peaks-loop 4.0.0-beta.9 → 4.0.1

package/README-en.md

@@ -5,10 +5,12 @@
 ### You talk. It runs the entire engineering chain for you — beyond just code, twice-run flows sediment into local tactics.
 
 [![npm](https://img.shields.io/npm/v/peaks-loop?style=for-the-badge&logo=npm&logoColor=white&color=cb3837)](https://www.npmjs.com/package/peaks-loop)
+[![publish](https://img.shields.io/github/actions/workflow/status/SquabbyZ/peaks-loop/publish.yml?style=for-the-badge&logo=githubactions&logoColor=white&label=publish)](https://github.com/SquabbyZ/peaks-loop/actions/workflows/publish.yml)
+[![ci](https://img.shields.io/github/actions/workflow/status/SquabbyZ/peaks-loop/ci.yml?style=for-the-badge&logo=githubactions&logoColor=white&label=ci)](https://github.com/SquabbyZ/peaks-loop/actions/workflows/ci.yml)
 [![license](https://img.shields.io/badge/license-MIT-blue?style=for-the-badge)](./LICENSE)
-[![node](https://img.shields.io/badge/node-%E2%89%A520-339933?style=for-the-badge&logo=node.js&logoColor=white)](https://www.npmjs.com/package/peaks-loop)
+[[![node](https://img.shields.io/badge/node-%E2%89%A520-339933?style=for-the-badge&logo=node.js&logoColor=white)](https://www.npmjs.com/package/peaks-loop)
 [![tests](https://img.shields.io/badge/tests-5%2C439%20passed-22c55e?style=for-the-badge&logo=vitest&logoColor=white)](#status)
-[![stars](https://img.shields.io/github/stars/SquabbyZ/peaks-loop?style=for-the-badge&logo=github&logoColor=white)](https://github.com/SquabbyZ/peaks-loop/stargazers)
+[![stars](https://img.shields.io/github/stars/SquabbyZ/peaks-loop?style=for-the-badge&logo=github&github=github&logoColor=white)](https://github.com/SquabbyZ/peaks-loop/stargazers)
 
 **English** · [简体中文](./README.md)
 
@@ -22,7 +24,15 @@
     style="border-radius: 14px; box-shadow: 0 12px 40px rgba(0,0,0,0.55); display: block;"
   />
   <br>
-  <sub>👆 18s looping GIF (<a href="https://raw.githubusercontent.com/SquabbyZ/peaks-loop/main/examples/video-demo/preview/peaks-loop-demo-en.mp4">full 30s mp4 download</a> · 13MB · 480p)</sub>
+  <sub>👆 18s looping GIF (full 30s mp4 is no longer shipped with the npm package — see <a href="https://github.com/SquabbyZ/peaks-loop/releases">GitHub Releases</a> · 13MB · 480p)</sub>
+</p>
+
+<p align="center">
+  <img
+    src="./assets/readme/releases-banner.svg"
+    alt="peaks-loop 4.0.0 GA release banner — first stable cutover from 4.0.0-beta.36"
+    width="92%"
+  />
 </p>
 
 ---
@@ -98,7 +108,7 @@ Every lane opens with **one slash command**.
 ## Why people pick it
 
 - **Natural language is the interface.** No CLI to learn, no commands to memorize. **Use an explicit slash command (e.g. `/peaks-code xxx`)** to route to the right orchestrator; everything after the slash is plain language. The LLM runs the commands on your behalf.
-- **Gates that actually block, not decorate.** 5,439 test cases, QA gate, review sign-off — all on by default. **Audit fails = stop. QA fails = stop.**
+- **Gates that actually block, not decorate.** 219 test cases (4 packages, all green), QA gate, review sign-off — all on by default. **Audit fails = stop. QA fails = stop.**
 - **Run-once flows become local tactics (bees).** Sedimented loop engineering lands in your local `~/.peaks/` pool — twice-clean runs auto-promote to standing tactics, broken runs come back for you to redefine. **Next time, just say "run that one" and the whole playbook slots back in.** Your few tactics grow with your taste.
 - **Sits on top of what you already run.** Not a new AI CLI to learn — it rides on **Claude Code** and **Z Code**. No shell grab, no prompt grab, no IDE grab. Other tools: adapters in progress, contributions welcome.
 - **You decide, it executes.** Decisions that touch your assets are yours; everything else it runs on its own. **Zero learning cost. One minute to first task.**
@@ -123,10 +133,10 @@ Every lane opens with **one slash command**.
 
 | | |
 | --- | --- |
-| **Latest** | [`4.0.0-beta.7`](https://github.com/SquabbyZ/peaks-loop/releases) — 4.x GA is in the works |
+| **Latest** | [`4.0.1`](https://github.com/SquabbyZ/peaks-loop/releases) — 4.x GA is in the works |
 | **Domains** | Code (`peaks-code`) · Content (`peaks-content`) · Project health (`peaks-doctor`) · Issue sweep (`peaks-issue-fix-orchestrator`) · Custom SOP (`peaks-sop`) · Cross-domain primitives (`peaks-solo` dispatcher · `peaks-resume` · `peaks-status` · `peaks-test`) |
 | **Sediment pool** | `~/.peaks/` local pool · twice-clean runs auto-promote to a bee · broken runs come back for you to redefine · the bee grows with your taste |
-| **Test suite** | 5,439 passed · 19 skipped · 0 failed |
+| **Test suite** | 219 passed · 0 failed (4 packages: peaks-loop / peaks-loop-mut / peaks-loop-shared-channel / peaks-loop-shared) |
 | **IDE adapters** | ✅ Claude Code · ✅ Z Code · 🚧 Codex / Cursor / Trae / Tongyi Lingma / Hermes / OpenClaw / Qoder (adapters in progress — contributions welcome) |
 | **Runtime** | Node ≥ 20 |
 | **License** | MIT |
@@ -202,7 +212,16 @@ It changes, but **the gates hold**. Audit fails = nothing ships. QA fails = noth
 <details>
 <summary><b>What's new in 4.x vs 3.x?</b></summary>
 
-**The biggest shift: from "code-only tool" to multi-domain orchestration system.** 4.x no longer just writes code — it ships four new domain orchestrators: `peaks-content` (content production), `peaks-doctor` (project health), `peaks-issue-fix-orchestrator` (batch issue fix), `peaks-sop` (custom SOPs). On top of that, `peaks-solo` auto-routes to the right domain from plain language. Plus 9 IDE adapters, crystallization-system renaming, post-run crystallization, 5,439 tests passing. Full list → [`CHANGELOG.md`](./CHANGELOG.md).
+**The biggest shift: from "code-only tool" to multi-domain orchestration system.** 4.x no longer just writes code — it ships four new domain orchestrators: `peaks-content` (content production), `peaks-doctor` (project health), `peaks-issue-fix-orchestrator` (batch issue fix), `peaks-sop` (custom SOPs). On top of that, `peaks-solo` auto-routes to the right domain from plain language. Plus 9 IDE adapters, crystallization-system renaming, post-run crystallization. Full list → [`CHANGELOG.md`](./CHANGELOG.md).
+
+### What 4.0.0 GA actually shipped (2026-07-30)
+
+| Epic | Solved | Verified by |
+| --- | --- | --- |
+| **Test suite rebuilt from scratch** | Old 559-file unit suite took 3+ hours; now 219 cases across 4 packages all green, `pnpm test:full` in ~67s. Deleted old assertions, wrote against the production contract, 4-dim split (render/behavior/integration/a11y). | commits `f17aa377` → `1d6233bc` · `.peaks/memory/2026-07-30-test-rebuild-epic-sediment.md` |
+| **Karpathy evaluation cost self-review** | LLM no longer "done for today, will continue tomorrow" after 1–2 slices — `karpathy-reviewer` reports `costRatio`; `peaks job karpathy-cost-check` auto-downgrades `block` → `warn` above 10. 24h-mode stays the override. | `peaks job karpathy-cost-check --review-file <path>` · 21-case unit test |
+| **Compact visibility** | `peaks compact history` for the LLM to read every compact event of the current session; `peaks statusline compact` for the IDE statusline ( `--` / `compact pending (0.85)` / `REDLINE 0.95` / `just compacted (0.92→?)` ). | `auto-compact-orchestrator` appends to `compact-history.jsonl` · 19-case unit test |
+| **Sub-package coverage + workspace-wide `pnpm test:full`** | Independent 4-dim tests for `peaks-loop-mut` / `peaks-loop-shared-channel`; `peaks-loop-shared` 0 file (passWithNoTests); redundant root mirror removed. | commits `593ffcdf` → `08e92d8f` · `pnpm test:full` runs all 4 packages in one go |
 
 </details>
 

package/README.md

@@ -5,10 +5,12 @@
 ### 你说话,它替你跑完一整条工程流水线 —— 不止写代码,跑两次就沉淀成本地战术。
 
 [![npm](https://img.shields.io/npm/v/peaks-loop?style=for-the-badge&logo=npm&logoColor=white&color=cb3837)](https://www.npmjs.com/package/peaks-loop)
+[![publish](https://img.shields.io/github/actions/workflow/status/SquabbyZ/peaks-loop/publish.yml?style=for-the-badge&logo=githubactions&logoColor=white&label=publish)](https://github.com/SquabbyZ/peaks-loop/actions/workflows/publish.yml)
+[![ci](https://img.shields.io/github/actions/workflow/status/SquabbyZ/peaks-loop/ci.yml?style=for-the-badge&logo=githubactions&logoColor=white&label=ci)](https://github.com/SquabbyZ/peaks-loop/actions/workflows/ci.yml)
 [![license](https://img.shields.io/badge/license-MIT-blue?style=for-the-badge)](./LICENSE)
 [![node](https://img.shields.io/badge/node-%E2%89%A520-339933?style=for-the-badge&logo=node.js&logoColor=white)](https://www.npmjs.com/package/peaks-loop)
 [![tests](https://img.shields.io/badge/tests-5%2C439%20passed-22c55e?style=for-the-badge&logo=vitest&logoColor=white)](#status)
-[![stars](https://img.shields.io/github/stars/SquabbyZ/peaks-loop?style=for-the-badge&logo=github&logoColor=white)](https://github.com/SquabbyZ/peaks-loop/stargazers)
+[![stars](https://img.shields.io/github/stars/SquabbyZ/peaks-loop?style=for-the-badge&logo=github&github=github&logoColor=white)](https://github.com/SquabbyZ/peaks-loop/stargazers)
 
 [English](./README-en.md) · **简体中文**
 
@@ -22,7 +24,15 @@
     style="border-radius: 14px; box-shadow: 0 12px 40px rgba(0,0,0,0.55); display: block;"
   />
   <br>
-  <sub>👆 18s 循环 GIF(<a href="https://raw.githubusercontent.com/SquabbyZ/peaks-loop/main/examples/video-demo/preview/peaks-loop-demo.mp4">完整 30s mp4 下载</a> · 13MB · 480p)</sub>
+  <sub>👆 18s 循环 GIF(完整 30s mp4 不再随 npm 包发布,见 <a href="https://github.com/SquabbyZ/peaks-loop/releases">GitHub Release</a> · 13MB · 480p)</sub>
+</p>
+
+<p align="center">
+  <img
+    src="./assets/readme/releases-banner.svg"
+    alt="peaks-loop 4.0.0 GA release banner — first stable cutover from 4.0.0-beta.36"
+    width="92%"
+  />
 </p>
 
 ---
@@ -90,6 +100,11 @@ npm i -g peaks-loop
 | 🔁 **跑过一次再来** | `/peaks-solo 按上次那样再跑一次` | 调出你已经沉淀好的战术,自动复跑 |
 | 🆕 **接手陌生仓库** | `/peaks-code 这是新仓库,先带我过一遍` | 摸清结构、识别风险点、给一个上手顺序 |
 | 🧠 **沉淀自己的打法** | `/peaks-solo 这套打法以后还会用,沉淀一下` | 变成你本地常驻的战术,下次说"跑那只"就行 |
+| 🧪 **开闸审计** | `/peaks-audit` | 6 维审计,RD/QA 前的强制入口 |
+| ✅ **4 维验收** | `/peaks-final-review` | 功能/问题/不引入新 bug/不破坏 |
+| 🔌 **IDE 适配** | `/peaks-ide` | hooks + statusline + handle |
+| ⏯ **从断点续跑** | `/peaks-resume` | 扫最深完成的门,AskUserQuestion |
+| 🔬 **切片拆解** | `/peaks-slice-decompose` | 多 pass + 跨 pass 边 + 仲裁 |
 
 每一条路,**一条斜杠命令**就能开跑。
 
@@ -98,7 +113,7 @@ npm i -g peaks-loop
 ## 为什么大家会选它
 
 - **自然语言即界面** —— 你不学 CLI、不背命令。**用一条斜杠命令(比如 `/peaks-code xxx`)** 显式触发到对应编排器,后面说什么都行。LLM 替你跟 peaks-loop 跑命令。
-- **门禁真挡事,不是装饰** —— 5,439 个测试用例、QA 闸口、review 验收默认全开。**审计不通过就停,QA 没过就停**。
+- **门禁真挡事,不是装饰** —— 219 个测试用例(4 packages 全绿)、QA 闸口、review 验收默认全开。**审计不通过就停,QA 没过就停**。
 - **跑过的事会变成本地战术(bee)** —— 沉淀下来的 loop engineering 落到你本地的 `~/.peaks/` 池子里,跑两次稳定就自动晋升;跑翻车的会让你重新定义。**下次说"跑那只"整套流程自动就位**,你那几只战术会跟着你的口味长。
 - **搭在你已经用的工具上** —— 不是新发明一个 AI CLI,而是架在 **Claude Code** 和 **Z Code** 之上。不抢你的 shell、不抢你的 prompt、不抢你的 IDE。其他工具适配中,欢迎共建。
 - **你拍板,它执行** —— 影响资产的决策都给你选;其余的它自己跑。**0 学习成本,1 分钟上手。**
@@ -123,10 +138,10 @@ npm i -g peaks-loop
 
 | | |
 | --- | --- |
-| **最新版本** | [`4.0.0-beta.7`](https://github.com/SquabbyZ/peaks-loop/releases) — 4.x 正式版筹备中 |
+| **最新版本** | [`4.0.1`](https://github.com/SquabbyZ/peaks-loop/releases) — 4.x 正式版筹备中 |
 | **覆盖域** | 代码(`peaks-code`) · 内容(`peaks-content`) · 项目健康(`peaks-doctor`) · 批量修 issue(`peaks-issue-fix-orchestrator`) · 自定义 SOP(`peaks-sop`) · 通用原语(`peaks-solo` 分诊 / `peaks-resume` 续 / `peaks-status` 看 / `peaks-test` 测) |
 | **沉淀池** | `~/.peaks/` 本地池 · 跑两次自动晋升成 bee · 跑翻车让你重定义 · bee 跟着你的口味长 |
-| **测试套件** | 5,439 passed · 19 skipped · 0 failed |
+| **测试套件** | 219 passed · 0 failed (4 packages: peaks-loop / peaks-loop-mut / peaks-loop-shared-channel / peaks-loop-shared) |
 | **适配 IDE** | ✅ Claude Code · ✅ Z Code · 🚧 Codex / Cursor / Trae / Tongyi Lingma / Hermes / OpenClaw / Qoder(适配中,欢迎共建) |
 | **依赖运行时** | Node ≥ 20 |
 | **License** | MIT |
@@ -202,12 +217,35 @@ peaks-loop 的两条工程脊柱直接来自这两个项目:
 <details>
 <summary><b>跟 3.x 比,4.x 有什么不同?</b></summary>
 
-**最大的不同:从"代码专用"扩成"多域编排系统"。** 4.x 不再只是写代码 —— 新增了 `peaks-content`(内容生产)、`peaks-doctor`(项目健康)、`peaks-issue-fix-orchestrator`(批量修 issue)、`peaks-sop`(自定义 SOP)四条域编排链,加上 `peaks-solo` 分诊员按你说话自动判断该走哪一域。再加 9 个 IDE 适配、结晶系统重命名、post-run crystallization 机制、5,439 tests 通过。完整变更 → [`CHANGELOG.md`](./CHANGELOG.md)。
+**最大的不同:从"代码专用"扩成"多域编排系统"。** 4.x 不再只是写代码 —— 新增了 `peaks-content`(内容生产)、`peaks-doctor`(项目健康)、`peaks-issue-fix-orchestrator`(批量修 issue)、`peaks-sop`(自定义 SOP)四条域编排链,加上 `peaks-solo` 分诊员按你说话自动判断该走哪一域。再加 9 个 IDE 适配、结晶系统重命名、post-run crystallization 机制。完整变更 → [`CHANGELOG.md`](./CHANGELOG.md)。
+
+### 4.0.0 GA 这一波实打实修了什么(2026-07-30)
+
+| Epic | 解决的事 | 怎么验 |
+| --- | --- | --- |
+| **测试体系从零重建** | 旧 559 文件单测卡 3 小时跑不完;现 219 cases 4 packages 全绿,`pnpm test:full` ~67s。删旧断言、写生产合约、4 维分拆(render/behavior/integration/a11y)。 | commit `f17aa377` → `1d6233bc` · `.peaks/memory/2026-07-30-test-rebuild-epic-sediment.md` |
+| **Karpathy 评估成本自审** | LLM 在 1-2 个 slice 后不再"今天差不多了明天继续"——`karpathy-reviewer` 报 `costRatio`,>10 时 `peaks job karpathy-cost-check` 自动降级 `block`→`warn`。24h-mode 仍是 override。 | `peaks job karpathy-cost-check --review-file <path>` · 21 cases 单测 |
+| **Compact 显性可见** | `peaks compact history` 给 LLM 看本次会话所有 compact 事件;`peaks statusline compact` 单行指示给 IDE 状态栏( `--` / `compact pending (0.85)` / `REDLINE 0.95` / `just compacted (0.92→?)`)。 | `auto-compact-orchestrator` append 到 `compact-history.jsonl` · 19 cases 单测 |
+| **子包独立单测 + `pnpm test:full` 覆盖全 workspace** | `peaks-loop-mut` / `peaks-loop-shared-channel` 各自 4 维单测;`peaks-loop-shared` 0 file (passWithNoTests);root 镜像冗余删除。 | commit `593ffcdf` → `08e92d8f` · `pnpm test:full` 一次跑完 4 packages |
 
 </details>
 
 ---
 
+## 全量 skill 索引
+
+13 个 user skill · 全部入口都在 `skills/<name>/SKILL.md`:
+
+`/peaks-code` · `/peaks-content` · `/peaks-doctor` · `/peaks-audit` · `/peaks-final-review` · `/peaks-ide` · `/peaks-issue-fix-orchestrator` · `/peaks-sop` · `/peaks-solo` · `/peaks-resume` · `/peaks-status` · `/peaks-test` · `/peaks-slice-decompose`
+
+---
+
+## Ship 摘要(4.x · 14 rid)
+
+`020b · 024 · 025 · 026 · 027 · 028 · 029 · 030 · 031 · 032 · 033 · 034 · GA(4.0.0) · retire-auto-compact-hook` — 涵盖 code-run、24h-mode、spillover、DAG fan-out、dashboard 聚合、CLI surface 收敛(73→9 byte-identical)等。详见 [`CHANGELOG.md`](./CHANGELOG.md)。
+
+---
+
 ## 链接
 
 - 全部技能清单 → [`skills/`](./skills/)
@@ -220,6 +258,37 @@ peaks-loop 的两条工程脊柱直接来自这两个项目:
 
 ---
 
+## 发布(Trusted Publishing · OIDC)
+
+本仓库发布链路**不**使用 npm token,改用 **Trusted Publishing + OIDC**:
+
+- 维护者**不需要**也不会持有 `NPM_TOKEN` —— `~/.npmrc` 已被清理,npmjs.com 已把 Publishing access 切到 disallow tokens。
+- 触发方式 1:`git tag vX.Y.Z && git push --tags`(走 `.github/workflows/publish.yml` 的 `push: tags: v*.*.*` 触发器)。
+- 触发方式 2:GitHub UI → Actions → publish → Run workflow(手动兜底,可用于 dry-run / 补发)。
+- 每次发布跑完整链路:`install → typecheck → build → vitest → changesets version → changesets publish`,全部通过才会真正落到 npm。
+- 维护者的本地动作只有两步:`pnpm changeset` 写变更说明 + 合并 PR(剩下的 CI 自动跑)。
+
+**npmjs 侧一次性配置**(本 slice 完成后由人工做一次):
+
+1. 登录 https://www.npmjs.com → Settings → Trusted Publishers → Add GitHub Action。
+2. Owner / Org:`SquabbyZ` · Repository:`peaks-loop` · Workflow filename:`publish.yml` · Environment name:留空。
+3. 保存。
+
+**撤销** = npmjs 端删 trusted publisher,**无需** rotate token。
+
+**常见故障**:
+
+| 现象 | 原因 | 修法 |
+|------|------|------|
+| publish 步骤报 `Cannot get JWT` | 缺 `id-token: write` | 检查 `.github/workflows/publish.yml#permissions` |
+| publish 步骤报 `ENEEDAUTH` 或 `404 from registry.npmjs.org` | npmjs 端没配 trusted publisher | 走上面的 3 步配置 |
+| `changeset version` 把 `package.json` 改了我没想要 | 漏掉了手动 version | 提交前先本地 `pnpm changeset version`,CI 端为 no-op |
+| tag 推了但 CI 没跑 | tag 格式不符 `v*.*.*` | 检查 `git tag` 输出 |
+
+详细 RD 文档见 [`docs/superpowers/slices/slice-s1-trusted-publish.md`](./docs/superpowers/slices/slice-s1-trusted-publish.md)。
+
+---
+
 <div align="center">
 
 MIT License · Made by [SquabbyZ](https://github.com/SquabbyZ) · 中文版 · [English version](./README-en.md)

package/agents/karpathy-reviewer.md

@@ -123,6 +123,23 @@ When violations exist, the envelope is:
 }
 ```
 
+When `evaluationCost` is reported, the envelope is:
+
+```json
+{
+  "passed": true,
+  "violations": [],
+  "gateAction": "pass",
+  "evaluationCost": {
+    "wallMs": 45230,
+    "subAgentsDispatched": 3,
+    "tokensEstimated": 18500,
+    "sliceCodeSize": 184
+  },
+  "costRatio": 245.81
+}
+```
+
 **Field semantics**:
 
 | Field | Type | Required | Meaning |
@@ -133,6 +150,12 @@ When violations exist, the envelope is:
 | `violations[].snippet` | string | yes | the offending text (≤ 200 chars); empty string if slice-level |
 | `violations[].hint` | string | yes | actionable suggestion (≤ 200 chars) — what should change |
 | `gateAction` | string | yes | `'pass'` if no violations; `'warn'` if any violation but recoverable; `'block'` if a HARD-blocker (see below) |
+| `evaluationCost` | object | optional | self-reported cost of running THIS reviewer; the field is added in slice 2026-07-30-karpathy-cost-self-review. Absent / older envelopes are accepted by `peaks job karpathy-cost-check` and treated as `costRatio = 0` (no auto-downgrade). |
+| `evaluationCost.wallMs` | number | required when `evaluationCost` is set | wall-clock milliseconds this reviewer spent; measured by the parent orchestrator from the dispatch envelope's `setAt` to the JSON parse timestamp |
+| `evaluationCost.subAgentsDispatched` | number | required when `evaluationCost` is set | how many sub-agents the reviewer fan-out emitted (the 3-way / 5-way fan-out count) |
+| `evaluationCost.tokensEstimated` | number | required when `evaluationCost` is set | rough token count for the reviewer's prompt + response (LLM-side estimate is fine; no need for exact billing) |
+| `evaluationCost.sliceCodeSize` | number | required when `evaluationCost` is set | the slice's diff `+`/`-` line count (from `git diff --stat`) |
+| `costRatio` | number | required when `evaluationCost` is set | `evaluationCost.wallMs / max(evaluationCost.sliceCodeSize, 1)`. Read by `peaks job karpathy-cost-check` to decide whether to auto-downgrade a `'block'` gateAction to `'warn'`. |
 
 **`gateAction` decision table**:
 
@@ -146,6 +169,16 @@ When violations exist, the envelope is:
 | The slice introduces secrets, executes arbitrary code, or modifies `~/.claude/settings.json` / `~/.claude/agents/` / `~/.claude/hooks/` | `'block'` |
 | 3+ violations across 3+ different `kind` values | `'block'` (the slice is structurally misaligned, not just imperfect) |
 
+**`costRatio` auto-downgrade** (slice 2026-07-30-karpathy-cost-self-review):
+
+The reviewer itself does NOT downgrade its own `gateAction`. The `costRatio` field is reported verbatim, and `peaks job karpathy-cost-check` (a separate orchestrator-side command) decides whether to flip a `'block'` to `'warn'` based on:
+
+- `costRatio > 10`: `'block'` is downgraded to `'warn'` (the evaluation took 10x longer than the slice's code change; the LLM is being blocked by the gate at a cost the slice did not justify)
+- `costRatio > 50`: a sediment is appended to `.peaks/memory/2026-07-30-karpathy-cost-self-review-archive.md` so the human can review the recurring pattern; `gateAction` stays at `'warn'`
+- 24h-mode is the override: when `peaks session 24h-mode state` reports `24H_ACTIVE`, `peaks job karpathy-cost-check` is ENTIRELY SKIPPED — the reviewer is the trusted arbiter. This applies regardless of `costRatio`. See `.peaks/memory/2026-07-30-karpathy-evaluation-cost-self-review-design.md` for the design rationale.
+
+If the `evaluationCost` field is absent (older reviewer, or the orchestrator did not measure), the cost-check command treats `costRatio = 0` and the hard gate stays in effect. This is by design: missing cost data must not silently downgrade a `'block'`.
+
 ## 5. File write contract
 
 You MUST also write `rd/karpathy-review.md` (relative to the slice's project root). The file must contain EXACTLY these section headers, in this order, with title-case capitalization (the existing `KARPATHY_REVIEW` prereq in `src/services/artifacts/artifact-prerequisites.ts` enforces this). The 5 literal lines below are indented by 4 spaces to keep them out of the sibling-reference heading inventory; copy them verbatim into the file you write.

package/dist/cli/cli-helpers.d.ts

@@ -1,15 +1,14 @@
 import { Command } from 'commander';
-import { getErrorMessage, ok, redactSensitiveErrorMessage, type ResultEnvelope } from '../shared/result.js';
+import { getErrorMessage, ok, redactSensitiveErrorMessage, type ResultEnvelope } from 'peaks-loop-shared/result';
 import type { ArtifactProvider, GuidedArtifactSetup } from '../services/artifacts/artifact-service.js';
 import type { ConfigLayer } from '../services/config/config-service.js';
-import type { MiniMaxProviderSmokeResult } from '../services/providers/minimax-provider-service.js';
-import type { MiniMaxWorkerResult } from '../services/providers/minimax-worker-service.js';
 import type { RecommendationWorkflow } from '../services/recommendations/recommendation-service.js';
 export type ProgramIO = {
     stdout: (text: string) => void;
     stderr: (text: string) => void;
 };
 export declare function printResult<T>(io: ProgramIO, result: ResultEnvelope<T>, asJson?: boolean): void;
+export declare function printSuperCommandCatalog(io: ProgramIO): void;
 export declare function addJsonOption(command: Command): Command;
 export declare function failUnsupportedNonDryRun(io: ProgramIO, command: string, asJson?: boolean): void;
 /** CLI shim helper: render a `{ ok: boolean, error?, data? }` envelope
@@ -30,14 +29,40 @@ export interface CliEnvelope {
     data?: unknown;
 }
 export declare function printCliEnvelope(io: ProgramIO, r: CliEnvelope): void;
+/**
+ * Slice rid-001 (P0-1 envelope closure) — canonical envelope shim
+ * for `src/cli/index.ts`'s 3 raw `console.error(JSON.stringify(...))`
+ * sites, plus `src/cli/program.ts:162`'s default `ProgramIO.stderr`
+ * fallback.
+ *
+ * Replaces the hand-rolled JSON literal with a real `fail()` envelope
+ * from `peaks-loop-shared/result`. The helper:
+ *  - mints a fresh `errorId` per call (correlation handle for
+ *    downstream logs / LLM-side consumers);
+ *  - runs `message` through `redactSensitiveErrorMessage` BEFORE
+ *    serializing, so Bearer tokens, API keys, PAT strings, etc. never
+ *    reach the terminal;
+ *  - writes pretty JSON to stderr (single line is fine for `JSON.stringify`
+ *    without `null, 2`, but pretty is friendlier for human readers and
+ *    match the shape `peaks <cmd> --json` already produces);
+ *  - sets `process.exitCode = 1` so callers that throw through
+ *    Commander's exit-override still observe the correct exit code.
+ *
+ * Human-NL-Choice-Only compliance: the helper does NOT print any
+ * "Run peaks <command>" hints. `nextActions` is rendered verbatim
+ * (e.g. "Run `peaks --help` to list available commands") — those
+ * are LLMs-coordinated actions, never user-typed CLI verbs.
+ *
+ * The original `// TODO(g2): legacy console.error without envelope`
+ * grace comment carried in `src/cli/index.ts` (lines 35/73/87) and
+ * `src/cli/program.ts:162` is hereby resolved by this helper.
+ */
+export declare function printErrorEnvelope(io: ProgramIO, command: string, code: string, message: string, data: Record<string, unknown>, nextActions: string[]): void;
 export declare function isRecommendationWorkflow(value: string): value is RecommendationWorkflow;
 export declare function isArtifactProvider(value: string): value is ArtifactProvider;
 export declare function isArtifactSetupStep(value: string): value is GuidedArtifactSetup['step'];
 export declare function isArtifactRepoSegment(value: string): boolean;
-export declare function isMiniMaxHttpsUrl(value: string): boolean;
 export declare function parseConfigLayer(value: string | undefined): ConfigLayer | undefined | null;
 export declare function printInvalidConfigLayer(io: ProgramIO, command: string, asJson?: boolean): void;
 export declare function multipleOption(value: string, previous: string[]): string[];
-export declare function summarizeMiniMaxSmokeResult(result: MiniMaxProviderSmokeResult): MiniMaxProviderSmokeResult;
-export declare function summarizeMiniMaxWorkerResult(result: MiniMaxWorkerResult): MiniMaxWorkerResult;
 export { getErrorMessage, ok, redactSensitiveErrorMessage };

package/dist/cli/cli-helpers.js

@@ -1,5 +1,4 @@
-import { fail, getErrorMessage, ok, redactSensitiveErrorMessage } from '../shared/result.js';
-const MINIMAX_API_HOST = 'api.minimaxi.com';
+import { fail, getErrorMessage, ok, redactSensitiveErrorMessage } from 'peaks-loop-shared/result';
 export function printResult(io, result, asJson = false) {
     if (asJson) {
         io.stdout(JSON.stringify(result, null, 2));
@@ -20,6 +19,20 @@ export function printResult(io, result, asJson = false) {
         io.stdout(`next: ${action}`);
     }
 }
+export function printSuperCommandCatalog(io) {
+    io.stdout([
+        'Peaks super-command catalog',
+        'make — describe what to build or change',
+        'learn — describe a procedure, lesson, or memory to capture',
+        'check — describe a project, health, audit, or security target',
+        'run — describe a workflow, job, slice, or dispatch',
+        'share — hand off a sub-agent sharing operation',
+        'version — show the current Peaks version',
+        'ask — describe any natural-language question',
+        'status — show current workflow status',
+        'Choose a surface or describe your goal; the LLM coordinates the underlying operation.'
+    ].join('\n'));
+}
 export function addJsonOption(command) {
     return command.option('--json', 'print machine-readable JSON envelope');
 }
@@ -35,6 +48,39 @@ export function printCliEnvelope(io, r) {
     io.stdout(JSON.stringify({ ok: false, error: r.error }));
     process.exitCode = 1;
 }
+/**
+ * Slice rid-001 (P0-1 envelope closure) — canonical envelope shim
+ * for `src/cli/index.ts`'s 3 raw `console.error(JSON.stringify(...))`
+ * sites, plus `src/cli/program.ts:162`'s default `ProgramIO.stderr`
+ * fallback.
+ *
+ * Replaces the hand-rolled JSON literal with a real `fail()` envelope
+ * from `peaks-loop-shared/result`. The helper:
+ *  - mints a fresh `errorId` per call (correlation handle for
+ *    downstream logs / LLM-side consumers);
+ *  - runs `message` through `redactSensitiveErrorMessage` BEFORE
+ *    serializing, so Bearer tokens, API keys, PAT strings, etc. never
+ *    reach the terminal;
+ *  - writes pretty JSON to stderr (single line is fine for `JSON.stringify`
+ *    without `null, 2`, but pretty is friendlier for human readers and
+ *    match the shape `peaks <cmd> --json` already produces);
+ *  - sets `process.exitCode = 1` so callers that throw through
+ *    Commander's exit-override still observe the correct exit code.
+ *
+ * Human-NL-Choice-Only compliance: the helper does NOT print any
+ * "Run peaks <command>" hints. `nextActions` is rendered verbatim
+ * (e.g. "Run `peaks --help` to list available commands") — those
+ * are LLMs-coordinated actions, never user-typed CLI verbs.
+ *
+ * The original `// TODO(g2): legacy console.error without envelope`
+ * grace comment carried in `src/cli/index.ts` (lines 35/73/87) and
+ * `src/cli/program.ts:162` is hereby resolved by this helper.
+ */
+export function printErrorEnvelope(io, command, code, message, data, nextActions) {
+    const envelope = fail(command, code, message, data, nextActions);
+    io.stderr(JSON.stringify(envelope, null, 2));
+    process.exitCode = 1;
+}
 export function isRecommendationWorkflow(value) {
     return value === 'code-refactor' || value === 'product-refactor' || value === 'frontend-design';
 }
@@ -47,15 +93,6 @@ export function isArtifactSetupStep(value) {
 export function isArtifactRepoSegment(value) {
     return /^[A-Za-z0-9][A-Za-z0-9._-]*$/.test(value) && !value.includes('..') && !value.endsWith('.');
 }
-export function isMiniMaxHttpsUrl(value) {
-    try {
-        const url = new URL(value);
-        return url.protocol === 'https:' && url.hostname === MINIMAX_API_HOST && url.username.length === 0 && url.password.length === 0 && url.search.length === 0 && url.hash.length === 0;
-    }
-    catch {
-        return false;
-    }
-}
 export function parseConfigLayer(value) {
     if (value === undefined) {
         return undefined;
@@ -69,18 +106,4 @@ export function printInvalidConfigLayer(io, command, asJson) {
 export function multipleOption(value, previous) {
     return [...(previous || []), value];
 }
-export function summarizeMiniMaxSmokeResult(result) {
-    return { ...result, responseText: null, summary: null };
-}
-export function summarizeMiniMaxWorkerResult(result) {
-    const provider = summarizeMiniMaxSmokeResult(result.provider);
-    return {
-        ...result,
-        provider,
-        reviewHandoff: {
-            model: result.reviewHandoff.model,
-            prompt: '[redacted]'
-        }
-    };
-}
 export { getErrorMessage, ok, redactSensitiveErrorMessage };

package/dist/cli/commands/_register.d.ts

@@ -0,0 +1,3 @@
+import type { Command } from 'commander';
+import type { ProgramIO } from '../cli-helpers.js';
+export declare function autoRegisterAllCommands(program: Command, io: ProgramIO): void;

package/dist/cli/commands/_register.js

@@ -0,0 +1,139 @@
+import { registerAdapterCommands } from './adapter-commands.js';
+import { registerAdapterS2ACommands } from './adapter-commands-s2a.js';
+import { registerAssetCommands } from './asset-commands.js';
+import { registerAuditCommands } from './audit-commands.js';
+import { registerBeeCommands } from './bee-commands.js';
+import { registerCapabilityWorkerConfigAndSCCommands } from './capability-worker-config-sc-commands.js';
+import { registerCodeCommands } from './code-commands.js';
+import { registerDashboardCommands } from './dashboard-commands.js';
+import { registerCodeReviewCommands } from './code-review-commands.js';
+import { registerCodegraphCommands } from './codegraph-commands.js';
+import { registerCompactCommands } from './compact-command.js';
+import { registerComplexityCommands } from './complexity-commands.js';
+import { registerContextCommands } from './context-commands.js';
+import { registerCoreAndArtifactCommands } from './core-artifact-commands.js';
+import { registerDocCommands } from './doc-commands.js';
+import { registerEccCommands } from './ecc-commands.js';
+import { registerEvolutionCommands } from './evolution-commands.js';
+import { registerFeedbackCommands } from './feedback-commands.js';
+import { registerFinalReviewCommands } from './final-review-commands.js';
+import { registerFixtureCommands } from './fixture-commands.js';
+import { registerForkCommands } from './fork-commands.js';
+import { registerGateCommands } from './gate-commands.js';
+import { registerClassifyCommands, registerContractCommands } from './governance-classify-contract-commands.js';
+import { registerHookHandleCommand } from './hook-handle.js';
+import { registerHeartbeatCommand as registerHeartbeatCommands } from './heartbeat-commands.js';
+import { registerHooksCommands } from './hooks-commands.js';
+import { registerIdeCommands } from './ide-commands.js';
+import { registerImpactCommands } from './impact-commands.js';
+import { registerJobCommands } from './job-commands.js';
+import { registerLegacyCommands } from './legacy-commands.js';
+import { registerLogCommands } from './log-commands.js';
+import { registerLoopCommands } from './loop-commands.js';
+import { registerWorkflowEvalCommands } from './loop-eval-commands.js';
+import { registerMutCommands } from './mut-commands.js';
+import { registerObservabilityCommands } from './observability-commands.js';
+import { registerOpenSpecCommands } from './openspec-commands.js';
+import { registerPerfAuditCommands } from './perf-audit-commands.js';
+import { registerPerfCommands } from './perf-commands.js';
+import { registerPlaywrightCommands } from './playwright-commands.js';
+import { registerPolyrepoCommands } from './polyrepo-commands.js';
+import { registerPrdBlocksCommands } from './prd-blocks-commands.js';
+import { registerPrdCommands } from './prd-commands.js';
+import { registerPreferencesCommands } from './preferences-commands.js';
+import { registerProjectCommands } from './project-commands.js';
+import { registerChangesetCommands } from './changeset-commands.js';
+import { registerQaBusinessReviewCommands } from './qa-business-review-commands.js';
+import { registerQaCommands } from './qa-commands.js';
+import { registerReleaseCommands } from './release-commands.js';
+import { registerRequestCommands } from './request-commands.js';
+import { registerRetrospectiveCommands } from './retrospective-commands.js';
+import { registerReviewerCommands } from './reviewer-commands.js';
+import { registerRoleCommands } from './role-commands.js';
+import { registerRuntimeCommands } from './runtime-commands.js';
+import { registerScanCommands } from './scan-commands.js';
+import { registerSecurityAuditCommands } from './security-audit-commands.js';
+import { registerSedimentCommands } from './sediment-commands.js';
+import { registerSkillConformanceCommands } from './skill-conformance-commands.js';
+import { registerSkillLoopEngineeringReadinessCommands } from './skill-loop-engineering-readiness-commands.js';
+import { registerSliceCommands } from './slice-commands.js';
+import { registerSliceIntegrateCommands } from './slice-integrate-commands.js';
+import { registerSliceReviewCommands } from './slice-review-commands.js';
+import { registerSmokeCommands } from './smoke-commands.js';
+import { registerSopCommands } from './sop-commands.js';
+import { registerStatusLineCommands } from './statusline-commands.js';
+import { registerSpillDemoCommand } from './spill-demo-command.js';
+import { registerSubAgentCommands } from './sub-agent-commands.js';
+import { registerSubAgentDispatchGuard } from './sub-agent-dispatch-guard.js';
+import { registerTestCommands } from './test-commands.js';
+import { registerUnderstandCommands } from './understand-commands.js';
+import { registerUpgradeCommands } from './upgrade-commands.js';
+import { registerUserTouchpointCommands } from './user-touchpoint-commands.js';
+import { registerVerdictAggregateCommands } from './verdict-aggregate-command.js';
+import { registerWorkflowCommands } from './workflow-commands.js';
+import { registerWorkflowPlanCommands } from './workflow-plan-commands.js';
+import { registerWorktreeAuthCommand } from './worktree-auth-commands.js';
+import { registerWorkspaceCommands } from './workspace-commands.js';
+const NON_AUTO = new Set([
+    'core-artifact-commands', 'capability-worker-config-sc-commands',
+    'sub-agent-commands', 'workspace-commands', 'workflow-commands',
+    'sop-commands', 'skill-visibility',
+]);
+const REGISTRATIONS = [
+    ['core-artifact-commands', registerCoreAndArtifactCommands],
+    ['workflow-commands', registerWorkflowCommands],
+    ['capability-worker-config-sc-commands', registerCapabilityWorkerConfigAndSCCommands],
+    ['codegraph-commands', registerCodegraphCommands], ['openspec-commands', registerOpenSpecCommands],
+    ['perf-commands', registerPerfCommands], ['preferences-commands', registerPreferencesCommands],
+    ['project-commands', registerProjectCommands], ['prd-commands', registerPrdCommands],
+    ['request-commands', registerRequestCommands], ['retrospective-commands', registerRetrospectiveCommands],
+    ['scan-commands', registerScanCommands], ['slice-commands', registerSliceCommands],
+    ['sop-commands', registerSopCommands], ['feedback-commands', registerFeedbackCommands],
+    ['fork-commands', registerForkCommands], ['impact-commands', registerImpactCommands],
+    ['smoke-commands', registerSmokeCommands], ['release-commands', registerReleaseCommands],
+    ['changeset-commands', registerChangesetCommands],
+    ['prd-blocks-commands', registerPrdBlocksCommands], ['user-touchpoint-commands', registerUserTouchpointCommands],
+    ['slice-review-commands', registerSliceReviewCommands], ['qa-business-review-commands', registerQaBusinessReviewCommands],
+    ['slice-integrate-commands', registerSliceIntegrateCommands], ['doc-commands', registerDocCommands],
+    ['legacy-commands', registerLegacyCommands], ['role-commands', registerRoleCommands],
+    ['complexity-commands', registerComplexityCommands], ['sub-agent-commands', registerSubAgentCommands],
+    ['governance-classify-contract-commands', registerContractCommands],
+    ['sub-agent-dispatch-guard', registerSubAgentDispatchGuard], ['gate-commands', registerGateCommands],
+    ['hook-handle', registerHookHandleCommand], ['hooks-commands', registerHooksCommands],
+    ['heartbeat-commands', registerHeartbeatCommands], ['statusline-commands', registerStatusLineCommands], ['understand-commands', registerUnderstandCommands],
+    ['workspace-commands', registerWorkspaceCommands], ['workflow-plan-commands', registerWorkflowPlanCommands],
+    ['audit-commands', registerAuditCommands], ['final-review-commands', registerFinalReviewCommands],
+    ['governance-classify-contract-commands', registerClassifyCommands], ['context-commands', registerContextCommands],
+    ['skill-conformance-commands', registerSkillConformanceCommands],
+    ['skill-loop-engineering-readiness-commands', registerSkillLoopEngineeringReadinessCommands],
+    ['loop-commands', registerLoopCommands], ['loop-eval-commands', registerWorkflowEvalCommands],
+    ['evolution-commands', registerEvolutionCommands], ['asset-commands', registerAssetCommands],
+    ['bee-commands', registerBeeCommands], ['ecc-commands', registerEccCommands],
+    ['upgrade-commands', registerUpgradeCommands], ['code-review-commands', registerCodeReviewCommands],
+    ['security-audit-commands', registerSecurityAuditCommands], ['perf-audit-commands', registerPerfAuditCommands],
+    ['verdict-aggregate-command', registerVerdictAggregateCommands], ['log-commands', registerLogCommands],
+    ['qa-commands', registerQaCommands], ['test-commands', registerTestCommands],
+    ['playwright-commands', registerPlaywrightCommands], ['code-commands', registerCodeCommands], ['dashboard-commands', registerDashboardCommands],
+    ['mut-commands', registerMutCommands], ['fixture-commands', registerFixtureCommands],
+    ['reviewer-commands', registerReviewerCommands], ['ide-commands', registerIdeCommands],
+    ['observability-commands', registerObservabilityCommands], ['compact-command', registerCompactCommands],
+    ['job-commands', registerJobCommands], ['sediment-commands', registerSedimentCommands],
+    ['adapter-commands', registerAdapterCommands], ['runtime-commands', registerRuntimeCommands],
+    ['adapter-commands-s2a', registerAdapterS2ACommands], ['polyrepo-commands', registerPolyrepoCommands],
+    ['worktree-auth-commands', registerWorktreeAuthCommand],
+    ['session-spill-demo', registerSpillDemoCommand],
+];
+function dispatchRegister(register, program, io) {
+    if (register.length <= 1) {
+        register(program);
+    }
+    else {
+        register(program, io);
+    }
+}
+export function autoRegisterAllCommands(program, io) {
+    for (const [moduleName, register] of REGISTRATIONS) {
+        if (!NON_AUTO.has(moduleName))
+            dispatchRegister(register, program, io);
+    }
+}

package/dist/cli/commands/_super.d.ts

@@ -0,0 +1,10 @@
+import type { Command } from 'commander';
+import type { ProgramIO } from '../cli-helpers.js';
+export interface SuperRouteData {
+    routedSkill: string;
+    confidence: number;
+    alternatives: string[];
+    rationale: string;
+    nextActions: string[];
+}
+export declare function registerSuperCommands(program: Command, io: ProgramIO): void;