Commit Graph

107 Commits

Author SHA1 Message Date
乐力齐
0a73b18823 Feature/return memoryconfig (#89)
* [add]Newly added: Memory configuration for returning results

* [add]Newly added: Memory configuration for returning results

* [changes]Based on the improvement of AI review
2026-01-13 14:55:12 +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
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
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
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
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
25ce86ae93 feat(agent tool): mcp tool repair 2026-01-07 18:59:28 +08:00
Ke Sun
b3f8de3062 Feature/behavior analysis (#53)
* init behavior analysis

* init behavior analysis

* feat(implicit-memory): add implicit memory analytics system
2026-01-07 18:14:25 +08:00
Mark
28eccd6ce9 Merge pull request #50 from SuanmoSuanyangTechnology/fix/workflow
Fix/workflow
2026-01-07 18:04:53 +08:00
mengyonghao
701d506c1f fix(memory): enable perceptual memory API and database configuration 2026-01-07 17:54:46 +08:00
Mark
04d79ac70f Merge branch 'develop' of github.com:SuanmoSuanyangTechnology/MemoryBear into develop 2026-01-07 17:49:45 +08:00
lixinyue11
bcb3d587a1 dev新增短期记忆功能 (#47)
* dev新增短期记忆功能

* dev新增短期记忆功能

* dev新增短期记忆功能

* dev新增短期记忆功能

* dev新增短期记忆功能

* dev新增短期记忆功能

* dev新增短期记忆功能
2026-01-07 16:36:11 +08:00
Eternity
c52b360068 Feature/memory perceptual (#48)
* perf(workflow): pass JSON data to HTTP node as a string

* perf(prompt_opt): simplify log output

* feat(memory): add perceptual memory page API and related database schema

* perf(log): clean up API exception log output

* perf(memory): simplify perceptual memory timeline response by removing metadata
2026-01-07 16:00:22 +08:00
Mark
cd76ccadc5 [modify] handoffs test 2026-01-07 15:51:12 +08:00
Mark
ba2220d7c8 [add ] handoffs service and test 2026-01-07 14:58:23 +08:00
谢俊男
26947d85ae feat(agent tool): agent tool bug fix 2026-01-06 20:05:18 +08:00
谢俊男
eb51e04a18 Merge branch 'refs/heads/develop' into feature/20260105_xjn
# Conflicts:
#	api/app/services/app_chat_service.py
2026-01-06 19:46:36 +08:00
Mark
499d549e41 Merge branch 'develop' of github.com:SuanmoSuanyangTechnology/MemoryBear into develop 2026-01-06 18:59:01 +08:00
Mark
eabaae4a8f [fix] model parameter error 2026-01-06 18:58:36 +08:00
乐力齐
3183f39535 Fix/Restore user information archive and one-sentence summary (#37)
* [fix]fix memory insights

* [fix]fix memory insights

* [fix]Based on the correction of the code by sourcery-ai

* [fix]Restore user information archive and one-sentence summary
2026-01-06 18:03:28 +08:00
Mark
6783375a14 [fix] model_parameters 2026-01-06 17:55:42 +08:00
Mark
a940717ed0 [add] publish and share run add workflow type app 2026-01-06 17:11:52 +08:00
谢俊男
492401f9b7 feat(agent tool): add agent tool plugin 2026-01-06 15:25:25 +08:00
Mark
190155f438 Merge branch 'develop' of github.com:SuanmoSuanyangTechnology/MemoryBear into develop 2026-01-06 14:44:13 +08:00
Mark
f59f508c4d [fix] public share agent run 2026-01-06 14:43:23 +08:00
Eternity
79d035ac02 fix(prompt_optim): allow streaming output to raise exceptions (#34) 2026-01-06 14:27:51 +08:00
乐力齐
a0f19ace92 Fix/memory insights (#30)
* [fix]fix memory insights

* [fix]fix memory insights

* [fix]Based on the correction of the code by sourcery-ai
2026-01-06 14:05:15 +08:00
Mark
85c7e531e4 Merge branch 'develop' of github.com:SuanmoSuanyangTechnology/MemoryBear into develop 2026-01-06 13:58:52 +08:00
Mark
ed62e92da6 [fix] miss agent_config 2026-01-06 13:56:40 +08:00
mengyonghao
05ec76f940 perf(prompt_opt): optimize streaming output structure and add variable parsing 2026-01-05 17:31:28 +08:00
Eternity
78207aca34 feat(workflow): add memory read and write node (#24) 2026-01-05 15:57:04 +08:00
谢俊男
c8b6e22143 feat(home page): optimize the statistical interface 2026-01-05 14:38:36 +08:00
乐力齐
1fc81d1347 Merge #105 into develop from feature/user-summary
[feature]用户记忆内容扩展

* feature/user-summary: (11 commits squashed)

  - [ADD]Support graph search

  - Merge #82 into develop from feature/20251219_myh
    
    fix: correct function naming for memory retrieval
    
    * feature/20251219_myh: (2 commits squashed)
    
      - perf(workflow): adjust default template to be compatible with frontend format
    
      - fix: correct function naming for memory retrieval
    
    Signed-off-by: Eternity <1533512157@qq.com>
    Reviewed-by: zhuwenhui5566@163.com <zhuwenhui5566@163.com>
    Reviewed-by: aliyun6762716068 <accounts_68cb7c6b61f5dcc4200d6251@mail.teambition.com>
    Merged-by: aliyun6762716068 <accounts_68cb7c6b61f5dcc4200d6251@mail.teambition.com>
    
    CR-link: https://codeup.aliyun.com/redbearai/python/redbear-mem-open/change/82

  - [fix]parsed excel document error:float division by zero

  - [fix]parsed excel document error:float division by zero

  - [fix]parsed excel document error:float division by zero

  - [fix]parsed excel document error:float division by zero

  - [changes]1.Fix the Neo4j alert;2.Separate the functions of &quot;insight&quot; and &quot;summary&quot;

  - [feature]Develop user summary

  - [feature]Developing Memory Insights

  - [changes]Modify the data types and processing procedures of the configuration parameters

  - [fix]fix

Signed-off-by: 乐力齐 <accounts_690c7b0af9007d7e338af636@mail.teambition.com>
Reviewed-by: aliyun6762716068 <accounts_68cb7c6b61f5dcc4200d6251@mail.teambition.com>
Merged-by: aliyun6762716068 <accounts_68cb7c6b61f5dcc4200d6251@mail.teambition.com>

CR-link: https://codeup.aliyun.com/redbearai/python/redbear-mem-open/change/105
2026-01-05 04:34:12 +00:00
乐力齐
e8a5cfe7e3 Merge #85 into develop from feature/actr-forget
[feature]actr-记忆遗忘需求开发

* feature/actr-forget: (12 commits squashed)

  - [feature]
    1.Extended fields of the date_config table;
    2.New activation value calculation has been added, and the ACTR parameter has been introduced in Neo4j.

  - [feature]1.Create a forgetting strategy executor;2.Create the forgetting scheduler

  - [feature]Introduce activation values for retrieval, and develop a two-stage retrieval reordering process

  - [feature]
    1.Extended fields of the date_config table;
    2.New activation value calculation has been added, and the ACTR parameter has been introduced in Neo4j.

  - [feature]1.Create a forgetting strategy executor;2.Create the forgetting scheduler

  - [feature]Introduce activation values for retrieval, and develop a two-stage retrieval reordering process

  - Merge branch &#39;feature/actr-forget&#39; of codeup.aliyun.com:redbearai/python/redbear-mem-open into feature/actr-forget

  - [fix]Eliminate the interference caused by redundant code

  - [feature]
    1.Extended fields of the date_config table;
    2.New activation value calculation has been added, and the ACTR parameter has been introduced in Neo4j.

  - [feature]1.Create a forgetting strategy executor;2.Create the forgetting scheduler

  - [feature]Introduce activation values for retrieval, and develop a two-stage retrieval reordering process

  - Merge branch &#39;feature/actr-forget&#39; of codeup.aliyun.com:redbearai/python/redbear-mem-open into feature/actr-forget

Signed-off-by: 乐力齐 <accounts_690c7b0af9007d7e338af636@mail.teambition.com>
Reviewed-by: aliyun6762716068 <accounts_68cb7c6b61f5dcc4200d6251@mail.teambition.com>
Merged-by: aliyun6762716068 <accounts_68cb7c6b61f5dcc4200d6251@mail.teambition.com>

CR-link: https://codeup.aliyun.com/redbearai/python/redbear-mem-open/change/85
2026-01-05 04:30:36 +00:00
lixiangcheng1
d299c39c55 Merge branch 'feature/20251219_lxc' into develop 2026-01-05 12:19:03 +08:00
lixiangcheng1
dd5e21a653 [ADD] add open api for knowledge、document、file、chunk、retrieval 2026-01-05 12:18:31 +08:00
mengyonghao
63f0fa5da2 Merge branch 'develop' into feature/20251219_myh
# Conflicts:
#	api/app/core/workflow/executor.py
#	api/app/core/workflow/nodes/node_factory.py
#	api/app/core/workflow/nodes/question_classifier/node.py
2026-01-05 11:10:01 +08:00
mengyonghao
eaf2437633 feat(prompt_opt): support streaming output for prompt optimization API 2026-01-05 10:53:53 +08:00
mengyonghao
bf6ede64bd feat(workflow): add support for passing workspace ID 2026-01-05 10:51:57 +08:00
朱文辉
e1bc6b8597 Merge #102 into develop from feature/20251219_xjn
feat(workflow_node): question classifier node optimization

* feature/20251219_xjn: (9 commits)
  feat(tool system): The specific method for obtaining the tool and the parameters to be passed
  feat(tool system): add mcp testing services
  Merge branch &#39;refs/heads/develop&#39; into feature/20251219_xjn
  feat(tool system): add all methods for obtaining the tool
  feat(tool system): add workflow tool nodes
  Merge branch &#39;refs/heads/develop&#39; into feature/20251219_xjn
  feat(home page): add statistical interface
  Merge branch &#39;refs/heads/develop&#39; into feature/20251219_xjn
  feat(workflow_node): question classifier node optimization

Signed-off-by: 谢俊男 <accounts_6853d0ea6f8174722fb0c8f1@mail.teambition.com>
Reviewed-by: zhuwenhui5566@163.com <zhuwenhui5566@163.com>
Merged-by: zhuwenhui5566@163.com <zhuwenhui5566@163.com>

CR-link: https://codeup.aliyun.com/redbearai/python/redbear-mem-open/change/102
2026-01-05 10:46:53 +08:00
Mark
3fe2ef6611 [modify] share chat 2026-01-04 20:51:37 +08:00
Mark
3a3cd59d8e [fix] app api multi agent call 2026-01-04 20:08:19 +08:00
谢俊男
a8c5368d49 feat(home page): add statistical interface 2026-01-04 15:36:24 +08:00