pi-gauntlet 7.43.0 → 7.43.1

package/CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## v7.43.1 - 2026-10-30
+
+### Fixed
+
+- Require `Do not edit any file.` in read-only `Amend-prepare:` task text so pi-cohort's completion guard accepts preparation that mentions implementation fixes without making edits.
+
 ## v7.43.0 - 2026-10-30
 
 ### Added

package/agents/plan-writer.md

@@ -32,7 +32,7 @@ Route an explicit implement-phase `Amend-prepare:` or `Amend-apply:` block here
 
 ### Amend-prepare:
 
-Read the spec and existing plan, the supplied amendment surface, and the evidence in the block (including structured `concerns`/`question`, checker FAIL lines, or baseline rows). Classify under that surface's preparation and redraw rules. Preparation writes nothing: run no Baseline or checker and apply no edit. Return `{ items: [{ evidence, recommended: "accept" | "alt-<n>", location: "<spec section>", edit: string }], redraws: [{ location: "<spec section>", reason: string (max 300 characters) }] }`. Both `items` and `redraws` arrays are required, including when empty; redraw proposals appear only in `redraws`, never in `items`. Fail malformed preparation output. Require this parent gate: a nonempty `redraws` array holds the whole batch at the existing redraw gate before grant evaluation or applying any sibling item. Keep redraw discovery in structured output: the parent never opens the preparation report to discover redraws. Bound each `edit` to one paragraph; keep the supporting evidence verbatim and recommend the named choice rather than defaulting to accept. Leave consent decoding and the human gate to the parent.
+Read the spec and existing plan, the supplied amendment surface, and the evidence in the block (including structured `concerns`/`question`, checker FAIL lines, or baseline rows). Classify under that surface's preparation and redraw rules. Do not edit any file. Preparation writes nothing: run no Baseline or checker and apply no edit. Return `{ items: [{ evidence, recommended: "accept" | "alt-<n>", location: "<spec section>", edit: string }], redraws: [{ location: "<spec section>", reason: string (max 300 characters) }] }`. Both `items` and `redraws` arrays are required, including when empty; redraw proposals appear only in `redraws`, never in `items`. Fail malformed preparation output. Require this parent gate: a nonempty `redraws` array holds the whole batch at the existing redraw gate before grant evaluation or applying any sibling item. Keep redraw discovery in structured output: the parent never opens the preparation report to discover redraws. Bound each `edit` to one paragraph; keep the supporting evidence verbatim and recommend the named choice rather than defaulting to accept. Leave consent decoding and the human gate to the parent.
 
 ### Amend-apply:
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-gauntlet",
-  "version": "7.43.0",
+  "version": "7.43.1",
   "description": "Opinionated, gated workflow skills, subagent personas, and runtime extensions for the pi coding agent.",
   "author": "Jacek Juraszek",
   "type": "module",

package/skills/brainstorming/reference/amendment-surface.md

@@ -40,7 +40,7 @@ When the spec file is mid-batch (uncommitted amend edits), the consent edit ride
 
 ## 1. Prepare - never apply yet
 
-**Implement callers only, with a task plan:** delegate preparation to `plan-writer` in a one-step chain with the ordinary five absolute paths, this surface's absolute path, and an implement-only `Amend-prepare:` block carrying evidence already in context (checker FAIL lines, structured `concerns`/`question`, or baseline rows). Consume `{ items: [{ evidence, recommended: "accept" | "alt-<n>", location: "<spec section>", edit: string }], redraws: [{ location: "<spec section>", reason: string (max 300 characters) }] }`; keep supporting context in the saved report. Require both `items` and `redraws` arrays, including when empty; redraw proposals appear only in `redraws`, never in `items`. Fail malformed preparation output. The child reads spec and plan, writes nothing, and bounds each proposed edit to one paragraph. Enforce the redraw gate: a nonempty `redraws` array holds the whole batch before grant evaluation or applying any sibling item. Hold amend siblings for re-batching after the redraw resolves; the primary never opens the preparation report to discover redraws. Run the standing-grant predicate and Value decoding unchanged; without amend permission, take sections 2-4 and stop for the human's answer. Forward only resolved, authorized items to the apply route in section 5. Planning callers keep the ordinary preparation below. For ledger-engine (`loop-implementation`) callers, prepare through the ordinary path below without a `plan-writer` dispatch.
+**Implement callers only, with a task plan:** delegate preparation to `plan-writer` in a one-step chain with the ordinary five absolute paths, this surface's absolute path, and an implement-only `Amend-prepare:` block carrying evidence already in context (checker FAIL lines, structured `concerns`/`question`, or baseline rows). Consume `{ items: [{ evidence, recommended: "accept" | "alt-<n>", location: "<spec section>", edit: string }], redraws: [{ location: "<spec section>", reason: string (max 300 characters) }] }`; keep supporting context in the saved report. Require both `items` and `redraws` arrays, including when empty; redraw proposals appear only in `redraws`, never in `items`. Fail malformed preparation output. Include the literal sentence `Do not edit any file.` in the `Amend-prepare:` task text. The child reads spec and plan, writes nothing, and bounds each proposed edit to one paragraph. Enforce the redraw gate: a nonempty `redraws` array holds the whole batch before grant evaluation or applying any sibling item. Hold amend siblings for re-batching after the redraw resolves; the primary never opens the preparation report to discover redraws. Run the standing-grant predicate and Value decoding unchanged; without amend permission, take sections 2-4 and stop for the human's answer. Forward only resolved, authorized items to the apply route in section 5. Planning callers keep the ordinary preparation below. For ledger-engine (`loop-implementation`) callers, prepare through the ordinary path below without a `plan-writer` dispatch.
 
 Collect every amendment pending at this decision point (same spec-review round, same blocked wave, same conformance inventory) into one batch. Never wait for more; a later finding is a new batch. For each item hold, unapplied:
 

package/skills/subagent-driven-development/reference/implement-amendments.md

@@ -2,7 +2,7 @@
 
 Read [amendment-surface.md](../../brainstorming/reference/amendment-surface.md) for the existing gate and Standing grants. Apply this delegation only during implement; keep the planning caller unchanged. Use the one-step carrier and schemas in [dispatch-contract.md](dispatch-contract.md) for every child, with saved output, file-only, fresh context and foreground execution.
 
-1. Dispatch `plan-writer` with `Amend-prepare:`, the five absolute paths (worktree, approved spec, plan, plan skill and plan contract) and the evidence already in context: plan_check FAIL lines, structured concerns/question or measured baseline rows. Preparation writes nothing. Require `{ items: [{ evidence, recommended: "accept" | "alt-<n>", location: "<spec section>", edit: string }], redraws: [{ location: "<spec section>", reason: string (max 300 characters) }] }`; keep each edit one paragraph. Keep the existing menu spelling `alt-n` for a named alternative; encode the selected number as `alt-<n>` in JSON. Require both items and redraws arrays, including empty arrays; put redraws only in redraws, never items. Fail malformed preparation output.
+1. Dispatch `plan-writer` with `Amend-prepare:`, the five absolute paths (worktree, approved spec, plan, plan skill and plan contract) and the evidence already in context: plan_check FAIL lines, structured concerns/question or measured baseline rows. Include the literal sentence `Do not edit any file.` in the `Amend-prepare:` task text. Preparation writes nothing. Require `{ items: [{ evidence, recommended: "accept" | "alt-<n>", location: "<spec section>", edit: string }], redraws: [{ location: "<spec section>", reason: string (max 300 characters) }] }`; keep each edit one paragraph. Keep the existing menu spelling `alt-n` for a named alternative; encode the selected number as `alt-<n>` in JSON. Require both items and redraws arrays, including empty arrays; put redraws only in redraws, never items. Fail malformed preparation output.
 2. Inspect structured redraws first. A nonempty array holds the whole batch at the redraw gate before grant evaluation or applying any sibling item, for redraw-only and mixed batches alike. Never open the preparation report to discover redraws. With no redraws, delegate reading the current `Amend-grant:` and Value decoding through the answer/evidence carrier. Preserve the surface's grant predicate: malformed -> stop and quote; absent, none or no permission -> the existing human menu and escalation gate. Stop on changed problem statement or a component added, removed or re-bounded.
 3. With amend permission, apply the recommended choice without reviewer, menu or confirmation turns; pass granted items verbatim to `plan-writer` under `Amend-apply:` plus the existing `Amend:` entry and parent-supplied `In-flight:` paths from `status --porcelain`, including staged in-place repair deliverables. Preserve Baseline ownership, protected-path and dirty-baseline exits; delegate attribution reads and human wording instead of loading documents in the primary. Authorize only the named spec sections and plan regeneration, preserving unaffected task titles and wave positions. Before the first apply, require original task numbers, titles, spec anchors, and wave positions in the existing saved apply report; retain that original inventory on every return, including failures. Add no sidecar.
 4. Consume the unchanged apply result `{ amendedSections: string[], tasksAdded: number[], tasksAnchorChanged: number[], tasksRemoved: number[], passed: boolean, failLines?: string[] }`. On `passed: false`, retry once in a fresh child with failLines as the rule and `previousApplyReport` set to the first apply report path. Require the retry to read original inventory, apply granted edits idempotently without duplicates, and compute deltas against that original inventory rather than the already-mutated plan. Missing original inventory fails the retry. Escalate a second failure; never repeat granted edits blindly.