Retry and Backoff for Long Agent Loops Under Overloaded and Rate-Limit Errors
The Anthropic SDK retries a failed call twice in about 1.2 seconds, which is fine for a chat request and wrong for a 200-turn agent run. Classify every failure into retry-after, capacity, transient or terminal, retry the model turn (never the tool call), share one pause gate across workers, catch the mid-stream overloaded_error that arrives as a 200, and checkpoint so a dead run resumes. Tested against anthropic 2.3.0 for Python.