adai/MemoryBear
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
2,546 Commits 37 Branches 16 Tags
853ce6f4e17ff4bcb0131cb4c3f56f9d3d9decf7
Commit Graph

553 Commits

Author SHA1 Message Date
Timebomb2018
264183cec2 feat(models): support reasoning_content streaming 2026-04-01 15:47:43 +08:00
Timebomb2018
9561578a2a Merge branch 'refs/heads/develop' into feature/agent-tool_xjn 
# Conflicts:
#	api/app/core/agent/langchain_agent.py
#	api/app/core/tools/mcp/client.py
 2026-04-01 15:27:34 +08:00
Ke Sun
3ea42ac27f Merge remote-tracking branch 'origin/release/v0.2.9' into develop 2026-03-31 19:16:13 +08:00
Ke Sun
3ea57d1cb0 Merge pull request #724 from SuanmoSuanyangTechnology/feature/memory-agent-perceptual 
feat(agent, memory): add agent-perceived memory writing
 2026-03-31 12:03:47 +08:00
Timebomb2018
876c39b1b0 fix(app): 
1. Token consumption of the omni model;
2. Token consumption of the cluster includes sub-agents
 2026-03-30 18:37:09 +08:00
lanceyq
c90b58bbcd [fix] The "write_tools" module actively shuts down the client, and it closes before the task event loop is completed. 2026-03-30 18:19:50 +08:00
lanceyq
052c7c19b3 [fix] Avoid unnecessary index creation costs 2026-03-30 17:44:02 +08:00
lanceyq
e15af5a2ba [fix] Create a complete index 2026-03-30 17:44:02 +08:00
Timebomb2018
9d91453200 fix(mcp): Addressing the issue of asynchronous connections for the MCP 2026-03-30 17:28:13 +08:00
Ke Sun
ea8db7cd90 Merge pull request #728 from SuanmoSuanyangTechnology/fix/aliases 
[fix] Refusing the user, I went to "other_name"
 2026-03-30 17:26:22 +08:00
Eternity
8dd24533bf fix(memory,task): add Redis fair lock for ordered memory writes 2026-03-30 17:20:54 +08:00
Ke Sun
533000030f Revert "fix(memory,task): add Redis fair lock for ordered memory writes" 2026-03-30 17:16:14 +08:00
Ke Sun
f7e89af9d2 fix(app): memory config initialization for end users 
- Add memory_config_id extraction and assignment when creating new end users in public share chat
- Introduce get_or_create_end_user_with_config method to handle memory config setup in single transaction
- Add batch_update_memory_config_id_by_app method for bulk updating end user memory configs
- Rename _update_endusers_memory_config_by_workspace to _update_endusers_memory_config_by_app for correct scope
- Update app publish flow to use app_id instead of workspace_id for memory config updates
- Remove unused actual_end_user_id variable in langchain_agent
- Ensures end users are properly associated with memory configs on creation and during app updates
 2026-03-30 16:44:43 +08:00
Eternity
e9ad13504a fix(memory,task): add Redis fair lock for ordered memory writes 2026-03-30 16:06:23 +08:00
lanceyq
dae7431075 [fix] Refusing the user, I went to "other_name" 2026-03-30 15:39:53 +08:00
Eternity
7acb7045f0 feat(agent, memory): add agent-perceived memory writing 2026-03-30 13:39:49 +08:00
lanceyq
5c11da6a2e [changes] Semantic pruning enables the file to pass through 2026-03-27 19:25:17 +08:00
lanceyq
289b1989e5 [changes] Semantic pruning enables the file to pass through 2026-03-27 19:13:38 +08:00
Ke Sun
f878846364 Merge pull request #716 from SuanmoSuanyangTechnology/fix/mem-cache 
feat(cache): Add thread-safe Redis client and enable activity stats c…
 2026-03-27 17:35:14 +08:00
Ke Sun
4e9b5736b1 feat(cache): Add thread-safe Redis client and enable activity stats cache 
- Add get_thread_safe_redis() function with thread-local storage and PID checking to prevent "Future attached to a different loop" errors in Celery thread and prefork pools
- Implement health_check_interval=30 to prevent stale connection errors after fork
- Uncomment and enable ActivityStatsCache module in cache/memory/__init__.py
- Uncomment ActivityStatsCache implementation in activity_stats_cache.py and update to use get_thread_safe_redis()
- Update interest_memory.py to use thread-safe Redis client
- Update write_tools.py to use thread-safe Redis client
- Remove redundant Chinese comments from aioRedis.py for cleaner code
- Ensures safe Redis operations across different execution contexts and Celery worker configurations
 2026-03-27 16:54:47 +08:00
Timebomb2018
46fa99a8b8 fix(app): 
1.Handling of large file upload issues;
2. Handling of abnormal display of conversation titles when the opening remarks function is enabled
 2026-03-27 16:27:09 +08:00
lanceyq
9730c5ce0f [changes] Construct the final return structure directly. 2026-03-27 12:24:52 +08:00
Eternity
bca43fcc75 perf(workflow): expose extract_document_text as instance method, optimize knowledge base parallel search 
- Change extract_document_text from private to instance method in multimodal service for external access
- Optimize knowledge base search logic to improve parallel retrieval performance
 2026-03-27 12:23:18 +08:00
lanceyq
8ba0a74473 [changes] Specified element quantity 2026-03-27 12:03:48 +08:00
Eternity
7fd00009a2 perf(workflow): introduce LazyDict to reduce variable serialization, optimize regex to reduce compilation 
- Use LazyDict for deferred serialization, improving performance
- Reuse regex patterns to avoid repeated compilation
 2026-03-27 12:00:30 +08:00
lanceyq
ac7c891ded 活动统计 2026-03-26 20:44:55 +08:00
Ke Sun
a5bce221bd refactor(memory-api): migrate end user creation to authenticated API endpoint 
- Remove unauthenticated end_user_controller and its router registration
- Move end user creation logic to authenticated memory_api_controller endpoint
- Add create_end_user method to MemoryAPIService with workspace authorization
- Fix retrieve_nodes import in read_graph to use correct function reference
- Consolidate end user management under authenticated memory API with API key scoping
 2026-03-26 20:12:11 +08:00
lanceyq
a874cc70a4 [changes] Add the content for client initialization failure alarm 2026-03-26 18:18:23 +08:00
lanceyq
2319432182 [changes] Set up Celery tasks to perform clustering 2026-03-26 18:18:23 +08:00
Ke Sun
7556468c6e Merge pull request #686 from SuanmoSuanyangTechnology/feature/user-alias 
Feature/user alias
 2026-03-26 17:34:00 +08:00
Mark
dfc0ee9424 Merge pull request #695 from SuanmoSuanyangTechnology/feature/agent-tool_xjn 
feat(workflow)
 2026-03-26 16:24:43 +08:00
Timebomb2018
1df3fc416a feat(workflow): Document extraction node 2026-03-26 16:19:40 +08:00
Eternity
6223b80cc4 fix(workflow): Fix LLM node, resolve abnormal field reading issue in message caching functionality 2026-03-26 16:19:01 +08:00
Timebomb2018
68489f1b28 feat(workflow): Document extraction node 2026-03-26 16:05:24 +08:00
lanceyq
863be50aaf [changes] Spatial verification, retrieval synchronization 2026-03-26 15:03:33 +08:00
Eternity
4d4a780ab7 style(memory): Pref an anomaly in the message null check logic. 2026-03-26 12:05:53 +08:00
lanceyq
f92eb9f45a [changes] Remove the unnecessary prompts 2026-03-25 19:23:31 +08:00
Mark
a136d44e27 Merge pull request #682 from SuanmoSuanyangTechnology/pref/workflow-engine 
pref(workflow): optimize workflow execution performance and reduce logging noise
 2026-03-25 18:59:27 +08:00
lanceyq
38c6c7f053 [changes] Simultaneously create the "end_user_info" data to ensure that the interface modification takes effect immediately. 2026-03-25 18:47:30 +08:00
lanceyq
c4461c4917 【add】User alias extraction and retrieval 2026-03-25 18:47:29 +08:00
Timebomb2018
294ee49d59 fix(file and app): 
embedding and volcano model
 2026-03-25 18:06:01 +08:00
Timebomb2018
caab58dd2f fix(file and app): 
1. Handle the encoding issue when downloading Markdown files;
2. Experience the sharing of memory configuration
 2026-03-25 17:54:27 +08:00
Eternity
85daf576e9 perf(workflow): Optimize downstream node activation method to reduce performance overhead 2026-03-25 17:19:56 +08:00
Eternity
45eef12842 perf(workflow): Adjust graph construction timing, adopting a lazy strategy for constructing cyclic subgraphs within nodes 2026-03-25 14:36:21 +08:00
Eternity
e86d679ae5 perf(workflow): improve performance of workflow analysis algorithms, fix typos, adjust debug log levels 2026-03-25 13:24:17 +08:00
Timebomb2018
def7367e33 Merge branch 'refs/heads/feature/agent-tool_xjn' into feature/20260105_xjn 2026-03-25 11:48:42 +08:00
Timebomb2018
54cff5861a feat(model): add volcano model 2026-03-25 11:45:49 +08:00
Ke Sun
1856c55c04 Merge pull request #679 from SuanmoSuanyangTechnology/pref/workflow-engine 
pref(workflow): use lightweight deque for streaming scheduler output queue to reduce read/write overhead
 2026-03-24 19:07:35 +08:00
Mark
04c54081c8 [add] celery support rbmq 2026-03-24 17:29:38 +08:00
Eternity
1c49e3c167 feat(workflow): use lightweight deque for streaming scheduler output queue to reduce read/write overhead 2026-03-24 17:17:30 +08:00