peaks-loop 4.0.0-beta.9 → 4.0.3

package/README-en.md

@@ -5,31 +5,26 @@
 ### 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)
-[![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)
+[![tests](https://img.shields.io/badge/tests-285%2B%20cases%20%C3%97%204%20pkgs-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&github=github&logoColor=white)](https://github.com/SquabbyZ/peaks-loop/stargazers)
 
 **English** · [简体中文](./README.md)
 
 </div>
 
 <p align="center">
-  <img
-    src="https://raw.githubusercontent.com/SquabbyZ/peaks-loop/main/examples/video-demo/preview/peaks-loop-demo-en.gif"
-    alt="peaks-loop 30-second demo (first 18s · install + slash command + 5 domains + sediment into bee)"
-    width="92%"
-    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>
+  <img src="./assets/readme/hero.svg" alt="peaks-loop 4.0.3 — Loop Engineering, Engineered" width="92%"/>
 </p>
 
 ---
 
 ## What it is
 
-peaks-loop is a **Loop Engineering crystallization system**, not a workflow tool — what sediments from the runs you do is **not** a procedure, it's a set of **Loop Engineering** method assets that are karpathy-engineered at the rule level and darwin-verified at the change level. The **Loop engineering, engineered** crystallization design lives at [`docs/superpowers/specs/2026-07-07-peaks-loop-loop-engineering-crystallization-design.md`](./docs/superpowers/specs/2026-07-07-peaks-loop-loop-engineering-crystallization-design.md).
+peaks-loop is a **Loop Engineering crystallization system**, not a workflow tool — what sediments from the runs you do is **not** a procedure, it's a set of **Loop Engineering** method assets that are karpathy-engineered at the rule level and darwin-verified at the change level.
 
 | Asset layer | Role | One-liner |
 | --- | --- | --- |
@@ -42,6 +37,10 @@ peaks-loop is a **Loop Engineering crystallization system**, not a workflow tool
 - `/peaks-code` is the **code-domain** long-task Loop Engineering orchestrator, not a general orchestrator; non-code lanes (`peaks-content` / `peaks-doctor` / `peaks-issue-fix-orchestrator` / `peaks-sop`) ship as independent `peaks-*` bees, **not** as subclasses of `peaks-code`.
 - Twice-clean runs sediment into your local tactic pool (bee); broken runs come back for you to redefine. Your few bees grow with your taste.
 
+<p align="center">
+  <img src="./assets/readme/architecture.svg" alt="peaks-loop four asset layers, seven gates, one engineering spine" width="92%"/>
+</p>
+
 ---
 
 ## Up and running in 30 seconds
@@ -79,6 +78,10 @@ No CLI to memorize. No manifest to hand-author. No second terminal to open. **Se
 
 Code, content, project health, issue sweeps, custom workflows — **4.x ships five first-class domains**, each with its own orchestrator. Same discipline on every lane: "gate fails = stop, run the next gate".
 
+<p align="center">
+  <img src="./assets/readme/command-palette.svg" alt="peaks-loop 13 slash commands — command palette" width="92%"/>
+</p>
+
 | Domain | Send this slash command | It will… |
 | --- | --- | --- |
 | 💻 **Code (code-domain) only** | `/peaks-code build this feature` | PRD → RD → code → QA → UI → slice, ready for your sign-off |
@@ -90,6 +93,11 @@ Code, content, project health, issue sweeps, custom workflows — **4.x ships fi
 | 🔁 **Replay** | `/peaks-solo run it like last time` | pull up your sedimented tactic, replay it |
 | 🆕 **Onboard** | `/peaks-code this is a new repo, walk me through it` | map structure, flag risks, hand you a learning order |
 | 🧠 **Sediment** | `/peaks-solo I'll do this again — save it` | ground it locally as a reusable tactic |
+| 🧪 **Open the audit gate** | `/peaks-audit` | 6-dim audit, mandatory entry before RD / QA |
+| ✅ **4-dim sign-off** | `/peaks-final-review` | functional / problem / no-new-bugs / no-regression |
+| 🔌 **IDE adapter** | `/peaks-ide` | hooks + statusline + handle |
+| ⏯ **Resume from a checkpoint** | `/peaks-resume` | scan the deepest finished gate, AskUserQuestion |
+| 🔬 **Slice decomposition** | `/peaks-slice-decompose` | multi-pass + cross-pass edges + arbitration |
 
 Every lane opens with **one slash command**.
 
@@ -98,7 +106,7 @@ 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.** 285+ test cases across 4 packages, all green by default; QA gate, review sign-off — all on. **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.**
@@ -114,23 +122,42 @@ Every lane opens with **one slash command**.
 | Security scan | ✅ on | secrets, SSRF, injection, dangerous IO |
 | QA review | ✅ on | task-level gate — fails loud, stops clean |
 | Review sign-off | ✅ on | nothing ships without eyes on it |
+| Anti-drift evaluation (Evolution Evaluation) | ✅ on | every improvement needs an independent scorer + a regression skeptic, otherwise revert |
 
 **All gates on by default. You only speak to turn one off.**
 
 ---
 
-## Status · shipping 4.x
+## Status · shipping 4.0.3 GA
+
+<p align="center">
+  <img src="./assets/readme/pulse.svg" alt="peaks-loop live metrics — 4 tiles + sparkline + pipeline progress" width="92%"/>
+</p>
+
+<p align="center">
+  <img src="./assets/readme/trace-stream.svg" alt="peaks-loop live diff & log stream — code diff + scrolling log + 7-gate chain" width="92%"/>
+</p>
 
 | | |
 | --- | --- |
-| **Latest** | [`4.0.0-beta.7`](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`) |
+| **Latest** | [![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) — GA (2026-07-30) |
+| **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` · `peaks-slice-decompose`) |
 | **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** | 285+ cases · 4 packages (peaks-loop / peaks-loop-mut / peaks-loop-shared-channel / peaks-loop-shared) · ~80s full run |
 | **IDE adapters** | ✅ Claude Code · ✅ Z Code · 🚧 Codex / Cursor / Trae / Tongyi Lingma / Hermes / OpenClaw / Qoder (adapters in progress — contributions welcome) |
 | **Runtime** | Node ≥ 20 |
 | **License** | MIT |
 
+### What 4.0.3 GA actually shipped (2026-07-30)
+
+| Epic | Solved | Verified by |
+| --- | --- | --- |
+| **Test suite rebuilt from scratch** | Old 559-file unit suite took 3+ hours; the 11-file / 161-case rebuild runs in ~80s, and combined with sub-package tests and later slices the workspace-wide total is 285+ cases across 4 packages. 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 |
+| **CLI surface collapsed (73 → 5 super-commands)** | Five super-commands (`peaks code / audit / doctor / openspec / release / release-pack`) replace 73 leaf commands, byte-identical contract preserved, opaque to downstream callers. | rid-009 · 26 routing tests |
+
 ---
 
 ## Strongly recommended · compose these four
@@ -138,17 +165,7 @@ Every lane opens with **one slash command**.
 > **Zero learning cost.** That's the biggest reason to use them together — not just that the effect is excellent, but that **all four projects speak the same interface: natural language + a choice.** You say one sentence; the LLM runs the commands, applies the gates, and follows the playbook.
 
 <p align="center">
-  <a href="https://github.com/affaan-m/ECC">
-    <img src="https://img.shields.io/badge/ECC-affaan--m-6366f1?style=for-the-badge&logo=github&logoColor=white" alt="affaan-m/ECC" />
-  </a>
-  &nbsp;
-  <a href="https://github.com/Egonex-AI/Understand-Anything">
-    <img src="https://img.shields.io/badge/Understand--Anything-Egonex--AI-22c55e?style=for-the-badge&logo=github&logoColor=white" alt="Egonex-AI/Understand-Anything" />
-  </a>
-  &nbsp;
-  <a href="https://github.com/obra/superpowers">
-    <img src="https://img.shields.io/badge/superpowers-obra-f59e0b?style=for-the-badge&logo=github&logoColor=white" alt="obra/superpowers" />
-  </a>
+  <img src="./assets/readme/footer.svg" alt="peaks-loop recommended stack" width="92%"/>
 </p>
 
 | Role | Project | One-liner |
@@ -202,12 +219,32 @@ 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).
 
 </details>
 
 ---
 
+## Full skill index
+
+13 user skills · every entry point lives in `skills/<name>/SKILL.md`:
+
+<p align="center">
+  <img src="./assets/readme/skill-index.svg" alt="peaks-loop 13 user skills — full index with category badges" width="92%"/>
+</p>
+
+---
+
+## Ship summary (4.x · 19 rids)
+
+`009 · 010 · 011 · 014 · 015 · 016 · 017 · 020b · 024 · 025 · 026 · 027 · 028 · 029 · 030 · 031 · 032 · 033 · 034` — CLI surface collapse (73 → 5 byte-identical), Trusted Publishing + OIDC, 24h-mode, context spillover, DAG wave + barrier, dashboard aggregation, test-rebuild epic, karpathy-cost self-review, compact visibility, retire-auto-compact-hook, and more.
+
+<p align="center">
+  <img src="./assets/readme/ship-summary.svg" alt="peaks-loop 4.x 19-rid ship timeline with category chips" width="92%"/>
+</p>
+
+---
+
 ## Links
 
 - All skills → [`skills/`](./skills/)
@@ -215,8 +252,8 @@ It changes, but **the gates hold**. Audit fails = nothing ships. QA fails = noth
 - Questions → [GitHub Issues](https://github.com/SquabbyZ/peaks-loop/issues)
 - Tribute: [multica-ai/andrej-karpathy-skills](https://github.com/multica-ai/andrej-karpathy-skills) · [alchaincyf/darwin-skill](https://github.com/alchaincyf/darwin-skill)
 - Recommended combo: [affaan-m/ECC](https://github.com/affaan-m/ECC) · [Egonex-AI/Understand-Anything](https://github.com/Egonex-AI/Understand-Anything) · [obra/superpowers](https://github.com/obra/superpowers)
-- Sediment design → [`docs/superpowers/specs/2026-07-04-peaks-maker-dynamic-skill-sediment-design.md`](./docs/superpowers/specs/2026-07-04-peaks-maker-dynamic-skill-sediment-design.md)
-- Loop Engineering crystallization design → [`docs/superpowers/specs/2026-07-07-peaks-loop-loop-engineering-crystallization-design.md`](./docs/superpowers/specs/2026-07-07-peaks-loop-loop-engineering-crystallization-design.md)
+
+---
 
 ---
 

package/README.md

@@ -5,31 +5,26 @@
 ### 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)
+[![tests](https://img.shields.io/badge/tests-285%2B%20cases%20%C3%97%204%20pkgs-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&github=github&logoColor=white)](https://github.com/SquabbyZ/peaks-loop/stargazers)
 
 [English](./README-en.md) · **简体中文**
 
 </div>
 
 <p align="center">
-  <img
-    src="https://raw.githubusercontent.com/SquabbyZ/peaks-loop/main/examples/video-demo/preview/peaks-loop-demo.gif"
-    alt="peaks-loop 30 秒演示(前 18 秒 · install + 斜杠命令 + 5 域 + 沉淀成 bee)"
-    width="92%"
-    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>
+  <img src="./assets/readme/hero.svg" alt="peaks-loop 4.0.3 — Loop Engineering, Engineered" width="92%"/>
 </p>
 
 ---
 
 ## 它是什么
 
-peaks-loop 是一个 **Loop Engineering 结晶系统**,不是工作流工具 —— 你跑过的工作里,沉淀下来的不是「流程」,是一套**可被 karpathy 风格工程化、又被 darwin 风格独立验证**的 Loop Engineering 方法资产。**Loop engineering 结晶系统** 的工程实现见 [`docs/superpowers/specs/2026-07-07-peaks-loop-loop-engineering-crystallization-design.md`](./docs/superpowers/specs/2026-07-07-peaks-loop-loop-engineering-crystallization-design.md)。
+peaks-loop 是一个 **Loop Engineering 结晶系统**,不是工作流工具 —— 你跑过的工作里,沉淀下来的不是「流程」,是一套**可被 karpathy 风格工程化、又被 darwin 风格独立验证**的 Loop Engineering 方法资产。
 
 | 资产层 | 角色 | 一句话 |
 | --- | --- | --- |
@@ -42,6 +37,10 @@ peaks-loop 是一个 **Loop Engineering 结晶系统**,不是工作流工具 —
 - `/peaks-code` 是 **code-domain** 长任务 Loop Engineering 编排器,不是通用编排器;非代码域(`peaks-content` / `peaks-doctor` / `peaks-issue-fix-orchestrator` / `peaks-sop`)都是独立的 `peaks-*` 蜂,不是 `peaks-code` 的子类。
 - 跑两次稳定就沉淀成本地战术(bee);跑翻车的会让你重定义。bee 跟着你的口味长。
 
+<p align="center">
+  <img src="./assets/readme/architecture.svg" alt="peaks-loop 四层资产 / 七道闸门 / 一条工程脊柱" width="92%"/>
+</p>
+
 ---
 
 ## 30 秒上手
@@ -79,6 +78,10 @@ npm i -g peaks-loop
 
 代码、内容、项目健康、issue 修复、自定义工作流 —— **4.x 已经覆盖五条域**,每条域都有专门编排器,按"门禁不通过就停"的纪律一条一条跑。
 
+<p align="center">
+  <img src="./assets/readme/command-palette.svg" alt="peaks-loop 13 slash commands — command palette" width="92%"/>
+</p>
+
 | 域 | 你发这条命令 | 它会做什么 |
 | --- | --- | --- |
 | 💻 **代码域 (code-domain) only** | `/peaks-code 帮我实现这个功能` | PRD → RD → 实现 → QA → UI → 切片,跑完交你拍板 |
@@ -90,6 +93,11 @@ 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 +106,7 @@ 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** —— 285+ 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。**
@@ -114,23 +122,42 @@ npm i -g peaks-loop
 | 安全扫描 | ✅ 开 | 凭据、SSRF、注入、危险 IO |
 | QA 复核 | ✅ 开 | 任务级闸门,坏在哪道停在哪道 |
 | review 验收 | ✅ 开 | 改完不立刻出门,review 通过才出门 |
+| 反漂移评估 (Evolution Evaluation) | ✅ 开 | 改进必须过独立评估者 + 反方怀疑者,过不了就回滚 |
 
 **所有闸门默认开,你想关哪一道才需要单独说。**
 
 ---
 
-## 当前状态 · 4.x 正式版
+## 当前状态 · 4.0.3 GA
+
+<p align="center">
+  <img src="./assets/readme/pulse.svg" alt="peaks-loop live metrics — 4 tiles + sparkline + pipeline progress" width="92%"/>
+</p>
+
+<p align="center">
+  <img src="./assets/readme/trace-stream.svg" alt="peaks-loop 实时 diff & log stream — code diff + 滚动日志 + 7-gate 链路" width="92%"/>
+</p>
 
 | | |
 | --- | --- |
-| **最新版本** | [`4.0.0-beta.7`](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) |
+| **最新版本** | [![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) — GA(2026-07-30) |
+| **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 / `peaks-slice-decompose` 切片) |
 | **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** | 285+ cases · 4 packages (peaks-loop / peaks-loop-mut / peaks-loop-shared-channel / peaks-loop-shared) · 80s 全量 |
 | **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 |
 
+### 4.0.3 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 11 test files / 161 cases 单测已上线,加上子包测试与新增切片,全量 4 packages 285+ cases 全绿,`pnpm test:full` ~80s。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 |
+| **CLI surface 收敛(73 → 5 super-commands)** | 5 个 super-command(`peaks code / audit / doctor / openspec / release / release-pack`)替换 73 个 leaf command,byte-identical 契约保留,改动对外透明。 | rid-009 · 26 routing test |
+
 ---
 
 ## 强烈推荐 · 四个项目组合起来用
@@ -138,17 +165,7 @@ npm i -g peaks-loop
 > **0 学习成本。** 这是组合起来用最大的好处 —— 不只是效果俱佳,更是因为这四个项目的**接口对齐到了"自然语言"**,你只需要说一句话,谁替你跑命令、按什么闸门、按什么战术手册,完全不用你记。
 
 <p align="center">
-  <a href="https://github.com/affaan-m/ECC">
-    <img src="https://img.shields.io/badge/ECC-affaan--m-6366f1?style=for-the-badge&logo=github&logoColor=white" alt="affaan-m/ECC" />
-  </a>
-  &nbsp;
-  <a href="https://github.com/Egonex-AI/Understand-Anything">
-    <img src="https://img.shields.io/badge/Understand--Anything-Egonex--AI-22c55e?style=for-the-badge&logo=github&logoColor=white" alt="Egonex-AI/Understand-Anything" />
-  </a>
-  &nbsp;
-  <a href="https://github.com/obra/superpowers">
-    <img src="https://img.shields.io/badge/superpowers-obra-f59e0b?style=for-the-badge&logo=github&logoColor=white" alt="obra/superpowers" />
-  </a>
+  <img src="./assets/readme/footer.svg" alt="peaks-loop 推荐组合" width="92%"/>
 </p>
 
 | 角色 | 项目 | 一句话 |
@@ -202,12 +219,32 @@ 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)。
 
 </details>
 
 ---
 
+## 全量 skill 索引
+
+13 个 user skill · 全部入口都在 `skills/<name>/SKILL.md`:
+
+<p align="center">
+  <img src="./assets/readme/skill-index.svg" alt="peaks-loop 13 user skills 索引卡" width="92%"/>
+</p>
+
+---
+
+## Ship 摘要(4.x · 19 rid)
+
+`009 · 010 · 011 · 014 · 015 · 016 · 017 · 020b · 024 · 025 · 026 · 027 · 028 · 029 · 030 · 031 · 032 · 033 · 034` — 涵盖 CLI surface 收敛(73→5 byte-identical)、Trusted Publishing + OIDC、24h-mode、context spillover、DAG wave+barrier、dashboard aggregation、test-rebuild epic、karpathy-cost self-review、compact visibility、retire-auto-compact-hook 等。
+
+<p align="center">
+  <img src="./assets/readme/ship-summary.svg" alt="peaks-loop 4.x 19 rid 历程表" width="92%"/>
+</p>
+
+---
+
 ## 链接
 
 - 全部技能清单 → [`skills/`](./skills/)
@@ -215,8 +252,8 @@ peaks-loop 的两条工程脊柱直接来自这两个项目:
 - 提问 → [GitHub Issues](https://github.com/SquabbyZ/peaks-loop/issues)
 - 致敬: [multica-ai/andrej-karpathy-skills](https://github.com/multica-ai/andrej-karpathy-skills) · [alchaincyf/darwin-skill](https://github.com/alchaincyf/darwin-skill)
 - 组合推荐: [affaan-m/ECC](https://github.com/affaan-m/ECC) · [Egonex-AI/Understand-Anything](https://github.com/Egonex-AI/Understand-Anything) · [obra/superpowers](https://github.com/obra/superpowers)
-- 沉淀设计 → [`docs/superpowers/specs/2026-07-04-peaks-maker-dynamic-skill-sediment-design.md`](./docs/superpowers/specs/2026-07-04-peaks-maker-dynamic-skill-sediment-design.md)
-- Loop Engineering 结晶设计 → [`docs/superpowers/specs/2026-07-07-peaks-loop-loop-engineering-crystallization-design.md`](./docs/superpowers/specs/2026-07-07-peaks-loop-loop-engineering-crystallization-design.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;