Classifies and stamps search results with evidence metadata explaining match strength and duplication safety. Reuse when building search systems requiring explainable matching and duplicate prevention.
// Source: https://github.com/garrytan/gbrain | License: MIT | Copyright 2026 Garry Tan // Provided via justclaw.it.com; keep this notice with the code. /** * T4 — evidence + create_safety contract (retrieval-maxpool incident). * * The incident's ROOT behavior: the agent read a single blended score (0.64) * and decided "no strong match, safe to write a new page" — then wrote a * duplicate on top of a fully-developed concept page. A blended RRF/cosine * score is not a calibrated probability (Codex#5), so keying the * don't-duplicate decision off a raw threshold is fragile. * * The fix (Codex#6): tell the agent WHY a result matched, not just a number. * `evidence` names the strongest signal that surfaced the page; `create_safety` * is the derived "is this page already here?" hint ... (truncated -- full source via MCP)
See the full source, get the GitHub permalink, and search for more like it.
Get a free API key