Tag: reliability
All the articles with the tag "reliability".
The Retry That Paid The Invoice Twice
At-least-once execution is the default everywhere. Checkpoints make resumption cheap; idempotency keys make it safe. Runnable code and the bug I hit.
Context Rot: When Your Agent Forgets It Was Denied
Dropping the oldest messages is amnesia with a token budget. Compact by turn group, pin the goal and the denials, and never orphan a tool call.
The Retry Loop Your Circuit Breaker Cannot See
A classic circuit breaker misses the agent-specific failure: retrying the same bad call against a healthy dependency. Thrash detection, with code.
You Will Find Out About The Runaway Agent From The Invoice
A token counter is not a cost control. Reserve-then-reconcile budgets that halt before the expensive call, across per-run and per-tenant windows.