Release/v0.2.2 (#258)

* 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 读取的接口，去掉全局锁 * 输出数组 * 反思优化1.0（优化隐私输出、时间检索） * 反思优化1.0（优化隐私输出、时间检索） * 反思优化1.0（优化隐私输出、时间检索） * 反思优化测试接口 * 反思优化测试接口 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察) * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 把group_id替换end_user_id * 把group_id替换end_user_id_ * 把group_id替换end_user_id_ * config_config替换成memory_config * config_config替换成memory_config * [fix]Fix the memory interface to use end_user_id. * config_config替换成memory_config * config_config替换成memory_config * config_config替换成memory_config * config_id字段改成UUID * config_id字段改成UUID * config_id字段改成UUID * config_id字段改成UUID，与develop校对恢复 * 检查项目，修复group_id的遗留问题 * 检查项目，修复group_id的遗留问题 * Fix/interface home (#182) * [fix]Fix the interface for statistics of recent activities and applications * [changes]Modify the code based on the AI review 1.Use the boolean auxiliary methods provided by SQLAlchemy instead of using == True in the is_active filter. 2.The calculation of the "PROJECT_ROOT" has now been hardcoded with five levels of nested os.path.dirname calls. * [fix]Fix the interface for statistics of recent activities and applications * [changes]Modify the code based on the AI review 1.Use the boolean auxiliary methods provided by SQLAlchemy instead of using == True in the is_active filter. 2.The calculation of the "PROJECT_ROOT" has now been hardcoded with five levels of nested os.path.dirname calls. * Fix/optimize inerface (#183) * [changes]Optimize the time consumption of the "/end_users" interface * [fix]Optimize the time consumption of the "/hot_memory_tags" interface * [changes]Optimize the time consumption of the "/end_users" interface * [fix]Optimize the time consumption of the "/hot_memory_tags" interface * [changes]Improve the code based on AI review * Fix/memory mcp2 1 (#184) * 优化快速检索的回复内容 * 优化快速检索的回复内容 * Fix/memory mcp2 1 (#185) * 优化快速检索的回复内容 * 优化快速检索的回复内容 * 路径的BUG修复 * 路径的BUG修复 * 路径的BUG修复 * 路径的BUG修复 * 路径的BUG修复 * Fix/memory mcp2 1 (#188) * 优化快速检索的回复内容 * 优化快速检索的回复内容 * 路径的BUG修复 * 路径的BUG修复 * 路径的BUG修复 * 路径的BUG修复 * 路径的BUG修复 * LLM生存缺少config_id认证，修复BUG * LLM生存缺少config_id认证，修复BUG * LLM生存缺少config_id认证，修复BUG * 解决冲突 * 解决冲突 * feat(home page): version description update * Fix/memory mcp2 1 (#190) * 优化快速检索的回复内容 * 优化快速检索的回复内容 * 路径的BUG修复 * 路径的BUG修复 * 路径的BUG修复 * 路径的BUG修复 * 路径的BUG修复 * LLM生存缺少config_id认证，修复BUG * LLM生存缺少config_id认证，修复BUG * LLM生存缺少config_id认证，修复BUG * 深度检索优化，搜索不到数据/提问的概念过于蘑菇，以引导的方式继续提问 * 深度检索优化，搜索不到数据/提问的概念过于蘑菇，以引导的方式继续提问 * 深度检索优化，搜索不到数据/提问的概念过于蘑菇，以引导的方式继续提问 * end_user_id清理干净 * end_user_id清理干净 * 修复遗留合并BUG * 修复遗留合并BUG * 修复遗留合并BUG * 修复遗留合并BUG * feat(web): memory related interface parameter transfer adjustment * 感知meta_data字段BUG修复 * Fix/memory bug fix (#171) * feat(sandbox): add Python 3 code execution sandbox support * feat(workflow): emit SSE events for node exception output * perf(sandbox): optimize code encryption handling * perf(workflow): update standard node output structure * [add] migration script * [modify] migration script * feat(web): add workflow runtime info * fix(web): handleSSE bugfix * fix(sandbox): prevent imports from being blocked when network is disabled * user_id->现实为config_id_old * user_id->显示为config_id_old传输 * Fix/memory bug fix (#199) * 图谱数据量限制数量去掉 * 图谱数据量限制数量去掉 * 图谱数据量限制数量去掉 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 读取的接口，去掉全局锁 * 输出数组 * 反思优化1.0（优化隐私输出、时间检索） * 反思优化1.0（优化隐私输出、时间检索） * 反思优化1.0（优化隐私输出、时间检索） * 反思优化测试接口 * 反思优化测试接口 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察) * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 把group_id替换end_user_id * 把group_id替换end_user_id_ * 把group_id替换end_user_id_ * config_config替换成memory_config * config_config替换成memory_config * [fix]Fix the memory interface to use end_user_id. * config_config替换成memory_config * config_config替换成memory_config * config_config替换成memory_config * config_id字段改成UUID * config_id字段改成UUID * config_id字段改成UUID * config_id字段改成UUID，与develop校对恢复 * 检查项目，修复group_id的遗留问题 * 检查项目，修复group_id的遗留问题 * 解决冲突 * 解决冲突 * end_user_id清理干净 * end_user_id清理干净 * 修复遗留合并BUG * 修复遗留合并BUG * 修复遗留合并BUG * 修复遗留合并BUG * 感知meta_data字段BUG修复 * user_id->现实为config_id_old * user_id->显示为config_id_old传输 --------- Co-authored-by: lanceyq <1982376970@qq.com> * user_id->显示为config_id_old传输 * feat(web): update read_all_config select valueKey * user_id->显示为config_id_old传输 * feat(workflow): Add a new node for executing code * fix(web): KnowledgeConfigModal bugfix * fix(web): iteration's variable add parameter-extractor node * fix(sandbox): treat non-zero exit codes as errors instead of relying only on stderr * Fix/memory bug fix (#200) * 图谱数据量限制数量去掉 * 图谱数据量限制数量去掉 * 图谱数据量限制数量去掉 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 读取的接口，去掉全局锁 * 输出数组 * 反思优化1.0（优化隐私输出、时间检索） * 反思优化1.0（优化隐私输出、时间检索） * 反思优化1.0（优化隐私输出、时间检索） * 反思优化测试接口 * 反思优化测试接口 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察) * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 把group_id替换end_user_id * 把group_id替换end_user_id_ * 把group_id替换end_user_id_ * config_config替换成memory_config * config_config替换成memory_config * [fix]Fix the memory interface to use end_user_id. * config_config替换成memory_config * config_config替换成memory_config * config_config替换成memory_config * config_id字段改成UUID * config_id字段改成UUID * config_id字段改成UUID * config_id字段改成UUID，与develop校对恢复 * 检查项目，修复group_id的遗留问题 * 检查项目，修复group_id的遗留问题 * 解决冲突 * 解决冲突 * end_user_id清理干净 * end_user_id清理干净 * 修复遗留合并BUG * 修复遗留合并BUG * 修复遗留合并BUG * 修复遗留合并BUG * 感知meta_data字段BUG修复 * user_id->现实为config_id_old * user_id->显示为config_id_old传输 * user_id->显示为config_id_old传输 * user_id->显示为config_id_old传输 --------- Co-authored-by: lanceyq <1982376970@qq.com> * Refactor/benchmark test (#196) * [changes]refactor locomo_test * [fix]Fix the circular import of ModelParameters * [changes]The benchmark test can run stably. * [fix]Complete end-to-end LoCoMo repair * [fix]Complete the end-to-end longmemeval and memsciqa fixes * [changes]Complete the benchmark test description document to ensure that the configuration parameters take effect. * [changes]refactor locomo_test * [fix]Fix the circular import of ModelParameters * [changes]The benchmark test can run stably. * [fix]Complete end-to-end LoCoMo repair * [fix]Complete the end-to-end longmemeval and memsciqa fixes * [changes]Complete the benchmark test description document to ensure that the configuration parameters take effect. * [changes]Benchmark test adaptation for end_user_id * [changes]refactor locomo_test * [fix]Fix the circular import of ModelParameters * [changes]The benchmark test can run stably. * [fix]Complete end-to-end LoCoMo repair * [fix]Complete the end-to-end longmemeval and memsciqa fixes * [changes]Complete the benchmark test description document to ensure that the configuration parameters take effect. * [fix]Complete the end-to-end longmemeval and memsciqa fixes * [changes]Complete the benchmark test description document to ensure that the configuration parameters take effect. * [changes]Benchmark test adaptation for end_user_id * [modify] migration script * delete benchmark-test (#204) * Refactor: Move evaluation folder to redbear-mem-benchmark submodule * [changes]Restore .gitmodules * feat(web): workflow add code node * 检查需要更改的格式问题 * Fix/redbear benchmark (#205) * Refactor: Move evaluation folder to redbear-mem-benchmark submodule * [changes]Update submodule reference * Refactor: Move evaluation folder to redbear-mem-benchmark submodule * [changes]Update submodule reference * Remove duplicate evaluation submodule, use redbear-mem-benchmark instead * Fix/memory bug fix (#207) * 图谱数据量限制数量去掉 * 图谱数据量限制数量去掉 * 图谱数据量限制数量去掉 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 读取的接口，去掉全局锁 * 输出数组 * 反思优化1.0（优化隐私输出、时间检索） * 反思优化1.0（优化隐私输出、时间检索） * 反思优化1.0（优化隐私输出、时间检索） * 反思优化测试接口 * 反思优化测试接口 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察) * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 把group_id替换end_user_id * 把group_id替换end_user_id_ * 把group_id替换end_user_id_ * config_config替换成memory_config * config_config替换成memory_config * [fix]Fix the memory interface to use end_user_id. * config_config替换成memory_config * config_config替换成memory_config * config_config替换成memory_config * config_id字段改成UUID * config_id字段改成UUID * config_id字段改成UUID * config_id字段改成UUID，与develop校对恢复 * 检查项目，修复group_id的遗留问题 * 检查项目，修复group_id的遗留问题 * 解决冲突 * 解决冲突 * end_user_id清理干净 * end_user_id清理干净 * 修复遗留合并BUG * 修复遗留合并BUG * 修复遗留合并BUG * 修复遗留合并BUG * 感知meta_data字段BUG修复 * user_id->现实为config_id_old * user_id->显示为config_id_old传输 * user_id->显示为config_id_old传输 * user_id->显示为config_id_old传输 * 检查需要更改的格式问题 --------- Co-authored-by: lanceyq <1982376970@qq.com> * fix(web): remove URI decode and encode * [add] plugin system and base sso module * 修复宿主列表获取memory_config_idBUG * Fix/memory bug fix (#209) * 图谱数据量限制数量去掉 * 图谱数据量限制数量去掉 * 图谱数据量限制数量去掉 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 读取的接口，去掉全局锁 * 输出数组 * 反思优化1.0（优化隐私输出、时间检索） * 反思优化1.0（优化隐私输出、时间检索） * 反思优化1.0（优化隐私输出、时间检索） * 反思优化测试接口 * 反思优化测试接口 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察) * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 把group_id替换end_user_id * 把group_id替换end_user_id_ * 把group_id替换end_user_id_ * config_config替换成memory_config * config_config替换成memory_config * [fix]Fix the memory interface to use end_user_id. * config_config替换成memory_config * config_config替换成memory_config * config_config替换成memory_config * config_id字段改成UUID * config_id字段改成UUID * config_id字段改成UUID * config_id字段改成UUID，与develop校对恢复 * 检查项目，修复group_id的遗留问题 * 检查项目，修复group_id的遗留问题 * 解决冲突 * 解决冲突 * end_user_id清理干净 * end_user_id清理干净 * 修复遗留合并BUG * 修复遗留合并BUG * 修复遗留合并BUG * 修复遗留合并BUG * 感知meta_data字段BUG修复 * user_id->现实为config_id_old * user_id->显示为config_id_old传输 * user_id->显示为config_id_old传输 * user_id->显示为config_id_old传输 * 检查需要更改的格式问题 * 修复宿主列表获取memory_config_idBUG --------- Co-authored-by: lanceyq <1982376970@qq.com> * [modify] file local server url * [add] migration script * fix(workflow): fix activation and branch control issues in streaming output * fix(workflow): fix function cache not taking effect and potential list index overflow * style(workflow): enforce PEP8 style and remove redundant imports * fix(workflow): fix streaming output error when variable is not a string * [fix]remove aspose-slides * perf(workflow): enhance streaming output node activation performance * feat(workflow): store token usage in message table * feat(web): add PageEmpty component * feat(web): add PageTabs component * perf(workflow): make memory configuration backward compatible * feat(web): update model management * config_id做映射 * config_id做映射 * Fix/memory bug fix (#211) * 图谱数据量限制数量去掉 * 图谱数据量限制数量去掉 * 图谱数据量限制数量去掉 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 读取的接口，去掉全局锁 * 输出数组 * 反思优化1.0（优化隐私输出、时间检索） * 反思优化1.0（优化隐私输出、时间检索） * 反思优化1.0（优化隐私输出、时间检索） * 反思优化测试接口 * 反思优化测试接口 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察) * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 把group_id替换end_user_id * 把group_id替换end_user_id_ * 把group_id替换end_user_id_ * config_config替换成memory_config * config_config替换成memory_config * [fix]Fix the memory interface to use end_user_id. * config_config替换成memory_config * config_config替换成memory_config * config_config替换成memory_config * config_id字段改成UUID * config_id字段改成UUID * config_id字段改成UUID * config_id字段改成UUID，与develop校对恢复 * 检查项目，修复group_id的遗留问题 * 检查项目，修复group_id的遗留问题 * 解决冲突 * 解决冲突 * end_user_id清理干净 * end_user_id清理干净 * 修复遗留合并BUG * 修复遗留合并BUG * 修复遗留合并BUG * 修复遗留合并BUG * 感知meta_data字段BUG修复 * user_id->现实为config_id_old * user_id->显示为config_id_old传输 * user_id->显示为config_id_old传输 * user_id->显示为config_id_old传输 * 检查需要更改的格式问题 * 修复宿主列表获取memory_config_idBUG * config_id做映射 * config_id做映射 --------- Co-authored-by: lanceyq <1982376970@qq.com> * feat(web): getModelListUrl add is_active param * config_id做映射+1 * config_id做映射+1 * config_id做映射+1 * feat(web): remove file url replace * Fix/memory bug fix (#212) * 图谱数据量限制数量去掉 * 图谱数据量限制数量去掉 * 图谱数据量限制数量去掉 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 读取的接口，去掉全局锁 * 输出数组 * 反思优化1.0（优化隐私输出、时间检索） * 反思优化1.0（优化隐私输出、时间检索） * 反思优化1.0（优化隐私输出、时间检索） * 反思优化测试接口 * 反思优化测试接口 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察) * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 把group_id替换end_user_id * 把group_id替换end_user_id_ * 把group_id替换end_user_id_ * config_config替换成memory_config * config_config替换成memory_config * [fix]Fix the memory interface to use end_user_id. * config_config替换成memory_config * config_config替换成memory_config * config_config替换成memory_config * config_id字段改成UUID * config_id字段改成UUID * config_id字段改成UUID * config_id字段改成UUID，与develop校对恢复 * 检查项目，修复group_id的遗留问题 * 检查项目，修复group_id的遗留问题 * 解决冲突 * 解决冲突 * end_user_id清理干净 * end_user_id清理干净 * 修复遗留合并BUG * 修复遗留合并BUG * 修复遗留合并BUG * 修复遗留合并BUG * 感知meta_data字段BUG修复 * user_id->现实为config_id_old * user_id->显示为config_id_old传输 * user_id->显示为config_id_old传输 * user_id->显示为config_id_old传输 * 检查需要更改的格式问题 * 修复宿主列表获取memory_config_idBUG * config_id做映射 * config_id做映射 * config_id做映射+1 * config_id做映射+1 * config_id做映射+1 --------- Co-authored-by: lanceyq <1982376970@qq.com> * feat(model and app statistic): 1. Optimize the model list; 2. Increase the model combination; 3. Add a model square; 4. Add application management statistics * feat(web): model logo update * 应用层memory_content->memory_config * fix(web): correct spelling * 应用层memory_content->memory_config * 应用层memory_content->memory_config * Fix/memory bug fix (#215) * 图谱数据量限制数量去掉 * 图谱数据量限制数量去掉 * 图谱数据量限制数量去掉 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 读取的接口，去掉全局锁 * 输出数组 * 反思优化1.0（优化隐私输出、时间检索） * 反思优化1.0（优化隐私输出、时间检索） * 反思优化1.0（优化隐私输出、时间检索） * 反思优化测试接口 * 反思优化测试接口 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察) * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 把group_id替换end_user_id * 把group_id替换end_user_id_ * 把group_id替换end_user_id_ * config_config替换成memory_config * config_config替换成memory_config * [fix]Fix the memory interface to use end_user_id. * config_config替换成memory_config * config_config替换成memory_config * config_config替换成memory_config * config_id字段改成UUID * config_id字段改成UUID * config_id字段改成UUID * config_id字段改成UUID，与develop校对恢复 * 检查项目，修复group_id的遗留问题 * 检查项目，修复group_id的遗留问题 * 解决冲突 * 解决冲突 * end_user_id清理干净 * end_user_id清理干净 * 修复遗留合并BUG * 修复遗留合并BUG * 修复遗留合并BUG * 修复遗留合并BUG * 感知meta_data字段BUG修复 * user_id->现实为config_id_old * user_id->显示为config_id_old传输 * user_id->显示为config_id_old传输 * user_id->显示为config_id_old传输 * 检查需要更改的格式问题 * 修复宿主列表获取memory_config_idBUG * config_id做映射 * config_id做映射 * config_id做映射+1 * config_id做映射+1 * config_id做映射+1 * 应用层memory_content->memory_config * 应用层memory_content->memory_config * 应用层memory_content->memory_config --------- Co-authored-by: lanceyq <1982376970@qq.com> * feat(model and app statistic): 1. Optimize the model list; 2. Increase the model combination; 3. Add a model square; 4. Add application management statistics * fix(web): model loading update * 统一字段为config_id_old * 统一字段为config_id_old * feat(model and app statistic): 1. Optimize the model list; 2. Increase the model combination; 3. Add a model square; 4. Add application management statistics * 统一字段为config_id_old * 统一字段为config_id_old * memory_content暂时不修改 * memory_content暂时不修改 * Fix/memory bug fix (#217) * 图谱数据量限制数量去掉 * 图谱数据量限制数量去掉 * 图谱数据量限制数量去掉 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 用户详情优化 * 读取的接口，去掉全局锁 * 输出数组 * 反思优化1.0（优化隐私输出、时间检索） * 反思优化1.0（优化隐私输出、时间检索） * 反思优化1.0（优化隐私输出、时间检索） * 反思优化测试接口 * 反思优化测试接口 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 读取接口内层嵌套BUG修复 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察) * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 新增中翻英功能（记忆时间线）(用户摘要)(兴趣分布接口)(查询核心档案)(记忆洞察)-接口添加翻译字段 * 把group_id替换end_user_id * 把group_id替换end_user_id_ * 把group_id替换end_user_id_ * config_config替换成memory_config * config_config替换成memory_config * [fix]Fix the memory interface to use end_user_id. * config_config替换成memory_config * config_config替换成memory_config * config_config替换成memory_config * config_id字段改成UUID * config_id字段改成UUID * config_id字段改成UUID * config_id字段改成UUID，与develop校对恢复 * 检查项目，修复group_id的遗留问题 * 检查项目，修复group_id的遗留问题 * 解决冲突 * 解决冲突 * end_user_id清理干净 * end_user_id清理干净 * 修复遗留合并BUG * 修复遗留合并BUG * 修复遗留合并BUG * 修复遗留合并BUG * 感知meta_data字段BUG修复 * user_id->现实为config_id_old * user_id->显示为config_id_old传输 * user_id->显示为config_id_old传输 * user_id->显示为config_id_old传输 * 检查需要更改的格式问题 * 修复宿主列表获取memory_config_idBUG * config_id做映射 * config_id做映射 * config_id做映射+1 * config_id做映射+1 * config_id做映射+1 * 应用层memory_content->memory_config * 应用层memory_content->memory_config * 应用层memory_content->memory_config * 统一字段为config_id_old * 统一字段为config_id_old * 统一字段为config_id_old * 统一字段为config_id_old * memory_content暂时不修改 * memory_content暂时不修改 --------- Co-authored-by: lanceyq <1982376970@qq.com> * feat(web): add app statistics * fix(workflow): fix streaming output issues with multi-output End nodes End nodes with multiple output segments could cause cursor errors or leave some segments inactive, resulting in incorrect final outputs. Unified _emit_active_chunks and _update_scope_activate to ensure all segments are activated in order and streamed correctly. * feat(web): add apps statistics api * fix(web): agent's knowledge_bases bugfix * Revert "feat(web): update read_all_config select valueKey" This reverts commit 46f0f3cee9. * [add] migrations script * perf(workflow): make memory write node backward-compatible and defer config validation * 旧数据兼容 * 旧数据兼容 * 旧数据兼容 * 旧数据兼容 * fix(web): model bugfix * fix(web): model bugfix * 提交遗漏 (#228) * [fix] chat api for workflow * [fix] web search set for v1 api * fix(web): model bugfix * fix(web): model list remove is_active * fix(model): bug fix * [add]migration script * [fix] api * [fix] api * fix(web): model bugfix * fix(model): the model type does not allow modification, delete tts and speech2text type * fix(model): bug fix * 遗漏的历史映射 * 遗漏的历史映射 * 遗漏的历史映射 * Add/develop memory (#239) * 遗漏的历史映射 * 遗漏的历史映射 * 遗漏的历史映射 * 遗漏的历史映射 * 遗漏的历史映射 * feat(web): model ui update * feat(web): model ui update * Add/develop memory (#243) * 遗漏的历史映射 * 遗漏的历史映射 * fix(model): bug fix * feat(web): model ui update * Add/develop memory (#247) * 遗漏的历史映射 * 遗漏的历史映射 * 遗漏的历史映射 * 遗漏的历史映射 * 遗漏的历史映射 * 遗漏的历史映射 * 遗漏的历史映射 * 遗漏的历史映射 * 遗漏的历史映射 * [modify] migration script * [add] migration script * fix(web): change form message * fix(web): the memoryContent field is compatible with numbers and strings * feat(web): code node hidden * fix(model): 1. create a basic model to check if the name and provider are duplicated. 2. The result shows error models because the provider created API Keys for all matching models. --------- Co-authored-by: lixinyue <2569494688@qq.com> Co-authored-by: lanceyq <1982376970@qq.com> Co-authored-by: yujiangping <yujiangping@taofen8.com> Co-authored-by: 乐力齐 <162269739+lanceyq@users.noreply.github.com> Co-authored-by: lixinyue11 <94037597+lixinyue11@users.noreply.github.com> Co-authored-by: yingzhao <zhaoyingyz@126.com> Co-authored-by: Timebomb2018 <18868801967@163.com> Co-authored-by: Mark <zhuwenhui5566@163.com> Co-authored-by: zhaoying <yzhao96@best-inc.com> Co-authored-by: Eternity <1533512157@qq.com> Co-authored-by: lixiangcheng1 <lixiangcheng1@wanda.cn>
2026-01-30 14:51:34 +08:00
parent 988a41f5e4
commit 0159fdf149
320 changed files with 11769 additions and 11942 deletions
--- a/api/app/schemas/app_schema.py
+++ b/api/app/schemas/app_schema.py
@@ -299,6 +299,18 @@ class AppRelease(BaseModel):
    created_at: datetime.datetime
    updated_at: datetime.datetime

+    @field_validator("config", mode="before")
+    @classmethod
+    def parse_config(cls, v):
+        """处理 config 字段，如果是字符串则解析为字典"""
+        if isinstance(v, str):
+            import json
+            try:
+                return json.loads(v)
+            except json.JSONDecodeError:
+                return {}
+        return v if v is not None else {}
+
    @field_serializer("created_at", when_used="json")
    def _serialize_created_at(self, dt: datetime.datetime):
        return int(dt.timestamp() * 1000) if dt else None
--- a/api/app/schemas/emotion_schema.py
+++ b/api/app/schemas/emotion_schema.py
@@ -1,11 +1,12 @@
 """情绪分析相关的请求和响应模型"""

 from typing import Optional
+from uuid import UUID
 from pydantic import BaseModel, Field

 class EmotionTagsRequest(BaseModel):
    """获取情绪标签统计请求"""
-    group_id: str = Field(..., description="组ID")
+    end_user_id: str = Field(..., description="组ID")
    emotion_type: Optional[str] = Field(None, description="情绪类型过滤（joy/sadness/anger/fear/surprise/neutral）")
    start_date: Optional[str] = Field(None, description="开始日期（ISO格式，如：2024-01-01）")
    end_date: Optional[str] = Field(None, description="结束日期（ISO格式，如：2024-12-31）")
@@ -14,14 +15,14 @@ class EmotionTagsRequest(BaseModel):

 class EmotionWordcloudRequest(BaseModel):
    """获取情绪词云数据请求"""
-    group_id: str = Field(..., description="组ID")
+    end_user_id: str = Field(..., description="组ID")
    emotion_type: Optional[str] = Field(None, description="情绪类型过滤（joy/sadness/anger/fear/surprise/neutral）")
    limit: int = Field(50, ge=1, le=200, description="返回词语数量")


 class EmotionHealthRequest(BaseModel):
    """获取情绪健康指数请求"""
-    group_id: str = Field(..., description="组ID")
+    end_user_id: str = Field(..., description="组ID")
    time_range: str = Field("30d", description="时间范围（7d/30d/90d）")


@@ -29,8 +30,8 @@ class EmotionHealthRequest(BaseModel):

 class EmotionSuggestionsRequest(BaseModel):
    """获取个性化情绪建议请求"""
-    group_id: str = Field(..., description="组ID")
-    config_id: Optional[int] = Field(None, description="配置ID（用于指定LLM模型）")
+    end_user_id: str = Field(..., description="组ID")
+    config_id: Optional[UUID] = Field(None, description="配置ID（用于指定LLM模型）")


 class EmotionGenerateSuggestionsRequest(BaseModel):
--- a/api/app/schemas/memory_agent_schema.py
+++ b/api/app/schemas/memory_agent_schema.py
@@ -7,11 +7,11 @@ class UserInput(BaseModel):
    message: str
    history: list[dict]
    search_switch: str
-    group_id: str
+    end_user_id: str
    config_id: Optional[str] = None


 class Write_UserInput(BaseModel):
    messages: list[dict]
-    group_id: str
-    config_id: Optional[str] = None
+    end_user_id: str
+    config_id: Optional[str] = None
--- a/api/app/schemas/memory_config_schema.py
+++ b/api/app/schemas/memory_config_schema.py
@@ -35,7 +35,7 @@ class ConfigurationError(Exception):
    def __init__(
        self,
        message: str,
-        config_id: Optional[int] = None,
+        config_id: Optional[UUID] = None,
        workspace_id: Optional[UUID] = None,
        context: Optional[Dict[str, Any]] = None,
    ):
@@ -72,7 +72,7 @@ class WorkspaceNotFoundError(ConfigurationError):
    def __init__(
        self,
        workspace_id: UUID,
-        config_id: Optional[int] = None,
+        config_id: Optional[UUID] = None,
        message: Optional[str] = None,
    ):
        if message is None:
@@ -89,7 +89,7 @@ class ModelNotFoundError(ConfigurationError):
        self,
        model_id: Union[str, UUID],
        model_type: str,
-        config_id: Optional[int] = None,
+        config_id: Optional[UUID] = None,
        workspace_id: Optional[UUID] = None,
        message: Optional[str] = None,
    ):
@@ -112,7 +112,7 @@ class ModelInactiveError(ConfigurationError):
        model_id: Union[str, UUID],
        model_name: str,
        model_type: str,
-        config_id: Optional[int] = None,
+        config_id: Optional[UUID] = None,
        workspace_id: Optional[UUID] = None,
        message: Optional[str] = None,
    ):
@@ -136,7 +136,7 @@ class InvalidConfigError(ConfigurationError):
        message: str,
        field_name: Optional[str] = None,
        invalid_value: Optional[Any] = None,
-        config_id: Optional[int] = None,
+        config_id: Optional[UUID] = None,
        workspace_id: Optional[UUID] = None,
    ):
        context = {}
@@ -155,7 +155,7 @@ class InvalidConfigError(ConfigurationError):
 class MemoryConfigValidation(BaseModel):
    """Pydantic model for validating memory configuration data from database."""
    
-    config_id: int = Field(..., gt=0, description="Configuration ID must be positive")
+    config_id: UUID = Field(..., description="Configuration ID (UUID)")
    config_name: str = Field(..., min_length=1, max_length=255)
    workspace_id: UUID = Field(..., description="Workspace UUID")
    workspace_name: str = Field(..., min_length=1, max_length=255)
@@ -275,7 +275,7 @@ class ModelValidation(BaseModel):


 def validate_memory_config_data(
-    config_data: Dict[str, Any], config_id: Optional[int] = None
+    config_data: Dict[str, Any], config_id: Optional[UUID] = None
 ) -> MemoryConfigValidation:
    """Validate memory configuration data using Pydantic model."""
    try:
@@ -302,7 +302,7 @@ def validate_memory_config_data(


 def validate_workspace_data(
-    workspace_data: Dict[str, Any], config_id: Optional[int] = None
+    workspace_data: Dict[str, Any], config_id: Optional[UUID] = None
 ) -> WorkspaceValidation:
    """Validate workspace data using Pydantic model."""
    try:
@@ -331,7 +331,7 @@ def validate_workspace_data(


 def validate_model_data(
-    model_data: Dict[str, Any], config_id: Optional[int] = None
+    model_data: Dict[str, Any], config_id: Optional[UUID] = None
 ) -> ModelValidation:
    """Validate model data using Pydantic model."""
    try:
@@ -364,7 +364,7 @@ def validate_model_data(
 class MemoryConfig:
    """Immutable memory configuration loaded from database."""
    
-    config_id: int
+    config_id: UUID
    config_name: str
    workspace_id: UUID
    workspace_name: str
--- a/api/app/schemas/memory_perceptual_schema.py
+++ b/api/app/schemas/memory_perceptual_schema.py
@@ -4,7 +4,7 @@ from typing import Optional

 from pydantic import BaseModel, Field

-from app.models.memory_perceptual_model import PerceptualType, FileStorageType
+from app.models.memory_perceptual_model import PerceptualType, FileStorageService


 class PerceptualFilter(BaseModel):
@@ -38,12 +38,14 @@ class PerceptualMemoryItem(BaseModel):
    """感知记忆项"""
    id: uuid.UUID = Field(..., description="Unique memory ID")
    perceptual_type: PerceptualType = Field(..., description="Type of perception, e.g., text, audio, or video")
+    storage_service: FileStorageService = Field(..., description="Storage service for file")
    file_path: str = Field(..., description="File path in the storage service")
-    file_ext: str = Field(..., description="File extension")
    file_name: str = Field(..., description="File name")
+    file_ext: str = Field(..., description="File extension")
    summary: Optional[str] = Field(None, description="summary")
-    storage_type: FileStorageType = Field(..., description="Storage type for file")
+    meta_data: Optional[dict] = Field(None, description="Metadata information")
    created_time: int = Field(..., description="create time")
+
    topic: str = Field(..., description="topic")
    domain: str = Field(..., description="domain")
    keywords: list[str] = Field(..., description="keywords")
--- a/api/app/schemas/memory_reflection_schemas.py
+++ b/api/app/schemas/memory_reflection_schemas.py
@@ -1,5 +1,8 @@
+import uuid
+
 from pydantic import BaseModel, Field
-from typing import Optional
+from typing import Optional, Union
+from uuid import UUID
 from enum import Enum


@@ -9,7 +12,7 @@ class OptimizationStrategy(str, Enum):
    ACCURACY_FIRST = "accuracy_first"
    BALANCED = "balanced"
 class Memory_Reflection(BaseModel):
-    config_id: Optional[int] = None
+    config_id:  Union[uuid.UUID, int, str]  = None
    reflection_enabled: bool
    reflection_period_in_hours: str
    reflexion_range: Optional[str] = "partial"
--- a/api/app/schemas/memory_storage_schema.py
+++ b/api/app/schemas/memory_storage_schema.py
@@ -1,5 +1,5 @@
 """
-所有的内容是放错误地方了，应该放在models
+
 """

 from typing import Any, Optional, List, Dict, Literal, Union
@@ -8,20 +8,8 @@ import uuid
 from pydantic import BaseModel, Field, ConfigDict, field_validator, model_validator


-# ============================================================================
-# 原 UserInput 相关 Schema (保留原有功能)
-# ============================================================================
-class UserInput(BaseModel):
-    message: str
-    history: list[dict]
-    search_switch: str
-    group_id: str


-class Write_UserInput(BaseModel):
-    message: str
-    group_id: str
-

 # ============================================================================
 # 从 json_schema.py 迁移的 Schema
@@ -159,7 +147,7 @@ class ReflexionResultSchema(BaseModel):
 # Composite key identifying a config row
 class ConfigKey(BaseModel):  # 配置参数键模型
    model_config = ConfigDict(populate_by_name=True, extra="forbid")
-    config_id: int = Field("config_id", description="配置唯一标识（字符串）")
+    config_id:Union[uuid.UUID, int, str] = Field(..., description="配置唯一标识（UUID或int)")
    user_id: str = Field("user_id", description="用户标识（字符串）")
    apply_id: str = Field("apply_id", description="应用或场景标识（字符串）")

@@ -250,17 +238,17 @@ class ConfigParamsCreate(BaseModel):  # 创建配置参数模型（仅 body，
 class ConfigParamsDelete(BaseModel):  # 删除配置参数模型（请求体）
    model_config = ConfigDict(populate_by_name=True, extra="forbid")
    # config_name: str = Field("配置名称", description="配置名称（字符串）")
-    config_id: int = Field("配置ID", description="配置ID（字符串）")
+    config_id:Union[uuid.UUID, int, str]  = Field(..., description="配置ID（支持UUID、整数或字符串）")


 class ConfigUpdate(BaseModel):  # 更新记忆萃取引擎配置参数时使用的模型
-    config_id: Optional[int] = None
+    config_id: Union[uuid.UUID, int, str] = None
    config_name: str = Field("配置名称", description="配置名称（字符串）")
    config_desc: str = Field("配置描述", description="配置描述（字符串）")


 class ConfigUpdateExtracted(BaseModel):  # 更新记忆萃取引擎配置参数时使用的模型
-    config_id: Optional[int] = None
+    config_id:Union[uuid.UUID, int, str]  = None
    llm_id: Optional[str] = Field(None, description="LLM模型配置ID")
    embedding_id: Optional[str] = Field(None, description="嵌入模型配置ID")
    rerank_id: Optional[str] = Field(None, description="重排序模型配置ID")
@@ -327,14 +315,14 @@ class ConfigUpdateExtracted(BaseModel):  # 更新记忆萃取引擎配置参数

 class ConfigUpdateForget(BaseModel):  # 更新遗忘引擎配置参数时使用的模型
    # 遗忘引擎配置参数更新模型
-    config_id: Optional[int] = None
+    config_id:Union[uuid.UUID, int, str]  = None
    lambda_time: Optional[float] = Field(0.5, ge=0.0, le=1.0, description="最低保持度，0-1 小数；默认 0.5")
    lambda_mem: Optional[float] = Field(0.5, ge=0.0, le=1.0, description="遗忘率，0-1 小数；默认 0.5")
    offset: Optional[float] = Field(0.0, ge=0.0, le=1.0, description="偏移度，0-1 小数；默认 0.0")


 class ConfigPilotRun(BaseModel):  # 试运行触发请求模型
-    config_id: int = Field(..., description="配置ID（唯一）")
+    config_id:Union[uuid.UUID, int, str] = Field(..., description="配置ID（唯一，支持UUID、整数或字符串）")
    dialogue_text: str = Field(..., description="前端传入的对话文本，格式如 '用户: ...\nAI: ...' 可多行，试运行必填")
    model_config = ConfigDict(populate_by_name=True, extra="forbid")

@@ -342,7 +330,7 @@ class ConfigPilotRun(BaseModel):  # 试运行触发请求模型
 class ConfigFilter(BaseModel):  # 查询配置参数时使用的模型
    model_config = ConfigDict(populate_by_name=True, extra="forbid")

-    config_id: Optional[int] = None
+    config_id: Union[uuid.UUID, int, str] = None
    user_id: Optional[str] = None
    apply_id: Optional[str] = None

@@ -418,7 +406,7 @@ class ForgettingConfigResponse(BaseModel):
    """遗忘引擎配置响应模型"""
    model_config = ConfigDict(populate_by_name=True, extra="forbid")
    
-    config_id: int = Field(..., description="配置ID")
+    config_id: Union[uuid.UUID, int, str] = Field(..., description="配置ID（支持UUID、整数或字符串）")
    decay_constant: float = Field(..., description="衰减常数 d")
    lambda_time: float = Field(..., description="时间衰减参数")
    lambda_mem: float = Field(..., description="记忆衰减参数")
@@ -435,8 +423,8 @@ class ForgettingConfigResponse(BaseModel):
 class ForgettingConfigUpdateRequest(BaseModel):
    """遗忘引擎配置更新请求模型"""
    model_config = ConfigDict(populate_by_name=True, extra="forbid")
-    
-    config_id: int = Field(..., description="配置ID")
+
+    config_id: Union[uuid.UUID, int,str] = Field(..., description="配置唯一标识（UUID或int)")
    decay_constant: Optional[float] = Field(None, ge=0.0, le=1.0, description="衰减常数 d")
    lambda_time: Optional[float] = Field(None, ge=0.0, le=1.0, description="时间衰减参数")
    lambda_mem: Optional[float] = Field(None, ge=0.0, le=1.0, description="记忆衰减参数")
@@ -511,7 +499,7 @@ class ForgettingCurveRequest(BaseModel):
    
    importance_score: float = Field(0.5, ge=0.0, le=1.0, description="重要性分数（0-1）")
    days: int = Field(60, ge=1, le=365, description="模拟天数（默认60天）")
-    config_id: Optional[int] = Field(None, description="配置ID（可选，如果为None则使用默认配置）")
+    config_id: Union[uuid.UUID, int, str] = Field(..., description="配置唯一标识（UUID或int)")


 class ForgettingCurveResponse(BaseModel):
--- a/api/app/schemas/model_schema.py
+++ b/api/app/schemas/model_schema.py
@@ -1,10 +1,12 @@
-from pydantic import BaseModel, Field, field_serializer, ConfigDict
+from pydantic import BaseModel, Field, field_serializer, field_validator, ConfigDict
 from typing import Optional, List, Dict, Any
 import datetime
 import uuid

-from app.models.models_model import ModelProvider, ModelType
+from app.models.models_model import ModelProvider, ModelType, LoadBalanceStrategy
+from app.core.logging_config import get_business_logger

+schema_logger = get_business_logger()


 # ModelConfig Schemas
@@ -12,15 +14,19 @@ class ModelConfigBase(BaseModel):
    """模型配置基础Schema"""
    name: str = Field(..., description="模型显示名称", max_length=255)
    type: ModelType = Field(..., description="模型类型")
+    logo: Optional[str] = Field(None, description="模型logo图片URL", max_length=255)
    description: Optional[str] = Field(None, description="模型描述")
+    provider: str = Field(..., description="供应商")
    config: Optional[Dict[str, Any]] = Field({}, description="模型配置参数")
    is_active: bool = Field(True, description="是否激活")
    is_public: bool = Field(False, description="是否公开")
+    load_balance_strategy: Optional[str] = Field(LoadBalanceStrategy.NONE.value, description="负载均衡策略")


 class ApiKeyCreateNested(BaseModel):
    """用于在创建模型时内嵌创建API Key的Schema"""
    model_name: str = Field(..., description="模型实际名称", max_length=255)
+    description: Optional[str] = Field(None, description="备注")
    provider: ModelProvider = Field(..., description="API Key提供商")
    api_key: str = Field(..., description="API密钥", max_length=500)
    api_base: Optional[str] = Field(None, description="API基础URL", max_length=500)
@@ -30,10 +36,23 @@ class ApiKeyCreateNested(BaseModel):

 class ModelConfigCreate(ModelConfigBase):
    """创建模型配置Schema"""
-    api_keys: Optional[ApiKeyCreateNested] = Field(None, description="同时创建的API Key配置")
+    api_keys: Optional[List[ApiKeyCreateNested]] = Field(None, description="同时创建的API Key配置")
    skip_validation: Optional[bool] = Field(False, description="是否跳过配置验证")


+class CompositeModelCreate(BaseModel):
+    """创建组合模型Schema"""
+    name: str = Field(..., description="组合模型名称", max_length=255)
+    type: Optional[ModelType] = Field(None, description="模型类型")
+    logo: Optional[str] = Field(None, description="模型logo图片URL", max_length=255)
+    description: Optional[str] = Field(None, description="模型描述")
+    config: Optional[Dict[str, Any]] = Field({}, description="模型配置参数")
+    is_active: bool = Field(True, description="是否激活")
+    is_public: bool = Field(False, description="是否公开")
+    api_key_ids: List[uuid.UUID] = Field(..., description="绑定的API Key ID列表")
+    load_balance_strategy: Optional[str] = Field(default=LoadBalanceStrategy.NONE.value, description="负载均衡策略")
+
+
 class ModelConfigUpdate(BaseModel):
    """更新模型配置Schema"""
    name: Optional[str] = Field(None, description="模型显示名称", max_length=255)
@@ -53,22 +72,48 @@ class ModelConfig(ModelConfigBase):
    updated_at: datetime.datetime
    api_keys: List["ModelApiKey"] = []

+    @field_validator("api_keys", mode="after")
+    @classmethod
+    def filter_active_api_keys(cls, api_keys: List["ModelApiKey"]) -> List["ModelApiKey"]:
+        return [key for key in api_keys if key.is_active]
+
+    @field_serializer("created_at", when_used="json")
+    def _serialize_created_at(self, dt: datetime.datetime | None):
+        return int(dt.timestamp() * 1000) if dt else None
+
+    @field_serializer("updated_at", when_used="json")
+    def _serialize_updated_at(self, dt: datetime.datetime):
+        return int(dt.timestamp() * 1000) if dt else None
+

 # ModelApiKey Schemas
-class ModelApiKeyBase(BaseModel):
-    """API Key基础Schema"""
-    model_name: str = Field(..., description="模型实际名称", max_length=255)
+class ModelApiKeyCreateByProvider(BaseModel):
+    """基于供应商创建API Key Schema"""
    provider: ModelProvider = Field(..., description="API Key提供商")
    api_key: str = Field(..., description="API密钥", max_length=500)
    api_base: Optional[str] = Field(None, description="API基础URL", max_length=500)
-    config: Optional[Dict[str, Any]] = Field(None, description="API Key特定配置")
+    description: Optional[str] = Field(None, description="备注")
+    config: Optional[Dict[str, Any]] = Field({}, description="API Key特定配置")
+    is_active: bool = Field(True, description="是否激活")
+    priority: str = Field("1", description="优先级", max_length=10)
+    model_config_ids: Optional[List[uuid.UUID]] = Field(None, description="关联的模型配置ID列表")
+
+
+class ModelApiKeyBase(BaseModel):
+    """API Key基础Schema"""
+    model_name: str = Field(..., description="模型实际名称", max_length=255)
+    description: Optional[str] = Field(None, description="备注")
+    provider: ModelProvider = Field(..., description="API Key提供商")
+    api_key: str = Field(..., description="API密钥", max_length=500)
+    api_base: Optional[str] = Field(None, description="API基础URL", max_length=500)
+    config: Optional[Dict[str, Any]] = Field({}, description="API Key特定配置")
    is_active: bool = Field(True, description="是否激活")
    priority: str = Field("1", description="优先级", max_length=10)


 class ModelApiKeyCreate(ModelApiKeyBase):
    """创建API Key Schema"""
-    model_config_id: uuid.UUID = Field(..., description="模型配置ID")
+    model_config_ids: Optional[List[uuid.UUID]] = Field(None, description="关联的模型配置ID列表")


 class ModelApiKeyUpdate(BaseModel):
@@ -85,11 +130,54 @@ class ModelApiKeyUpdate(BaseModel):
 class ModelApiKey(ModelApiKeyBase):
    """API Key Schema"""
    id: uuid.UUID
-    model_config_id: uuid.UUID
    usage_count: str
    last_used_at: Optional[datetime.datetime]
    created_at: datetime.datetime
    updated_at: datetime.datetime
+    model_configs: Any = Field(default=None, exclude=True)
+    model_config_ids: List[uuid.UUID] = Field(default_factory=list, description="关联的模型配置ID列表")
+
+    def model_post_init(self, __context: Any) -> None:
+        """实例化后强制提取 model_configs 的ID到 model_config_ids"""
+        # 如果手动传入了 model_config_ids，不覆盖
+        if self.model_config_ids and len(self.model_config_ids) > 0:
+            return
+
+        # 从 model_configs 提取ID（只提取与 model_name 相同的非组合模型）
+        if self.model_configs is not None:
+            try:
+                # 情况1：ORM 对象列表（SQLAlchemy 关联）
+                if hasattr(self.model_configs, '__iter__') and not isinstance(self.model_configs, dict):
+                    self.model_config_ids = [
+                        mc.id for mc in self.model_configs
+                        if hasattr(mc, 'id') 
+                        and not getattr(mc, 'is_composite', False)
+                        and getattr(mc, 'name', None) == self.model_name
+                    ]
+                # 情况2：字典列表
+                elif isinstance(self.model_configs, list):
+                    self.model_config_ids = [
+                        mc['id'] if isinstance(mc, dict) else mc.id
+                        for mc in self.model_configs
+                        if ((isinstance(mc, dict) 
+                             and 'id' in mc 
+                             and not mc.get('is_composite', False)
+                             and mc.get('name') == self.model_name) or 
+                            (hasattr(mc, 'id') 
+                             and not getattr(mc, 'is_composite', False)
+                             and getattr(mc, 'name', None) == self.model_name))
+                    ]
+            except Exception as e:
+                schema_logger.warning(f"提取 model_config_ids 失败：{e}")
+                self.model_config_ids = []
+
+    model_config = ConfigDict(
+        from_attributes=True,  # 支持从 ORM 解析
+        arbitrary_types_allowed=True,  # 允许任意类型（ORM 对象）
+        populate_by_name=True,  # 按属性名匹配字段
+        validate_assignment=True  # 确保赋值触发校验
+    )
+

    @field_serializer("created_at", when_used="json")
    def _serialize_created_at(self, dt: datetime.datetime):
@@ -98,15 +186,12 @@ class ModelApiKey(ModelApiKeyBase):
    @field_serializer("updated_at", when_used="json")
    def _serialize_updated_at(self, dt: datetime.datetime):
        return int(dt.timestamp() * 1000) if dt else None
-    
-    model_config = ConfigDict(from_attributes=True)

    @field_serializer("last_used_at", when_used="json")
    def _serialize_last_used_at(self, dt: datetime.datetime):
        return int(dt.timestamp() * 1000) if dt else None


-# 查询和响应Schemas
 class ModelConfigQuery(BaseModel):
    """模型配置查询Schema"""
    type: Optional[List[ModelType]] = Field(None, description="模型类型筛选（支持多个）")
@@ -117,6 +202,17 @@ class ModelConfigQuery(BaseModel):
    page: int = Field(1, description="页码", ge=1)
    pagesize: int = Field(10, description="每页数量", ge=1, le=100)

+
+# 查询和响应Schemas
+class ModelConfigQueryNew(BaseModel):
+    """模型配置查询Schema"""
+    type: Optional[List[ModelType]] = Field(None, description="模型类型筛选（支持多个）")
+    provider: Optional[ModelProvider] = Field(None, description="提供商筛选(通过API Key)")
+    is_active: Optional[bool] = Field(None, description="激活状态筛选")
+    is_public: Optional[bool] = Field(None, description="公开状态筛选")
+    is_composite: Optional[bool] = Field(None, description="组合模型筛选")
+    search: Optional[str] = Field(None, description="搜索关键词", max_length=255)
+
 class ModelMarketplace(BaseModel):
    """模型广场响应Schema"""
    llm_models: List[ModelConfig] = []
@@ -159,4 +255,53 @@ class ModelValidateResponse(BaseModel):


 # 更新前向引用
-ModelConfig.model_rebuild()
+ModelConfig.model_rebuild()
+
+
+# ModelBase Schemas
+class ModelBaseCreate(BaseModel):
+    """创建基础模型Schema"""
+    name: str = Field(..., description="模型唯一标识", max_length=255)
+    type: ModelType = Field(..., description="模型类型")
+    provider: ModelProvider = Field(..., description="提供商")
+    logo: Optional[str] = Field(None, description="模型logo图片URL", max_length=255)
+    description: Optional[str] = Field(None, description="模型描述")
+    is_official: bool = Field(True, description="是否供应商官方模型")
+    tags: List[str] = Field(default_factory=list, description="模型标签")
+
+
+class ModelBaseUpdate(BaseModel):
+    """更新基础模型Schema"""
+    name: Optional[str] = Field(None, description="模型唯一标识", max_length=255)
+    type: Optional[ModelType] = Field(None, description="模型类型")
+    provider: Optional[ModelProvider] = Field(None, description="提供商")
+    logo: Optional[str] = Field(None, description="模型logo图片URL", max_length=255)
+    description: Optional[str] = Field(None, description="模型描述")
+    is_deprecated: Optional[bool] = Field(None, description="是否弃用")
+    is_official: Optional[bool] = Field(None, description="是否供应商官方模型")
+    tags: Optional[List[str]] = Field(None, description="模型标签")
+
+
+class ModelBase(BaseModel):
+    """基础模型Schema"""
+    model_config = ConfigDict(from_attributes=True)
+    
+    id: uuid.UUID
+    name: str
+    type: str
+    provider: str
+    logo: Optional[str]
+    description: Optional[str]
+    is_deprecated: bool
+    is_official: bool
+    tags: List[str]
+    add_count: int
+
+
+class ModelBaseQuery(BaseModel):
+    """基础模型查询Schema"""
+    type: Optional[ModelType] = Field(None, description="模型类型")
+    provider: Optional[ModelProvider] = Field(None, description="提供商")
+    is_official: Optional[bool] = Field(None, description="是否官方模型")
+    is_deprecated: Optional[bool] = Field(None, description="是否弃用")
+    search: Optional[str] = Field(None, description="搜索关键词", max_length=255)
--- a/api/app/schemas/multi_agent_schema.py
+++ b/api/app/schemas/multi_agent_schema.py
@@ -4,7 +4,7 @@ import datetime
 from typing import Optional, List, Dict, Any, Union
 from pydantic import BaseModel, Field, ConfigDict, field_serializer

-from app.schemas import ModelParameters
+from app.schemas.app_schema import ModelParameters


 # ==================== 子 Agent 配置 ====================
--- a/api/app/schemas/release_share_schema.py
+++ b/api/app/schemas/release_share_schema.py
@@ -1,7 +1,7 @@
 import uuid
 import datetime
 from typing import Optional, List, Dict, Any
-from pydantic import BaseModel, Field, ConfigDict, field_serializer
+from pydantic import BaseModel, Field, ConfigDict, field_serializer, field_validator


 # ---------- Input Schemas ----------
@@ -88,6 +88,18 @@ class SharedReleaseInfo(BaseModel):
    # 嵌入配置
    allow_embed: bool

+    @field_validator("config", mode="before")
+    @classmethod
+    def parse_config(cls, v):
+        """处理 config 字段，如果是字符串则解析为字典"""
+        if isinstance(v, str):
+            import json
+            try:
+                return json.loads(v)
+            except json.JSONDecodeError:
+                return {}
+        return v if v is not None else {}
+

 class EmbedCode(BaseModel):
    """嵌入代码"""