Commit Graph

94 Commits

Author SHA1 Message Date
朱潮
8cab0180e3 update novare 2026-03-13 21:50:57 +08:00
朱潮
082630e281 table_rag_retrieve 和 rag_retrieve 增加调用策略 2026-03-12 11:59:38 +08:00
autobee-sparticle
6309a53860
feat(novare): 添加人员在離判定规则,利用 last_communication_time 字段判断人员是否在 NOVARE 楼内 (#13)
EB API 始终返回人员最后已知坐标,不区分在馆/离馆。通过检查 last_communication_time
与当前时刻的差值(阈值5分钟/24小时),实现三级在離判定并提供对应的日语回答模板。

Closes sparticleinc/mygpt-frontend#1963

Co-authored-by: zhuchao <zhuchaowe@163.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-04 17:21:16 +09:00
朱潮
f7773a93e1 Merge branch 'upgrade/deepagents-0.4.4' 2026-03-04 14:08:51 +08:00
朱潮
f72a53462a Merge branch 'master' of https://github.com/sparticleinc/catalog-agent 2026-03-02 16:07:10 +08:00
朱潮
17f4217f29 添加了同名人员处理说明 2026-03-02 16:06:58 +08:00
朱潮
186d2fe265 添加tmp脚本删除 2026-03-02 15:27:26 +08:00
朱潮
f435ab6a61 script manage prompt 2026-03-02 15:05:03 +08:00
朱潮
fc756a1353 调整提示词 2026-03-02 13:23:58 +08:00
autobee-sparticle
90a2d0555f
fix(novare): 添加设备状态术语转换规则,避免系统术语泄露 (#9)
* chore: add .worktrees/ to .gitignore

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(novare): 添加设备状态术语转换规则,避免系统术语泄露

问题:Bot 在回答设备状态时直接使用「オフライン」等系统内部术语,
与用户认知模型不匹配,导致困惑。

解决方案:在 prompt/novare.md 的「响应规范」部分添加术语转换规则:
- 禁止在用户回复中使用系统内部术语
- 优先报告功能状态(亮度、温度等),不提及连接状态
- 提供具体的场景处理示例和正确/错误对比

closes #1853

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: zhuchao <zhuchaowe@163.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-26 18:14:29 +09:00
朱潮
925a0a318a add project root 2026-02-15 18:55:49 +08:00
朱潮
e67d50b4fc rename general agent 2026-02-06 17:05:17 +08:00
朱潮
6d32a49c09 update novare.md 2026-02-05 10:35:58 +08:00
朱潮
5134c0d8a6 添加环境变量 2026-01-25 21:46:02 +08:00
朱潮
f29fd1fb54 📝 docs(prompt): add skill execution workflow with read_file pattern
- Add 3-step workflow: read_file → extract command → bash execute
- Include complete example showing read_file + bash execution pattern
- Clarify that SKILL.md must be read with read_file tool before execution
- Add key rules with checkmarks (always read_file, always absolute paths)

Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
2026-01-21 17:50:58 +08:00
朱潮
d3f60e129b 📝 docs(prompt): enhance skill script path handling instructions
- Add CRITICAL path handling section with skill-specific conversion rules
- Include path conversion table showing SKILL.md relative paths to absolute paths
- Add 4-step execution guide for skill script path resolution
- Clarify skill directory structure (scripts/ can be at root or in scripts/ subfolder)

Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
2026-01-21 17:21:53 +08:00
朱潮
60bd1e4042 feat(prompt): add fact retrieval prompt with contact tracking
Add comprehensive prompt for extracting and storing user facts from
conversations, with special focus on relationship/contact tracking:
- Full name and nickname association (e.g., "Mike" → "Michael Johnson")
- Relationship context recording (family, friend, colleague, etc.)
- Multi-language name support
- Few-shot examples for various fact extraction scenarios

Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>
2026-01-21 13:22:17 +08:00
朱潮
f694101747 refactor: migrate from Memori to Mem0 for long-term memory
Replace Memori with Mem0 for memory management:
- Delete memori_config.py, memori_manager.py, memori_middleware.py
- Add mem0_config.py, mem0_manager.py, mem0_middleware.py
- Update environment variables (MEMORI_* -> MEM0_*)
- Integrate Mem0 with LangGraph middleware
- Add sync connection pool for Mem0 in DBPoolManager
- Move checkpoint message prep to config creation

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-20 21:15:30 +08:00
朱潮
723b249e42 增加2个系统级别的skill 2026-01-16 23:05:30 +08:00
朱潮
90117b41fe 修复符号链接的问题,和deep_agent提示词 2026-01-13 14:22:44 +08:00
朱潮
37958291ae Merge branch 'rag_receive_top_k' 2026-01-08 17:28:59 +08:00
朱潮
fc5c1adaaa feat(mcp): add top_k optional parameter to RAG retrieve tool 2026-01-08 17:27:35 +08:00
朱潮
8bb8c3fbc8 add scripts/ 2026-01-04 17:19:03 +08:00
朱潮
e7f6378f6b system_prompt_deep_agent 2026-01-04 16:45:24 +08:00
朱潮
96f5079bf9 📝 docs(deep-agent): remove directory access restriction from system prompt
Remove the CRITICAL section about directory access restrictions.
Path handling guidance is still maintained.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-31 21:02:34 +08:00
朱潮
7c9e270a66 feat(deep-agent): add custom workspace_root support for shell commands
- Add create_custom_cli_agent function to support custom workspace_root
- Set shell workspace to ~/.deepagents/{bot_id} for deep_agent type
- Pass system_prompt to create_custom_cli_agent for proper context
- Fix duplicate <env> tag in system_prompt_deep_agent.md

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-31 18:18:38 +08:00
朱潮
766b9becda feat(deep-agent): add skills support and improve project structure
- Add skills parameter to ChatRequest for skill file processing
- Extract and unzip skill files to robot project skills directory
- Add robot_config.json with bot_id and environment variables
- Update symlink setup to skip if ~/.deepagents already exists
- Enhance system prompt with directory access restrictions
- Refactor _get_robot_dir to handle symlink paths correctly

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-31 13:21:58 +08:00
朱潮
d3465d418e add symlink 2025-12-23 17:36:45 +08:00
朱潮
aaad9df20a add skills 2025-12-22 23:47:12 +08:00
朱潮
a92bea5b58 删除一些环境变量 2025-12-18 09:41:43 +08:00
朱潮
a97ff5a185 优化思考 2025-12-15 11:57:31 +08:00
朱潮
ab68c4309d think增加流式输出模式 2025-12-14 07:53:24 +08:00
朱潮
be264884a2 add think tag 2025-12-13 11:21:16 +08:00
朱潮
bcd1b7cc9d update guideline_prompt 2025-12-13 10:11:21 +08:00
朱潮
ec9558fd4c update guidline 2025-12-13 02:52:01 +08:00
朱潮
eb17dff54a wowtalk prompt 2025-12-11 12:12:39 +08:00
朱潮
ee41279569 add last_message 2025-12-08 22:15:49 +08:00
朱潮
d3a4a84713 merge 2025-12-04 21:05:31 +08:00
朱潮
c58b20e56f 修改guideline_prompt:只需要列出详细的工具调用步骤即可,不需要考虑回复用户的话术,步骤数量根据实际需求调整。 2025-12-04 13:50:25 +08:00
朱潮
25f8f7c98f 修改guideline_prompt 2025-12-04 12:22:08 +08:00
朱潮
e96e0791ad 修改guideline_prompt 2025-12-03 20:34:54 +08:00
朱潮
bba23921d8 修改guideline_reasoning 2025-12-03 20:29:28 +08:00
朱潮
cf33da310d 修改general_agent提示词 2025-12-03 17:53:18 +08:00
朱潮
a7f27fe33b 修改guideline提示词 2025-12-03 14:13:39 +08:00
朱潮
4d995ac990 优化Guidelines指令遵循 2025-12-02 11:00:31 +08:00
朱潮
bb640e6d6e 优化guideline提示词,新增admin后台修改prompt功能 2025-12-02 10:10:00 +08:00
朱潮
c5b68a91f3 优化guideline 提示词 2025-12-02 09:10:15 +08:00
朱潮
154662ac6e 只传输执行计划给agent 2025-12-01 23:20:09 +08:00
朱潮
6964abe622 优化think提示词 2025-12-01 22:39:56 +08:00
朱潮
c214ebd124 优化think提示词 2025-12-01 22:38:50 +08:00