instructor
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library
cl-condition-system
condition/restartパターンを適用。エラーハンドリング実装時に使用
reactor-sub-agent
專責處理 RIF (Required Behavior Frame) 類型的需求。讀取規格目錄結構，生成/審查 Event Handler 設計與實作。支援冪等性、重試、死信佇列。
webhooks
Webhook implementation and consumption patterns. Use when implementing webhook endpoints, sending webhooks, handling retries, or ensuring reliable delivery. Keywords: webhooks, callbacks, HMAC, signature verification, retry, exponential backoff, idempotency, event delivery, webhook security.
error-handling
Comprehensive error handling patterns and strategies. Use when implementing exception handling, error recovery, retry logic, circuit breakers, fallback mechanisms, or designing error hierarchies. Triggers: error, exception, try-catch, retry, fallback, circuit breaker, error propagation, error messages.
litellm
When calling LLM APIs from Python code. When connecting to llamafile or local LLM servers. When switching between OpenAI/Anthropic/local providers. When implementing retry/fallback logic for LLM calls. When code imports litellm or uses completion() patterns.
third-party-integration
Integrate external APIs and services with error handling, retry logic, and data transformation. Use when connecting to payment processors, messaging services, analytics platforms, or other third-party providers.
