Commit graph

6 commits

Author SHA1 Message Date
jinliyl
ad7893e9c4
fix(mcp): resolve circular import issues and update dependencies (#296)
* fix(mcp): resolve circular import issues and update dependencies

- Moved fastmcp imports inside functions to prevent circular dependencies
- Replaced _TRANSPORT_MAP with _VALID_TRANSPORTS set for transport validation
- Updated version number from 0.4.0.3 to 0.4.0.4
- Added claude-agent-sdk dependency to core optional dependencies
- Used TYPE_CHECKING imports for FastMCP related types
- Restructured transport mapping logic within function scope
- Fixed string annotation for CallToolResult type hints

* refactor(tests): update date handling in daily steps tests

- Replace _date.today() with timezone-aware now function
- Use Asia/Shanghai timezone for date formatting
- Change return format to use strftime instead of isoformat
- Import now function from reme.steps.evolve module

* refactor(tests): clean up unused imports in daily steps test

- Removed unused date import from datetime module
- Removed redundant pathlib Path import that was already imported later
- Kept necessary imports for asyncio, os, tempfile, warnings, and frontmatter modules

* test(daily_steps): update test to include application context for daily list step

- Add ApplicationContext initialization with temporary workspace directory
- Register file store component in application context
- Pass application context to DailyListStep constructor
- Maintain existing test assertion behavior for date metadata verification
2026-06-26 09:37:08 +08:00
jinliyl
afe12b16db
feat(file_store): add embedding backfill for persisted chunks (#292)
- Implement _backfill_missing_embeddings method to handle chunks without embeddings
- Add logic to identify and process chunks that predate embedding feature
- Integrate backfill process into store loading sequence
- Add proper error handling and logging for backfill operations
- Create unit test for embedding backfill functionality
- Ensure backfilled embeddings are properly persisted to storage
2026-06-24 17:32:21 +08:00
jinliyl
7d86658f33
Refactor logging levels and add dream schema definitions (#291)
* chore(logging): change info logs to debug level for data loading operations

- Changed stopwords loading log from info to debug level
- Changed file catalog nodes loading log from info to debug level
- Changed file graph nodes loading log from info to debug level

* feat(dream): add dream schema definitions and enum for auto-dream functionality

- Add DreamBucketEnum with procedure, personal, and wiki values
- Create comprehensive dream-related Pydantic models including DreamUnit,
  DreamTopic, DreamExtractOutput, IntegrateOutcome, TopicSelectionOutput,
  ProactiveResult, and DreamState
- Move schema definitions from local step module to shared schema package
- Update dream extraction and integration steps to use new enum-based
  bucket validation
- Initialize digest directories for each dream bucket type
- Enhance embedding store health check with workspace directory logging

* refactor(tests): update DreamState import path in test_auto_dream.py

- Move DreamState import from reme.steps.evolve.dream.schema to reme.schema
- Maintain same functionality with updated module reference
- Align import with new schema location in project structure
2026-06-24 16:44:03 +08:00
jinliyl
a3bd81bde2
Update version to 0.4.0.2 and improve tokenizer index handling (#290)
* fix(core): update version number to 0.4.0.1

- Incremented version from 0.4.0.0 to 0.4.0.1 in __init__.py

* fix(index): remove stopwords path from tokenizer config and add keyword index repair

- Remove stopwords_path from tokenizer config to prevent index forking by install path
- Add _sync_keyword_index_from_chunks method to repair keyword index when persisted state mismatches
- Implement test for keyword index repair from persisted chunks when missing
- Add test to verify tokenizer fingerprint ignores stopwords absolute path
- Update version from 0.4.0.1 to 0.4.0.2

* feat(dream): add scan_days parameter to dream extraction process

- Add scan_days configuration option to default.yaml with default value of 2
- Implement recent_dates utility function to calculate date ranges for scanning
- Modify DreamExtractStep to scan multiple days based on scan_days parameter
- Update dream extraction to process files across multiple dates instead of single day
- Extend DreamState schema to include dates and scan_days fields
- Update DreamTopicsStep to handle multi-day topic processing
- Modify finish step to checkpoint files from all scanned dates
- Add comprehensive tests for multi-day scanning functionality
- Update prompt templates to include scan dates information
- Refactor topics writing logic to target specific date rather than current date
2026-06-24 15:01:07 +08:00
Sen Huang
e31db5fe19
docs: rename vault_dir to workspace_dir in documentation and examples (#286)
* docs: rename vault_dir to workspace_dir in documentation and examples

* refactor(extract): format long method call across multiple lines

* refactor(extract): format system prompt parameters for better readability
2026-06-22 16:58:57 +08:00
jinliyl
206a53e5ed
init: reme version 0.4.0 (#284) 2026-06-22 15:41:19 +08:00