Commit Graph

6 Commits

Author SHA1 Message Date
0f4cf1078a fix(ui,runtime,search): stabilize markdown/table rendering, runtime notices, and title/search config
This commit bundles a coordinated fix set across frontend and backend runtime flows:\n\n1) Markdown table overflow UX\n- Wrap rendered markdown tables in a dedicated horizontal-scroll container.\n- Preserve wrapper attributes through sanitize so styles always apply.\n- Keep page-level horizontal scroll disabled while allowing in-container table scroll.\n- Improve table container visual consistency (border/radius/shadow/scrollbar behavior).\n\n2) Code block horizontal jitter\n- Adjust code/pre scrollbar gutter and box model handling to remove left-right jump.\n\n3) Execution mode auto-fallback sync + toast behavior\n- Add expiry-driven frontend sync timer for direct->sandbox fallback state refresh.\n- Ensure permission/execution UI state updates at expiry time.\n- Keep fallback warning toast persistent but avoid false-positive toasts when simply switching to sandbox conversations.\n- Trigger fallback toast only when a real direct-expiry transition is detected.\n\n4) Runtime guidance/notify display consistency\n- Unify live polling rendering behavior with history replay behavior.\n- Restore real-time display of guidance/notify/sub-agent/background-command messages.\n- Keep runtime_mode_notice hidden only in idle state as requested.\n\n5) Backend runtime notice emission policy\n- Suppress runtime mode notice insertion when no task is running (idle path).\n- Preserve notice injection when task is actively running.\n\n6) Tool-call ordering safety for injected completion notices\n- Delay inline sub-agent/background-command completion message insertion until all parallel tool calls in the same assistant turn are finished.\n- Prevent invalid assistant/tool_call ordering that causes provider 400 errors for missing tool_call_id responses.\n\n7) Left panel scrolling behavior\n- Enable vertical scrolling for project files / todo / sub-agent / background-command panels.\n- Hide panel scrollbars while preserving scroll capability.\n\n8) Tavily multi-key selection support\n- Introduce config/search.py with selectable env variable name for Tavily key resolution.\n- Keep existing AGENT_TAVILY_API_KEY naming compatible.\n- Export search config through config package.\n\n9) Dedicated conversation-title model config\n- Add AGENT_TITLE_API_BASE_URL / AGENT_TITLE_API_KEY / AGENT_TITLE_MODEL_ID.\n- Route title generation calls to these dedicated credentials/model with fallback defaults.\n\n10) Supporting updates\n- Update .env.example to document new Tavily and title-generation env vars.\n- Include current custom model profile tweak (kimi-k2.6).\n\nValidated with:\n- npm run build\n- python3 -m py_compile (affected backend/config modules)\n- python3 -m unittest test.test_server_refactor_smoke
2026-05-13 15:13:52 +08:00
6ee8cda2a7 feat(security): harden host execution model with sandbox/direct controls
This commit introduces a substantial security and runtime architecture update for host mode, with three major goals: (1) enforce OS-level sandboxing by default, (2) support a controlled temporary direct-execution escape hatch for admin users, and (3) eliminate silent fallback behavior that could hide risk.

Backend/runtime changes:\n- Added a unified host sandbox runner (macOS sandbox-exec / Linux bubblewrap+seccomp / Windows WSL2).\n- Converted host terminal creation to sandboxed interactive shells by default.\n- Kept run_command/run_python on the same execution policy and added host execution mode plumbing (sandbox|direct).\n- Added session-scoped direct mode with TTL auto-revert (default 10 minutes), configurable via environment.\n- Added execution mode APIs (GET/POST /api/execution-mode), host+admin gating, status propagation, and rate limiting.\n- Added runtime refresh hooks so tool calls honor TTL expiration and mode transitions consistently.\n- Removed docker->host silent fallback paths: docker startup/runtime failures now fail fast instead of degrading silently.\n- Added host sandbox prompt injection (host-only) to guide agent behavior under permission constraints.

Configuration and policy changes:\n- Added HOST_EXECUTION_MODE_DEFAULT and HOST_EXECUTION_DIRECT_TTL_SECONDS.\n- Added HOST_SANDBOX_MACOS_WRITABLE_PATHS to support user-defined writable path allowlists.\n- Updated macOS sandbox profile generation to use minimal defaults (workspace + tmp + /dev/null) plus explicit allowlist extensions.\n- Updated .env.example documentation for new execution/sandbox controls.

Frontend changes:\n- Extended permission popover to a two-column model (Permission + Execution Environment) for host admin sessions.\n- Added execution mode state/options to app state, fetching, and status synchronization flows.\n- Added execution mode switching action and user feedback toasts.\n- Kept warning emphasis via text styling only (removed warning border per UX request).

Validation:\n- Python syntax checks passed for modified backend modules.\n- Existing smoke tests passed: python3 -m unittest test.test_server_refactor_smoke\n- Frontend production build passed: npm run build
2026-05-10 19:19:01 +08:00
b151f8ff71 feat: add host workspace manager, mcp-tool-config skill, and UI enhancements 2026-04-28 13:04:51 +08:00
ed5315eef6 feat: add MCP management and host-only runtime policy 2026-04-26 23:49:04 +08:00
7348eab83a docs: refresh readme and phase2 summary 2025-11-23 21:24:09 +08:00
b81d6760bd feat: containerize terminals and add resource controls 2025-11-23 18:49:35 +08:00