Bản ghi thay đổi trực tiếp

- Emojis: browse all emoji categories with search, select to view code points, copy as emoji/HTML/CSS - Character Map: browse Unicode blocks (Latin, Greek, Cyri...

- GraphingMode now uses the same light calcColors scheme as other calculator modes - Graph line colors updated to work on light background - Calculator tool win...

- Mail icon now shows red unread count badge and dropdown with "Create New Email" / "View My Emails" - Calculator icon now has dropdown with all 6 modes (adds p...

- 13 Next.js API proxy routes under /api/kb/ - KB home page with article tree, search, pinned articles - Article viewer, editor (Plate rich text), new article, ...

- /api/kb/** routes to kamowskb-service - /api/rag/** routes to kamowsrag-service - Updated application.yml and k8s configmap with service URLs

- New RagClient service for calling RAGService semantic search - ChatOrchestrationService injects KB context before AI responds - Configurable via AiOrgSettings...

- Qdrant v1.12.1 deployment + ClusterIP service (ports 6333/6334) - HuggingFace TEI with all-MiniLM-L6-v2 deployment + service (port 8080) - Updated deploy-serv...

- 4 bộ nhớ mới: KbArticStatus, KbReviewStatus, KbMediaType, KbEmbeddingStatus - Dịch vụ type.KNOWLEGE BASE(18) và 6 KB chức năng phải mục (21-26) - 6 thực thể J...

- Styled headings (h1-h4) with bottom borders and proper sizing - Bullet lists (ul) and numbered lists (ol) with proper indentation and spacing - Bold text with...

- Provider Setup is now the first tab, Usage & Overview is last - Renamed "Sales Agent Setup" to "AI Sales Agent Setup" - Updated settings slideout nav and sett...

When the frontend sends a 'models' array of model IDs in the provider update request, models in the array are set active and models not in the array (belonging ...

- Add POST handler to messages API route - Fix message type mismatches between input, context, and messages component - Show user message immediately, display l...

Receives user message, sends to AI provider via ChatOrchestrationService, returns complete response. Supports REST-based chat flow.

- HuggingFaceAdapter handles HF's URL structure **************** - Model discovery via HF API (warm text-generation models) - Registered in ProviderAdapterFacto...

- Input grows up to 11 lines (220px) when window is maximized, 6 lines otherwise - Enter submits message, Alt+Enter inserts newline (was Shift+Enter) - Use Resi...

- Add "Add model manually" form in Provider Setup edit view - Add POST handler to /api/ai/models API route - Users can specify model ID and display name for cus...

- POST /api/ai/models endpoint for manually adding models - DELETE /api/ai/models/{id} endpoint - CUSTOM providers use first discovered model for chat test inst...

Each provider adapter discovers available models from the provider API. Models are automatically saved to the database when Test Connection succeeds.

- Replace placeholder help tips with user-friendly explanations for all AI settings tabs (Usage, Providers, MCP, Security, Sales Agents) - Update PROVIDER_TYP...

Fetches both models and providers. Shows providers as selectable options alongside any configured models, so users can pick a provider even when specific models...

Uses light backgrounds, var(--color-primary) accents, and org theme colors consistent with Calculator, Softphone, and other tool windows.

- Add Sales Agent Setup tab to AI settings (placeholder) - Add Artificial Intelligence section to settings slideout panel - Fix My Account nav links (Relationsh...

AI chat orchestration service on port 4205 with: - WebSocket streaming with session auth via ***/Redis - Chat orchestration with auto-routing, usage tracking, a...