Implement workspace-scoped conversation storage with legacy migration based on host workspace metadata, active host workspace state protection, and frontend/backend conversation list scoping.
Add proactive recent-conversation prompt support with a configurable personal-space limit, frozen per conversation metadata, empty-conversation filtering, and a dedicated prompt template.
Add conversation_search and conversation_review tools with readable formatted results, workspace-only access, current-conversation exclusion, multi-keyword search, list mode, message/tool counts, read/save review modes, long-review fallback to .agents/review, and frontend detail renderers.
Move internal workspace artifacts under .agents, update upload/skills/compact/review paths, show .agents internal directories in prompt file trees, and adjust versioning ignores.
Add create_skill and a Skills tool category, move read_skill into that category, validate and archive skill folders, support host global skills and Docker/API private skills, and sync private skills into .agents/skills and prompts.
Update memory stamping with conversation/time source metadata and include frontend icon/status/display updates plus tests for workspace conversation storage and skills management.
Current status includes:
- Virtual monitor surface and components
- Monitor store for state management
- Tool call animations and transitions
- Liquid glass shader integration
Known issue to fix: Tool status display timing - "正在xx" appears
after tool execution completes instead of when tool call starts.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
