Commit graph

100 commits

Author SHA1 Message Date
jinliyl
7b02c45218
style(memory): update message formatting and improve logging (#175)
* style(memory): update message formatting and improve logging

- Change default include_thinking parameter to True in as_msg_handler.py
- Replace angle brackets with square brackets for block formatting in as_msg_stat.py
- Add newline replacement in text truncation method in as_msg_stat.py
- Add loading duration timing to embedding cache loading in base_embedding_model.py
- Replace XML-style tags with markdown headers in compactor.py conversation format
- Update compactor.yaml prompts to reference markdown-style headers instead of XML tags
- Modify summarizer.py to use markdown-style conversation header format

* refactor(file-watcher): replace scan_on_start with rebuild_index_on_start parameter

- Replace scan_on_start and clear_on_start boolean parameters with single rebuild_index_on_start
- Update BaseFileWatcher constructor to use rebuild_index_on_start instead of two separate flags
- Modify initialization logic to clear and rescan when rebuild_index_on_start is True
- Remove scan_on_start parameter from CLI and light configuration files
- Update documentation to remove scan_on_start from quick start guides
- Rename all test methods and classes from scan_on_start to rebuild_index_on_start
- Add timezone-aware datetime helper method to summarizer component
- Format log message with proper line breaks for readability

* fix(core): resolve file watcher initialization issue and update version

- Fixed file watcher task creation to properly handle rebuild index on start logic
- Moved initialization and watch loop into async function to ensure proper execution order
- Updated package version from 0.3.1.1 to 0.3.1.2
- Added missing comma in embedding model logging statement

* fix(core): reduce max formatter text length limit

- Changed _DEFAULT_MAX_FORMATTER_TEXT_LENGTH from 2000 to 1000
- Updated constant value in as_msg_stat.py schema module

* fix(file-watcher): change default rebuild index behavior on start

- Changed rebuild_index_on_start parameter default from False to True
- This ensures index is rebuilt by default when file watcher starts
- Maintains consistent state initialization for file watching operations

* feat(compactor): add return_dict option and improve summary validation

- Add _is_valid_summary function to validate summary content format
- Introduce return_dict parameter to return structured results with validation
- Update prompt templates with clearer task descriptions and formatting rules
- Refactor update_user_message prompts to combine prefix and suffix logic
- Return dictionary with user_message, history_compact, and is_valid fields when enabled
- Add proper error handling for exception cases in memory compaction
- Maintain backward compatibility with string return when return_dict=False

* feat(memory): add thinking block configuration option

- Add add_thinking_block parameter to compactor component
- Pass include_thinking flag to message formatting in compactor
- Add add_thinking_block parameter to reme_light compact function
- Add add_thinking_block parameter to reme_light summarize function
- Add add_thinking_block parameter to summarizer component
- Pass include_thinking flag to message formatting in summarizer
- Remove previous-summary tags from compressed summary format
2026-03-24 00:20:15 +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
zouyingcao
65971bafe3
Update: check the code&docs for evaluation on bfcl&appworld (#141)
* fix: df.columns bug

* fix: await for asynchronous method

* update: docs for bfcl&appworld quickstart

* update: benchmark/bfcl for new version quickstart

* slightly revise bfcl cookbook

* update for pre-commit

* handle boolean flags in split_into_trainval.py

* fix typo in faq.md
2026-03-06 16:11:39 +08:00
caozouying.czy
dc441d86a7 check pre-commit for faq.md 2026-03-03 11:26:31 +08:00
caozouying.czy
1074ec78b2 Merge branch 'main' of https://github.com/zouyingcao/ReMe 2026-03-02 11:21:07 +08:00
caozouying.czy
fe262320d3 add faq.md 2026-03-02 11:12:40 +08:00
jinliyl
0bb6321285
docs(reme): update README with comprehensive documentation for file-b… (#122)
* docs(reme): update README
2026-02-28 22:27:38 +08:00
caozouying.czy
7c397603fa update paper_data format 2026-02-25 12:05:28 +08:00
jinli.yl
12f0667f11 docs(readme): update documentation with ReMe CLI quick start guides and latest updates 2026-02-15 19:05:42 +08:00
jinli.yl
c104cb865e docs(cli): add comprehensive quick start guide for ReMe CLI 2026-02-15 18:48:32 +08:00
jinli.yl
2159f6a29f docs(cli): update quick start documentation title 2026-02-15 18:41:33 +08:00
jinli.yl
c8b7dbc584 docs(cli): update Chinese quick start documentation 2026-02-15 18:39:57 +08:00
jinli.yl
a753a81852 feat(core): upgrade version to 0.3.0.0b1 and add metadata configuration 2026-02-15 18:29:46 +08:00
jinli.yl
a8604af78f feat(cli): enable vector search and improve chat history management 2026-02-15 13:29:46 +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
78b993f830 refactor(core): restructure project modules and update base classes 2026-01-22 22:07:32 +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
a172a6854b feat(vector-store): add sorting capability to list operations across all backends 2026-01-09 19:50:42 +08:00
caozouying.czy
d91fc6a14c update docs/cookbook/appworld/quickstart.md for better reproduction 2026-01-09 17:18:53 +08:00
jinli.yl
1ea8f07aac feat(core): add flow module and enhance documentation 2026-01-02 00:16:24 +08:00
jinli.yl
91a07e4186 feat(vector-store): add base vector store interface and multiple implementations 2025-12-31 13:18:33 +08:00
jinli.yl
fbdfdfee57 feat(token-counter): add token counting system with multiple implementations 2025-12-31 11:17:12 +08:00
jinli.yl
e5f17d6e67 docs(guidelines): add test file creation guidelines with loguru logger 2025-12-30 22:01:56 +08:00
jinli.yl
266b19ecd0 feat(core): add enumeration and schema modules with utility functions 2025-12-30 18:16:33 +08:00
jinli.yl
cb907ea201 feat(utils): add universal timer decorator with loguru integration 2025-12-30 17:38:58 +08:00
jinliyl
da8260e5c0
Merge pull request #59 from agentscope-ai/dev_czy_1126
Update appworld_react_agent.py for better reproduction & Upload task memory paper data
2025-12-25 14:07:38 +08:00
caozouying.czy
f85ab472d9 upload task memory data in our paper 2025-12-24 14:35:09 +08:00
jinli.yl
43cfc0872a docs(vector_store): add configuration examples for vector store backends 2025-12-17 11:59:25 +08:00
jinli.yl
82b973dbf8 feat(audio): add macOS microphone recording script 2025-12-04 20:37:32 +08:00
jinli.yl
a1b4ce3df7 docs(work_memory): add diagram to message offload documentation 2025-11-27 20:37:05 +08:00
jinli.yl
46249bbea7 docs(index): update agent memory definition and architecture figure 2025-11-27 20:31:00 +08:00
jinli.yl
a968b6fd44 docs(cookbook): add Jupytext metadata and improve quick start guide 2025-11-27 19:49:09 +08:00
jinli.yl
de53ac0e16 docs(work_memory): add working memory documentation files 2025-11-27 19:36:56 +08:00
jinli.yl
ed2ca3f9d4 docs(readme): update documentation with working memory features 2025-11-27 19:27:38 +08:00
方应
fe4eb7a0a8 Add the description document about the op in working memory. 2025-11-27 17:34:36 +08:00
方应
121002974a Merge remote-tracking branch 'origin/main' into dev_1117 2025-11-27 17:28:45 +08:00
方应
dfd2a35ccb Add the description document about the op in working memory. 2025-11-27 17:25:14 +08:00
jinli.yl
a2b7a61664 feat(working_memory): add working memory demo with ReAct agent 2025-11-27 16:52:47 +08:00
jinli.yl
b421515c73 refactor(core): restructure context management and working memory modules 2025-11-24 21:17:02 +08:00
jinli.yl
e92a8f7e0b chore(version): update project version to 0.2.0.0 2025-11-11 00:09:43 +08:00
jinli.yl
d587dbfd56 docs(readme): update python version and pypi version badges- Updated Python version badge from 3.12+ to 3.10+ 2025-11-07 14:57:30 +08:00
jinli.yl
27561aa94f docs(vector_store): update vector store configuration guide 2025-11-07 14:53:14 +08:00
jinli.yl
73668f051e feat(core): add pre-commit hooks and improve module documentation 2025-11-07 14:14:11 +08:00
dengjiaji
d87dbb65f9 docs(config): update source repository URL 2025-11-04 16:48:10 +08:00
jinli.yl
e5b2cd9f28 docs(index): update citation information 2025-11-04 16:19:48 +08:00
jinli.yl
e7d4f00c9f docs(config): update github repository links to agentscope-ai 2025-11-04 16:17:40 +08:00
jinli.yl
8984f973ab docs(readme): update project name in README 2025-11-04 16:01:12 +08:00
jinli.yl
6a863122f7 docs(readme): reorganize latest updates section 2025-11-04 15:56:20 +08:00
jinli.yl
d9f332ece2 docs(readme): update project name to memory management kit 2025-10-29 15:43:58 +08:00