@mstar-harness/dsh 3.2.4 → 3.2.5
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.
|
@@ -2,7 +2,7 @@
|
|
|
2
2
|
name: pr-deep-review
|
|
3
3
|
description: Use when asked to deeply review a pull request, branch, or diff before merge — deciding whether a change is safe to ship with evidence-backed findings, rather than a shallow "looks good" pass. Produces a `ship it` / `needs fixes` / `blocked` verdict. Also for a batch of sibling PRs. Do not use for self-checking a change you just authored.
|
|
4
4
|
agent: project-manager
|
|
5
|
-
input: "[pr|branch|scope]
|
|
5
|
+
input: "[pr|branch|scope]"
|
|
6
6
|
---
|
|
7
7
|
|
|
8
8
|
# Deep PR Review
|
|
@@ -87,7 +87,7 @@ Then open cited code yourself and dispose by-design / mis-attributed / duplicate
|
|
|
87
87
|
## Verdict synthesis
|
|
88
88
|
|
|
89
89
|
- Order findings by impact-if-shipped; no padding, no invented requirements, no style grading.
|
|
90
|
-
- List **every** `must-fix
|
|
90
|
+
- List **every** accepted finding — `must-fix`, `should-fix`, and nits alike; nothing is truncated.
|
|
91
91
|
- The verdict is **derived from the tally, not chosen**: classify every accepted finding (§ Merge class) → apply leftover `unmet` AC increments if any (§ Linked-issue hygiene) → apply **Verdict-from-tally** (§ Tally and derived score) → emit that one token. The reviewer does not pick a verdict by vibe.
|
|
92
92
|
- Exactly one verdict:
|
|
93
93
|
- `ship it` — evidence-backed, safe to ship.
|
|
@@ -250,7 +250,7 @@ The posted review body is a three-section report. Section order fixed; omit a su
|
|
|
250
250
|
|
|
251
251
|
### Findings
|
|
252
252
|
|
|
253
|
-
<Ranked findings
|
|
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.>
|
|
254
254
|
|
|
255
255
|
### Linked-issue AC
|
|
256
256
|
|
|
@@ -353,6 +353,3 @@ Then ranked findings / leftover AC summary. Do not put `score_pct%` on the `- ve
|
|
|
353
353
|
|
|
354
354
|
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).
|
|
355
355
|
|
|
356
|
-
### List cut
|
|
357
|
-
|
|
358
|
-
The default "top 1–3 unless `full`" applies to **nits only**: every `must-fix` and `should-fix` finding is listed. If nits are omitted from the narrative list, add one line `nits: <n> omitted from list (counted in tally)` — `tally.nit` stays complete.
|
package/package.json
CHANGED