Commit Graph

8 Commits

Author SHA1 Message Date
catlog22
5cae3cb3c8 feat(memorycore): add tags system, session summaries, hook injection, tag filtering, and solidify compress mode
Implement 5 interconnected memorycore enhancements:

1. Tags backend: add tags TEXT column to memories table with migration,
   JSON array storage, full CRUD support via upsertMemory/getMemory/getMemories
2. LLM auto-tag extraction: extend extraction prompt to produce tags,
   parse and validate in pipeline, create CMEM from extraction results
3. Session summary API: expose rollout_summary via new REST endpoints
   GET /api/core-memory/sessions/summaries and sessions/:id/summary
4. Hook injection: increase SESSION_START_LIMIT to 1500, add Component 5
   (Recent Sessions) to UnifiedContextBuilder with 300-char budget
5. Tag filtering: add getMemoriesByTags() with json_each() for safe
   SQL matching, wire through MCP tool, CLI --tags flag, REST ?tags= param
6. Solidify compress mode: add --type compress to solidify.md with
   getRecentMemories(), archiveMemories(), buildCompressionMetadata()

Security fixes: safeParseTags() for corrupt DB data, json_each() instead
of LIKE injection, ESCAPE clause for searchSessionsByKeyword, singleton
store in unified-context-builder.
2026-02-23 22:56:25 +08:00
catlog22
99ee4e7d36 feat: unified task.json schema migration and multi-module updates
- Create task-schema.json (JSON Schema draft-07) with 10 field blocks fusing
  Unified JSONL, 6-field Task JSON, and Solution Schema advantages
- Migrate unified-execute-with-file from JSONL to .task/*.json directory scanning
- Migrate 3 producers (lite-plan, plan-converter, collaborative-plan) to
  .task/*.json multi-file output
- Add review-cycle Phase 7.5 export-to-tasks (FIX-*.json) and issue-resolve
  --export-tasks option
- Add schema compatibility annotations to action-planning-agent, workflow-plan,
  and tdd-plan
- Add spec-generator skill phases and templates
- Add memory v2 pipeline (consolidation, extraction, job scheduler, embedder)
- Add secret-redactor utility and core-memory enhancements
- Add codex-lens accuracy benchmarks and staged env config overrides
2026-02-11 17:40:56 +08:00
catlog22
e671b45948 feat: Enhance configuration management and embedding capabilities
- Added JSON-based settings management in Config class for embedding and LLM configurations.
- Introduced methods to save and load settings from a JSON file.
- Updated BaseEmbedder and its subclasses to include max_tokens property for better token management.
- Enhanced chunking strategy to support recursive splitting of large symbols with improved overlap handling.
- Implemented comprehensive tests for recursive splitting and chunking behavior.
- Added CLI tools configuration management for better integration with external tools.
- Introduced a new command for compacting session memory into structured text for recovery.
2025-12-24 16:32:27 +08:00
catlog22
45f92fe066 feat: 实现 MCP 工具集中式路径验证,增强安全性和可配置性
- 新增 path-validator.ts:参考 MCP filesystem 服务器设计的集中式路径验证器
  - 支持 CCW_PROJECT_ROOT 和 CCW_ALLOWED_DIRS 环境变量配置
  - 多层路径验证:绝对路径解析 → 沙箱检查 → 符号链接验证
  - 向后兼容:未设置环境变量时回退到 process.cwd()

- 更新所有 MCP 工具使用集中式路径验证:
  - write-file.ts: 使用 validatePath()
  - edit-file.ts: 使用 validatePath({ mustExist: true })
  - read-file.ts: 使用 validatePath() + getProjectRoot()
  - smart-search.ts: 使用 getProjectRoot()
  - core-memory.ts: 使用 getProjectRoot()

- MCP 服务器启动时输出项目根目录和允许目录信息

- MCP 管理界面增强:
  - CCW Tools 安装卡片新增路径设置 UI
  - 支持 CCW_PROJECT_ROOT 和 CCW_ALLOWED_DIRS 配置
  - 添加"使用当前项目"快捷按钮
  - 支持 Claude 和 Codex 两种模式
  - 添加中英文国际化翻译

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-21 18:14:06 +08:00
catlog22
c12ef3e772 feat: 优化 core_memory MCP 工具,支持跨项目导出和精简列表输出
- 新增 findMemoryAcrossProjects 函数,支持按 CMEM-xxx ID 跨所有项目搜索记忆
- export 操作增强:当前项目找不到时自动搜索所有项目数据库
- list 操作优化:返回精简格式,preview 截断为 100 字符,减少输出体积

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-21 16:39:45 +08:00
catlog22
31cc060837 feat: Add vector embeddings for core memory semantic search
- Add memory_chunks table for storing chunked content with embeddings
- Create Python embedder script (memory_embedder.py) using CodexLens fastembed
- Add TypeScript bridge (memory-embedder-bridge.ts) for Python interop
- Implement content chunking with paragraph/sentence-aware splitting
- Add vectorSimilarity dimension to clustering (weight 0.3)
- New CLI commands: ccw memory embed, search, embed-status
- Extend core-memory MCP tool with embed/search/embed_status operations

Clustering improvement: max relevance 0.388 → 0.809 (+109%)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-20 13:09:43 +08:00
catlog22
68f9de0c69 refactor: Replace knowledge graph with session clustering system
Remove legacy knowledge graph and evolution tracking features,
introduce new session clustering model for Core Memory.

Changes:
- Remove knowledge_graph, knowledge_graph_edges, evolution_history tables
- Add session_clusters, cluster_members, cluster_relations tables
- Add session_metadata_cache for metadata caching
- Add new interfaces: SessionCluster, ClusterMember, ClusterRelation, SessionMetadataCache
- Add CRUD methods for cluster management
- Add session metadata upsert and search methods
- Remove extractKnowledgeGraph, getKnowledgeGraph, trackEvolution methods
- Remove API routes for /knowledge-graph, /evolution, /graph
- Add database migration to clean up old tables
- Update generateClusterId() for CLST-* ID format

Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2025-12-18 19:21:52 +08:00
catlog22
e096fc98e2 feat: Implement core memory management with knowledge graph and evolution tracking
- Added core-memory.js and core-memory-graph.js for managing core memory views and visualizations.
- Introduced functions for viewing knowledge graphs and evolution history of memories.
- Implemented modal dialogs for creating, editing, and viewing memory details.
- Developed core-memory.ts for backend operations including list, import, export, and summary generation.
- Integrated Zod for parameter validation in core memory operations.
- Enhanced UI with dynamic rendering of memory cards and detailed views.
2025-12-18 10:07:29 +08:00