The governance runs, acts, and records — reproducibly.
This snapshot measures how the Phionyx self-governance runtime governs the AI that writes Phionyx itself — aggregate numbers only, reviewer-reproducible. It is refreshed when the maintainer re-runs the public audit script (manual, not a continuous feed); the snapshot date is shown below. What is already proven: every governed decision is signed into a tamper-evident, hash-chained record, and the gate refuses, regenerates, or rewrites work that fails its checks — it acts, it does not only log. What is not yet proven: the full closed loop — a signed decision whose real-world outcome is later confirmed — which is honestly near zero today and accumulates forward. Coverage is one input, not the goal.
What the runtime proves today
tamper-evident and hash-chained within the runtime; the public feed publishes aggregate counts, not the records themselves (10 chains).
the gate refused / regenerated / rewrote work that failed its checks — it acts, it does not only log.
the deterministic measurement script is public; these numbers are its output over the private dev telemetry, and the published snapshot is the audit artifact.
What we don’t claim yet: that a signed decision’s real-world outcome has been independently confirmed end to end. Confirming outcomes takes time and real labels (which we never fabricate), so that long-loop evidence is still accruing. We’d rather show that gap than hide it.
Invocation discipline · rolling 30-day window (one input, not the headline)
Our own rule asks the AI to call the gate twice per commit, so “coverage” is simply how often it did. It is a discipline check, not the point — calling the gate never proves the work is correct (that is what the signed record above is for). Reading the per-day Coverage column:
—no governed activity recorded that day — not measured, and not counted as a failure.0.0%the gate was available but the AI did not call it.100%+the AI called the gate more often than the twice-per-commit baseline — extra discipline, not an error.
Per-day breakdown (30 days)
since 2026-05-17 15:51 UTC
| Date | Commits | Gate | All MCP | Coverage |
|---|---|---|---|---|
| 2026-06-16 | 4 | 12 | 23 | 100%+ |
| 2026-06-15 | 6 | 19 | 38 | 100%+ |
| 2026-06-14 | 18 | 65 | 123 | 100%+ |
| 2026-06-13 | 1 | 22 | 37 | 100%+ |
| 2026-06-12 | 4 | 0 | 0 | — |
| 2026-06-11 | 2 | 0 | 0 | — |
| 2026-06-10 | 15 | 4 | 8 | 13.3% |
| 2026-06-09 | 11 | 32 | 64 | 100%+ |
| 2026-06-08 | 11 | 24 | 41 | 100%+ |
| 2026-06-07 | 36 | 14 | 24 | 19.4% |
| 2026-06-06 | 20 | 16 | 20 | 40.0% |
| 2026-06-05 | 2 | 0 | 1 | 0.0% |
| 2026-06-04 | 2 | 0 | 3 | 0.0% |
| 2026-06-03 | 1 | 0 | 7 | 0.0% |
| 2026-06-02 | 1 | 0 | 12 | 0.0% |
| 2026-06-01 | 1 | 1 | 4 | 50.0% |
| 2026-05-31 | 1 | 0 | 0 | — |
| 2026-05-30 | 5 | 0 | 0 | — |
| 2026-05-29 | 24 | 10 | 10 | 20.8% |
| 2026-05-28 | 67 | 51 | 51 | 38.1% |
| 2026-05-27 | 24 | 36 | 36 | 75.0% |
| 2026-05-26 | 40 | 15 | 22 | 18.8% |
| 2026-05-25 | 34 | 2 | 5 | 2.9% |
| 2026-05-24 | 26 | 4 | 16 | 7.7% |
| 2026-05-23 | 27 | 0 | 0 | — |
| 2026-05-22 | 17 | 0 | 0 | — |
| 2026-05-21 | 6 | 0 | 0 | — |
| 2026-05-20 | 3 | 0 | 0 | — |
| 2026-05-19 | 18 | 0 | 0 | — |
| 2026-05-18 | 2 | 0 | 0 | — |
Directive distribution
The aggregate of every directive written to telemetry across MCP tools + observability hooks — broader than the gate's five directive dispositions (pass · damp · rewrite · regenerate · reject) because non-gate tools also write entries.
auto_attest — observability hooks (session start, user prompt log, commit attestation, …). Recorded but excluded from coverage math by design.
checkpoint — emitted by phionyx_checkpoint (lightweight context-note tool, not a gate).
n/a — entries without an explicit directive field (e.g. session start, prompt log, attestation writes).
solid / weak / incomplete — emitted by phionyx_causal_trace (chain-quality verdicts, distinct from the gate's five directive dispositions).
ok — emitted by the trust-boundary MCP server on successful third-party-tool attestation writes.
Reproduce
python3 case-studies/agentic-development-2026-05/scripts/runtime_evidence_self_audit.py --days 30Same audit script lives at case-studies/.../scripts/runtime_evidence_self_audit.py. Generated 2026-06-16 12:51 UTC · schema v0.7.2 · regenerated on maintainer re-run (snapshot date above).