@windyroad/architect 0.9.1 → 0.9.2-preview.430

package/.claude-plugin/plugin.json

@@ -123,5 +123,5 @@
     }
   },
   "name": "wr-architect",
-  "version": "0.9.1"
+  "version": "0.9.2"
 }

package/agents/agent.md

@@ -156,6 +156,17 @@ Emit **NEEDS DIRECTION** only when ALL of the following hold:
 
 Do NOT emit Needs Direction for the "obvious choice" / only-one-viable-option case (see "When NOT to flag" above) — over-firing on obvious choices is the over-ask trap CLAUDE.md P132 warns against. Needs Direction is the architect-surface instance of ADR-044 category 1 (direction-setting); `AskUserQuestion` remains a primary-agent affordance — you name the question + options, the main agent owns the ask.
 
+### When to flag [Unratified Dependency] (ADR-074 (Confirm a decision's substance before building dependent work) surface 3)
+
+When the change or plan under review **explicitly cites or implements** a specific ADR (e.g. the diff/prose says "per ADR-072", a `Refs: ADR-NNN`, or it is authoring the work the ADR governs), check whether that ADR has been **ratified** before letting the change stand. You have Read/Glob/Grep (no Bash), so perform the **read-only equivalent** of `packages/architect/scripts/is-decision-unconfirmed.sh` — mirror BOTH halves of its "unconfirmed" definition:
+
+1. **Frontmatter-scoped marker check.** Read the cited ADR file and inspect ONLY its YAML frontmatter (the block between the leading `---` and the next `---`). The ADR is **ratified** iff that frontmatter contains a line matching `human-oversight: confirmed` — case-insensitive, tolerating trailing whitespace (the canonical predicate greps `-iE '^human-oversight:[[:space:]]*confirmed[[:space:]]*$'`). A body mention of that string does NOT count — it must be in frontmatter.
+2. **Superseded skip.** A `*.superseded.md` ADR is retired — treat it as ratified-equivalent (do NOT flag); a newer ADR replaced it.
+
+Emit **ISSUES FOUND / [Unratified Dependency]** only when the cited ADR's frontmatter lacks the marker AND it is not superseded — action: "ratify ADR-NNN via `/wr-architect:review-decisions` before this lands." 
+
+**Key the flag on the oversight marker, NEVER on `status:`.** `status: proposed`/`accepted` and `human-oversight:` are orthogonal axes (ADR-066). Building on a **ratified** ADR is fine even when its `status` is still `proposed` — do NOT flag it. Only the *unratified* (marker-absent, non-superseded) case flags. In steady state almost every ADR is ratified (born-confirmed via `create-adr` + the review-decisions drain), so this fires on essentially nothing — do not over-scan or flag transitive/ambient dependence on governed code, only an explicit cite/implement of a specific unratified ADR (the inverse-P078 / P132 over-fire guard).
+
 Issue types:
 - **[Decision Conflict]**: Change conflicts with an accepted/proposed decision
 - **[Undocumented Decision]**: Change represents an architectural choice not covered by any existing decision
@@ -163,6 +174,7 @@ Issue types:
 - **[Decision Format]**: A decision file doesn't follow MADR 4.0 format
 - **[Missing Supersession]**: A new decision should supersede an old one but doesn't
 - **[Confirmation Violation]**: New code violates a confirmation criterion of an existing decision
+- **[Unratified Dependency]**: The change/plan explicitly cites or implements an ADR that is **unratified** (its frontmatter lacks `human-oversight: confirmed`, and it is not `*.superseded.md`) — building on it before a human ratifies its substance is the P315 failure mode (ADR-074 (Confirm a decision's substance before building dependent work) enforcement surface 3)
 
 ## Constraints
 

package/agents/test/architect-unratified-dependency-verdict.bats

@@ -0,0 +1,55 @@
+#!/usr/bin/env bats
+# Doc-lint guard: architect agent.md must carry the [Unratified Dependency]
+# verdict (ADR-074 enforcement surface 3 / RFC-010 / P318) — flag a change or
+# plan that explicitly cites/implements an ADR lacking `human-oversight:
+# confirmed` (unratified, non-superseded), keyed on the oversight marker NOT
+# `status:`. Closes the residual P315 foreground gap at the architect-review
+# surface (the ITIL propose-fix surface is covered by RFC-008).
+#
+# tdd-review: structural-permitted (justification: P176 — agent behaviour is
+# prompt-driven with no skill-invocation harness to exercise the verdict
+# behaviourally; ADR-052 Surface 2 structural-justified case, NOT an ADR-005
+# Permitted Exception). When P176 lands, upgrade to a behavioural test that
+# feeds the agent a change citing an unratified ADR and asserts the verdict.
+#
+# Cross-reference:
+#   ADR-074 (Confirm a decision's substance before building dependent work — surface 3)
+#   ADR-066 (oversight marker; orthogonal status/oversight axes; the "unconfirmed" definition)
+#   RFC-010 / P318 (this enforcement surface)
+#   ADR-052 Surface 2 (structural-justified verdict) + P176 (harness gap)
+#   @jtbd JTBD-002 (ship with confidence) / JTBD-001 (enforce governance without slowing down)
+
+setup() {
+  AGENT_DIR="$(cd "$(dirname "$BATS_TEST_FILENAME")/.." && pwd)"
+  AGENT_FILE="${AGENT_DIR}/agent.md"
+}
+
+@test "agent.md lists [Unratified Dependency] as an issue/verdict type (ADR-074 surface 3)" {
+  run grep -n '\[Unratified Dependency\]' "$AGENT_FILE"
+  [ "$status" -eq 0 ]
+}
+
+@test "agent.md has a 'When to flag [Unratified Dependency]' section citing ADR-074" {
+  run grep -niE "When to flag \[Unratified Dependency\]" "$AGENT_FILE"
+  [ "$status" -eq 0 ]
+  run grep -n "ADR-074" "$AGENT_FILE"
+  [ "$status" -eq 0 ]
+}
+
+@test "agent.md keys the flag on the oversight marker, NOT on status (orthogonal axes)" {
+  # ADR-066 / user correction 2026-05-27: building on a ratified-but-proposed ADR is fine.
+  run grep -niE "NEVER on .?status|not .?\`?status|orthogonal" "$AGENT_FILE"
+  [ "$status" -eq 0 ]
+}
+
+@test "agent.md scopes the marker check to frontmatter + skips superseded (mirrors is-decision-unconfirmed.sh)" {
+  run grep -niE "frontmatter" "$AGENT_FILE"
+  [ "$status" -eq 0 ]
+  run grep -niE "superseded" "$AGENT_FILE"
+  [ "$status" -eq 0 ]
+}
+
+@test "agent.md guards against over-firing on transitive/ambient dependence (inverse-P078)" {
+  run grep -niE "explicit(ly)? cite|over-?(fire|scan)|transitive" "$AGENT_FILE"
+  [ "$status" -eq 0 ]
+}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@windyroad/architect",
-  "version": "0.9.1",
+  "version": "0.9.2-preview.430",
   "description": "Architecture decision enforcement for AI coding agents",
   "bin": {
     "windyroad-architect": "./bin/install.mjs"

package/skills/review-design/SKILL.md

@@ -67,6 +67,8 @@ Build a self-contained prompt for the architect subagent that includes:
 - Any explicit scope from the user
 - The request: "Review these proposed changes against the project's ADRs. Flag any violations, gaps that need a new ADR, or compliance questions."
 
+The architect's verdict taxonomy includes **[Unratified Dependency]** (ADR-074 surface 3): if the plan/change explicitly cites or implements an ADR that lacks `human-oversight: confirmed` (unratified, non-superseded), the architect flags ISSUES FOUND with a "ratify via /wr-architect:review-decisions first" action. This applies to plan review exactly as to edit review — a plan built on an unratified decision should not proceed until that decision's substance is ratified. No extra prompt wiring is needed (the agent owns the check); this note records that the surface-3 check is in-scope for plan review.
+
 ### 5. Delegate to wr-architect:agent
 
 Invoke the architect subagent via the `Skill` tool: