pi-gauntlet 4.12.0 → 4.12.1

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.
package/CHANGELOG.md CHANGED
@@ -1,5 +1,11 @@
1
1
  # Changelog
2
2
 
3
+ ## v4.12.1 - 2026-08-19
4
+
5
+ - `check-delivery`: two new `## Delivery` overrides slots - `synthesized AC gaps: block|soft` (default `soft`; `block` runs synthesized ACs through the same verdict matrix as authored ones, so an unexplained gap blocks) and `descope edits: strikethrough` (default none; on gate approval, ratified `proposed descope` AC lines are struck in the ticket body with an evidence-drafted reason, write order body -> comment -> status, surgical patch against the re-fetched body, whole-write manual degradation when no edit-body verb resolves). Single-ticket scope boundary recorded in the skill: sweep/reconciliation passes stay consumer territory.
6
+ - `shape-ticket`: the batched write may include one optional gated Reporter-note comment per approved issue (overflow of demoted Idea material; verbatim at the same single confirmation gate; missing post-comment verb degrades to manual posting, never silently dropped). Roast dispatch failure now retries once with fresh artifacts; a second failure is surfaced inline at the gate (`roast unavailable (dispatch failed twice: <reason>)`) instead of a silent note.
7
+ - README: both skills' contracts synced (slot docs, five-verb custom-tracker contract incl. `post comment`).
8
+
3
9
  ## v4.12.0 - 2026-08-18
4
10
 
5
11
  - New skill: `check-delivery` - explicit-only post-merge detective control: proves an issue actually shipped (SHA-bound squash-aware default-branch landing, optional deploy-watch + delivery-target check, per-AC evidence with a 6-verdict table and reviewer script) before its tracker status advances; never writes a terminal state; single human-gated batched write with `Delivered: <sha>` marker idempotency; generic across `gh`/`linearis` with a 7-slot `## Delivery` overrides contract so consumer closeout prompts reduce to an overrides block plus a one-line wrapper.
package/README.md CHANGED
@@ -35,7 +35,7 @@ pi-gauntlet's only hard dependency is pi-cohort - every gate that dispatches a r
35
35
 
36
36
  Concretely, one change through the gauntlet:
37
37
 
38
- 0. *(Optional)* Before there's even a spec, `/skill:shape-ticket` can create or repair a single tracker issue - shaping a raw ask into a Context/Problem/Idea/Acceptance Criteria ticket, gated by an AC integrity check, a cheap council roast, and one human-confirmed write. It's a tool, not a phase: no worktree, no plan/phase tracker, runs from any repo state. It never activates on its own (`disable-model-invocation: true`) - invoke it explicitly.
38
+ 0. *(Optional)* Before there's even a spec, `/skill:shape-ticket` can create or repair a single tracker issue - shaping a raw ask into a Context/Problem/Idea/Acceptance Criteria ticket, gated by an AC integrity check, a cheap council roast, and one human-confirmed write that may include one optional gated Reporter-note comment. A failed roast is retried once, then surfaced inline at the gate if it fails again. It's a tool, not a phase: no worktree, no plan/phase tracker, runs from any repo state. It never activates on its own (`disable-model-invocation: true`) - invoke it explicitly.
39
39
  1. You describe the change. **`brainstorming`** sets up an isolated worktree, explores the codebase, and turns your description into a written spec. A multi-model critique runs on it automatically. If the spec replaces a known prior spec, brainstorming marks the predecessor with a `> **Superseded by:**` banner under its title (default format, syntax overridable via `.pi/gauntlet-overrides.md`; event-driven only — gauntlet never sweeps historical specs). **You read and approve the spec - human gate 1.** No implementation code exists yet.
40
40
  2. **`writing-plans`** decomposes the approved spec into atomic, independently-verifiable tasks, grouped into parallel waves where they don't touch the same files.
41
41
  3. **`subagent-driven-development`** executes the plan one task at a time, each in a fresh subagent, behind spec-compliance review then code-quality review. TDD-locked: red, green, refactor.
@@ -144,7 +144,7 @@ Section headers should match skill names (`## verification-before-completion`) o
144
144
 
145
145
  **Discovery ladder:** skills check three locations, in order, and use the first one found - never merged: `.pi/gauntlet-overrides.md`, then `<repo root>/gauntlet-overrides.md`, then `<repo root>/doc/gauntlet-overrides.md` (`<repo root>` = `git rev-parse --show-toplevel`, or the current directory outside a repo). Pick one location per repo.
146
146
 
147
- **`## Issue tracker` section:** `shape-ticket` resolves tracker access through a capability ladder, and this is its first rung - it overrides the zero-config `gh` (GitHub) / `linearis` (Linear) defaults for any other tracker. Name the CLI's read, search, create, and update commands explicitly. For a Jira CLI, for example:
147
+ **`## Issue tracker` section:** `shape-ticket` resolves tracker access through a capability ladder, and this is its first rung - it overrides the zero-config `gh` (GitHub) / `linearis` (Linear) defaults for any other tracker. Name the CLI's read, search, create, update, and post comment commands explicitly. For a Jira CLI, for example:
148
148
 
149
149
  ```markdown
150
150
  ## Issue tracker
@@ -155,9 +155,10 @@ Use the `jira` CLI (authenticated via `jira login`), not `gh` or `linearis`.
155
155
  - search (dup/reversal check): `jira issue search --jql "project = ABC AND text ~ '<query>'"`
156
156
  - create: `jira issue create --project ABC --type Task --summary "<title>" --description "<body>"`
157
157
  - update: `jira issue edit ABC-123 --summary "<title>" --description "<body>"`
158
+ - post comment (Reporter note only): `jira issue comment ABC-123 --body "<text>"`
158
159
  ```
159
160
 
160
- **`## Delivery` section:** `check-delivery` resolves its overrides through the same discovery ladder. Defaults are pessimistic where it matters: an unset `target state` keeps the write comment-only; unset `deploy watch`/`delivery target` skip stage 2 (reported, never silently passed); `browser evidence` defaults to never. The remaining slots have working defaults shown below:
161
+ **`## Delivery` section:** `check-delivery` resolves its overrides through the same discovery ladder. Defaults are pessimistic where it matters: an unset `target state` keeps the write comment-only; unset `deploy watch`/`delivery target` skip stage 2 (reported, never silently passed); `browser evidence` defaults to never. `check-delivery` is single-ticket by design - sweep/reconciliation passes over many tickets stay consumer territory, invoking the skill once per ticket. The remaining slots have working defaults shown below:
161
162
 
162
163
  | Slot | Meaning | Default (unset) |
163
164
  |---|---|---|
@@ -168,6 +169,17 @@ Use the `jira` CLI (authenticated via `jira login`), not `gh` or `linearis`.
168
169
  | `browser evidence` | When/how to capture UI evidence (requires a browser tool) | never |
169
170
  | `ref convention` | How commits/PRs reference tickets (e.g. `(ref ABC-123)`) | tracker-native forms (`#N`, `Fixes #N`, bare `ABC-123`) |
170
171
  | `AC location` | Where ACs live if not the ticket body | ticket body |
172
+ | `synthesized AC gaps` | `block` or `soft` - whether an unmet synthesized AC produces a blocking `unexplained gap` or a non-blocking proposal | `soft` |
173
+ | `descope edits` | `strikethrough` - on gate approval, strike ratified `proposed descope` AC lines in the ticket body | none - no body edits ever |
174
+
175
+ Malformed slot values fail safe, with one warning per invocation naming the
176
+ bad value: `synthesized AC gaps` treats anything other than `block`/`soft`
177
+ as `soft`; `descope edits` treats anything other than `strikethrough` as
178
+ unset (no body edits). `descope edits` also requires a resolved edit-body
179
+ write verb: when the slot is active and the approval ratifies a `proposed
180
+ descope` but no edit-body verb resolves, the whole batched write (body
181
+ edit, evidence comment, status advance) degrades to manual - none
182
+ auto-posted.
171
183
 
172
184
  ```markdown
173
185
  ## Delivery
@@ -176,6 +188,8 @@ Use the `jira` CLI (authenticated via `jira login`), not `gh` or `linearis`.
176
188
  - delivery target: curl -fsS https://staging.example.com/version | grep <sha>
177
189
  - timeout: 15m
178
190
  - ref convention: (ref ABC-123)
191
+ - synthesized AC gaps: block
192
+ - descope edits: strikethrough
179
193
  ```
180
194
 
181
195
  ## REVIEW.md convention
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "pi-gauntlet",
3
- "version": "4.12.0",
3
+ "version": "4.12.1",
4
4
  "description": "Opinionated, gated workflow skills, subagent personas, and runtime extensions for the pi coding agent.",
5
5
  "author": "Jacek Juraszek",
6
6
  "type": "module",
@@ -15,14 +15,16 @@ disable-model-invocation: true
15
15
  | Comments amend/contradict the body's ACs | pause for operator resolution, then proceed - never silently pick a reading |
16
16
  | Zero ACs after extraction and synthesis | STOP - "cannot verify a ticket that asserts nothing" |
17
17
  | Genuine open deliverable PR found | STOP - "work still in flight" |
18
- | Same shipped SHA already recorded (marker + target state reached) | "already recorded" - no write |
18
+ | Same shipped SHA already recorded (marker + target state reached) | "already recorded" - no write (body-only descope repair excepted - see stage 0) |
19
19
  | Deliverable set ambiguous, or not on default branch | STOP - abort, no write |
20
20
  | Delivery target configured but unreachable / times out / can't bind to the SHA | STOP - abort, no write |
21
21
  | Any AC verdict is `unexplained gap` | Failure path - no delivery write; findings comment offered, gated |
22
22
  | All ACs clear (incl. proposals, non-observable, unverified-no-target) | One confirmation gate, then one batched write |
23
23
  | No delivery target configured | Stage 2 reported skipped - never silently passed |
24
24
  | No target state configured | Comment only - never guesses a workflow state |
25
- | Missing write capability | Full verification + both write halves emitted for manual execution |
25
+ | Missing write capability | Full verification + every write half that exists this run emitted for manual execution |
26
+ | Unmet synthesized AC | Non-blocking proposal under `synthesized AC gaps: soft` (default); same verdict matrix as authored ACs under `block` |
27
+ | Ratified `proposed descope` + `descope edits: strikethrough` | Body edit joins the batched write: body -> comment -> status |
26
28
 
27
29
  ## Overview
28
30
 
@@ -52,6 +54,17 @@ Explicit invocation only (`/skill:check-delivery <ticket-ref>`), read-only
52
54
  against the repository (no builds, no branch/tag/worktree mutation) plus at
53
55
  most one batched tracker write, runs from wherever invoked, no worktree.
54
56
 
57
+ ## Scope boundary
58
+
59
+ Single-ticket by design: the pipeline's depth (repo-identity preflight,
60
+ stage-1 landed-commit resolution, per-AC evidence binding, one human gate
61
+ with pre-write re-fetch) does not loop soundly - N tickets means N gates,
62
+ or a batch gate that dilutes per-ticket consent. Sweep passes (bucketing
63
+ open tickets, orphan scans for merged-but-unreferenced work) are
64
+ portfolio triage - a different control, inherently project-flavored - and
65
+ stay consumer territory. A consumer sweep may invoke this skill per
66
+ ticket as its verification step.
67
+
55
68
  ## Hard constraint
56
69
 
57
70
  Input is exactly one tracker ref (`ABC-123`, `#N`, `owner/repo#N`, or a
@@ -77,10 +90,14 @@ Resolved in order:
77
90
  4. Ask the user.
78
91
 
79
92
  Missing **read** capability = STOP. Missing **write** capability degrades
80
- gracefully: run the full verification, then emit **both halves** of the
81
- batched write for manual execution - the evidence-comment text, and, when a
82
- target state is configured, the exact status-advance command - reporting the
83
- advance as not performed.
93
+ gracefully on ordinary runs: run the full verification, then emit every
94
+ write half that exists this run for manual execution - the
95
+ evidence-comment text, and, when a target state is configured, the exact
96
+ status-advance command - reporting the advance as not performed. When
97
+ `descope edits` is active and the approval ratifies a `proposed descope`
98
+ but no edit-body verb resolves, the **whole** batched write degrades to
99
+ manual instead: body edit, evidence comment, and status advance (when
100
+ configured) all emitted for manual execution, none auto-posted.
84
101
 
85
102
  **Zero-config verb table** (overrides replace it):
86
103
 
@@ -89,6 +106,7 @@ advance as not performed.
89
106
  | read issue + comments | `gh issue view <n> --json title,body,comments` | `linearis issues read <id> --with-comments` |
90
107
  | post comment | `gh issue comment <n> --body ...` | `linearis issues discuss <id> --body ...` |
91
108
  | update state | override-defined only (never invented labels/columns) | `linearis issues update <id> --status <name>` |
109
+ | edit body (only `descope edits`) | `gh issue edit <n> --body ...` | `linearis issues update <id> --description ...` |
92
110
 
93
111
  ## Verification pipeline
94
112
 
@@ -107,9 +125,14 @@ current tracker status first: if it is already in a terminal/done state,
107
125
  report that and stop cleanly - no write; a terminal ticket is never
108
126
  downgraded to the configured non-terminal target state. Extract ACs
109
127
  from the AC section; if none exists, synthesize candidate ACs from the body,
110
- label them synthesized, and **cap their blocking power** - a synthesized AC
111
- never produces a blocking `unexplained gap`; unmet ones surface as
112
- non-blocking proposals at the gate. If a comment amends or contradicts a
128
+ label them synthesized. Their blocking power follows the `synthesized AC
129
+ gaps` slot: under `soft` (the default) a synthesized AC never produces a
130
+ blocking `unexplained gap` - unmet ones surface as non-blocking proposals
131
+ at the gate; under `block` the cap is removed - synthesized ACs run the
132
+ same stage 3 verdict matrix as authored ACs, so an unmet one with no
133
+ sanctioned explanation is a blocking `unexplained gap` (`allowed gap` and
134
+ `proposed descope` remain available outcomes exactly as for authored ACs).
135
+ If a comment amends or contradicts a
113
136
  body AC, surface the conflict to the operator and get an explicit
114
137
  resolution before proceeding - never silently pick a reading. If
115
138
  extraction and synthesis together yield zero candidate ACs, STOP:
@@ -121,6 +144,13 @@ configured) was already reached -> report "already recorded" and stop
121
144
  cleanly - success, no write. If the marker exists but the target state
122
145
  was not reached, skip the duplicate comment but still offer the status
123
146
  write (comment-landed/status-failed repair, per Idempotency below).
147
+ Exception when `descope edits: strikethrough` is configured: if a prior
148
+ run's evidence comment records a `proposed descope` whose matching AC line
149
+ in the body is still unstruck, the run is **not** "already recorded" - it
150
+ short-circuits to a gated body-only repair: the strike is presented at the
151
+ confirmation gate, resolving only the shipped SHA already recorded in the
152
+ marker (no fresh stage 1-3 re-verification); on approval, only the body
153
+ edit executes - no duplicate comment, no status advance.
124
154
 
125
155
  **Stage 1 - Merge landed.** One ordered algorithm, not a toolbox:
126
156
 
@@ -212,7 +242,10 @@ explicit yes-gate as the success path. Never posted unprompted.
212
242
  All-clear path -> **one confirmation gate**: present the shipped SHA,
213
243
  deliverable set, stage results (including any skip), the per-AC verdict
214
244
  table with evidence, the reviewer script, and the exact write about to
215
- happen. On approval, one batched write:
245
+ happen. On approval, one batched write. The numbered steps below are the
246
+ ordinary-run shape; when a ratified descope strike is in play, the
247
+ body-edit half precedes step 1 - see the `descope edits` paragraph below
248
+ for its mechanics, not repeated here:
216
249
 
217
250
  1. **Evidence comment** - marker line `Delivered: <sha>` as the first line,
218
251
  the deliverable set (PR links), stage 2 outcome (or "skipped: no
@@ -224,13 +257,53 @@ happen. On approval, one batched write:
224
257
  state, never invents a label.
225
258
 
226
259
  Comment first, status last, so a partial failure leaves evidence without a
227
- misleading state. Before writing, re-fetch the ticket: if ACs or status
228
- changed since gather, re-present the delta instead of writing. Declining
229
- the gate = no write, report stays in-session.
260
+ misleading state - this is the stated order for ordinary runs. Before
261
+ writing, re-fetch the ticket: if ACs or status changed since gather,
262
+ re-present the delta instead of writing. Declining the gate = no write,
263
+ report stays in-session.
264
+
265
+ When `descope edits: strikethrough` is configured and the approval
266
+ ratifies one or more `proposed descope` ACs, the batched write gains a
267
+ body-edit half, ordered **body edit -> evidence comment -> status
268
+ advance** - a partial failure never leaves a status advanced against a
269
+ body still advertising a descoped AC. A failed body-edit half aborts the
270
+ remaining halves outright: the comment and status advance do not run. Any
271
+ partial failure reports exactly which halves landed and which did not.
272
+ The edit strikes exactly the ratified AC lines and nothing else: the AC's
273
+ list item is preserved, its text struck, and a one-line reason appended -
274
+ `- [ ] ~~<AC text>~~ - descoped: <one-line reason>`. The checkbox is
275
+ rendered exactly as found (`- [x]` stays `- [x]`, `- [ ]` stays `- [ ]`) -
276
+ the edit never flips checked state. The reason is one sentence drafted
277
+ from the verdict's evidence, never invented.
278
+
279
+ Strike-target identity: the target is the AC-section list item whose
280
+ normalized text equals the verdict's AC text - normalize by stripping the
281
+ list marker and checkbox, collapsing internal whitespace, and comparing
282
+ the remaining text case-insensitively. When `AC location` is not
283
+ the ticket body, or no unique matching list item exists (synthesized,
284
+ prose, duplicate, or multi-line ACs), the strike is skipped for that AC,
285
+ reported as skipped at the gate, and the evidence comment carries the
286
+ descope record alone. A line already containing `~~` and `- descoped:`
287
+ counts as struck and is skipped.
288
+
289
+ Both zero-config edit verbs replace the whole body, so the strike is
290
+ applied as a surgical patch against the freshly re-fetched body at write
291
+ time - never by replaying the gather-time snapshot. If the target lines
292
+ moved or changed, re-present the delta instead of writing.
293
+
294
+ The exact before/after of the struck lines is presented at the same
295
+ single confirmation gate as the comment and status - one approval covers
296
+ all halves, including every proposed strike; there is no per-strike
297
+ subset selection, so objecting to one strike declines the whole gate this
298
+ round. Descope edits occur only on the all-clear batched write - the
299
+ failure path writes no body edit.
230
300
 
231
301
  ## Idempotency and concurrency
232
302
 
233
- Append-only, at-least-once. Same shipped SHA already marked -> skip the
303
+ Append-only, at-least-once for comments - a comment is never edited once
304
+ posted. The ratified-descope body strike is the one sanctioned in-place
305
+ body edit; it does not change this comment guarantee. Same shipped SHA
306
+ already marked -> skip the
234
307
  duplicate comment, but still offer the status write if the configured
235
308
  target state was not reached on the prior run (comment-landed /
236
309
  status-failed repair). A newer shipped SHA -> a fresh comment, never an
@@ -252,6 +325,8 @@ the newer SHA.
252
325
  | `browser evidence` | When/how to capture UI evidence (requires a browser tool) | never |
253
326
  | `ref convention` | How commits/PRs reference tickets (e.g. `(ref ABC-123)`) | tracker-native forms (`#N`, `Fixes #N`, bare `ABC-123`) |
254
327
  | `AC location` | Where ACs live if not the ticket body | ticket body |
328
+ | `synthesized AC gaps` | `block` or `soft` - whether an unmet synthesized AC produces a blocking `unexplained gap` or a non-blocking proposal | `soft` |
329
+ | `descope edits` | `strikethrough` - on gate approval, strike ratified `proposed descope` AC lines in the ticket body | none - no body edits ever |
255
330
 
256
331
  Worked example:
257
332
 
@@ -270,6 +345,11 @@ contract: a consumer's closeout prompt reduces to a `## Delivery` block plus
270
345
  a one-line wrapper invoking this skill. Worktree cleanup is out of scope -
271
346
  that belongs to `finishing-a-development-branch`.
272
347
 
348
+ Malformed slot values fail safe, with one warning per invocation naming the
349
+ bad value: `synthesized AC gaps` treats anything other than `block`/`soft`
350
+ as `soft`; `descope edits` treats anything other than `strikethrough` as
351
+ unset (no body edits).
352
+
273
353
  ## Rationalization table
274
354
 
275
355
  | Excuse | Reality |
@@ -280,6 +360,7 @@ that belongs to `finishing-a-development-branch`.
280
360
  | "No target configured, so delivery passed" | Unconfigured is a reported **skip**, never a silent pass |
281
361
  | "The ticket says done in a comment" | Ticket narrative is not evidence; only SHA-pinned code or target observations count |
282
362
  | "Just move it to Done, the human can reopen" | Never a terminal status - acceptance is the human's move, not this skill's |
363
+ | "The AC was only synthesized, so the gap can't block" | Under `synthesized AC gaps: block`, a synthesized AC runs the same verdict matrix as an authored one - an unexplained gap blocks |
283
364
 
284
365
  ## Red flags - STOP
285
366
 
@@ -298,6 +379,9 @@ that belongs to `finishing-a-development-branch`.
298
379
  - Silently picking a reading when a comment amends or contradicts a body AC
299
380
  - Continuing verification with zero candidate ACs
300
381
  - Advancing past a genuine open deliverable PR
382
+ - Striking an AC line the gate approval did not ratify as `proposed descope`
383
+ - Applying a body edit by replaying the gather-time snapshot instead of
384
+ patching the re-fetched body
301
385
 
302
386
  ## Project overrides
303
387
 
@@ -13,7 +13,7 @@ disable-model-invocation: true
13
13
  | Free text / vague ask, no ticket ref | Create mode: gather -> dup-check -> draft -> gates -> roast -> confirm -> write (9-step pipeline below) |
14
14
  | Issue ref (`#N`, `ABC-123`, URL) | Repair mode: fetch full ticket + 1-hop links -> diff old->new -> gates -> roast -> confirm -> re-fetch and re-diff before write (9-step pipeline below) |
15
15
  | Ref + extra text | Repair mode, extra text folded into gather |
16
- | Ticket already conforms + metadata clean | No-op: report and stop, no gate, no write |
16
+ | Ticket already conforms + metadata clean + no Reporter note proposed | No-op: report and stop, no gate, no write |
17
17
  | AC is wishful/tautological | Hard stop for the whole run - no write until fixed or split to discovery |
18
18
  | AC is unspecified-but-binding or needs external input | Ticket filed, parked in not-ready state, blocker named |
19
19
  | Independent shippable slices detected | Split proposed at the gate, one approval, per-issue subset selection |
@@ -25,7 +25,7 @@ Every path that writes ends at the **same single confirmation gate** - no write
25
25
 
26
26
  One process, two entry points: **create** a new tracker issue from a prompt, or **repair** an existing one by re-fetching it and proposing a full replacement. Repair is never a silent patch - it is always shown old->new, links and tracker fields preserved. Running this skill on any ticket trues it up; repeated use is a self-healing backlog pass.
27
27
 
28
- **Core principle:** the ticket carries **what and why, never how**. A prescribed solution in the source material is demoted to the **Idea** section as an attributed sketch ("reporter's proposed approach: ...") - never the Problem, never an Acceptance Criterion, never a tracker comment.
28
+ **Core principle:** the ticket carries **what and why, never how**. A prescribed solution in the source material is demoted to the **Idea** section as an attributed sketch ("reporter's proposed approach: ...") - never the Problem, never an Acceptance Criterion, never an *ungated* tracker comment - the one gated Reporter-note comment (step 4) is the sole exception.
29
29
 
30
30
  **Violating the letter of the rules is violating the spirit of the rules.** "The gate basically happened" is not the gate happening.
31
31
 
@@ -41,7 +41,7 @@ It is a tool, not a phase: no `plan_tracker`, no `phase_tracker`, no worktree re
41
41
  - **Free text or no argument** -> **create mode**, from the argument plus surrounding conversation.
42
42
  - **Ref + extra text** -> repair mode, with the text folded into gather.
43
43
  - **Unreadable ref** -> abort repair, offer create mode from any accompanying text. Never guess ticket content from a ref you cannot fetch.
44
- - **Out of scope**: read-only asks (search, status lookup) and administrative writes (status transitions, posting comments) - use the tracker CLI directly.
44
+ - **Out of scope**: read-only asks (search, status lookup) and administrative writes (status transitions, standalone comment posts) - use the tracker CLI directly; the gated Reporter-note comment inside a create/repair write is the sole comment exception.
45
45
 
46
46
  ## The pipeline
47
47
 
@@ -67,13 +67,27 @@ One question at a time, only when intent is unclear or no AC is derivable. Never
67
67
 
68
68
  Full replacement body: `Context` / `Problem` / `Idea` / `Acceptance Criteria`, plus optional `Out of scope / Follow-up` and `Post-deployment housekeeping`. Apply the wording rules (below). Preserve links and tracker fields.
69
69
 
70
+ The draft may propose **at most one comment per approved issue**, e.g.
71
+ `Reporter note: <demoted detail>`. Overflow test: the Idea section keeps
72
+ exactly one attributed sketch line; any demoted material left over after
73
+ that line is overflow, and the overflow is the comment body (long pasted
74
+ code, verbose repro trails, a full proposed diff are the typical shapes).
75
+ No overflow, no comment - unless the user asks in-session, in which case
76
+ the user-named content is the comment body and stands in for overflow.
77
+ Default off: overrides cannot force a comment absent overflow or an
78
+ in-session ask. In repair mode an existing `Reporter note:` comment
79
+ satisfies the overflow (skip), unless the demoted detail materially changed, in which case a new comment
80
+ is proposed - comments are never edited. In a split, the comment attaches
81
+ only to the issue that retained the demoted Idea material; if none does,
82
+ it is omitted.
83
+
70
84
  ### 5 - Deterministic gates
71
85
 
72
86
  Before any subagent dispatch, inline and cheap: AC integrity gate, evidence gate, metadata audit, split detection (all below).
73
87
 
74
88
  ### 6 - No-op check
75
89
 
76
- If the body already conforms AND the metadata audit is clean: report "conforms, no changes proposed" and stop. No write, no confirmation prompt, no roast. A conforming ticket never pays for a dispatch.
90
+ If the body already conforms AND the metadata audit is clean AND no Reporter note is proposed: report "conforms, no changes proposed" and stop. No write, no confirmation prompt, no roast. A conforming ticket never pays for a dispatch - a conforming body with pending overflow still reaches the gate.
77
91
 
78
92
  ### 7 - Roast
79
93
 
@@ -89,12 +103,13 @@ Present, per proposed issue:
89
103
  - Evidence list.
90
104
  - Roast dispositions: applied / surfaced-ambiguous.
91
105
  - Split proposal, if any.
106
+ - Proposed Reporter-note comment, verbatim, if any - one approval covers title + body + metadata + comment; no affirmative on the exact text = no comment.
92
107
 
93
108
  Number the options. A split offers per-issue subset selection, e.g. "approve 1,3; decline 2". **No affirmative answer on the exact presented diff = no write.**
94
109
 
95
110
  ### 9 - Write
96
111
 
97
- Immediately before mutation - after approval, not at gate-open. Repair mode: re-fetch the ticket and diff against the exact snapshot the user approved (use tracker version/ETag preconditions where the CLI exposes them); any mismatch (human edited mid-review) loops back to step 8 with the delta. Create mode: no ticket exists yet, so there is nothing to re-fetch or diff - write the approved body as-new. Then one batched write per approved issue; a split is N gated writes under the one approval, honoring subset selection. Mid-batch failure: report exactly what landed; the remaining changeset is preserved for retry.
112
+ Immediately before mutation - after approval, not at gate-open. Repair mode: re-fetch the ticket and diff against the exact snapshot the user approved (use tracker version/ETag preconditions where the CLI exposes them); any mismatch (human edited mid-review) loops back to step 8 with the delta. Create mode: no ticket exists yet, so there is nothing to re-fetch or diff - write the approved body as-new. Then one batched write per approved issue, body first, then the approved Reporter-note comment if any; a split is N gated writes under the one approval, honoring subset selection. Mid-batch failure: report exactly what landed; the remaining changeset is preserved for retry.
98
113
 
99
114
  ## AC integrity gate
100
115
 
@@ -151,9 +166,20 @@ Inline council dispatch, reusing spec-council config and personas - **not** `/sk
151
166
  2. **Dispatch shape**, mirroring `/skill:roasting-the-spec`: write the draft body and the source snapshot (original ticket + comments, or the create-mode inputs) to absolute temp files under `mktemp -d`; delimit untrusted snapshots as data. Dispatch members with `cwd` = repo root, absolute `output` paths per member, run-level `control: { needsAttentionAfterMs: 600000 }` (sits beside `tasks`, not inside each task). Give the chair the member files via `reads`. Member task text: *the draft at `<path>` is the artifact under review; this ticket brief supersedes your spec-axis template - emit the same findings format against the draft; do not edit any file.*
152
167
  3. **Effort: cheap by default.** Append a `:low` thinking suffix to each member's model string at dispatch (this beats the persona's frontmatter `xhigh` pin). Same for the chair: a configured chair string gets any existing suffix replaced with `:low`; an unconfigured chair is dispatched as the parent's model with `:low` appended. The `worker` fallback carries no thinking pin - it runs at the preset's default. **Full-roast escape:** the user may request a full roast, dispatching all model strings bare/as-configured, restoring the xhigh pins.
153
168
  4. **Brief covers two axes**, absorbing the fidelity-review role without a new persona: *fidelity* - compare draft against source intent (original ticket + comments in repair; prompt + answers in create), flag `lost` / `added` / `gap`; and *quality* - problem framing, AC integrity beyond the deterministic gate, scope, wording.
154
- 5. Disposition: unambiguous concrete fixes applied to the draft (one re-pass max); ambiguous findings surfaced at the confirmation gate. Roast edits affect the body draft pre-write only, never a tracker comment, and re-run the deterministic gates (pipeline step 5).
169
+ 5. Disposition: unambiguous concrete fixes applied to the draft (one re-pass max); ambiguous findings surfaced at the confirmation gate. Roast edits affect the body draft pre-write only, never posted as a tracker comment, and re-run the deterministic gates (pipeline step 5).
155
170
  6. **Runtime conditional (the one allowed):** on a harness with no `gauntlet_setting`/`subagent()` (e.g. Claude Code), dispatch fresh general-purpose subagents via that harness's native facility at low effort, with the same two-axis brief and temp-file artifacts.
156
- 7. Roast dispatch failure -> proceed to the confirmation gate with a "roast unavailable" note (the deterministic gates already ran; the human still adjudicates). **Roast failure never blocks the run.**
171
+ 7. **Roast failure and retry.** A roast has failed when the dispatch
172
+ errored, or the artifact the parent reads - the chair synthesis
173
+ (council path) or the worker output (worker path) - is missing, empty,
174
+ or not findings-shaped; partial member loss with a usable chair
175
+ synthesis is success, not failure. On failure, retry once: re-run the
176
+ same full configured dispatch with fresh temp artifacts. If the retry
177
+ also fails, proceed to the confirmation gate with the failure rendered
178
+ inline in the gate message itself: `roast unavailable (dispatch failed
179
+ twice: <reason>)` - the human approves knowing review didn't run. The
180
+ retry is a dispatch retry only - it never grants a second draft-edit
181
+ re-pass (the one-re-pass limit is unchanged). **Roast failure never
182
+ blocks the run.**
157
183
 
158
184
  ## Tracker abstraction and capability ladder
159
185
 
@@ -174,10 +200,11 @@ Auth failure at detection time makes that rung dead; continue down the ladder (u
174
200
  | search (dup/reversal) | `gh search issues` / `gh issue list --search` (incl. `state:closed`) | `linearis issues search <query>` |
175
201
  | create | `gh issue create --title --body [--label]` | `linearis issues create <title> --description ... --team <team>` |
176
202
  | update | `gh issue edit <n> --title --body [--add-label/--remove-label]` | `linearis issues update <id> --title ... --description ...` |
203
+ | post comment (Reporter note only) | `gh issue comment <n> --body ...` | `linearis issues discuss <id> --body ...` |
177
204
 
178
205
  linearis create requires `--team <team>`; it resolves like any other metadata field - named by repo docs/overrides, else asked - never invented.
179
206
 
180
- **Tracker-agnostic contract** required of whatever resolves: read the full ticket incl. comments; write title + body + metadata; search (dup/reversal check); tracker-native reference form for links. Field names, states, and taxonomies come from steps 1-2 of the ladder, never hardcoded in this skill.
207
+ **Tracker-agnostic contract** required of whatever resolves: read the full ticket incl. comments; write title + body + metadata; post a comment; search (dup/reversal check); tracker-native reference form for links. Field names, states, and taxonomies come from steps 1-2 of the ladder, never hardcoded in this skill. If an approved Reporter-note comment has no resolvable post-comment verb, the body write still proceeds; the comment text is emitted for manual posting and reported as not performed - never silently dropped.
181
208
 
182
209
  **States:** generalized routing - ready (gates pass), not-ready/triage-equivalent (parked, blocker named). **Zero-config GitHub park fallback:** GitHub Issues have no native not-ready state, and this skill never invents labels - so parking writes no state/label; instead the blocker is recorded in the body (a `Blocked on: <missing value / external input>` line under the ACs), and the run report states the ticket is parked-by-convention. A repo-documented triage/not-ready label or status overrides this. Never auto-assign to an active cycle/sprint unless asked.
183
210
 
@@ -245,11 +272,11 @@ Read this when applying the AC integrity gate (drafting, repairing, or adjudicat
245
272
  - Unreadable ticket -> abort repair, offer create mode.
246
273
  - Ticket changed between gather and write -> re-fetch, diff, re-present, re-ask.
247
274
  - Write fails mid-batch -> report exactly what landed; remaining changeset preserved for retry.
248
- - Conforming ticket -> no-op verdict (requires metadata audit also clean), stop.
275
+ - Conforming ticket -> no-op verdict (requires metadata audit also clean and no Reporter note proposed), stop.
249
276
  - Headless run -> stops at the confirmation gate.
250
277
  - Ref with no fetch path -> ask; never guess.
251
278
  - Split declined -> single ticket with phased AC groups.
252
- - Roast dispatch failure -> gate with "roast unavailable" note.
279
+ - Roast failure -> retry once; second failure -> gate with `roast unavailable (dispatch failed twice: <reason>)` inline.
253
280
 
254
281
  ## Red flags - STOP
255
282