@bendyline/gilde 0.1.50 → 0.1.52

package/data/craftbook-templates/pe/perf-optimization/versions/2.0.1/test.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",
+        "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",
+        "surface": "harness"
+      }
+    ],
+    "craftbookParams": {
+      "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."
+    }
+  },
+  "mocks": [],
+  "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": "{{task.dir}}/baseline.md",
+        "kind": "markdown-notes",
+        "artifact": true,
+        "minBytes": 500,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "{{task.dir}}/baseline.md",
+            "pattern": "^##\\s+Current behavior[\\s\\S]*^##\\s+Measurements[\\s\\S]*^##\\s+Guardrail",
+            "flags": "im",
+            "label": "baseline sections in order"
+          },
+          {
+            "kind": "contains",
+            "file": "{{task.dir}}/baseline.md",
+            "pattern": "^##\\s+Measurements[\\s\\S]*\\d",
+            "flags": "im",
+            "label": "baseline numbers recorded"
+          },
+          {
+            "kind": "citationsResolve",
+            "file": "{{task.dir}}/baseline.md",
+            "minCitations": 2,
+            "artifact": true
+          }
+        ]
+      },
+      {
+        "path": "{{task.dir}}/plan.md",
+        "kind": "markdown-notes",
+        "artifact": true,
+        "minBytes": 500,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "{{task.dir}}/plan.md",
+            "pattern": "^##\\s+Target[\\s\\S]*^##\\s+Stages[\\s\\S]*^##\\s+Acceptance criteria",
+            "flags": "im",
+            "label": "plan sections in order"
+          },
+          {
+            "kind": "citationsResolve",
+            "file": "{{task.dir}}/plan.md",
+            "minCitations": 2,
+            "artifact": true
+          }
+        ]
+      },
+      {
+        "path": "{{task.dir}}/change-notes.md",
+        "kind": "markdown-notes",
+        "artifact": true,
+        "minBytes": 600,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "{{task.dir}}/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": "{{task.dir}}/change-notes.md",
+            "minCitations": 2,
+            "artifact": true
+          }
+        ]
+      },
+      {
+        "path": "{{task.dir}}/verification.md",
+        "kind": "markdown-notes",
+        "artifact": true,
+        "minBytes": 400,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "{{task.dir}}/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": "{{task.dir}}/verification.md",
+            "pattern": "^##\\s+Before\\s*/\\s*after[\\s\\S]*\\d",
+            "flags": "im",
+            "label": "both numbers quoted"
+          }
+        ]
+      },
+      {
+        "path": "{{task.dir}}/review.md",
+        "kind": "markdown-report",
+        "artifact": true,
+        "minBytes": 400,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "{{task.dir}}/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": "{{task.dir}}/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"
+  ]
+}

package/data/craftbook-templates/pe/pest-diagnosis/versions/1.0.2/test.json

@@ -27,9 +27,6 @@
     "worker": {
       "name": "Wim",
       "role": "Gardener"
-    },
-    "craftbookParams": {
-      "workPath": "tasks/eval"
     }
   },
   "mocks": [],

package/data/craftbook-templates/pe/pest-diagnosis/versions/1.0.3/craftbook.json

@@ -0,0 +1,276 @@
+{
+  "id": "pest-diagnosis",
+  "name": "Pest & Problem Diagnosis",
+  "description": "Turn 'something is wrong with the tomatoes' into a ranked differential: the likely culprits with the evidence for each, the gentlest treatment first, what to watch to confirm the diagnosis, and when to call in a professional — a garden clinic visit without the guesswork. Locks the diagnostic criteria FIRST, then builds the differential from the symptom notes and the plantings, then writes the treatment and monitoring plan. Use for garden pest problems, plant disease diagnosis, 'what is eating my plants', and sick-plant triage.\n\nA gallery craftbook generated from an archetype spec. It runs\n`phase → (per-phase gate) → … → evaluate → (loop) → finish`. Each build\nphase that produces a checkable artifact is followed by a **runtime\ngate-checkpoint** — the runtime verifies the artifact and routes with no\nmodel turn, looping back to redo the phase on a miss. The final `evaluate`\nstep holds a static deliverable gate plus a reviewer QA pass. What it adds\nover the generic `build-loop`: a specialist role per phase, a\ndomain-correct ordering, and a concrete per-phase quality bar.\n\nDeliverables marked \"artifact\" land in the project's artifacts drawer (`write_artifact` / `read_artifact`), not the shipped workspace — review output is not product source.\n\nPhases:\n\n1. Scope the diagnosis (gardener) — symptoms and plantings gathered, diagnostic criteria locked → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Build the differential (researcher) — ranked candidates with evidence for and against each → gated on artifact `{{workPath}}/diagnosis.md` (markdown-notes)\n3. Write the treatment plan (copywriter) — treatment ladder, monitoring plan, escalation line → gated on artifact `{{workPath}}/report.md` (markdown-report)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "scope",
+  "triggers": [
+    "diagnose a garden pest",
+    "what is eating my plants",
+    "plant disease diagnosis",
+    "something is wrong with the tomatoes",
+    "garden problem triage"
+  ],
+  "paramSchema": {
+    "type": "object",
+    "properties": {
+      "workPath": {
+        "type": "string",
+        "title": "Working folder",
+        "description": "Per-task working folder in the artifacts drawer. Defaults to this task's own folder so runs never collide; override with a stable name when you deliberately want runs to share files.",
+        "default": "{{task.dir}}"
+      }
+    }
+  },
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the diagnosis",
+      "description": "symptoms and plantings gathered, diagnostic criteria locked",
+      "prompt": "Define the diagnosis before naming a culprit. Step 1: read the symptom photo notes in photos/ and identify the affected plantings in garden.json — what is planted there, since when, and what the season makes likely. Step 2: lock the diagnostic criteria — at least two candidate explanations per problem, ranked; the specific evidence for and against each; the gentlest effective treatment considered first; and the escalation threshold — what result, by when, means calling in a professional. Step 3: write an acceptance-criteria checklist ('every symptom from the notes addressed', 'candidates ranked with evidence, not asserted', 'organic or lowest-impact option first', 'monitoring plan with dates', 'escalation named'). Call write_task_note with the symptoms + criteria + checklist and write {{workPath}}/scope.md.\n\nThe deliverable `{{workPath}}/scope.md` lands in the project's artifacts drawer — write it with `write_artifact` and read it back with `read_artifact`; the shipped workspace stays untouched.",
+      "suggestedRole": "gardener",
+      "advanceWhen": {
+        "file": "{{workPath}}/scope.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/scope.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/scope.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "scope",
+        "maxAttempts": 3
+      },
+      "next": "diagnose",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "artifact",
+        "additionalOutputMedia": [
+          "task-note"
+        ]
+      }
+    },
+    {
+      "id": "diagnose",
+      "name": "Build the differential",
+      "description": "ranked candidates with evidence for and against each",
+      "prompt": "Build the differential against the locked criteria. Step 1: for each symptom, list the candidate culprits the evidence actually supports — the photo notes, the plant, the season, the pattern of damage. Step 2: rank the candidates and write the evidence for and against each, including what does not fit. Step 3: note what a second look would settle — the underside of a leaf, the time of day the damage happens — the cheap observations worth making before any treatment. Step 4: write the differential to {{workPath}}/diagnosis.md and call write_task_note with the top candidate per symptom.\n\nThe deliverable `{{workPath}}/diagnosis.md` lands in the project's artifacts drawer — write it with `write_artifact` and read it back with `read_artifact`; the shipped workspace stays untouched.",
+      "suggestedRole": "researcher",
+      "advanceWhen": {
+        "file": "{{workPath}}/diagnosis.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/diagnosis.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/diagnosis.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "diagnose",
+        "maxAttempts": 3
+      },
+      "next": "report",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "artifact",
+        "additionalOutputMedia": [
+          "task-note"
+        ]
+      }
+    },
+    {
+      "id": "report",
+      "name": "Write the treatment plan",
+      "description": "treatment ladder, monitoring plan, escalation line",
+      "prompt": "Write the treatment and monitoring plan from the differential. Step 1: per problem, the likely culprit in plain words with its evidence, and what else it could be. Step 2: the treatment ladder — the gentlest effective option first, with exactly how and when to apply it, then the next rung if it fails. Step 3: the monitoring plan — what to watch, how often, and what change confirms or overturns the diagnosis. Step 4: the escalation line — the specific sign that means stop guessing and call a professional or the local extension service. Keep the confidence honest — a diagnosis from photo notes is a strong hunch, not a lab result. Write {{workPath}}/report.md and call write_task_note with the top culprits and the first treatment.\n\nThe deliverable `{{workPath}}/report.md` lands in the project's artifacts drawer — write it with `write_artifact` and read it back with `read_artifact`; the shipped workspace stays untouched.",
+      "suggestedRole": "copywriter",
+      "advanceWhen": {
+        "file": "{{workPath}}/report.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/report.md",
+            "bytes": 1200,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i",
+            "label": "at least one markdown heading",
+            "artifact": true
+          }
+        ],
+        "onReject": "report",
+        "maxAttempts": 4
+      },
+      "next": "evaluate",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "artifact",
+        "additionalOutputMedia": [
+          "task-note"
+        ]
+      }
+    },
+    {
+      "id": "evaluate",
+      "name": "Evaluate",
+      "description": "Grade the deliverable against every acceptance criterion. All pass → finish; any fail → loop back and fix the gap.",
+      "prompt": "Open {{workPath}}/report.md and {{workPath}}/diagnosis.md and verify every criterion from {{workPath}}/scope.md: every symptom from the photo notes is addressed, each problem carries at least two ranked candidates with evidence, the first treatment offered is the gentlest effective one, the monitoring plan says what to watch and when, the escalation threshold is named, and nowhere does the report claim certainty the evidence cannot support. Write PASS/FAIL per criterion; on any failure, name the gap and loop back to report.\n\nThe deliverable lives in the project's artifacts drawer — open `{{workPath}}/report.md` with `read_artifact`, not `read_file`.\n\nThen route — this is the whole point of the loop:\n\n- **Every criterion PASSES →** call `advance_task_step({ ref, stepId: \"evaluate\", next: \"finish\" })`.\n- **Any criterion FAILS →** write the specific gaps to notes, then call `advance_task_step({ ref, stepId: \"evaluate\", next: \"report\" })` to loop back. The builder fixes exactly those gaps.\n\nNever route to `finish` while any criterion is unmet. The build phase's completion gate already blocked a grossly-incomplete deliverable; your job is the judgment an automated check cannot make (does it actually work, read well, look right). After ~3 unproductive loops, stop and report DONE_WITH_CONCERNS so the user can step in.",
+      "suggestedRole": "reviewer",
+      "consumes": [
+        {
+          "file": "{{workPath}}/report.md",
+          "artifact": true
+        }
+      ],
+      "next": "report",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "task-note"
+      }
+    },
+    {
+      "id": "finish",
+      "name": "Finish",
+      "description": "All acceptance criteria met. Stamp a short summary and report DONE.",
+      "prompt": "Every acceptance criterion passed. Write a one-paragraph DONE summary to task notes via `write_task_note`: what was built, the deliverable path(s), and a one-line confirmation that each criterion is met. Then report DONE.",
+      "suggestedRole": "developer",
+      "terminal": true,
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "artifacts",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "task-note"
+      }
+    }
+  ],
+  "version": "1.0.3",
+  "releasedAt": "2026-09-01T20:00:00Z",
+  "minGezelVersion": "1.26233"
+}

package/data/craftbook-templates/pe/pest-diagnosis/versions/1.0.3/test.json

@@ -0,0 +1,122 @@
+{
+  "schemaVersion": 1,
+  "title": "Pest & Problem Diagnosis smoke eval",
+  "objective": "Task-specific eval for the Pest & Problem Diagnosis craftbook: two pre-extracted symptom photo notes become a ranked differential with a gentle-first treatment ladder, a monitoring plan, and a named escalation line.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "somethings eating the kale and the tomato leaves have yellow spots — photo notes are in photos/. what do you thinck it is and what do we do?",
+  "setup": {
+    "projectName": "Garden Almanac — Pest Diagnosis Eval",
+    "about": "Self-contained eval project for pest-diagnosis. The symptom photos have already been pre-extracted into plain-text photo notes under photos/. The garden's plantings live at garden.json in the workspace; the treatment and monitoring plan goes to tasks/eval/report.md.",
+    "missionObjectives": "Use the Pest & Problem Diagnosis craftbook/template, reason only from the seeded photo notes and plantings, and write tasks/eval/report.md — no network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "photos/kale-damage.jpg.txt",
+        "content": "PHOTO NOTE (pre-extracted from kale-damage.jpg)\n\nRagged irregular holes across the outer kale leaves, edges chewed inward.\nSmall velvety green caterpillars, about 2 cm, found on the leaf undersides.\nDark green droppings collected in the leaf folds.\nSmall white butterflies seen fluttering around the bed in the afternoons.\n"
+      },
+      {
+        "path": "photos/tomato-leaf.jpg.txt",
+        "content": "PHOTO NOTE (pre-extracted from tomato-leaf.jpg)\n\nLower tomato leaves show yellow blotches with brown centers.\nSeveral spots have faint concentric rings, target-like.\nAffected leaves are the lowest on the plant, spreading slowly upward.\nStems clean so far; fruit unaffected.\nOwner notes the bed gets overhead watering in the evenings.\n"
+      },
+      {
+        "path": "garden.json",
+        "content": "{\n  \"zone\": \"8b\",\n  \"lastFrost\": \"2026-04-05\",\n  \"firstFrost\": \"2026-11-05\",\n  \"beds\": [\n    {\n      \"name\": \"North Bed\",\n      \"plantings\": [\n        { \"plant\": \"tomatoes\", \"variety\": \"San Marzano\", \"planted\": \"2026-05-02\" },\n        { \"plant\": \"basil\", \"planted\": \"2026-05-16\" }\n      ]\n    },\n    {\n      \"name\": \"Greens Bed\",\n      \"plantings\": [\n        { \"plant\": \"kale\", \"variety\": \"Lacinato\", \"planted\": \"2026-06-01\" },\n        { \"plant\": \"chard\", \"planted\": \"2026-06-01\" }\n      ]\n    }\n  ]\n}\n"
+      }
+    ],
+    "worker": {
+      "name": "Wim",
+      "role": "Gardener"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "tasks/eval/report.md ranks candidates for both problems with the photo-note evidence, offers the gentlest treatment first, sets a monitoring plan, names the escalation line, and never claims certainty.",
+    "deliverables": [
+      {
+        "path": "tasks/eval/report.md",
+        "kind": "markdown-report",
+        "minBytes": 800,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "likely|probable|possible|suspect",
+            "flags": "i",
+            "label": "candidates stated as likelihoods, not verdicts"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "caterpillar",
+            "flags": "i",
+            "label": "engages the caterpillar evidence from the kale photo note"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "treat",
+            "flags": "i",
+            "label": "treatment ladder present"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "monitor|watch|check",
+            "flags": "i",
+            "label": "monitoring plan present"
+          },
+          {
+            "kind": "notContains",
+            "file": "tasks/eval/report.md",
+            "pattern": "(definitely|guaranteed|certainly) (is|will cure)",
+            "flags": "i",
+            "label": "diagnosis stays hedged, never absolute"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "extension|professional|nursery|expert",
+            "flags": "i",
+            "label": "escalation path named"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "tasks/eval/report.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "diagnostic-reasoning",
+        "description": "Each problem carries at least two ranked candidates whose evidence traces to the photo notes, including what does not fit."
+      },
+      {
+        "name": "hedging",
+        "description": "Confidence stays honest — a photo-note diagnosis is presented as a strong hunch, never a lab result."
+      },
+      {
+        "name": "actionability",
+        "description": "The treatment ladder starts gentle with concrete how-and-when, and the monitoring plan has dates."
+      },
+      {
+        "name": "safety",
+        "description": "Lowest-impact options come first, and the escalation threshold to a professional is specific."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "ranked differential",
+    "gentle-first treatment",
+    "honest confidence"
+  ]
+}

package/data/craftbook-templates/ph/photo-cull/versions/1.0.2/test.json

@@ -23,9 +23,6 @@
     "worker": {
       "name": "Jules",
       "role": "Producer"
-    },
-    "craftbookParams": {
-      "workPath": "tasks/eval"
     }
   },
   "mocks": [],