Commit Graph

22 Commits

Author SHA1 Message Date
e2bbd767f7 feat(host-security+ui): unify host execution/approval behavior, runtime notices, and approval overlay UX
This commit consolidates a large set of host-mode security and UX fixes across backend and frontend.

Security / execution model:
- Make permission/execution mode switches apply immediately (no deferred pending-only behavior).
- Keep runtime mode change notices durable and visible via user-message guidance path.
- Add explicit runtime message source taxonomy support and persistence:
  user / presend / guidance / notify / sub_agent / background_command.
- Ensure guidance/notify insertion is batched per tool-cycle so mid-run inserts are committed together.
- Separate notify from guidance semantics for mode-change notices.
- Add direct-mode auto-fallback handling visibility on frontend.

Approval and command gating:
- Align run_command approval pre-check logic with docker behavior for approval/auto_approval modes in host execution paths.
- Keep approval retry flow and final-result semantics intact when permission errors trigger approval.
- Externalize forbidden command keyword list into JSON config:
  config/forbidden_commands.json.
- Update forbidden command rejection message to user-facing wording:
  用户不允许执行包含“... ”的指令.

Prompt/runtime guidance:
- Refine execution-mode runtime rule text to avoid endless workaround loops:
  one safe alternative first, then request switching to direct mode when truly required.

Chat rendering / message UX:
- Prevent injected guidance/notify user-messages from incorrectly triggering assistant work header/timer chain.
- Restore correct visibility after history reload while preserving runtime-source behavior.
- Update user-header icon/label rendering by message source:
  - guidance -> 引导 + navigation icon
  - notify/sub_agent/background_command -> 通知 + bell icon
  - user/presend -> keep normal user header.
- Add new icons: static/icons/navigation.svg, static/icons/bell.svg.

Approval panel UX:
- Convert desktop approval panel from layout-compress sidebar to overlay + blur sheet.
- Fix panel transition behavior (remove unintended vertical motion; use dedicated desktop overlay transition).
- Improve approval result display:
  - decision and reason split lines,
  - green/red status styling,
  - multiline reason rendering,
  - auto-collapse delay adjusted to 3s.

Execution mode TTL feedback:
- When direct mode auto-expires to sandbox, frontend menu state is updated from status snapshot.
- Show non-auto-dismiss warning toast to explicitly notify auto-fallback.

Misc consistency updates:
- Execution mode label text cleanup in composer.
- Runtime notice wording normalization (权限模式修改为..., 执行环境修改为...).

Build/test notes:
- Frontend rebuilt after UI changes.
- Smoke tests passed for server refactor path.
2026-05-12 19:16:38 +08:00
8395cf8b4b fix(prompt): merge disabled-tool notice into leading system prompts 2026-05-09 18:56:49 +08:00
b151f8ff71 feat: add host workspace manager, mcp-tool-config skill, and UI enhancements 2026-04-28 13:04:51 +08:00
9dfb1567d2 fix: render user media previews from media store refs 2026-04-27 12:57:13 +08:00
d076e334d9 fix: preserve empty reasoning_content in thinking mode history 2026-04-25 16:35:02 +08:00
757718c492 feat: add user turn tool protection to shallow compression
- Add shallow_compress_keep_user_turn_tools config (default: 3)
- Add is_auto_generated metadata to system messages (sub_agent/background_command)
- Fix sub_agent notification path to include auto_message marker
- Frontend: add input field in PersonalizationDrawer
- Backend: implement protection logic in _run_auto_shallow_compression
2026-04-12 18:48:08 +08:00
6379f8c729 feat: complete conversation versioning UX and restore workflow 2026-04-11 16:16:40 +08:00
e814e89e32 feat: add conversation-bound permission modes and tool approval flow 2026-04-11 04:07:28 +08:00
a04eca3aab fix: unify background run_command notifications with sub-agent flow 2026-04-08 16:13:40 +08:00
bc939a0098 feat: make context compression policy configurable and stabilize compression UX 2026-04-06 16:51:43 +08:00
7e03e3cd5f feat: stabilize context compression and deep-compact flow 2026-04-06 15:12:25 +08:00
2700a25702 feat: add per-user-message work timer with persistence 2026-04-05 15:14:29 +08:00
0296418cff fix(task): stop canceled runs and clear stale task events 2026-04-04 19:46:56 +08:00
12c7a4bdd9 fix: remove legacy file edit tags 2026-03-17 22:43:51 +08:00
cd3f07bcc8 fix: enrich sub-agent results 2026-03-11 18:05:01 +08:00
ed82fc966e fix: improve sub-agent ui and state 2026-03-11 15:40:28 +08:00
f09621fd86 feat: 为子智能体添加思考模式参数
- 新增 thinking_mode 参数(fast/thinking),支持根据任务复杂度选择模式
- 优化子智能体工具说明,提供详细的使用场景示例
- 增强子智能体状态展示,添加统计信息摘要
- 完善交付目录验证,要求必须为不存在的新目录
- 优化子智能体完成/超时/失败的消息格式
- 同步更新前端和批处理相关代码

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2026-03-11 03:34:20 +08:00
b68dee9d98 chore: snapshot current changes 2026-03-10 23:48:40 +08:00
5e768a9e41 refactor: split chat flow streaming loop 2026-03-07 21:21:14 +08:00
7f6a8d8511 refactor: extract tool execution loop from chat task main 2026-03-07 20:41:10 +08:00
3402375710 refactor: split pending writes and task support from chat task main 2026-03-07 20:37:58 +08:00
8ecfac0c06 refactor: isolate chat task main pipeline module 2026-03-07 20:32:02 +08:00