Q15 of 60 — CCA Practice Exam

Structured Data Extraction

Your structured data extraction pipeline processes 1,200 insurance claim documents per night using a extract_claim_fields tool with eager_input_streaming: true. In production monitoring, you observe that roughly 3% of extraction jobs fail with a JSON parse error at the accumulation step — and the error logs show these failures correlate almost entirely with documents that triggered the max_tokens stop reason. Your current error handler logs the failure and skips the document. What is the most effective architectural fix for this failure mode?

A. Increase max_tokens on the extraction request to ensure Claude has enough room to complete the full JSON parameter before the stream terminates, eliminating truncation at the source.

B. Disable eager_input_streaming on the extract_claim_fields tool so the API buffers and validates the complete parameter before streaming, eliminating mid-stream truncation at the cost of higher latency.

C. Add specific handling for the max_tokens stop reason: wrap the accumulated partial JSON in a structured error object (e.g., {"INVALID_JSON": "<partial>"}) and return it to Claude as an error tool result so Claude can recover with a corrective pass.

D. Switch the accumulation logic to parse the JSON incrementally on each input_json_delta event rather than waiting for content_block_stop, so partial fields can be extracted before truncation occurs.