wehub-resource-sync
e76d0ad892
CI / Test (macos-latest, Node 18.x, bun) (push) Has been cancelled
CI / Test (macos-latest, Node 18.x, npm) (push) Has been cancelled
CI / Test (macos-latest, Node 18.x, pnpm) (push) Has been cancelled
CI / Test (macos-latest, Node 18.x, yarn) (push) Has been cancelled
CI / Test (ubuntu-latest, Node 18.x, bun) (push) Has been cancelled
CI / Test (ubuntu-latest, Node 18.x, npm) (push) Has been cancelled
CI / Test (ubuntu-latest, Node 18.x, pnpm) (push) Has been cancelled
CI / Test (ubuntu-latest, Node 18.x, yarn) (push) Has been cancelled
CI / Test (windows-latest, Node 18.x, npm) (push) Has been cancelled
CI / Test (windows-latest, Node 18.x, pnpm) (push) Has been cancelled
CI / Test (windows-latest, Node 18.x, yarn) (push) Has been cancelled
CI / Test (macos-latest, Node 20.x, bun) (push) Has been cancelled
CI / Test (macos-latest, Node 20.x, npm) (push) Has been cancelled
CI / Test (macos-latest, Node 20.x, pnpm) (push) Has been cancelled
CI / Test (macos-latest, Node 20.x, yarn) (push) Has been cancelled
CI / Test (ubuntu-latest, Node 20.x, bun) (push) Has been cancelled
CI / Test (ubuntu-latest, Node 20.x, npm) (push) Has been cancelled
CI / Test (ubuntu-latest, Node 20.x, pnpm) (push) Has been cancelled
CI / Test (ubuntu-latest, Node 20.x, yarn) (push) Has been cancelled
CI / Test (windows-latest, Node 20.x, npm) (push) Has been cancelled
CI / Test (windows-latest, Node 20.x, pnpm) (push) Has been cancelled
CI / Test (windows-latest, Node 20.x, yarn) (push) Has been cancelled
CI / Test (macos-latest, Node 22.x, bun) (push) Has been cancelled
CI / Test (macos-latest, Node 22.x, npm) (push) Has been cancelled
CI / Test (macos-latest, Node 22.x, pnpm) (push) Has been cancelled
CI / Test (macos-latest, Node 22.x, yarn) (push) Has been cancelled
CI / Test (ubuntu-latest, Node 22.x, bun) (push) Has been cancelled
CI / Test (ubuntu-latest, Node 22.x, npm) (push) Has been cancelled
CI / Test (ubuntu-latest, Node 22.x, pnpm) (push) Has been cancelled
CI / Test (ubuntu-latest, Node 22.x, yarn) (push) Has been cancelled
CI / Test (windows-latest, Node 22.x, npm) (push) Has been cancelled
CI / Test (windows-latest, Node 22.x, pnpm) (push) Has been cancelled
CI / Test (windows-latest, Node 22.x, yarn) (push) Has been cancelled
CI / Validate Components (push) Has been cancelled
CI / Python Tests (push) Has been cancelled
CI / Security Scan (push) Has been cancelled
CI / Coverage (push) Has been cancelled
CI / Lint (push) Has been cancelled
2.0 KiB
2.0 KiB
Optimización de Rendimiento
Estrategia de Selección de Modelos
Haiku 4.5 (90% de la capacidad de Sonnet, 3x ahorro de costos):
- Agentes ligeros con invocación frecuente
- Programación en pareja y generación de código
- Agentes workers en sistemas multi-agente
Sonnet 4.6 (Mejor modelo para codificación):
- Trabajo de desarrollo principal
- Orquestación de flujos de trabajo multi-agente
- Tareas de codificación complejas
Opus 4.5 (Razonamiento más profundo):
- Decisiones arquitectónicas complejas
- Requisitos de razonamiento máximo
- Tareas de investigación y análisis
Gestión de la Ventana de Contexto
Evitar el último 20% de la ventana de contexto para:
- Refactoring a gran escala
- Implementación de features que abarca múltiples archivos
- Depuración de interacciones complejas
Tareas con menor sensibilidad al contexto:
- Ediciones de un solo archivo
- Creación de utilidades independientes
- Actualizaciones de documentación
- Correcciones de bugs simples
Extended Thinking + Modo Plan
El extended thinking está habilitado por defecto, reservando hasta 31,999 tokens para razonamiento interno.
Controlar el extended thinking mediante:
- Toggle: Option+T (macOS) / Alt+T (Windows/Linux)
- Config: Establecer
alwaysThinkingEnableden~/.claude/settings.json - Límite de presupuesto:
export MAX_THINKING_TOKENS=10000 - Modo verbose: Ctrl+O para ver la salida del pensamiento
Para tareas complejas que requieren razonamiento profundo:
- Asegurarse de que el extended thinking esté habilitado (activado por defecto)
- Habilitar el Modo Plan para un enfoque estructurado
- Usar múltiples rondas de crítica para un análisis exhaustivo
- Usar sub-agentes con roles divididos para perspectivas diversas
Solución de Problemas de Build
Si el build falla:
- Usar el agente build-error-resolver
- Analizar los mensajes de error
- Corregir de forma incremental
- Verificar después de cada corrección