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
🌐 Questa è una traduzione automatica. Le correzioni della comunità sono benvenute!
🇨🇳 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 di compressione della memoria persistente creato per Claude Code.
Avvio Rapido • Come Funziona • Strumenti di Ricerca • Documentazione • Configurazione • Risoluzione dei Problemi • Licenza
Claude-Mem preserva il contesto in modo fluido tra le sessioni catturando automaticamente le osservazioni sull'utilizzo degli strumenti, generando riepiloghi semantici e rendendoli disponibili per le sessioni future. Questo consente a Claude di mantenere la continuità della conoscenza sui progetti anche dopo la fine o la riconnessione delle sessioni.
Avvio Rapido
Avvia una nuova sessione di Claude Code nel terminale e inserisci i seguenti comandi:
> /plugin marketplace add thedotmack/claude-mem
> /plugin install claude-mem
Riavvia Claude Code. Il contesto delle sessioni precedenti apparirà automaticamente nelle nuove sessioni.
Caratteristiche Principali:
- 🧠 Memoria Persistente - Il contesto sopravvive tra le sessioni
- 📊 Divulgazione Progressiva - Recupero della memoria a strati con visibilità del costo in token
- 🔍 Ricerca Basata su Skill - Interroga la cronologia del tuo progetto con la skill mem-search
- 🖥️ Interfaccia Web Viewer - Stream della memoria in tempo reale su http://localhost:37777
- 💻 Skill per Claude Desktop - Cerca nella memoria dalle conversazioni di Claude Desktop
- 🔒 Controllo della Privacy - Usa i tag
<private>per escludere contenuti sensibili dall'archiviazione - ⚙️ Configurazione del Contesto - Controllo granulare su quale contesto viene iniettato
- 🤖 Funzionamento Automatico - Nessun intervento manuale richiesto
- 🔗 Citazioni - Fai riferimento a osservazioni passate con ID (accedi tramite http://localhost:37777/api/observation/{id} o visualizza tutto nel web viewer su http://localhost:37777)
- 🧪 Canale Beta - Prova funzionalità sperimentali come Endless Mode tramite il cambio di versione
Documentazione
📚 Visualizza Documentazione Completa - Sfoglia i documenti markdown su GitHub
Per Iniziare
- Guida all'Installazione - Avvio rapido e installazione avanzata
- Guida all'Uso - Come funziona automaticamente Claude-Mem
- Strumenti di Ricerca - Interroga la cronologia del progetto con linguaggio naturale
- Funzionalità Beta - Prova funzionalità sperimentali come Endless Mode
Best Practice
- Context Engineering - Principi di ottimizzazione del contesto per agenti AI
- Progressive Disclosure - Filosofia alla base della strategia di priming del contesto di Claude-Mem
Architettura
- Panoramica - Componenti del sistema e flusso dei dati
- Evoluzione dell'Architettura - Il percorso dalla v3 alla v5
- Architettura degli Hook - Come Claude-Mem utilizza gli hook del ciclo di vita
- Riferimento Hook - Spiegazione dei 7 script hook
- Servizio Worker - API HTTP e gestione Bun
- Database - Schema SQLite e ricerca FTS5
- Architettura di Ricerca - Ricerca ibrida con database vettoriale Chroma
Configurazione e Sviluppo
- Configurazione - Variabili d'ambiente e impostazioni
- Sviluppo - Build, test e flusso di contribuzione
- Risoluzione dei Problemi - Problemi comuni e soluzioni
Come Funziona
Componenti Principali:
- 5 Hook del Ciclo di Vita - SessionStart, UserPromptSubmit, PostToolUse, Stop, SessionEnd (6 script hook)
- Installazione Intelligente - Controllo delle dipendenze in cache (script pre-hook, non un hook del ciclo di vita)
- Servizio Worker - API HTTP sulla porta 37777 con interfaccia web viewer e 10 endpoint di ricerca, gestita da Bun
- Database SQLite - Memorizza sessioni, osservazioni, riepiloghi
- Skill mem-search - Query in linguaggio naturale con divulgazione progressiva
- Database Vettoriale Chroma - Ricerca ibrida semantica + keyword per recupero intelligente del contesto
Vedi Panoramica dell'Architettura per i dettagli.
Skill mem-search
Claude-Mem fornisce una ricerca intelligente tramite la skill mem-search che si attiva automaticamente quando chiedi del lavoro passato:
Come Funziona:
- Chiedi semplicemente in modo naturale: "Cosa abbiamo fatto nell'ultima sessione?" o "Abbiamo già risolto questo bug prima?"
- Claude invoca automaticamente la skill mem-search per trovare il contesto rilevante
Operazioni di Ricerca Disponibili:
- Search Observations - Ricerca full-text nelle osservazioni
- Search Sessions - Ricerca full-text nei riepiloghi delle sessioni
- Search Prompts - Ricerca nelle richieste utente grezze
- By Concept - Trova per tag di concetto (discovery, problem-solution, pattern, ecc.)
- By File - Trova osservazioni che fanno riferimento a file specifici
- By Type - Trova per tipo (decision, bugfix, feature, refactor, discovery, change)
- Recent Context - Ottieni il contesto recente della sessione per un progetto
- Timeline - Ottieni la timeline unificata del contesto attorno a un punto specifico nel tempo
- Timeline by Query - Cerca osservazioni e ottieni il contesto della timeline attorno alla corrispondenza migliore
- API Help - Ottieni la documentazione dell'API di ricerca
Esempi di Query in Linguaggio Naturale:
"Quali bug abbiamo risolto nell'ultima sessione?"
"Come abbiamo implementato l'autenticazione?"
"Quali modifiche sono state apportate a worker-service.ts?"
"Mostrami il lavoro recente su questo progetto"
"Cosa stava succedendo quando abbiamo aggiunto l'interfaccia del viewer?"
Vedi Guida agli Strumenti di Ricerca per esempi dettagliati.
Funzionalità Beta
Claude-Mem offre un canale beta con funzionalità sperimentali come Endless Mode (architettura di memoria biomimetica per sessioni estese). Passa dalla versione stabile a quella beta dall'interfaccia web viewer su http://localhost:37777 → Settings.
Vedi Documentazione delle Funzionalità Beta per dettagli su Endless Mode e come provarlo.
Requisiti di Sistema
- Node.js: 18.0.0 o superiore
- Claude Code: Ultima versione con supporto plugin
- Bun: Runtime JavaScript e process manager (installato automaticamente se mancante)
- uv: Gestore di pacchetti Python per la ricerca vettoriale (installato automaticamente se mancante)
- SQLite 3: Per l'archiviazione persistente (incluso)
Configurazione
Le impostazioni sono gestite in ~/.claude-mem/settings.json (creato automaticamente con valori predefiniti alla prima esecuzione). Configura il modello AI, la porta del worker, la directory dei dati, il livello di log e le impostazioni di iniezione del contesto.
Vedi la Guida alla Configurazione per tutte le impostazioni disponibili ed esempi.
Sviluppo
Vedi la Guida allo Sviluppo per le istruzioni di build, test e flusso di contribuzione.
Risoluzione dei Problemi
Se riscontri problemi, descrivi il problema a Claude e la skill troubleshoot diagnosticherà automaticamente e fornirà correzioni.
Vedi la Guida alla Risoluzione dei Problemi per problemi comuni e soluzioni.
Segnalazione Bug
Crea report di bug completi con il generatore automatizzato:
cd ~/.claude/plugins/marketplaces/thedotmack
npm run bug-report
Contribuire
I contributi sono benvenuti! Per favore:
- Fai il fork del repository
- Crea un branch per la funzionalità
- Apporta le tue modifiche con i test
- Aggiorna la documentazione
- Invia una Pull Request
Vedi Guida allo Sviluppo per il flusso di contribuzione.
Licenza
Questo progetto è rilasciato sotto la GNU Affero General Public License v3.0 (AGPL-3.0).
Copyright (C) 2025 Alex Newman (@thedotmack). Tutti i diritti riservati.
Vedi il file LICENSE per i dettagli completi.
Cosa Significa:
- Puoi usare, modificare e distribuire questo software liberamente
- Se modifichi e distribuisci su un server di rete, devi rendere disponibile il tuo codice sorgente
- Le opere derivate devono anche essere rilasciate sotto AGPL-3.0
- NON c'è GARANZIA per questo software
Nota su Ragtime: La directory ragtime/ è rilasciata separatamente sotto la PolyForm Noncommercial License 1.0.0. Vedi ragtime/LICENSE per i dettagli.
Supporto
- Documentazione: docs/
- Problemi: GitHub Issues
- Repository: github.com/thedotmack/claude-mem
- Autore: Alex Newman (@thedotmack)
Creato con Claude Agent SDK | Alimentato da Claude Code | Realizzato con TypeScript