A 429 With retry-after: 120 Makes the Anthropic SDK Try to Wait 120 Seconds
I ran the Anthropic SDK's automatic retries against a mock server in 12 scenarios. Two retries by default, retry-after obeyed with no cap, and spend-limit 429s that no amount of waiting fixes. Code for a retry wrapper with a wait cap and a time budget, plus the logs.
Confirm Your Model Actually Responds Before a Scheduled Run Begins
A model you configured can be gone before your nightly job even wakes up. Tell retirement, withdrawal, and regional restriction apart with a single startup probe, then rewrite the run config to an eligible model — with complete, working TypeScript.
Centralizing the anthropic-beta Header So a Retired Beta Won't Kill Your Batch
Scattered anthropic-beta headers turn a beta retirement or GA graduation into a 400 that takes down an entire batch. A small capability registry, a startup preflight, and tiered fallback keep your pipeline running across feature generations.
Three Hidden Pitfalls When Implementing Claude API Streaming
Real-world lessons from building with Claude API streaming: runtime environment mismatches, error handling gaps, and silent token cost overruns — with working TypeScript examples.
First Claude API Call Failing? Common Error FAQ
Claude API beginner's error resolution guide. Covers 401 authentication errors, 429 rate limiting, 400 bad requests, empty responses, streaming failures, tool_use errors, context window exceeded, tool_result submission, and Spanner temporarily unavailable issues.