@bendyline/gilde 0.1.26 → 0.1.28

package/data/craftbook-templates/tr/transcribe-index/versions/1.0.1/test.json

@@ -0,0 +1,151 @@
+{
+  "schemaVersion": 1,
+  "title": "Transcribe and Index a Tape smoke eval",
+  "objective": "Task-specific eval for the Transcribe and Index a Tape craftbook: a provided timestamped transcript of a family tape becomes appended clip records in the archive index — real timecodes, roster-true people tags, searchable descriptions — plus a warm tape summary.",
+  "tags": [
+    "data"
+  ],
+  "prompt": "digitized tape 4 last night and the transcript is already in the project — can you index the momments so we can actually find things later?",
+  "setup": {
+    "projectName": "Home Video Archive — Tape Index Eval",
+    "about": "Self-contained eval project for transcribe-index. The transcript for tape-04 is already on file at transcripts/tape-04.md (timestamped tape time). The archive index is clips.json (six records from tapes 01-03 — append, never rewrite), the family roster is family.md, and the prior indexing log is notes/archive-log.md. The tape summary goes to report.md.",
+    "missionObjectives": "Use the Transcribe and Index a Tape craftbook/template, treat the provided transcript as the source, append the tape's notable moments to clips.json with timecodes from the transcript and people tags from the roster, and write report.md. No transcription services or real media tools — the transcript is provided.",
+    "files": [
+      {
+        "path": "transcripts/tape-04.md",
+        "content": "# Tape 04 - Opa Willem's 80th birthday (spring 1998)\n\nDigitized from VHS. Timestamps are tape time.\n\n[00:00:40] Guests arriving at the farmhouse. Oma Ria at the door taking coats, waving at the camera.\n[00:03:12] Marloes and Sofie stringing the paper garlands in the kitchen, arguing sweetly about the ladder.\n[00:08:55] Opa Willem's toast. He stands, taps the glass, and gives the speech everyone still quotes - eighty years and the same bicycle. The whole room on its feet by the end.\n[00:14:30] The singing. Tante Els starts Lang zal hij leven and the room joins in, second verse louder than the first.\n[00:21:05] Jeroen tells the flooded-kitchen story from 1976. Opa Willem laughing so hard he has to put his glass down.\n[00:27:48] Bram's first steps, right there in the background while the cake is being served. Half the room misses it, the camera does not.\n[00:33:20] A quiet moment. Opa Willem and Oma Ria alone on the bench by the window, saying nothing.\n[00:38:02] Goodbyes at the door, headlights in the lane, Oma Ria waving until the last car turns.\n"
+      },
+      {
+        "path": "clips.json",
+        "content": "[\n  {\n    \"tape\": \"tape-01\",\n    \"timecode\": \"00:02:10\",\n    \"people\": [\n      \"Opa Willem\",\n      \"Oma Ria\"\n    ],\n    \"description\": \"Willem and Ria dancing at the 1985 street party\"\n  },\n  {\n    \"tape\": \"tape-01\",\n    \"timecode\": \"00:19:44\",\n    \"people\": [\n      \"Tante Els\"\n    ],\n    \"description\": \"Els singing at the piano, street party evening\"\n  },\n  {\n    \"tape\": \"tape-02\",\n    \"timecode\": \"00:05:31\",\n    \"people\": [\n      \"Marloes\",\n      \"Sofie\"\n    ],\n    \"description\": \"the sisters learning to ride one bike between them\"\n  },\n  {\n    \"tape\": \"tape-02\",\n    \"timecode\": \"00:28:07\",\n    \"people\": [\n      \"Jeroen\"\n    ],\n    \"description\": \"Jeroen's infamous fishing cast into the reeds\"\n  },\n  {\n    \"tape\": \"tape-03\",\n    \"timecode\": \"00:11:59\",\n    \"people\": [\n      \"Opa Willem\",\n      \"Jeroen\"\n    ],\n    \"description\": \"Willem teaching Jeroen to sharpen a chisel\"\n  },\n  {\n    \"tape\": \"tape-03\",\n    \"timecode\": \"00:36:22\",\n    \"people\": [\n      \"Oma Ria\",\n      \"Marloes\"\n    ],\n    \"description\": \"Ria and Marloes baking, flour everywhere\"\n  }\n]\n"
+      },
+      {
+        "path": "family.md",
+        "content": "# Family roster\n\n- Opa Willem - grandfather, the storyteller of the family\n- Oma Ria - grandmother, married to Willem since 1948\n- Tante Els - Willem and Ria's eldest, starts every song\n- Marloes - granddaughter, organized most of the parties\n- Jeroen - grandson, keeper of the embarrassing stories\n- Sofie - granddaughter, Marloes' sister\n- Bram - great-grandson, born 1997\n"
+      },
+      {
+        "path": "notes/archive-log.md",
+        "content": "# Indexing log - prior tapes\n\nMoments indexed so far, by tape and tape-time:\n\n- tape-01 [00:02:10] Willem and Ria dancing at the 1985 street party\n- tape-01 [00:19:44] Els singing at the piano\n- tape-02 [00:05:31] the sisters and the shared bike\n- tape-02 [00:28:07] the fishing cast into the reeds\n- tape-03 [00:11:59] the chisel-sharpening lesson\n- tape-03 [00:36:22] baking day, flour everywhere\n"
+      }
+    ],
+    "worker": {
+      "name": "Fem",
+      "role": "Archivist"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "clips.json grew by at least five tape-04 records whose timecodes come verbatim from the transcript, people tags match the roster, the six prior records survived untouched, and report.md reads like a family document with real highlights.",
+    "deliverables": [
+      {
+        "path": "clips.json",
+        "kind": "json",
+        "checks": [
+          {
+            "kind": "recordSchema",
+            "file": "clips.json",
+            "fields": [
+              {
+                "name": "tape",
+                "type": "nonempty"
+              },
+              {
+                "name": "timecode",
+                "type": "nonempty"
+              },
+              {
+                "name": "people"
+              },
+              {
+                "name": "description",
+                "type": "nonempty"
+              }
+            ],
+            "minRows": 11
+          },
+          {
+            "kind": "valuesSubsetOf",
+            "file": "clips.json",
+            "sourceFiles": [
+              "transcripts/tape-04.md",
+              "notes/archive-log.md"
+            ],
+            "pattern": "\"(\\d{2}:\\d{2}:\\d{2})\"",
+            "label": "every timecode comes verbatim from the transcript or the prior indexing log"
+          },
+          {
+            "kind": "contains",
+            "file": "clips.json",
+            "pattern": "toast",
+            "flags": "i",
+            "label": "the famous toast is indexed"
+          },
+          {
+            "kind": "contains",
+            "file": "clips.json",
+            "pattern": "Bram",
+            "label": "the first-steps moment carries its people tag"
+          },
+          {
+            "kind": "judge",
+            "file": "clips.json",
+            "rubric": "Every people tag on the new tape-04 records matches a roster name from family.md exactly, the descriptions read as searchable phrases someone would actually type, and the six prior-tape records are unchanged.",
+            "sourceFiles": [
+              "family.md",
+              "transcripts/tape-04.md"
+            ],
+            "label": "roster-true tags and searchable descriptions"
+          }
+        ]
+      },
+      {
+        "path": "report.md",
+        "kind": "markdown-report",
+        "minBytes": 500,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "\\d{2}:\\d{2}:\\d{2}",
+            "label": "highlights point at real timecodes"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "clips.json",
+      "kind": "json"
+    },
+    "axes": [
+      {
+        "name": "completeness",
+        "description": "The moments worth finding are all indexed — the toast, the song, the story, the first steps, the quiet moment."
+      },
+      {
+        "name": "people-tagging",
+        "description": "People tags are roster-exact; nobody is misnamed or invented."
+      },
+      {
+        "name": "moment-selection",
+        "description": "Records capture the moments a family would search for, not filler."
+      },
+      {
+        "name": "fidelity",
+        "description": "Timecodes and descriptions trace to the transcript; prior records untouched."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "timecode fidelity",
+    "roster-true people tags",
+    "append without clobbering"
+  ]
+}

package/data/craftbook-templates/ty/type-safety-pass/versions/1.0.1/craftbook.json

@@ -0,0 +1,148 @@
+{
+  "id": "type-safety-pass",
+  "name": "Type-Safety Pass",
+  "description": "Tighten the types of a module — eliminate `any`/implicit-any, add precise annotations, narrow unions, and make illegal states unrepresentable — without changing runtime behavior. Audits FIRST to inventory every loose type, unsafe cast, and missing annotation, then replaces them with precise types, then a reviewer confirms the type-checker is clean under strict settings and behavior is unchanged. Covers killing `any`, strict null checks, discriminated unions, generics, type narrowing, removing unsafe casts, and compile-clean-under-strict verification.\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. Audit the types (developer) — inventory every any, cast, and missing annotation → gated on artifact `notes/audit.md` (markdown-notes)\n2. Fix the types (developer) — replace loose types with precise ones → gated on `src/typed.ts` (code-module)\n3. Verify type safety (reviewer) — confirm strict-clean and behavior unchanged → gated on artifact `notes/verify.md` (markdown-notes)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "audit",
+  "triggers": [
+    "tighten the types",
+    "kill any types",
+    "add type annotations",
+    "make this type-safe",
+    "fix type errors"
+  ],
+  "steps": [
+    {
+      "id": "audit",
+      "name": "Audit the types",
+      "description": "inventory every any, cast, and missing annotation",
+      "prompt": "Inventory the type weaknesses before fixing them. Step 1: Search the module for every `any` (explicit and implicit), every unsafe cast (`as`, `!` non-null assertions), and every untyped parameter/return. Step 2: For each, note what the CORRECT type should be (look at the values that actually flow through). Step 3: Identify spots where a union should be narrowed or a discriminated union / generic would make illegal states unrepresentable. Step 4: Note the strict compiler settings to enable (e.g. strict, noImplicitAny, strictNullChecks). Step 5: Write a numbered acceptance-criteria checklist of 5-9 items (e.g. 'no explicit or implicit any remains', 'no unsafe casts without justification', 'the type-checker passes under strict', 'runtime behavior is unchanged'). `write_task_note` the inventory + checklist and write the same to the produces path.\n\nThe deliverable `notes/audit.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": "developer",
+      "advanceWhen": {
+        "file": "notes/audit.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "notes/audit.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "notes/audit.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "audit",
+        "maxAttempts": 3
+      },
+      "next": "fix"
+    },
+    {
+      "id": "fix",
+      "name": "Fix the types",
+      "description": "replace loose types with precise ones",
+      "prompt": "Apply precise types from the audit. Step 1: Annotate every parameter and return; replace each `any` with the real type the values demand. Step 2: Remove unsafe casts and non-null assertions by narrowing properly (type guards, discriminated unions) instead of asserting. Step 3: Where it helps, introduce generics or union types so illegal states cannot be constructed. Step 4: Enable the strict compiler settings and resolve every resulting error — do NOT silence them with `any` or `@ts-ignore`. Step 5: Confirm runtime behavior is unchanged (this is a types-only pass). Write the typed source to the produces path. On a loop-back, address only the remaining flagged spots. `write_task_note` the count of `any`s removed and which criteria now pass.",
+      "suggestedRole": "developer",
+      "advanceWhen": {
+        "file": "src/typed.ts",
+        "minBytes": 1,
+        "sniff": "nonempty"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "src/typed.ts",
+            "bytes": 200
+          },
+          {
+            "kind": "sniff",
+            "file": "src/typed.ts",
+            "sniff": "nonempty"
+          },
+          {
+            "kind": "esmImports",
+            "file": "src/typed.ts"
+          },
+          {
+            "kind": "sourceParses",
+            "file": "src/typed.ts"
+          }
+        ],
+        "onReject": "fix",
+        "maxAttempts": 3
+      },
+      "next": "verify"
+    },
+    {
+      "id": "verify",
+      "name": "Verify type safety",
+      "description": "confirm strict-clean and behavior unchanged",
+      "prompt": "Verify the types are genuinely tighter and nothing was swept under the rug. Step 1: Run the type-checker under the strict settings and confirm zero errors. Step 2: Search for any remaining `any`, `as`, `!`, or `@ts-ignore`/`@ts-expect-error` and confirm each remaining one is justified (or gone). Step 3: Confirm the runtime behavior is unchanged (tests still green, no logic edits disguised as type edits). Step 4: Spot-check that the new types are precise, not just `unknown`-everywhere busywork. Write a verification note with the type-check result and the residual-escape-hatch count to the produces path.\n\nThe deliverable `notes/verify.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": "reviewer",
+      "advanceWhen": {
+        "file": "notes/verify.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "src/typed.ts",
+            "bytes": 200
+          },
+          {
+            "kind": "sniff",
+            "file": "src/typed.ts",
+            "sniff": "nonempty"
+          },
+          {
+            "kind": "esmImports",
+            "file": "src/typed.ts"
+          },
+          {
+            "kind": "sourceParses",
+            "file": "src/typed.ts"
+          }
+        ],
+        "onReject": "verify",
+        "maxAttempts": 4
+      },
+      "next": "evaluate"
+    },
+    {
+      "id": "evaluate",
+      "name": "Evaluate",
+      "description": "Grade the deliverable against every acceptance criterion. All pass → finish; any fail → loop back and fix the gap.",
+      "prompt": "Run the type-checker under strict settings and the test suite. For EACH acceptance criterion: confirm no explicit/implicit `any` remains, confirm unsafe casts and ignore-comments are gone or justified, confirm the type-checker is clean under strict, and confirm runtime behavior is unchanged. Write PASS/FAIL per criterion; replacing one `any` with another or using `@ts-ignore` to pass is a FAIL.\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: \"fix\" })` 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": "src/typed.ts"
+        }
+      ],
+      "next": "fix"
+    },
+    {
+      "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
+    }
+  ],
+  "version": "1.0.1",
+  "releasedAt": "2026-08-14T00:00:00Z"
+}

package/data/craftbook-templates/ty/type-safety-pass/versions/1.0.1/test.json

@@ -0,0 +1,92 @@
+{
+  "schemaVersion": 1,
+  "title": "Type-Safety Pass smoke eval",
+  "objective": "Self-contained smoke eval for the Type-Safety Pass craftbook using the code generic harness.",
+  "tags": [
+    "code"
+  ],
+  "prompt": "We need a small Node helper for this — the requirments are in source/requirements.md. Put it in src/solution.mjs.",
+  "setup": {
+    "projectName": "Type-Safety Pass Eval",
+    "about": "Self-contained eval project for type-safety-pass. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/src/solution.mjs.",
+    "missionObjectives": "Use the Type-Safety Pass craftbook/template, read the seeded local fixtures, and write src/solution.mjs without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Type-Safety Pass Eval Brief\n\nClient: Boreal Desk, a home-office accessories company.\nAudience: operations leads who need an artifact they can use this week.\n\nFixed source facts for grounding:\n- The returns desk pilot covered 18 SKUs.\n- Median first response improved from 18 hours to 6 hours.\n- Preventable refund leakage fell from 14.2% to 8.9%.\n- The top unresolved complaint is status silence after photo submission.\n- Required next actions are automated status emails, barcode-exception training, and a weekly Finance exception export.\n\nUse these facts when the task asks for prose, analysis, copy, UI content, or test data. Do not use live web services, real credentials, or current outside data.\n\nCraftbook under test: type-safety-pass - Type-Safety Pass.\n"
+      },
+      {
+        "path": "source/requirements.md",
+        "content": "# Runner Requirements\n\nBuild a dependency-free Node ESM helper for Boreal Desk support operations. Export at least one function. Include a tiny self-test section using node:assert or an equivalent assertion helper. Use fixture values for 18 -> 6 hour response time and 14.2 -> 8.9 refund leakage.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Developer"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "src/solution.mjs is a local ESM module with basic self-test scaffolding.",
+    "deliverables": [
+      {
+        "path": "src/solution.mjs",
+        "kind": "code-with-tests",
+        "minBytes": 1500,
+        "checks": [
+          {
+            "kind": "esmImports",
+            "file": "src/solution.mjs"
+          },
+          {
+            "kind": "contains",
+            "file": "src/solution.mjs",
+            "pattern": "export\\s+(function|const|class)|export\\s*\\{",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "src/solution.mjs",
+            "pattern": "assert|test|describe|it|expect",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "src/solution.mjs",
+            "pattern": "18|6|14\\.2|8\\.9|Boreal",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "src/solution.mjs",
+      "kind": "typescript"
+    },
+    "axes": [
+      {
+        "name": "correctness",
+        "description": "The module does what the requirements ask, with sensible edge handling."
+      },
+      {
+        "name": "verification",
+        "description": "Self-tests exercise real behavior, not trivial truths."
+      },
+      {
+        "name": "clarity",
+        "description": "Exports, naming, and structure make the module usable without reading every line."
+      },
+      {
+        "name": "robustness",
+        "description": "Invalid input and boundary cases fail loudly rather than silently."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "runnable ESM",
+    "test scaffolding",
+    "local fixtures"
+  ]
+}

package/data/craftbook-templates/ve/version-bump/versions/1.0.1/craftbook.json

@@ -0,0 +1,155 @@
+{
+  "id": "version-bump",
+  "name": "Version Bump",
+  "description": "Perform a coordinated, semver-correct version bump across a project — deciding MAJOR/MINOR/PATCH from the actual change set, then updating every place the version is stamped in lockstep (package manifest(s), version constant, lockfile, badges, docs) plus the changelog header, so nothing drifts out of sync. A planner determines the correct semver level and enumerates every file that carries the version, a developer applies the bump everywhere consistently, and a reviewer verifies no location was missed and the new version is internally consistent. Use this when 'bumping the version', preparing a tag, or releasing a new package version where a half-applied bump (manifest says 2.0.0 but the constant says 1.9.0) is a classic ship bug.\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 bump (planner) — pick the semver level and enumerate every version-bearing file → gated on artifact `notes/scope.md` (markdown-notes)\n2. Apply the bump (developer) — update every version location in lockstep → gated on `version-bump.json` (json)\n3. Verify consistency (reviewer) — confirm no location drifted and the bump is consistent → gated on artifact `notes/verify.md` (markdown-notes)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "scope",
+  "triggers": [
+    "bump the version",
+    "release a new version",
+    "set version to 2.0.0",
+    "prepare a version tag",
+    "semver bump"
+  ],
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the bump",
+      "description": "pick the semver level and enumerate every version-bearing file",
+      "prompt": "1. Read the change set since the last release (changelog Unreleased, merged PRs, git log) and decide the semver level: MAJOR for any breaking/incompatible change, MINOR for new backward-compatible functionality, PATCH for backward-compatible fixes only — state the deciding change. 2. Compute the exact new version string from the current one (find the current version first; respect any pre-release/build suffix convention). 3. Enumerate EVERY location that stamps the version: package manifest(s) (and workspace members if a monorepo), any VERSION constant in source, the lockfile, README/docs badges, and the changelog header. 4. Note any inter-package version constraints that must move together. 5. Good looks like: the chosen new version with a one-line semver justification and a complete, file-by-file list of every place that must change with its current and target value. Write this as an acceptance-criteria checklist ('semver level matches the change set', 'every version-bearing file is listed with old→new', 'monorepo/peer constraints accounted for', 'changelog header updated to the new version') plus the analysis to the notes file via write_task_note AND to notes/scope.md.\n\nThe deliverable `notes/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": "planner",
+      "advanceWhen": {
+        "file": "notes/scope.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "notes/scope.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "notes/scope.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "scope",
+        "maxAttempts": 3
+      },
+      "next": "bump"
+    },
+    {
+      "id": "bump",
+      "name": "Apply the bump",
+      "description": "update every version location in lockstep",
+      "prompt": "1. Open notes/scope.md and update the version string in EVERY enumerated location to the exact target value — do not eyeball one and miss another. 2. Update package manifest(s) and any workspace members, the source VERSION constant, the lockfile (regenerate if the tooling requires it), docs/badges, and the changelog header. 3. Keep any pre-release/build suffix convention intact. 4. Do not change anything unrelated to the version stamp. 5. After editing, grep the repo for the OLD version string to confirm no stray occurrence remains (except historical changelog entries, which are correct to leave). 6. Produce a manifest of what changed: for each file, the path and the old→new version, plus the result of the stale-version grep. 7. Good looks like: every location from scope.md now reads the new version, the old version survives only in historical changelog entries, and the manifest records each edit. Write the change manifest (JSON with one entry per file) to version-bump.json.\n\nBefore working, open the artifact input `notes/scope.md` with `read_artifact`; do not look for it in the workspace.",
+      "suggestedRole": "developer",
+      "consumes": [
+        {
+          "file": "notes/scope.md",
+          "artifact": true
+        }
+      ],
+      "advanceWhen": {
+        "file": "version-bump.json",
+        "minBytes": 1,
+        "sniff": "json-valid"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "version-bump.json",
+            "bytes": 2
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkJsonValid",
+            "scope": "standard",
+            "inputs": {
+              "file": "version-bump.json"
+            }
+          }
+        ],
+        "onReject": "bump",
+        "maxAttempts": 3
+      },
+      "next": "verify"
+    },
+    {
+      "id": "verify",
+      "name": "Verify consistency",
+      "description": "confirm no location drifted and the bump is consistent",
+      "prompt": "1. Open version-bump.json and confirm every file from notes/scope.md was bumped to the SAME target version — no drift between manifest, constant, lockfile, and docs. 2. Independently grep the repo for both the old and the new version strings: the new version should appear in every expected place; the old version should remain only in historical changelog entries. 3. Verify the semver level still matches the change set described in scope.md. 4. Confirm the changelog header was updated and nothing unrelated changed. 5. Write a PASS/FAIL per acceptance criterion with the grep evidence, and list any missed or inconsistent location. 6. Any failure routes back to the bump phase. Write findings to notes/verify.md.\n\nBefore working, open the artifact input `notes/scope.md` with `read_artifact`; do not look for it in the workspace.\n\nThe deliverable `notes/verify.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": "reviewer",
+      "consumes": [
+        {
+          "file": "notes/scope.md",
+          "artifact": true
+        },
+        {
+          "file": "version-bump.json"
+        }
+      ],
+      "advanceWhen": {
+        "file": "notes/verify.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "version-bump.json",
+            "bytes": 2
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkJsonValid",
+            "scope": "standard",
+            "inputs": {
+              "file": "version-bump.json"
+            }
+          }
+        ],
+        "onReject": "verify",
+        "maxAttempts": 4
+      },
+      "next": "evaluate"
+    },
+    {
+      "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 version-bump.json and verify it against notes/scope.md, PASS/FAIL each criterion. Confirm: (a) it is valid JSON listing every version-bearing file from scope.md with an old→new entry; (b) every listed location carries the SAME new version (no drift between manifest, source constant, lockfile, docs); (c) the new version is semver-correct for the change set; (d) the changelog header reflects the new version; (e) the old version string survives only in historical changelog entries (verify with a grep). Any missed or inconsistent location routes back to the bump phase.\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: \"bump\" })` 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": "version-bump.json"
+        }
+      ],
+      "next": "bump"
+    },
+    {
+      "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
+    }
+  ],
+  "version": "1.0.1",
+  "releasedAt": "2026-08-14T00:00:00Z"
+}

package/data/craftbook-templates/ve/version-bump/versions/1.0.1/test.json

@@ -0,0 +1,92 @@
+{
+  "schemaVersion": 1,
+  "title": "Version Bump smoke eval",
+  "objective": "Self-contained smoke eval for the Version Bump craftbook using the code generic harness.",
+  "tags": [
+    "code"
+  ],
+  "prompt": "We need a small Node helper for this — the requirments are in source/requirements.md. Put it in src/solution.mjs.",
+  "setup": {
+    "projectName": "Version Bump Eval",
+    "about": "Self-contained eval project for version-bump. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/src/solution.mjs.",
+    "missionObjectives": "Use the Version Bump craftbook/template, read the seeded local fixtures, and write src/solution.mjs without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Version Bump Eval Brief\n\nClient: Boreal Desk, a home-office accessories company.\nAudience: operations leads who need an artifact they can use this week.\n\nFixed source facts for grounding:\n- The returns desk pilot covered 18 SKUs.\n- Median first response improved from 18 hours to 6 hours.\n- Preventable refund leakage fell from 14.2% to 8.9%.\n- The top unresolved complaint is status silence after photo submission.\n- Required next actions are automated status emails, barcode-exception training, and a weekly Finance exception export.\n\nUse these facts when the task asks for prose, analysis, copy, UI content, or test data. Do not use live web services, real credentials, or current outside data.\n\nCraftbook under test: version-bump - Version Bump.\n"
+      },
+      {
+        "path": "source/requirements.md",
+        "content": "# Runner Requirements\n\nBuild a dependency-free Node ESM helper for Boreal Desk support operations. Export at least one function. Include a tiny self-test section using node:assert or an equivalent assertion helper. Use fixture values for 18 -> 6 hour response time and 14.2 -> 8.9 refund leakage.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Developer"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "src/solution.mjs is a local ESM module with basic self-test scaffolding.",
+    "deliverables": [
+      {
+        "path": "src/solution.mjs",
+        "kind": "code-with-tests",
+        "minBytes": 1500,
+        "checks": [
+          {
+            "kind": "esmImports",
+            "file": "src/solution.mjs"
+          },
+          {
+            "kind": "contains",
+            "file": "src/solution.mjs",
+            "pattern": "export\\s+(function|const|class)|export\\s*\\{",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "src/solution.mjs",
+            "pattern": "assert|test|describe|it|expect",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "src/solution.mjs",
+            "pattern": "18|6|14\\.2|8\\.9|Boreal",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "src/solution.mjs",
+      "kind": "typescript"
+    },
+    "axes": [
+      {
+        "name": "correctness",
+        "description": "The module does what the requirements ask, with sensible edge handling."
+      },
+      {
+        "name": "verification",
+        "description": "Self-tests exercise real behavior, not trivial truths."
+      },
+      {
+        "name": "clarity",
+        "description": "Exports, naming, and structure make the module usable without reading every line."
+      },
+      {
+        "name": "robustness",
+        "description": "Invalid input and boundary cases fail loudly rather than silently."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "runnable ESM",
+    "test scaffolding",
+    "local fixtures"
+  ]
+}