Commit graph

7 commits

Author SHA1 Message Date
michael
2c6f3d0686 Switch LlamaParse to llama-cloud SDK with agentic_plus tier
Replace deprecated llama-cloud-services package with llama-cloud>=1.0 (API v2).
Use AsyncLlamaCloud client with tier="agentic_plus" for maximum parsing accuracy
on complex layouts, tables, and visual structure.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-12 15:29:23 -06:00
michael
9e2473c3e9 Add Knowledge Base management system for AI agent specs
Full-stack implementation enabling UI-driven management of the 5 AI agent knowledge bases
(Legal, Brand Barclays, Brand Barclaycard, Channel Best Practices, Channel Tech Specs).

Backend:
- 4 new DB models: KnowledgeBase, SourceDocument, SpecVersion, ProcessingJob
- Migration 006: creates tables, seeds 5 KB rows, imports existing prompts/*.md as v1 specs
- KnowledgeBaseRepository with full CRUD for all 4 tables
- LlamaParseService for document parsing, KnowledgeBaseService for pipeline orchestration
- ReferenceDocsService updated with DB-backed spec loading + cache invalidation
- 11 REST endpoints under /api/knowledge-base (list, detail, upload, delete, process, job status, versions, diff, activate)
- StorageService extended with KB document storage

Frontend:
- TypeScript types for all KB entities (KnowledgeBaseListItem, SourceDocument, ProcessingJob, SpecVersion, DiffResult)
- ApiService methods for all KB endpoints including multipart file upload
- KnowledgeBase component with 3-level UI: agent grid, detail view (documents + versions tabs), diff viewer
- Drag-and-drop file upload, processing progress bar with 3s polling, version comparison
- KnowledgeBaseIcon + Sidebar nav item with adminOnly filtering

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-02-12 15:00:36 -06:00
michael
c1030ee292 Add PDF rasterization support for reliable preview and analysis
PDFs are now converted to PNG images at 200 DPI before being sent to
Gemini for analysis. This fixes the unreliable iframe-based PDF preview
and ensures all pages are properly analyzed.

- Add PyMuPDF dependency for PDF rasterization
- Create pdf_service.py with rasterize() and get_page_count()
- Update agent interfaces to accept list of images for multi-page support
- Add analyze_with_images() to Gemini service for multi-image analysis
- Return rasterized PDF pages via WebSocket for frontend display
- Add page navigation UI for multi-page PDFs in preview components

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-24 09:36:56 -06:00
Michael Clervi
dc17cd087c permissions changes 2025-12-18 16:51:27 +00:00
michael
99af0164e6 Add PostgreSQL database support with Alembic migrations
Backend:
- Add PostgreSQL service to docker-compose with health checks
- Add SQLAlchemy async models for all entities (Agency, User, Campaign,
  Proof, ProofVersion, FlaggedItem, ResolvedItem, ErrorItem)
- Add Alembic migration framework with initial schema migration
- Add repository layer for CRUD operations
- Add REST API endpoints for campaigns, proofs, and audit items
- Add file storage service for proof uploads
- Update WebSocket handler to optionally persist analysis results

Frontend:
- Add apiService.ts for REST API communication
- Update geminiService.ts to support database persistence options

Deployment:
- Update deploy.sh to handle database migrations (6-step process)
- Update Dockerfile to include alembic configuration
- Add PostgreSQL environment variables to .env templates

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-16 12:27:18 -06:00
michael
321a9ca820 Implement Microsoft MSAL SSO with PKCE flow
Frontend:
- Add @azure/msal-browser and @azure/msal-react packages
- Create authConfig.ts with MSAL configuration for PKCE flow
- Create authService.ts for token acquisition and user info
- Wrap App with MsalProvider in index.tsx
- Replace dummy login with real MSAL loginPopup() in Login.tsx
- Update App.tsx to use useIsAuthenticated/useMsal hooks
- Update Profile.tsx to display real user data from claims
- Update geminiService.ts to include access_token in WebSocket messages
- Update WIPReviewer.tsx to pass msalInstance for auth

Backend:
- Add python-jose and httpx dependencies for JWT verification
- Create auth_service.py with Azure AD JWKS fetching and token verification
- Create auth.py FastAPI dependency for protected REST endpoints
- Update main.py to verify tokens on WebSocket and protect /info endpoint
- Add AZURE_TENANT_ID, AZURE_CLIENT_ID, DISABLE_AUTH to config

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-16 08:43:30 -06:00
michael
e97d0e935c initial commit 2025-12-12 09:03:17 -06:00