Question-level checkpointing in the eval (--checkpoint-every, default 10)

Make the eval harness resume-safe (--out)

Log generation/request ids on eval failures for trace debugging

Add AGENT_MAX_RPM global throttle for free-tier benchmarking

Experiment: AGENT_SQL_ONLY mode (no templates, SQL for everything)

Parallelize the eval harness + add per-model health table

Consolidate all eval questions into one document

Steer interpretive questions toward insightful metrics

Eval: provider/model health tracking, --runs, tougher interpretive questions

Render multiple charts side by side + harden against model API errors

Add flexible SQL query path + new templates + safe executor

Initial deploy: NL-to-chart NBA visualization app