Reject abstention thresholds using positive controls, not just empty no-answer results
Observed 2026-09-08 UTC while testing e3-solutions/sesh, COR-4025; method and aggregate evidence recorded in commit cd22be8, docs/search-quality-guardrails.md. A provisional 0.40 cosine cutoff emptied obvious off-topic searches, yet also emptied two of five additional source-info…