ReactMarkdown creates "loose lists" wrapping <li> content in <p> tags
regardless of markdown formatting. Fix by unwrapping <p> children
inside the custom li component. Also skip rendering empty paragraphs.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
messages.length was stale in sendMessage callback because messages
was not in the dependency array.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- cleanMarkdown: collapse ALL double newlines to single, add back
paragraph breaks only before bold section headers. This eliminates
loose lists entirely — no more gaps between list items.
- Auto-rename conversation from "New Conversation" to first message
text (truncated to 50 chars) after sending the first message.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Nuclear fix: use !important on all list-related margins/padding
in components.css to guarantee no other CSS rules can add gaps
between list items.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Add .message-content li p { margin: 0 } to prevent paragraph margins
inside list items (ReactMarkdown wraps li content in p tags)
- Add .message-content li ul/ol { margin: 1px } for nested lists
- Reduce nested list margins from 8px to 1px in theme.css
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Remove all double blank lines between sections, bold headers and
lists, and between list items to eliminate visual gaps in bot responses.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Remove contact blocking rule (contacts are OK to show)
- Hide "Who to reach out to" doc from Sources citation only
- Make responses concise: no filler, direct answers, tight lists
- Require clickable markdown links [Text](URL) instead of raw URLs
- Reduce verbose response format to compact structured sections
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
- Always try clipboard API first, fall through to execCommand fallback
on failure (fixes iframe/SharePoint where clipboard API throws)
- Reduce line-height from 1.6 to 1.3 in components.css to fix large
gaps between lines in bot responses
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Replace incorrect dialect.get_dbapi_connection().now() call with
datetime.now(timezone.utc) to fix AttributeError on Azure AD login.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Enhance system instructions for detailed onboarding-style responses with comprehensive navigation, links, and step-by-step guidance
- Increase file_search max_num_results from 20 to 30 for more comprehensive context
- Improve search result filtering and citation checking for better response quality
- Add ultra-compact message styling with minimal line spacing (line-height 1.1-1.2, margins 1-4px)
- Add complete message formatting styles for headings, lists, code blocks, links, and blockquotes
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
When OpenAI's stored response expires, the API returns a
previous_response_not_found error. Handle this gracefully by
catching the error and retrying without the stale ID.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
The backend uses the token to call Microsoft Graph API for user info,
which requires an access token, not an ID token.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Added note about using relative URLs for production to avoid mixed
content errors when served over HTTPS.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Login component now automatically shows Azure AD SSO when configured
(via REACT_APP_AZURE_CLIENT_ID and REACT_APP_AZURE_TENANT_ID), or falls
back to simple login for testing when not configured.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Added homepage field in package.json for static asset paths
- Added basename to BrowserRouter for correct routing
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
react-scripts@5.0.1 has peer dependency on TypeScript 4.x but project
uses TypeScript 5.x. The --legacy-peer-deps flag ignores this conflict.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
If migrations fail due to tables already existing (common when deploying
to a database that was set up manually), the script now stamps the
database with the current head revision instead of failing.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Azure AD fields are now optional with None defaults, allowing the app
to start without Azure AD configured (falls back to simple auth).
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Existing Redis instance was using port 6379, causing Docker container
startup failures. Changed host-exposed port to 6380 while keeping
internal container port at 6379.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Problem:
- Getting Internal Server Error (500) when fetching messages
- Pydantic validation error: metadata field expected dict but received SQLAlchemy MetaData object
- Error: "Input should be a valid dictionary [type=dict_type, input_value=MetaData()]"
Solution:
- Added field_validator for metadata field in MessageResponse schema
- Validator converts any non-dict metadata to empty dict before validation
- Used 'before' mode to process data before Pydantic validation
- Added field alias 'meta_data' to match database column name
Changes:
- backend/app/schemas/conversation.py:
* Added field_validator import from pydantic
* Added validate_metadata validator to MessageResponse
* Validator handles None, dict, and non-dict (SQLAlchemy objects)
* Returns empty dict for None or non-dict values
* Preserves actual dict values as-is
Testing:
- User can now successfully retrieve message history
- API returns 200 OK with proper JSON response
- All messages display with metadata as empty dict
- No more validation errors in backend logs
Security verification:
- User can only see their own conversations ✓
- User cannot access admin's conversations (403 Forbidden) ✓
- Message history properly isolated per user ✓
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Problem:
- MSAL was throwing runtime errors when Azure credentials were incomplete
- Script error in browser due to invalid MSAL configuration
- PublicClientApplication constructor failing with empty/undefined values
Solution:
- Added tenant ID validation in addition to client ID check
- Wrapped MSAL initialization in try-catch to handle configuration errors gracefully
- Log warning instead of crashing when MSAL cannot be initialized
- Allow application to continue with simple login when Azure is not configured
Changes:
- Check both REACT_APP_AZURE_CLIENT_ID and REACT_APP_AZURE_TENANT_ID
- Use try-catch when creating PublicClientApplication instance
- Set msalInstance to null on initialization failure
- Console warning for debugging when Azure AD is not properly configured
This prevents runtime errors and allows the application to work in test mode
without requiring valid Azure AD configuration.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Problem:
- MSAL library was causing crypto errors in browser
- Black screen on load due to MSAL initialization failure
- Error: crypto module not available in browser environment
Solution:
- Made MSAL initialization conditional based on Azure AD configuration
- Only initialize MSAL if REACT_APP_AZURE_CLIENT_ID is properly configured
- Allow simple login to work without MSAL for testing purposes
- Gracefully handle both MSAL and simple login modes
Changes:
- frontend/src/context/AuthContext.tsx:
* Check if Azure AD is configured before initializing MSAL
* Set msalInstance to null when Azure is not configured
* Updated all MSAL calls to check for null before use
* Simple login works independently of MSAL
- frontend/package.json:
* Added crypto polyfills as devDependencies (for future use)
* Packages: crypto-browserify, buffer, stream-browserify, etc.
- frontend/src/styles/theme.css:
* Added login form styles (login-container, login-card, form-group, etc.)
Benefits:
- No more crypto errors in browser
- Simple login works without Azure AD configuration
- Easy testing with test accounts (admin/user)
- Production Azure AD login still supported when configured
- Graceful fallback for environments without Azure setup
Testing:
- Frontend compiles successfully without crypto errors
- All services running: backend, frontend, postgres, redis
- Simple login working with test accounts
- No black screen on load
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Changes:
- Uncommented frontend service in docker-compose.yml
- Updated README.md with complete setup instructions for both backend and frontend
- Added DEPLOYMENT.md with comprehensive production deployment guide
Docker Compose:
- Frontend now included in docker-compose up
- All services (postgres, redis, backend, frontend) start together
- Frontend runs on port 3000 with hot reload in development mode
README Updates:
- Added frontend .env setup instructions
- Listed all required environment variables for both services
- Updated "Access the application" section with frontend URL
- Clarified that database tables are created automatically on first run
DEPLOYMENT.md (new):
- Complete production deployment guide
- Server setup with Docker installation
- Production environment configuration
- Nginx reverse proxy setup with SSL/TLS
- Let's Encrypt SSL certificate instructions
- Database backup and restore procedures
- Monitoring and logging setup
- Security checklist
- Performance optimization tips
- Scaling strategies for high-traffic scenarios
- Troubleshooting guide
Now users can:
1. Run `docker-compose up --build` to start all services
2. Access frontend at http://localhost:3000
3. Access backend API at http://localhost:8000
4. Follow DEPLOYMENT.md for production deployment
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Features:
- New UserDetailsView component with expandable conversations
- Each conversation shows all messages with token usage and cost
- User information section (email, role, status, last login)
- Token usage statistics grid (8 stat cards)
- Message content truncation for long messages (500 chars)
- Role-based styling (user: blue, assistant: gold)
Backend:
- New GET /admin/users/{user_id}/details endpoint
- Complex SQL queries with joins for user stats and conversations
- Pydantic schemas: UserDetails, ConversationDetail, MessageDetail
- Per-message and per-conversation token tracking
Frontend:
- React Router integration for /admin/users/:userId route
- Navigation from Usage page "View" button to user details
- Back button to return to admin panel
- Proper error handling and loading states
- Responsive CSS styling with hover effects
Changes:
- backend/app/api/v1/endpoints/admin.py: Added getUserDetails endpoint
- frontend/src/components/UserDetailsView.tsx: New component
- frontend/src/App.tsx: Added route for user details page
- frontend/src/components/TokenUsageDashboard.tsx: Added navigation handler
- frontend/src/services/api.ts: Added adminAPI.getUserDetails method
- frontend/src/styles/admin.css: Added comprehensive styling for user details
- frontend/package.json: Added react-router-dom dependency
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Backend changes:
- Add admin analytics endpoints for daily usage per user
- Add GET /tokens/daily-users endpoint with date/user breakdown
- Update OpenAI SDK from 1.58.1 to 2.6.1
- Switch from Assistants API to Responses API with file_search tool
- Implement strict RAG-only system instructions
- Add citation validation to prevent hallucinations
- Add get_daily_usage_by_user repository method
- Add DailyUserUsage schema for admin analytics
Frontend changes:
- Implement comprehensive admin usage dashboard
- Add overall system statistics (users, conversations, messages, tokens, cost)
- Add daily usage table with per-user breakdown
- Add chat state clearing on logout and user change for isolation
- Center welcome message and input field in chat interface
- Add admin-specific styling for usage analytics tables
- Fix useCallback dependencies to prevent infinite loops
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Major changes:
- Switch from Chat Completions API to Assistants API
- Integrate file_search tool with Vector Store (vs_QkOKiQCqzCHS4iFT5lP9qUxc)
- Add strict system instructions to reject off-topic questions
- Create assistant with file_search tool on first use
- Use threads for multi-turn conversations
- Extract file citations from responses
- Validate responses are RAG-only
Bot now:
- ONLY answers questions from Vector Store documents
- Rejects jokes, weather, general knowledge questions
- Tells users what topics it can help with
- Cites source documents when available
- Maintains conversation context via threads
- Update openai package to 1.58.1 (from 1.10.0)
- Replace Responses API (doesn't exist) with Chat Completions API
- Simplify OpenAI service to use standard chat endpoint
- Remove file_search tool references (not available in base API)
- Keep system instructions for professional responses
- Update cached tokens detection for new API format
- Remove unused imports and parameters
The Responses API was not a real OpenAI endpoint. Using standard
Chat Completions API which is the correct way to interact with
OpenAI models like gpt-5-nano-2025-08-07.
- Update token pricing with actual gpt-5-nano-2025-08-07 prices:
* Input: $0.05 per 1M = $0.00005 per 1K
* Cached: $0.005 per 1M = $0.000005 per 1K
* Output: $0.40 per 1M = $0.0004 per 1K
- Add cached_tokens support in OpenAI service
- Update cost calculation to use cached token pricing
- Add cached_tokens column to token_usage table (migration)
- Fix chat interface keyboard handling:
* Send message on Enter key
* New line on Shift+Enter
* Change onKeyPress to onKeyDown for better support
- Add textarea auto-resize with maxHeight limit
- Improve responsive styles for mobile devices
- Add iOS-specific fixes (prevent zoom on input focus)
Changes:
1. Hide "📊 Usage" button from regular users - only admins can see statistics
2. Updated .env.example with detailed pricing documentation
3. Clarified that OpenAI API does NOT return costs, only token counts
4. Cost is calculated locally: (tokens / 1000) × price_per_1k
Cost Calculation:
- OpenAI API returns only usage.input_tokens and usage.output_tokens
- We calculate cost based on PROMPT_TOKEN_COST and COMPLETION_TOKEN_COST from .env
- Current values are placeholders - need to update with real prices from OpenAI pricing page
- Formula: cost = (prompt_tokens / 1000) × PROMPT_TOKEN_COST + (completion_tokens / 1000) × COMPLETION_TOKEN_COST
Admin-only features:
- 📊 Usage (token statistics)
- 👨💼 Admin (user management & analytics)
Regular users only see:
- 💬 Chat
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Fixed email validation and token hashing:
- Changed test user emails from @test.local to @example.com (valid domain)
- Replaced passlib bcrypt for JWT token hashing with SHA-256 (no length limit)
- Improved error handling in SimpleLogin component for validation errors
- Deleted old test users and recreated with valid emails
Credentials:
- Admin: admin@example.com / admin
- User: user@example.com / user
Note: bcrypt still used for password hashing (in auth_service.py),
but SHA-256 for JWT token hashing to avoid 72-byte limit.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Implemented simple authentication for testing and admin panel for user management:
Backend:
- Add simple email/password login for test users (admin@test.local, user@test.local)
- Implement RBAC (Role-Based Access Control) with Permission enum
- Create admin endpoints for user management and system analytics
- Add bcrypt password hashing for test users
- Create script to generate test users in database
Frontend:
- Add SimpleLogin component for test authentication
- Create AdminPanel with user management and system analytics
- Add role-based navigation (Admin tab visible only for admins)
- Update AuthContext to support both MSAL and simple login
- Add API methods for admin operations
Features:
- Admins can view all users, manage roles, activate/deactivate accounts
- Admins can view system-wide analytics (users, conversations, tokens, costs)
- Regular users only see their own chats and usage
- Role badges in UI show user role (user/admin/superadmin)
Note: Simple authentication is for testing only. Production uses Azure AD MSAL.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
All phases are now complete:
- Phase 1: Foundation ✅
- Phase 2: Core Features ✅
- Phase 3: Full UI ✅
Documentation updated to reflect completion status.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Alembic Migration:
- 001_initial_migration.py - Create all database tables
- Users, Sessions, Conversations, Messages, TokenUsage, UserMemory
- Proper indexes and foreign keys with cascade deletes
- Ready for production deployment
ChatList Sidebar:
- List all conversations with last message date
- Click to select and load conversation
- New Chat button at top
- Inline title editing (click ✏️ Rename)
- Archive conversations (hidden from list)
- Delete conversations with confirmation
- Dropdown menu (⋮) for actions
- Active conversation highlighting
- Empty state with helpful message
TokenUsageDashboard:
- Total tokens and cost display
- 7/30/90 days period selector
- Bar chart visualization for last 7 days
- Detailed daily breakdown table
- Average tokens per day calculation
- Hover tooltips on chart bars
- Responsive grid layout
App Layout:
- Sidebar toggle button (☰)
- Navigation tabs: 💬 Chat | 📊 Usage
- Collapsible sidebar (mobile friendly)
- User info and logout in header
- Full-height layout with proper overflow
- Persistent sidebar state
Layout Styles (layout.css):
- Complete app structure (header, sidebar, main content)
- Responsive sidebar (full-screen on mobile)
- Chat list item styles with hover effects
- Dropdown menu positioning
- Token dashboard cards and charts
- Chart bar animations
- Mobile-optimized breakpoints
UI Features:
- Sidebar can be toggled on/off
- Switch between Chat and Usage views
- Conversations load on app start
- Active conversation tracked in sidebar
- Inline editing with ✓/✕ buttons
- Confirmation dialog for deletions
- Loading states for all operations
- Error handling with user feedback
Theme Updates:
- Chat container now full-height
- Removed max-width restriction
- Better integration with sidebar layout
All functionality now complete:
✅ MSAL authentication
✅ Conversation management (CRUD)
✅ Message sending with AI responses
✅ Sidebar with conversation list
✅ Token usage analytics dashboard
✅ Navigation between views
✅ Responsive design
✅ Full RAG enforcement
✅ Citation validation
✅ Multi-turn conversations
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
React Components:
- LoginButton: MSAL login trigger with loading state
- ChatInterface: Main chat UI with message list and input
- App: Complete app with authentication flow and routing
Features:
- Full authentication flow (login → loading → chat)
- Message display with markdown support
- Real-time typing indicator during AI response
- Auto-scroll to latest message
- User/assistant message distinction
- Warning display for unverified responses
- Keyboard shortcuts (Enter to send, Shift+Enter for newline)
- Loading states for all async operations
- User info display with logout button
Styling (components.css):
- Login screen with centered card
- Loading spinner animation
- Message bubbles with avatars
- Typing indicator animation
- User header with logout button
- Responsive design for mobile
- Warning banners for unverified content
- Markdown styling (code blocks, lists, etc.)
App Structure:
- AuthProvider wraps entire app
- ChatProvider for chat state
- AppContent handles auth routing
- Auto-load conversations on login
- Context-based state management
UX Enhancements:
- Smooth animations (slideIn, pulse, bounce)
- Disabled states for buttons during loading
- Error handling with user-friendly messages
- Session persistence across refreshes
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
MSAL Configuration:
- Azure AD authentication setup with MSAL.js
- Session storage for security
- Microsoft Graph API scopes (User.Read, openid, profile, email)
API Service (axios):
- Configured axios client with interceptors
- Automatic Bearer token injection
- Token refresh on 401 errors
- Complete API methods for auth, conversations, messages, tokens
Auth Context:
- AuthProvider with MSAL integration
- Login/logout functionality with popup flow
- Backend JWT session management
- Automatic session verification on mount
- User state management
Chat Context:
- ChatProvider for conversation and message state
- CRUD operations for conversations
- Message sending with AI response handling
- Real-time state updates
- Error handling and loading states
Features:
- Automatic token refresh
- Session persistence in localStorage
- Error recovery with automatic logout
- Type-safe API calls
- Reactive state management
Context Hooks:
- useAuth() - Access authentication state
- useChat() - Access chat functionality
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Conversation Endpoints (/api/v1/conversations):
- POST / - Create new conversation
- GET / - List user's conversations with pagination
- GET /{id} - Get conversation details
- PUT /{id} - Update conversation title
- POST /{id}/archive - Archive conversation
- DELETE /{id} - Delete conversation with cascade
Message Endpoints (/api/v1/conversations/{id}/messages):
- GET / - Get messages for conversation with pagination
- POST / - Send message and get AI response
Token Usage Endpoints (/api/v1/tokens):
- GET /usage - Get token usage summary with daily breakdown
Schemas:
- ConversationCreate/Update/Response
- ConversationListResponse for listing
- MessageCreate/Response
- SendMessageResponse with usage stats
- TokenUsageSummary with analytics
Features:
- Full permission checks (user ownership verification)
- Pagination support for all list endpoints
- Detailed error handling with appropriate HTTP codes
- Usage statistics tracking per message
- Cost calculation and reporting
- File search results in message metadata
Security:
- All endpoints require authentication
- User can only access their own conversations
- Proper 403/404 error handling
- Request validation with Pydantic
Router Updates:
- Connected all new endpoints to /api/v1
- Organized by resource (auth, conversations, messages, tokens)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Authentication Core:
- Security utilities: JWT token creation, validation, hashing
- AuthService: Azure AD token validation via Microsoft Graph API
- User session management with access/refresh tokens
- Token expiration handling (1 hour access, 7 days refresh)
API Endpoints:
- POST /api/v1/auth/login - Login with Azure AD MSAL token
- POST /api/v1/auth/refresh - Refresh access token
- POST /api/v1/auth/logout - Logout and invalidate session
- GET /api/v1/auth/me - Get current user info
- GET /api/v1/auth/health - Auth service health check
Middleware:
- get_current_user: Extract and validate user from Bearer token
- get_current_active_user: Ensure user is active
- get_current_admin_user: Require admin role
- get_optional_user: Optional authentication
Security Features:
- JWT with HS256 signing
- Token hashing with bcrypt for storage
- Session validation with expiration checks
- Microsoft Graph API integration for Azure AD validation
- IP address and user agent tracking
- Active session management
Schemas:
- LoginRequest/Response with tokens and user info
- RefreshTokenRequest/Response
- UserInfo for current user details
- LogoutResponse
Main App Updates:
- Connected auth router to /api/v1/auth
- All authentication endpoints now accessible
Dependencies Added:
- pyjwt for JWT handling
- httpx for async HTTP requests to Microsoft Graph
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Features:
- OpenAIService class for Responses API integration
- file_search tool integration with Vector Store
- Strict RAG-only enforcement via system instructions
- Citation validation to prevent hallucinations
- Warning logs for responses without proper citations
- Support for multi-turn conversations via previous_response_id
- Async streaming support for real-time responses
- Comprehensive error handling and logging
Test Coverage:
- Service initialization and configuration
- System instructions validation
- Citation detection (valid, missing, no-info responses)
- Search results formatting
- RAG usage validation with hallucination detection
- Response generation with mocked API calls
- Multi-turn conversation support
- Error handling
- Integration test stubs (skipped, require API key)
Key RAG Safety Features:
- Low temperature (0.3) for factual responses
- Citation keyword detection
- Automatic disclaimer for uncited responses
- Separate handling of valid "no info" responses
- Warning logs for potential hallucinations
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
