@sabaiway/agent-workflow-kit 1.30.0 → 1.32.0

package/references/shared/deploy-tail.md

@@ -0,0 +1,61 @@
+## Gotchas
+
+The non-obvious traps — scan these before bootstrapping or upgrading. Each is also enforced inline in the bootstrap/upgrade procedures (`${CLAUDE_SKILL_DIR}/references/modes/bootstrap.md`, `${CLAUDE_SKILL_DIR}/references/modes/upgrade.md`); this is the consolidated high-signal list.
+
+- **Source vs target directory.** Templates and scripts are read from the skill's own dir (`${CLAUDE_SKILL_DIR}/` in Claude Code, the `SKILL.md` folder elsewhere). The **working directory is the target project** — never write kernel files back into the skill.
+- **The `Co-Authored-By` trailer is added by the harness, not by prose.** When attribution is `off`, a doc directive alone won't stop it — for Claude Code you **must** also set `"includeCoAuthoredBy": false` in the project's `.claude/settings.json` (create it if absent). Other tools: disable their equivalent co-author/footer setting.
+- **Hidden mode must never touch `package.json`.** Editing it is a *tracked* change and leaks the whole system. Hidden mode wires nothing into `package.json`; the pre-commit hook (untracked in `.git/hooks/`) calls `node scripts/<x>.mjs` directly. After hiding, **verify `git status` shows the artifacts as ignored**.
+- **Hidden mode is project-local, and the hide tool owns the known footprint.** `tools/hide-footprint.mjs` writes **one managed block** in the **project-local `.git/info/exclude`** — never the machine-global `core.excludesFile` (which would silently affect every repo on the host; **AD-014** amends **AD-006**). It hides the kit's own artifacts **and** the known external AI/agent footprint (the `KNOWN_FOOTPRINT` table in [contracts](${CLAUDE_SKILL_DIR}/references/contracts.md#visibility-contract)). A **tracked** file is **never silently un-tracked** — the tool prints the `git rm --cached` it will not run. Never leak its internal marker / asks terms to the user; translate every outcome to plain language.
+- **`CLAUDE.md` is a symlink, not a copy.** `ln -s AGENTS.md CLAUDE.md` — single source, no duplication. A copy drifts; a symlink can't.
+- **Never overwrite an existing entry point or hook.** If `AGENTS.md` / `CLAUDE.md` already exist, or the installer reports a pre-existing non-marker git hook, **stop and ask** the user to merge vs replace — don't clobber.
+- **Unrecognized invocations are read-only.** Only a **known** subcommand reaches its mode; the **bare** invocation bootstraps (and an existing `docs/ai/` makes it ask upgrade-vs-bootstrap first, never overwrite); **any other / ambiguous** token routes to `help` (read-only). A garbage invocation never writes. The mapping is pinned by `tools/commands.mjs` `routeInvocation` (unit-tested) — don't hand-route around it.
+- **No Node runtime → skip enforcement.** If the project has no Node (recon step 1), skip bootstrap steps 8–9 (scripts + hook) and follow the cap/archive/index policy manually, or port the scripts to the project's language.
+- **Conversational language never translates artifacts.** It governs *dialogue only*. Code, identifiers, paths, commands, log output, abbreviations, and every deployed `docs/ai/` / `AGENTS.md` file stay in their source language. See [Communication contract](${CLAUDE_SKILL_DIR}/references/contracts.md#communication-contract).
+- **Never auto-commit.** Report quality-gate results and wait for explicit approval — in both modes.
+- **Never leak kit internals to the user.** No ADR ids, tool / function / operation names (`reconcile`, `inject`, `ensureSlot`), marker / slot / fragment / anchor terminology, or verbatim tool stderr in anything the user reads. Translate every tool outcome into plain language a third-party user — who has never read this `SKILL.md` — can understand and act on (e.g. the cap-refusal report in `${CLAUDE_SKILL_DIR}/references/modes/upgrade.md` step 3).
+- **Uninstall never deletes user-authored content, and dry-runs first.** `/agent-workflow-kit uninstall` removes only what is **provably ours** (a managed skill dir / wrapper symlink / fenced block / marker hook) and **prints — never runs** the `rm` / `git rm --cached` for `docs/ai` and the entry-point docs, and an **edit** instruction (not an `rm`) for `.claude/settings.json`. Always run `--dry-run` first, show the plan, get consent, then `--yes`. A skill dir or symlink that is not provably ours is a STOP, never a clobber (the `setup` posture, inverted). Removing a shared global (memory/engine/a bridge) may affect another project — say so.
+
+---
+
+## Setup contracts
+
+The three setup choices — **visibility** (step 2), **conversational language** (step 3), and **agent attribution** (step 4) — each have a full contract in [`references/contracts.md`](${CLAUDE_SKILL_DIR}/references/contracts.md). Load it when you need the complete rule (e.g. while filling the matching `AGENTS.md` block, or when an `upgrade` migration touches one). Defaults, in brief: visibility = `visible` (committed); language = whatever the user is already writing in; attribution = `off`. Ask each as a structured multiple-choice prompt where supported (`AskUserQuestion` in Claude Code), otherwise in prose.
+
+---
+
+## System principles (encode these into the project's `AGENTS.md`)
+
+1. **Single entry point.** `AGENTS.md` is the only entry point (tool aliases like `CLAUDE.md` symlink to it); it never bloats — details live in `docs/ai/`.
+2. **Memory Map.** A "read-when / update-when" table for every file. Without it agents get lost.
+3. **Three protocols.** Start of Session → During Work → Task Completion, each a short checklist.
+4. **Update docs BEFORE code.** Page behaviour changing? Update `pages/<page>.md` first, then the code.
+5. **No silent failures.** Every internal validation/guard that rejects an action logs structured context (component, action, ids, inputs); user-facing failures also surface in the UI.
+6. **TDD by default.** Test before code (unit for functions, E2E for user flows).
+7. **ADR for strategic choices.** Long-term-consequence decisions get a `decisions.md` entry.
+8. **Hard Constraints are tool-enforced.** Style rules live in linter/type-checker configs, not prose.
+9. **Ask before commit.** The agent reports quality-gate results and waits for explicit approval; it never auto-commits.
+10. **Honest `known_issues.md`.** Every bug with a workaround gets Impact + Plan so it isn't re-discovered later.
+11. **One conversational language.** Talk to the user in the language chosen at bootstrap; keep code, paths, commands, and abbreviations in their source language. See *Communication contract*.
+12. **Attribution is opt-in.** Honour the *Attribution* block: by default no agent/AI/model mention anywhere (commits, PRs, code, comments, docs), and no `Co-Authored-By` trailer. See *Attribution contract*.
+13. **Orchestrate via a named recipe.** Compose execution through a named recipe (Solo / Reviewed / Council / Delegated) and **always commit yourself** — backends are advisory or delegated, never autonomous. Encoded via the reconciled `workflow:orchestration` pointer (it routes to `/agent-workflow-kit recipes` + the engine canon), not by bloating the entry point.
+
+---
+
+## Hard Constraints (template — adapt to the stack)
+
+Deploy these into `AGENTS.md`; remove rows that don't apply to the stack.
+
+| Rule | Enforcement |
+|------|-------------|
+| No `export default` (named exports only) | Linter |
+| No `any` / no unsafe casts | Linter / type-checker |
+| Functional style (no mutation in app code) | Linter |
+| No single-letter variables | Code review |
+| Interactive elements semantic (button/link, not div+onClick) | Linter / a11y |
+| No hardcoded colors — design tokens only | Code review |
+| No business logic in components → hooks/services | Architecture review |
+| No changes without tests (TDD) | Required |
+| Check page docs before changes; update them after | Process |
+| Ask user before committing | Process |
+| Every page has an HTML-validity / a11y E2E test | Required |
+| **No silent failures** — structured logging on every rejected action | Required |

package/references/shared/report-footer.md

@@ -0,0 +1,116 @@
+### The one-line backend-status line (shared by bootstrap + upgrade)
+
+Bootstrap (step 11) and **every** successful `upgrade` exit (steps 4 + 8) print the **same**
+read-only, one-line summary of the optional execution-backends. The line is **machine-composed** —
+run the status-line composer and **paste its single emitted line verbatim**:
+`node ${CLAUDE_SKILL_DIR}/tools/recipes.mjs --status-line`
+The tool runs the backend detector and appends the recipe recommendation itself
+(`composeStatusLine`); the agent **composes nothing factual** — no readiness token, no glyph, no
+recipe clause of its own, ever.
+
+- **Placeholder template (structure only — never copy this example; paste the tool's line):**
+  `backends: <alias> <✓|✗> <readiness> · <alias> <✓|✗> <readiness> — run /agent-workflow-kit backends · recipes: <recommendation clause> — see /agent-workflow-kit recipes`
+- The **`recipes:` clause is appended after** the `— run /agent-workflow-kit backends` pointer (never
+  replacing it) and routes to the read-only `recipes` mode (`see /agent-workflow-kit recipes`). It is
+  **never blank**: both backends ready → *"Council available, Reviewed the everyday default"*; one
+  ready → *"Reviewed available (via …)"*; **none installed → *"Solo — run /agent-workflow-kit setup to
+  add a backend"***; a backend present-but-not-ready → Solo with that backend's specific remedy.
+  (Composed by `recommendRecipe` inside the same tool run — never by the agent.)
+- **Invariants:** **read-only · never blocks the commit gate · never runs a subscription CLI · the
+  pointer is the in-agent `backends` mode, never a network fetch · the appended `recipes:` clause
+  routes to the in-agent `recipes` mode the same way · `init`/npx never *places* bridges (it
+  refreshes only what `setup` already placed, AD-011 §5).**
+- **Composer unavailable → skip with a stated reason, never silently.** The composer is a Node script
+  the **agent host** runs (not the target project), so the only skip condition is "**the agent host
+  can't run it**" — `node` is not on the agent's PATH, or the tool itself errors — **not** "the
+  project has no Node runtime". On that condition, skip the line and say so **with the concrete
+  reason**, e.g. *"Couldn't run the backend status-line composer here (node is not on the agent host
+  PATH), so I'm skipping the backend-status line."* — never a silent skip (Hard Constraint — no
+  silent failures).
+
+### The version block + welcome mat (shared by bootstrap + upgrade)
+
+Bootstrap (step 11) and **every** successful `upgrade` exit (steps 4 + 8) close with the same
+**report footer**, in this **canonical order**: success state → **version block** → the **one-line
+backend-status line** → **welcome mat**. Only the version block comes from
+`node ${CLAUDE_SKILL_DIR}/tools/family-registry.mjs --json` (add `--dir <project>` for the deploy
+axis) — **never hardcoded semver**; the backend-status line is its own shared contract (above), and
+the welcome mat **composes signals already gathered** (the version block's notes + the backend-status
+line), not a fresh helper call. **Beside the backend-status line**, when the target project carries a
+`docs/ai/orchestration.json`, also paste the one-line **configured-recipe line** verbatim from
+`node ${CLAUDE_SKILL_DIR}/tools/recipes.mjs --active-line` (run from the project root; `${CLAUDE_SKILL_DIR}/references/modes/recipes.md`
+documents it; same agent-host skip-with-reason contract as the status line). Present everything in the
+user's conversational language; never paste the JSON or any internal field name.
+
+**Success state — the happy path never leads with a structure number.** No happy-path report surfaces
+the project's internal `docs/ai` structure version, the stamp filename, or the internal versioning
+vocabulary — that number is inert here and only confuses; it belongs to *Version disclosure* (below).
+Frame the success itself plainly, in the **user's conversational language** (never hardcode a phrase):
+- a **zero-diff no-op `upgrade`** (step 4) → **settings already current — no update is required**
+  (illustrative tone for a Russian-speaking user, an example of the meaning, not a literal string to
+  embed: *«Настройки уже актуальны — обновление не требуется»*);
+- a **fresh `bootstrap`** → its normal "deployed and ready" success, minus the number.
+
+**Version block — the installed package versions, fed from `--json`** (the `docs/ai` structure version
+is shown on demand only — see *Version disclosure* below, **not** here):
+- **`Installed on this machine — package versions:`** `kit <v> · memory <v> · engine <v> ·
+  codex-bridge <v> · antigravity-bridge <v>` — one per `installed[]` entry, labelled by its `display`
+  and showing its `version`, or, when there is no version, the plain phrase for its `state` (map
+  below). Append any `installed[].notes` **in plain words** (e.g. the memory-behind refresh+restart
+  line).
+
+**`state` → plain language** (map the envelope's `installed[].state` token; never show the raw token):
+`installed` → its version · `absent` → "not installed" · `other-tool` → "a different tool occupies
+that skill slot" · `placeholder` → "a placeholder, not a working install" · `invalid` → "installed
+but its manifest didn't validate" · `unsupported` → "installed but its manifest schema is too new for
+this kit" · `uncheckable` → "couldn't be checked (a permission error)".
+
+**Helper-failure contract (mirror the backend-status line).** The version block needs the
+family-registry helper, which the **agent host** runs. If the host can't run it (`node` not on the
+agent's PATH, or the helper errors), **skip the version block and say so with the concrete reason** —
+e.g. *"Couldn't run the family-registry helper here (node is not on the agent host PATH), so I'm
+skipping the installed-versions block."* — never a silent skip (Hard Constraint). It is non-essential:
+the rest of the report — and the commit gate — proceeds.
+
+**Welcome mat — the last line(s) of the footer.** After the version block and the backend-status
+line, print *"Run `/agent-workflow-kit help` to see every command."* then **one** recommended next
+step, chosen **caveat-aware** from signals already in hand (the version block's notes + the
+backend-status line — no new helper call) in this priority order:
+1. a member is **behind** (a behind-class `installed[].notes` caveat fired — any member, the bridges
+   included) → *refresh the behind member first*, quoting **that note's own recovery command
+   verbatim** (a memory/engine note carries its `npx …@latest init` + restart the session; a bridge
+   note carries `/agent-workflow-kit setup`). An **uncheckable** member ("couldn't be checked" — an
+   unknown-freshness note) is **never** a refresh trigger: only a behind note fires this step — the
+   uncheckable note already appears in the version block, add nothing more;
+2. else **no backend is ready** (the backend-status line shows none ready) → *set one up with
+   `/agent-workflow-kit setup`*;
+3. else **a backend is ready but the orchestration config is still all-Solo** (no `reviewed` /
+   `council` / `delegated` slot anywhere — inspect `docs/ai/orchestration.json`, or read the
+   procedures advisor's resolved recipes) → *put it to work with `/agent-workflow-kit recipes`*;
+4. else (a backend is ready **and** a backend-backed recipe is already selected) → the optional
+   *`/agent-workflow-kit velocity`* opt-in (never run it without a yes).
+
+Keep it compact — a few short lines, plain language, no kit-internal terms.
+
+### Version disclosure — the `docs/ai` structure version, on demand only
+
+The deployment carries an internal **`docs/ai` structure version** (the envelope's `deploymentHead`) —
+the number `upgrade` compares the project's stamp against to decide whether a migration is due. The
+happy path deliberately **hides** it: a user cannot act on it, and because it advances far more slowly
+than the published package version, it reads as *"why is this smaller than what GitHub shows?"* Surface
+it in exactly **three** places, and nowhere else:
+1. the **never-downgrade STOP** (`${CLAUDE_SKILL_DIR}/references/modes/upgrade.md` step 2) — the stamp is ahead of what this kit knows,
+   so the number IS the message;
+2. the **explicit version-status view** (`${CLAUDE_SKILL_DIR}/references/modes/status.md`) the user deliberately opens;
+3. when the **user explicitly asks** about versions.
+
+When you show it, **name what it versions — "the `docs/ai` structure version"** (render that meaning in
+the user's conversational language) — **never** "lineage head", "deployment head", or any raw internal
+token. Pair it with **one plain-language line** telling the two axes apart, on demand only:
+
+> the number your project carries versions its `docs/ai` **structure**; the (usually larger) number on
+> npm/GitHub is the **tool's own package version** — the two advance independently, so a bigger package
+> number is **not** a newer deployment.
+
+**Never** print this two-axes line on a successful equal-head exit — only at the STOP, the status view,
+or on an explicit ask.

package/tools/engine-source.mjs

@@ -107,7 +107,8 @@ export const detectEngine = (engineDir, { source, rel } = {}, deps = {}) => {
 // on the happy path; THROWS a loud Error naming the resolved dir + the reason + the exact
 // remediation on absent/invalid/unreadable — never a fallback (fail-closed). The "methodology engine
 // not found/invalid" prefix is a stable contract: the agent classifies the reconcile STOP by it
-// (distinct from the cap-skip message), so do not reword it without updating SKILL.md.
+// (distinct from the cap-skip message), so do not reword it without updating the upgrade mode file
+// (references/modes/upgrade.md, step 3 exit classification).
 export const readEngineFragment = (engineDir, deps = {}) => {
   const detection = detectEngine(engineDir, { source: deps.source, rel: deps.rel }, deps);
   const installHint = `npx @sabaiway/agent-workflow-engine@latest init  (or set ${ENGINE_ENV})`;