@bendyline/gilde 0.1.39 → 0.1.41

package/authoring/tactical/evals/hotfix-flow.json

@@ -0,0 +1,220 @@
+{
+  "schemaVersion": 1,
+  "title": "Hotfix with minimal blast radius and a rollback path",
+  "objective": "The craftbook drives an urgent fix of a seeded null-guard crash in a receipts formatter: reproduction with the least machinery, the smallest change at the real defect site, honest validation with a rollback path, and an enforced review — verified mechanically, including a mutant re-seed proving the patch engaged the real site.",
+  "tags": [
+    "code",
+    "bug-fix",
+    "hotfix",
+    "tactical-fleet"
+  ],
+  "prompt": "Use the Hotfix Flow craftbook for this emergency: the nightly receipts export is crashing in production on orders without a gift note. The incident report is in source/incident.md. Reproduce it with the least machinery that shows it, patch minimally at the real defect site, and leave a rollback path.",
+  "setup": {
+    "projectName": "Receiptline",
+    "about": "A tiny order-receipt formatting module behind a nightly export. No test suite - the export script is the only runnable surface.",
+    "files": [
+      {
+        "path": "package.json",
+        "content": "{\n  \"name\": \"receiptline\",\n  \"private\": true,\n  \"version\": \"1.0.0\",\n  \"type\": \"module\"\n}\n",
+        "modelInput": false
+      },
+      {
+        "path": "src/format-order.js",
+        "content": "export function formatOrder(order) {\n  const lines = [];\n  lines.push('Order ' + order.id + ' for ' + order.customer);\n  for (const item of order.items) {\n    lines.push('  ' + item.qty + ' x ' + item.name + ' @ ' + money(item.unitPrice));\n  }\n  lines.push('Total: ' + money(orderTotal(order)));\n  lines.push('Gift note: ' + order.giftNote.trim());\n  return lines.join('\\n');\n}\n\nexport function orderTotal(order) {\n  let total = 0;\n  for (const item of order.items) {\n    total += item.qty * item.unitPrice;\n  }\n  return Math.round(total * 100) / 100;\n}\n\nfunction money(value) {\n  return value.toFixed(2);\n}\n"
+      },
+      {
+        "path": "data/orders.json",
+        "content": "[\n  {\n    \"id\": \"A-1041\",\n    \"customer\": \"Ana Torres\",\n    \"items\": [{ \"qty\": 1, \"name\": \"Ceramic Vase\", \"unitPrice\": 30 }],\n    \"giftNote\": \"  Happy birthday, Ana!  \"\n  },\n  {\n    \"id\": \"A-1042\",\n    \"customer\": \"Ben Ito\",\n    \"items\": [{ \"qty\": 2, \"name\": \"Stone Mug\", \"unitPrice\": 9.5 }]\n  },\n  {\n    \"id\": \"A-1043\",\n    \"customer\": \"Priya Shah\",\n    \"items\": [\n      { \"qty\": 3, \"name\": \"Linen Napkin\", \"unitPrice\": 4 },\n      { \"qty\": 1, \"name\": \"Oak Tray\", \"unitPrice\": 18 }\n    ]\n  }\n]\n",
+        "modelInput": false
+      },
+      {
+        "path": "scripts/print-receipts.mjs",
+        "content": "import { readFileSync } from 'node:fs';\nimport { formatOrder } from '../src/format-order.js';\n\nconst orders = JSON.parse(\n  readFileSync(new URL('../data/orders.json', import.meta.url), 'utf8'),\n);\nfor (const order of orders) {\n  console.log(formatOrder(order));\n  console.log('---');\n}\n",
+        "modelInput": false
+      },
+      {
+        "path": "source/incident.md",
+        "content": "# Incident: receipts export crashing\n\n02:14 - the nightly receipts export died partway through and retail has no morning receipts. Support traced it to orders without a gift note:\n\n    TypeError: Cannot read properties of undefined (reading 'trim')\n        at formatOrder (src/format-order.js)\n\n`node scripts/print-receipts.mjs` reproduces it: the first order (which has a gift note) prints fine, then the export falls over on the second order in `data/orders.json`.\n\nWhat must hold once this is fixed:\n\n- Orders with a gift note keep printing the trimmed note line.\n- Orders without one print a normal receipt with NO gift-note line.\n- Item lines and totals unchanged.\n\nWe need the smallest safe patch now. The proper cleanup of the formatter can wait for daylight - write it down instead of doing it.\n"
+      },
+      {
+        "path": "tests/verify-hotfix.mjs",
+        "surface": "harness",
+        "content": "import assert from 'node:assert/strict';\nimport { execFileSync } from 'node:child_process';\nimport { cpSync, mkdirSync, rmSync, writeFileSync } from 'node:fs';\nimport { join } from 'node:path';\nimport { formatOrder, orderTotal } from '../src/format-order.js';\n\nconst root = process.cwd();\n\n// 1) The crash case is fixed: an order without a gift note formats cleanly.\nconst plain = {\n  id: 'A-1042',\n  customer: 'Ben Ito',\n  items: [{ qty: 2, name: 'Stone Mug', unitPrice: 9.5 }],\n};\nconst plainReceipt = formatOrder(plain);\nassert.ok(!plainReceipt.includes('undefined'), 'a receipt must not leak \"undefined\"');\nassert.ok(!/Gift note:/.test(plainReceipt), 'an order without a gift note must not print a gift-note line');\nassert.ok(plainReceipt.includes('Total: 19.00'), 'totals must survive the patch');\nconsole.log('HOTFIX_ORACLE crash case fixed');\n\n// 2) Neighborhood intact: gift notes still print trimmed, totals still add up.\nconst gifted = {\n  id: 'A-1041',\n  customer: 'Ana Torres',\n  items: [{ qty: 1, name: 'Ceramic Vase', unitPrice: 30 }],\n  giftNote: '  Happy birthday, Ana!  ',\n};\nconst giftedReceipt = formatOrder(gifted);\nassert.ok(giftedReceipt.includes('Gift note: Happy birthday, Ana!'), 'gift notes must still print, trimmed');\nconst multi = {\n  id: 'A-1043',\n  customer: 'Priya Shah',\n  items: [\n    { qty: 3, name: 'Linen Napkin', unitPrice: 4 },\n    { qty: 1, name: 'Oak Tray', unitPrice: 18 },\n  ],\n};\nassert.equal(orderTotal(multi), 30, 'orderTotal must be untouched');\nconsole.log('HOTFIX_ORACLE neighborhood intact');\n\n// 3) The export the incident names runs clean end to end.\nconst exportOut = execFileSync(process.execPath, ['scripts/print-receipts.mjs'], {\n  cwd: root,\n  stdio: 'pipe',\n  timeout: 30000,\n}).toString();\nassert.ok(exportOut.includes('A-1043'), 'the export must reach the last order');\nconsole.log('HOTFIX_ORACLE export green');\n\n// 4) Re-seed the original defect into a mutant tree: the crash must come\n// back, proving the patch engaged the real site rather than the callers\n// or the data (both of which are pinned fixtures anyway).\nconst ORIGINAL = `export function formatOrder(order) {\n  const lines = [];\n  lines.push('Order ' + order.id + ' for ' + order.customer);\n  for (const item of order.items) {\n    lines.push('  ' + item.qty + ' x ' + item.name + ' @ ' + money(item.unitPrice));\n  }\n  lines.push('Total: ' + money(orderTotal(order)));\n  lines.push('Gift note: ' + order.giftNote.trim());\n  return lines.join('\\\\n');\n}\n\nexport function orderTotal(order) {\n  let total = 0;\n  for (const item of order.items) {\n    total += item.qty * item.unitPrice;\n  }\n  return Math.round(total * 100) / 100;\n}\n\nfunction money(value) {\n  return value.toFixed(2);\n}\n`;\nconst mutantRoot = join(root, '.oracle-mutant');\nrmSync(mutantRoot, { recursive: true, force: true });\nmkdirSync(join(mutantRoot, 'src'), { recursive: true });\ncpSync(join(root, 'scripts'), join(mutantRoot, 'scripts'), { recursive: true });\ncpSync(join(root, 'data'), join(mutantRoot, 'data'), { recursive: true });\ncpSync(join(root, 'package.json'), join(mutantRoot, 'package.json'));\nwriteFileSync(join(mutantRoot, 'src', 'format-order.js'), ORIGINAL);\nlet mutantStatus = 0;\ntry {\n  execFileSync(process.execPath, ['scripts/print-receipts.mjs'], {\n    cwd: mutantRoot,\n    stdio: 'pipe',\n    timeout: 30000,\n  });\n} catch (err) {\n  mutantStatus = typeof err.status === 'number' ? err.status : 1;\n}\nassert.notEqual(mutantStatus, 0, 're-seeding the original defect must restore the crash - the patch did not engage the real site');\nconsole.log('HOTFIX_ORACLE mutant caught');\nconsole.log('HOTFIX_ORACLE done');\n"
+      }
+    ],
+    "craftbookParams": {
+      "workPath": "tasks/eval",
+      "scope": "The nightly receipts export crashes on orders without a gift note; see source/incident.md. Smallest safe patch now - the proper cleanup is deferred, not attempted."
+    }
+  },
+  "success": {
+    "summary": "The seeded null-guard crash is fixed at the real site with minimal blast radius, the export runs clean, a mutant re-seed restores the crash, and the fleet artifacts carry honest evidence, a Follow-up debt record, and a runnable rollback.",
+    "deliverables": [
+      {
+        "path": "tasks/eval/repro.md",
+        "kind": "markdown-notes",
+        "artifact": true,
+        "minBytes": 500,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/repro.md",
+            "pattern": "^##\\s+Symptom[\\s\\S]*^##\\s+Repro command[\\s\\S]*^##\\s+Expected[\\s\\S]*^##\\s+Actual[\\s\\S]*^##\\s+Evidence",
+            "flags": "im",
+            "label": "reproduction sections in order"
+          },
+          {
+            "kind": "citationsResolve",
+            "file": "tasks/eval/repro.md",
+            "minCitations": 2,
+            "artifact": true
+          }
+        ]
+      },
+      {
+        "path": "tasks/eval/fix-notes.md",
+        "kind": "markdown-notes",
+        "artifact": true,
+        "minBytes": 700,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/fix-notes.md",
+            "pattern": "^##\\s+Problem[\\s\\S]*^##\\s+Change[\\s\\S]*^##\\s+Files touched[\\s\\S]*^##\\s+Risk[\\s\\S]*^##\\s+How to verify[\\s\\S]*^##\\s+Follow-up",
+            "flags": "im",
+            "label": "fix-notes sections in order, Follow-up included"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/fix-notes.md",
+            "pattern": "src/format-order\\.js",
+            "label": "names the real defect site"
+          },
+          {
+            "kind": "citationsResolve",
+            "file": "tasks/eval/fix-notes.md",
+            "minCitations": 2,
+            "artifact": true
+          }
+        ]
+      },
+      {
+        "path": "tasks/eval/validation.md",
+        "kind": "markdown-notes",
+        "artifact": true,
+        "minBytes": 400,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/validation.md",
+            "pattern": "^##\\s+Repro re-run[\\s\\S]*^##\\s+Result[\\s\\S]*^##\\s+Rollback",
+            "flags": "im",
+            "label": "validation sections in order, Rollback included"
+          }
+        ]
+      },
+      {
+        "path": "tasks/eval/review.md",
+        "kind": "markdown-report",
+        "artifact": true,
+        "minBytes": 400,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/review.md",
+            "pattern": "Verdict:\\s*(?:PASS|REVISE)",
+            "flags": "i",
+            "label": "explicit reviewer verdict"
+          }
+        ]
+      }
+    ],
+    "checks": [
+      {
+        "kind": "notContains",
+        "file": "src/format-order.js",
+        "pattern": "\\btry\\s*\\{|\\bcatch\\s*\\(",
+        "label": "the crash is fixed at the site, not swallowed with try/catch"
+      },
+      {
+        "kind": "sourceParses",
+        "file": "src/format-order.js"
+      },
+      {
+        "kind": "nodeRuns",
+        "file": "scripts/print-receipts.mjs",
+        "timeoutMs": 30000
+      },
+      {
+        "kind": "nodeScriptPasses",
+        "script": "tests/verify-hotfix.mjs",
+        "timeoutMs": 60000,
+        "requiredOutput": [
+          {
+            "pattern": "HOTFIX_ORACLE crash case fixed",
+            "label": "the null-guard crash is gone"
+          },
+          {
+            "pattern": "HOTFIX_ORACLE neighborhood intact",
+            "label": "gift notes and totals still behave"
+          },
+          {
+            "pattern": "HOTFIX_ORACLE export green",
+            "label": "the incident's export runs end to end"
+          },
+          {
+            "pattern": "HOTFIX_ORACLE mutant caught",
+            "label": "re-seeding the defect restores the crash"
+          }
+        ]
+      }
+    ],
+    "taskNotes": {
+      "minBytes": 120,
+      "checks": [
+        {
+          "kind": "contains",
+          "file": "task-notes.md",
+          "pattern": "\\bDONE\\b[\\s\\S]*validation\\.md",
+          "flags": "i",
+          "label": "DONE note names the validation deliverable"
+        }
+      ]
+    },
+    "taskGraph": {
+      "requireCraftbookTask": true,
+      "requireTerminalStep": true
+    },
+    "unchangedFixtures": [
+      "source/incident.md",
+      "package.json",
+      "data/orders.json",
+      "scripts/print-receipts.mjs"
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "tasks/eval/fix-notes.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "Minimal blast radius",
+        "description": "The change is the smallest that stops the failure at the real defect site - no refactor, rename, or cleanup rode along with the emergency patch."
+      },
+      {
+        "name": "Honest evidence under pressure",
+        "description": "Reproduction and validation quote real observed behavior, and anything that could not actually be run is labeled unverified rather than claimed."
+      },
+      {
+        "name": "Deferred debt discipline",
+        "description": "Follow-up records the proper fix and the debt the patch leaves (with a backport note where relevant) instead of attempting a deeper repair mid-incident, and Rollback is a concrete, runnable path."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "minimal-diff discipline",
+    "honest verification",
+    "runnable rollback"
+  ]
+}

package/authoring/tactical/evals/perf-optimization.json

@@ -0,0 +1,235 @@
+{
+  "schemaVersion": 1,
+  "title": "Measured near-linear fix for a quadratic hot path",
+  "objective": "The craftbook drives a measured optimization of a seeded O(n^2) duplicate finder: baseline numbers recorded with their method, one bottleneck fixed at the real site, the same measurement re-run to prove the gain, and an enforced review — verified mechanically via a deterministic instrumented op-count budget, reference-equal results, and a green-suite run.",
+  "tags": [
+    "code",
+    "performance",
+    "tactical-fleet"
+  ],
+  "prompt": "Use the Targeted Performance Fix craftbook for this: support says importing a 200-row sheet crawls, and profiling points at findDuplicates - a 200-item list burns about 40,000 comparisons. The brief is in source/perf-brief.md. Get findDuplicates near-linear without changing its results.",
+  "setup": {
+    "projectName": "Sheet Importer",
+    "about": "A tiny sheet-import module with an instrumented duplicate finder. Tests run with `npm run test` (node --test).",
+    "files": [
+      {
+        "path": "package.json",
+        "content": "{\n  \"name\": \"sheet-importer\",\n  \"private\": true,\n  \"version\": \"1.0.0\",\n  \"type\": \"module\",\n  \"scripts\": {\n    \"test\": \"node --test\"\n  }\n}\n"
+      },
+      {
+        "path": "src/instrument.js",
+        "content": "let comparisons = 0;\n\nexport function countComparison() {\n  comparisons += 1;\n}\n\nexport function comparisonCount() {\n  return comparisons;\n}\n\nexport function resetComparisons() {\n  comparisons = 0;\n}\n"
+      },
+      {
+        "path": "src/find-duplicates.js",
+        "content": "import { countComparison } from './instrument.js';\n\nexport function findDuplicates(items) {\n  const duplicates = [];\n  for (let i = 0; i < items.length; i += 1) {\n    let count = 0;\n    for (let j = 0; j < items.length; j += 1) {\n      countComparison();\n      if (items[j] === items[i]) count += 1;\n    }\n    if (count > 1 && !duplicates.includes(items[i])) duplicates.push(items[i]);\n  }\n  return duplicates;\n}\n"
+      },
+      {
+        "path": "tests/duplicates.test.mjs",
+        "content": "import assert from 'node:assert/strict';\nimport { test } from 'node:test';\nimport { findDuplicates } from '../src/find-duplicates.js';\n\ntest('reports each duplicate once, in first-appearance order', () => {\n  assert.deepEqual(findDuplicates(['a', 'b', 'a', 'c', 'b']), ['a', 'b']);\n});\n\ntest('returns empty for unique lists', () => {\n  assert.deepEqual(findDuplicates(['x', 'y', 'z']), []);\n});\n\ntest('order pins to first appearance, not second occurrence', () => {\n  assert.deepEqual(findDuplicates(['a', 'b', 'b', 'a']), ['a', 'b']);\n});\n"
+      },
+      {
+        "path": "source/perf-brief.md",
+        "content": "# Performance brief\n\nSupport reports that importing a 200-row sheet crawls. Profiling points at `findDuplicates` in src/find-duplicates.js: for a 200-item list it performs about 40,000 instrumented comparisons (200 x 200 full rescans). The counter lives in src/instrument.js - `comparisonCount()` reads it, `resetComparisons()` clears it.\n\nTarget: get `findDuplicates` near-linear - well under 2,000 instrumented comparisons for a 200-item list - WITHOUT changing its results. Each duplicated value is reported once, in order of FIRST appearance.\n\nRules:\n\n- src/instrument.js is measurement infrastructure; leave it exactly as it is.\n- Keep the measurement honest: keep calling `countComparison()` for every equality comparison the new implementation still performs. Deleting instrumentation instead of deleting work is measurement theater.\n- Measure with a repeatable command: a small script that builds a 200-item list, calls `findDuplicates`, and prints `comparisonCount()`.\n"
+      },
+      {
+        "path": "tests/verify-perf.mjs",
+        "surface": "harness",
+        "content": "import assert from 'node:assert/strict';\nimport { execFileSync } from 'node:child_process';\nimport { findDuplicates } from '../src/find-duplicates.js';\nimport { comparisonCount, resetComparisons } from '../src/instrument.js';\n\n// Independent reference: each duplicated value once, first-appearance order.\nfunction referenceDuplicates(items) {\n  const counts = new Map();\n  for (const item of items) counts.set(item, (counts.get(item) ?? 0) + 1);\n  const out = [];\n  const added = new Set();\n  for (const item of items) {\n    if ((counts.get(item) ?? 0) > 1 && !added.has(item)) {\n      added.add(item);\n      out.push(item);\n    }\n  }\n  return out;\n}\n\n// 1) Results identical to reference on small pinned cases.\nassert.deepEqual(findDuplicates(['a', 'b', 'a', 'c', 'b']), ['a', 'b']);\nassert.deepEqual(findDuplicates([]), []);\nassert.deepEqual(findDuplicates(['a', 'b', 'b', 'a']), ['a', 'b']);\n\n// 2) Deterministic 200-item workload: results equal reference AND the\n// instrumented op-count is under the stated budget (seeded code: 40000).\nconst items = [];\nfor (let i = 0; i < 200; i += 1) items.push('v' + ((i * 7) % 149));\nresetComparisons();\nconst result = findDuplicates(items);\nassert.deepEqual(result, referenceDuplicates(items), 'results changed - speed that changes answers is a bug');\nconsole.log('PERF_OPTIMIZATION_ORACLE results ok');\nconst ops = comparisonCount();\nassert.ok(\n  ops <= 2000,\n  'findDuplicates on 200 items performed ' + ops + ' instrumented comparisons - the budget is 2000 and the seeded code did 40000',\n);\nconsole.log('PERF_OPTIMIZATION_ORACLE ops ' + ops + ' within budget');\n\n// 3) The whole suite is green on the optimized tree (real run).\nfunction runSuite(cwd) {\n  try {\n    execFileSync(process.execPath, ['--test'], { cwd, stdio: 'pipe', timeout: 30000 });\n    return 0;\n  } catch (err) {\n    return typeof err.status === 'number' ? err.status : 1;\n  }\n}\nassert.equal(runSuite(process.cwd()), 0, 'the suite must be green on the optimized tree');\nconsole.log('PERF_OPTIMIZATION_ORACLE suite green');\nconsole.log('PERF_OPTIMIZATION_ORACLE done');\n"
+      }
+    ],
+    "craftbookParams": {
+      "workPath": "tasks/eval",
+      "scope": "findDuplicates in src/find-duplicates.js does about 40,000 instrumented comparisons for a 200-item list; get it near-linear (well under 2,000 comparisons) without changing its results. See source/perf-brief.md."
+    }
+  },
+  "success": {
+    "summary": "The quadratic rescan is gone, the instrumented op-count for 200 items is under budget, results are identical to the reference on a deterministic workload, the suite is green on a real run, and every fleet artifact exists with honest numbers and citations.",
+    "deliverables": [
+      {
+        "path": "tasks/eval/baseline.md",
+        "kind": "markdown-notes",
+        "artifact": true,
+        "minBytes": 500,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/baseline.md",
+            "pattern": "^##\\s+Current behavior[\\s\\S]*^##\\s+Measurements[\\s\\S]*^##\\s+Guardrail",
+            "flags": "im",
+            "label": "baseline sections in order"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/baseline.md",
+            "pattern": "^##\\s+Measurements[\\s\\S]*\\d",
+            "flags": "im",
+            "label": "baseline numbers recorded"
+          },
+          {
+            "kind": "citationsResolve",
+            "file": "tasks/eval/baseline.md",
+            "minCitations": 2,
+            "artifact": true
+          }
+        ]
+      },
+      {
+        "path": "tasks/eval/plan.md",
+        "kind": "markdown-notes",
+        "artifact": true,
+        "minBytes": 500,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/plan.md",
+            "pattern": "^##\\s+Target[\\s\\S]*^##\\s+Stages[\\s\\S]*^##\\s+Acceptance criteria",
+            "flags": "im",
+            "label": "plan sections in order"
+          },
+          {
+            "kind": "citationsResolve",
+            "file": "tasks/eval/plan.md",
+            "minCitations": 2,
+            "artifact": true
+          }
+        ]
+      },
+      {
+        "path": "tasks/eval/change-notes.md",
+        "kind": "markdown-notes",
+        "artifact": true,
+        "minBytes": 600,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/change-notes.md",
+            "pattern": "^##\\s+Stages executed[\\s\\S]*^##\\s+Files touched[\\s\\S]*^##\\s+Deviations from plan",
+            "flags": "im",
+            "label": "change-notes sections in order"
+          },
+          {
+            "kind": "citationsResolve",
+            "file": "tasks/eval/change-notes.md",
+            "minCitations": 2,
+            "artifact": true
+          }
+        ]
+      },
+      {
+        "path": "tasks/eval/verification.md",
+        "kind": "markdown-notes",
+        "artifact": true,
+        "minBytes": 400,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/verification.md",
+            "pattern": "^##\\s+Before\\s*/\\s*after[\\s\\S]*^##\\s+Suite[\\s\\S]*^##\\s+Result",
+            "flags": "im",
+            "label": "verification sections in order"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/verification.md",
+            "pattern": "^##\\s+Before\\s*/\\s*after[\\s\\S]*\\d",
+            "flags": "im",
+            "label": "both numbers quoted"
+          }
+        ]
+      },
+      {
+        "path": "tasks/eval/review.md",
+        "kind": "markdown-report",
+        "artifact": true,
+        "minBytes": 400,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/review.md",
+            "pattern": "Verdict:\\s*(?:PASS|REVISE)",
+            "flags": "i",
+            "label": "explicit reviewer verdict"
+          }
+        ]
+      }
+    ],
+    "checks": [
+      {
+        "kind": "notContains",
+        "file": "src/find-duplicates.js",
+        "pattern": "for\\s*\\(let j = 0; j < items\\.length",
+        "label": "the seeded inner full-list rescan is gone"
+      },
+      {
+        "kind": "sourceParses",
+        "file": "src/find-duplicates.js"
+      },
+      {
+        "kind": "nodeScriptPasses",
+        "script": "tests/verify-perf.mjs",
+        "timeoutMs": 60000,
+        "requiredOutput": [
+          {
+            "pattern": "PERF_OPTIMIZATION_ORACLE results ok",
+            "label": "results identical to the reference"
+          },
+          {
+            "pattern": "PERF_OPTIMIZATION_ORACLE ops \\d+ within budget",
+            "label": "instrumented op-count under the stated budget"
+          },
+          {
+            "pattern": "PERF_OPTIMIZATION_ORACLE suite green",
+            "label": "suite green on the optimized tree"
+          }
+        ]
+      }
+    ],
+    "taskNotes": {
+      "minBytes": 120,
+      "checks": [
+        {
+          "kind": "contains",
+          "file": "task-notes.md",
+          "pattern": "\\bDONE\\b[\\s\\S]*(npm\\s+run\\s+test|node\\s+--test)",
+          "flags": "i",
+          "label": "DONE note names the real test command"
+        }
+      ]
+    },
+    "taskGraph": {
+      "requireCraftbookTask": true,
+      "requireTerminalStep": true
+    },
+    "unchangedFixtures": [
+      "source/perf-brief.md",
+      "package.json",
+      "src/instrument.js"
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "tasks/eval/verification.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "Measurement honesty",
+        "description": "Baseline numbers were gathered by a stated, repeatable method before the change, and verification re-ran the identical method and quoted both figures side by side - no adjectives standing in for numbers, no swapped workload."
+      },
+      {
+        "name": "Bottleneck focus",
+        "description": "One bottleneck was named with its mechanism and fixed at the real site by that mechanism - not a synthetic proxy, a weakened measurement, or scattered micro-tweaks."
+      },
+      {
+        "name": "Correctness under speed",
+        "description": "Results stayed identical on the same inputs, the suite stayed green between stages with real receipts, and residual risk or unverified claims are labeled honestly."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "numbers with their method",
+    "same-method re-measurement",
+    "enforced review loop"
+  ]
+}