@bendyline/gilde 0.1.50 → 0.1.52

package/data/craftbook-templates/an/anniversary-cut/versions/1.0.5/test.json

@@ -0,0 +1,157 @@
+{
+  "schemaVersion": 1,
+  "title": "Anniversary Cut smoke eval",
+  "objective": "Task-specific eval for the Anniversary Cut craftbook: a 30-record family archive is curated into a birthday reel for Ria's 70th — clips selected with reasons and era coverage, assembled through the fake pipeline, delivered with chapters and a dedication.",
+  "tags": [
+    "external"
+  ],
+  "prompt": "moms 70th is next month — can you put together a highlight reel from the archive with the fake pipeline? the clips index has everythign tagged",
+  "setup": {
+    "projectName": "Home Video Archive — Anniversary Reel Eval",
+    "about": "Self-contained eval project for anniversary-cut. The archive index is clips.json (30 indexed moments across tapes 01-09, 1986-2024) and the family roster is family.md — mam is Ria, the reel is for her 70th. The selection goes to cutlist.json, the fake media-assembly pipeline is the ready-made mock-probe project script (writes renders/anniversary-cut.mp4 plus renders/assembly-log.json), and the chapter list with the dedication goes to tasks/eval/report.md.",
+    "missionObjectives": "Use the Anniversary Cut craftbook/template, select the reel from clips.json with a stated reason per clip and coverage across the eras, assemble through the provided mock-probe script, and deliver tasks/eval/report.md with a chapter list and dedication. No invented footage, no real media tools — only the wired fake pipeline.",
+    "files": [
+      {
+        "path": "clips.json",
+        "content": "[\n  {\n    \"id\": \"t01-c01\",\n    \"tape\": \"tape-01\",\n    \"year\": 1986,\n    \"timecode\": \"00:04:12\",\n    \"durationSeconds\": 41,\n    \"people\": [\n      \"Ria\",\n      \"Opa Cor\"\n    ],\n    \"description\": \"Ria and her father at the harbor, gulls everywhere\"\n  },\n  {\n    \"id\": \"t01-c02\",\n    \"tape\": \"tape-01\",\n    \"year\": 1986,\n    \"timecode\": \"00:17:40\",\n    \"durationSeconds\": 28,\n    \"people\": [\n      \"Ria\"\n    ],\n    \"description\": \"Ria winning the village quiz, arms up\"\n  },\n  {\n    \"id\": \"t01-c03\",\n    \"tape\": \"tape-01\",\n    \"year\": 1987,\n    \"timecode\": \"00:29:05\",\n    \"durationSeconds\": 35,\n    \"people\": [\n      \"Ria\",\n      \"Henk\"\n    ],\n    \"description\": \"the first appearance of Henk, very nervous at the door\"\n  },\n  {\n    \"id\": \"t02-c01\",\n    \"tape\": \"tape-02\",\n    \"year\": 1988,\n    \"timecode\": \"00:03:55\",\n    \"durationSeconds\": 74,\n    \"people\": [\n      \"Ria\",\n      \"Henk\"\n    ],\n    \"description\": \"wedding day - the vows, rain starting right on cue\"\n  },\n  {\n    \"id\": \"t02-c02\",\n    \"tape\": \"tape-02\",\n    \"year\": 1988,\n    \"timecode\": \"00:21:18\",\n    \"durationSeconds\": 52,\n    \"people\": [\n      \"Ria\",\n      \"Henk\",\n      \"Opa Cor\"\n    ],\n    \"description\": \"wedding toast by Opa Cor, the whole tent laughing\"\n  },\n  {\n    \"id\": \"t02-c03\",\n    \"tape\": \"tape-02\",\n    \"year\": 1988,\n    \"timecode\": \"00:40:02\",\n    \"durationSeconds\": 33,\n    \"people\": [\n      \"Ria\"\n    ],\n    \"description\": \"Ria dancing in the wedding dress, shoes off\"\n  },\n  {\n    \"id\": \"t03-c01\",\n    \"tape\": \"tape-03\",\n    \"year\": 1990,\n    \"timecode\": \"00:02:33\",\n    \"durationSeconds\": 47,\n    \"people\": [\n      \"Ria\",\n      \"Daan\"\n    ],\n    \"description\": \"bringing Daan home, Ria narrating the whole drive\"\n  },\n  {\n    \"id\": \"t03-c02\",\n    \"tape\": \"tape-03\",\n    \"year\": 1991,\n    \"timecode\": \"00:15:20\",\n    \"durationSeconds\": 26,\n    \"people\": [\n      \"Ria\",\n      \"Daan\"\n    ],\n    \"description\": \"first birthday cake, most of it on Daan\"\n  },\n  {\n    \"id\": \"t03-c03\",\n    \"tape\": \"tape-03\",\n    \"year\": 1992,\n    \"timecode\": \"00:31:44\",\n    \"durationSeconds\": 39,\n    \"people\": [\n      \"Henk\",\n      \"Daan\"\n    ],\n    \"description\": \"Henk and Daan asleep in the same chair\"\n  },\n  {\n    \"id\": \"t04-c01\",\n    \"tape\": \"tape-04\",\n    \"year\": 1993,\n    \"timecode\": \"00:05:10\",\n    \"durationSeconds\": 44,\n    \"people\": [\n      \"Ria\",\n      \"Fleur\"\n    ],\n    \"description\": \"Fleur arrives - Daan inspecting his sister very seriously\"\n  },\n  {\n    \"id\": \"t04-c02\",\n    \"tape\": \"tape-04\",\n    \"year\": 1994,\n    \"timecode\": \"00:19:27\",\n    \"durationSeconds\": 31,\n    \"people\": [\n      \"Ria\",\n      \"Daan\",\n      \"Fleur\"\n    ],\n    \"description\": \"the paddling pool afternoon, hose chaos\"\n  },\n  {\n    \"id\": \"t04-c03\",\n    \"tape\": \"tape-04\",\n    \"year\": 1995,\n    \"timecode\": \"00:36:51\",\n    \"durationSeconds\": 58,\n    \"people\": [\n      \"Ria\"\n    ],\n    \"description\": \"Ria singing at Oma's birthday, surprising everyone\"\n  },\n  {\n    \"id\": \"t05-c01\",\n    \"tape\": \"tape-05\",\n    \"year\": 1997,\n    \"timecode\": \"00:08:14\",\n    \"durationSeconds\": 42,\n    \"people\": [\n      \"Ria\",\n      \"Henk\",\n      \"Daan\",\n      \"Fleur\"\n    ],\n    \"description\": \"the flooded-kitchen incident, all four bailing with pans\"\n  },\n  {\n    \"id\": \"t05-c02\",\n    \"tape\": \"tape-05\",\n    \"year\": 1998,\n    \"timecode\": \"00:22:39\",\n    \"durationSeconds\": 27,\n    \"people\": [\n      \"Daan\",\n      \"Fleur\"\n    ],\n    \"description\": \"school play - Fleur as the sun, Daan as a reluctant tree\"\n  },\n  {\n    \"id\": \"t05-c03\",\n    \"tape\": \"tape-05\",\n    \"year\": 1999,\n    \"timecode\": \"00:41:03\",\n    \"durationSeconds\": 36,\n    \"people\": [\n      \"Ria\"\n    ],\n    \"description\": \"Ria finishing her first half marathon, red-faced and delighted\"\n  },\n  {\n    \"id\": \"t06-c01\",\n    \"tape\": \"tape-06\",\n    \"year\": 2002,\n    \"timecode\": \"00:06:30\",\n    \"durationSeconds\": 49,\n    \"people\": [\n      \"Ria\",\n      \"Fleur\"\n    ],\n    \"description\": \"camping in the dunes, tent collapsing at dawn\"\n  },\n  {\n    \"id\": \"t06-c02\",\n    \"tape\": \"tape-06\",\n    \"year\": 2004,\n    \"timecode\": \"00:18:22\",\n    \"durationSeconds\": 38,\n    \"people\": [\n      \"Ria\",\n      \"Henk\"\n    ],\n    \"description\": \"silver-grey Vespa arrives, Ria refuses to let Henk drive it\"\n  },\n  {\n    \"id\": \"t06-c03\",\n    \"tape\": \"tape-06\",\n    \"year\": 2006,\n    \"timecode\": \"00:33:47\",\n    \"durationSeconds\": 30,\n    \"people\": [\n      \"Daan\"\n    ],\n    \"description\": \"Daan's graduation, Ria filming and crying at the same time\"\n  },\n  {\n    \"id\": \"t07-c01\",\n    \"tape\": \"tape-07\",\n    \"year\": 2009,\n    \"timecode\": \"00:04:58\",\n    \"durationSeconds\": 45,\n    \"people\": [\n      \"Ria\",\n      \"Fleur\"\n    ],\n    \"description\": \"Fleur's graduation, the hat that would not stay on\"\n  },\n  {\n    \"id\": \"t07-c02\",\n    \"tape\": \"tape-07\",\n    \"year\": 2011,\n    \"timecode\": \"00:20:15\",\n    \"durationSeconds\": 34,\n    \"people\": [\n      \"Ria\",\n      \"Henk\"\n    ],\n    \"description\": \"25th anniversary dance in the kitchen, radio on\"\n  },\n  {\n    \"id\": \"t07-c03\",\n    \"tape\": \"tape-07\",\n    \"year\": 2013,\n    \"timecode\": \"00:38:29\",\n    \"durationSeconds\": 29,\n    \"people\": [\n      \"Ria\"\n    ],\n    \"description\": \"Ria teaching the neighbourhood kids to bake, chaos and flour\"\n  },\n  {\n    \"id\": \"t08-c01\",\n    \"tape\": \"tape-08\",\n    \"year\": 2015,\n    \"timecode\": \"00:07:21\",\n    \"durationSeconds\": 40,\n    \"people\": [\n      \"Ria\",\n      \"Daan\"\n    ],\n    \"description\": \"Daan's wedding - Ria's speech, short and devastatingly funny\"\n  },\n  {\n    \"id\": \"t08-c02\",\n    \"tape\": \"tape-08\",\n    \"year\": 2017,\n    \"timecode\": \"00:23:44\",\n    \"durationSeconds\": 32,\n    \"people\": [\n      \"Ria\",\n      \"Henk\"\n    ],\n    \"description\": \"the allotment garden's first real harvest, absurd zucchini\"\n  },\n  {\n    \"id\": \"t08-c03\",\n    \"tape\": \"tape-08\",\n    \"year\": 2019,\n    \"timecode\": \"00:39:56\",\n    \"durationSeconds\": 51,\n    \"people\": [\n      \"Ria\",\n      \"Fleur\",\n      \"Noor\"\n    ],\n    \"description\": \"meeting Noor - Ria holding her granddaughter for the first time\"\n  },\n  {\n    \"id\": \"t09-c01\",\n    \"tape\": \"tape-09\",\n    \"year\": 2020,\n    \"timecode\": \"00:03:40\",\n    \"durationSeconds\": 25,\n    \"people\": [\n      \"Ria\",\n      \"Noor\"\n    ],\n    \"description\": \"window visit, Noor waving both arms\"\n  },\n  {\n    \"id\": \"t09-c02\",\n    \"tape\": \"tape-09\",\n    \"year\": 2021,\n    \"timecode\": \"00:16:12\",\n    \"durationSeconds\": 37,\n    \"people\": [\n      \"Ria\",\n      \"Noor\"\n    ],\n    \"description\": \"first baking lesson for Noor, history repeating in flour\"\n  },\n  {\n    \"id\": \"t09-c03\",\n    \"tape\": \"tape-09\",\n    \"year\": 2022,\n    \"timecode\": \"00:29:33\",\n    \"durationSeconds\": 43,\n    \"people\": [\n      \"Ria\",\n      \"Henk\",\n      \"Daan\",\n      \"Fleur\",\n      \"Noor\"\n    ],\n    \"description\": \"the whole family at the coast, the five-person kite disaster\"\n  },\n  {\n    \"id\": \"t09-c04\",\n    \"tape\": \"tape-09\",\n    \"year\": 2023,\n    \"timecode\": \"00:44:18\",\n    \"durationSeconds\": 28,\n    \"people\": [\n      \"Ria\"\n    ],\n    \"description\": \"Ria back on the Vespa for her 68th, victory lap of the block\"\n  },\n  {\n    \"id\": \"t09-c05\",\n    \"tape\": \"tape-09\",\n    \"year\": 2024,\n    \"timecode\": \"00:52:02\",\n    \"durationSeconds\": 33,\n    \"people\": [\n      \"Ria\",\n      \"Noor\"\n    ],\n    \"description\": \"Noor reading her first book aloud to Ria on the bench\"\n  },\n  {\n    \"id\": \"t09-c06\",\n    \"tape\": \"tape-09\",\n    \"year\": 2024,\n    \"timecode\": \"00:58:41\",\n    \"durationSeconds\": 30,\n    \"people\": [\n      \"Henk\",\n      \"Ria\"\n    ],\n    \"description\": \"Henk failing to surprise Ria with breakfast, caught mid-plan\"\n  }\n]\n"
+      },
+      {
+        "path": "family.md",
+        "content": "# Family roster\n\n- Ria - mam, turns 70 next month, the reel is for her\n- Henk - pap, married Ria in 1988\n- Daan - eldest, born 1990\n- Fleur - daughter, born 1993\n- Noor - Fleur's daughter, born 2019\n- Opa Cor - Ria's father, on the earliest tapes\n"
+      }
+    ],
+    "worker": {
+      "name": "Noor",
+      "role": "Curator"
+    }
+  },
+  "mocks": [
+    {
+      "kind": "cli",
+      "id": "probe",
+      "description": "Provenance-trusted project script `mock-probe` that executes the fake media-assembly pipeline: validates cutlist.json against the clips.json archive and writes the stub reel plus its run log.",
+      "shim": {
+        "path": "scripts/mock-probe.ts",
+        "content": "import { defineScript, gezel } from '@bendyline/gezel-sdk';\n\nexport const meta = defineScript({\n  name: 'mock-probe',\n  description:\n    'Fake media-assembly pipeline for this eval: validates cutlist.json against the clips.json archive index, refuses any clip that is not indexed, then writes the stub reel to renders/anniversary-cut.mp4 and its run log to renders/assembly-log.json.',\n  inputs: {},\n  outputs: {\n    log: { type: 'string', description: 'The assembly run log JSON written to renders/assembly-log.json.' },\n  },\n  requires: ['workspace.read', 'workspace.write'],\n});\n\nconst cutlist = JSON.parse(await gezel.fs.read('cutlist.json'));\nconst archive = JSON.parse(await gezel.fs.read('clips.json'));\nif (!Array.isArray(cutlist) || cutlist.length === 0) {\n  throw new Error('cutlist.json must be a non-empty JSON array');\n}\nconst byId = new Map(archive.map((clip) => [clip.id, clip]));\nlet total = 0;\nconst assembled = [];\nfor (const row of cutlist) {\n  const clip = byId.get(row.clip);\n  if (!clip) throw new Error(`unknown clip in cutlist: ${row.clip} is not indexed in clips.json`);\n  total += typeof clip.durationSeconds === 'number' ? clip.durationSeconds : 0;\n  assembled.push(row.clip);\n}\nconst log = {\n  status: 'ok',\n  engine: 'mock-assemble',\n  segments: assembled.length,\n  clips: assembled,\n  totalDurationSeconds: Math.round(total * 100) / 100,\n};\nawait gezel.fs.write('renders/anniversary-cut.mp4', `MOCKMP4 anniversary reel stub\\n${'0'.repeat(2048)}\\n`);\nawait gezel.fs.write('renders/assembly-log.json', `${JSON.stringify(log, null, 2)}\\n`);\ngezel.output({ log: JSON.stringify(log) });\n"
+      }
+    }
+  ],
+  "success": {
+    "summary": "cutlist.json selects real archive clips with reasons, the fake pipeline produced the reel and a status-ok log, and tasks/eval/report.md carries a chapter list and a dedication for Ria.",
+    "deliverables": [
+      {
+        "path": "cutlist.json",
+        "kind": "json",
+        "checks": [
+          {
+            "kind": "recordSchema",
+            "file": "cutlist.json",
+            "fields": [
+              {
+                "name": "clip",
+                "type": "nonempty"
+              },
+              {
+                "name": "reason",
+                "type": "nonempty"
+              }
+            ],
+            "minRows": 5
+          },
+          {
+            "kind": "valuesSubsetOf",
+            "file": "cutlist.json",
+            "sourceFiles": [
+              "clips.json"
+            ],
+            "pattern": "\"clip\"\\s*:\\s*\"([^\"]+)\"",
+            "label": "every selected clip exists in the archive — no invented footage"
+          }
+        ]
+      },
+      {
+        "path": "renders/anniversary-cut.mp4",
+        "kind": "generic-file",
+        "minBytes": 200
+      },
+      {
+        "path": "renders/assembly-log.json",
+        "kind": "json",
+        "checks": [
+          {
+            "kind": "jsonPathEquals",
+            "file": "renders/assembly-log.json",
+            "path": "status",
+            "value": "ok",
+            "label": "the assembly log reports status ok"
+          }
+        ]
+      },
+      {
+        "path": "tasks/eval/report.md",
+        "kind": "markdown-report",
+        "minBytes": 700,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "chapter",
+            "flags": "i",
+            "label": "a chapter list for the reel"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "Ria",
+            "label": "the dedication names Ria"
+          },
+          {
+            "kind": "judge",
+            "file": "tasks/eval/report.md",
+            "rubric": "The selection covers Ria across her eras (1980s through the 2020s) rather than clustering in one period, the family-famous moments (the wedding, meeting Noor) are in, each chapter's line gives a warm reason, and the dedication fits a 70th birthday.",
+            "sourceFiles": [
+              "clips.json",
+              "family.md"
+            ],
+            "label": "era coverage and warmth"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "tasks/eval/report.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "emotional-arc",
+        "description": "The reel opens and closes strong and moves through Ria's life with intent."
+      },
+      {
+        "name": "selection-reasons",
+        "description": "Every clip earns its place with a stated reason, not a shrug."
+      },
+      {
+        "name": "era-coverage",
+        "description": "Decades are represented; the reel is a life, not one summer."
+      },
+      {
+        "name": "presentation",
+        "description": "Chapters and dedication turn a render into a gift."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "no invented footage",
+    "era coverage",
+    "dedication warmth"
+  ]
+}

package/data/craftbook-templates/an/annotated-bibliography/versions/1.0.2/test.json

@@ -19,9 +19,6 @@
     "worker": {
       "name": "Bente",
       "role": "Researcher"
-    },
-    "craftbookParams": {
-      "workPath": "tasks/eval"
     }
   },
   "mocks": [],

package/data/craftbook-templates/an/annotated-bibliography/versions/1.0.3/craftbook.json

@@ -0,0 +1,279 @@
+{
+  "id": "annotated-bibliography",
+  "name": "Annotated Bibliography",
+  "description": "Build a formal annotated bibliography for a research topic: a planner locks the scope, the citation style, and the annotation rubric (summary + evaluation + relevance), then a researcher locates each source and writes a consistent, properly-formatted annotation that summarizes, critically evaluates, and situates it for the research question. The ordering matters because annotations written without a fixed rubric vary wildly in depth and a bibliography assembled without a citation style is inconsistent; locking style and the three-part annotation rubric first yields a uniform, scholarly, reusable artifact. Use this for annotated bibliographies, a sourced reference list with summaries, research source logs, literature foundations for a paper, and 'list and evaluate my sources' requests.\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 bibliography (planner) — topic, citation style, and annotation rubric → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Locate & evaluate sources (researcher) — find each source, draft its three-part annotation → gated on artifact `{{workPath}}/sources.md` (markdown-notes)\n3. Write the bibliography (copywriter) — formatted, ordered, uniformly-annotated bibliography → gated on `bibliography.md` (markdown-doc)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "scope",
+  "triggers": [
+    "annotated bibliography",
+    "list and evaluate sources",
+    "sourced reference list with summaries",
+    "research source log",
+    "bibliography with annotations"
+  ],
+  "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 bibliography",
+      "description": "topic, citation style, and annotation rubric",
+      "prompt": "1. State the research question/topic and the inclusion criteria (source types, recency, minimum count — aim 6+). 2. Lock the citation style exactly (APA, MLA, Chicago, or a stated custom format) with a one-line example of a correctly-formatted entry. 3. Lock the annotation rubric: each annotation must have (a) a 2-4 sentence summary of the source, (b) a critical evaluation of its credibility/method/bias, and (c) a relevance note tying it to the research question. 4. Decide ordering (alphabetical by author, or thematic). 5. Write an acceptance-criteria checklist (e.g. 'every entry is formatted in the locked citation style', 'every annotation has all three rubric parts', 'sources meet the inclusion criteria', 'entries are ordered as specified', 'minimum source count met'). 6. Record decisions. Call write_task_note with the style example, rubric, and checklist; write the same to {{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": "planner",
+      "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": "research",
+      "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": "research",
+      "name": "Locate & evaluate sources",
+      "description": "find each source, draft its three-part annotation",
+      "prompt": "1. Find sources meeting the inclusion criteria, prioritizing primary and authoritative works on the topic. 2. For each, record in {{workPath}}/sources.md: the full bibliographic data needed for the locked citation style, plus a draft three-part annotation (summary, critical evaluation, relevance) per the rubric. 3. In the evaluation part, judge the source honestly — author authority, method or evidence quality, recency, and any bias or limitation — not just praise. 4. Verify each source actually exists and the bibliographic details are correct; flag any you cannot confirm. 5. Ensure you exceed the minimum count and cover the topic without padding with weak sources. Good looks like a sources file where each entry already has correct citation data and a complete three-part annotation. Do not format the final document yet.\n\nThe deliverable `{{workPath}}/sources.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}}/sources.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/sources.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/sources.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "research",
+        "maxAttempts": 3
+      },
+      "next": "write",
+      "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"
+      }
+    },
+    {
+      "id": "write",
+      "name": "Write the bibliography",
+      "description": "formatted, ordered, uniformly-annotated bibliography",
+      "prompt": "1. Write bibliography.md as an ordered list of entries: each a citation formatted exactly in the locked style, followed by its annotation containing all three rubric parts (summary, evaluation, relevance). 2. Apply the citation style precisely and consistently — punctuation, author order, italics/markers as the style requires. 3. Keep annotation length and depth uniform across entries. 4. Order entries as specified (alphabetical/thematic). 5. Draw everything from {{workPath}}/sources.md; do not invent or alter citation data. 6. On a loop-back, fix only the named gaps. 7. Call write_task_note with the bibliography path and entry count.\n\nBefore working, open the artifact input `{{workPath}}/sources.md` with `read_artifact`; do not look for it in the workspace.",
+      "suggestedRole": "copywriter",
+      "consumes": [
+        {
+          "file": "{{workPath}}/sources.md",
+          "artifact": true
+        }
+      ],
+      "advanceWhen": {
+        "file": "bibliography.md",
+        "minBytes": 1,
+        "sniff": "nonempty"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "bibliography.md",
+            "bytes": 500
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkContains",
+            "scope": "standard",
+            "inputs": {
+              "file": "bibliography.md",
+              "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+              "flags": "i"
+            }
+          }
+        ],
+        "onReject": "write",
+        "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"
+        ],
+        "outputMedium": "workspace",
+        "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 bibliography.md and check EACH criterion PASS/FAIL: (1) every entry is formatted in the locked citation style and is consistent (check 3 against the style example in {{workPath}}/scope.md); (2) every annotation contains all three rubric parts — summary, critical evaluation, and relevance; (3) the evaluation part genuinely assesses credibility/method/bias rather than only summarizing; (4) sources meet the inclusion criteria and the minimum count is met; (5) entries are ordered as specified; (6) citation data matches {{workPath}}/sources.md with nothing fabricated. An entry missing a rubric part, or with a malformed/invented citation, FAILS.\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: \"write\" })` 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": "bibliography.md"
+        }
+      ],
+      "next": "write",
+      "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": "1.0.3",
+  "releasedAt": "2026-09-01T20:00:00Z",
+  "minGezelVersion": "1.26233"
+}

package/data/craftbook-templates/an/annotated-bibliography/versions/1.0.3/test.json

@@ -0,0 +1,102 @@
+{
+  "schemaVersion": 1,
+  "title": "Annotated bibliography from seeded source cards",
+  "objective": "Measure whether the annotated-bibliography craftbook locks style/rubric and produces uniform summary, evaluation, and relevance annotations.",
+  "tags": [
+    "data"
+  ],
+  "prompt": "In the `Annotated Bibliography Eval` project, read `source/source-cards.md` and write `bibliography.md` for a research question about rural telehealth follow-up programs. Use APA-style entries and give every source a Summary, Critical evaluation, and Relevance annotation. Do not invent sources beyond the six seeded cards.",
+  "setup": {
+    "projectName": "Annotated Bibliography Eval",
+    "about": "Self-contained eval project for annotated-bibliography. Six source cards are in workspace/source/source-cards.md.",
+    "missionObjectives": "Write a six-entry APA-style annotated bibliography with uniform three-part annotations and no invented sources.",
+    "files": [
+      {
+        "path": "source/source-cards.md",
+        "content": "# Source cards\n\nResearch question: What makes rural telehealth follow-up programs effective after hospital discharge?\n\n1. Allen, Priya. 2022. Rural Telehealth Follow-up and Readmission Risk. Journal of Rural Care. Finds video follow-up within 72 hours lowered 30-day readmissions by 11% across four clinics; limitation: observational design.\n2. Chen, Marco. 2021. Broadband Gaps in Remote Patient Monitoring. Health Systems Review. Surveys 900 households; shows connectivity failures explain many missed visits; limitation: self-reported bandwidth.\n3. Dunn, Elise. 2023. Nurse-led Coaching After Discharge. Care Transitions Quarterly. Randomized pilot, n=240; nurse coaching improved medication adherence by 18 points; limitation: single region.\n4. Garcia, Alma. 2020. Telehealth Trust in Older Adults. Community Health Methods. Qualitative interviews with 42 older adults; highlights trust, language access, and caregiver presence.\n5. Patel, Neel. 2024. Cost Model for Hybrid Follow-up. Rural Health Economics. Compares phone, video, and in-person follow-ups; finds hybrid model breaks even after 1,600 annual encounters.\n6. Williams, June. 2019. Privacy Concerns in Home Monitoring. Nursing Informatics. Reviews consent and device-sharing risks; older but still useful for privacy checklist.\n"
+      }
+    ],
+    "worker": {
+      "name": "Bente",
+      "role": "Researcher"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "workspace/bibliography.md has six source-grounded entries with APA-style citation data plus summary, credibility/method evaluation, and relevance notes.",
+    "deliverables": [
+      {
+        "path": "bibliography.md",
+        "kind": "markdown-doc",
+        "minBytes": 2600,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "bibliography.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "bibliography.md",
+            "pattern": "Allen|Chen|Dunn|Garcia|Patel|Williams",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "bibliography.md",
+            "pattern": "Summary|Critical evaluation|Relevance",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "bibliography.md",
+            "pattern": "APA|telehealth|rural|readmission",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "bibliography.md",
+            "pattern": "observational|limitation|bias|method",
+            "flags": "i"
+          },
+          {
+            "kind": "notContains",
+            "file": "bibliography.md",
+            "pattern": "Retrieved from Wikipedia|unknown author",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "bibliography.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "accuracy",
+        "description": "Computed figures are correct against the seeded records."
+      },
+      {
+        "name": "grounding",
+        "description": "Every claim traces to the seeded data — nothing invented."
+      },
+      {
+        "name": "structure",
+        "description": "Tables and sections make the analysis checkable at a glance."
+      },
+      {
+        "name": "actionability",
+        "description": "Recommendations follow from the findings and are concretely doable."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "rubric uniformity",
+    "source coverage",
+    "critical evaluation"
+  ]
+}