|
2 | 2 |
|
3 | 3 | All notable changes to claude-mem. |
4 | 4 |
|
| 5 | +## [v10.5.0] - 2026-02-26 |
| 6 | + |
| 7 | +## Smart Explore: AST-Powered Code Navigation |
| 8 | + |
| 9 | +This release introduces **Smart Explore**, a token-optimized structural code search system built on tree-sitter AST parsing. It applies the same progressive disclosure pattern used in human-readable code outlines — but programmatically, for AI agents. |
| 10 | + |
| 11 | +### Why This Matters |
| 12 | + |
| 13 | +The standard exploration cycle (Glob → Grep → Read) forces agents to consume entire files to understand code structure. A typical 800-line file costs ~12,000 tokens to read. Smart Explore replaces this with a 3-layer progressive disclosure workflow that delivers the same understanding at **6-12x lower token cost**. |
| 14 | + |
| 15 | +### 3 New MCP Tools |
| 16 | + |
| 17 | +- **`smart_search`** — Walks directories, parses all code files via tree-sitter, and returns ranked symbols with signatures and line numbers. Replaces the Glob → Grep discovery cycle in a single call (~2-6k tokens). |
| 18 | +- **`smart_outline`** — Returns the complete structural skeleton of a file: all functions, classes, methods, properties, imports (~1-2k tokens vs ~12k for a full Read). |
| 19 | +- **`smart_unfold`** — Expands a single symbol to its full source code including JSDoc, decorators, and implementation (~1-7k tokens). |
| 20 | + |
| 21 | +### Token Economics |
| 22 | + |
| 23 | +| Approach | Tokens | Savings | |
| 24 | +|----------|--------|---------| |
| 25 | +| smart_outline + smart_unfold | ~3,100 | 8x vs Read | |
| 26 | +| smart_search (cross-file) | ~2,000-6,000 | 6-12x vs Explore agent | |
| 27 | +| Read (full file) | ~12,000+ | baseline | |
| 28 | +| Explore agent | ~20,000-40,000 | baseline | |
| 29 | + |
| 30 | +### Language Support |
| 31 | + |
| 32 | +10 languages via tree-sitter grammars: TypeScript, JavaScript, Python, Rust, Go, Java, C, C++, Ruby, PHP. |
| 33 | + |
| 34 | +### Other Changes |
| 35 | + |
| 36 | +- Simplified hooks configuration |
| 37 | +- Removed legacy setup.sh script |
| 38 | +- Security fix: replaced `execSync` with `execFileSync` to prevent command injection in file path handling |
| 39 | + |
5 | 40 | ## [v10.4.4] - 2026-02-26 |
6 | 41 |
|
7 | 42 | ## Fix |
@@ -1197,21 +1232,3 @@ Comprehensive test suite in a new PR, targeting **v8.6.0** |
1197 | 1232 |
|
1198 | 1233 | 🤖 Generated with [Claude Code](https://claude.com/claude-code) |
1199 | 1234 |
|
1200 | | -## [v8.5.5] - 2026-01-03 |
1201 | | - |
1202 | | -## Improved Error Handling and Logging |
1203 | | - |
1204 | | -This patch release enhances error handling and logging across all worker services for better debugging and reliability. |
1205 | | - |
1206 | | -### Changes |
1207 | | -- **Enhanced Error Logging**: Improved error context across SessionStore, SearchManager, SDKAgent, GeminiAgent, and OpenRouterAgent |
1208 | | -- **SearchManager**: Restored error handling for Chroma calls with improved logging |
1209 | | -- **SessionStore**: Enhanced error logging throughout database operations |
1210 | | -- **Bug Fix**: Fixed critical bug where `memory_session_id` could incorrectly equal `content_session_id` |
1211 | | -- **Hooks**: Streamlined error handling and loading states for better maintainability |
1212 | | - |
1213 | | -### Investigation Reports |
1214 | | -- Added detailed analysis documents for generator failures and observation duplication regressions |
1215 | | - |
1216 | | -**Full Changelog**: https://github.com/thedotmack/claude-mem/compare/v8.5.4...v8.5.5 |
1217 | | - |
|
0 commit comments