feat(audit): add rolling timestamped phase0 refresh cadence

2026-02-27 10:00:45 -08:00
parent 55f1a3dd7b
commit 149adb1c85
21 changed files with 1821 additions and 6 deletions
@@ -0,0 +1,72 @@
+# Phase-0 Backend Drift Check
+
+Generated at: 2026-02-27T17:59:43.707Z
+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=2026-02-27-175943 file=/home/will/lab/flynn/docs/plans/artifacts/phase0_baseline_live_backend_pi_embedded_2026-02-27-175943.json
+- candidate generated_at: 2026-02-27T17:59:43.514Z
+- baseline: tag=2026-02-27 file=/home/will/lab/flynn/docs/plans/artifacts/phase0_baseline_live_backend_pi_embedded_2026-02-27.json
+- baseline generated_at: 2026-02-27T17:36:02.214Z
+- candidate snapshot: sampled=59 outcomes=26 completion=100% cancel=0% error=0% cancel_p95_ms=n/a
+- baseline snapshot: sampled=59 outcomes=26 completion=100% cancel=0% error=0% cancel_p95_ms=n/a
+- deltas:
+  sampled_event_count_pct=0%
+  run_total_outcomes_pct=0%
+  completion_rate_pp=0
+  cancel_rate_pp=0
+  error_rate_pp=0
+  cancel_latency_p95_ms=n/a
+  reaction_match_rate_pp=0
+  reaction_skip_rate_pp=0
+- freshness gate: PASS (age_hours=0 threshold=36)
+- drift gate: PASS
+  PASS candidate_sampled_events actual=59 threshold=>= 10
+  PASS sampled_events_drop_pct actual=0 threshold=<= 80
+  PASS run_outcomes_drop_pct actual=0 threshold=<= 80
+  PASS completion_rate_drop_pp actual=0 threshold=<= 35
+  PASS cancel_rate_increase_pp actual=0 threshold=<= 25
+  PASS error_rate_increase_pp actual=0 threshold=<= 25
+  PASS cancel_latency_p95_increase_ms actual=n/a threshold=<= 6000
+
+## native
+- status: PASS
+- candidate: tag=2026-02-27-175943 file=/home/will/lab/flynn/docs/plans/artifacts/phase0_baseline_live_backend_native_2026-02-27-175943.json
+- candidate generated_at: 2026-02-27T17:59:43.624Z
+- baseline: tag=2026-02-27 file=/home/will/lab/flynn/docs/plans/artifacts/phase0_baseline_live_backend_native_2026-02-27.json
+- baseline generated_at: 2026-02-27T17:36:02.514Z
+- candidate snapshot: sampled=15 outcomes=2 completion=100% cancel=0% error=0% cancel_p95_ms=n/a
+- baseline snapshot: sampled=15 outcomes=2 completion=100% cancel=0% error=0% cancel_p95_ms=n/a
+- deltas:
+  sampled_event_count_pct=0%
+  run_total_outcomes_pct=0%
+  completion_rate_pp=0
+  cancel_rate_pp=0
+  error_rate_pp=0
+  cancel_latency_p95_ms=n/a
+  reaction_match_rate_pp=0
+  reaction_skip_rate_pp=0
+- freshness gate: PASS (age_hours=0 threshold=36)
+- drift gate: PASS
+  PASS candidate_sampled_events actual=15 threshold=>= 10
+  PASS sampled_events_drop_pct actual=0 threshold=<= 80
+  PASS run_outcomes_drop_pct actual=0 threshold=<= 80
+  PASS completion_rate_drop_pp actual=0 threshold=<= 35
+  PASS cancel_rate_increase_pp actual=0 threshold=<= 25
+  PASS error_rate_increase_pp actual=0 threshold=<= 25
+  PASS cancel_latency_p95_increase_ms actual=n/a threshold=<= 6000
+