@bendyline/gilde 0.1.51 → 0.1.53

package/data/craftbook-templates/bu/bug-fix-tdd/versions/2.0.1/test.json

@@ -0,0 +1,221 @@
+{
+  "schemaVersion": 1,
+  "title": "Bug fix with red-then-green proof",
+  "objective": "The craftbook drives a disciplined fix of a seeded boundary bug: a failing reproduction test written into the real test layout, the smallest change at the real defect site, a green suite afterwards, and an enforced review — all verified mechanically, including a mutant run proving the regression guard bites.",
+  "tags": [
+    "code",
+    "bug-fix",
+    "tdd",
+    "tactical-fleet"
+  ],
+  "prompt": "Use the Reproduce-Then-Fix a Bug craftbook for this: customers report that buying exactly 10 of an item does not get the bulk discount, but the pricing page promises the discount at 10 or more. The report is in source/bug-report.md. Reproduce it with a failing test first, then fix it properly.",
+  "setup": {
+    "projectName": "Orderly Pricing",
+    "about": "A tiny order-pricing module for a web shop. Tests run with `npm run test` (node --test).",
+    "files": [
+      {
+        "path": "package.json",
+        "content": "{\n  \"name\": \"orderly\",\n  \"private\": true,\n  \"version\": \"1.0.0\",\n  \"type\": \"module\",\n  \"scripts\": {\n    \"test\": \"node --test\"\n  }\n}\n"
+      },
+      {
+        "path": "src/pricing.js",
+        "content": "const BULK_THRESHOLD = 10;\nconst BULK_DISCOUNT = 0.15;\n\nexport function lineTotal(unitPrice, qty) {\n  if (!Number.isFinite(unitPrice) || unitPrice < 0) throw new Error('bad unitPrice');\n  if (!Number.isInteger(qty) || qty < 0) throw new Error('bad qty');\n  const subtotal = unitPrice * qty;\n  if (qty > BULK_THRESHOLD) {\n    return round2(subtotal * (1 - BULK_DISCOUNT));\n  }\n  return round2(subtotal);\n}\n\nfunction round2(value) {\n  return Math.round(value * 100) / 100;\n}\n"
+      },
+      {
+        "path": "tests/pricing.test.mjs",
+        "content": "import assert from 'node:assert/strict';\nimport { test } from 'node:test';\nimport { lineTotal } from '../src/pricing.js';\n\ntest('small orders pay full price', () => {\n  assert.equal(lineTotal(4, 5), 20);\n});\n\ntest('large orders get the bulk discount', () => {\n  assert.equal(lineTotal(10, 20), 170);\n});\n\ntest('rejects bad quantities', () => {\n  assert.throws(() => lineTotal(4, -1));\n});\n"
+      },
+      {
+        "path": "source/bug-report.md",
+        "content": "# Bug report\n\nFrom support: \"Our pricing page says 'buy 10 or more, save 15%'. A customer bought exactly 10 units at 8.00 and was charged 80.00 - no discount. Buying 11 units gives the discount. Exactly 10 does not.\"\n\nExpected: 10 units at 8.00 with the 15% bulk discount = 68.00.\nActual: charged the full 80.00.\n"
+      },
+      {
+        "path": "tests/verify-pricing.mjs",
+        "content": "import assert from 'node:assert/strict';\nimport { execFileSync } from 'node:child_process';\nimport { cpSync, mkdirSync, readFileSync, readdirSync, rmSync, writeFileSync } from 'node:fs';\nimport { join } from 'node:path';\nimport { lineTotal } from '../src/pricing.js';\n\n// 1) Behavior: the boundary is fixed and the neighborhood still holds.\nassert.equal(lineTotal(8, 10), 68, 'exactly 10 units must get the bulk discount');\nassert.equal(lineTotal(8, 11), 74.8, 'above the threshold keeps the discount');\nassert.equal(lineTotal(8, 9), 72, 'below the threshold pays full price');\nassert.equal(lineTotal(4, 5), 20, 'small orders unchanged');\nconsole.log('BUGFIX_ORACLE behavior ok');\n\n// 2) Regression guard bites: rebuild the tree with the ORIGINAL seeded\n// defect and the test suite must now FAIL - proof that a reproduction\n// test exists and would catch a revert. The current tree's suite must\n// pass (green after the fix).\nconst root = process.cwd();\nconst mutantRoot = join(root, '.oracle-mutant');\nrmSync(mutantRoot, { recursive: true, force: true });\nmkdirSync(join(mutantRoot, 'src'), { recursive: true });\ncpSync(join(root, 'tests'), join(mutantRoot, 'tests'), { recursive: true });\nrmSync(join(mutantRoot, 'tests', 'verify-pricing.mjs'), { force: true });\ncpSync(join(root, 'package.json'), join(mutantRoot, 'package.json'));\nconst current = readFileSync(join(root, 'src', 'pricing.js'), 'utf8');\nconst mutant = current.replace(/qty\\s*>=\\s*BULK_THRESHOLD/g, 'qty > BULK_THRESHOLD').replace(/qty\\s*>=\\s*10/g, 'qty > 10');\nassert.notEqual(mutant, current, 'could not re-seed the defect - the fix should have made the threshold inclusive');\nwriteFileSync(join(mutantRoot, 'src', 'pricing.js'), mutant);\n\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}\n\nassert.equal(runSuite(root), 0, 'the suite must be green on the fixed tree');\nconsole.log('BUGFIX_ORACLE suite green');\nassert.notEqual(runSuite(mutantRoot), 0, 'reverting the fix must make at least one test fail - the regression guard is missing or toothless');\nconsole.log('BUGFIX_ORACLE mutant caught');\nconst testFiles = readdirSync(join(root, 'tests')).filter((f) => f.endsWith('.mjs') && f !== 'verify-pricing.mjs');\nassert.ok(testFiles.length >= 1, 'test layout missing');\nconsole.log('BUGFIX_ORACLE done');\n",
+        "surface": "harness"
+      }
+    ],
+    "craftbookParams": {
+      "scope": "Buying exactly 10 units does not get the bulk discount; see source/bug-report.md."
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "The seeded boundary defect is fixed at the real site, the suite is green, a regression test catches a revert (mutant run), and every fleet artifact exists with honest citations.",
+    "deliverables": [
+      {
+        "path": "{{task.dir}}/repro.md",
+        "kind": "markdown-notes",
+        "artifact": true,
+        "minBytes": 500,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "{{task.dir}}/repro.md",
+            "pattern": "^##\\s+Symptom[\\s\\S]*^##\\s+Repro command[\\s\\S]*^##\\s+Expected[\\s\\S]*^##\\s+Actual[\\s\\S]*^##\\s+Red evidence",
+            "flags": "im",
+            "label": "reproduction sections in order"
+          },
+          {
+            "kind": "citationsResolve",
+            "file": "{{task.dir}}/repro.md",
+            "minCitations": 2,
+            "artifact": true
+          }
+        ]
+      },
+      {
+        "path": "{{task.dir}}/diagnosis.md",
+        "kind": "markdown-notes",
+        "artifact": true,
+        "minBytes": 600,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "{{task.dir}}/diagnosis.md",
+            "pattern": "^##\\s+Defect site[\\s\\S]*^##\\s+Causal chain[\\s\\S]*^##\\s+Siblings checked",
+            "flags": "im",
+            "label": "diagnosis sections in order"
+          },
+          {
+            "kind": "contains",
+            "file": "{{task.dir}}/diagnosis.md",
+            "pattern": "src/pricing\\.js",
+            "label": "names the real defect site"
+          }
+        ]
+      },
+      {
+        "path": "{{task.dir}}/fix-notes.md",
+        "kind": "markdown-notes",
+        "artifact": true,
+        "minBytes": 700,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "{{task.dir}}/fix-notes.md",
+            "pattern": "^##\\s+Problem[\\s\\S]*^##\\s+Change[\\s\\S]*^##\\s+Files touched[\\s\\S]*^##\\s+Regression coverage[\\s\\S]*^##\\s+Risk[\\s\\S]*^##\\s+How to verify",
+            "flags": "im",
+            "label": "fix-notes sections in order"
+          },
+          {
+            "kind": "citationsResolve",
+            "file": "{{task.dir}}/fix-notes.md",
+            "minCitations": 2,
+            "artifact": true
+          }
+        ]
+      },
+      {
+        "path": "{{task.dir}}/validation.md",
+        "kind": "markdown-notes",
+        "artifact": true,
+        "minBytes": 400,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "{{task.dir}}/validation.md",
+            "pattern": "^##\\s+Repro re-run[\\s\\S]*^##\\s+Suite[\\s\\S]*^##\\s+Result",
+            "flags": "im",
+            "label": "validation sections in order"
+          }
+        ]
+      },
+      {
+        "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/pricing.js",
+        "pattern": "qty\\s*>\\s*BULK_THRESHOLD|qty\\s*>\\s*10\\b",
+        "label": "the seeded exclusive-threshold defect is gone"
+      },
+      {
+        "kind": "sourceParses",
+        "file": "src/pricing.js"
+      },
+      {
+        "kind": "nodeRuns",
+        "file": "tests/pricing.test.mjs"
+      },
+      {
+        "kind": "nodeScriptPasses",
+        "script": "tests/verify-pricing.mjs",
+        "timeoutMs": 60000,
+        "requiredOutput": [
+          {
+            "pattern": "BUGFIX_ORACLE behavior ok",
+            "label": "boundary behavior fixed"
+          },
+          {
+            "pattern": "BUGFIX_ORACLE suite green",
+            "label": "suite green on the fixed tree"
+          },
+          {
+            "pattern": "BUGFIX_ORACLE mutant caught",
+            "label": "regression guard catches a revert"
+          }
+        ]
+      }
+    ],
+    "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/bug-report.md",
+      "package.json"
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "{{task.dir}}/fix-notes.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "Repro-first discipline",
+        "description": "A failing test was genuinely written and run before the fix, in the project's real test layout, and the red evidence quotes a real run rather than a claim."
+      },
+      {
+        "name": "Fix minimality",
+        "description": "The change is the smallest correct edit at the real defect site; no special-casing of the reported input, no unrelated churn."
+      },
+      {
+        "name": "Honest verification",
+        "description": "Validation re-ran the original reproduction, distinguishes verified results from anything unverified, and the review graded evidence rather than summaries."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "red-then-green proof",
+    "real-path citations",
+    "enforced review loop"
+  ]
+}

package/data/craftbook-templates/bu/build-loop/versions/1.1.1/craftbook.json

@@ -0,0 +1,139 @@
+{
+  "id": "build-loop",
+  "name": "Build Loop",
+  "description": "A generic **make-something** procedure: `build → evaluate → (loop) → finish`.\n\nIt exists for the common case where the user wants a thing built (\"make an arcade game\", \"build a landing page\", \"write a script that does X\") and no domain-specific craftbook fits better. It gives a small/medium model the thing it loses on multi-phase work: a **durable structure with a gate** — so it drives one deliverable to a checkable bar instead of declaring victory early.\n\n## How the loop works\n\n1. **Build** (developer) first writes an **acceptance-criteria checklist** to task notes, then builds the deliverable to meet it. For a web build that's `index.html`.\n2. **Evaluate** (reviewer) grades the deliverable against every criterion and routes: all pass → `advance_task_step(next: \"finish\")`; any fail → write the gaps → `advance_task_step(next: \"build\")` to loop back.\n3. **Finish** stamps a DONE summary.\n\nEvaluate's default forward edge loops back to **Build**, not Finish — so the safe failure mode is \"keep improving\", never \"ship half-done\".\n\n## Advancement rides on the deliverable, not a meta-tool call\n\nThe Build step declares an `advanceWhen` contract: when a complete `index.html` lands (clears a size floor + a non-truncation `html-complete` sniff), the runtime advances Build → Evaluate **automatically**, without the model calling `advance_task_step`. This is deliberate: models reliably *do work* (`write_file`) but reliably *skip* the meta-navigation tool — two eval runs (gemma4-31b, gemma4-e4b-q8) produced the deliverable and advanced **zero** steps. Observable-progress auto-advance closes that gap. For a non-`index.html` deliverable the auto-advance is a no-op and Build advances model-driven (its prompt says so).\n\n## Why criteria-first matters for small models\n\nThe acceptance-criteria checklist is the scaffold. Without it a weak model declares victory early; with it, \"is this good?\" becomes \"does criterion 4 pass?\" — answerable even by a small model, and the thing the gate and the next loop iteration check against.\n\n## Specific books beat this one\n\nThis is the **fallback**. A domain craftbook earns its keep by encoding things this generic shape can't: the right *specialist role per phase* (a space-shooter splits design into a game-designer and a visual-designer) and the *domain-correct ordering* (a branding site locks a visual language before any HTML). When selection finds a specific match, prefer it; fall back to Build Loop when nothing fits. In a **solo** project the meester pins this book with every step collapsed onto the one specialist (it can't recruit); in a **crew** project it pins the matching multi-role gallery book instead.\n\n## Roles are suggestions\n\n`build → developer`, `evaluate → reviewer` are `suggestedRole` hints resolved via `ensureGezel`; domain gallery books override them (game-designer, visual-designer, copywriter, …).\n\n## Next: an automated evaluate gate\n\nEvaluate is still reviewer-gated (a gezel grades + routes). The follow-up replaces its routing with a script that judges and advances deterministically — now reachable because observable-advance gets the workflow *to* Evaluate without depending on the model to navigate there.\n",
+  "entryStepId": "build",
+  "steps": [
+    {
+      "id": "build",
+      "name": "Build",
+      "description": "Lock concrete acceptance criteria, then build the deliverable to meet them. The workflow advances to Evaluate automatically when the deliverable lands.",
+      "prompt": "**Two things, in order.**\n\n1. **Lock the bar.** Write an **acceptance-criteria checklist** to task notes via `write_task_note` — 4-8 concrete, checkable statements that define \"good enough\" (e.g. \"clicking Start begins play\", \"score increments on a hit\", \"page loads with no console error\"). This is the contract Evaluate grades against; without it the loop has no target.\n2. **Build it.** Create the real deliverable with your file-writing capability, to satisfy every criterion. For a web build that's `index.html` (inline CSS + JS, no build step). On a loop-back from Evaluate, read the gaps in notes and fix ONLY those — don't regress criteria that already passed.\n\n**Advancing:** the workflow moves you to Evaluate automatically when you actually WRITE `index.html` this turn — you do NOT need to call `advance_task_step`. On a loop-back, narrating the gaps is not enough: the step holds until you make a real edit to `index.html`. For any other deliverable path, write the file, then call `advance_task_step({ ref, stepId: \"build\", next: \"evaluate\" })` yourself.",
+      "suggestedRole": "developer",
+      "advanceWhen": {
+        "file": "index.html",
+        "minBytes": 800,
+        "sniff": "html-complete",
+        "requireChange": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "index.html",
+            "bytes": 2048
+          },
+          {
+            "kind": "jsParses",
+            "file": "index.html"
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkHtmlComplete",
+            "scope": "standard",
+            "inputs": {
+              "file": "index.html"
+            }
+          }
+        ],
+        "onReject": "build",
+        "maxAttempts": 4
+      },
+      "next": "evaluate",
+      "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"
+        ],
+        "outputMedium": "workspace",
+        "additionalOutputMedia": [
+          "task-note"
+        ]
+      }
+    },
+    {
+      "id": "evaluate",
+      "name": "Evaluate",
+      "description": "Grade the deliverable against EVERY acceptance criterion. All pass → finish. Any fail → write the gaps and loop back to Build.",
+      "prompt": "**You are the gate. Judge, then route — do not build here.**\n\n1. `read_task_notes({ ref })` for the acceptance-criteria checklist + the deliverable path.\n2. Open the deliverable and check it against each criterion (exercise it in a browser/with a test capability if the project has one — don't grade from source alone when you can observe behavior). Write a PASS/FAIL per criterion to notes.\n\nThen route:\n\n- **Every criterion PASSES →** `advance_task_step({ ref, stepId: \"evaluate\", next: \"finish\" })`.\n- **Any criterion FAILS →** write the specific gaps to notes, then `advance_task_step({ ref, stepId: \"evaluate\", next: \"build\" })` to loop back.\n\nNever route to `finish` with an unmet criterion — under-delivering is the failure this gate exists to catch. After ~3 unproductive loops, stop and report DONE_WITH_CONCERNS so the user can step in.",
+      "suggestedRole": "reviewer",
+      "next": "build",
+      "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"
+      }
+    },
+    {
+      "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": "1.1.1",
+  "releasedAt": "2026-09-01T20:00:00Z"
+}

package/data/craftbook-templates/bu/build-loop/versions/1.1.1/test.json

@@ -0,0 +1,121 @@
+{
+  "schemaVersion": 1,
+  "title": "Generic build-evaluate loop",
+  "objective": "Measure whether the fallback build-loop craftbook creates acceptance criteria, builds a complete interactive deliverable, and iterates through deterministic gates.",
+  "tags": [
+    "external"
+  ],
+  "prompt": "In the `Build Loop Eval` project, build a self-contained `index.html` checklist timer for a small workshop. It must let a facilitator add agenda items, mark items done, start/pause a countdown timer, reset the timer, show remaining time, and display a completion summary. Lock acceptance criteria in task notes first, then build the page with inline CSS/JS and no external assets.",
+  "setup": {
+    "projectName": "Build Loop Eval",
+    "about": "Self-contained eval project for the build-loop craftbook. The deliverable is workspace/index.html.",
+    "missionObjectives": "Build an interactive checklist timer with acceptance criteria, add/complete agenda behavior, start/pause/reset timer, remaining time display, and completion summary.",
+    "files": [],
+    "worker": {
+      "name": "Bram",
+      "role": "Developer"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "workspace/index.html is a complete interactive checklist timer with substantial JS/CSS and task notes show the criteria-first loop was used.",
+    "deliverables": [
+      {
+        "path": "index.html",
+        "kind": "html-page",
+        "minBytes": 3200,
+        "checks": [
+          {
+            "kind": "cssMinBytes",
+            "bytes": 650,
+            "file": "index.html"
+          },
+          {
+            "kind": "jsParses",
+            "file": "index.html"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "agenda|checklist",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "start|pause|reset",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "remaining|countdown|timer",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "complete|summary",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "addEventListener|setInterval",
+            "flags": "i"
+          }
+        ]
+      }
+    ],
+    "taskNotes": {
+      "minBytes": 160,
+      "checks": [
+        {
+          "kind": "contains",
+          "file": "task-notes.md",
+          "pattern": "acceptance criteria|criteria checklist",
+          "flags": "i"
+        }
+      ]
+    }
+  },
+  "rubric": {
+    "artifact": {
+      "path": "index.html",
+      "kind": "html"
+    },
+    "axes": [
+      {
+        "name": "safety",
+        "description": "Dry-run posture is explicit: no real credentials, clear stop-before-side-effect boundary."
+      },
+      {
+        "name": "mapping",
+        "description": "Fake endpoints/commands are mapped completely to the workflow steps."
+      },
+      {
+        "name": "signals",
+        "description": "Success, failure, retry, and abort conditions are all defined."
+      },
+      {
+        "name": "containment",
+        "description": "The plan cannot accidentally reach a real service from a mock context."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "criteria-first build",
+    "loop behavior",
+    "interactive HTML gates"
+  ],
+  "extensions": {
+    "legacySimulators": [
+      {
+        "id": "build-loop-fake-service-fixture",
+        "kind": "data-source",
+        "status": "implemented",
+        "description": "Seeded local fake service contract replacing live CLIs, HTTP APIs, credentials, and side effects."
+      }
+    ]
+  }
+}