@mstar-harness/dsh 3.2.5 → 3.2.6

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -230,7 +230,7 @@ Posting the GitHub Review is a **mandatory deliverable** of the `pr` variant —
230
230
 
231
231
  ### Report template (GitHub Review `body`)
232
232
 
233
- 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).
233
+ 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). The block below shows only **fill-in slots**: a `<...>` that wraps descriptive text (`<verdict>`, `<n>`, `<finding title>`, …) is a slot — replace the whole bracket pair with real content and never render those brackets. The literal HTML tags in the template (`<details>`, `<summary>`, `<br>`) are **structural** — keep them verbatim so the collapsible block survives. The Slot rules below the template are guidance — never copy them into the posted body.
234
234
 
235
235
  **Section emoji map** — verdict: `ship it` ✅ · `needs fixes` ⚠️ · `blocked` ⛔. Finding classes: 🔴 must-fix · 🟠 should-fix · 🔵 nit · ❓ unverified.
236
236
 
@@ -246,36 +246,52 @@ The posted review body is a three-section report. Section order fixed; omit a su
246
246
 
247
247
  ## 📋 Review
248
248
 
249
- **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.>
249
+ **What this PR does**: <2–3 sentence summary of the diff's intent and surface>
250
250
 
251
251
  ### Findings
252
252
 
253
- <Ranked findings. Each finding keeps its normal format — title, evidence (`file:line`), impact, **Merge class**, **Confidence**, fix sketch — with its class emoji prefixing the title.>
253
+ #### <class-emoji> <finding title>
254
+
255
+ - **Evidence**: `file:line` — what the code does
256
+ - **Impact**: why it matters
257
+ - **Merge class**: must-fix | should-fix | nit
258
+ - **Confidence**: HIGH | MEDIUM | LOW
259
+ - **Fix sketch**: one-line suggestion
254
260
 
255
261
  ### Linked-issue AC
256
262
 
257
- <When § Linked-issue hygiene applied: per-criterion met / unmet / cut with one-line reasoning. Otherwise `none`.>
263
+ <per-criterion: met / unmet / cut one-line reasoning, or `none`>
258
264
 
259
265
  ### ✅ Verified
260
266
 
261
- <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.>
267
+ - <check or command> <what it showed>
268
+ - ❓ <unverified lead, if any>
262
269
 
263
270
  ### 🗑️ Considered & rejected
264
271
 
265
- <- <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.>
272
+ - **<short finding title>**: rejected <one-line reason>
266
273
 
267
274
  ## 🛠️ Plan to fix
268
275
 
269
- <details><summary>展开修复计划 / Expand fix plan</summary>
276
+ <details><summary>Expand fix plan</summary>
270
277
  <br>
271
278
 
272
279
  ```md
273
- <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.>
280
+ <fix plan in markdown>
274
281
  ```
275
282
 
276
283
  </details>
277
284
  ````
278
285
 
286
+ **Slot rules (guidance — not part of the posted body):**
287
+
288
+ - **What this PR does**: from the PR description plus your own read of the changed files, not copied marketing text.
289
+ - **Findings**: ranked by impact-if-shipped (§ Verdict synthesis); every accepted finding listed, nothing truncated; repeat the `#### <class-emoji> <title>` block per finding.
290
+ - **Linked-issue AC**: fill only when § Linked-issue hygiene applied; otherwise a bare `none`.
291
+ - **Verified**: the smallest runtime checks actually run and what they showed; unverified leads as `❓` lines here, never in the findings table.
292
+ - **Considered & rejected**: one bullet per rejected candidate from the three-way attack / vet pass (§ Attack and vet), so the next reviewer does not re-chase it; bare `none` when nothing was rejected.
293
+ - **Plan to fix**: fix plan in markdown (ordered steps per finding, files touched, verification gates); follow-up plan index folds in above the ```md block (§ Folding plans); when there is no fix plan, replace the whole `<details>` block with a single line `none`.
294
+
279
295
  - 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.
280
296
  - When the fix plan itself contains fenced code blocks, open the outer fence with four backticks so the inner fences survive.
281
297
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@mstar-harness/dsh",
3
- "version": "3.2.5",
3
+ "version": "3.2.6",
4
4
  "description": "Morning Star harness dsh (DeepSeek Harness) cordis function plugin — in-process engine gates (status/dispatch/lease) with hard refusal channels.",
5
5
  "keywords": [
6
6
  "dsh",