Resilience

Resilience examples enact production patterns for keeping an LLM app up. Sources under examples/resilience/.

Name	Scenario	Source
`resilience_error_handling`	User submits an age string; show how parse errors propagate through a Runnable chain so the caller can surface a friendly message.	src
`resilience_error_recovery`	URL shortener that fails twice then succeeds — exponential backoff retry keeps the user-facing call working.	src
`resilience_rate_limiters`	Cost-based budget — cap LLM spend at $1/min using TokenBucket / SlidingWindow / CostBased / Composite.	src
`resilience_ssrf_protection`	URL-fetch tool that gets a URL from user input — reject internal IPs, localhost, and AWS metadata before any HTTP call.	src

How to run

cargo run -p cognis-examples --example resilience_ssrf_protection
cargo run -p cognis-examples --example resilience_rate_limiters

Wrappers, middleware, recovery patterns.

Don’t pay twice.

PII, deny-lists, sandboxing.