agent-Specialization/prompts
JOJO b7fe5f2b02 feat(memory): improve workspace memory and skill workflows
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.
2026-05-27 03:04:43 +08:00
..
agents_md_inject.txt feat: 添加AGENTS.md自动注入的prompt模板 2026-04-12 16:34:06 +08:00
deep_thinking_mode_guidelines.txt feat: expand model support and qwen-vl ux 2026-01-03 07:01:24 +08:00
execution_mode.txt feat(security): harden host execution model with sandbox/direct controls 2026-05-10 19:19:01 +08:00
human_like_style.txt feat: 添加智能体交流风格选项 2026-04-14 01:47:06 +08:00
main_system_qwenvl.txt refactor(messages): 统一运行期消息插入为 [系统通知|source] 前缀的 user 消息 2026-05-23 02:01:36 +08:00
main_system.txt refactor(messages): 统一运行期消息插入为 [系统通知|source] 前缀的 user 消息 2026-05-23 02:01:36 +08:00
permission_mode.txt feat: 权限模式支持管道命令并优化prompt注入 2026-04-13 16:23:24 +08:00
personalization.txt fix: refine title prompt and sandbox config 2026-01-29 11:54:24 +08:00
recent_conversations.txt feat(memory): improve workspace memory and skill workflows 2026-05-27 03:04:43 +08:00
skills_system.txt feat: add read_skill tool and frontend read-skill rendering 2026-04-19 16:57:02 +08:00
sub_agent_guidelines.txt feat: 添加 terminal-guide 和 sub-agent-guide skills 2026-03-16 21:17:02 +08:00
thinking_mode_guidelines.txt feat: expand model support and qwen-vl ux 2026-01-03 07:01:24 +08:00
title_generation_prompt.txt chore: instruct title gen to ignore first user instructions 2026-01-05 01:13:13 +08:00
todo_guidelines.txt fix: update run_command limits and planning guidance 2026-04-14 14:12:11 +08:00
workspace_system.txt feat: add silent disable option and workspace prompt split 2026-02-03 23:11:15 +08:00