adai/MemoryBear
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
606 Commits 37 Branches 16 Tags
95b61e99729fa1952b4b9c7d4ddd7ac53da3ffd6
Commit Graph

337 Commits

Author SHA1 Message Date
mengyonghao
95b61e9972 perf(workflow): optimize default value of rerank_id configuration 2026-01-14 10:55:05 +08:00
mengyonghao
84e24ede04 fix(workflow): move node config validation to runtime for proper error handling 2026-01-14 10:47:38 +08:00
mengyonghao
7438fedd6b fix(workflow): fix workflow state not updating correctly after streaming runs 2026-01-14 10:46:33 +08:00
mengyonghao
4448296e7b feat(workflow): officially support workflow session variables 2026-01-14 10:46:23 +08:00
mengyonghao
e60bc37fbf fix(workflow): set default empty value for custom variables in start node 2026-01-13 17:28:41 +08:00
mengyonghao
ada63d9f5c fix(workflow): fix typo in key value 2026-01-13 15:40:22 +08:00
mengyonghao
8f114b0dfa fix(workflow): support reordering without a rerank model in knowledge base 2026-01-13 15:34:57 +08:00
mengyonghao
9427584825 fix(workflow): render jinja variables with actual values in non-strict mode 2026-01-13 15:10:01 +08:00
mengyonghao
592c2ac217 fix(workflow): handle missing environment variable defaults 2026-01-13 15:09:06 +08:00
mengyonghao
dd7abc0d27 fix(workflow): use int type for memory node config id 2026-01-13 15:06:12 +08:00
mengyonghao
fe4a53563e fix(workflow): use loose rendering for end-node variables 2026-01-13 15:04:44 +08:00
Mark
c4addc7e54 Merge pull request #82 from SuanmoSuanyangTechnology/feat/memory-perceptual 
Feat/memory perceptual
 2026-01-12 21:16:14 +08:00
mengyonghao
6a0cbd7d8e perf(memory): optimize working memory summarization prompt 2026-01-12 21:14:45 +08:00
mengyonghao
38253fa49a feat(memory): enrich perceptual memory timeline content 2026-01-12 21:14:12 +08:00
mengyonghao
c1fba39496 feat(workflow): add conversation_id parameter 2026-01-12 21:13:21 +08:00
Mark
d3b093c09d Merge branch 'develop' of github.com:SuanmoSuanyangTechnology/MemoryBear into develop 2026-01-12 21:11:09 +08:00
Mark
1ce5020c73 [fix] handoff limit error 2026-01-12 21:10:58 +08:00
lixinyue11
89b7d94bd1 Flx/develop config (#81) 
* 修改BUG，读取接口的end_user_id获取不准确修复，statements检索内容为空需要给空列表

* 反思的默认部分检索替换为partial

* 反思的默认部分检索替换为partial

* 反思的默认部分检索替换为partial

* 情绪归类

* 情绪归类

* 情绪归类

* 情绪归类

* 情绪归类

* 情绪归类
 2026-01-12 20:50:09 +08:00
mengyonghao
6a78ed7c8a fix(workflow): fix default values in parameter extraction node and incorrect value retrieval in comparison operations 2026-01-12 20:32:17 +08:00
Mark
a006bc94b9 Merge pull request #74 from SuanmoSuanyangTechnology/feature/agent-tool_xjn 
feat(draft run)
 2026-01-12 20:30:20 +08:00
乐力齐
4e1ff99cc5 [fix]Restore episodic memory and retrieve memory type (#78) 2026-01-12 19:02:25 +08:00
乐力齐
d477520b67 [fix]Return the "statement" attribute (#76) 
* [fix]Return the "statement" attribute

* [fix]Trigger the forgetting cycle using the end_user_id
 2026-01-12 18:47:40 +08:00
lixinyue11
17318d8205 Flx/develop config (#77) 
* 修改BUG，读取接口的end_user_id获取不准确修复，statements检索内容为空需要给空列表

* 反思的默认部分检索替换为partial

* 反思的默认部分检索替换为partial

* 反思的默认部分检索替换为partial
 2026-01-12 18:46:07 +08:00
lixinyue11
5b05009123 修改BUG，读取接口的end_user_id获取不准确修复，statements检索内容为空需要给空列表 (#75) 2026-01-12 17:40:49 +08:00
Mark
6dbc411adb Merge branch 'develop' of github.com:SuanmoSuanyangTechnology/MemoryBear into develop 2026-01-12 17:20:49 +08:00
Mark
63f965fafe [fix] error with tools ,agent no response 2026-01-12 17:20:39 +08:00
谢俊男
a10e07bd60 feat(draft run): the judgment tool list is a list or an object 2026-01-12 16:58:38 +08:00
谢俊男
b00049e94e feat(home page and apps): 
1. Add a version introduction to the homepage;
2. Query the app list. When the 'ids' parameter is provided, retrieve the specified applications by splitting them with commas, without pagination
 2026-01-12 16:22:34 +08:00
Mark
f2390412d2 [fix] Pydantic save json error 2026-01-12 15:59:10 +08:00
Mark
7a0746cf4e [add] migration script 2026-01-12 15:30:22 +08:00
lixinyue11
eb7374cedc Fix/develop memory deail (#71) 
* 新增记忆空间详情

* 新增记忆空间详情

* 新增记忆关联的数量

* 修改记忆时间线

* 修改记忆时间线

* 修改记忆时间线

* Parameterize elementId in Cypher query

* 关系演化，互动频率优化

* 关系演化，互动频率优化

* 关系演化，互动频率优化

* 关系演化，互动频率优化

* 关系演化，互动频率优化

* 关系演化，互动频率优化

* 修改日期

* 修改日期

* 修改日期

* 修改日期

* 修改日期

* 修改日期

* 修改日期

* 输出删除多嵌套的data

---------

Co-authored-by: Ke Sun <33739460+keeees@users.noreply.github.com>
 2026-01-12 13:55:21 +08:00
lixinyue11
f6ca6a547f Fix/develop memory deail (#69) 
* 新增记忆空间详情

* 新增记忆空间详情

* 新增记忆关联的数量

* 修改记忆时间线

* 修改记忆时间线

* 修改记忆时间线

* Parameterize elementId in Cypher query

* 关系演化，互动频率优化

* 关系演化，互动频率优化

* 关系演化，互动频率优化

* 关系演化，互动频率优化

* 关系演化，互动频率优化

* 关系演化，互动频率优化

---------

Co-authored-by: Ke Sun <33739460+keeees@users.noreply.github.com>
 2026-01-12 12:28:17 +08:00
乐力齐
9722601bae Feature/episodic memory (#70) 
* [feature]episodic memory

* [feature]episodic memory

* [changes]AI review and modify code

* [feature]Explicit memory

* [feature]Explicit memory
 2026-01-12 12:27:33 +08:00
Eternity
2a12be310d Feature/memory work (#68) 
* feat(memory): add conversation title to conversation list response for frontend display

* feat(memory): optimize conversation retrieval, enable working memory to return conversation question summaries

* fix(memory): fix conversation re-generation logic

* style(desc): improve description of get_conversation function
 2026-01-12 12:16:04 +08:00
Eternity
d9f03a7e94 feat(memory): add conversation title to conversation list response for frontend display (#67) 2026-01-12 10:24:30 +08:00
乐力齐
539821454a Feature/episodic memory (#64) 
* [feature]episodic memory

* [feature]episodic memory

* [changes]AI review and modify code
 2026-01-10 16:35:32 +08:00
lixinyue11
7d28717030 Fix/develop memory deail (#63) 
* 新增记忆空间详情

* 新增记忆空间详情

* 新增记忆关联的数量

* 修改记忆时间线

* 修改记忆时间线

* 修改记忆时间线

* Parameterize elementId in Cypher query

---------

Co-authored-by: Ke Sun <33739460+keeees@users.noreply.github.com>
 2026-01-10 12:37:11 +08:00
Mark
5cb7962593 [add] migration script 2026-01-08 19:16:55 +08:00
Eternity
c5dd09cf50 Feature/memory work (#61) 
* refactor(conversation): separate service and repository layers for conversation module

- Split ConversationService and repository/UnitOfWork layers
- Service layer now only handles business logic and orchestration
- Repository layer handles all direct database operations
- UnitOfWork encapsulates transactional operations for messages
- Ensured all public methods have clear English docstrings with arguments, return values, and exceptions

* feat(memory): implement work memory endpoints and services

- Added API routes for conversation count, conversation list, messages, and detail.
- Integrated ConversationService for database queries and LLM-based summary generation.

* feat(memory): implement work memory endpoints and services

- Added API routes for conversation count, conversation list, messages, and detail.
- Integrated ConversationService for database queries and LLM-based summary generation.

* feat(workflow): fix issues causing workflow failures

if-else None value error
knowledge empty list rerank
end node output none node value
assigner input none value

* feat(memory): convert memory file creation time to timestamp and include title and first-line fields in file type

* fix(memory): fix serialization output and default value issues

* fix(workflow): fix issue with hybrid search logic in knowledge retrieval node
 2026-01-08 18:48:29 +08:00
lixinyue11
009ceefa30 新增记忆空间详情 (#58) 
* 新增记忆空间详情

* 新增记忆空间详情
 2026-01-08 17:51:49 +08:00
Ke Sun
7167c2002f feat(implicit memory): upgrade pydantic v2 compatibility and confidence level handling 
- Replace deprecated `.dict()` with `.model_dump(mode='json')` for pydantic v2 compatibility
- Convert confidence level from enum-based strings to numerical values (0-100 scale)
- Add confidence level mapping in controller (high: 85, medium: 50, low: 20)
- Update dimension analyzer to handle both string and numeric confidence inputs
- Refactor habit analyzer confidence level validation logic
- Remove ConfidenceLevel enum import and replace with integer-based approach
- Update memory config validators for numerical confidence level support
- Ensure all implicit memory schemas use model_dump for serialization
- Improve type consistency across memory analytics modules
 2026-01-08 17:50:01 +08:00
lixinyue11
e05f33b286 修复RAG集群BUG (#59) 2026-01-08 16:13:22 +08:00
Mark
50480dc506 [add] migration script 2026-01-08 15:21:23 +08:00
乐力齐
a4af0f7432 Feature/actr forget (#55) 
* [changes]Request to remove 'config_id' has been received.

* [add]Add the access history record table

* [changes]Request to remove 'config_id' has been received.

* [add]Add the access history record table

* [add]Obtain the record of the forgetting trend

* [changes]Based on the AI's suggestion, make the necessary modifications.
 2026-01-08 15:15:13 +08:00
谢俊男
4ac010eda7 feat(agent tool): mcp and custom tool repair 2026-01-08 14:00:28 +08:00
lixiangcheng1
7165d53982 [fix]Clearly debug the model API key 2026-01-07 20:45:23 +08:00
Mark
2360ef64de Merge branch 'develop' of github.com:SuanmoSuanyangTechnology/MemoryBear into develop 2026-01-07 19:35:39 +08:00
Mark
e6a1643bea [modfiy] default_model_config_id miss error 2026-01-07 19:35:29 +08:00
谢俊男
25ce86ae93 feat(agent tool): mcp tool repair 2026-01-07 18:59:28 +08:00
Mark
99b4a17f43 [fix] update config 2026-01-07 18:35:18 +08:00