|
1 | 1 | # CHANGELOG |
2 | 2 |
|
3 | 3 |
|
| 4 | +## v0.8.0 (2025-02-28) |
| 5 | + |
| 6 | +### Chores |
| 7 | + |
| 8 | +- Formatting |
| 9 | + ([`93cc637`](https://github.com/basicmachines-co/basic-memory/commit/93cc6379ebb9ecc6a1652feeeecbf47fc992d478)) |
| 10 | + |
| 11 | +- Refactor logging setup |
| 12 | + ([`f4b703e`](https://github.com/basicmachines-co/basic-memory/commit/f4b703e57f0ddf686de6840ff346b8be2be499ad)) |
| 13 | + |
| 14 | +### Features |
| 15 | + |
| 16 | +- Add enhanced prompts and resources |
| 17 | + ([#15](https://github.com/basicmachines-co/basic-memory/pull/15), |
| 18 | + [`093dab5`](https://github.com/basicmachines-co/basic-memory/commit/093dab5f03cf7b090a9f4003c55507859bf355b0)) |
| 19 | + |
| 20 | +## Summary - Add comprehensive documentation to all MCP prompt modules - Enhance search prompt with |
| 21 | + detailed contextual output formatting - Implement consistent logging and docstring patterns across |
| 22 | + prompt utilities - Fix type checking in prompt modules |
| 23 | + |
| 24 | +## Prompts Added/Enhanced - `search.py`: New formatted output with relevance scores, excerpts, and |
| 25 | + next steps - `recent_activity.py`: Enhanced with better metadata handling and documentation - |
| 26 | + `continue_conversation.py`: Improved context management |
| 27 | + |
| 28 | +## Resources Added/Enhanced - `ai_assistant_guide`: Resource with description to give to LLM to |
| 29 | + understand how to use the tools |
| 30 | + |
| 31 | +## Technical improvements - Added detailed docstrings to all prompt modules explaining their purpose |
| 32 | + and usage - Enhanced the search prompt with rich contextual output that helps LLMs understand |
| 33 | + results - Created a consistent pattern for formatting output across prompts - Improved error |
| 34 | + handling in metadata extraction - Standardized import organization and naming conventions - Fixed |
| 35 | + various type checking issues across the codebase |
| 36 | + |
| 37 | +This PR is part of our ongoing effort to improve the MCP's interaction quality with LLMs, making the |
| 38 | + system more helpful and intuitive for AI assistants to navigate knowledge bases. |
| 39 | + |
| 40 | +🤖 Generated with [Claude Code](https://claude.ai/code) |
| 41 | + |
| 42 | +--------- |
| 43 | + |
| 44 | +Co-authored-by: phernandez <phernandez@basicmachines.co> |
| 45 | + |
| 46 | +- Add new `canvas` tool to create json canvas files in obsidian. |
| 47 | + ([#14](https://github.com/basicmachines-co/basic-memory/pull/14), |
| 48 | + [`0d7b0b3`](https://github.com/basicmachines-co/basic-memory/commit/0d7b0b3d7ede7555450ddc9728951d4b1edbbb80)) |
| 49 | + |
| 50 | +Add new `canvas` tool to create json canvas files in obsidian. |
| 51 | + |
| 52 | +--------- |
| 53 | + |
| 54 | +Co-authored-by: phernandez <phernandez@basicmachines.co> |
| 55 | + |
| 56 | +- Incremental sync on watch ([#13](https://github.com/basicmachines-co/basic-memory/pull/13), |
| 57 | + [`37a01b8`](https://github.com/basicmachines-co/basic-memory/commit/37a01b806d0758029d34a862e76d44c7e5d538a5)) |
| 58 | + |
| 59 | +- incremental sync on watch - sync non-markdown files in knowledge base - experimental |
| 60 | + `read_resource` tool for reading non-markdown files in raw form (pdf, image) |
| 61 | + |
| 62 | + |
4 | 63 | ## v0.7.0 (2025-02-19) |
5 | 64 |
|
6 | 65 | ### Bug Fixes |
|
0 commit comments