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.
This commit lands a broad host-security architecture update focused on enforceable sandbox execution, clearer permission semantics, and operator usability.
Core execution/security changes
- Introduce and wire a unified host sandbox runner for multi-OS execution:
- macOS: sandbox-exec
- Linux: bubblewrap + seccomp
- Windows: WSL2 path
- Remove silent fallback behavior in failure paths; sandbox-unavailable cases now fail closed instead of dropping to unsafe host execution.
- Ensure host execution mode (sandbox/direct) is propagated consistently into runtime components, including sub-agent startup.
Permission mode model upgrade
- Rework readonly/approval behavior for run_command from brittle command-text gating to execution-layer enforcement:
- readonly: run_command executes in read-only sandbox profile.
- approval: run_command first executes read-only; when permission-denied is detected, request approval and retry once with writable sandbox for that single call.
- Tool loop now returns final post-approval execution result, not intermediate permission-denied payloads.
- Update permission-mode system messaging to describe user-visible behavior without exposing internal implementation details.
Path authorization system
- Add dynamic host policy module and persisted policy file.
- Support dual path classes:
- writable_paths (read+write)
- readable_extra_paths (read-only)
- Enforce file access in file_manager by access type (read vs write) under host mode.
- Add host-only frontend 路径授权 management dialog (settings三级菜单入口), including mode switch between 可读可写 and 仅可读 with separate drafts and save flow.
Sub-agent and terminal alignment
- Sub-agent process launch now respects host execution mode and sandbox controls in host mode.
- Keep terminal session model compatible with sandbox-first behavior and execution-mode propagation.
Tool surface updates
- Remove legacy file-management tools from active tool definitions (create_file/create_folder/rename_file/delete_file) while preserving historical conversation compatibility.
Docs updates
- Add dedicated architecture doc: docs/host_sandbox_and_permission_model.md
- Refresh README and AGENTS sections to reflect updated permission/execution model and path-authorization semantics.
Validation performed
- python unittest smoke suite passes: test.test_server_refactor_smoke
- frontend build passes: npm run build
- syntax checks for touched Python modules completed
