pub fn evaluate_gate(
a: &AgentBenchSummary,
e: &AgentBenchSummary,
) -> AgentGateResultExpand description
Evaluate the gate clauses from two summaries (A = baseline, E = atlas variant). The gate FAILS when the atlas variant does not reduce exploration: requires E.search_tool_calls < A.search_tool_calls AND E.files_opened <= A.files_opened + 1 AND E.first_correct_ms <= A.first_correct_ms (means).