flynn/docs/plans/artifacts/phase0_baseline_live_backend_drift_2026-02-27.md

Phase-0 Backend Drift Check

Generated at: 2026-02-27T17:04:49.009Z Artifacts: /home/will/lab/flynn/docs/plans/artifacts Backends: pi_embedded, native Freshness max age (hours): 36 Overall gate: PASS

Thresholds

• requireBaselineHistory: false
• minCandidateSampledEvents: 10
• maxSampledEventsDropPct: 80
• maxRunOutcomesDropPct: 80
• maxCompletionRateDropPp: 35
• maxCancelRateIncreasePp: 25
• maxErrorRateIncreasePp: 25
• maxCancelLatencyP95IncreaseMs: 6000

pi_embedded

• status: PASS
• candidate: tag=2026-02-27 file=/home/will/lab/flynn/docs/plans/artifacts/phase0_baseline_live_backend_pi_embedded_2026-02-27.json
• candidate generated_at: 2026-02-27T16:45:18.488Z
• baseline: none
• candidate snapshot: sampled=56 outcomes=25 completion=100% cancel=0% error=0% cancel_p95_ms=n/a
• deltas: sampled_event_count_pct=n/a run_total_outcomes_pct=n/a completion_rate_pp=n/a cancel_rate_pp=n/a error_rate_pp=n/a cancel_latency_p95_ms=n/a reaction_match_rate_pp=n/a reaction_skip_rate_pp=n/a
• freshness gate: PASS (age_hours=0.33 threshold=36)
• drift gate: PASS PASS candidate_sampled_events actual=56 threshold=>= 10 PASS sampled_events_drop_pct actual=n/a threshold=<= 80 PASS run_outcomes_drop_pct actual=n/a threshold=<= 80 PASS completion_rate_drop_pp actual=n/a threshold=<= 35 PASS cancel_rate_increase_pp actual=n/a threshold=<= 25 PASS error_rate_increase_pp actual=n/a threshold=<= 25 PASS cancel_latency_p95_increase_ms actual=n/a threshold=<= 6000

native

• status: PASS
• candidate: tag=2026-02-27 file=/home/will/lab/flynn/docs/plans/artifacts/phase0_baseline_live_backend_native_2026-02-27.json
• candidate generated_at: 2026-02-27T16:45:18.490Z
• baseline: none
• candidate snapshot: sampled=13 outcomes=2 completion=100% cancel=0% error=0% cancel_p95_ms=n/a
• deltas: sampled_event_count_pct=n/a run_total_outcomes_pct=n/a completion_rate_pp=n/a cancel_rate_pp=n/a error_rate_pp=n/a cancel_latency_p95_ms=n/a reaction_match_rate_pp=n/a reaction_skip_rate_pp=n/a
• freshness gate: PASS (age_hours=0.33 threshold=36)
• drift gate: PASS PASS candidate_sampled_events actual=13 threshold=>= 10 PASS sampled_events_drop_pct actual=n/a threshold=<= 80 PASS run_outcomes_drop_pct actual=n/a threshold=<= 80 PASS completion_rate_drop_pp actual=n/a threshold=<= 35 PASS cancel_rate_increase_pp actual=n/a threshold=<= 25 PASS error_rate_increase_pp actual=n/a threshold=<= 25 PASS cancel_latency_p95_increase_ms actual=n/a threshold=<= 6000