pi-gauntlet 8.1.6 → 8.1.7

package/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## v8.1.7 - 2026-11-02
+
+- The loop engine escalates a row to `escalationLoop.implModel` once its attempts reach `min(loopEngine.escalateAfter, effective allowance - 1)` instead of only on the last allowed attempt; `piGauntlet.loopEngine.escalateAfter` defaults to 3 (floor 1, non-integer values warn and fall back), so the default configuration still escalates attempt 4 while an allowance of 10 runs attempt 4 on `implModel` and attempts 5-10 on the worker. The threshold is held in driver memory from Entry or restore and never written to the ledger. `loop-implementer` reads its target row's `## Decisions` lines oldest first and honors failed-line guidance, with the dispatch payload unchanged. (#119)
+
 ## v8.1.6 - 2026-11-01
 
 ### Changed

package/README.md

@@ -39,7 +39,7 @@ Concretely, one change through the gauntlet:
 1. Opt in with `/skill:brainstorming` and describe the change. The command is the reliable discovery-and-entry path; explicit prose requesting brainstorming/the gauntlet also supplies consent when the skill is already loaded or an available instruction or route identifies it. An ordinary implementation request or an agent recommendation is not consent. A leading run of GitHub references (`#N`, `owner/repo#N`, or a `/pull/N` or `/issues/N` URL), separated by whitespace or commas, resolves each reference as a PR first: related open, same-repository, non-fork PRs on one base form one rework subject, including drafts. Admission runs in listed order and relatedness is checked before provisioning; the first retained PR is home, whose existing branch rebases onto the fetched PR base by default, then member commits replay onto it in listed order. The first intent word `merge-forward` opts out and keeps the merge path. An unresolved conflict after its scoped helper aborts that step and continues to the spec with the repair as Task 1. A single non-PR reference follows the ticket path. The first non-reference token starts intent text; mid-sentence references and other ticket/free-text subjects keep their existing paths. The combined code, PR-carried specs, claims, and review threads are the brainstorm input, with each PR's provenance retained; only home's bound ticket supplies acceptance criteria, while member tickets supply context. A single PR retains the same rework path without member replays or a close offer. The combined state is judged against constraints from the fetched current base HEAD, not the fork point or the PRs' proposed policy edits; see the [PR-subject contract](skills/brainstorming/reference/pr-subject.md) and [PR-head worktree owner](skills/using-git-worktrees/reference/pr-head.md). **`brainstorming`** sets up an isolated worktree (on the existing branch for PR rework), explores the codebase, and turns the subject into a written spec - when its recon finds a cited case that the ask is the wrong change (misdiagnosed, wrong-sized, already solved, a band-aid, or cutting across a sound pattern - including a repo convention that is itself debt) and can name the alternative, question one is a framing question (`as framed`, `pivot: <alternative>`, or `smaller or none`); otherwise it opens with one sentence naming what it checked, and every approach it proposes ends with a `Pattern:` line naming what it follows or cuts across; when the run starts from a ticket, the spec carries the ticket's acceptance criteria verbatim, each with a disposition (`in-scope`, `deviates:`, `deferred:`, `venue:`, `elsewhere:` for a row another repo's part delivers), scope cuts come only from your answer to a cut question and are listed at the gate, the conformance gate checks the in-scope ones, and `/skill:check-delivery` verifies `venue:` rows before the prod deploy. 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`; candidates come from brainstorming's scout recon, never a mechanical sweep). **You read and approve the spec - human gate 1.** Options 1/2/4/5 approve and pick an engine; option 6 approves the content only: it writes `**Engine:** deferred` under `**Amend-grant:** none`, pushes the branch, opens a draft PR carrying just the spec, prints the URL, and ends the flow - no plan, no loop, no handoff brief. For a coordinated spec, it first pushes every companion branch to origin, then opens one home draft PR; it creates no companion PRs. A later `brainstorming #N` reconstructs the recorded companions from their origin branches before re-presenting the implementation gate; the [publication and re-gate owner](skills/brainstorming/reference/spec-pr.md) defines all-member preflight, recovery, and cleanup. The branch stays; a gauntlet-owned worktree is removed, a host-owned checkout is reported and left. Option 6 is withheld on a PR subject (`Withheld: draft PR - #N already exists`) and when the branch's diff against the default branch is not spec-only. A later `brainstorming #N` on that PR classifies it from the diff alone: one added spec carrying the marker plus banner-only predecessor edits re-presents the gate with 1/2/4/5 (3 only when the spec commit carries a council audit) and skips gather, questionary, council, and scout; a spec-only diff without the marker prints `spec-only PR without the gate marker - running lint and council` and takes the normal brainstorm path with the carried spec as the draft; any other diff takes the rework path. Approval at that re-gate writes `**Engine:**`, `**Amend-grant:**`, and `**PR:** <owner/repo#N>` as a new commit on the PR branch and chains into planning or the loop as usual. Before approval, PR rework's sole write/run exception outside the spec directories permits only the base sync (rebase or merge), each member replay or merge, their conflict helpers' edits to the conflicted files, and their scoped conflict tests; other subjects have no implementation code yet.
 2. By default, **`writing-plans`** decomposes the approved spec into atomic, independently-verifiable tasks, grouped into parallel waves where they don't touch the same files. Experimental approval options 4/5 instead select **`loop-implementation`**: the plan phase is skipped and a stamped acceptance-criteria ledger replaces the task plan. Option 4 retains amendment review; option 5 grants auto-apply amends, with redraws still stopping. See [Loop engine operations](doc/configuration.md#loop-engine-operations).
 3. **`subagent-driven-development`** executes the plan in waves, with task implementers followed by one integrated `wave-reviewer` after the scoped test gate passes. The reviewer checks anchored spec clauses and code quality together; repairs stay on the current tree and pass the same gate before re-review. TDD-locked: red, green, refactor. Independent implementation, review, and council batches remain parallel, but their dispatches are foreground: the orchestrator waits for terminal results before accepting work or advancing a phase.
-The loop alternative to step 3 runs one fresh `loop-implementer` per seed or row iteration, without implement-phase reviewers. Each row starts with the shared allowance (default 4); approval replies such as `4; allowance 6` override it for one run. Under either loop approval option, the last allowed attempt escalates once per row on `escalationLoop.implModel` (the main-loop model when unset); one exit-verification repair per flow uses the same model. Exhaustion and stagnation stop for a human decision: `retry <n> | <hint>` adds one attempt to that row, while `rows +N` raises every row's allowance. Attempts never reset and there is no total iteration cap. Ledger refresh completes implement when every row is closed; verify step 1 runs the gate set: deduplicated (owning checkout, command) pairs from done rows' recorded checks, with ownership from the ledger. Gate output goes to logs; the driver keeps exit codes and paths, not test output. CI on push owns the full run.
+The loop alternative to step 3 runs one fresh `loop-implementer` per seed or row iteration, without implement-phase reviewers. Each row starts with the shared allowance (default 4); approval replies such as `4; allowance 6` override it for one run. Under either loop approval option, attempt `escalateAfter + 1` (default 4), clamped to the last allowed attempt, escalates once per row on `escalationLoop.implModel` (the main-loop model when unset); later attempts use the ordinary worker model, and one exit-verification repair per flow uses the same escalation model. Exhaustion and stagnation stop for a human decision: `retry <n> | <hint>` adds one attempt to that row, while `rows +N` raises every row's allowance. Attempts never reset and there is no total iteration cap. Ledger refresh completes implement when every row is closed; verify step 1 runs the gate set: deduplicated (owning checkout, command) pairs from done rows' recorded checks, with ownership from the ledger. Gate output goes to logs; the driver keeps exit codes and paths, not test output. CI on push owns the full run.
 
 4. **verify**: the parent first runs the plan's full verification command set for waves, or the ledger gate set for loop; only a passing result permits whole-diff code review, then the **conformance gate**. A review fix invalidates that result, so the parent reruns the same set before the next review or conformance gate. Loop conformance repairs and finish also use the gate set, never the ledger's full `verification:` command. When the overrides file declares a happy path for the touched paths (see [Project-specific overrides](#project-specific-overrides)), the parent runs it once here, between code review and the conformance gate, and the reviewer reads its transcript as runtime evidence - a hang or a failed request shows up in the audit with the transcript quoted - as a gap when an origin clause ties to it, otherwise as a `happy-path: failed - unattributable` line - never as a silent green. The conformance subagent reads the finished code and docs against your *original words* from step 1, not the plan, and reports per-requirement: delivered, partial, missing, drifted, or unauthorized. Unauthorized rows - shipped surface no human input asked for, whether it crept in or was laundered through the spec - follow their recommendation like every other row: a contained removal auto-runs, anything another requirement leans on is deferred with a plain-language "I'd cut it / I'd keep it" recommendation. Inside a brainstorming-entered flow this gate is machine-blocked from being skipped. Compatible executable recommendations auto-run through an isolated fix-and-re-audit loop with no prompt; anything still open surfaces as a numbered decision brief - one item per decision, the problem in plain words first, lettered options each with a one-line consequence, and `Recommended: <letter> - <reason>` or `No recommendation - pick one`. Reply with one line per item (`1. B`), or bare `1` to take every recommendation (no-recommendation items are re-asked by number); a current `CONFORMS` / no-concerns result goes straight to the branch options with no extra conformance sign-off.
 5. **`finishing-a-development-branch`**: PR, draft PR, squash, keep, or discard; PR rework's row 1 offers a lease push of the rebased home branch to the existing PR (`Base:` records in `merge:` form push non-force). A spec whose header carries `**PR:**` (approved at a spec-PR re-gate) and no `## Rework record` replaces the two create rows with `Push to PR #N and mark it ready for review` and `Push to PR #N, keep it a draft` (`Push to PR #N (already ready for review)` when the PR is already ready): both push without force after strip-and-seal, the first then runs `gh pr ready`, neither rewrites the PR body, and both are withheld when origin's branch head is no longer an ancestor of local HEAD. For coordinated specs, these [header-linked rows 1/2](skills/finishing-a-development-branch/reference/spec-pr.md#push-rows-12) deliver companions in recorded order before one home seal carrying every companion PR URL, then push home and apply its readiness choice. Row 1 makes companion drafts ready too; row 2 creates drafts but never converts an already-ready PR back to draft. Companion URLs appear in the shipped summary, companions first and home last, not in the unchanged home PR body; keep that summary for cross-repo review because successful home delivery removes receipts. A spec still carrying `**Engine:** deferred` stops finishing (and `gauntlet-resume`) with `spec approved for handoff only - run brainstorming #N` before any phase change, verification, or push. The PR-rework push appends a `## Rework` block naming absorbed PRs while retaining the original description bytes; the header-linked `**PR:**` push leaves the body untouched. Only after a successful rework push and home-description edit does one gated confirmation show the exact close comments and eligible member targets, linking home; declining or any other finish option leaves members open. Closing never deletes member branches, and finish posts no review-thread replies. Its `Before:` handle includes the full portable pre-rework SHA and the local `refs/gauntlet/pre-rework/pr-<N>` ref in the rework checkout. The [finishing owner](skills/finishing-a-development-branch/SKILL.md#pr-subject-row-1-push-to-the-pr-branch) defines the landing and body-update contract. Once a PR exists, run `/skill:gatekeep-pr <pr>` to verify it before merging - it judges the diff against the spec at the PR's head (the acceptance-criteria dispositions and Design you approved; the PR description when no spec applies) - rows the spec defers or deviates are settled, every other row needs its mechanism (code, tests, docs) - and against the rubric; whatever can be seen only after merge is left to step 6. **Human gate 2** - the only other decision you make.
@@ -617,6 +617,7 @@ The conformance gate's model, the spec council's roster, and the phase-tracker's
 | `closureReview.maxFixRounds` | phase-tracker | `5` | fix rounds before escalation - [detail](./doc/configuration.md#conformance-gate-model) |
 | `escalationLoop.implModel` | phase-tracker | unset (main loop) | execution escalation under either loop option; review escalation remains separate - [detail](./doc/configuration.md#escalation-loop) |
 | `loopEngine.maxIterationsPerRow` | phase-tracker | `4` (floor `1`) | fresh-ledger per-row allowance; run override on approval 4/5 - [detail](./doc/configuration.md#setting-and-command-resolution) |
+| `loopEngine.escalateAfter` | phase-tracker | `3` (floor `1`) | pre-dispatch threshold; escalated attempt index is value + 1, clamped to the last allowed attempt - [detail](./doc/configuration.md#setting-and-command-resolution) |
 | `phaseModels.plan` / `.implement` / `.verify` / `.ship` | phase-tracker | unset (no switch) | `provider/id[:level]` applied persistently at that phase's start - [detail](./doc/configuration.md#phase-models) |
 | `flowGuards.enforce` | phase-tracker | `true` | phase gates on/off - [detail](./doc/configuration.md#phase-tracker) |
 | `flowGuards.specDirs` | phase-tracker, plan-tracker; telemetry and spec-index consumers | `["doc/specs", "docs/specs"]` | where specs and sibling plans live - [detail](./doc/configuration.md#phase-tracker) |

package/agents/loop-implementer.md

@@ -28,7 +28,7 @@ Read additive inputs `Leg:`, `Rules:`, mapped original AC and, for companions, e
 ## Procedure
 
 1. Read the given spec in full before reading the ledger or code. Read the given ledger next. Save the exact `pending:` tuple and bumped `iterations:` count before editing.
-2. Close the `target` row first. Use `previous decision` and `hint` to avoid repeating work and to try a different approach; keep the target unchanged.
+2. Close the `target` row first. Read every `row <n> ...` line for the target row from `## Decisions`, oldest first, before choosing an approach. Treat them as ordered guidance: avoid what a `failed` line's third slot says not to redo, follow what it says to try differently, and never repeat an approach a prior line of this row rules out. Exclude other rows' lines from guidance for this target. Read `retry` and `escalated` lines in the same pass: use the retry hint as guidance; treat the escalation marker as historical evidence that escalation is spent, and never infer the current attempt's model from it. Keep `previous decision` as the latest admitted target line and the tie-break for most recent. Use `previous decision` and `hint` to avoid repeating work and to try a different approach; keep the target unchanged.
 3. Run `git diff --stat <base>`. Open full diff hunks only for files the row being worked on touches, using `git diff <base> -- <row files>`; read the relevant code before editing it.
 4. Implement the target row using Three-scenario TDD and Test economy below. Treat empty evidence on an unreached row as a normal state after partial seeding, not a seed failure; create its first check before implementing it, then close or fail the row with command-first evidence under step 5. Run only its targeted check under Evidence command, never the owning checkout's full verification command or the full suite.
 5. Update the target row's mutable cells: set `status` to `done` on a passing check or `failed` on a failing check, increment `attempts` by 1, and set `evidence` to one physical Markdown table cell opening with the command you ran under Evidence command, up to the first unescaped semicolon, plus at most three result lines separated by semicolons. Escape pipes as `\|` and use plain text without angle-bracket markup. On failure, record the concrete cause in plain words: the spec-vs-code contradiction, failing assertion, or missing credential, tool, or fixture. Keep reasoning and transcripts out of evidence.

package/extensions/lib/gauntlet-settings.test.ts

@@ -21,35 +21,44 @@ import {
 } from "./gauntlet-settings.ts";
 
 test("loopEngine resolves defaults, integers, clamps, and malformed values", () => {
-  const warning = "loopEngine.maxIterationsPerRow must be an integer; using default 4";
-  for (const [raw, expected, expectedWarning] of [
-    [undefined, 4, undefined], [7, 7, undefined], [0, 1, undefined], [-3, 1, undefined],
-    ["4", 4, warning], [4.5, 4, warning], [true, 4, warning], [null, 4, warning],
-  ] as const) {
-    assert.deepEqual(resolveLoopEngine({ loopEngine: { maxIterationsPerRow: raw } }), {
-      maxIterationsPerRow: expected, warning: expectedWarning,
-    });
+  for (const [key, fallback] of [["maxIterationsPerRow", 4], ["escalateAfter", 3]] as const) {
+    const warning = `loopEngine.${key} must be an integer; using default ${fallback}`;
+    for (const [raw, expected, expectedWarning] of [
+      [undefined, fallback, undefined], [7, 7, undefined], [0, 1, undefined], [-3, 1, undefined],
+      [String(fallback), fallback, warning], [2.5, fallback, warning], [true, fallback, warning], [null, fallback, warning],
+    ] as const) {
+      assert.deepEqual(resolveLoopEngine({ loopEngine: { [key]: raw } }), {
+        maxIterationsPerRow: 4, escalateAfter: 3, [key]: expected, warning: expectedWarning,
+      }, `${key}: ${String(raw)}`);
+    }
   }
-  assert.deepEqual(resolveLoopEngine({}), { maxIterationsPerRow: 4, warning: undefined });
+  assert.deepEqual(resolveLoopEngine({}), { maxIterationsPerRow: 4, escalateAfter: 3, warning: undefined });
 });
 
 test("loopEngine ignores the removed key by own-property presence and orders warnings", () => {
   const removed = "loopEngine.maxIterations is removed; set loopEngine.maxIterationsPerRow";
   for (const raw of [30, undefined, null, false]) {
     assert.deepEqual(resolveLoopEngine({ loopEngine: { maxIterations: raw } }), {
-      maxIterationsPerRow: 4, warning: removed,
+      maxIterationsPerRow: 4, escalateAfter: 3, warning: removed,
     });
   }
-  for (const [raw, expected, warning] of [
-    [7, 7, removed],
-    ["4", 4, removed + "; loopEngine.maxIterationsPerRow must be an integer; using default 4"],
+  for (const [raw, expected, allowanceWarning] of [
+    [7, 7, undefined],
+    ["4", 4, "loopEngine.maxIterationsPerRow must be an integer; using default 4"],
   ] as const) {
-    assert.deepEqual(resolveLoopEngine({ loopEngine: { maxIterations: 99, maxIterationsPerRow: raw } }), {
-      maxIterationsPerRow: expected, warning,
-    });
+    for (const [escalateAfter, threshold, thresholdWarning] of [
+      [7, 7, undefined],
+      ["3", 3, "loopEngine.escalateAfter must be an integer; using default 3"],
+    ] as const) {
+      const loopEngine = { maxIterations: 99, maxIterationsPerRow: raw, escalateAfter };
+      assert.deepEqual(resolveLoopEngine({ loopEngine }), {
+        maxIterationsPerRow: expected, escalateAfter: threshold,
+        warning: [removed, allowanceWarning, thresholdWarning].filter(Boolean).join("; "),
+      });
+    }
   }
   assert.deepEqual(resolveLoopEngine({ loopEngine: Object.create({ maxIterations: 99 }) }), {
-    maxIterationsPerRow: 4, warning: undefined,
+    maxIterationsPerRow: 4, escalateAfter: 3, warning: undefined,
   });
 });
 
@@ -61,6 +70,17 @@ test("mergeGauntlet: repo key replaces preset key whole-object", () => {
   const merged = mergeGauntlet(preset, repo);
   assert.deepEqual(merged.specCouncil, { members: ["b"] });
   assert.deepEqual(merged.closureReview, { model: "m" });
+  for (const [repoLoop, expected] of [
+    [undefined, { maxIterationsPerRow: 8, escalateAfter: 6 }],
+    [{ maxIterationsPerRow: 10 }, { maxIterationsPerRow: 10, escalateAfter: 3 }],
+    [{ escalateAfter: 2 }, { maxIterationsPerRow: 4, escalateAfter: 2 }],
+  ] as const) {
+    const loop = mergeGauntlet(
+      { loopEngine: { maxIterationsPerRow: 8, escalateAfter: 6 } },
+      repoLoop === undefined ? {} : { loopEngine: repoLoop },
+    );
+    assert.deepEqual(resolveLoopEngine(loop), { ...expected, warning: undefined });
+  }
 });
 
 test("mergeGauntlet: undefined layers -> {}", () => {

package/extensions/lib/gauntlet-settings.ts

@@ -11,7 +11,7 @@ export interface PiGauntlet {
   flowGuards?: { enforce?: unknown; specDirs?: unknown };
   verifyBeforeShip?: { testCommands?: unknown; warningReference?: unknown };
   escalationLoop?: { implModel?: unknown };
-  loopEngine?: { maxIterationsPerRow?: unknown; maxIterations?: unknown };
+  loopEngine?: { maxIterationsPerRow?: unknown; escalateAfter?: unknown; maxIterations?: unknown };
   phaseModels?: { plan?: unknown; implement?: unknown; verify?: unknown; ship?: unknown };
   telemetry?: { enabled?: unknown; dir?: unknown; buckets?: unknown };
 }
@@ -93,11 +93,14 @@ export function resolveClosureReview(g: PiGauntlet): ClosureReviewResolved {
   return { model, enforce, maxFixRounds };
 }
 
-export function resolveLoopEngine(g: PiGauntlet): { maxIterationsPerRow: number; warning: string | undefined } {
+export function resolveLoopEngine(g: PiGauntlet): { maxIterationsPerRow: number; escalateAfter: number; warning: string | undefined } {
   const loop = g.loopEngine;
   const raw = loop?.maxIterationsPerRow;
   const valid = typeof raw === "number" && Number.isInteger(raw);
   const maxIterationsPerRow = valid ? Math.max(1, raw) : 4;
+  const rawEscalateAfter = loop?.escalateAfter;
+  const validEscalateAfter = typeof rawEscalateAfter === "number" && Number.isInteger(rawEscalateAfter);
+  const escalateAfter = validEscalateAfter ? Math.max(1, rawEscalateAfter) : 3;
   const warnings: string[] = [];
   if (loop && Object.hasOwn(loop, "maxIterations")) {
     warnings.push("loopEngine.maxIterations is removed; set loopEngine.maxIterationsPerRow");
@@ -105,7 +108,10 @@ export function resolveLoopEngine(g: PiGauntlet): { maxIterationsPerRow: number;
   if (raw !== undefined && !valid) {
     warnings.push("loopEngine.maxIterationsPerRow must be an integer; using default 4");
   }
-  return { maxIterationsPerRow, warning: joinWarn(warnings) };
+  if (rawEscalateAfter !== undefined && !validEscalateAfter) {
+    warnings.push("loopEngine.escalateAfter must be an integer; using default 3");
+  }
+  return { maxIterationsPerRow, escalateAfter, warning: joinWarn(warnings) };
 }
 
 export interface EscalationLoopResolved {

package/extensions/phase-tracker.test.ts

@@ -1468,16 +1468,17 @@ test("gauntlet_setting escalationLoop: setting absent -> ctx-derived main-loop m
 });
 
 test("gauntlet_setting loopEngine resolves the key", async () => {
-  for (const [loopEngine, expected, warning] of [
-    [undefined, 4, undefined],
-    [{ maxIterationsPerRow: 8 }, 8, undefined],
-    [{ maxIterations: 99, maxIterationsPerRow: "4" }, 4,
-      "loopEngine.maxIterations is removed; set loopEngine.maxIterationsPerRow; loopEngine.maxIterationsPerRow must be an integer; using default 4"],
+  for (const [loopEngine, expected, escalateAfter, warning] of [
+    [undefined, 4, 3, undefined],
+    [{ maxIterationsPerRow: 8, escalateAfter: 2 }, 8, 2, undefined],
+    [{ escalateAfter: 0 }, 4, 1, undefined],
+    [{ maxIterations: 99, maxIterationsPerRow: "4", escalateAfter: "3" }, 4, 3,
+      "loopEngine.maxIterations is removed; set loopEngine.maxIterationsPerRow; loopEngine.maxIterationsPerRow must be an integer; using default 4; loopEngine.escalateAfter must be an integer; using default 3"],
   ] as const) {
     const h = harness({ cwd: tempCwd({ piGauntlet: { loopEngine } }) });
     const tool = h.tools.find(t => t.name === "gauntlet_setting")!;
     const result = await tool.execute("loop", { key: "loopEngine" }, undefined, undefined, h.ctx) as any;
-    assert.deepEqual(result.details, { key: "loopEngine", maxIterationsPerRow: expected, warning, errors: [] });
+    assert.deepEqual(result.details, { key: "loopEngine", maxIterationsPerRow: expected, escalateAfter, warning, errors: [] });
     assert.equal(Object.hasOwn(result.details, "maxIterations"), false);
   }
 });
@@ -1489,6 +1490,7 @@ test("gauntlet_setting loopEngine composes settings load warnings", async () =>
   const result = await h.tools.find(t => t.name === "gauntlet_setting")!.execute("loop", { key: "loopEngine" }, undefined, undefined, h.ctx) as any;
   assert.equal(result.details.key, "loopEngine");
   assert.equal(result.details.maxIterationsPerRow, 4);
+  assert.equal(result.details.escalateAfter, 3);
   assert.equal(Object.hasOwn(result.details, "maxIterations"), false);
   assert.ok(result.details.errors.length);
   assert.equal(result.details.warning, `⚠️ gauntlet settings load error (using defaults): ${result.details.errors.join("; ")}`);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pi-gauntlet",
-  "version": "8.1.6",
+  "version": "8.1.7",
   "description": "Opinionated, gated workflow skills, subagent personas, and runtime extensions for the pi coding agent.",
   "author": "Jacek Juraszek",
   "type": "module",

package/skills/gauntlet-resume/reference/reconstruction.md

@@ -93,9 +93,9 @@ After confirmation:
 1. Read ledger line 1: require `# Ledger - loop engine`. Resolve its path-only `**Spec:**` header to an absolute spec path under the worktree's configured spec directories, not by basename. Run SKILL.md entry checks 1-6 in order, including check 6, **Grant field**, on that spec, before any tracker mutation. Run Pending recovery's read-only admission-evidence check below.
 2. Call `phase_tracker({ action: "start", phase: "brainstorm" })`, then `phase_tracker({ action: "skip", phase: "brainstorm", reason: "resume: <spec path>" })`, then `phase_tracker({ action: "start", phase: "plan" })`.
 3. Admit exactly one positive safe-integer `cap:` or `allowance:` header; both or neither is `ledger header malformed: <observed header lines>`, requiring human repair by hand. Call `plan_check({ planPath: <absolute ledger path> })` with legacy-compatible admission. On FAIL, stop with findings, retaining plan in_progress. Start the message with `gauntlet: stuck` followed by the findings reason on that line; never enter `## Plan repair` or writing-plans. On PASS, call `phase_tracker({ action: "skip", phase: "plan", reason: "resume: <spec> (loop engine)" })`, then `phase_tracker({ action: "start", phase: "implement" })`. Use the resolved absolute spec path as `<spec>` in the reason. Restore implement through refresh, not `init`.
-4. **Shared allowance boundary (every ledger restore, before phase continuation).** Read `/skill:loop-implementation`. Skip Entry step 1 entirely; restore base, verification, iterations, row attempts and decisions from the ledger without reseeding. Apply the following order on bare-worktree and brief routes alike:
+4. **Shared allowance boundary (every ledger restore, before phase continuation).** Read `/skill:loop-implementation`. Skip Entry step 1's allowance seeding; restore base, verification, iterations, row attempts and decisions from the ledger without reseeding. Resolve `gauntlet_setting({ key: "loopEngine" })` exactly once at the driver's authorized-restore grant boundary and retain `escalateAfter` in driver memory for this run; share this read with step 4.2, never refresh it inside the loop. On an unavailable tool, stop before any dispatch or write with `cannot resolve escalation threshold: settings tool unavailable (loopEngine.escalateAfter)`. Apply the following order on bare-worktree and brief routes alike:
    1. Apply pending recovery below against the unmigrated ledger, including home returns whose child commit removed the tuple. Validate the original one-commit `<pre-dispatch HEAD>..HEAD` range against its unchanged before-image. For companions, retain unchanged home HEAD and admit the expected iterations-bump-plus-tuple dirt. On unrecoverable attribution or before-image, stop before refresh. Resolve ambiguous-history admission before tracker calls as required below. Retain every discard/reset and interrupted-dispatch gate; migration changes neither admission ranges nor the home HEAD used for recovery.
-   2. Migrate only an admitted, clean, tuple-free ledger with no retained recovery stop. With `cap:` and no `allowance:`, resolve `gauntlet_setting({ key: "loopEngine" })` for this migration only and replace the cap line with `allowance: <maxIterationsPerRow>`. Commit only that header replacement as parent `loop: migrate allowance`; preserve iterations, every attempts cell and all decisions. On an unavailable tool, stop before any write with `cannot migrate allowance: settings tool unavailable (loopEngine.maxIterationsPerRow)`. With an existing allowance, use it without settings resolution or a migration commit. Defer migration through any retained recovery stop or dirty tree; after authorized recovery reaches a clean tuple-free tree, migrate before the next dispatch or verification.
+   2. Migrate only an admitted, clean, tuple-free ledger with no retained recovery stop. With `cap:` and no `allowance:`, reuse the single restore-boundary settings read and replace the cap line with `allowance: <maxIterationsPerRow>`. Commit only that header replacement as parent `loop: migrate allowance`; preserve iterations, every attempts cell and all decisions. With an existing allowance, use it without allowance resolution or a migration commit; the restore read supplies `escalateAfter` only. Defer migration through any retained recovery stop or dirty tree; after authorized recovery reaches a clean tuple-free tree, migrate before the next dispatch or verification.
    3. Require `allowance:` and no `cap:` before continuation, including for all-closed ledgers; otherwise stop with `ledger has no allowance: line - resume through /skill:gauntlet-resume`. For a retained recovery stop or unresolved dirty tree, defer this final validation with migration and project the unmigrated ledger solely to report the stop.
    4. Call `plan_tracker({ action: "refresh", path: <absolute ledger path> })` exactly once after phase restoration, recovery and eligible migration/final validation, before any unresolved dirty-tree stop or dispatch. On verify/ship, restore the saved mixed task list first as `brief-contract.md` specifies; on implement, use no `init`. On refresh failure, stop with its findings and leave the existing task list untouched. Read `plan_tracker status` and report its exact observed state, never an inferred list.
    Render the allowance header, rows, iterations, attempts, effective allowances and all decisions; distinguish the latest operational `row <n> ...` decision from the last physical history line. Compute each effective allowance as the header plus one per matching retry decision; ignore the retry's audit ceiling. Keep `cap +N` history as inert text and restore no funded rounds. Report any retained recovery stop now with no redispatch, using the driver's unresolved-row counts and discard-authorization menu for dirty trees. Resume the original phase only after this boundary: implement at `Before each dispatch`; verify/ship at `After the loop` step 1.

package/skills/loop-implementation/SKILL.md

@@ -9,7 +9,7 @@ Run this driver in the main session. Carry the absolute implementation worktree
 
 ## Entry
 
-1. Read project overrides below. Resolve `gauntlet_setting({ key: "loopEngine" })` and retain `maxIterationsPerRow` (default 4). Stop on an unavailable settings tool. Select this run's seed value in step 4 and persist it only in the ledger, not in the spec or settings.
+1. Read project overrides below. Resolve `gauntlet_setting({ key: "loopEngine" })` and retain `maxIterationsPerRow` (default 4) and `escalateAfter` (default 3). Hold `escalateAfter` in driver memory for this run; never print it or write it to the ledger, and never re-resolve it inside the loop, including after amendment grant re-decodes. Stop on an unavailable settings tool. Select this run's seed value in step 4 and persist it only in the ledger, not in the spec or settings.
 2. Resolve verification once using this ordered table. Print `verification command: <command> (<source>)`.
 
 | Observed configuration | Action |
@@ -18,7 +18,7 @@ Run this driver in the main session. Carry the absolute implementation worktree
 | Otherwise overrides has `## verification-before-completion` | Use its exactly one backticked command; zero or several is a configuration error. |
 | Neither section supplies a command | Discover the project's test entrypoint from its actual manifest/build instructions; print discovery as source. Stop on an unresolved or ambiguous entrypoint. |
 
-At seed and at an authorized restore, before entering the dispatch loop, read the spec in full. Decode `**Amend-grant:**` through [amendment-surface Value decoding](../brainstorming/reference/amendment-surface.md). Capture the decoded grant, ordered leg membership, each leg's absolute checkout paths and combined spec/task Rules for dispatch and handoff; use home for zero or one leg.
+At seed and at an authorized restore, before entering the dispatch loop, read the spec in full. Decode `**Amend-grant:**` through [amendment-surface Value decoding](../brainstorming/reference/amendment-surface.md). Capture the decoded grant, ordered leg membership, each leg's absolute checkout paths and combined spec/task Rules for dispatch and handoff; use home for zero or one leg. At an authorized fresh-session restore, resolve `gauntlet_setting({ key: "loopEngine" })` exactly once at this boundary and hold `escalateAfter` for the run; share that read with reconstruction's Shared allowance boundary, including legacy allowance migration. With an unavailable tool, stop before dispatch with `cannot resolve escalation threshold: settings tool unavailable (loopEngine.escalateAfter)`; never supply an in-loop default.
 
 At seed and at an authorized restore, when the held membership has more than one leg, read `reference/coordinated-legs.md` IN FULL now with read at its absolute path; stop on an unreadable reference naming its path, never reconstruct it. On fresh entry apply its `## Entry` section at step 4 instead of the home-only skeleton below, using step 4's resolved allowance seed value. On a restore apply its `## Resume` section before the dirty-tree stop and before any pending recovery. Keep legacy and single-member ledger bytes unchanged, with no coordinated metadata.
 
@@ -44,7 +44,7 @@ allowance: <n>
 Use the actual repo-relative spec path alone in the Spec header. Read base with `git -C "<worktree>" rev-parse HEAD`. Index every spec AC in order, including nested disposition lines without treating them as extra ACs; keep row text only in the spec. Initialize explicit/absent `in-scope` and `venue:` rows `open`, attempts 0, evidence empty. Initialize only `deviates:`, `deferred:`, `elsewhere:` rows `cut`, attempts 0, disposition text as evidence. Write `allowance:` immediately after `iterations: 0` using step 4's seed value; never scale it by row count or seed dispatches: 24 non-cut rows at default 4 yield allowance 4. All-cut ledgers keep the same allowance and exit through rule 1 without a seed dispatch. Later cuts, reopens and requirement-preserving amendments leave allowance unchanged; redraw deletes the ledger and reseeds it. Serialize evidence in one physical table cell, result lines separated by semicolons, pipes escaped, plain text without angle markup.
 5. Call `plan_check({ planPath: <ledger path> })`. Stop with findings as a configuration error. Commit the stamped skeleton as `loop: seed ledger`; call `phase_tracker({ action: "start", phase: "implement" })`, then `plan_tracker({ action: "refresh", path: <absolute ledger path> })`, including all-cut ledgers with no seed dispatch.
 
-For resume, use the admitted ledger, its base and verification command, and durable iterations and allowance instead of overwriting it. Skip Entry step 1 for an admitted ledger; settings apply only to fresh seeding. Apply `/skill:gauntlet-resume` pending recovery and its `loop: migrate allowance` step before refresh and any unresolved dirty-tree stop. Render rows, allowance and decision history; stop on a dirty tree before dispatch.
+For resume, use the admitted ledger, its base and verification command, and durable iterations and allowance instead of overwriting it. Skip Entry step 1's allowance seeding for an admitted ledger; the allowance setting applies only to fresh seeding, and the restore boundary resolves `escalateAfter` once. Apply `/skill:gauntlet-resume` pending recovery and its `loop: migrate allowance` step before refresh and any unresolved dirty-tree stop. Render rows, allowance and decision history; stop on a dirty tree before dispatch.
 
 ## Driver holds
 
@@ -65,7 +65,7 @@ Read the ledger and require `allowance:` and no `cap:` before the ordered table,
 | 1 | No `open` or `failed` row | Refresh; require implement complete; continue at ## After the loop step 0. All-cut and baseline-complete ledgers exit here. |
 | 2 | Unresolved row attempts >= effective allowance | Human stop under approval option 4 and option 5 alike. Exempt `done` and `cut`. |
 | 3 | Last two child row commits both changed no file outside the ledger and no row status, or two consecutive validation misses | Human stop. Count child `loop: row ...` commits only for empty-child stagnation, excluding seed and parent repair/retry/cut commits. A decision alone is not progress. |
-| 4 | Dispatch allowed | Select target by the priority below, then apply the last-attempt escalation check. |
+| 4 | Dispatch allowed | Select target by the priority below, then apply the escalation threshold check. |
 
 When a refresh leaves implement active at rule 1, take the matching human stop; never start verify. Before evaluating rule 2, compute each row's effective allowance as the ledger's `allowance:` plus the count of that row's `row <n> retry | ... | allowed attempts <m>` lines in `## Decisions`. Count each retry once; the stored `<m>` is historical, not an absolute override. Ignore every other decision and grant in this arithmetic. Use the same rule for every coordinated entry, regardless of leg. With allowance 4 and two retries, a row has effective allowance 6 even if the historical `<m>` values are 5 and 99; raising the shared header to 7 makes it 9, while an unretried row gets 7. After migration, a row already at or above its effective allowance is exhausted. Never reset or reduce attempts.
 
@@ -73,9 +73,9 @@ Use the held decoded amendment grant for amendment choices only; ignore its wave
 
 Select `seed` until a validated `loop: seed evidence` commit with its `row 0 done` decision survives on the branch, independently of `iterations`; otherwise select the still-unresolved human retry target, then the still-failed row named by the previous decision, then first failed row, then first open row. Read seed survival from the ledger at HEAD and the matching validated commit, not from evidence completeness. Never re-seed a validated partial seed to fill empty evidence cells. Use the latest admitted return's target decision for targeting and the child's `previous decision:` input, never an extra's line; skip allowance-grant and legacy grant history while retaining the entire Decisions section. Durable status beats a decision's suggestion. Keep the retry hint only for its target.
 
-For a numbered target at attempts == effective allowance - 1 with no existing durable `row <n> escalated` decision, resolve `gauntlet_setting({ key: "escalationLoop" })` under approval option 4 and option 5 alike. Use the returned non-empty `implModel` string, including the resolver's main-loop model fallback when the setting is unset or malformed. With the settings tool unavailable or `implModel` undefined (neither a configured model nor a main-loop model), stop before dispatch with `Problem: escalationLoop.implModel unavailable`; write no escalation decision and leave attempts at effective allowance - 1. Never substitute a default-model last attempt for that stop.
+For a numbered target with no durable `row <n> escalated` decision, compute `threshold = min(escalateAfter, effective allowance - 1)` from the held `escalateAfter` and the row's effective allowance. When the row's pre-dispatch attempts >= threshold, make this dispatch the escalated round: resolve `gauntlet_setting({ key: "escalationLoop" })` under approval option 4 and option 5 alike. Use the returned non-empty `implModel` string, including the resolver's main-loop model fallback when the setting is unset or malformed. With the settings tool unavailable or `implModel` undefined (neither a configured model nor a main-loop model), stop before dispatch with `Problem: escalationLoop.implModel unavailable`; write no escalation decision and leave attempts unchanged. Never substitute a default-model attempt for that stop.
 
-With the resolved model, append `row <n> escalated | implModel round | allowed attempts <effective allowance>`, commit parent `loop: escalate row <n>`, print `escalated round for row <n>`, and dispatch that last allowed attempt with `model: <implModel>` through the normal loop-implementer target, bump and validation path. At allowance 1, escalate the first and only allowed attempt. Exclude this parent commit from child-only stagnation; it starts no new empty-child or validation-miss window. Treat the escalated decision as exactly one round within the effective allowance, never an extra attempt. Recover the row's escalation identity from `## Decisions` on every dispatch and resume; unrecoverable means spent. Preserve `row <n> escalated` for the whole flow across retry, `rows +N`, amendments and resume. Once spent, omit the model override on every later authorized attempt, including a new last allowed attempt; never resolve another row escalation or append a second marker. With no marker and recoverable history, apply the normal last-attempt predicate after retry or `rows +N`; a previously missing model or migrated row has not spent escalation. Dispatch errors, non-DONE and validation failures consume it before any recommendation decision.
+With the resolved model, append `row <n> escalated | implModel round | allowed attempts <effective allowance>`, commit parent `loop: escalate row <n>`, print `escalated round for row <n>`, and dispatch that attempt with `model: <implModel>` through the normal loop-implementer target, bump and validation path. Exclude this parent commit from child-only stagnation; it starts no new empty-child or validation-miss window. With defaults (allowance 4, `escalateAfter` 3), escalate attempt 4; clamp larger thresholds to the last allowed attempt. At allowance 1, escalate the first and only allowed attempt. A row found past the threshold unspent escalates on its next dispatch. Treat the escalated decision as exactly one round within the effective allowance, never an extra attempt. Recover the row's escalation identity from `## Decisions` on every dispatch and resume; unrecoverable means spent. Preserve `row <n> escalated` for the whole flow across retry, `rows +N`, amendments and resume. Once spent, omit the model override on every later authorized attempt, including every attempt up to a raised effective allowance; never resolve another row escalation or append a second marker. With no marker and recoverable history, apply the threshold predicate after retry or `rows +N`; a previously missing model or migrated row has not spent escalation. Dispatch errors, non-DONE and validation failures consume it before any recommendation decision.
 
 ## Dispatch
 
@@ -128,7 +128,7 @@ Offer retry and `rows +N` only at row stops (allowance, stagnation or missing-mo
 
 Serialize the bare decision as `rows +50 |` with an empty words cell. Raising allowance resets neither window (empty-child or validation-miss); exclude `loop: raise allowance` from child-commit counting. Only retry starts new windows.
 
-For dirty/commit-boundary retry, ask the human to authorize discarding uncommitted changes/resetting to last valid commit. Preserve the pre-dispatch escalation decision through authorized discard/reset; it stays spent. Boundary rejection never increments attempts: an escalated last-attempt rejection leaves attempts at effective allowance - 1, so after authorized recovery dispatch on the default model without requiring retry or `rows +N`, subject to the normal boundaries. An admitted validation miss instead increments attempts through `loop: repair row <n>` to the effective allowance and stops under rule 2, retaining the spent decision. Preserve consumed dispatch count: set iterations to restored HEAD's value +1 before the next normal bump. An interrupted dispatch consumes the same count; recover it from disk/branch rather than silently repeating iteration 0.
+For dirty/commit-boundary retry, ask the human to authorize discarding uncommitted changes/resetting to last valid commit. Preserve the pre-dispatch escalation decision through authorized discard/reset; it stays spent. Boundary rejection never increments attempts: an escalated rejection leaves attempts at the pre-dispatch count, so after authorized recovery dispatch on the worker model without requiring retry or `rows +N`, subject to the normal boundaries. An admitted validation miss instead increments attempts by exactly one through `loop: repair row <n>`, retains the spent decision and returns to the ordered table: a row at its effective allowance stops under rule 2; a row below it gets its next attempt on the worker model. Exhaustion and stagnation keep precedence over dispatch; neither window resets. Preserve consumed dispatch count: set iterations to restored HEAD's value +1 before the next normal bump. An interrupted dispatch consumes the same count; recover it from disk/branch rather than silently repeating iteration 0.
 
 Outside the dispatch loop, perform authorized amendment actions under the amendment surface's own reads. After the amendment commit, re-decode the grant and refresh the held membership, checkout paths and Rules from the updated spec before returning to the loop; apply this to funding and standing-grant amendments too. Leave the `**Amend-grant:**` header grammar unchanged.