BGE-M3 returns dense_embedding instead of embedding; use dense_embedding
as fallback when embedding is None to avoid TypeError.
Made-with: Cursor
Co-authored-by: AleksandrMordvinov <mad190192@gmail.com>
* refactor(memory): remove mark filtering parameters and simplify get_memory logic
* feat(core): bump version to 0.3.1.0
* refactor(memory): update comment to clarify dialog storage persistence
* refactor(core): update text truncation utilities and tool result handling
- Add new truncate_text_head function for head-based truncation
- Introduce TRUNCATION_MARKER_START constant for truncation detection
- Replace tail-based truncation with head-based truncation in tool result compaction
- Remove tool_result_threshold and retention_days parameters from RemeLight initialization
- Update ToolResultCompactor to use configurable thresholds for recent vs old messages
- Modify compact_tool_result method to accept multiple threshold parameters
- Adjust cleanup logic to use default compactor configuration
- Simplify is_truncated function to check only start marker
* ```
feat(memory): add long line splitting in tool result compaction
- Added _split_long_lines function to break oversized lines at 10000 characters
- Implemented line splitting before saving tool results to files
- Prevents extremely long lines from breaking file-based storage
- Maintains compatibility with existing tool result format
- Preserves original content integrity through chunked processing
```
Use user-specified timezone instead of system local time when generating
daily note filenames and timestamps in memory summarization and CLI.
Changes:
- Summarizer: accept 'timezone' param in __init__; use
datetime.now(zoneinfo.ZoneInfo(tz)) instead of naive datetime.now()
- ReMeLight.summary_memory(): accept 'timezone' param and pass to Summarizer
- CliAgent: accept 'timezone' param in __init__; pass to Summarizer
and use for current_time timestamp in system prompts
- Fallback to system local time if timezone is None (preserves original behavior)
Fixes timezone mismatch when system timezone differs from user's actual
location (e.g., server in UTC+8 but user in America/Chicago).
* update
* refactor(memory): remove unnecessary type check and update error logging
* refactor(core): standardize logger import and update agentscope dependency
* fix(memory): disable console output and add logging for summarizer component
* feat(core): replace OpenAI token counter with custom ReMe token counter
- Replace OpenAITokenCounter with ReMeTokenCounter implementation
- Add support for HuggingFace mirror and configurable tokenizer
- Register ReMeTokenCounter as default token counter in registry
- Update config to use hf backend with Qwen2.5-7B-Instruct model
refactor(memory): convert token counting methods to async in message handlers
- Change count_str_token, stat_message, count_msgs_token to async methods
- Update format_msgs_to_str and context_check to use async token counting
- Modify _format_tool_result_output to support async token counting
- Adjust all dependent methods to await async token counting calls
feat(memory): add dialog persistence to in-memory storage
- Implement _append_messages_to_dialog for saving messages to JSONL files
- Add dialog_path parameter to ReMeInMemoryMemory constructor
- Persist messages to daily JSONL files based on timestamp grouping
- Update mark_messages_compressed to save and remove compressed messages
- Modify clear_content to persist all messages before clearing memory
refactor(ops): update token counter type hints and initialization
- Change BaseOp to use HuggingFaceTokenCounter instead of TokenCounterBase
- Update type annotations for as_token_counter property and parameters
- Remove direct token counter injection from Compactor and ContextChecker
- Pass as_token_counter parameter through service context mechanism
style(logging): improve error logging with exception details
- Replace logger.error with logger.exception in browser control tool
- Change logger.error to logger.exception in memory get tool error handling
- Add proper exception logging with stack trace information
chore(config): add token counter configuration to light YAML
- Add as_token_counters section with default hf backend configuration
- Configure Qwen/Qwen2.5-7B-Instruct model with mirror support enabled
- Set up pretrained_model_name_or_path and use_mirror parameters
test(context): update context check tests to async implementation
- Convert verify_context_check_invariants to async function
- Update context check test methods to use async calls
- Change stat_message calls to await async implementation
- Modify test_empty_messages and test_below_threshold_returns_all to async
* feat(core): implement context checking and memory management features
* refactor(core): replace direct loguru import with logger utility function
* refactor(reme): remove RuntimeContext dependency and simplify context checking
* feat(docs): add raw conversation persistence to ReMe framework
* add: as_token_counters config for reme_cli
* add: reme_cli function
* update: format the terminal printing for reme_cli
* update: check for pre-commit
* single quotes for the inner dictionary keys
* update the usage of get_std_logger for pre-commit
* update the usage of get_std_logger for pre-commit
* add 'console_enabled' param in compactor&summarizer
* 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
