mirror of
https://github.com/thedotmack/claude-mem
synced 2026-04-25 17:15:04 +02:00
3ea0b60b9f
* feat: add domain management system with support for multiple domain profiles
- Introduced DomainManager class for loading and managing domain profiles.
- Added support for a default domain ('code') and fallback mechanisms.
- Implemented domain configuration validation and error handling.
- Created types for domain configuration, observation types, and concepts.
- Added new directory for domain profiles and ensured its existence.
- Updated SettingsDefaultsManager to include CLAUDE_MEM_DOMAIN setting.
* Refactor domain management to mode management
- Removed DomainManager class and replaced it with ModeManager for better clarity and functionality.
- Updated types from DomainConfig to ModeConfig and DomainPrompts to ModePrompts.
- Changed references from domains to modes in the settings and paths.
- Ensured backward compatibility by maintaining the fallback mechanism to the 'code' mode.
* feat: add migration 008 to support mode-agnostic observations and refactor service layer references in documentation
* feat: add new modes for code development and email investigation with detailed observation types and concepts
* Refactor observation parsing and prompt generation to incorporate mode-specific configurations
- Updated `parseObservations` function to use 'observation' as a universal fallback type instead of 'change', utilizing active mode's valid observation types.
- Modified `buildInitPrompt` and `buildContinuationPrompt` functions to accept a `ModeConfig` parameter, allowing for dynamic prompt content based on the active mode.
- Enhanced `ModePrompts` interface to include additional guidance for observers, such as recording focus and skip guidance.
- Adjusted the SDKAgent to load the active mode and pass it to prompt generation functions, ensuring prompts are tailored to the current mode's context.
* fix: correct mode prompt injection to preserve exact wording and type list visibility
- Add script to extract prompts from main branch prompts.ts into code.yaml
- Fix prompts.ts to show type list in XML template (e.g., "[ bugfix | feature | ... ]")
- Keep 'change' as fallback type in parser.ts (maintain backwards compatibility)
- Regenerate code.yaml with exact wording from original hardcoded prompts
- Build succeeds with no TypeScript errors
* fix: update ModeManager to load JSON mode files and improve validation
- Changed ModeManager to load mode configurations from JSON files instead of YAML.
- Removed the requirement for an "observation" type and updated validation to require at least one observation type.
- Updated fallback behavior in the parser to use the first type from the active mode's type list.
- Added comprehensive tests for mode loading, prompt injection, and parser integration, ensuring correct behavior across different modes.
- Introduced new mode JSON files for "Code Development" and "Email Investigation" with detailed observation types and prompts.
* Add mode configuration loading and update licensing information for Ragtime
- Implemented loading of mode configuration in WorkerService before database initialization.
- Added PolyForm Noncommercial License 1.0.0 to Ragtime directory.
- Created README.md for Ragtime with licensing details and usage guidelines.
* fix: add datasets directory to .gitignore to prevent accidental commits
* refactor: remove unused plugin package.json file
* chore: add package.json for claude-mem plugin with version 7.4.5
* refactor: remove outdated tests and improve error handling
- Deleted tests for ChromaSync error handling, smart install, strip memory tags, and user prompt tag stripping due to redundancy or outdated logic.
- Removed vitest configuration as it is no longer needed.
- Added a comprehensive implementation plan for fixing the modes system, addressing critical issues and improving functionality.
- Created a detailed test analysis report highlighting the quality and effectiveness of the current test suite, identifying areas for improvement.
- Introduced a new plugin package.json for runtime dependencies related to claude-mem hooks.
* refactor: remove parser regression tests to streamline codebase
* docs: update CLAUDE.md to clarify test management and changelog generation
* refactor: remove migration008 for mode-agnostic observations
* Refactor observation type handling to use ModeManager for icons and emojis
- Removed direct mappings of observation types to icons and work emojis in context-generator, FormattingService, SearchManager, and TimelineService.
- Integrated ModeManager to dynamically retrieve icons and emojis based on the active mode.
- Improved maintainability by centralizing the logic for observation type representation.
* Refactor observation metadata constants and update context generator
- Removed the explicit declaration of OBSERVATION_TYPES and OBSERVATION_CONCEPTS from observation-metadata.ts.
- Introduced fallback default strings for DEFAULT_OBSERVATION_TYPES_STRING and DEFAULT_OBSERVATION_CONCEPTS_STRING.
- Updated context-generator.ts to utilize observation types and concepts from ModeManager instead of constants.
* refactor: remove intermediate error handling from hooks (Phase 1)
Apply "fail fast" error handling strategy - errors propagate and crash loud
instead of being caught, wrapped, and re-thrown at intermediate layers.
Changes:
- Remove try/catch around fetch calls in all hooks - let errors throw
- Add try/catch ONLY around JSON.parse at entry points
- Delete error-handler.ts and hook-error-handler.ts (no longer needed)
- Update worker-utils.ts: functions now throw instead of returning null
- Update transcript-parser.ts: throw on missing path, empty file, malformed JSON
- Remove all handleWorkerError, handleFetchError imports
Philosophy: If something breaks, we KNOW it broke. No silent failures.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: remove intermediate error handling from worker service (Phase 2)
Apply "fail fast" error handling strategy to worker service layer.
Changes:
- worker-service.ts: Remove try/catch from version endpoint, cleanup,
MCP close, process enumeration, force kill, and isAlive check
- SessionRoutes.ts: Remove try/catch from JSON.stringify calls, remove
.catch() from Chroma sync and SDK agent calls
- SettingsRoutes.ts: Remove try/catch from toggleMcp()
- DatabaseManager.ts: Remove .catch() from backfill and close operations
- SDKAgent.ts: Keep outer try/catch (top-level), remove .catch() from
Chroma sync operations
- SSEBroadcaster.ts: Remove try/catch from broadcast and sendToClient
Philosophy: Errors propagate and crash loud. BaseRouteHandler.wrapHandler
provides top-level catching for HTTP routes.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: remove error swallowing from SQLite services (Phase 3)
Apply "fail fast" error handling strategy to database layer.
SessionStore.ts migrations:
- ensureWorkerPortColumn(): Remove outer try/catch, let it throw
- ensurePromptTrackingColumns(): Remove outer try/catch, let it throw
- removeSessionSummariesUniqueConstraint(): Keep inner transaction
rollback, remove outer catch
- addObservationHierarchicalFields(): Remove outer try/catch
- makeObservationsTextNullable(): Keep inner transaction rollback,
remove outer catch
- createUserPromptsTable(): Keep inner transaction rollback, remove
outer catch
- getFilesForSession(): Remove try/catch around JSON.parse
SessionSearch.ts:
- ensureFTSTables(): Remove try/catch, let it throw
Philosophy: Migration errors that are swallowed mean we think the
database is fine when it's not. Keep only inner transaction rollback
try/catch blocks.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* refactor: remove error hiding from utilities (Phase 4)
Apply "fail fast" error handling strategy to utility layer.
logger.ts:
- formatTool(): Remove try/catch, let JSON.parse throw on malformed input
context-generator.ts:
- loadContextConfig(): Remove try/catch, let parseInt throw on invalid settings
- Transcript extraction: Remove try/catch, let file read errors propagate
ChromaSync.ts:
- close(): Remove nested try/catch blocks, let close errors propagate
Philosophy: No silent fallbacks or hidden defaults. If something breaks,
we know it broke immediately.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: serve static UI assets and update package root path
- Added middleware to serve static UI assets (JS, CSS, fonts, etc.) in ViewerRoutes.
- Updated getPackageRoot function to correctly return the package root directory as one level up from the current directory.
* feat: Enhance mode loading with inheritance support
- Introduced parseInheritance method to handle parent--override mode IDs.
- Added deepMerge method for recursively merging mode configurations.
- Updated loadMode method to support inheritance, loading parent modes and applying overrides.
- Improved error handling for missing mode files and logging for better traceability.
* fix(modes): correct inheritance file resolution and path handling
* Refactor code structure for improved readability and maintainability
* feat: Add mode configuration documentation and examples
* fix: Improve concurrency handling in translateReadme function
* Refactor SDK prompts to enhance clarity and structure
- Updated the `buildInitPrompt` and `buildContinuationPrompt` functions in `prompts.ts` to improve the organization of prompt components, including the addition of language instructions and footer messages.
- Removed redundant instructions and emphasized the importance of recording observations.
- Modified the `ModePrompts` interface in `types.ts` to include new properties for system identity, language instructions, and output format header, ensuring better flexibility and clarity in prompt generation.
* Enhance prompts with language instructions and XML formatting
- Updated `buildInitPrompt`, `buildSummaryPrompt`, and `buildContinuationPrompt` functions to include detailed language instructions in XML comments.
- Ensured that language instructions guide users to keep XML tags in English while writing content in the specified language.
- Modified the `buildSummaryPrompt` function to accept `mode` as a parameter for consistency.
- Adjusted the call to `buildSummaryPrompt` in `SDKAgent` to pass the `mode` argument.
* Refactor XML prompt generation in SDK
- Updated the buildInitPrompt, buildSummaryPrompt, and buildContinuationPrompt functions to use new placeholders for XML elements, improving maintainability and readability.
- Removed redundant language instructions in comments for clarity.
- Added new properties to ModePrompts interface for better structure and organization of XML placeholders and section headers.
* feat: Update observation prompts and structure across multiple languages
* chore: Remove planning docs and update Ragtime README
Remove ephemeral development artifacts:
- .claude/plans/modes-system-fixes.md
- .claude/test-analysis-report.md
- PROMPT_INJECTION_ANALYSIS.md
Update ragtime/README.md to explain:
- Feature is not yet implemented
- Dependency on modes system (now complete in PR #412)
- Ready to be scripted out in future release
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* fix: Move summary prompts to mode files for multilingual support
Summary prompts were hardcoded in English in prompts.ts, breaking
multilingual support. Now properly mode-based:
- Added summary_instruction, summary_context_label,
summary_format_instruction, summary_footer to code.json
- Updated buildSummaryPrompt() to use mode fields instead of hardcoded text
- Added summary_footer with language instructions to all 10 language modes
- Language modes keep English prompts + language requirement footer
This fixes the gaslighting where we claimed full multilingual support
but summaries were still generated in English.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* chore: Clean up README by removing local preview instructions and streamlining beta features section
* Add translated README files for Ukrainian, Vietnamese, and Chinese languages
* Add new language modes for code development in multiple languages
- Introduced JSON configurations for Code Development in Greek, Finnish, Hebrew, Hindi, Hungarian, Indonesian, Italian, Dutch, Norwegian, Polish, Brazilian Portuguese, Romanian, Swedish, Turkish, and Ukrainian.
- Each configuration includes prompts for observations, summaries, and instructions tailored to the respective language.
- Ensured that all prompts emphasize the importance of generating observations without referencing the agent's actions.
* Add multilingual support links to README files in various languages
- Updated README.id.md, README.it.md, README.ja.md, README.ko.md, README.nl.md, README.no.md, README.pl.md, README.pt-br.md, README.ro.md, README.ru.md, README.sv.md, README.th.md, README.tr.md, README.uk.md, README.vi.md, and README.zh.md to include links to other language versions.
- Each README now features a centered paragraph with flags and links for easy navigation between different language documents.
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
14 KiB
14 KiB
🌐 Esta es una traducción automática. ¡Las correcciones de la comunidad son bienvenidas!
🇨🇳 中文 • 🇯🇵 日本語 • 🇧🇷 Português • 🇰🇷 한국어 • 🇪🇸 Español • 🇩🇪 Deutsch • 🇫🇷 Français 🇮🇱 עברית • 🇸🇦 العربية • 🇷🇺 Русский • 🇵🇱 Polski • 🇨🇿 Čeština • 🇳🇱 Nederlands • 🇹🇷 Türkçe • 🇺🇦 Українська • 🇻🇳 Tiếng Việt • 🇮🇩 Indonesia • 🇹🇭 ไทย • 🇮🇳 हिन्दी • 🇧🇩 বাংলা • 🇷🇴 Română • 🇸🇪 Svenska • 🇮🇹 Italiano • 🇬🇷 Ελληνικά • 🇭🇺 Magyar • 🇫🇮 Suomi • 🇩🇰 Dansk • 🇳🇴 Norsk
Sistema de compresión de memoria persistente construido para Claude Code.
Inicio Rápido • Cómo Funciona • Herramientas de Búsqueda • Documentación • Configuración • Solución de Problemas • Licencia
Claude-Mem preserva el contexto sin interrupciones entre sesiones al capturar automáticamente observaciones de uso de herramientas, generar resúmenes semánticos y ponerlos a disposición de sesiones futuras. Esto permite a Claude mantener la continuidad del conocimiento sobre proyectos incluso después de que las sesiones terminen o se reconecten.
Inicio Rápido
Inicia una nueva sesión de Claude Code en la terminal e ingresa los siguientes comandos:
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
Reinicia Claude Code. El contexto de sesiones anteriores aparecerá automáticamente en nuevas sesiones.
Características Principales:
- 🧠 Memoria Persistente - El contexto sobrevive entre sesiones
- 📊 Divulgación Progresiva - Recuperación de memoria en capas con visibilidad del costo de tokens
- 🔍 Búsqueda Basada en Habilidades - Consulta el historial de tu proyecto con la habilidad mem-search
- 🖥️ Interfaz de Visor Web - Transmisión de memoria en tiempo real en http://localhost:37777
- 💻 Habilidad para Claude Desktop - Busca en la memoria desde conversaciones de Claude Desktop
- 🔒 Control de Privacidad - Usa etiquetas
<private>para excluir contenido sensible del almacenamiento - ⚙️ Configuración de Contexto - Control detallado sobre qué contexto se inyecta
- 🤖 Operación Automática - No se requiere intervención manual
- 🔗 Citas - Referencias a observaciones pasadas con IDs (accede vía http://localhost:37777/api/observation/{id} o visualiza todas en el visor web en http://localhost:37777)
- 🧪 Canal Beta - Prueba características experimentales como Endless Mode mediante cambio de versión
Documentación
📚 Ver Documentación Completa - Explora documentos markdown en GitHub
Primeros Pasos
- Guía de Instalación - Inicio rápido e instalación avanzada
- Guía de Uso - Cómo funciona Claude-Mem automáticamente
- Herramientas de Búsqueda - Consulta el historial de tu proyecto con lenguaje natural
- Características Beta - Prueba características experimentales como Endless Mode
Mejores Prácticas
- Ingeniería de Contexto - Principios de optimización de contexto para agentes de IA
- Divulgación Progresiva - Filosofía detrás de la estrategia de preparación de contexto de Claude-Mem
Arquitectura
- Descripción General - Componentes del sistema y flujo de datos
- Evolución de la Arquitectura - El viaje de v3 a v5
- Arquitectura de Hooks - Cómo Claude-Mem usa hooks de ciclo de vida
- Referencia de Hooks - 7 scripts de hooks explicados
- Servicio Worker - API HTTP y gestión de Bun
- Base de Datos - Esquema SQLite y búsqueda FTS5
- Arquitectura de Búsqueda - Búsqueda híbrida con base de datos vectorial Chroma
Configuración y Desarrollo
- Configuración - Variables de entorno y ajustes
- Desarrollo - Compilación, pruebas y contribución
- Solución de Problemas - Problemas comunes y soluciones
Cómo Funciona
Componentes Principales:
- 5 Hooks de Ciclo de Vida - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 scripts de hooks)
- Instalación Inteligente - Verificador de dependencias en caché (script pre-hook, no un hook de ciclo de vida)
- Servicio Worker - API HTTP en el puerto 37777 con interfaz de visor web y 10 endpoints de búsqueda, gestionado por Bun
- Base de Datos SQLite - Almacena sesiones, observaciones, resúmenes
- Habilidad mem-search - Consultas en lenguaje natural con divulgación progresiva
- Base de Datos Vectorial Chroma - Búsqueda híbrida semántica + palabras clave para recuperación inteligente de contexto
Ver Descripción General de la Arquitectura para más detalles.
Habilidad mem-search
Claude-Mem proporciona búsqueda inteligente a través de la habilidad mem-search que se invoca automáticamente cuando preguntas sobre trabajo previo:
Cómo Funciona:
- Simplemente pregunta naturalmente: "¿Qué hicimos en la última sesión?" o "¿Arreglamos este error antes?"
- Claude invoca automáticamente la habilidad mem-search para encontrar contexto relevante
Operaciones de Búsqueda Disponibles:
- Search Observations - Búsqueda de texto completo en observaciones
- Search Sessions - Búsqueda de texto completo en resúmenes de sesiones
- Search Prompts - Búsqueda de solicitudes de usuario sin procesar
- By Concept - Buscar por etiquetas de concepto (discovery, problem-solution, pattern, etc.)
- By File - Buscar observaciones que referencian archivos específicos
- By Type - Buscar por tipo (decision, bugfix, feature, refactor, discovery, change)
- Recent Context - Obtener contexto de sesión reciente para un proyecto
- Timeline - Obtener línea de tiempo unificada de contexto alrededor de un punto específico en el tiempo
- Timeline by Query - Buscar observaciones y obtener contexto de línea de tiempo alrededor de la mejor coincidencia
- API Help - Obtener documentación de la API de búsqueda
Ejemplos de Consultas en Lenguaje Natural:
"What bugs did we fix last session?"
"How did we implement authentication?"
"What changes were made to worker-service.ts?"
"Show me recent work on this project"
"What was happening when we added the viewer UI?"
Ver Guía de Herramientas de Búsqueda para ejemplos detallados.
Características Beta
Claude-Mem ofrece un canal beta con características experimentales como Endless Mode (arquitectura de memoria biomimética para sesiones extendidas). Cambia entre versiones estables y beta desde la interfaz del visor web en http://localhost:37777 → Settings.
Ver Documentación de Características Beta para detalles sobre Endless Mode y cómo probarlo.
Requisitos del Sistema
- Node.js: 18.0.0 o superior
- Claude Code: Última versión con soporte de plugins
- Bun: Runtime de JavaScript y gestor de procesos (se instala automáticamente si falta)
- uv: Gestor de paquetes de Python para búsqueda vectorial (se instala automáticamente si falta)
- SQLite 3: Para almacenamiento persistente (incluido)
Configuración
Los ajustes se gestionan en ~/.claude-mem/settings.json (se crea automáticamente con valores predeterminados en la primera ejecución). Configura el modelo de IA, puerto del worker, directorio de datos, nivel de registro y ajustes de inyección de contexto.
Ver la Guía de Configuración para todos los ajustes disponibles y ejemplos.
Desarrollo
Ver la Guía de Desarrollo para instrucciones de compilación, pruebas y flujo de contribución.
Solución de Problemas
Si experimentas problemas, describe el problema a Claude y la habilidad troubleshoot diagnosticará automáticamente y proporcionará soluciones.
Ver la Guía de Solución de Problemas para problemas comunes y soluciones.
Reportes de Errores
Crea reportes de errores completos con el generador automático:
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
Contribuciones
¡Las contribuciones son bienvenidas! Por favor:
- Haz fork del repositorio
- Crea una rama de característica
- Realiza tus cambios con pruebas
- Actualiza la documentación
- Envía un Pull Request
Ver Guía de Desarrollo para el flujo de contribución.
Licencia
Este proyecto está licenciado bajo la GNU Affero General Public License v3.0 (AGPL-3.0).
Copyright (C) 2025 Alex Newman (@thedotmack). Todos los derechos reservados.
Ver el archivo LICENSE para detalles completos.
Lo Que Esto Significa:
- Puedes usar, modificar y distribuir este software libremente
- Si modificas y despliegas en un servidor de red, debes hacer tu código fuente disponible
- Los trabajos derivados también deben estar licenciados bajo AGPL-3.0
- NO hay GARANTÍA para este software
Nota sobre Ragtime: El directorio ragtime/ está licenciado por separado bajo la PolyForm Noncommercial License 1.0.0. Ver ragtime/LICENSE para detalles.
Soporte
- Documentación: docs/
- Problemas: GitHub Issues
- Repositorio: github.com/thedotmack/claude-mem
- Autor: Alex Newman (@thedotmack)
Construido con Claude Agent SDK | Impulsado por Claude Code | Hecho con TypeScript