48 commits

Author	SHA1	Message	Date
Zhouwk	e0d0e3e568	提供支持向量数据库的profile功能 (#221) ... * feat(reme): 添加配置选项以启用或禁用个人资料功能 - 在 ReMe 初始化方法中添加 enable_profile 参数，默认值为 True - 根据 enable_profile 设置决定是否创建 profile 目录和设置 profile_dir - 在 PersonalSummarizer 中根据 enable_profile 条件性地添加个人资料相关工具 - 在 PersonalRetriever 中根据 enable_profile 条件性地添加 ReadAllProfiles 工具 - 修改 profile_path 属性以在禁用个人资料时返回 None - 修改 get_profile_handler 方法以在禁用个人资料时返回 None - 为 enable_profile 参数添加文档说明其用于云向量存储场景 * refactor(benchmark): 重构LongMemEval基准测试中的ReMe实例管理 - 移除未使用的shutil导入 - 将固定的ReMe实例改为每个问题创建独立实例以实现隔离 - 更新LLM配置名称从qwen3-max-think到qwen-max-t - 修改模型调用逻辑使用正确的model_name参数 - 添加qwen-flash和GPT-4o-mini等新模型配置 - 统一使用"User"作为用户名，通过集合名实现隔离 - 调整并发处理数从4降至1，批处理大小从10增至30 - 每个问题类型采样数从2增至4 - 添加异步上下文管理确保资源正确释放 * reformat 2 files * refactor(benchmark): 重构长记忆评估中的模型配置 - 将原有的 eval_model_name 替换为专门的 retrieve_model_name 用于检索操作 - 添加对 qwen-max 模型配置的支持 - 更新参数解析器以支持新的检索模型参数 - 修改最大并发数默认值从 1 提升到 4 - 调整样本数量默认值从 4 减少到 1 - 统一模型参数命名规范，区分摘要、检索和评估模型 - 优化内存处理器初始化逻辑，支持独立的检索模型配置 * fix(benchmark): 移除数据路径默认值并设为必填参数 - 将LongMemEval评估脚本中的data_path参数改为必需参数 - 将HaluMem评估脚本中的data_path参数改为必需参数 - 删除了硬编码的默认文件路径配置 - 强制用户显式指定数据集文件路径以避免路径错误 * Update __init__.py * Update __init__.py * fix(benchmark): 修复ReMe评估中的模型配置和空值处理问题 - 移除了retrieve_memory调用中不需要的llm_config_name参数 - 修复了长字符串打印的换行格式问题 - 添加了eval_result为空时的初始化处理 - 在accuracy评估中加入了eval_model_name参数传递 * style(benchmark): 格式化模型名称打印输出 - 移除了多行字符串中的换行符和多余空格 - 将模型名称信息合并为单行连续显示 - 保持了原有的打印格式和信息完整性 * docs(readme): 更新文档添加实验结果表格 - 在英文版 README 中添加 🧪 Experiments 章节 - 添加 LoCoMo 和 HaluMem 两个基准测试的结果表格 - 在中文版 README_ZH 中添加 🧪 实验 章节 - 添加 LoCoMo 和 HaluMem 测试集的实验配置说明 - 添加完整的实验数据对比表格和评估协议说明 * docs(readme): 更新文档中的内存系统链接 - 为基于文件的记忆系统添加锚点链接 - 为基于向量库的记忆系统添加锚点链接 - 修复英文文档中的链接格式 - 修复中文文档中的链接格式和空行问题 * docs(readme): update experimental results section in documentation - Remove outdated experimental data placeholder "Coming soon..." - Add complete evaluation results for LoCoMo and HaluMem benchmarks - Include detailed performance metrics tables for all memory methods - Update experimental settings description with ReMe backbone details - Align evaluation protocol information with LLM-as-a-Judge approach - Maintain consistent formatting between English and Chinese documentation * docs(benchmark): add quick start guides for halumem and longmemeval experiments - Created HaluMem experiment quick start guide with ReMe integration setup - Added detailed steps for installing ReMe environment using conda - Included repository cloning instructions for HaluMem benchmark - Provided complete command examples for running HaluMem experiments - Created LongMeMEval quick start guide with data download procedures - Added wget commands for downloading cleaned dataset files - Included evaluation script instructions for computing experiment statistics - Documented parameter configurations for different model types and batch sizes * docs(longmemeval): update quickstart guide documentation - Changed project name from Halumem to Longmemeval in title - Updated description to reference Longmemeval experiments instead of Halumem - Maintained existing ReMe integration instructions unchanged * chore(logger): add test comment to logger configuration - Added test comment in logger utility function - Removed duplicate log handling by keeping the remove() call * chore(logger): add test comment to logger configuration - Added test comment in logger utility function - Removed duplicate log handling by keeping the remove() call * feat(core): add file logging capability to application - Added log_to_file parameter to Application class constructor - Integrated log_to_file option in logger initialization - Updated ServiceContext to support file logging configuration - Modified init_logger function to conditionally enable file logging - Added log_to_file field to ServiceConfig schema - Updated ReMe class to include file logging option - Wrapped file logging setup in conditional check to prevent unnecessary operations * docs(benchmark): update HaluMem quickstart guide with dataset download instructions - Replace repository cloning with direct dataset download using curl - Add commands to download HaluMem-Medium.jsonl and HaluMem-Long.jsonl files - Include both official Hugging Face and mirror download sources - Update data path reference from nested directory to local data folder - Add dataset page link and mirror usage instructions for mainland China access * feat(memory): add profile retrieval tool and refactor profile management - Introduce RetrieveProfile tool for fetching specific user profiles - Refactor ProfileHandler to support both filesystem and vector backends - Add async methods to ProfileHandler with synchronous fallbacks - Update PersonalRetriever to support two-stage profile and memory retrieval - Enhance PersonalSummarizer with improved tool partitioning logic - Add profile_backend, profile_store_name, and profile_max_capacity configuration options - Replace direct ProfileHandler imports with get_profile_handler method - Implement profile search functionality with dedicated prompts and workflows - Add FileProfileBackend and VectorProfileBackend implementations - Update base memory tool with new profile configuration parameters * feat(profile): add custom profile collection name support - Add profile_collection_name parameter to Application constructor - Allow custom database collection name for vector profiles instead of default suffix - Update profile vector store configuration logic to use custom collection name - Modify _ensure_profile_vector_store_config to handle custom collection names - Update docstring with detailed parameter descriptions for profile configuration options * test(history): add single history id acceptance test for multiple mode - Add test case to verify multiple-mode history lookup accepts a single history_id string - Create FakeVectorStore stub with minimal implementation for ReadHistory tests - Return requested history node from vector store mock - Initialize ReadHistory tool with multiple mode enabled - Add pylint disable comment for protected access to vector store property * refactor(memory): update profile handler and vector tools with improved formatting and error handling - Add module docstring to profiles/__init__.py - Add pylint disable comments for no-name-in-module and missing-function-docstring - Format long error message in ProfileHandler.sync_run method for better readability - Reformat parameters in ProfileHandler.aadd method to separate lines - Update model_copy call in reme.py to span multiple lines for better readability - Format aadd_batch call in update_profile.py to span multiple lines	2026-04-28 15:11:45 +08:00
Zhouwk	625d184ca1	添加log_to_file的开关 (#205)	2026-04-13 10:49:26 +08:00
Xinmin Zeng	bf79986f9c	fix: surface summarize/retrieve failures instead of masking them (#160) ... * fix(memory): surface summarize and retrieve failures clearly * fix(memory): make raise_exception configurable * fix(tests): resolve flake8 and pylint errors in error handling tests - Remove unnecessary sys.path.insert hack - Add module/class/function docstrings - Initialize call_kwargs in __init__ to fix W0201 - Suppress W0212 with inline pylint disable for _started access - Remove unnecessary lambda wrappers (W0108)	2026-03-27 12:22:29 +08:00
jinliyl	d0c9d89092	feat(memory): add ContextChecker component for context size management (#144) ... * feat(memory): add ContextChecker component for context size management * refactor(memory): restructure file-based memory tools and update imports * docs(readme): update documentation with detailed architecture and components * docs(readme): update Chinese documentation with enhanced memory management diagrams * refactor(cookbook): move cookbook files to test directory and clean up docs * docs(readme): update link path for old version documentation * docs(readme): update documentation with improved architecture diagrams and component details * docs(readme): update documentation with improved clarity and structure * refactor(docs): update in-memory memory documentation * docs(readme): add experiment reproduction link to quickstart guide	2026-03-06 23:43:42 +08:00
Zhouwk	9294e65dfb	Add bool trigger on Profile memory ; Update Longmemeval Eval and HalumemEval (#129) ... * feat(reme): 添加配置选项以启用或禁用个人资料功能	2026-03-03 11:29:49 +08:00
jinli.yl	3dcb9e09f4	fix(profiles): disable thinking parameters in ReadAllProfiles tool	2026-03-02 11:53:30 +08:00
jinli.yl	c4e6225336	refactor(memory): restructure tool and procedural memory agents with enhanced capabilities	2026-02-27 16:17:22 +08:00
jinli.yl	370450f157	refactor(reme): remove unused context methods and update config path default	2026-02-26 18:25:38 +08:00
jinli.yl	23f7c51a1a	refactor(core): restructure application initialization and service context	2026-02-26 17:56:59 +08:00
jinli.yl	6efecf1a3e	refactor(memory): rename fs components to fb and reorganize modules	2026-02-26 16:47:04 +08:00
jinli.yl	eae6c63d15	feat(cli): add ReMeCli class with interactive chat functionality	2026-02-11 17:23:15 +08:00
jinli.yl	0692023379	refactor(core): rename API base parameters and remove snippet character limit	2026-02-10 00:30:06 +08:00
jinli.yl	1a35150648	feat(core): add config path parameter and enhance fs cli capabilities	2026-02-08 04:56:10 +08:00
jinli.yl	f0bc2da7b0	feat(chat): add FsCli chat agent with streaming capabilities	2026-02-08 03:05:11 +08:00
jinli.yl	55d61f1dc5	refactor(core): update registry naming and application configuration	2026-02-07 15:05:02 +08:00
jinli.yl	de28c8e243	refactor(core): rename memory_storage to memory_store and add base fs tool	2026-02-07 03:37:12 +08:00
jinliyl	f6ca7a733a	Merge branch 'main' into dev_0205	2026-02-06 17:47:44 +08:00
jinli.yl	1dd81f9c25	refactor(core): update config parsing and memory management system	2026-02-06 15:02:41 +08:00
jinliyl	90cd9ddea8	Merge pull request #100 from agentscope-ai/dev_0205 ... Dev 0205	2026-02-06 12:17:15 +08:00
jinli.yl	88674c52f9	fix(memory): resolve enum value access and tool processing issues	2026-02-06 12:16:28 +08:00
jinli.yl	c5438c52fc	feat(memory): implement file watcher with delta and full sync strategies	2026-02-06 01:58:28 +08:00
jinli.yl	8c05f96fb6	feat(agent): implement memory targets filtering in base memory agent ... - Add memory_targets parameter to filter memory target type mapping - Modify memory_target_type_mapping property to use filtered targets when available - Update REME class to collect memory targets from user, task, and tool names - Pass collected memory targets to agent initialization - Support both string and list inputs for user, task, and tool names - Maintain	2026-02-04 17:51:28 +08:00
jinli.yl	857cd52a8e	feat(memory): add memory management and file system tools	2026-02-03 22:29:45 +08:00
方应	6e26006c9f	feat(core): 添加 v2 版本的个人总结器和检索器支持 ... - 在版本控制逻辑中加入 v2 版本的支持判断 - 激活了之前被注释掉的 ReadHistory 工具并整合到检索器中 - 调整了 ReMeSummarizer 和 ReMeRetriever 的版本兼容性检查	2026-02-03 14:55:26 +08:00
方应	d83551c2cf	feat(benchmark): 更新ReMe评估配置参数 ... - 将最大并发数从2调整为1，批量大小从20调整为40 - 算法版本从halumem更新为v1 - 添加了新的reme_model_name参数用于模型名称配置 - 在MemoryProcessor中使用reme_model_name替代eval_model_name - 主函数中添加batch_size参数传递 - 命令行解析器中添加batch_size参数选项 - 在ReMe中将ReadHistory替换为ReadHistoryV2并配置新参数	2026-02-03 14:31:04 +08:00
jinli.yl	4159cfc51c	feat(memory): add ReadHistoryV2 tool with enhanced history retrieval capabilities	2026-02-02 17:14:16 +08:00
jinli.yl	b5fe827a36	refactor(reme): convert _resolve_memory_target to static method	2026-01-31 03:47:25 +08:00
jinli.yl	6a7396732b	feat(reme): add comprehensive memory management API	2026-01-31 03:40:38 +08:00
jinli.yl	5a5e06a43d	feat(memory): add draft memory functionality and update memory/profile management tools	2026-01-31 02:36:10 +08:00
jinli.yl	3680571c94	refactor(core): simplify component registration and improve application lifecycle management	2026-01-31 01:05:31 +08:00
方应	07905a0358	feat(memory): 添加用户配置文件增删功能并优化内存管理 ... - 新增 AddProfile 工具类用于添加用户配置文件 - 新增 DeleteProfile 工具类用于删除指定ID的配置文件 - 从 __init__.py 中移除已废弃的 UpdateProfileFilterOlder 工具 - 在 reme.py 中注释掉 AddProfile 和 DeleteProfile 的导入 - 从 reme.py 的工具列表中移除 UpdateProfileFilterOlder 相关代码 - 优化 ES 和 Qdrant 向量存储客户端初始化的日志记录 - 更新个人记忆检索器和摘要器的 YAML 配置文件格式 - 修复 personal_halumem_summarizer.py 中的参数传递格式问题 - 在 UpdateProfile 工具中添加按 memory_target 分组的功能	2026-01-30 17:03:58 +08:00
方应	0f90926781	Merge remote-tracking branch 'origin/main' ... # Conflicts: # reme/reme.py	2026-01-30 16:33:32 +08:00
方应	053c537845	feat(agent): 添加 Halumem 版本的记忆检索器和摘要器 ... - 添加 PersonalHalumemRetriever 和 PersonalHalumemSummarizer 类 - 在 memory 模块中注册新的检索器和摘要器 - 添加 UpdateProfileFilterOlder、DeleteProfile 和 AddProfile 工具 - 将 AddDraftAndRetrieveSimilarMemory 重命名为 AddAndRetrieveSimilarMemory - 修改配置文件中的默认模型名称为 qwen-flash - 在 benchmark 中添加 Halumem 评估支持和实时更新功能 - 降低 ProfileHandler 的最大容量限制并添加重复节点过滤逻辑 - 在 ReMe 中添加 halumem 版本的记忆代理配置	2026-01-30 16:30:18 +08:00
jinli.yl	0ea51a9378	refactor(core): implement lazy initialization for Elasticsearch and Qdrant clients	2026-01-29 16:27:02 +08:00
jinli.yl	6e72bcac2e	refactor(memory): update memory registration and configuration handling	2026-01-29 14:18:53 +08:00
jinli.yl	af75924b46	feat(retrieval): integrate read history component into retrieval chain	2026-01-29 11:51:51 +08:00
jinli.yl	cf62a73228	refactor(memory): restructure memory modules and add versioned personal memory agents	2026-01-29 11:21:50 +08:00
jinli.yl	380cf5da15	fix(memory): handle MEMORY_NOT_FOUND case and update retrieval logic	2026-01-29 01:08:04 +08:00
jinli.yl	f841ccc4b9	feat(memory): enhance memory management with improved tool parameters and agent coordination	2026-01-29 00:12:03 +08:00
jinli.yl	3684eb25eb	feat(memory): update profile management with time-based filtering	2026-01-28 20:47:04 +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	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	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	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