CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-06-25 02:59:59 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix(ship): port #1302 SKILL.md edits to .tmpl + resolver source

Browse Source 
PR #1302 added Verification Mode + UNVERIFIABLE classification + per-item
confirmation gate to ship/SKILL.md, but only the generated SKILL.md was
edited — not the .tmpl source or scripts/resolvers/review.ts. The next
`bun run gen:skill-docs` run would have wiped the changes.

Port the same content into the resolver and .tmpl so regeneration produces
the intended output.
This commit is contained in:
Garry Tan
2026-05-08 21:46:03 -07:00
parent 1722f65d28
commit d45e1248bc
2 changed files with 84 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ship/SKILL.md.tmpl
+5 -5
View File
@@ -268,16 +268,16 @@ If multiple suites need to run, run them sequentially (each needs a test lane).
> {{PLAN_COMPLETION_AUDIT_SHIP}}
>
> After your analysis, output a single JSON object on the LAST LINE of your response (no other text after it):
> `{"total_items":N,"done":N,"changed":N,"deferred":N,"summary":"<markdown checklist for PR body>"}`
> `{"total_items":N,"done":N,"changed":N,"deferred":N,"unverifiable":N,"summary":"<markdown checklist for PR body>"}`
**Parent processing:**
1. Parse the LAST line of the subagent's output as JSON.
2. Store `done`, `deferred` for Step 20 metrics; use `summary` in PR body.
3. If `deferred > 0` and no user override, present the deferred items via AskUserQuestion before continuing.
4. Embed `summary` in PR body's `## Plan Completion` section (Step 19).
2. Store `done`, `deferred`, `unverifiable` for Step 20 metrics; use `summary` in PR body.
3. If `deferred > 0` or `unverifiable > 0` and no user override, present the items via the appropriate AskUserQuestion (see Gate Logic priority order above) before continuing.
4. Embed `summary` in PR body's `## Plan Completion` section (Step 19). If `unverifiable > 0` and the user picked option A in the UNVERIFIABLE gate, also embed `## Plan Completion — Manual Verifications` listing each user-confirmed item.
**If the subagent fails or returns invalid JSON:** Fall back to running the audit inline. Never block /ship on subagent failure.
**If the subagent fails or returns invalid JSON:** Fall back to running the audit inline (parent processes the same plan-extraction + classification logic). If the inline fallback also fails (e.g., plan file unreadable, parser error), do NOT silently pass — surface the failure as an explicit AskUserQuestion: "Plan Completion audit could not run ({reason}). Options: (A) Skip audit and ship anyway — record that the audit was skipped in PR body and Step 20 metrics; (B) Stop and fix the audit." Default and recommended option is (B). Silent fail-open is the failure shape that VAS-449 surfaced.
---