memory-hygienelisted

# memory-hygiene — Stale Memory Detection and Re-Verification > Addresses the "stale-but-confident" failure mode: verified information that silently drifts > while remaining highly ranked in retrieval — identified as a critical harness failure mode > in *Scaling the Harness in Agentic AI* (arXiv:2605.26112). FH is an online-first harness. Its memory entries point to live external resources (GitHub repos, arXiv records, Zenodo DOIs, monitoring routines). These drift faster than in offline systems — which makes hygiene both more necessary and more tractable (live re-verification is possible). ## Trigger Conditions ### Natural Language Triggers | Phrase | Intent | |---|---| | "memory check", "check stale memories" | Manual hygiene scan | | "are my memories still accurate?" | Full re-verification pass | | "clean up memory", "memory audit" | Propose archival candidates | | "something in memory might be wrong" | Targeted re-check | ### Automatic Trigger - **harvest-loop Step 0-c**: Runs automatically as the first step of every full harvest-loop - **Cadence guard**: Skip if memory-hygiene ran within the last 7 days (`tracks/_meta/memory_hygiene_*.md` mtime check) ## Staleness Classification | Type | Staleness Threshold | Re-verification Method | |---|---|---| | `project` — status/milestone entries | **14 days** | Re-read source file or live resource | | `reference` — external URLs, DOIs, GitHub repos | **30 days** | WebFetch or gh CLI check | | `feedback` — operating rule