pi-gauntlet 8.2.0 → 8.2.1

package/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## v8.2.1 - 2026-11-06
+
+- Shape-ticket's AC integrity gate drops workflow-stage proof after splitting bundled observations, retains retired proof in the Reporter note, and routes an emptied AC list to recovery or park.
+
 ## v8.2.0 - 2026-11-05
 
 - Check-delivery accepts explicit ticket sets in pi: fresh `delivery-checker` children verify in parallel after one parent fetch, then the parent gates and writes each ticket in turn. Single-ref behavior stays in-session. Per-ticket consent replaces the single-ticket refusal in Item 3 of the check-delivery consumer-feedback spec.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-gauntlet",
-  "version": "8.2.0",
+  "version": "8.2.1",
   "description": "Opinionated, gated workflow skills, subagent personas, and runtime extensions for the pi coding agent.",
   "author": "Jacek Juraszek",
   "type": "module",

package/skills/brainstorming/reference/ticket-acceptance.md

@@ -1,6 +1,6 @@
 # Ticket Handling
 
-A ticket is guidance, not sole truth. Fetch it; propose scope, approach, or acceptance changes when code disagrees, and record deviations in the spec. Carry implied requirements and terms from the ticket body (Context, Problem, Idea) and every `Reporter note:` comment section into the spec as any other requirement; keep the ticket body's explicit acceptance criteria verbatim in the section below. Retain concrete details from a requirement-carrying note (paths, source measurements, preserved entry points) within that requirement in Design, not only in a context or premise note. Preserve a source measurement as a description of the input, not a new target or limit. Extract ACs from the body only, never comments. With no fetch path or a whole-ticket fetch failure, list the unfetched ref and use `none - ticket not fetched (<reason>)` in `## Acceptance criteria`; show that existing `none` line at the gate so the user can paste rows. On body success with comments marked `comments not fetched (<reason>)` or `comments incomplete after page <k> (<reason>)`, retain the fetched AC rows and carry an adjacent gate-summary line: `Implied requirements came from the body only - <comment status>; paste missing comment text.` Continue to the gate without a new stop.
+A ticket is guidance, not sole truth. Fetch it; propose scope, approach, or acceptance changes when code disagrees, and record deviations in the spec. Carry implied requirements and terms from the ticket body (Context, Problem, Idea) and every `Reporter note:` comment section into the spec as any other requirement; keep the ticket body's explicit acceptance criteria verbatim in the section below. Retain concrete details from a requirement-carrying note (paths, source measurements, preserved entry points) within that requirement in Design, not only in a context or premise note. Preserve a source measurement as a description of the input, not a new target or limit. Extract ACs from the body only, never comments. A Reporter note line marked `retired workflow-stage proof:` is provenance of a proof shape-ticket's AC integrity gate dropped, never a Design requirement; every other note requirement carries as above. With no fetch path or a whole-ticket fetch failure, list the unfetched ref and use `none - ticket not fetched (<reason>)` in `## Acceptance criteria`; show that existing `none` line at the gate so the user can paste rows. On body success with comments marked `comments not fetched (<reason>)` or `comments incomplete after page <k> (<reason>)`, retain the fetched AC rows and carry an adjacent gate-summary line: `Implied requirements came from the body only - <comment status>; paste missing comment text.` Continue to the gate without a new stop.
 
 **Extract the ticket's ACs.** When the ticket body has a heading matching `/acceptance criteria/i`, every list item under it is an AC (numbered, bullet, or checkbox) until the next heading of that heading's level or higher, and no other list in the body is; a heading one level deeper inside the section is a repo group - it names the repo whose part delivers the rows under it and does not end extraction. When there is no such heading, every top-level checkbox row in the body is an AC, except rows under a `Post-deployment housekeeping`, `Out of scope`, or `Follow-up` heading. Otherwise the ticket has no ACs. A nested list under an AC row rides with its parent as one row; an AC heading holding prose and no list makes each paragraph one row. Carry checked and unchecked rows alike, all written `- [ ]`. Take the rows and their repo-group headings from the gather draft's `## Ticket acceptance criteria (verbatim)` heading; when the ticket was not fetched, the gate summary shows the `none` line so the user can paste the rows, which then become rows.
 
@@ -21,7 +21,13 @@ Under `Ticket <ref>, <heading or "checkbox list">, rows verbatim:`, the section
 
 **Cut question.**
 
-Start the message with `gauntlet: question` alone at column zero on the first physical line, followed by a newline, before premise correction or framing. Never append a colon to the marker. Follow the [first-line rule](menu-layout.md). `deviates:` and `deferred:` come only from the user's answer to this question; never propose one. Ask it, in the questionary format, when the user's prompt or an answer raises dropping or changing a row, or when code, a cited contract, or the user shows a row is wrong or impossible: `A) in-scope - <reading> B) deviates: <why> C) deferred: <where> D) repair the ticket - /skill:shape-ticket <ref> <row and evidence>`, `Recommendation:` A or D with the reason the row ships in this gauntlet; B and C are never recommended. On D, run `/skill:shape-ticket <ref> <row and evidence>` (repair mode per `shape-ticket/SKILL.md:43`, its own confirm gate), then re-fetch the ticket, replace the gather draft's `## Ticket acceptance criteria (verbatim)` block, and re-extract; a cancel at that gate returns to this question with the row unchanged. Carry the full question and the user's answer of every question that offered a disposition into the council's `Human input` block. The gate lists every `deferred:`, `deviates:`, and `venue:` row on its `Scope cuts:` line (`spec-finalization.md`). A disposition changes in any later phase - a reviewer finding `recommended: rescope` at the finish gate, a wrong row noticed mid-implementation, or a ticket edited after approval when the user asks - through [Amending an approved spec](../SKILL.md#amending-an-approved-spec) (`amendment-surface.md`); the row text still never changes. For ticket rows, preserve the ticket contract: Never author acceptance criteria on the ticket's behalf; that is `/skill:shape-ticket`'s job.
+Start the message with `gauntlet: question` alone at column zero on the first physical line, followed by a newline, before premise correction or framing. Never append a colon to the marker. Follow the [first-line rule](menu-layout.md). `deviates:` and `deferred:` come only from the user's answer to this question; never propose one. Ask it, in the questionary format, on any trigger in the table below, with the options `A) in-scope - <reading> B) deviates: <why> C) deferred: <where> D) repair the ticket - /skill:shape-ticket <ref> <row and evidence>` and the table's `Recommendation:`; B and C are never recommended. On D, run `/skill:shape-ticket <ref> <row and evidence>` (repair mode per `shape-ticket/SKILL.md:43`, its own confirm gate), then re-fetch the ticket, replace the gather draft's `## Ticket acceptance criteria (verbatim)` block, and re-extract; on a cancel at that gate or an initial ticket-read abort, return to this question with the row unchanged and report no repair. Carry the full question and the user's answer of every question that offered a disposition into the council's `Human input` block. The gate lists every `deferred:`, `deviates:`, and `venue:` row on its `Scope cuts:` line (`spec-finalization.md`). A disposition changes in any later phase - a reviewer finding `recommended: rescope` at the finish gate, a wrong row noticed mid-implementation, or a ticket edited after approval when the user asks - through [Amending an approved spec](../SKILL.md#amending-an-approved-spec) (`amendment-surface.md`); the row text still never changes. For ticket rows, preserve the ticket contract: Never author acceptance criteria on the ticket's behalf; that is `/skill:shape-ticket`'s job.
+
+| Trigger | Screened | Recommendation |
+|---|---|---|
+| The user's prompt or an answer raises dropping or changing a row | When raised | A or D with the reason the row ships in this gauntlet |
+| Code, a cited contract, or the user shows a row is wrong or impossible | When shown | A or D with the reason the row ships in this gauntlet |
+| An observation in a ticket row is a workflow-stage proof under `shape-ticket/SKILL.md` `## AC integrity gate` (read that table at first use; a read, never a `/skill:shape-ticket` invocation) - the row as a whole or a stage-only clause beside a behavior; a row whose CI or suite result is itself the behavior under change is not one | The draft's verbatim block at checklist step 4, before question one, after the framing check; pasted rows when they land at the gate. Ask as the first ordinary question - after the framing question when a concern exists, else after the holds-statement. Never edit or split the ticket row; the intact row goes to the question | D - a stage proof is not an outcome |
 
 ## Row production at spec-writing
 
@@ -48,6 +54,7 @@ Apply these integrity classes inline without invoking ticket shaping. Preserve e
 | Unspecified-but-binding | Resolve the value from Design and record the resolution there; ask the user for a missing value |
 | External-input | Ask the user for the external yardstick before writing |
 | Post-deployment | Rewrite to a pre-production observation when available, retaining `venue:`; move production-only observations to a tracked, non-blocking `Post-deployment housekeeping` Design clause, never an AC row |
+| Workflow-stage proof | Before drafting, read `shape-ticket/SKILL.md` `## AC integrity gate` at first use and leave stage-only validation material (a suite command, a CI or workflow result, a PR state, a merge) out of the row set - it is proof, not an outcome, so no row is drafted and no scope decision is involved. For a row already drafted with that proof, keep its committed outcome and rewrite the proof to the Design behavior; delete the row only after its Design commitment is cut through the user's scope-decision procedure |
 
 Preserve behavioral binary outcomes with setup, action, and expected result; require no invented numeric baseline. Use only design-sourced values; never invent a baseline, target, measurement, or enumerated set. Ask for missing inputs before writing; never silently remove an outcome. Let an outcome leave in-scope only through an explicit scope decision by the user (the cut question or a clarification answer); record `deviates:`/`deferred:` and an `## Out of scope` entry so `Scope cuts:` discloses it. With no valid row remaining, stop for clarification or an explicit scope decision before writing; never emit a `none` fallback.
 

package/skills/shape-ticket/SKILL.md

@@ -104,7 +104,7 @@ Exempt one deletion-safe rule-7 pointer per failure, rule-5 one-sentence/one-num
 
 For ordinary repair only, if the body already conforms AND the metadata audit is clean AND no comment is proposed AND the audit carries no obsolete line: report "conforms, no changes proposed" and stop. No write, no confirmation prompt, no roast. A conforming ticket without an obsolete line never pays for a roast dispatch; the gather audit already ran and its Audit lines ride on the no-op report. Treat the obsolete line and other draft-changing audit findings under `reference/repo-audit.md` as non-conforming; quiet findings alone keep the no-op. A conforming body with pending overflow still reaches the gate.
 
-"Conforms" includes the ticket wording contract (`reference/ticket-wording.md`, resolved against this skill's own directory), applied inline as a short checklist over Context/Problem/Idea: strip test passes (rule 2)? plain-words lead per asserted failure (rule 4)? example or `none (<reason>)` per failure (rule 5)? repo-native terms defined or dropped and requester-used terms left undefined under rule 6's attribution test? Idea within one attributed sketch line? Context/Problem free of step-5 closed-list matches? references parenthetical and deletion-safe (rule 7)? links summarized, no spiderman hops (rule 8, with the named example serving as a source footer's summary)? every gathered URL, attachment, or pasted screenshot is carried in a source: footer under its example (Evidence gate carry rule)? every non-discovery Problem example has a source: footer (Evidence gate gap rule)? Any "no" makes the body non-conforming: repair proposes a rewrite through the normal draft -> gates -> roast -> gate path instead of reporting "conforms" - the contract-briefed roast backstops this inline judgment. Route each failure through draft -> step 5 -> roast -> old/new gate, with a new comment for newly displaced detail. For a conformance-only rewrite with no audit or uniqueness change to AC text, rows, or groups, touch Context/Problem/Idea prose only: copy the original bytes under the AC heading unchanged and compare bytes before presenting the gate; any mismatch stops that ticket. Any AC text, row, or group change from audit or uniqueness instead takes substantive full-replacement repair with `- [ ]` normalization; retain displaced text verbatim in the Reporter note. Check source carrying for every title; check source gaps only for non-discovery bodies. Preserve existing `source:` lines verbatim. For missing-footer-only repair, add only the footer under step 8 and leave existing prose and AC bytes unchanged; never report "conforms, no changes proposed".
+"Conforms" includes the ticket wording contract (`reference/ticket-wording.md`, resolved against this skill's own directory), applied inline as a short checklist over Context/Problem/Idea: strip test passes (rule 2)? plain-words lead per asserted failure (rule 4)? example or `none (<reason>)` per failure (rule 5)? repo-native terms defined or dropped and requester-used terms left undefined under rule 6's attribution test? Idea within one attributed sketch line? Context/Problem free of step-5 closed-list matches? references parenthetical and deletion-safe (rule 7)? links summarized, no spiderman hops (rule 8, with the named example serving as a source footer's summary)? every gathered URL, attachment, or pasted screenshot is carried in a source: footer under its example (Evidence gate carry rule)? every non-discovery Problem example has a source: footer (Evidence gate gap rule)? Any "no" makes the body non-conforming: repair proposes a rewrite through the normal draft -> gates -> roast -> gate path instead of reporting "conforms" - the contract-briefed roast backstops this inline judgment. Route each failure through draft -> step 5 -> roast -> old/new gate, with a new comment for newly displaced detail. For a conformance-only rewrite with no audit or uniqueness change to AC text, rows, or groups, touch Context/Problem/Idea prose only: copy the original bytes under the AC heading unchanged and compare bytes before presenting the gate; any mismatch stops that ticket. Any AC text, row, or group change from audit, uniqueness, or the AC integrity gate (a drop or a relocation) instead takes substantive full-replacement repair with `- [ ]` normalization; retain displaced text verbatim in the Reporter note. Check source carrying for every title; check source gaps only for non-discovery bodies. Preserve existing `source:` lines verbatim. For missing-footer-only repair, add only the footer under step 8 and leave existing prose and AC bytes unchanged; never report "conforms, no changes proposed".
 
 ### 7 - Roast
 
@@ -168,12 +168,13 @@ The test is structural, not keyword-based:
 | Unspecified-but-binding | closure-gating word with no value ("acceptable latency") | file allowed, **park** in the tracker's not-ready state, missing value named |
 | External-input dependency | yardstick another party must hand over first | **park**, blocker named; if resolving it is the assignee's own work, stays ready (over-fire guard) |
 | Post-deployment | observable only with the change live in production | **relocate** to Post-deployment housekeeping, non-blocking; never an AC |
+| Workflow-stage proof | sole observable is a delivery-pipeline stage - a CI or workflow run result, a pull request's state or review, a merge, or a full verification-suite run - not a behavior of the change | **drop**; retain the row's text in the Reporter note as `retired workflow-stage proof: <row text>`. Label every retained original containing a dropped stage clause, including AC uniqueness's split-row copy, with `retired workflow-stage proof:`; leave no unmarked duplicate. Remove only stage-proof rows or clauses. For this drop, copy surviving behavior text and untouched rows byte-for-byte even in substantive full-replacement repair; normalize checkbox syntax, not wording or setup/action framing |
 
-Precedence when one AC has multiple defects: wishful/tautological first (hard stop); then unspecified/external-input (park); a clean condition that is merely prod-only relocates. Hard-stop output quotes the offending AC, names the class, and gives concrete ways out.
+Precedence when one AC has multiple defects: wishful/tautological first (hard stop); then unspecified/external-input (park); a clean condition that is merely prod-only relocates; one that is only a stage proof drops. Hard-stop output quotes the offending AC, names the class, and gives concrete ways out.
 
 **Hard-stop run semantics:** apply the gathered overlap reference's independent alternative gates for overlap only. Apply ordinary repair hard-stop locality only across tickets in a batch: within one ticket, any surviving wishful/tautological AC stops that whole ticket's body and comment writes, with no approval option; for a singleton this stops the entire run. A source-ticket split remains all-or-nothing across its N bodies. Present the stopped draft and report in its turn without an approval option. Values supplied in-session recover only that ticket: re-draft, re-gate, and re-present its own exact diff for approval, never attach it to prior approval. Never silently write minus offending ACs.
 
-**Deploy-window rule.** Every AC must be fulfillable **before production deployment**. Local, UAT, staging, and experimental proofs with representative data are equal; an AC row names setup, action, and observable result and never names an environment - the spec picks the venue. Prod-only observations (backfills, post-release monitoring, prod smoke checks) go to `Post-deployment housekeeping` - tracked, explicitly non-blocking, never ACs. If relocation empties the AC list, that is the no-AC failure: recover a real pre-prod AC or park the ticket.
+**Deploy-window rule.** Every AC must be fulfillable **before production deployment**. Local, UAT, staging, and experimental proofs with representative data are equal; an AC row names setup, action, and observable result and never names an environment - the spec picks the venue. Prod-only observations (backfills, post-release monitoring, prod smoke checks) go to `Post-deployment housekeeping` - tracked, explicitly non-blocking, never ACs. If relocation or a stage-proof drop empties the AC list, that is the no-AC failure: recover a real pre-prod AC or park the ticket.
 
 **Guards:** never invent a number, list, label, or URL to pass a gate - `none (<reason>)` is a valid explicit outcome. Speculative items go to `Out of scope / Follow-up`, offered as separate linked tickets. Implicit constraints surfaced during gather are **proposed** as ACs at the gate, never silently auto-written.
 

package/skills/shape-ticket/reference/examples.md

@@ -19,6 +19,11 @@ Read this when applying the AC integrity gate (drafting, repairing, or adjudicat
 - Bad: `- [ ] Import completes in acceptable time`
 - Good: `- [ ] Importing a 10k-row CSV completes in under 60s`
 
+**Workflow-stage proof**
+
+- Bad: `- [ ] The importer rejects a row without an id and CI is green on the PR head`
+- Good: `- [ ] The importer rejects a row without an id` (the CI result is the PR gate's observation, not an outcome)
+
 **Discovery pair** (bad ticket -> good ticket, not just a bad->good AC)
 
 - Bad ticket: `Investigate checkout performance` - unbounded, no artifact.