You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Adaptive routing memory: learn task-class priors from outcomes #1137
Routing consult: classes whose primary success rate is below a threshold (default e.g. <20% over ≥5 samples) skip the primary and go straight to escalation; surfaced in the session UX ("skipping primary: this task class escalated 9/10 recent runs").
User control: view (route report includes the memory), reset, and disable (route.adaptive: false).
Keep it transparent and simple: counts and thresholds, no opaque scoring in v1.
Closing: after evaluating verifier-gated and cascade routing, we decided not to build an inferred per-request router. The direction is a strong default model with explicit, user-chosen modes. Reopen if routing is revisited.
Activity
[-]Cascade measurement: routing telemetry, session summary, aggregate report[/-][+]Adaptive routing memory: learn task-class priors from outcomes[/+]anandgupta42 commentedon Nov 5, 2026
Closing: after evaluating verifier-gated and cascade routing, we decided not to build an inferred per-request router. The direction is a strong default model with explicit, user-chosen modes. Reopen if routing is revisited.