feat(spec-phase): prohibition probe — surface "must-NOT" constraints (#644) (#1149)

Adds the spec-time prohibition probe (spec-phase Step 5.6) — the second adapter of the probe-core resolution model. Surfaces unwritten must-NOT constraints as negative SPEC acceptance criteria with test/judgment verification tiers; fail-closed at verify time. Per ADR-550. Closes #644.
This commit is contained in:
Rezolv
2026-06-14 21:29:11 -04:00
committed by GitHub
parent 9a4a448c27
commit 395fb519e7
29 changed files with 1503 additions and 11 deletions

View File

@@ -84,3 +84,12 @@ The capability system (ADR-857) classifies **predicate-generation as core verifi
- **"Exogenous grading"** is the verify-time half of this ADR's **judgment-tier** (Decision 4): the autonomous verifier records an LLM-judge verdict **marked non-authoritative** and flags *"unverified prohibition — human review recommended"* — grading against the spec's explicit predicates, never a self-graded restatement (the prose-drift / self-graded-review failure modes reproduced on #664). The judgment-tier soft-gate **is** the contract's "never a silent pass" guarantee at the core boundary.
- **The probe *adapters* are the core-default *generator*** — `edge-probe`'s `classifyShape`/`proposeEdges` and the prohibition probe's adversarial LLM-propose, the surfaces that *propose* predicates — default-on and non-removable, but **independently versionable**. The classifier's measured recall gap (the prose→shape under-fire on terse prose) is the reason they stay their own modules under this ADR rather than being folded into the slow core rail. **`probe-core` is not the generator:** per Decision 7b it ingests already-proposed items, and its deterministic validators are the **contract**'s CI-testable surface (Decision 5) — so `probe-core` sits on the contract side, the adapters on the generator side. ADR-857 phase 6 wires these modules onto the core predicate rail; it does **not** relabel them as a `capabilities/edge-probe/` plug-in.
- Decision 5's rule — *the CI-testable surface is the contract, not the classifier* — extends to ADR-857's core rail: the deterministic conformance test is the contract shape the verifier consumes, never the LLM's judgment.
## Addendum (2026-06-12): test-tier disposition — fail-closed now, heavy enforcement deferred
Decision 4 describes the `test`-tier as a "**Hard gate in both interactive and autonomous modes.**" The #644 implementation revises that to a **fail-closed-now / deferred-enforcement** resolution (the "B-with-guard" maintainer decision of 2026-06-12), so the architecture-of-record matches the shipped code:
- A well-formed but **unwired** `test`-tier prohibition resolves via `dispositionForProhibition()` to `{ status: 'unverified', flagged: true }` — **provably never green** without explicit evidence (REQ-PROHIB-06). This is the load-bearing safety half and it holds today.
- The **heavy negative-test enforcement mechanism** — a contrived `test`-tier consumer that mechanically runs the negative test — is **deferred to a follow-up**, because the #644 corpus is entirely `judgment`-tier and wiring a synthetic test-tier consumer now would be gold-plating. The fail-closed disposition guards the gap in the meantime: the gate cannot silently pass, it can only report `unverified`/flagged until enforcement lands.
Net effect on D4: the *guarantee* ("a `test`-tier prohibition is never a silent pass") is preserved exactly; what is deferred is only the mechanical-pass half of the gate, not the never-green safety property. This addendum supersedes the unqualified "hard gate" wording of Decision 4 for `test`-tier items until the enforcement follow-up lands. The decision also lives in `src/probe-core.cts` comments, `verify-phase.md`, and the #644 changeset.