@sabaiway/agent-workflow-kit 1.29.0 → 1.30.0

package/CHANGELOG.md

@@ -4,6 +4,63 @@ Semantically versioned ([semver](https://semver.org)), newest first. The `versio
 is the current release. `upgrade` mode reads a project's `docs/ai/.workflow-version` and applies
 every `migrations/<version>-<slug>.md` newer than it, in semver order.
 
+## 1.30.0 — Review-recipe enforcement: the configured recipe is impossible to miss, "reviewed ≠ shipped" is detectable, grounding is a command (AD-038)
+
+A **feature** release (ships the bundled bridges refreshed to **2.2.0**). Origin: a real
+council-substitution incident + independent kit-user feedback — the configured review recipe could
+be silently skipped, downgraded, or run before later edits, and nothing could detect it. Three
+mechanisms, each self-firing at its point of use:
+
+- **The discovery line** — `tools/recipes.mjs --active-line` (`Mode: recipes`): exactly ONE
+  machine-composed line rendering the **CONFIGURED** recipe of every activity/slot from
+  `docs/ai/orchestration.json` + live readiness — source labeled, degradation stated, wrapper set
+  named, explicitly contrasted with the readiness recommendation (which is informational). Wired
+  where a session already reads: the deployed `agent_rules.md` §1.1 gains step 2 (read the
+  orchestration config BEFORE picking a task; a silent recipe downgrade is a forbidden
+  substitution) and `handover.md` gains a standing **"Active recipes:"** slot — both template
+  regions byte-identical with the memory copies (new `test/template-region-parity.test.mjs`,
+  injected-divergence non-vacuous); `set-recipe` now ECHOES the freshly composed line + a
+  handover-slot reminder after every successful `--write` (additive `activeLine` field in
+  `--json`). New `test/active-recipe-line.test.mjs` proves the line derives from the CONFIG, not
+  the recommendation.
+- **`/agent-workflow-kit review-state`** (`tools/review-state.mjs`, read-only + colocated tests) —
+  makes "reviewed ≠ shipped" mechanically detectable. The 2.2.0 review wrappers append one JSONL
+  receipt per SUCCESSFUL review to `<git dir>/agent-workflow-review-receipts.jsonl`
+  (`AW_REVIEW_RECEIPTS` overrides; never committable by construction); the checker resolves the
+  effective `plan-execution.review` recipe, recomputes the canonical **uncommitted-state
+  fingerprint** (sha256 over staged diff + unstaged diff + untracked-not-ignored contents — exactly
+  the review-payload domain), and `--check` exits 0 only when every recipe-named backend holds a
+  **fresh, grounded, current-fingerprint** receipt (**presence, not unanimity** — verdicts stay
+  orchestrator judgment). Any later edit stales the receipts; plan/diff receipts and continuations
+  (`fresh:false`) are informational-only — after a fold, only a fresh grounded re-run restores
+  green. Normative exit contract in the tool header; plan-in-flight detector keyed on the
+  documented `docs/plans` naming convention; honest residual stated (`--no-verify`, receipt-file
+  deletion — discipline, not a sandbox). The gate line is **never auto-seeded** ([[AD-021]]): the
+  template `gates.json` stays empty; the candidate line lives in `Mode: review-state`/`Mode: gates`
+  prose. New `test/review-fingerprint-parity.test.mjs` proves bash (both wrappers, byte-identical
+  block) ↔ node fingerprint parity — hash, serialization, AND behavioral domain equality.
+- **`/agent-workflow-kit grounding`** (`tools/grounding.mjs` + colocated tests) — the
+  grounded-review facts assembler, catalogued honestly as a **WRITER**: `--constraints` slices the
+  root `AGENTS.md` Hard-Constraints section verbatim (exactly-one-match, else a loud STOP);
+  `--plan <path>` extracts the decision-bearing sections (`## Approach` + `## Verification`
+  required, `## Decisions (locked)` when present; duplicates STOP); output honors the wrapper's
+  `AGY_MAX_PROMPT_BYTES` budget minus `--reserve-bytes` with a loud tail-trim; `--out` accepts only
+  gitignored / out-of-repo scratch (a tracked or in-repo not-ignored path is refused — a new
+  untracked file would move the fingerprint it grounds). `procedures.mjs` renders the invocation as
+  a POPULATED pre-step whenever agy is dispatched (exactly one plan in flight → its path; else a
+  placeholder + discovery caveat; additive `groundingPreStep` in `--json`).
+- **Bundled bridges 2.2.0** (mirrors byte-refreshed): `codex-review.sh` mandates + parses ONE
+  literal `Verdict: ship|revise|rethink` line (schema mode reads the JSON field); `agy-review.sh`
+  records the `### Verdict` token verbatim (SHIP / SHIP WITH NITS / REWORK), `grounded` +
+  `factsHash` from `--facts` (an empty payload is visible), and marks continuations `fresh:false`
+  with a one-line fresh-run notice; a receipt write failure warns and never fails the review. The
+  review-role `capability.json` contracts gain the `receipt` block (the fingerprint definition
+  home) — three-way lockstep wrapper `--help` ↔ manifest ↔ `detect-backends.mjs` registry,
+  drift-guarded.
+- **Catalog/report wiring:** two new SKILL modes + README rows; the bootstrap/upgrade report
+  footers paste the active-recipe line beside the backend-status line; `package-content` pin
+  94 → 96 (the two new tools).
+
 ## 1.29.0 — Velocity scope C: an opt-in PreToolUse gate-approval hook
 
 A **feature** release (ships the bundled bridges unchanged at **2.1.0**). The shipped, probe-proven

package/README.md

@@ -234,6 +234,8 @@ file), or run the guarded `/agent-workflow-kit uninstall`.
 | `/agent-workflow-kit recipes` | any time | **read-only** orchestration advisor: presents four named recipes for composing the bridges into plan → execute → review — **Solo / Reviewed / Council / Delegated** — plans + recommends one for your environment (degrading with a stated reason when a backend isn't ready), and offers the choice. The orchestrator runs it via the bridge skills and **always commits**; the kit never executes a recipe, never runs a subscription CLI, never commits. |
 | `/agent-workflow-kit procedures <activity>` | any time | **read-only** activity-procedures advisor: prints a named activity's ordered steps (`plan-authoring` / `plan-execution`) read **live** from the engine, plus the **resolved recipe per slot** from your `docs/ai/orchestration.json` (agent-writable via `set-recipe`, or hand-edited) + backend readiness (default Reviewed when a backend is ready, Council on request, slot-aware incl. Delegated) — and, for every dispatched backend, the **full driving contract at the point of use** (exact copy-pasteable invocation, grounding levers like agy's `--facts`/`--decided`, the round-2 `--continue` delta, guarded passthrough), verbatim from the bridge manifests (drift-guarded; each wrapper's `--help` prints the same). `--override <slot>=<recipe>` adjusts one slot per run. Composes with `recipes`; never writes, never commits, never runs a subscription CLI. |
 | `/agent-workflow-kit set-recipe` | any time | **config writer** for `docs/ai/orchestration.json`: tell the agent your preference in plain language and it maps it to explicit `--set <activity>.<slot>=<recipe>` / `--unset` ops; the kit validates, **previews by default**, and writes only on `--write` (deployment-gated, atomic, symlink/TOCTOU-safe), resolving the effective recipe vs live readiness. Writes **only** that file — **never runs a backend, never commits**; hand-editing stays fully supported. |
+| `/agent-workflow-kit review-state` | any time | **read-only review-receipt checker** — makes "reviewed ≠ shipped" detectable: the bridge review wrappers append a receipt per successful review (into a file inside the git dir — never committable); this checks that every backend your configured `plan-execution.review` recipe names holds a **fresh, grounded receipt for the current uncommitted tree** (any later edit moves the fingerprint and stales the receipt; a review continuation never re-attests a folded tree). `--check` gives a gate exit code to declare in `docs/ai/gates.json` **by hand** (never auto-seeded). Never writes, never commits, never runs a subscription CLI; it spawns read-only `git` queries to fingerprint the tree — and `git commit --no-verify` stays possible (discipline, not a sandbox). |
+| `/agent-workflow-kit grounding` | any time | **grounded-review facts assembler** — mechanizes populating `agy-review --facts @f`: slices your entry-point's **Hard Constraints** section verbatim (exactly one match, else a loud stop) and/or a plan's decision-bearing sections (`## Approach` + `## Verification` required, `## Decisions (locked)` when present; duplicates stop), under the same byte budget the agy wrapper enforces (minus `--reserve-bytes` for the artifact share), with a loud tail-trim on overflow. Prints to stdout; `--out` writes **one scratch file only** (gitignored / outside the repo — a tracked or not-ignored in-repo path is refused). Never commits, never runs a subscription CLI. |
 | `/agent-workflow-kit uninstall` | opt-in, any time | **guarded teardown** — the inverse of `init` / `setup`. Removes only what's **provably ours** (managed skill dirs + bridge wrappers; in a project, the hidden-mode git-ignore block it added + the pre-commit hook it installed); **never deletes** your `docs/ai` / `AGENTS.md` (prints the exact `rm` to run by hand) or your `.claude/settings.json` (prints an **edit** — remove the attribution key, review any velocity `permissions.*` — never an `rm`). Always `--dry-run` first; preflight-then-mutate; never commits. |
 | `/agent-workflow-kit velocity` | Claude Code · opt-in | **onboarding velocity profile** — seeds a fixed, audited **read-only** allowlist into `.claude/settings.json` so routine read-only commands stop idling on approval prompts while you're away; opt-in `acceptEdits`; plus a **read-only advisory** of likely project gate commands to add by hand. Writes **only** `.claude/settings.json` — **never** allowlists commit/push/publish, never writes `settings.local.json`, never commits. A seeded entry is a **trust posture, not a sandbox** (a runtime residual remains at the settings level — its guard ships as the opt-in `hook` command); a direct commit/push/publish still asks. `--dry-run` first. |
 | `/agent-workflow-kit agents` | Claude Code · opt-in | **cheap-lane subagents** — places bundled subagent definitions (`.claude/agents/`) pinned to a **cheap model** (haiku, low effort, read-only tools) for mechanical work: extraction sweeps, changelog fact-skeletons, gate-failure triage. Judgment, review, and real code stay on your main lane — these vehicles only extract and draft, and their output is verified. Preview by default (`--apply` writes); an existing customized file is **preserved, never overwritten**; never touches `settings*.json`, never commits. |

package/SKILL.md

@@ -3,7 +3,7 @@ name: agent-workflow-kit
 description: Deploy or upgrade a portable AI-agent memory-and-workflow system in any project. Use when the user wants to bootstrap `docs/ai/` + an entry-point `AGENTS.md` (+ `CLAUDE.md` alias) + cap/archive/index enforcement in a new or existing repo, set up the Memory Map and session protocols, install the docs-rotation pre-commit hook, or run `/agent-workflow-kit` / `/agent-workflow-kit upgrade`. Triggers on phrases like "set up the memory system", "deploy the AI workflow here", "bootstrap docs/ai", "upgrade the workflow".
 disable-model-invocation: true
 metadata:
-  version: '1.29.0'
+  version: '1.30.0'
 ---
 
 # agent-workflow-kit
@@ -177,8 +177,11 @@ 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. Present everything in the user's conversational language; never paste
-the JSON or any internal field name.
+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; *Mode: recipes*
+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
@@ -275,6 +278,8 @@ The declaration is **seeded at bootstrap** (the template loop, step 6) and **ens
 
 Declared gates can also be **auto-approved** (no permission prompt on a byte-exact invocation from the project root) via the opt-in PreToolUse hook — *Mode: hook*: the SAME declaration, a second consumer; editing gates.json needs no re-wiring.
 
+**Candidate line — the review-receipt gate (opt-in, never auto-seeded; AD-021).** Projects that configure a reviewed/council `plan-execution.review` recipe can declare the AD-038 review-state check as one more gate — the exact candidate `{ id, title, cmd }` line and its contract live under *Mode: review-state* (step 3). The template `gates.json` stays EMPTY; adding the line is the maintainer's explicit consent, by hand.
+
 **Invariants:** the runner writes nothing · never commits · never runs a subscription CLI · executes only the project's OWN declared commands (never a kit-invented one) · the bash contract fails loud, never reinterprets.
 
 ### Mode: bootstrap
@@ -447,6 +452,8 @@ The four recipes (defined over each bridge's `provides` roles — `codex`: execu
 2. **Offer the choice** via **`AskUserQuestion` where your agent supports it** (`AskUserQuestion` in Claude Code) — one option per recipe, the `recommendRecipe` choice listed **first** — otherwise in prose. Then print `planRecipe(chosen, detection)` (the per-stage dispatch + degradation reasons + quota/health notes) so the user sees exactly what running it entails.
 3. **Availability = `readiness === ready`, full stop.** Every other readiness supplies the human reason (needs-skill → "not installed — `/agent-workflow-kit setup`"; needs-cli → "install the CLI"; needs-credentials → "log in"; degraded → "wrapper not on PATH — `/agent-workflow-kit setup`"). This is set-up state only — **never** a claim that a backend's service is responsive (the detector cannot observe a runtime stall; `agy`'s Issue-001 is a *standing advisory*, not a readiness signal).
 
+**The configured-recipe line (`--active-line`, read-only).** `node ${CLAUDE_SKILL_DIR}/tools/recipes.mjs --active-line` prints exactly **one** machine-composed line: the **CONFIGURED** recipe of every activity/slot, resolved from the target project's `docs/ai/orchestration.json` (read from the current directory) + live readiness — each slot with its source (configured vs computed default), its degradation stated, and its dispatched wrapper set — explicitly contrasted with the readiness **recommendation** (which is informational; the configured recipes are what runs). Paste it verbatim: it fills the session-start discovery step (the deployed `agent_rules.md` §1.1) and the handover "Active recipes:" slot; `set-recipe` echoes the same line after every successful write. A malformed config fails loud (exit 1), never a silent fallback.
+
 **Invariants:** read-only · never runs a subscription CLI · never commits · the orchestrator executes the recipe via the bridge skills, not the kit.
 
 ### Mode: procedures
@@ -567,6 +574,33 @@ Run `node ${CLAUDE_SKILL_DIR}/tools/gate-hook.mjs [--dry-run | --apply] [--cwd <
 
 **Exit codes:** `0` done / dry-run (incl. the reported diverged-but-wired state); `1` a precondition STOP; `2` bad arguments.
 
+### Mode: review-state
+
+Read-only **review-receipt checker** (AD-038) — it makes *"reviewed ≠ shipped"* mechanically detectable. The bridge review wrappers (`codex-review` / `agy-review`, from bridge version 2.2.0) append one receipt line per **successful** review to a file **inside the git dir** (`<git dir>/agent-workflow-review-receipts.jsonl` — never committable by construction; `AW_REVIEW_RECEIPTS` overrides). This mode resolves the effective `plan-execution.review` recipe (the SAME config + read-only detector the `procedures` advisor reads), recomputes the canonical **uncommitted-state fingerprint** (staged + unstaged + untracked-not-ignored contents — exactly the review-payload domain; the prose definition lives in each bridge's `capability.json` review contract, implementations cross-checked by the kit's fingerprint-parity test), and reports, per recipe-named backend, whether a **fresh, grounded, current-fingerprint** receipt exists. It **never writes, never commits, never runs a subscription CLI**; it does spawn **read-only `git` queries** to compute the fingerprint — stated honestly (that is still read-only, but it is a subprocess).
+
+Run `node ${CLAUDE_SKILL_DIR}/tools/review-state.mjs [--check] [--json]`:
+
+1. Plain run → the human report: resolved recipe + source, plan-in-flight, tree fingerprint, per-backend receipt state (current / stale / ungrounded / missing) with verdict + grounding + timestamp.
+2. **`--check`** → the gate exit code. The **normative exit contract lives in the tool header** (the single home — do not re-enumerate it elsewhere): exit 0 for a solo-resolved recipe (configured, or degraded there — no ready reviewer), no plan in flight (the `docs/plans` naming convention: `queue.md` and `EXECUTE-`/`FEEDBACK-`-prefixed or `PROMPT`/`prompt`/`handoff`-carrying names are scratch), a clean tree, a non-git cwd, or every recipe-named backend receipted **current + grounded**; exit 1 when a backend is missing, **stale** (ANY edit after its review moves the fingerprint), or grounded:false under reviewed/council. **Presence, not unanimity:** verdict adjudication (ship/revise, the divergence crossover) stays orchestrator judgment — the gate only proves the configured backends really reviewed THIS tree. Plan/diff receipts and continuations (`agy-review --continue`) are **informational-only**: after a fold, only a **fresh grounded re-run** (`codex-review code`; `agy-review code --facts @f`) restores green.
+3. **Wire it as a gate by hand — never auto-seeded (AD-021).** The candidate line for your own `docs/ai/gates.json`: `{ "id": "review-state", "title": "Review receipts current for the uncommitted tree", "cmd": "node <path-to-this-skill>/tools/review-state.mjs --check" }` — with the path your project actually reaches the kit by. Once declared, the opt-in *Mode: hook* auto-approves it like any other declared gate.
+
+**Human residual (stated, accepted):** `git commit --no-verify` and receipt-file deletion/forgery remain possible — this is a self-discipline mechanism against silent process drift, not a security boundary.
+
+**Invariants:** read-only · never writes · never commits · never runs a subscription CLI · spawns read-only `git` queries only · the receipt writers are the bridge review wrappers, never the kit.
+
+### Mode: grounding
+
+The **grounded-review facts assembler** (AD-038) — an ungrounded `agy` review GUESSES, and while the grounding contract is mechanized (`agy-review code --facts @f`), populating the facts file was a manual chore. This mode emits the two **mechanical** halves of a facts payload; the orchestrator still owns any judgment-bearing additions. **Catalogued honestly as a WRITER** — `--out <path>` writes one file — with the invariant: `--out` accepts **only gitignored / out-of-repo scratch destinations** and REFUSES a tracked path AND an in-repo not-ignored path (a new untracked file would itself move the review fingerprint the facts are about to ground); **stdout is the default**. It never commits and never runs a subscription CLI.
+
+Run `node ${CLAUDE_SKILL_DIR}/tools/grounding.mjs [--constraints] [--plan <path>] [--reserve-bytes <n>] [--out <path>]`:
+
+1. **`--constraints`** — slice the root `AGENTS.md` **Hard Constraints** section, verbatim and whole (exactly ONE matching heading; zero or several is a loud STOP, never a guess — the marker-slot discipline).
+2. **`--plan <path>`** — extract the plan's decision-bearing canonical sections, verbatim + whole: `## Approach` (REQUIRED — its "What we are NOT doing" text rides inside; it is not a heading in canon) and `## Verification` (REQUIRED — STOP if missing), plus `## Decisions (locked)` when present (the optional engine §7 heading); a DUPLICATE heading is always a STOP.
+3. **Byte budget** — the output honors the same `AGY_MAX_PROMPT_BYTES` contract the agy wrapper enforces (override may only tighten; the OS argv ceiling is rejected), MINUS **`--reserve-bytes <n>`** — the artifact share the caller expects `agy-review` to add around these facts. Overflow is trimmed tail-first with a loud in-band marker + stderr report — never a silent cut.
+4. Feed the result to the wrapper: `agy-review code --facts @<out>`. The `procedures` advisor renders this invocation as a concrete pre-step whenever the resolved review dispatch includes agy — populated with the in-flight plan path when exactly one plan is in flight.
+
+**Invariants:** writer (writes at most the ONE `--out` scratch file — gitignored / out-of-repo only) · never commits · never runs a subscription CLI · verbatim slices only (assembly is mechanical; facts judgment stays with the orchestrator).
+
 ---
 
 ## Gotchas

package/bridges/antigravity-cli-bridge/SKILL.md

@@ -2,7 +2,7 @@
 name: antigravity-cli-bridge
 description: Delegate work to Google's Antigravity CLI (`agy`) — the successor to Gemini CLI — to reach Gemini, Claude, and GPT-OSS models under a Google AI Pro/Ultra subscription from the terminal. Use when the user wants to run a headless `agy` prompt, hand a focused task or second-opinion review to `agy`, install or authenticate Antigravity CLI, check or economise its quota/models, bridge project context into `agy`, set up a second delegated-execution backend beside Codex, or troubleshoot `agy` flags, models, auth, conversations, or its no-JSON headless behaviour.
 metadata:
-  version: '2.1.0'
+  version: '2.2.0'
 ---
 
 # antigravity-cli-bridge

package/bridges/antigravity-cli-bridge/bin/agy-review.sh

@@ -42,6 +42,8 @@
 #   AGY_PROBE=1              throwaway probe — silences the off-frontier model advisory
 #   AGY_REVIEW_ALLOW_ADDDIR=1  oversized CODE review: offload the change set to a private
 #                            staging dir and pass it via --add-dir (re-enables Issue-001 stall risk)
+#   AW_REVIEW_RECEIPTS       override the review-receipt file (default: <git dir>/
+#                            agent-workflow-review-receipts.jsonl — see the --help Receipt block)
 set -euo pipefail
 
 # --- --help / -h (pre-preflight: no agy, no login, no git tree needed) ---------
@@ -72,6 +74,18 @@ Round-2 / resume:
   agy-review --conversation <id> [--decided @f] [--focus "…"]
   (a continuation sends a small delta — agy holds the artifact server-side; --facts is invalid on a continuation)
 
+Receipt:
+  side effect — a successful review appends one JSON receipt line to
+  <git dir>/agent-workflow-review-receipts.jsonl (AW_REVIEW_RECEIPTS overrides; plan/diff outside
+  a git tree: warn + skip unless overridden): fingerprint = sha256 over the canonical
+  uncommitted-state payload (staged diff + unstaged diff + untracked-not-ignored contents — the
+  review-payload domain) in code mode, the artifact-file sha256 in plan/diff mode; verdict
+  recorded verbatim from the mandated '### Verdict' section (SHIP / SHIP WITH NITS / REWORK);
+  grounded = whether a NON-EMPTY --facts payload was supplied (an empty payload records
+  grounded:false — fail-closed, the state gate rejects it), factsHash = sha256 of the facts
+  payload; a continuation receipt is fresh:false (informational-only — it cannot attest the
+  folded tree); a write failure warns, never fails the review
+
 Closed grammar: unknown flags are rejected; no '--' passthrough (the only escapes are AGY_PROBE=1 and AGY_REVIEW_ALLOW_ADDDIR=1).
 Requires at run time: the agy CLI on PATH + a Google AI subscription login (--help needs neither).
 HELP
@@ -80,6 +94,10 @@ HELP
 esac
 
 DEFAULT_AGY_REVIEW_MODEL="Gemini 3.1 Pro (High)"
+# Review-receipt identity (AD-038). AW_BRIDGE_VERSION mirrors this bridge's SKILL.md/capability.json
+# version (drift-guarded by agy-review.test.mjs against capability.json).
+AW_RECEIPT_BACKEND="agy"
+AW_BRIDGE_VERSION="2.2.0"
 # `-` not `:-` so an EXPLICIT empty AGY_MODEL= survives (drop --model, use settings.json — agy.sh:52).
 AGY_MODEL="${AGY_MODEL-$DEFAULT_AGY_REVIEW_MODEL}"
 # Frontier review models. ANY model is allowed; a sub-frontier one only earns a soft, silenceable warning.
@@ -181,6 +199,95 @@ is_binary() {
   [[ "${nul:-0}" -gt 0 ]]
 }
 
+# --- Review receipts (AD-038) — byte-identical in codex-review.sh and agy-review.sh ---------------
+# sha256 hex of stdin. sha256sum, else shasum -a 256; neither → warn + fail (the caller records a
+# null fingerprint — a null never satisfies the review-state checker, fail-safe direction).
+sha256_stdin() {
+  if command -v sha256sum >/dev/null 2>&1; then sha256sum | awk '{print $1}'
+  elif command -v shasum >/dev/null 2>&1; then shasum -a 256 | awk '{print $1}'
+  else
+    echo "warning: no sha256sum/shasum on PATH — cannot compute the review fingerprint." >&2
+    return 1
+  fi
+}
+
+# The canonical uncommitted-state fingerprint payload (code mode). Domain == the review payload:
+# tracked staged + unstaged changes + untracked-not-ignored file contents (binary/symlink/non-regular
+# untracked paths ride as name-only notes, mirroring the assembled change set). The prose definition
+# lives in capability.json roles.review.contract.receipt (both bridges, lockstep); the kit checker
+# (tools/review-state.mjs) implements the SAME serialization in node — cross-checked by the kit's
+# review-fingerprint-parity.test.mjs.
+emit_fingerprint_payload() {
+  git diff --cached --no-ext-diff
+  git diff --no-ext-diff
+  local path
+  while IFS= read -r -d '' path; do
+    if [[ -L "$path" ]]; then
+      printf 'untracked-symlink:%s -> %s\n' "$path" "$(readlink -- "$path" 2>/dev/null || echo '?')"
+    elif [[ ! -f "$path" ]]; then
+      printf 'untracked-nonregular:%s\n' "$path"
+    elif is_binary "$path"; then
+      printf 'untracked-binary:%s\n' "$path"
+    else
+      printf 'untracked:%s\n' "$path"
+      cat -- "$path"
+    fi
+  done < <(git ls-files --others --exclude-standard -z)
+}
+
+# sha256 of the canonical payload, emitted from the work-tree ROOT (a subdir invocation hashes the
+# same bytes). Empty output on failure (no git tree / no sha256 tool) — recorded as null.
+compute_tree_fingerprint() {
+  ( cd "$(git rev-parse --show-toplevel)" && emit_fingerprint_payload ) | sha256_stdin
+}
+
+# JSON-encode a receipt scalar: empty → null, else a quoted string (every value comes from a closed
+# vocabulary or a hex digest — no escaping needed by construction).
+receipt_json_scalar() {
+  if [[ -z "${1:-}" ]]; then printf 'null'; else printf '"%s"' "$1"; fi
+}
+
+# write_review_receipt <artifact|""> <fresh: true|false> <fingerprint|""> <verdict> <grounded: true|false> <factsHash|"">
+# Appends ONE receipt line (the AD-038 fixture shape) as a side effect of a SUCCESSFUL review —
+# to $AW_REVIEW_RECEIPTS when set, else <git dir>/agent-workflow-review-receipts.jsonl (inside the
+# git dir by construction, so it is never committable). Fail-safe: every failure here warns loudly
+# and returns 0 — a missing receipt fails the kit's review-state CHECKER, never the review run.
+write_review_receipt() {
+  local artifact="$1" fresh="$2" fingerprint="$3" verdict="$4" grounded="$5" facts_hash="$6"
+  local receipts="${AW_REVIEW_RECEIPTS:-}"
+  if [[ -z "$receipts" ]]; then
+    local receipt_git_dir
+    if ! receipt_git_dir="$(git rev-parse --absolute-git-dir 2>/dev/null)"; then
+      echo "warning: not inside a git work tree and AW_REVIEW_RECEIPTS is unset — skipping the review receipt." >&2
+      return 0
+    fi
+    receipts="$receipt_git_dir/agent-workflow-review-receipts.jsonl"
+  fi
+  local line
+  line="$(printf '{"schema":1,"artifact":%s,"fresh":%s,"fingerprint":%s,"backend":"%s","verdict":"%s","grounded":%s,"factsHash":%s,"wrapperVersion":"%s","timestamp":"%s"}' \
+    "$(receipt_json_scalar "$artifact")" "$fresh" "$(receipt_json_scalar "$fingerprint")" \
+    "$AW_RECEIPT_BACKEND" "$verdict" "$grounded" "$(receipt_json_scalar "$facts_hash")" \
+    "$AW_BRIDGE_VERSION" "$(date -u +%Y-%m-%dT%H:%M:%SZ)")"
+  if ! printf '%s\n' "$line" >>"$receipts" 2>/dev/null; then
+    echo "warning: could not append the review receipt to $receipts — the review itself succeeded;" >&2
+    echo "         the review-state gate will read the current tree as un-receipted." >&2
+  fi
+}
+
+# Parse the mandated '### Verdict' section of a captured review: the first non-empty line after the
+# heading, matched against the closed verdict vocabulary (SHIP WITH NITS before SHIP — substring).
+# No heading / no match → "unknown" (recorded, never guessed).
+parse_agy_verdict() { # $1 = captured-output file
+  local line
+  line="$(awk '/^### Verdict/{flag=1; next} flag && NF {print; exit}' "$1" 2>/dev/null)"
+  case "$line" in
+    *"SHIP WITH NITS"*) printf 'SHIP WITH NITS' ;;
+    *REWORK*)           printf 'REWORK' ;;
+    *SHIP*)             printf 'SHIP' ;;
+    *)                  printf 'unknown' ;;
+  esac
+}
+
 # Emit the full code-review surface: repo map, status, staged + unstaged diffs, and the CONTENTS of
 # every untracked REGULAR file (NUL-safe iteration). Symlinks are shown as their target (never
 # followed — no out-of-repo leak); other non-regular paths (FIFO/socket/device/dir) are skipped.
@@ -246,6 +353,8 @@ mode=""
 target=""
 PLAN_CONTENT=""
 DIFF_CONTENT=""
+REVIEW_ARTIFACT=""
+REVIEW_FINGERPRINT=""
 if [[ -z "$resume_mode" ]]; then
   mode="${1:-}"; shift || true
   case "$mode" in
@@ -259,7 +368,10 @@ if [[ -z "$resume_mode" ]]; then
         echo "error: $mode file '$target' not found." >&2; exit 2
       fi
       # Read the target NOW (before any cd) — its path is relative to the invocation cwd.
-      if [[ "$mode" == "plan" ]]; then PLAN_CONTENT="$(cat -- "$target")"; else DIFF_CONTENT="$(cat -- "$target")"; fi ;;
+      if [[ "$mode" == "plan" ]]; then PLAN_CONTENT="$(cat -- "$target")"; else DIFF_CONTENT="$(cat -- "$target")"; fi
+      # Plan/diff receipt identity: the artifact-file sha256 (informational-only for the tree checker).
+      REVIEW_ARTIFACT="$mode"
+      REVIEW_FINGERPRINT="$(sha256_stdin <"$target" || true)" ;;
     *)
       usage; exit 2 ;;
   esac
@@ -392,6 +504,10 @@ else
       echo "agy-review: no uncommitted changes to review — the working tree is clean." >&2
       exit 0
     fi
+    # The canonical fingerprint of the tree agy is about to review — computed at assembly time,
+    # so the receipt attests exactly the reviewed state.
+    REVIEW_ARTIFACT="code"
+    REVIEW_FINGERPRINT="$(compute_tree_fingerprint || true)"
   fi
 
   emit_artifact() {
@@ -468,14 +584,39 @@ else
 fi
 
 # --- Execute via agy-run (single home of timeout + subscription + byte ceiling) ---
+# The output is teed into the private staging dir so the mandated '### Verdict' section can be
+# parsed into the review receipt — the user-facing stream is unchanged.
+review_out_file="$staging/review-output"
 set +e
 if (( ${#run_passthrough[@]} > 0 )); then
   AGY_MODEL="$AGY_MODEL" AGY_TIMEOUT="$AGY_TIMEOUT" AGY_HARD_TIMEOUT="$AGY_HARD_TIMEOUT" \
-    "$AGY_RUN" "@$prompt_file" -- "${run_passthrough[@]}"
+    "$AGY_RUN" "@$prompt_file" -- "${run_passthrough[@]}" | tee "$review_out_file"
+  rc=${PIPESTATUS[0]}
 else
   AGY_MODEL="$AGY_MODEL" AGY_TIMEOUT="$AGY_TIMEOUT" AGY_HARD_TIMEOUT="$AGY_HARD_TIMEOUT" \
-    "$AGY_RUN" "@$prompt_file"
+    "$AGY_RUN" "@$prompt_file" | tee "$review_out_file"
+  rc=${PIPESTATUS[0]}
 fi
-rc=$?
 set -e
+
+# --- Review receipt (AD-038): only a SUCCESSFUL review attests --------------------
+if [[ $rc -eq 0 ]]; then
+  verdict="$(parse_agy_verdict "$review_out_file")"
+  if [[ -n "$resume_mode" ]]; then
+    # A continuation never re-embeds the current artifact (agy holds the ORIGINAL round server-side;
+    # --facts is rejected above), so it cannot attest the folded tree: fresh:false, artifact /
+    # fingerprint / factsHash null, grounded false — informational-only, ignored by the state gate.
+    write_review_receipt "" false "" "$verdict" false ""
+    echo "notice: a continuation receipt is fresh:false (informational-only) — only a fresh grounded run" >&2
+    echo "        (agy-review code --facts @f) mints a receipt that satisfies the review-state gate." >&2
+  else
+    grounded=false
+    facts_hash=""
+    if [[ -n "$FACTS_CONTENT" ]]; then
+      grounded=true
+      facts_hash="$(printf '%s' "$FACTS_CONTENT" | sha256_stdin || true)"
+    fi
+    write_review_receipt "$REVIEW_ARTIFACT" true "$REVIEW_FINGERPRINT" "$verdict" "$grounded" "$facts_hash"
+  fi
+fi
 exit $rc

package/bridges/antigravity-cli-bridge/bin/agy-review.test.mjs

@@ -38,7 +38,7 @@ const FAKE_AGY = [
   '  fi; prev="$a"',
   'done',
   'if [[ -n "${AGY_FAKE_SLEEP:-}" ]]; then sleep "$AGY_FAKE_SLEEP"; fi',
-  'echo "FAKE_AGY_REVIEW_OUTPUT"',
+  'printf "%s\\n" "${AGY_FAKE_OUTPUT:-FAKE_AGY_REVIEW_OUTPUT}"',
   'exit "${AGY_FAKE_EXIT:-0}"',
   '',
 ].join('\n');
@@ -553,6 +553,13 @@ describe('agy-review.sh — --help contract (manifest-pinned)', () => {
     assert.ok(REVIEW_CONTRACT.continue.length > 0, 'manifest continue must be non-empty');
     setEq(got, REVIEW_CONTRACT.continue.map(norm), 'help continue ⟷ manifest continue');
   });
+
+  it('Receipt renders the manifest receipt contract verbatim (AD-038 three-way lockstep)', () => {
+    const help = runHelp('--help').stdout;
+    assert.equal(norm(helpSection(help, 'Receipt:').join(' ')), norm(REVIEW_CONTRACT.receipt));
+    assert.match(REVIEW_CONTRACT.receipt, /sha256 over the canonical uncommitted-state payload/, 'the fingerprint definition lives in the manifest contract');
+    assert.match(REVIEW_CONTRACT.receipt, /fresh:false/, 'the continuation informational-only clause is contractual');
+  });
 });
 
 describe('agy-review.sh — source-level reverse guard (parser arms ⟷ manifest)', () => {
@@ -625,3 +632,164 @@ describe('agy-review.sh — declared contract is really accepted (forward guard)
     assert.doesNotMatch(r.stdout, /Usage:/);
   });
 });
+
+// ── review receipts (AD-038) ─────────────────────────────────────────────────────
+// The normative fixture (docs: the AD-038 plan Decisions — copied verbatim; backend/verdict here
+// carry this bridge's vocabulary; dynamic values are asserted by shape):
+const RECEIPT_FIXTURE = JSON.parse(
+  '{"schema":1,"artifact":"code","fresh":true,"fingerprint":"<sha256hex>","backend":"codex","verdict":"revise","grounded":true,"factsHash":null,"wrapperVersion":"2.2.0","timestamp":"2026-07-03T12:00:00Z"}',
+);
+const RECEIPTS_REL = join('.git', 'agent-workflow-review-receipts.jsonl');
+const readReceipts = (repo) => {
+  const p = join(repo, RECEIPTS_REL);
+  if (!existsSync(p)) return [];
+  return readFileSync(p, 'utf8').trim().split('\n').filter(Boolean).map((l) => JSON.parse(l));
+};
+const sha256HexOf = async (buf) => {
+  const { createHash } = await import('node:crypto');
+  return createHash('sha256').update(buf).digest('hex');
+};
+const VERDICT_OUTPUT = '### Verdict\nSHIP WITH NITS — solid, two nits.\n### Blocking\nnone\n### Non-blocking\n1. nit\n### Questions\nnone';
+
+describe('agy-review.sh — review receipts (AD-038)', () => {
+  it('a fresh grounded code review appends ONE fixture-shaped receipt (verdict verbatim, factsHash real)', async () => {
+    const sb = makeSandbox();
+    const r = run(sb, { args: ['code', '--facts', 'a tiny fact'], env: { AGY_FAKE_OUTPUT: VERDICT_OUTPUT } });
+    const receipts = readReceipts(sb.repo);
+    rmSync(sb.home, { recursive: true, force: true });
+    assert.equal(r.status, 0, r.stderr);
+    assert.equal(receipts.length, 1, 'exactly one receipt line');
+    const receipt = receipts[0];
+    assert.deepEqual(Object.keys(receipt), Object.keys(RECEIPT_FIXTURE), 'fixture key set + order');
+    assert.equal(receipt.schema, 1);
+    assert.equal(receipt.artifact, 'code');
+    assert.equal(receipt.fresh, true);
+    assert.match(receipt.fingerprint, /^[0-9a-f]{64}$/, 'a real sha256 hex fingerprint');
+    assert.equal(receipt.backend, 'agy');
+    assert.equal(receipt.verdict, 'SHIP WITH NITS', 'the mandated ### Verdict section is recorded verbatim');
+    assert.equal(receipt.grounded, true, '--facts was supplied');
+    assert.equal(receipt.factsHash, await sha256HexOf('a tiny fact'), 'sha256 of the facts payload — an empty/changed facts file is visible');
+    assert.equal(receipt.wrapperVersion, MANIFEST.version, 'receipt version ⟷ capability.json version');
+    assert.match(receipt.timestamp, /^\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}Z$/);
+  });
+
+  it('an ungrounded fresh run records grounded:false + factsHash null (the vacuous-grounding hole stays visible)', () => {
+    const sb = makeSandbox();
+    const r = run(sb, { args: ['code'], env: { AGY_FAKE_OUTPUT: VERDICT_OUTPUT } });
+    const receipts = readReceipts(sb.repo);
+    rmSync(sb.home, { recursive: true, force: true });
+    assert.equal(r.status, 0, r.stderr);
+    assert.equal(receipts[0].grounded, false);
+    assert.equal(receipts[0].factsHash, null);
+  });
+
+  it('an EMPTY --facts file records grounded:false (fail-closed — vacuous grounding never satisfies the gate) and still warns', () => {
+    const sb = makeSandbox();
+    writeFileSync(join(sb.home, 'empty-facts.md'), '');
+    const r = run(sb, { args: ['code', '--facts', `@${join(sb.home, 'empty-facts.md')}`], env: { AGY_FAKE_OUTPUT: VERDICT_OUTPUT } });
+    const receipts = readReceipts(sb.repo);
+    rmSync(sb.home, { recursive: true, force: true });
+    assert.equal(r.status, 0, r.stderr);
+    assert.equal(receipts[0].grounded, false, 'an empty payload is recorded as ungrounded, never as grounded-by-flag');
+    assert.equal(receipts[0].factsHash, null);
+    assert.match(r.stderr, /no --facts supplied|ungrounded review GUESSES/, 'the ungrounded warning fires for an empty payload');
+  });
+
+  it('parses REWORK and plain SHIP; records "unknown" when the mandated section is absent', () => {
+    for (const [output, want] of [
+      ['### Verdict\nREWORK — the contract is violated.', 'REWORK'],
+      ['### Verdict\nSHIP — clean.', 'SHIP'],
+      ['free-form text with no verdict heading', 'unknown'],
+    ]) {
+      const sb = makeSandbox();
+      const r = run(sb, { args: ['code', '--facts', 'f'], env: { AGY_FAKE_OUTPUT: output } });
+      const receipts = readReceipts(sb.repo);
+      rmSync(sb.home, { recursive: true, force: true });
+      assert.equal(r.status, 0, r.stderr);
+      assert.equal(receipts[0].verdict, want, `verdict for: ${output.slice(0, 30)}`);
+    }
+  });
+
+  it('a continuation receipt is fresh:false with null identity fields, and the wrapper prints the fresh-run notice', () => {
+    const sb = makeSandbox();
+    const r = run(sb, { args: ['--continue', '--decided', 'already folded'], env: { AGY_FAKE_OUTPUT: VERDICT_OUTPUT } });
+    const receipts = readReceipts(sb.repo);
+    rmSync(sb.home, { recursive: true, force: true });
+    assert.equal(r.status, 0, r.stderr);
+    assert.equal(receipts.length, 1);
+    const receipt = receipts[0];
+    assert.deepEqual(Object.keys(receipt), Object.keys(RECEIPT_FIXTURE), 'same fixture shape');
+    assert.equal(receipt.fresh, false, 'a continuation cannot attest the folded tree');
+    assert.equal(receipt.artifact, null);
+    assert.equal(receipt.fingerprint, null);
+    assert.equal(receipt.grounded, false);
+    assert.equal(receipt.factsHash, null);
+    assert.equal(receipt.verdict, 'SHIP WITH NITS', 'the round-2 verdict is still recorded (informational)');
+    assert.match(r.stderr, /fresh grounded run/, 'the one-line notice names the required fresh run');
+    assert.match(r.stderr, /review-state gate/);
+  });
+
+  it('plan mode: artifact "plan", fingerprint = the artifact-file sha256', async () => {
+    const sb = makeSandbox();
+    writeFileSync(join(sb.repo, 'p.md'), '# plan body\n');
+    const r = run(sb, { args: ['plan', 'p.md', '--facts', 'f'], env: { AGY_FAKE_OUTPUT: VERDICT_OUTPUT } });
+    const receipts = readReceipts(sb.repo);
+    rmSync(sb.home, { recursive: true, force: true });
+    assert.equal(r.status, 0, r.stderr);
+    assert.equal(receipts[0].artifact, 'plan');
+    assert.equal(receipts[0].fingerprint, await sha256HexOf('# plan body\n'), 'plan fingerprint = file sha256');
+  });
+
+  it('plan/diff outside a git work tree: warn + skip the receipt (exit 0) unless AW_REVIEW_RECEIPTS is set', () => {
+    const sb = makeSandbox();
+    const outside = join(sb.home, 'no-repo');
+    mkdirSync(outside, { recursive: true });
+    writeFileSync(join(outside, 'p.md'), '# plan outside git\n');
+
+    const skipped = run(sb, { args: ['plan', 'p.md', '--facts', 'f'], cwd: outside, env: { AGY_FAKE_OUTPUT: VERDICT_OUTPUT } });
+    assert.equal(skipped.status, 0, skipped.stderr);
+    assert.match(skipped.stderr, /not inside a git work tree and AW_REVIEW_RECEIPTS is unset — skipping/);
+
+    const override = join(sb.home, 'receipts-override.jsonl');
+    const written = run(sb, {
+      args: ['plan', 'p.md', '--facts', 'f'],
+      cwd: outside,
+      env: { AGY_FAKE_OUTPUT: VERDICT_OUTPUT, AW_REVIEW_RECEIPTS: override },
+    });
+    const body = existsSync(override) ? readFileSync(override, 'utf8') : '';
+    rmSync(sb.home, { recursive: true, force: true });
+    assert.equal(written.status, 0, written.stderr);
+    assert.match(body, /"backend":"agy"/, 'the override path receives the receipt outside a git tree');
+    assert.match(body, /"artifact":"plan"/);
+  });
+
+  it('a receipt write failure warns loudly but never fails the review (fail-safe direction)', () => {
+    const sb = makeSandbox();
+    const r = run(sb, {
+      args: ['code', '--facts', 'f'],
+      env: { AGY_FAKE_OUTPUT: VERDICT_OUTPUT, AW_REVIEW_RECEIPTS: join(sb.home, 'no-such-dir', 'r.jsonl') },
+    });
+    rmSync(sb.home, { recursive: true, force: true });
+    assert.equal(r.status, 0, 'the review run itself succeeds');
+    assert.match(r.stderr, /could not append the review receipt/);
+    assert.match(r.stdout, /SHIP WITH NITS/, 'the findings still reach stdout');
+  });
+
+  it('a failed agy run writes NO receipt (only a successful review attests)', () => {
+    const sb = makeSandbox();
+    const r = run(sb, { args: ['code', '--facts', 'f'], env: { AGY_FAKE_EXIT: '7' } });
+    const receipts = readReceipts(sb.repo);
+    rmSync(sb.home, { recursive: true, force: true });
+    assert.notEqual(r.status, 0);
+    assert.equal(receipts.length, 0);
+  });
+
+  it('the clean-tree preflight exits before any receipt is written', () => {
+    const sb = makeSandbox({ clean: true });
+    const r = run(sb, { args: ['code', '--facts', 'f'] });
+    const receipts = readReceipts(sb.repo);
+    rmSync(sb.home, { recursive: true, force: true });
+    assert.equal(r.status, 0);
+    assert.equal(receipts.length, 0, 'no review ran — no receipt');
+  });
+});

package/bridges/antigravity-cli-bridge/capability.json

@@ -3,7 +3,7 @@
   "schema": 1,
   "name": "antigravity-cli-bridge",
   "kind": "execution-backend",
-  "version": "2.1.0",
+  "version": "2.2.0",
   "provides": ["review", "probe"],
   "roles": {
     "review": {
@@ -27,7 +27,8 @@
         "continue": [
           "agy-review --continue [--decided @f] [--focus \"…\"]",
           "agy-review --conversation <id> [--decided @f] [--focus \"…\"]"
-        ]
+        ],
+        "receipt": "side effect — a successful review appends one JSON receipt line to <git dir>/agent-workflow-review-receipts.jsonl (AW_REVIEW_RECEIPTS overrides; plan/diff outside a git tree: warn + skip unless overridden): fingerprint = sha256 over the canonical uncommitted-state payload (staged diff + unstaged diff + untracked-not-ignored contents — the review-payload domain) in code mode, the artifact-file sha256 in plan/diff mode; verdict recorded verbatim from the mandated '### Verdict' section (SHIP / SHIP WITH NITS / REWORK); grounded = whether a NON-EMPTY --facts payload was supplied (an empty payload records grounded:false — fail-closed, the state gate rejects it), factsHash = sha256 of the facts payload; a continuation receipt is fresh:false (informational-only — it cannot attest the folded tree); a write failure warns, never fails the review"
       }
     },
     "probe": { "cmd": "agy-run", "source": "bin/agy.sh", "output": "advisory" }

package/bridges/codex-cli-bridge/SKILL.md

@@ -2,7 +2,7 @@
 name: codex-cli-bridge
 description: Delegate work to the OpenAI Codex CLI (`codex`) under a ChatGPT subscription — run plan/instruction EXECUTION in a sandboxed workspace, or get a read-only ADVISORY review of a plan or working-tree diff — as a second delegated-execution backend beside Antigravity. Use when the user wants to hand a bounded coding task or plan to `codex exec`, get a second-opinion review from codex, install or authenticate Codex CLI, understand its sandbox/network/approval policy, drive codex efficiently from the main agent (exec vs review, resume, the commit boundary), bridge project context (`AGENTS.md`) into codex, or troubleshoot codex flags, models, auth, or its no-TTY headless behaviour.
 metadata:
-  version: '2.1.0'
+  version: '2.2.0'
 ---
 
 # codex-cli-bridge