jinli.yl
3684eb25eb
feat(memory): update profile management with time-based filtering
2026-01-28 20:47:04 +08:00
jinli.yl
3989a3c1c4
refactor(memory): update memory target mappings and profile handling
2026-01-28 20:38:34 +08:00
jinli.yl
c06fd78763
refactor(memory): refactor memory tools and handlers for improved structure
2026-01-28 20:10:38 +08:00
jinli.yl
c174aade76
feat(memory): extend memory system with procedural and tool memory support
2026-01-28 16:54:28 +08:00
jinli.yl
afa4eb9114
refactor(memory): update memory reference handling and agent orchestration
2026-01-28 01:47:49 +08:00
jinli.yl
2fffb847a0
refactor(memory): restructure memory tools and handlers
2026-01-28 01:18:06 +08:00
jinli.yl
22a6321661
refactor(memory): optimize vector store operations and enhance memory management
2026-01-27 01:57:50 +08:00
jinli.yl
85a843ee2e
feat(benchmark): add configurable evaluation model for ReMe benchmark
2026-01-27 01:41:34 +08:00
jinli.yl
c21b69da11
refactor(memory): update memory management and retrieval implementation
2026-01-27 01:26:17 +08:00
jinli.yl
e63a3fa632
feat(core): add simple request methods and improve memory management
2026-01-27 01:07:39 +08:00
jinli.yl
013fba8538
update
2026-01-26 17:50:23 +08:00
jinliyl
b02d3ab269
Merge pull request #85 from agentscope-ai/dev_0123
...
Dev 0123
2026-01-26 17:41:49 +08:00
jinli.yl
e77d228fae
refactor(memory): update memory system with service context and vector store enhancements
2026-01-26 17:33:07 +08:00
jinli.yl
d3fa645832
refactor(agent): restructure memory agents and base react implementation
2026-01-26 16:30:58 +08:00
jinli.yl
035703029f
feat(memory): restructure memory agent modules and enhance vector store operations
2026-01-23 23:53:54 +08:00
jinliyl
fe777d4d9b
Merge pull request #83 from zouyingcao/main
...
add: workflow/procedural_memory test
2026-01-23 17:42:26 +08:00
caozouying.czy
a19c8a546b
add: workflow/procedural_memory
2026-01-23 17:30:32 +08:00
caozouying.czy
a2099202a0
add: workflow/procedural_memory
2026-01-23 17:03:54 +08:00
jinli.yl
9f8ad20c53
feat(memory): add ReAct agent and memory management tools
2026-01-23 15:47:02 +08:00
jinli.yl
869bdd5153
refactor(types): update type hints to use built-in generic types
2026-01-23 14:27:22 +08:00
jinli.yl
d9d661da39
chore(workflow): add procedural memory module init file
2026-01-23 11:51:00 +08:00
jinliyl
888ccea5f5
Merge pull request #79 from agentscope-ai/dev_0121
...
Dev 0121
2026-01-23 10:45:12 +08:00
jinli.yl
83d111ae41
up init
2026-01-23 10:43:31 +08:00
jinli.yl
c927d264e1
refactor(memory): restructure memory tools with new identity and meta memory features
2026-01-23 00:33:16 +08:00
jinli.yl
3c272ac859
feat(memory): add history management tools with dynamic registration
2026-01-23 00:11:00 +08:00
jinli.yl
af44052a57
feat(memory): add memory tools module with user profile operations
2026-01-22 23:48:13 +08:00
jinli.yl
30990308d8
refactor(memory): migrate and optimize user profile memory tools
2026-01-22 23:46:11 +08:00
jinli.yl
3f0d45c51e
refactor(tool): restructure tool modules and update base classes
2026-01-22 22:53:11 +08:00
jinli.yl
78b993f830
refactor(core): restructure project modules and update base classes
2026-01-22 22:07:32 +08:00
jinli.yl
4348148b72
refactor(core): restructure core modules and update pre-commit configuration
2026-01-22 16:25:20 +08:00
jinli.yl
4560ff09ad
refactor(core): migrate core modules and update imports
2026-01-21 17:10:05 +08:00
jinli.yl
32ff65ca0d
feat(core): refactor context management and add schema definitions
2026-01-21 17:05:56 +08:00
jinli.yl
c7fc8255b1
refactor(core): move core module to core_old and update import paths
2026-01-21 16:34:09 +08:00
jinli.yl
c3c7b5a4a0
fix(llm): enhance rate limit error detection in base LLM implementation
2026-01-20 20:47:24 +08:00
jinli.yl
ff7d25e313
chore(mem_tool): reorder required fields in user profile update schema
2026-01-20 20:35:20 +08:00
jinli.yl
db510dd96e
feat(bench): add human-in-the-loop evaluation framework for AI memory systems
2026-01-20 20:25:26 +08:00
jinli.yl
d145a67843
feat(config): update default LLM model configuration
...
- Changed default model from qwen3-30b-a3b-instruct-2507 to qwen-flash
- Updated evaluation tools to use EVALUATION_PROMPT_FOR_QUESTION instead of QUESTION2
- Added new PROMPT_MEMZERO_JSON2 configuration with context priority rules
- Modified llm_request_for_json to use qwen-flash as default model
- Updated halumem evaluation to specify qwen3-max model explicitly for certain requests
2026-01-19 16:52:35 +08:00
jinli.yl
e7a36067eb
refactor(llm): replace concurrency control with request rate limiting
2026-01-19 01:02:55 +08:00
jinli.yl
74c1386a69
refactor(mem_agent): optimize agent execution and enhance evaluation pipeline
2026-01-19 00:46:52 +08:00
jinli.yl
08b771b6c4
feat(mem-agent): introduce version 4 memory agents and tools
2026-01-18 15:50:46 +08:00
jinli.yl
e6ad682ede
feat(core): add ReMe V3 implementation with optional MCP client and enhanced filtering
2026-01-17 01:15:49 +08:00
jinli.yl
4d312ea682
feat(memory): add metadata toggle option to vector retrieval tool
2026-01-14 18:18:37 +08:00
jinliyl
12efcc9224
Merge pull request #75 from agentscope-ai/halumem_bugfix
...
Halumem bugfix
2026-01-14 16:53:55 +08:00
jinli.yl
681fb22170
feat(embedding): update dimensions parameter to support optional type
2026-01-14 16:21:33 +08:00
jinli.yl
ef7c4daa9a
feat(memory): add memory management tools and agents for AI system
2026-01-14 14:03:52 +08:00
jinli.yl
327dc58f70
feat(bench): add HaluMem dataset statistics analyzer and update LLM concurrency control
...
- Add new analyze_dataset_stats.py script for comprehensive HaluMem dataset analysis
- Include statistics for user sessions, dialogues, content lengths and chunk distributions
- Replace rate limiting with concurrency control in BaseLLM using semaphore mechanism
- Update configuration to use max_concurrency instead of max_rps and rps_window
- Modify dialogue formatting to include only user messages in evaluation
- Add percentile calculations and detailed content size distribution metrics
- Implement session splitting logic based on character length thresholds
- Provide per-user statistics and summary tables for dataset analysis
- Refactor BaseLLM to use internal _chat_impl and _stream_chat_impl methods
- Remove rate limiting locks and timestamps from LLM initialization
- Add command-line interface for dataset statistics analysis tool
2026-01-14 10:14:35 +08:00
jinli.yl
9b69d96b76
refactor(llm): replace recursive rate limiting with loop-based implementation
2026-01-14 00:58:18 +08:00
jinli.yl
25fee2e67f
refactor(llm): optimize rate limiting implementation with recursive checks
2026-01-14 00:54:18 +08:00
jinli.yl
e64667ba77
chore(config): reduce RPS limits for AI model requests
...
- Lowered max_rps from 20 to 2 to prevent rate limiting issues
- Reduced rps_window from 10 to 1 for stricter request throttling
- Updated default configuration values for better performance stability
2026-01-14 00:47:28 +08:00
jinli.yl
de6e3968a3
refactor(llm): optimize rate limiting implementation
2026-01-14 00:44:32 +08:00
