Exemplos de checkpoints
InicianteGrátis6 minatualizado 2026-10-21
Exemplos reais de utilização eficaz de checkpoints no Claude Code.
Nota: os checkpoints são criados automaticamente a cada prompt do utilizador. Não precisa de os guardar manualmente. Para retroceder, prima Esc duas vezes (Esc+Esc) ou use /rewind para abrir o navegador de checkpoints.
Exemplo 1: Migração de base de dados
Cenário
Precisa de migrar de MySQL para PostgreSQL, mas quer explorar tanto uma migração direta como uma abordagem gradual de escrita dupla.
Fluxo de trabalho
Terminal
User: Let's implement a direct migration from MySQL to PostgreSQL
[Checkpoint A created automatically]
Claude: I'll implement the direct migration...
[Changes database driver, updates queries, modifies schema]
User: Run the tests
[Checkpoint B created automatically]
Claude: Running tests...
❌ 15 tests failing - connection pool issues
User: This approach has issues. Let's try the dual-write pattern instead.
[User presses Esc+Esc, selects Checkpoint A, chooses "Restore code and conversation"]
User: Now implement a dual-write pattern where we write to both databases
Claude: I'll implement dual-write migration...
[Implements dual-write layer, gradual migration strategy]
User: Run the tests
Claude: Running tests...
✅ All tests passing
User: The dual-write approach is clearly safer. Let's commit this.Exemplo 2: Otimização de Desempenho
Cenário
Várias estratégias de otimização de desempenho para experimentar.
Fluxo de trabalho
Terminal
User: Let's optimize the API response time. Current: 450ms
[Checkpoint "Baseline" created automatically]
Claude: I'll add database query caching...
[Implements Redis caching]
User: Run performance tests
Claude: Results: 280ms average response time (38% improvement)
User: Let me try a different approach.
[User presses Esc+Esc, selects "Baseline" checkpoint, chooses "Restore code and conversation"]
User: Try database query optimization instead
Claude: I'll optimize database queries...
[Adds indexes, optimizes N+1 queries]
User: Run performance tests
Claude: Results: 180ms average response time (60% improvement)
User: Let me also try a third approach.
[User presses Esc+Esc, selects "Baseline" checkpoint, chooses "Restore code and conversation"]
User: Try response compression and CDN
Claude: I'll add compression and CDN...
[Implements gzip, sets up CDN]
User: Run performance tests
Claude: Results: 320ms average response time (29% improvement)
User: Query optimization was the best. Let me go back and combine it with caching.
[User presses Esc+Esc, selects the checkpoint after query optimization, chooses "Restore code and conversation"]
User: Now add Redis caching on top of these optimized queries
Claude: [Adds Redis caching on top of optimized queries]
User: Run performance tests
Claude: Results: 95ms average response time (79% improvement) 🎉
User: Perfect! This is the winner. Let's commit this.Exemplo 3: Iteração de UI/UX
Cenário
Experimentar diferentes layouts para um dashboard.
Fluxo de trabalho
Terminal
User: Let's redesign the dashboard with a sidebar layout
[Checkpoint "Start" created automatically]
Claude: [Implements sidebar layout]
User: Show me a screenshot
Claude: [Shows screenshot]
User: The sidebar feels cramped. Let's try a top navigation instead.
[User presses Esc+Esc, selects "Start" checkpoint, chooses "Restore code and conversation"]
User: Try a top navigation layout
Claude: [Implements top navigation]
User: Show me a screenshot
Claude: [Shows screenshot]
User: Better, but let's try a card-based grid layout
[User presses Esc+Esc, selects "Start" checkpoint, chooses "Restore code and conversation"]
User: Try a card-based grid layout
Claude: [Implements card grid]
User: Show me a screenshot
Claude: [Shows screenshot]
User: This is great! But can we combine the top nav with the card grid?
[User presses Esc+Esc, selects the checkpoint after the card grid, chooses "Restore code and conversation"]
User: Add top navigation to the card grid layout
Claude: [Adds top navigation to card grid]
User: Perfect! This is the final design.Exemplo 4: Sessão de depuração
Cenário
Caçar um bug complicado com múltiplas hipóteses.
Fluxo de trabalho
Terminal
User: There's a memory leak in the application
[Checkpoint "Before debugging" created automatically]
Claude: Let me investigate...
[Analyzes code]
User: I think it's in the event listeners. Let's fix those.
Claude: [Fixes event listener cleanup]
User: Run memory profiler
Claude: Still leaking memory - event listeners weren't the issue
User: Let me go back and try a different hypothesis.
[User presses Esc+Esc, selects "Before debugging" checkpoint, chooses "Restore code and conversation"]
User: Maybe it's the database connections?
Claude: [Implements connection pooling fixes]
User: Run memory profiler
Claude: Still leaking - not the connections either
User: Let me go back and try another angle.
[User presses Esc+Esc, selects "Before debugging" checkpoint, chooses "Restore code and conversation"]
User: Let's check for circular references
Claude: [Finds and fixes circular references in cache]
User: Run memory profiler
Claude: ✅ Memory leak fixed! The circular references in the caching layer were the culprit.
User: Excellent! Let's commit this fix.Exemplo 5: Evolução do design de uma API
Cenário
Conceção de uma API REST com múltiplas iterações.
Fluxo de trabalho
Terminal
User: Create a REST API for our blog platform
[Checkpoint "Before API design" created automatically]
Claude: [Creates basic CRUD API]
User: This is too simple. Let's add pagination and filtering
Claude: [Adds pagination and filtering]
User: We need better resource relationships
Claude: [Implements HATEOAS links]
User: Actually, let's try GraphQL instead of REST
[User presses Esc+Esc, selects "Before API design" checkpoint, chooses "Restore code and conversation"]
User: Implement a GraphQL API for our blog platform instead
Claude: [Implements GraphQL API]
User: I think REST is better for our use case.
[User presses Esc+Esc, selects the checkpoint after HATEOAS, chooses "Restore code and conversation"]
User: Let's finalize the REST approach.Exemplo 6: Gestão de Configuração
Cenário
Testar diferentes abordagens de configuração.
Fluxo de Trabalho
Terminal
User: Move configuration to environment variables
[Checkpoint "Original config" created automatically]
Claude: [Implements env var configuration]
User: Test in development
Claude: Works locally but deployment issues in production
User: Let me try a different approach.
[User presses Esc+Esc, selects "Original config" checkpoint, chooses "Restore code and conversation"]
User: Try a config file approach with validation
Claude: [Implements YAML config with JSON schema validation]
User: Test in development
Claude: ✅ Works well, good validation errors
User: Can we also support env vars for sensitive values?
Claude: [Adds env var override for secrets]
User: Test deployment
Claude: ✅ All environments working correctly
User: Perfect! This is production-ready.Exemplo 7: Estratégia de testes
Cenário
Implementar testes abrangentes.
Fluxo de trabalho
Terminal
User: Add unit tests for the auth module
[Checkpoint created automatically]
Claude: [Adds Jest unit tests]
User: Run tests
Claude: 45 tests passing, 78% coverage
User: Add integration tests too
Claude: [Adds integration tests]
User: Run tests
Claude: 89 tests passing, 92% coverage, but tests are slow (3 minutes)
User: The tests are too slow. Let's optimize.
Claude: [Optimizes test setup, adds parallel execution]
User: Run tests
Claude: 89 tests passing, 92% coverage, 35 seconds ✅
User: Great! Now add E2E tests for critical paths
Claude: [Adds Playwright E2E tests]
User: Run all tests
Claude: 112 tests passing, 94% coverage, 2 minutes
User: Perfect balance of coverage and speed!Exemplo 8: Utilizar o Summarize a partir de um Checkpoint
Cenário
Depois de uma longa sessão de depuração, pretende condensar a conversa mantendo o contexto.
Fluxo de trabalho
Terminal
User: [After 20+ messages of debugging and exploration]
[User presses Esc+Esc, selects an early checkpoint, chooses "Summarize from here"]
[Optionally provides instructions: "Focus on what we tried and what worked"]
Claude: [Generates a summary of the conversation from that point forward]
[Original messages are preserved in the transcript]
[The summary replaces the visible conversation, reducing context window usage]
User: Now let's continue with the approach that worked.Pontos-chave
- Os checkpoints são automáticos: cada prompt do utilizador cria um checkpoint - não é preciso guardar manualmente
- Use Esc+Esc ou /rewind: estas são as duas formas de aceder ao explorador de checkpoints
- Escolha a opção de restauro certa: restaure o código, a conversa, ambos, ou faça um resumo, consoante as suas necessidades
- Não tenha medo de experimentar: os checkpoints permitem experimentar alterações radicais com segurança
- Combine com o git: use os checkpoints para exploração e o git para o trabalho finalizado
- Resuma sessões longas: use "Summarize from here" para manter as conversas geríveis
Última atualização: 29 de julho de 2026
Versão do Claude Code: 2.1.220
Fontes:
- https://code.claude.com/docs/en/checkpointing
- https://code.claude.com/docs/en/changelog
- https://code.claude.com/docs/en/model-config
Modelos compatíveis: Claude Fable 5, Claude Opus 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Haiku 4.5
Guia da comunidade open-source (MIT) · tradução e manutenção Doutor AI.
Precisa de uma solução à medida?
Não sabe por onde começar a usar IA no seu negócio? Receba uma avaliação gratuita e um plano à medida - sem compromisso.
Poupe horas todas as semanas com IA, sem complicações
O Doutor AI dá-lhe 1859 prompts de IA prontos a copiar, por indústria e em português simples - mais uma biblioteca técnica completa para quem quer ir mais longe.
Ver planos