@sabaiway/agent-workflow-engine 1.11.0 → 1.12.0

package/CHANGELOG.md

@@ -4,6 +4,22 @@ All notable changes to the methodology engine. Versions are this **package's** n
 they are distinct from the **deployment-lineage** stamp written into a project's `docs/ai/`
 (which tracks the shared `agent-workflow` lineage, head `1.3.0`).
 
+## 1.12.0 — Plans carry a home for review-settled decisions (§7 optional `## Decisions (locked)`)
+
+A **feature** release (canon text + its tests; installer unchanged; deployment-lineage head stays
+`1.3.0` — no migration). Decisions a plan's review loop SETTLED (fixtures, contracts, boundary
+clauses) now have a canonical, machine-extractable home:
+
+- **`references/planning.md` §7** — the plan-document structure gains one optional row after
+  `## Approach`: `## Decisions (locked) ← optional: settled, binding decisions the executor must
+  not re-litigate`. The heading string is load-bearing: the kit's grounded-review facts assembler
+  (`grounding.mjs`, AD-038) extracts the section by exact-heading match.
+- **`references/planning.md` §8** — one checklist bullet: decisions the review loop settled live
+  under the optional `## Decisions (locked)` heading — binding for the executor, never re-litigated
+  at Execute.
+- **`test/planning-canon.test.mjs`** — pins the exact §7 row (heading + optional + executor-binding
+  wording, positioned after `## Approach`) and the §8 mention.
+
 ## 1.11.0 — Plans carry only checked syntax (the §9 checked-vs-unchecked boundary)
 
 A **feature** release (canon text + its tests; installer unchanged). The §9 "No code-mechanics in

package/SKILL.md

@@ -3,7 +3,7 @@ name: agent-workflow-engine
 description: Canonical home of the agent-workflow planning methodology — the Plan→Phase→Step→Substep vocabulary, plan lifecycle, queue.md series index, mandatory Cleanup phase, the bounded methodology slot fragment, the orchestration-recipe vocabulary (Solo / Reviewed / Council / Delegated), and the activity-procedures canon (plan-authoring / plan-execution, with typed recipe slots). A published, installable npm package (available:true) that *provides* the methodology text; it mutates nothing. The composition root (agent-workflow-kit) reads this canon LIVE from the installed engine and injects the bounded slots from it — one source of truth, no bundled mirror; `npx @sabaiway/agent-workflow-kit@latest init` installs the engine.
 disable-model-invocation: true
 metadata:
-  version: '1.11.0'
+  version: '1.12.0'
 ---
 
 # agent-workflow-engine

package/capability.json

@@ -3,7 +3,7 @@
   "schema": 1,
   "name": "agent-workflow-engine",
   "kind": "methodology-engine",
-  "version": "1.11.0",
+  "version": "1.12.0",
   "available": true,
   "provides": ["plan"],
   "roles": {},

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sabaiway/agent-workflow-engine",
-  "version": "1.11.0",
+  "version": "1.12.0",
   "description": "Canonical home of the agent-workflow planning methodology — the Plan→Phase→Step vocabulary, plan lifecycle, queue.md series index, and mandatory Cleanup phase, consumed by the kit (composition root). The methodology engine of the agent-workflow family.",
   "keywords": [
     "ai-agents",

package/references/planning.md

@@ -89,6 +89,7 @@ A harness "approved — you can now start coding" prompt (e.g. Claude Code's **E
 
 ## Context              ← why this Plan exists, current state, why now (reads cold)
 ## Approach             ← chosen design + an explicit "What we are NOT doing"
+## Decisions (locked)   ← optional: settled, binding decisions the executor must not re-litigate
 ## Phase 1: <name>
    ### 1.1. <step>      ← exact paths + commands
 ## Phase 2: <name>
@@ -108,6 +109,7 @@ A harness "approved — you can now start coding" prompt (e.g. Claude Code's **E
 - If part of a series: `queue.md` is initialised / updated (§3).
 - No `git add <plan>` and no "commit the plan" wording in the final report.
 - Every code-touching decision cites the `file:line` it is grounded in; the plan stays at intent / invariant / acceptance altitude, leaving fine code-mechanics to Execute (§9).
+- Decisions the review loop SETTLED (fixtures, contracts, boundary clauses) live under the optional `## Decisions (locked)` heading (§7) — binding for the executor, never re-litigated at Execute.
 
 ## 9. Right-altitude & code-grounded folds