Merge remote-tracking branch 'origin/next' into feat/1279-fail-first-prover
# Conflicts: # docs/adr/550-spec-phase-probe-contract.md # gsd-core/workflows/verify-phase.md # tests/workflow-size-baseline.json
This commit is contained in:
Dave
@@ -356,6 +356,21 @@ For each Requirement gathered so far, run the two-stage recall→precision pass:
|
||||
Criteria AND mark the prohibition `resolved` with a verification tier: `test` (a
|
||||
mechanical negative test/lint/assertion exists) or `judgment` (real but not mechanically
|
||||
checkable — routes to judgment review).
|
||||
- **Capture the wired-check descriptor on `test`-tier (#1278, SOFT).** When a prohibition is
|
||||
resolved `verification: test`, ALSO capture the descriptor of the wired check so
|
||||
`verify-phase` can LOCATE it deterministically (no verifier invention at verify time).
|
||||
Capture the flat scalars — persisted into SPEC and projected onto the
|
||||
`must_haves.prohibitions` item by `projectProhibitions`:
|
||||
- `check_kind` — `node-test` | `lint-rule`.
|
||||
- `check_target` — the negative-test file path (for `node-test`), or the path to lint
|
||||
(for `lint-rule`).
|
||||
- `check_rule` — the eslint rule id (e.g. `local/no-source-grep`); `lint-rule` only.
|
||||
This is a **SOFT capture (CHK-04): a `test`-tier prohibition WITHOUT a descriptor is still
|
||||
allowed** — if the author cannot yet name the wired check, leave the descriptor empty and
|
||||
proceed. It is NOT a hard authoring block; the item simply stays fail-closed/flagged
|
||||
downstream (an absent/partial descriptor → `descriptorFromProjection` null/under-specified
|
||||
→ producer fail-closed locate, never green). Do NOT capture `failFirst` here — it is a
|
||||
verify-time caller attestation, not a spec-authored field (#1279).
|
||||
- **Dismiss (reason)** → mark `dismissed` with a REQUIRED non-empty reason (PROB-05). The
|
||||
reason string is the audit trail; silence is not a valid dismissal.
|
||||
- **Defer** → leave `unresolved`.
|
||||
@@ -374,7 +389,11 @@ For each Requirement gathered so far, run the two-stage recall→precision pass:
|
||||
**`--auto` mode:** auto-`resolved` where a defensible negative acceptance criterion can be
|
||||
written (test or judgment tier); otherwise leave `unresolved`. **`--auto` NEVER auto-dismisses
|
||||
a prohibition** — a wrong dismissal is the exact silent failure this probe eliminates (PROB-06,
|
||||
the load-bearing safety property). Log: `[auto] prohibitions: R resolved, U unresolved`.
|
||||
the load-bearing safety property). On a `test`-tier auto-resolution, capture the `check_kind` /
|
||||
`check_target` / `check_rule` descriptor **only when a wired check is unambiguous**; otherwise
|
||||
leave it empty — `--auto` NEVER fabricates a check path (a wrong locate is re-validated and
|
||||
fails closed at the producer, but a fabricated path is still noise to avoid). Log:
|
||||
`[auto] prohibitions: R resolved, U unresolved`.
|
||||
|
||||
**Text mode (PROB-09):** per Step 5's text-mode rule, replace the AskUserQuestion menus above
|
||||
with plain-text numbered lists — there is NO hard AskUserQuestion dependency, so the probe
|
||||
@@ -382,7 +401,11 @@ runs identically for non-Claude / text-mode hosts.
|
||||
|
||||
Populate the `## Prohibitions` section of SPEC.md from the resolved prohibitions (each
|
||||
`resolved`/`test` row is a checkable negative acceptance criterion; `resolved`/`judgment`
|
||||
rows route to judgment review; `⚠ UNRESOLVED` rows are flagged as assumptions).
|
||||
rows route to judgment review; `⚠ UNRESOLVED` rows are flagged as assumptions). A
|
||||
`resolved`/`test` row ALSO carries its captured `check_kind` / `check_target` / `check_rule`
|
||||
descriptor when present (so the projection feeds `verify-phase`'s deterministic locate, #1278);
|
||||
a `test` row with no captured descriptor is still valid — it stays fail-closed/flagged
|
||||
downstream rather than blocking authoring.
|
||||
|
||||
## Step 6: Generate SPEC.md
|
||||
|
||||
|
||||
@@ -70,17 +70,17 @@ Aggregate all must_haves across plans for phase-level verification.
|
||||
**Prohibitions (`must_haves.prohibitions`, ADR-550 D3 — the must-NOT sibling block):** When a plan carries `must_haves.prohibitions`, extract each `{ statement, status, verification }` item and route it by `verification` tier in verdict assembly (ADR-550 D4, "B-with-guard", 2026-06-12 maintainer decision). These are NEGATIVE checks (the must-NOT must NOT have happened), distinct from positive `truths`:
|
||||
|
||||
- **judgment-tier → mode-dependent soft-gate.** Interactive verify defers each item to the end-of-phase human checkpoint (`human_verify_mode: end-of-phase`). Autonomous verify records a NON-AUTHORITATIVE LLM-judge verdict + a prominent `unverified-prohibition — human review recommended` flag (autonomous completion reads "complete with N flagged prohibitions"). NEVER a silent pass; NEVER a hard halt of an AFK run.
|
||||
- **test-tier → ENFORCED via `check prohibition-enforcement` (green on pass, hard-gate on miss/fail).** Accept the `verification: test` value (the SPEC↔must_haves.prohibitions projection contract holds — no forced schema change later). For each test-tier item, the verifier invokes the deterministic producer:
|
||||
- **test-tier → ENFORCED via `check prohibition-enforcement` (green on pass, hard-gate on miss/fail).** Accept the `verification: test` value (the SPEC↔must_haves.prohibitions projection contract holds — no forced schema change later). For each test-tier item, the verifier builds `request.check` **DETERMINISTICALLY from the projected descriptor** — it does NOT invent `{ kind, target, rule }`. Read the flat scalar keys `check_kind` / `check_target` / `check_rule` off the `must_haves.prohibitions` item and reconstruct the `CheckDescriptor` via the `descriptorFromProjection` adapter in `prohibition-enforcement` (`descriptorFromProjection(projectedItem)` → `{ kind: check_kind, target: check_target, rule?: check_rule }`). Then attest `failFirst: true` in the request — `failFirst` is the ONE field NOT sourced from the projection; it stays a verify-time caller attestation (#1279 machine-proves it against a violation fixture). Invoke the producer (CLI surface unchanged):
|
||||
|
||||
```bash
|
||||
gsd_run check prohibition-enforcement <request.json>
|
||||
```
|
||||
|
||||
where `<request.json>` carries `{ prohibition, check, mode }` — `check` being the wired mechanical-check descriptor `{ kind: 'node-test' | 'lint-rule', target, rule?, violationFixture, failFirst? }`. For `node-test`, `target` is the negative-test file path; for `lint-rule`, `target` is the PATH to lint and `rule` is the eslint rule id (e.g. `local/no-source-grep`) — both required (a lint-rule without `rule` is not a valid wired check). `violationFixture` is the author-supplied path to a KNOWN-BAD subject the producer runs the check against to **machine-prove fail-first** (for `node-test`, injected via the `GSD_PROHIB_SUBJECT` env convention); `failFirst` is a DEMOTED, non-authoritative hint kept only for backward route-JSON shape (no path greens on it alone — FF-08). The producer LOCATES the wired check, **machine-proves it is fail-first** by running it against the violation and confirming it goes RED, RUNS it for a genuine non-vacuous pass, builds `enforcementEvidence`, and emits the `dispositionForProhibition()` verdict (#1259 + #1279, ADR-550 D5d). Fail-first is **machine-proven, not caller-attested** — absent a provable violation the producer fails closed, never falling back to attestation. Route the result by its typed fields:
|
||||
where `<request.json>` carries `{ prohibition, check, mode }` — `check` being the wired mechanical-check descriptor `{ kind: 'node-test' | 'lint-rule', target, rule?, violationFixture, failFirst? }`, with `kind`/`target`/`rule` now sourced from the projected `check_*` scalars (not author/verifier invention — #1278). For `node-test`, `target` (from `check_target`) is the negative-test file path; for `lint-rule`, `target` is the PATH to lint and `rule` (from `check_rule`) is the eslint rule id (e.g. `local/no-source-grep`) — both required (a lint-rule without `rule` is not a valid wired check). `violationFixture` is the author-supplied path to a KNOWN-BAD subject the producer runs the check against to **machine-prove fail-first** (for `node-test`, injected via the `GSD_PROHIB_SUBJECT` env convention — #1279); `failFirst` is a DEMOTED, non-authoritative hint kept only for backward route-JSON shape (no path greens on it alone — FF-08). The producer LOCATES the wired check from the projection, **machine-proves it is fail-first** by running it against the violation and confirming it goes RED, RUNS it for a genuine non-vacuous pass, builds `enforcementEvidence`, and emits the `dispositionForProhibition()` verdict (#1259 + #1278 + #1279, ADR-550 D5d). Fail-first is **machine-proven, not caller-attested** — absent a provable violation the producer fails closed, never falling back to attestation. Route the result by its typed fields:
|
||||
- **`status: 'green'`, `flagged: false`** (a genuinely-passing wired negative test / lint rule, `located: true`, non-empty `evidence`) → the item is satisfiable → it can reach **passed**.
|
||||
- **missing, non-attested, or genuinely-non-passing check** (`located: false` OR `status: 'unverified'`, `flagged: true`) → **hard-gate**: disposes flagged-unverified, NEVER green, routing to `gaps_found` in BOTH interactive and autonomous modes (a failing mechanical check blocks even AFK; ADR-550 D4 / D3). The deterministic fail-closed default backing every miss/fail is `dispositionForProhibition()` in probe-core (`status: 'unverified'`, `flagged: true` on empty `enforcementEvidence`).
|
||||
|
||||
> **Descriptor authoring — current scope (#1259).** The `check` descriptor is **supplied by the phase author / verifier**; there is no projection field yet that deterministically derives `{ kind, target, rule, failFirst }` from a prohibition in `must_haves.prohibitions` (which carries only `{ statement, status, verification }`). So #1259 lands the **deterministic run+verdict half** (locate→run→evidence→disposition, all CI-testable) while the **locate→descriptor half is author-provided** for now. Deterministic auto-locate — so a wired passing test closes the gap with zero manual descriptor authoring — is a **tracked follow-up: #1278**. Until then, the green path requires the author to wire the descriptor explicitly.
|
||||
> **Descriptor source — deterministic locate (#1278, DELIVERED).** The `check` descriptor's `{ kind, target, rule }` is now sourced **deterministically from the projected `check_kind` / `check_target` / `check_rule` scalars** on the `must_haves.prohibitions` item (authored at `/gsd:spec-phase`, projected by `projectProhibitions`, read back via the `descriptorFromProjection` adapter). So a wired passing test closes the gap with **zero manual descriptor authoring** — the verifier no longer invents the locate (removing the spoofable invent-at-verify-time surface; ADR-857 §147 exogenous grading). **Fail-closed is preserved:** an item with NO projected descriptor — or a PARTIAL one (e.g. a `lint-rule` missing `check_rule`) — makes `descriptorFromProjection` return `null` / an under-specified descriptor, which falls through to the producer's existing fail-closed LOCATE (`located: false`) → flagged-unverified, NEVER green, in BOTH modes. The only field still attested at verify time (not projected) is `failFirst`; machine-proving it against a violation fixture is the remaining **tracked follow-up: #1279**.
|
||||
|
||||
**Option B: Use Success Criteria from ROADMAP.md**
|
||||
|
||||
|
||||
Reference in New Issue
Block a user