant (individual + collective)
- Fix pin refresh propagation in card and tabs view
- Fix note creation refresh in tabs mode, pass all notes to tabs view
- Add RTL support (dir="auto") on note content elements
- Pass UI language dynamically to AI endpoints instead of hardcoded 'fr'
- Add 18 missing i18n keys in both en.json and fr.json
- Sparkles button on images for AI title generation (bottom-right, pulse animation)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Chat (AIChat floating widget): conversationId was never captured from
the API response, so every message created a new conversation with no
context. Now creates the conversation upfront before streaming (same
pattern as ChatContainer) so the ID persists across messages.
Note history: was stored globally in UserAISettings, so enabling
history on one note enabled it for ALL notes. Now each Note has its
own historyEnabled boolean field. The "Enable history" action only
affects the specific note. A migration adds the column with default
false.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Commit untracked 20260428150000_add_note_history migration (creates
NoteHistory table + noteHistory column) that was causing 500s in prod
- Exclude static files (.json, .svg, .ico, etc.) from auth middleware
to fix manifest.json 403
- Add console.error to echo API routes for production debug visibility
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Backup before migration (pg_dump/SQLite copy), DB connection wait with
retries, idempotent prisma migrate deploy, old backup cleanup (keep 5),
and server refuses to start if migration fails.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Add noteHistoryMode setting (manual default / auto) with DB migration
- Manual mode: commit button in editor toolbar creates snapshots on demand
- Auto mode: smart snapshots with 20-char diff threshold + 5min cooldown,
structural changes (color, pin, archive, labels) bypass cooldown
- Add delete individual history entries from history modal
- Fix sidebar: Notes nav no longer active on notebook pages
- Fix sidebar icon: replace filled Lightbulb with outlined FileText
- Fix title suggestions: change from amber to sky blue color scheme
- Fix hydration mismatch: add suppressHydrationWarning on locale dates
- Complete i18n: add history, sort, and AI chat translations for all 16 languages
- Translate French AI assistant section (40+ keys) from English to French
- Update README with new features and stack info
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Next.js bakes public/ at build time — dynamically uploaded files were
never served in Docker standalone mode. Store uploads in data/uploads/
and serve via /api/uploads/ with a rewrite for backward compatibility.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Add stop button to all chat interfaces (floating, contextual, full-page)
- Add conversation sliding window (50 messages) to prevent context overflow
- Add chat timeout warning (30s toast)
- Force response language in chat system prompt (mandatory per-locale)
- Add image paste from clipboard in all note editors (card, list, input)
- Fix upload API to infer extension from MIME type for clipboard images
- Add image description support in note AI chat (base64 vision)
- Fix search regex crash on special characters (escape user input)
- Fix search case-insensitivity on PostgreSQL (mode: 'insensitive')
- Add try/catch around semantic search in chat route (prevent blocking)
- Add new chat button to floating AI assistant
- Fix empty thinking bubbles for reasoning models (filter non-text parts)
- Remove duplicate AI assistant toggle from note editor header
- Improve link metadata scraping (timeout, content-type check, relative URLs)
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Log key points in /api/ai/tags and ContextualAutoTagService to trace
where label suggestions fail: notebook lookup, AI raw response,
JSON parsing, filtered results.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Use prisma.$transaction in auto-label-creation.service with tx client
- Fix DELETE /api/labels to properly JSON.parse + disconnect labelRelations
- Fix PUT /api/labels rename to handle JSON labels
- Graceful error handling in /api/ai/tags and /api/ai/auto-labels
- Client-side label-deleted event in home-client, notes-tabs-view, label-management-dialog
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Add visibilitychange listener: refreshes agent data immediately when
user returns to the tab (more reliable than interval-only polling)
- Only show toast for actions created within last 5 minutes to avoid
false positives on page reload
- Hide "Prochaine exécution" line entirely if nextRun is in the past
instead of showing confusing "En attente de déclenchement"
- Add detailed logging to cron endpoint for debugging
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
The getAgents() function was recalculating nextRun to future dates when
it found past values. This prevented the cron scheduler from ever
finding due agents (nextRun <= now was always false since getAgents
had already pushed it to the future).
Also fix toast polling: use null sentinel for agents without initial
actions so first execution is still detected. Limit cron to 3 agents
per cycle and add logging.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Add scheduledTime, scheduledDay, timezone fields to Agent schema
- Create calculateNextRun() helper with timezone-aware scheduling
- Add POST /api/cron/agents endpoint for external scheduler
- Calculate nextRun on agent create, update, and after execution
- Add time/day picker in agent form (daily/weekly/monthly)
- Show "Next run" countdown in agent card
- Add i18n keys for schedule UI (FR + EN)
External scheduler (N8N, Vercel Cron) should call /api/cron/agents
every 5-15 min. Requires `prisma db push` to apply schema changes.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Add trashedAt: null filter to notebook note count queries in /api/notebooks
- Pass isTrashView, onRestore, onPermanentDelete from NoteCard to NoteActions
- Implement handleRestore and handlePermanentDelete in NoteCard
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Fix React bug #33580: remove Suspense boundaries co-located with Link components
- Delete settings/loading.tsx and admin/loading.tsx (root cause of race condition)
- Convert all admin navigation from Next.js Link to anchor tags
- Move admin pages to dedicated (admin) route group
- Add AdminHeader matching main header visual design
- Add AdminSidebar with anchor-based navigation
- Add /api/admin/models route handler (replaces server actions for GET)
- Add /api/debug/client-error for server-side browser error reporting
- Add useNoteRefreshOptional() to fix crash in AdminHeader
- Hide Admin Dashboard menu for non-admin users
- Change app icons from yellow to blue (#3A7CA5) matching brand primary
- Fix admin search bar width to match main header
Made-with: Cursor
Security:
- Add auth + file type/size validation to upload API
- Add admin auth to /api/admin/ endpoints
- Add SSRF protection to scrape action
- Whitelist fields in PUT /api/notes/[id] to prevent mass assignment
- Protect /lab, /agents, /chat, /canvas, /notebooks routes in middleware
AI provider fixes:
- Add deepseek/openrouter to factory ProviderType (was silently falling back to ollama)
- Fix title-suggestion.service.ts to use factory instead of hardcoded OpenAI
- Fix getAIProvider→getChatProvider in memory-echo, notebook-summary, agent-executor
- Fix getAIProvider→getTagsProvider in notebook-suggestion, title-suggestions, transform-markdown
Functional bugs:
- Fix ALLOW_REGISTRATION AND→OR logic
- Fix note-editor.tsx passing stale props to useAutoTagging instead of local state
- Fix stale Note.embedding type (migrated to NoteEmbedding table)
- Remove hardcoded SQLite path from prisma.ts
Frontend:
- Add AbortController to useAutoTagging and useTitleSuggestions hooks
- Add error rollback to optimistic UI in note-inline-editor
- Remove stale closure over notebookId/language in useAutoTagging
Cleanup:
- Rename docker-compose from keepnotes→memento
- Remove unused unstable_cache import from config.ts
- Remove dead useUndoRedo hook
- Fix TagSuggestion type (add isNewLabel, reasoning)
- Remove dead AIConfig/AIProviderType types
- Fix ghost-tags unused isEmpty var and as any cast
- Fix note-editor titleSuggestions typed as any[]
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- app/api/ai/tags/route.ts: getAIProvider → getTagsProvider (was using
embedding model instead of tags model for legacy tag generation)
- lib/ai/services/auto-label-creation.service.ts: same fix
- hooks/use-auto-tagging.ts: remove notebookId gate that blocked all
suggestions in "General Notes" — the API has a legacy path for this
- app/actions/admin-settings.ts: revalidateTag → updateTag (Next.js 16
requires 2 args for revalidateTag)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Remove BMAD framework, IDE configs, dev screenshots, test files,
internal docs, and backup files
- Rename keep-notes/ to memento-note/
- Update all references from keep-notes to memento-note
- Add Apache 2.0 license with Commons Clause (non-commercial restriction)
- Add clean .gitignore and .env.docker.example
