The $40 Agent Run

The research agent finishes its work correctly and terminates on its own — and still costs $40 a run. The trace shows just 12 steps, no looping or repetition: every step resends the full text of every page read so far, and all 12 run on the most expensive model — including 'pick the next link'. This cost is architecture, not a bug. Cut it to ≤ $4 at the same report quality on the eval.

Success: ≤ $4 per run at the same eval quality.