Q1 of 60 — CCA Practice Exam

Structured Data Extraction

Your structured data extraction pipeline processes 10,000 contracts per day using a main Claude Code session. For each contract, the pipeline loads a shared 8,000-token legal taxonomy into context, then runs an extraction pass. To handle a sudden spike in document volume, a teammate proposes parallelizing extraction by spawning a separate worker for each document. They suggest using forks rather than named subagents, arguing it will be cheaper. Examining the architecture, you realize the team also wants each worker to use a lightweight, cost-optimized model rather than the main session's model. Which constraint makes forks the wrong choice here, despite their caching advantage?

A. Forks share the parent's prompt cache, so the 8,000-token legal taxonomy would be re-encoded separately for each forked worker, eliminating any cost savings.

B. Forks inherit the main session's model and cannot be configured to use a different model, so the cost-optimized model cannot be applied to forked workers.

C. Forks load the full conversation history into each worker's context, which inflates token usage as the main session grows longer throughout the day.

D. Forks run with the same tool permissions as the parent session, preventing the extraction workers from being restricted to read-only document access.