Commit Graph

4 Commits

Author SHA1 Message Date
d81430e1aa test: extend test coverage for backend and frontend
Backend:
- Add fetcher_test.go (HTML stripping, URL fetching utilities)
- Add model_registry_test.go (parsing, size ranges, model matching)
- Add database_test.go (CRUD operations, migrations)
- Add tests for geolocation, search, tools, version handlers

Frontend unit tests (469 total):
- OllamaClient: 22 tests for API methods with mocked fetch
- Memory/RAG: tokenizer, chunker, summarizer, embeddings, vector-store
- Services: prompt-resolution, conversation-summary
- Components: Skeleton, BranchNavigator, ConfirmDialog, ThinkingBlock
- Utils: export, import, file-processor, keyboard
- Tools: builtin math parser (44 tests)

E2E tests (28 total):
- Set up Playwright with Chromium
- App loading, sidebar navigation, settings page
- Chat interface, responsive design, accessibility
- Import dialog, project modal interactions

Config changes:
- Add browser conditions to vitest.config.ts for Svelte 5 components
- Add playwright.config.ts for E2E testing
- Add test:e2e scripts to package.json
- Update .gitignore to exclude test artifacts

Closes #8
2026-01-22 11:05:49 +01:00
6868027a1c feat: add model-specific prompts and custom model creation
Adds two related features for enhanced model customization:

**Model-Specific System Prompts:**
- Assign prompts to models via Settings > Model Prompts
- Capability-based default prompts (vision, tools, thinking, code)
- Auto-select appropriate prompt when switching models in chat
- Per-model prompt mappings stored in IndexedDB

**Custom Ollama Model Creation:**
- Create custom models with embedded system prompts via Models page
- Edit system prompts of existing custom models
- Streaming progress during model creation
- Visual "Custom" badge for models with embedded prompts
- Backend handler for Ollama /api/create endpoint

New files:
- ModelEditorDialog.svelte: Create/edit dialog for custom models
- model-creation.svelte.ts: State management for model operations
- model-prompt-mappings.svelte.ts: Model-to-prompt mapping store
- model-info-service.ts: Fetches and caches model info from Ollama
- modelfile-parser.ts: Parses system prompts from Modelfiles
2026-01-03 21:12:49 +01:00
2241075563 feat: add model browser with pull functionality and file size display
- Add model registry backend that scrapes ollama.com library page
- Extract capabilities (vision, tools, thinking, embedding, cloud) from HTML
- Store models in SQLite with search, filter by type and capabilities
- Add tag sizes fetching from individual model pages
- Create Model Browser UI with search, filters, and pagination
- Implement streaming model pull with progress bar
- Auto-refresh model selector and select new model after pull
- Add cloud capability detection (uses different HTML pattern)
- Update Go version to 1.24 in Dockerfile

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-01 01:02:42 +01:00
de835b7af7 feat: initial commit - Ollama WebUI with tools, sync, and backend
Complete Ollama Web UI implementation featuring:

Frontend (SvelteKit + Svelte 5 + Tailwind CSS + Skeleton UI):
- Chat interface with streaming responses and markdown rendering
- Message tree with branching support (edit creates branches)
- Vision model support with image upload/paste
- Code syntax highlighting with Shiki
- Built-in tools: get_current_time, calculate, fetch_url
- Function model middleware (functiongemma) for tool routing
- IndexedDB storage with Dexie.js
- Context window tracking with token estimation
- Knowledge base with embeddings (RAG support)
- Keyboard shortcuts and responsive design
- Export conversations as Markdown/JSON

Backend (Go + Gin + SQLite):
- RESTful API for conversations and messages
- SQLite persistence with branching message tree
- Sync endpoints for IndexedDB ↔ SQLite synchronization
- URL proxy endpoint for CORS-bypassed web fetching
- Health check endpoint
- Docker support with host network mode

Infrastructure:
- Docker Compose for development and production
- Vite proxy configuration for Ollama and backend APIs
- Hot reload development setup

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-31 08:11:33 +01:00