@mstar-harness/dsh 3.2.2 → 3.2.4

package/harness-commands/pr-deep-review.md

@@ -36,4 +36,4 @@ Execute **`mstar-audit`** § `pr` variant end to end（SKILL.md common core：re
 
 Review findings that need fixing can be turned into self-contained plans for the normal Prepare → Execute flow (reusing `mstar-audit` SKILL.md **`## Plan output (all variants)`** — same contract as the `pr` variant).
 
-Output verdict + findings to the user, with the posted GitHub Review URL. Posting procedure (when a PR number exists) → **`references/pr-review.md`** § Comment posting. Never auto-approve or merge.
+Output verdict + findings to the user, with the posted GitHub Review URL. Posting procedure (when a PR number exists) → **`references/pr-review.md`** § Comment posting; each reviewer also saves the durable local report → **`references/pr-review.md`** § Local report archive. Never auto-approve or merge.

package/harness-skills/mstar-artifacts/references/knowledge-and-designs.md

@@ -28,7 +28,7 @@
 - **不放什么**：已锁定的仓库级规范（→ **`{SPECS_DIR}/`**）；已提升的跨迭代实施 SSOT（→ **`{KNOWLEDGE_DIR}/`**，经 compound）；单 plan QC/QA 原始报告（→ `{SDD_DIR}/review/`）。
 - **索引**：`**{ITERATION_DIR}/README.md**` **一行 = 一次迭代**（指向 `<iteration-id>/`）；`<iteration-id>/README.md` 登记 package 内文档（Documents 单表）。
 - **维护**：`@product-manager` / `@architect` 起草 package；`**@project-manager**` 维护索引与 metadata；**iteration-close** 时 **`mstar-compound`** 盘点 package 并**提升**至 `{KNOWLEDGE_DIR}/`。
-- **Compass 路径**：canonical `{ITERATION_DIR}/<iteration-id>/delivery-compass.md`；legacy flat `{ITERATION_DIR}/<iteration-id>-delivery-compass.md` 仅兼容读。
+- **Compass 路径**：canonical `{ITERATION_DIR}/<iteration-id>/delivery-compass.md`（迭代状态 SSOT）；legacy flat `{ITERATION_DIR}/<iteration-id>-delivery-compass.md` 仅兼容读。
 
 ## `{SPECS_DIR}`（可选·长期规格）
 

package/harness-skills/mstar-artifacts/references/plan-files-and-reports.md

@@ -21,7 +21,6 @@ QC/QA 原始过程报告默认是 **ephemeral review bundle**，置于 `{SDD_DIR
 | QC 汇总结论（tri 模式） | `qc-consolidated.md` |
 | QA 验收报告（`QA gate: mandatory`） | `qa.md`（或 Assignment 指定的同目录 basename） |
 
-`{PLAN_DIR}/reports/` is **legacy / explicit audit mode only**. Use it only when the user or project policy explicitly requires tracked raw reports; the default harness path is `{SDD_DIR}/review/`.
 
 ## SDD 运行时（不入 reports）
 

package/harness-skills/mstar-audit/references/pr-review.md

@@ -205,7 +205,7 @@ Posting the GitHub Review is a **mandatory deliverable** of the `pr` variant —
 
 - **Before anything else:** synthesize the verdict first, then post **before** worktree cleanup (see § Worktree isolation — cleanup happens after the comment is posted).
 - **No PR number** (bare branch / arbitrary diff): set `comments: n/a-no-pr` and skip the API. Chat output still required; this is not a Blocked review.
-- **Auth / API failure:** deliver the chat verdict anyway; Completion Report status `Partial`/`Blocked` with the `gh` error. Do not claim `Done` — comments are mandatory when a PR exists.
+- **Auth / API failure:** deliver the chat verdict anyway; Completion Report status `Partial`/`Blocked` with the `gh` error. Do not claim `Done` — comments are mandatory when a PR exists. **The local report is still saved** (§ Local report archive — posting failure does not skip archival).
 
 ### Procedure
 
@@ -217,7 +217,7 @@ Posting the GitHub Review is a **mandatory deliverable** of the `pr` variant —
 2. Build one review payload:
    - `event`: `COMMENT` — **never** `APPROVE`, **never** `REQUEST_CHANGES`, never a merge.
    - `commit_id`: the PR head SHA.
-   - `body`: **first two lines are the display contract** — `{verdict} · {score_pct}%` then the tally line (`must-fix=<n> should-fix=<n> nit=<n> unverified=<n>`) — then ranked findings (short) + linked-issue leftover reasoning + optional folded plan index (below). `event` stays `COMMENT` — **never** `APPROVE`, **never** `REQUEST_CHANGES`, never a merge.
+   - `body`: follow **§ Report template (below)** — three sections (Verdict → Review → Plan to fix). `event` stays `COMMENT` — **never** `APPROVE`, **never** `REQUEST_CHANGES`, never a merge.
    - `comments[]`: one entry per finding whose `path` + `line` is in the three-dot diff, `side: RIGHT`. Finding body = title + evidence + impact + fix sketch — not the whole plan.
 3. Post it:
    ```
@@ -225,22 +225,99 @@ Posting the GitHub Review is a **mandatory deliverable** of the `pr` variant —
    ```
    (payload on stdin).
 4. **Line fallback:** if GitHub rejects some inline comments (e.g. 422 — line not in the diff), retry the review **without** those entries and fold them into the summary body. Do not loop more than once.
-5. Record `html_url` / review id for `comments:`. Only now clean up the worktree (or after the n/a-no-PR skip).
+5. Save the local report (§ Local report archive) — **mandatory in all three branches**: POST succeeded (record `html_url` / review id for `comments:` first), POST failed, or `n/a-no-pr` (archive the chat display content). Only then clean up the worktree; bare branch/diff reviews have no worktree, but the save still happens.
 6. **Batch:** each reviewer posts on **their own PRs** only. No second PM summary comment unless the Assignment says so.
 
-### Folding plans into the summary
+### Report template (GitHub Review `body`)
+
+The posted review body is a three-section report. Section order fixed; omit a subsection only when its content is genuinely empty (write `none`, never delete the heading).
+
+**Section emoji map** — verdict: `ship it` ✅ · `needs fixes` ⚠️ · `blocked` ⛔. Finding classes: 🔴 must-fix · 🟠 should-fix · 🔵 nit · ❓ unverified.
+
+````markdown
+## <verdict-emoji> Verdict: `<verdict>` · Confidence <score_pct>%
+
+| Findings | Count |
+| --- | --- |
+| 🔴 must-fix | <n> |
+| 🟠 should-fix | <n> |
+| 🔵 nit | <n> |
+| ❓ unverified | <n> |
+
+## 📋 Review
+
+**What this PR does**: <2–3 sentences summarizing the diff's intent and surface — from the PR description plus your own read of the changed files, not copied marketing text.>
+
+### Findings
+
+<Ranked findings (§ List cut). Each finding keeps its normal format — title, evidence (`file:line`), impact, **Merge class**, **Confidence**, fix sketch — with its class emoji prefixing the title.>
+
+### Linked-issue AC
+
+<When § Linked-issue hygiene applied: per-criterion met / unmet / cut with one-line reasoning. Otherwise `none`.>
+
+### ✅ Verified
+
+<Concise what-checks-proved summary — the smallest runtime checks actually run and what they showed. Residual unverified leads go here as `- ❓ <lead>` lines, not into the findings table.>
+
+### 🗑️ Considered & rejected
+
+<- <finding>: rejected because <one line>. Otherwise `none` — rejections come from the three-way attack / vet pass (§ Attack and vet), so the next reviewer does not re-chase them.>
 
-Fold follow-up plans into the review body **only if** this review wrote them. A short index — title, priority, effort, 1–3 sentence sketch, plan path — inside:
+## 🛠️ Plan to fix
 
+<details><summary>展开修复计划 / Expand fix plan</summary>
+<br>
+
+```md
+<Fix plan in markdown when the audit produced one: ordered steps per finding, files touched, verification gates. Omit the block entirely only when no fix is proposed.>
 ```
-<details><summary>Follow-up plans</summary>
 
-- <plan title> — P1 / S — <1–3 sentence sketch> (`{PLAN_DIR}/audit-<date>/NNN-<slug>.md`)
 </details>
+````
+
+- The Verdict section replaces the old two-line tally header on GitHub: same facts (verdict token + `score_pct` as Confidence + four-class tally), structured. The chat display contract (§ Display contract) is unchanged.
+- When the fix plan itself contains fenced code blocks, open the outer fence with four backticks so the inner fences survive.
+
+### Folding plans into the summary
+
+Fold follow-up plans into the review body **only if** this review wrote them. Put a short index — title, priority, effort, 1–3 sentence sketch, plan path — as the first content inside the § Report template **Plan to fix** `<details>` block, before the ```md fix-plan block:
+
+```
+- <plan title> — P1 / S — <1–3 sentence sketch> (`{PLAN_DIR}/audit-<date>/NNN-<slug>.md`)
 ```
 
 Never dump full plan files.
 
+### Local report archive
+
+The posted PR comment is the deliverable; the local report is the durable reference copy — the PR thread may be buried, locked, or deleted, and bare-branch/diff reviews have no thread at all. The review seat saves **one markdown file per reviewed PR** (or branch/diff) as part of the mandatory deliverable, before worktree cleanup:
+
+- **Path**: `{PROJECT_DIR}/<project-id>/reports/pr-review/` — `<project-id>` from the Assignment / project context, `_default` when the review runs outside any project flow (same id convention as `projects/<id>/residuals.json`). Gitignored local SSOT, same posture as residuals; a finding that must survive across clones gets promoted to tracked `{KNOWLEDGE_DIR}` / `{SPECS_DIR}`, not by tracking this directory.
+- **Write via the primary checkout, never the worktree**: harness discovery must not start from the review worktree — its root has no gitignored `.mstar/`, and anything written there is destroyed by `git worktree remove` (§ Worktree isolation). Record the primary repository's absolute path **before** creating the worktree and write the report under it. Never create a `.mstar/` inside the review worktree to "host" the report.
+- **Filename**: `<YYYY-MM-DD>-pr<N>.md`; bare branch → `<YYYY-MM-DD>-<branch-slug>.md`; arbitrary diff → `<YYYY-MM-DD>-diff-<short-head-sha>.md`, or `<YYYY-MM-DD>-diff.md` when no head SHA was provided with the changeset (never invent one). Same target twice in one day → append `-r2`, `-r3`, … (never overwrite a prior report).
+- **Frontmatter** (machine-readable metadata):
+  ```yaml
+  ---
+  type: pr-review
+  pr: <n>                # omit for bare branch / diff
+  url: <pr url>          # omit for bare branch / diff
+  head: <head sha>
+  base: <base ref>
+  verdict: ship it | needs fixes | blocked
+  score_pct: <n>
+  tally: { must-fix: <n>, should-fix: <n>, nit: <n>, unverified: <n> }
+  review_url: <posted review html_url>   # n/a-no-pr when skipped; failed: <gh error summary> when POST failed
+  generated_at: <YYYY-MM-DD>
+  ---
+  ```
+
+`head:` / `base:` are omitted when genuinely unknown (arbitrary diff without stated provenance) — never fabricate identifiers.
+
+**Posting failure does not skip archival.** The report is saved regardless of the POST outcome: on failure it archives the chat display content plus the `gh` error summary, so a failed POST still leaves the durable copy.
+- **Body**: the exact text posted as the GitHub Review body — verbatim, not a paraphrase. When `comments: n/a-no-pr` or posting failed, the body is the chat display content instead (§ Display contract two lines + ranked findings + leftover AC), so the local copy is still complete.
+- Fix plans referenced by the Plan-to-fix section keep living in `{PLAN_DIR}/audit-<date>/` when written — the report links them, never duplicates them.
+
 ## Output shape
 
 - `- findings:` — list of evidence-backed findings (`none` when none). Each accepted finding includes **Merge class** (§ Merge class).
@@ -261,16 +338,20 @@ Never dump full plan files.
   - `inline: <N> posted / <M> attempted (<K> summary-only fallback)`
   - `plans_folded: yes` | `no`
 
-### Display contract (chat + GitHub Review `body`)
+- `- report:` — local archive path (§ Local report archive), e.g. `{PROJECT_DIR}/<project-id>/reports/pr-review/2026-08-24-pr134.md` (`_default` when project-less); `n/a` only when the harness dir is undiscoverable.
+
+### Display contract (chat output)
 
-First two lines of the display (chat output and the GitHub Review `body`) — verbatim:
+First two lines of the **chat** display — verbatim:
 
 ```
 {verdict} · {score_pct}%
 must-fix=<n> should-fix=<n> nit=<n> unverified=<n>
 ```
 
-Then existing ranked findings / leftover AC / optional `<details>` plan index. Do not put `score_pct%` on the `- verdict:` token line.
+Then ranked findings / leftover AC summary. Do not put `score_pct%` on the `- verdict:` token line.
+
+The GitHub Review `body` no longer uses the two-line header — it follows § Report template, whose Verdict section carries the same facts structured (verdict token + Confidence + four-class emoji tally table).
 
 ### List cut
 

package/harness-skills/mstar-conventions/SKILL.md

@@ -84,7 +84,8 @@ enforcement=hard
 
 **创建默认**：全部缺失或皆空 → 创建并使用 `{HARNESS_DIR}/specs/`（统一落在 `.mstar/` 下）。**禁止**在 greenfield init 时优先创建裸仓库根 `specs/`。
 
-**Legacy（仅兼容读）**：若以上皆无内容，但 `{HARNESS_DIR}/designs/` 或仓库根 `designs/` **非空**，可作 `{SPECS_DIR}` 使用；init 时**不**新建 `designs/`。
+**Legacy 兼容读**：若以上皆无内容，但 `{HARNESS_DIR}/designs/` 或仓库根 `designs/` **非空**，可作 `{SPECS_DIR}` 使用；init 时**不**新建 `designs/`。
+
 
 > **Engine check (when available):** import `resolveSpecsDir` from `@mstar-harness/engine` in a host hook — or run `mstar path resolve` (prints the resolved specs dir) — to confirm the candidate order (empty-dir-as-absent included). On `fail` -> do not proceed; fix and re-run. Skill text below remains authoritative when the runtime is absent.
 
@@ -107,7 +108,7 @@ enforcement=hard
 PM 在需要持久化追踪时：
 
 1. 建 `.mstar/`、`plans/`、`status.json`（**v2 空模板**见 **`mstar-artifacts/templates/status.empty.json`**：`version: 2` + `workflows: []`）
-2. 可选 `notes.json`（legacy）、`knowledge/`、`iterations/`、`{HARNESS_DIR}/specs/`、`sdd/`（空目录占位；运行时 per-plan 子目录由 **`mstar-sdd`** → `mstar sdd workspace <plan-id>` 创建；`workflows/` / `projects/` 由 engine writers 按需创建，**不**预建）
+2. 可选 `knowledge/`、`iterations/`、`{HARNESS_DIR}/specs/`、`sdd/`（空目录占位；运行时 per-plan 子目录由 **`mstar-sdd`** → `mstar sdd workspace <plan-id>` 创建；`workflows/` / `projects/` 由 engine writers 按需创建，**不**预建）
 3. 项目根 `.gitignore` 追加 Morning Star **进程产物**忽略集（见下文「Git 跟踪策略」）— CLI `init` 可自动添加
 4. Git：**进程本地、结果共享** — 默认跟踪 `{HARNESS_DIR}/AGENTS.md`、`{KNOWLEDGE_DIR}/**`、`{SPECS_DIR}/**`；`plans/`、`iterations/`、`status.json` 等为**本地会话 SSOT**，默认 gitignored。跨 clone 持久 handoff = knowledge + specs + `{HARNESS_DIR}/AGENTS.md`（及根 `CONCEPTS.md` / `STRATEGY.md` 若使用）；须跨 clone 的 residual 须提升（compound）或写入 tracked results — **勿**默认 `git add` `status.json` / `plans/`。
 
@@ -129,7 +130,6 @@ PM 在需要持久化追踪时：
 - `iterations/`
 - `plans/`
 - `sdd/`
-- `notes.json`（legacy；运行时 notes 走 `workflows/<id>/notes.jsonl`）
 - `status.json`
 - `workflows/`（v3 每 lifecycle 运行态：`<id>/snapshot.json` + `<id>/notes.jsonl`）
 - `projects/`（v3 项目层：`<id>/roadmap.md` + `<id>/residuals.json`）

package/harness-skills/mstar-conventions/references/artifact-storage-paths.md

@@ -47,7 +47,6 @@
 | `docs/` | 人类文档（安装、贡献指南等），知识产物不放此处 |
 | `{ITERATION_DIR}/` | 迭代 package（compass + guides/specs）；知识文档不放此处 |
 | `{SPECS_DIR}/` | 仅限冻结规格/ADR，运行时知识不放此处 |
-| `{PLAN_DIR}/reports/` | Legacy / explicit audit mode only；默认 QC/QA 原始过程报告进 `{SDD_DIR}/review/`，知识文档不放此处 |
 
 ## `<category>` 取值
 

package/harness-skills/mstar-conventions/references/harness-bootstrap-and-agents-layering.md

@@ -14,7 +14,7 @@
 
 1. 创建 `{HARNESS_DIR}`（推荐 `.mstar/`）与 `{PLAN_DIR}`（推荐 `.mstar/plans/`）。
 2. 初始化 `status.json`：从 **`mstar-artifacts/templates/status.empty.json`** 复制（**v2 形状**：`version: 2` + `workflows: []`）；residual canonical 见 **`mstar-artifacts` SKILL.md**；字段与生命周期见 **`mstar-artifacts/references/status-and-residuals.md`**。`workflows/` 与 `projects/` 子目录由 engine writers 按需创建（**不**在 bootstrap 预建）。
-3. 初始化可选 `notes.json`（legacy）；`sdd/` 空目录占位（per-plan 子目录由 **`mstar-sdd`** → `mstar sdd workspace <plan-id>` 创建）。
+3. `sdd/` 空目录占位（per-plan 子目录由 **`mstar-sdd`** → `mstar sdd workspace <plan-id>` 创建）。
 4. 项目根 `.gitignore` 追加 Morning Star **进程产物**忽略集（canonical snippet → `mstar-conventions` SKILL.md「Git 跟踪策略」；legacy `.agents/` 有等价表）。
 5. 可选：创建 `{ITERATION_DIR}`（`iterations/` + `README.md`）与 `{KNOWLEDGE_DIR}`（`knowledge/` + `README.md`）；`{HARNESS_DIR}/specs/`（解析后的 `{SPECS_DIR}` 默认落点）；内容边界见 `mstar-conventions` SKILL.md 与 `references/knowledge-and-designs.md`。
 6. 创建 `{HARNESS_DIR}/AGENTS.md`（harness 子树规则；**tracked**）：符号表可复述 `{HARNESS_DIR}`、`{PLAN_DIR}`、`{ITERATION_DIR}`、`{KNOWLEDGE_DIR}`、`{SPECS_DIR}` 与 `docs/` 分工；新项目推荐 `.mstar/AGENTS.md`，已有项目可继续使用 `.agents/AGENTS.md`。
@@ -28,7 +28,7 @@
 | 类别 | 默认 tracked | 默认 gitignored |
 |------|--------------|-----------------|
 | 结果（跨 clone handoff） | `{HARNESS_DIR}/AGENTS.md`、`{KNOWLEDGE_DIR}/**`、`{SPECS_DIR}/**` | — |
-| 进程（本地会话 SSOT） | — | `plans/`、`iterations/`、`status.json`、`workflows/`、`projects/`、`notes.json`、`sdd/`、`archived/` |
+| 进程（本地会话 SSOT） | — | `plans/`、`iterations/`、`status.json`、`workflows/`、`projects/`、`sdd/`、`archived/` |
 
 跨 clone 须持久的 residual 或决策：经 **`mstar-compound`** 提升入 `{KNOWLEDGE_DIR}/`、写入 `{SPECS_DIR}/`，或记入 tracked `{HARNESS_DIR}/AGENTS.md` — **勿**默认 `git add` `status.json` / `plans/`。
 

package/harness-skills/mstar-roles/references/project-manager/plan-management.md

@@ -19,8 +19,8 @@ Legacy fallbacks:
 
 1. Create `{HARNESS_DIR}` and `{PLAN_DIR}` when absent.
 2. Initialize `{HARNESS_DIR}/status.json` from template if available.
-3. Ensure Morning Star **process-artifact** gitignore set is present (canonical snippet → `mstar-conventions` SKILL.md「Git 跟踪策略」): `{HARNESS_DIR}/archived/`, `iterations/`, `plans/`, `sdd/`, `notes.json`, `status.json`, `workflows/`, `projects/` (legacy `.agents/` equivalents when applicable). Per-plan `{SDD_DIR}/review/` is created by the SDD/review flow when needed.
-4. Optional: `{HARNESS_DIR}/notes.json` (legacy), `{HARNESS_DIR}/knowledge/README.md`. `workflows/` / `projects/` subdirs are created on demand by engine writers — no pre-creation.
+3. Ensure Morning Star **process-artifact** gitignore set is present (canonical snippet → `mstar-conventions` SKILL.md「Git 跟踪策略」): `{HARNESS_DIR}/archived/`, `iterations/`, `plans/`, `sdd/`, `status.json`, `workflows/`, `projects/` (legacy `.agents/` equivalents when applicable). Per-plan `{SDD_DIR}/review/` is created by the SDD/review flow when needed.
+4. Optional: `{HARNESS_DIR}/knowledge/README.md`. `workflows/` / `projects/` subdirs are created on demand by engine writers — no pre-creation.
 
 If legacy plan directories already exist, reuse them; avoid dual-structure duplication.
 
@@ -29,7 +29,7 @@ If legacy plan directories already exist, reuse them; avoid dual-structure dupli
 **Principle:** process stays local; results are shared with the team. Full rules → `mstar-conventions` SKILL.md「Git 跟踪策略」.
 
 - **Default tracked** under `{HARNESS_DIR}`: `AGENTS.md`, `{KNOWLEDGE_DIR}/**`, `{SPECS_DIR}/**` (resolved specs path; default `{HARNESS_DIR}/specs/`).
-- **Default gitignored** (local session SSOT / coordination): `archived/`, `iterations/`, `plans/`, `sdd/`, `notes.json`, `status.json`, `workflows/`, `projects/`.
+- **Default gitignored** (local session SSOT / coordination): `archived/`, `iterations/`, `plans/`, `sdd/`, `status.json`, `workflows/`, `projects/`.
 - `status.json` (v2 root), workflow snapshots, project registers and main plan files remain **local session SSOT** — PM must keep them current on disk, but **do not** default `git add` / `git commit` for cross-clone handoff. Promote durable residuals and decisions into tracked `knowledge/` / `specs/` / `AGENTS.md` (compound) when they must survive clone.
 - If a project explicitly opts into tracking process artifacts, record that policy in `{HARNESS_DIR}/AGENTS.md` and ensure team alignment.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mstar-harness/dsh",
-  "version": "3.2.2",
+  "version": "3.2.4",
   "description": "Morning Star harness dsh (DeepSeek Harness) cordis function plugin — in-process engine gates (status/dispatch/lease) with hard refusal channels.",
   "keywords": [
     "dsh",