Use getChatProvider() + provider.getModel() instead of
resolveAiRouteWithTiming which doesn't return a provider function.
Follow the pattern used in chat/insights/route.ts.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The AI router only supports lanes: 'chat', 'tags', 'embedding'.
'suggest-charts' was not a valid lane causing 500 errors.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Add step-by-step console logging in API route
- Show actual error message in dialog
- Add debug info section
- Wrap each section in try-catch to isolate failure point
- Remove conflicting tool approach, use direct JSON
- Add fallback: extract numbers from regex if AI fails
- Add debug section to show what content was analyzed
- Be more lenient: any 2+ numbers = valid chart
- Better error messages
- Add console logging for debugging
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
1. Script warning in layout.tsx
- Use Next.js Script component instead of plain <script>
2. QUOTA_EXCEEDED bug for chart suggestions
- Add 'suggest_charts' to VALID_FEATURES
- Add 'suggest_charts' to TIER_LIMITS for all tiers
- Fix route to use 'suggest_charts' instead of invalid 'ai' feature
This fixes the issue where users with valid credit were getting
QUOTA_EXCEEDED errors because 'ai' was not a valid feature name.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Add quotaExceeded flag to response for better error UX
- Show dedicated quota exceeded state with upgrade button
- Improve AI prompt to better detect data patterns
- Add chart type-specific colors (blue, indigo, emerald, violet, etc.)
- Replace generic primary/10 colors with varied accent colors
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Implement slash command "/suggest-charts" that analyzes note content
and suggests 3 appropriate chart types with visual previews.
Created:
- chart-suggestion.tool.ts: AI tool for data extraction and chart recommendations
- suggest-charts/route.ts: API endpoint for chart suggestions
- chart-suggestion.service.ts: Frontend service layer
- chart-suggestions-dialog.tsx: Modal with 3 chart proposals and thumbnails
- tiptap-chart-extension.tsx: TipTap Node extension for rendering chart blocks
Modified:
- rich-text-editor.tsx: Added slash command, toolbar button, and dialog integration
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Add slides.tool.ts with support for title, bullets, chart, stats, table, cards, timeline, quote, comparison, equation, image, summary slide types
- Chart types: bar, horizontal-bar, line, donut, radar
- Integrate with agent executor and canvas system
- Add multilingual support (en/fr)
- Various UI improvements and bug fixes
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- Add /api/admin/embeddings/dimension (GET column dim, POST test model dim)
- Add /api/admin/embeddings/migrate (alter column, clear, re-index)
- Admin form warns on dimension mismatch after save, offers migrate button
- Remove hardcoded 1536 from validate endpoint and embedding service
- Add validateDimension() utility to EmbeddingService
- Fix health route: import prisma correctly, use router instead of missing registry
- i18n keys for dimension warning (EN/FR)
Google OAuth was implemented locally but never deployed; the login button
only renders when AUTH_GOOGLE_ID and AUTH_GOOGLE_SECRET are set. Also
restores /api/ai/test-* endpoints removed by mistake and wires Google
credentials into deploy workflows.
Co-authored-by: Cursor <cursoragent@cursor.com>
Le job deploy référençait needs:[ci] dans un autre workflow (inefficace
sur Gitea). Déclenchement via workflow_run après CI réussie, empreinte
GIT_COMMIT dans l'image, endpoint /api/build-info et health check sur
127.0.0.1:3000 avec comparaison du SHA attendu.
Co-authored-by: Cursor <cursoragent@cursor.com>
- Sidebar: dynamic brand-accent colors, brainstorm section restyled
- AI chat general: popup panel with expand/collapse, hides when contextual AI open
- AI chat contextual: tabs reordered (Actions first), X close button, height fix
- Settings: all tabs restyled, 6 new color presets (sage, terracotta, iron, etc.)
- Global color cleanup: emerald/orange hardcoded → brand-accent dynamic
- Brainstorm page: orange → brand-accent throughout
- PageEntry animation component added to key pages
- Floating AI button: bg-brand-accent instead of hardcoded black
- i18n: all 15 locales updated with new AI/billing keys
- Billing: freemium quota tracking, BYOK, stripe subscription scaffolding
- Admin: integrated into new design
- AGENTS.md + CLAUDE.md project rules added
- Add brainstorm feature with collaborative canvas, AI idea generation, live cursors, playback, and export
- Add PDF upload/extraction/ingestion pipeline with pgvector document search (RAG)
- Add document Q&A overlay with streaming chat and PDF preview
- Add note attachments UI with status polling, grid layout, and auto-scroll
- Add task extraction AI tool and agent executor improvements
- Fix NoteEmbedding missing updatedAt column, re-index 66 notes with 1536-dim embeddings
- Fix brainstorm 'Create Note' button: add success toast and redirect to created note
- Fix memory echo notification infinite polling
- Fix chat route to always include document_search tool
- Add brainstorm i18n keys across all 14 locales
- Add socket server for real-time brainstorm collaboration
- Add hierarchical notebook selector and organize notebook dialog improvements
- Add sidebar brainstorm section with session management
- Update prisma schema with brainstorm tables, attachments, and document chunks
- Add parentId to Notebook model (tree structure)
- Update sidebar to render parent/child notebooks with expand/collapse
- Add sub-notebook creation from parent notebook
- Remove 'list' from NotesViewMode type everywhere
- Delete 22 unused components, hooks, and UI files
- Wrap revalidatePath in try-catch to prevent save 500
- Update notebook API to support parentId in creation
- Redesign agents page with architectural-grid (8) design system:
rounded-2xl cards, serif headings, motion tabs, dashed templates section
- Replace agent form popup with full-page detail view (SettingsView style)
with dark planning card, section tooltips, and help button
- Hide advanced mode for slide/excalidraw generators
- Add 'describe images' action to contextual AI assistant
- Add copy button to action/resource preview with HTTP fallback
- Add delete history button to agent run log panel
- Increase AI word limit from 2000 to 5000 (reformulate + transform-markdown)
- Increase max steps slider from 25 to 50
- Fix image description error with clear model compatibility message
- Fix doubled execution count display in agent detail view
- Remove dead files: notes-list-view.tsx, notes-view-toggle.tsx
- Remove 'list' view mode from NotesViewMode type
- Add missing i18n keys (back, configuration, options, copy, cleared)
- 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>
