Release v0.6.0 #4

Merged
vikingowl merged 10 commits from dev into main 2026-01-22 12:13:30 +01:00
Owner

Release v0.6.0

🤖 New Feature: Agents (v1)

Agents allow you to create specialized AI personas with custom system prompts and tool sets.

Features:

  • Agent identity: Name and description
  • System prompt: Reference prompts from your Prompt Library
  • Tool filtering: Enable specific tools per agent
  • Preferred model: Optionally set a default model for the agent
  • Per-chat selection: Choose an agent from the chat interface
  • Project assignment: Assign agents to projects (many-to-many)

UI:

  • New Agents tab in Settings for managing agents
  • Agent selector dropdown in chat (next to system prompt selector)
  • Full CRUD operations with search and filtering

🧪 Test Coverage Improvements

  • Extended test coverage for backend and frontend
  • 60+ new unit tests for agents feature
  • 14 E2E tests for agents UI and chat integration

📝 Documentation & Configuration

  • Added .env.example with configuration documentation
  • Fixed hardcoded Ollama URL (now configurable)
  • Updated CONTRIBUTING.md with branching strategy

🔧 Developer Experience

  • Added justfile for common development commands
  • Sync status indicator and warning banner
  • Improved Playwright config with BASE_URL support

Full Changelog: v0.5.2...v0.6.0

Closes #7

## Release v0.6.0 ### 🤖 New Feature: Agents (v1) Agents allow you to create specialized AI personas with custom system prompts and tool sets. **Features:** - **Agent identity**: Name and description - **System prompt**: Reference prompts from your Prompt Library - **Tool filtering**: Enable specific tools per agent - **Preferred model**: Optionally set a default model for the agent - **Per-chat selection**: Choose an agent from the chat interface - **Project assignment**: Assign agents to projects (many-to-many) **UI:** - New **Agents** tab in Settings for managing agents - **Agent selector** dropdown in chat (next to system prompt selector) - Full CRUD operations with search and filtering ### 🧪 Test Coverage Improvements - Extended test coverage for backend and frontend - 60+ new unit tests for agents feature - 14 E2E tests for agents UI and chat integration ### 📝 Documentation & Configuration - Added `.env.example` with configuration documentation - Fixed hardcoded Ollama URL (now configurable) - Updated CONTRIBUTING.md with branching strategy ### 🔧 Developer Experience - Added `justfile` for common development commands - Sync status indicator and warning banner - Improved Playwright config with BASE_URL support --- **Full Changelog**: v0.5.2...v0.6.0 Closes #7
vikingowl added 10 commits 2026-01-22 12:12:53 +01:00
- Add SyncStatusIndicator component showing connection status in TopNav
- Add SyncWarningBanner that appears after 30s of backend disconnection
- Green dot when synced, amber pulsing when syncing, red when error/offline
- Warning banner is dismissible but reappears on next failure

Closes #11
- Backend runs on port 9090 (matches vite proxy default)
- Adds health check command for all services
- Includes llama.cpp server commands
- Adds test and build commands
- Add branching workflow: main -> dev -> feature/*
- Document that PRs should target dev branch
- Add release workflow documentation
- Add .env.example with all documented environment variables
- Fix conversation-summary.ts to use proxy instead of hardcoded localhost

Closes #9
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
Adds agents feature with the following capabilities:
- Agent identity: name, description
- System prompt reference from Prompt Library (promptId)
- Tool set: subset of available tools (enabledToolNames)
- Optional preferred model
- CRUD operations with IndexedDB storage (schema v7)
- Project-agent relationships (many-to-many via junction table)
- Per-chat agent selection via AgentSelector component
- Settings UI via AgentsTab in Settings page

Integration:
- Agent tools filter LLM tool calls via getToolDefinitionsForAgent()
- Agent prompt integrates with prompt resolution (priority 3)
- AgentSelector dropdown in chat UI (opens upward)

Tests:
- 22 storage layer tests
- 22 state management tests
- 7 tool integration tests
- 9 prompt resolution tests
- 14 E2E tests

Closes #7
vikingowl merged commit 6dcaf37c7f into main 2026-01-22 12:13:30 +01:00
Sign in to join this conversation.
No Reviewers
No Label
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: vikingowl/vessel#4