@sabaiway/agent-workflow-memory 1.10.0 → 1.11.1

package/CHANGELOG.md

@@ -4,6 +4,30 @@ All notable changes to the memory substrate. Versions are this **package's** npm
 they are distinct from the **deployment-lineage** stamp written into a project's
 `docs/ai/.memory-version` (which tracks the shared `agent-workflow` lineage, head `1.3.0`).
 
+## 1.11.1 — One batched setup prompt (the F11 ask reword; AD-042)
+
+A **patch** release (prose reword only; deployment-lineage head stays `1.3.0` — no migration).
+The three bootstrap setup questions (visibility / conversational language / attribution) are now
+asked as **ONE structured multi-question prompt where supported** (`AskUserQuestion`, up to 4
+questions per call), each answer recorded individually, nothing written until ALL are answered —
+first contact interrupts once, not three times (`SKILL.md` bootstrap preamble + steps 2–4). The
+upgrade path batches its two migration asks the same way ONLY when both `AGENTS.md` blocks are
+missing (a pre-1.1.0 deployment), collecting them in step 4 BEFORE the migrations apply and never
+re-asking a collected answer (a migration's own "Ask the user" step stays the standalone
+fallback). The `references/contracts.md` ask paragraph is reworded byte-identical with the kit's
+copy — pinned cross-package by the kit's new `ask-contract` test.
+
+## 1.11.0 — The template lens block becomes a render of the engine canon (AD-041)
+
+A **feature** release (template text only; deployment-lineage head stays `1.3.0` — no migration).
+`references/templates/agent_rules.md` §2.6 (the planning/review/process-fidelity lens block) is
+now a **render of the engine's canonical `agent-rules-lens` fragment**: the intro gains the
+provenance clause (rendered from the canon; refreshed on upgrade; a custom edit is preserved
+verbatim, but flagged). Standalone-first is unchanged — the template still seeds the complete
+block with no kit/engine present; an unmodified older seed converges to the current canon at the
+next kit bootstrap/upgrade touch (the kit's new `lens-region` reconcile matches it against the
+engine's known-prior store). Future lens wording changes no longer require a memory release.
+
 ## 1.10.0 — Installer verb parity (the AD-034 cmp-keyed contract) + the recipe discovery step in the templates
 
 A **feature** release (installer messaging + template text; deployment-lineage head stays `1.3.0`

package/SKILL.md

@@ -3,7 +3,7 @@ name: agent-workflow-memory
 description: Deploy or upgrade a portable AI-agent memory substrate in any project — an entry-point `AGENTS.md` (+ `CLAUDE.md` alias) and a structured `docs/ai/` context store with cap/archive/index enforcement. Use when the user wants to bootstrap `docs/ai/`, set up the Memory Map and session protocols, install the docs-rotation pre-commit hook, or run `/agent-workflow-memory` / `/agent-workflow-memory upgrade`. Triggers on "set up the memory system", "deploy the AI memory here", "bootstrap docs/ai", "upgrade the memory substrate". This is the substrate only — the workflow methodology (plan→execute→review, queue, Cleanup) is owned elsewhere and injected into AGENTS.md by the family composition root.
 disable-model-invocation: true
 metadata:
-  version: '1.10.0'
+  version: '1.11.1'
 ---
 
 # agent-workflow-memory
@@ -68,24 +68,26 @@ bootstrapping over a live system, but the user makes the final call.
 > Use that as the copy/read source; the working directory is the **target project**.
 
 > The three setup questions (steps 2–4) are decisions only the user can make and are hard to
-> reverse after a commit. Ask each as a **structured multiple-choice prompt where supported**
-> (`AskUserQuestion` in Claude Code, recommended option first), otherwise in prose — and
-> **wait for the answer before writing anything**.
+> reverse after a commit. Ask them as **ONE structured multi-question prompt where supported**
+> (`AskUserQuestion` in Claude Code, up to 4 questions per call, recommended option first),
+> otherwise in prose; **record each answer individually** — and **write nothing until ALL are
+> answered**.
 
 1. **Recon (read-only).** Before writing anything: `package.json` / `pyproject.toml` / `go.mod`
    / `Cargo.toml` → stack, package manager, scripts; `ls -la` root → README, existing
    `AGENTS.md`/`CLAUDE.md`, CI / linter configs; `git log --oneline -30` + `git status`; `src/`
    2–3 levels deep; tests + linter rules. Record stack, package manager, daily commands, layers.
-2. **Choose visibility — ASK explicitly and wait.** `visible` (committed — canonical,
+2. **Choose visibility — ask the batched prompt NOW (all three questions, per the preamble
+   above) and wait until every answer is in.** `visible` (committed — canonical,
    recommended) or `hidden` (in-tree, git-ignored via the **project-local** `.git/info/exclude` —
    never the machine-global excludes). See
    [Visibility contract](references/contracts.md#visibility-contract).
-3. **Choose conversational language — ASK explicitly and wait.** Which language the agent
+3. **Choose conversational language — answered in the step-2 batch.** Which language the agent
    *talks to them* in. Offer the language they're already writing in as the default. Carry it
    into the `{{COMM_LANGUAGE}}` slot of the *Communication language* block (step 5). See
    [Communication contract](references/contracts.md#communication-contract). Dialogue only —
    never the files.
-4. **Choose agent attribution — ASK explicitly and wait.** May the agent attribute work to
+4. **Choose agent attribution — answered in the step-2 batch.** May the agent attribute work to
    itself / AI — `Co-Authored-By` trailers, "Generated with …" footers, AI/agent/model mentions?
    **Default `off`.** Carry it into `{{AGENT_ATTRIBUTION}}` (step 5). **If `off` and the project
    uses Claude Code**, also set `"includeCoAuthoredBy": false` in the project's
@@ -196,13 +198,20 @@ Fill strategy:
    structure number, stamp filename, or internal versioning vocabulary on this happy-path exit — the
    number is inert here and belongs to *Version disclosure* (below).
 3. Show the relevant `${CLAUDE_SKILL_DIR}/CHANGELOG.md` context (entries newer than the stamp).
-4. Apply `${CLAUDE_SKILL_DIR}/migrations/<version>-<slug>.md` in **semver order**, only those
-   newer than the stamp. Migrations are **idempotent**.
+4. **Collect the migration answers FIRST, then apply.** If `AGENTS.md` is missing BOTH the
+   *Communication language* and *Attribution* blocks — i.e. both blocks are missing (a pre-1.1.0
+   deployment) — ask the two questions as ONE structured multi-question prompt; record each
+   answer individually, write nothing until ALL are answered, and carry the answers into the
+   migrations below: a migration whose answer was already collected never re-asks (its own
+   "Ask the user" step is the standalone fallback); a single missing block keeps its single ask
+   (step 5). Then apply `${CLAUDE_SKILL_DIR}/migrations/<version>-<slug>.md` in **semver order**,
+   only those newer than the stamp. Migrations are **idempotent**.
 5. Reconcile drift: add any substrate files/scripts the project is missing; **never clobber
    project-authored content** (their `decisions.md`, `known_issues.md`, page specs stay). For a
    pre-1.1.0 deployment with no *Communication language* block, ask + insert
    (`migrations/1.1.0-communication-language.md`); pre-1.2.0 with no *Attribution* block, ask +
-   insert defaulting to `off` (`migrations/1.2.0-agent-attribution.md`).
+   insert defaulting to `off` (`migrations/1.2.0-agent-attribution.md`). (An answer already
+   collected by the step-4 batched prompt is carried in — never re-asked here.)
 6. **Preserve BOTH pointer slots.** If `AGENTS.md` has the `workflow:methodology` and/or
    `workflow:orchestration` markers, **never regenerate the file wholesale** — extract any bytes
    between each pair and reinsert them unchanged. If a pair is absent (a legacy `AGENTS.md`),

package/capability.json

@@ -3,7 +3,7 @@
   "schema": 1,
   "name": "agent-workflow-memory",
   "kind": "memory-substrate",
-  "version": "1.10.0",
+  "version": "1.11.1",
   "provides": ["context"],
   "roles": {},
   "detect": {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sabaiway/agent-workflow-memory",
-  "version": "1.10.0",
+  "version": "1.11.1",
   "description": "Portable, cross-agent memory substrate for AI coding agents — an AGENTS.md entry point + docs/ai context with cap/archive/index enforcement, deployable standalone or as part of the agent-workflow family. The memory layer of the agent-workflow family.",
   "keywords": [
     "ai-agents",

package/references/contracts.md

@@ -5,8 +5,9 @@ language**, and **agent attribution** — each have a contract below. `SKILL.md`
 main procedure stays lean; load this file when you need the full rule for a contract (e.g. while
 filling the matching `AGENTS.md` block, or when an `upgrade` migration touches it).
 
-Ask each as a **structured multiple-choice prompt where your agent supports it** (`AskUserQuestion`
-in Claude Code), otherwise in prose — and always wait for the answer before writing.
+Ask the three as **ONE structured multi-question prompt where your agent supports it**
+(`AskUserQuestion` in Claude Code, up to 4 questions per call), otherwise in prose; record each
+answer individually — and write nothing until ALL are answered.
 
 ---
 

package/references/templates/agent_rules.md

@@ -72,7 +72,7 @@ Apply this as part of §2 before any user-facing summary:
 - **Large artifact (≈>100 lines):** deliver a real summary or the key excerpt inline **and** link the file — never flood the reader with a 2000-line paste, never hide the answer behind a bare pointer.
 
 ### 2.6. Planning, review & process-fidelity invariants
-Apply these when authoring a plan, reviewing, folding a finding, or editing code — the layer read **before any code change**. (Full canon: the project's planning / workflow-methodology + orchestration canon.)
+Apply these when authoring a plan, reviewing, folding a finding, or editing code — the layer read **before any code change**. (Full canon: the project's planning / workflow-methodology + orchestration canon. This section is rendered from that canon and refreshed on upgrade; a custom edit is preserved verbatim, but flagged.)
 - **Fold by code, not prose.** Before folding a code-touching finding into a plan or change, read the cited `file:line` and cite it — a prose fold drifts from the code and seeds the next bug.
 - **Right altitude.** Pin intent + invariants + acceptance criteria (named tests); leave fine code-mechanics to Execute, where prose cannot diverge from reality.
 - **No code-mechanics in the plan.** A Step still carries its exact paths + commands (the plan-structure / self-review canon) — checked syntax: the plan's own Verification runs them against an explicit expected outcome or gate; the only other syntax a plan may carry is a literal fixture/schema fragment a named test copies or validates. Un-run, logic-bearing syntax — control-flow, a regex, a glob, a grammar, an algorithm body, a mini-DSL — never lives in plan prose, however plausible or shell-verified it looks: a fold or draft that wants one is the trigger to write the test instead.