@bendyline/gilde 0.1.51 → 0.1.52

package/data/craftbook-templates/li/library-package/versions/1.0.3/test.json

@@ -0,0 +1,92 @@
+{
+  "schemaVersion": 1,
+  "title": "Reusable Library Package smoke eval",
+  "objective": "Self-contained smoke eval for the Reusable Library Package 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": "Reusable Library Package Eval",
+    "about": "Self-contained eval project for library-package. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/src/solution.mjs.",
+    "missionObjectives": "Use the Reusable Library Package 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": "# Reusable Library Package 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: library-package - Reusable Library Package.\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/li/literature-review/versions/1.0.3/craftbook.json

@@ -0,0 +1,279 @@
+{
+  "id": "literature-review",
+  "name": "Literature Review",
+  "description": "Survey the existing literature on a topic and synthesize it into a structured review: a planner sets the scope, inclusion criteria, and the themes to organize around, then a researcher gathers and characterizes each source (method, finding, quality), then a copywriter synthesizes them thematically rather than source-by-source, surfacing consensus, disagreement, and gaps. The ordering matters because a review written without inclusion criteria becomes an arbitrary pile, and one written source-by-source reads like a list of summaries instead of a synthesis; locking themes and a source matrix first forces the comparative analysis that makes a real lit review. Use this for academic-style literature surveys, state-of-the-art reviews, 'what does the research say' questions, and synthesizing a body of papers or articles.\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 review (planner) — topic boundaries, inclusion criteria, organizing themes → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Gather & characterize sources (researcher) — build the source matrix: method, finding, quality per source → gated on artifact `{{workPath}}/sources.md` (markdown-notes)\n3. Synthesize the review (copywriter) — write a thematic synthesis with consensus, conflict, gaps → gated on artifact `{{workPath}}/review.md` (markdown-report)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "scope",
+  "triggers": [
+    "literature review",
+    "what does the research say",
+    "survey the literature",
+    "state of the art review",
+    "summarize the papers on"
+  ],
+  "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 review",
+      "description": "topic boundaries, inclusion criteria, organizing themes",
+      "prompt": "1. State the review topic and its boundaries in one sentence (what is in and out of scope). 2. Define inclusion criteria: source types accepted (peer-reviewed, official reports, etc.), recency window, and a minimum source count (aim 6+). 3. Decide 3-5 organizing themes or dimensions the review will be structured around (NOT source-by-source) plus a source-characterization matrix schema (columns like source, year, method, key finding, quality/limitation). 4. Write an acceptance-criteria checklist (e.g. 'review is organized by theme not by source', 'each source appears in the matrix with all columns filled', 'consensus vs disagreement is explicitly called out', 'a gaps/future-work section exists', 'minimum source count met'). 5. Record decisions. Call write_task_note with the themes, matrix schema, and checklist, and 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": "gather",
+      "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": "gather",
+      "name": "Gather & characterize sources",
+      "description": "build the source matrix: method, finding, quality per source",
+      "prompt": "1. Find sources meeting the inclusion criteria, prioritizing seminal and recent work. 2. For each source, add a row to the matrix in {{workPath}}/sources.md with every scoped column filled: citation key [n], title/author/year, method or evidence type, key finding (with the figure or claim), and a one-line quality note or limitation. 3. As you go, tag which organizing theme(s) each source speaks to so the writer can group them. 4. Note where sources agree and where they conflict on the same question. 5. Flag anything you could not verify as UNVERIFIED. Good looks like a matrix where the comparative structure of the field is already visible. Do not write the prose review 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": "gather",
+        "maxAttempts": 3
+      },
+      "next": "synthesize",
+      "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": "synthesize",
+      "name": "Synthesize the review",
+      "description": "write a thematic synthesis with consensus, conflict, gaps",
+      "prompt": "1. Write {{workPath}}/review.md organized by the locked themes (one section per theme), NOT one section per source. 2. In each theme, synthesize across sources: state what is established, cite the supporting sources [n], then explicitly note where sources disagree and why. 3. Open with an introduction framing the topic and scope, and close with a 'Gaps & future directions' section. 4. Add a numbered References list built from {{workPath}}/sources.md so every [n] resolves. 5. Keep it comparative and analytical, not a chain of one-paragraph summaries. 6. On a loop-back, fix only the named gaps. 7. Call write_task_note with the review path and which criteria now pass.\n\nBefore working, open the artifact input `{{workPath}}/sources.md` with `read_artifact`; do not look for it in the workspace.\n\nThe deliverable `{{workPath}}/review.md` lands in the project's artifacts drawer — write it with `write_artifact` and read it back with `read_artifact`; the shipped workspace stays untouched.",
+      "suggestedRole": "copywriter",
+      "consumes": [
+        {
+          "file": "{{workPath}}/sources.md",
+          "artifact": true
+        }
+      ],
+      "advanceWhen": {
+        "file": "{{workPath}}/review.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/review.md",
+            "bytes": 1500,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/review.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i",
+            "label": "at least one markdown heading",
+            "artifact": true
+          }
+        ],
+        "onReject": "synthesize",
+        "maxAttempts": 4
+      },
+      "next": "evaluate",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "artifact",
+        "additionalOutputMedia": [
+          "task-note"
+        ]
+      }
+    },
+    {
+      "id": "evaluate",
+      "name": "Evaluate",
+      "description": "Grade the deliverable against every acceptance criterion. All pass → finish; any fail → loop back and fix the gap.",
+      "prompt": "Open {{workPath}}/review.md and check EACH criterion PASS/FAIL: (1) the review is organized by theme, not source-by-source; (2) every source in {{workPath}}/sources.md is cited and every matrix column was actually used to inform the prose; (3) consensus AND disagreement are explicitly surfaced for at least the main themes; (4) a gaps/future-work section exists; (5) the minimum source count is met and inclusion criteria respected; (6) every inline [n] resolves to the References list. A pile of per-source summaries with no synthesis FAILS even if every source is present.\n\nThe deliverable lives in the project's artifacts drawer — open `{{workPath}}/review.md` with `read_artifact`, not `read_file`.\n\nThen route — this is the whole point of the loop:\n\n- **Every criterion PASSES →** call `advance_task_step({ ref, stepId: \"evaluate\", next: \"finish\" })`.\n- **Any criterion FAILS →** write the specific gaps to notes, then call `advance_task_step({ ref, stepId: \"evaluate\", next: \"synthesize\" })` to loop back. The builder fixes exactly those gaps.\n\nNever route to `finish` while any criterion is unmet. The build phase's completion gate already blocked a grossly-incomplete deliverable; your job is the judgment an automated check cannot make (does it actually work, read well, look right). After ~3 unproductive loops, stop and report DONE_WITH_CONCERNS so the user can step in.",
+      "suggestedRole": "reviewer",
+      "consumes": [
+        {
+          "file": "{{workPath}}/review.md",
+          "artifact": true
+        }
+      ],
+      "next": "synthesize",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "task-note"
+      }
+    },
+    {
+      "id": "finish",
+      "name": "Finish",
+      "description": "All acceptance criteria met. Stamp a short summary and report DONE.",
+      "prompt": "Every acceptance criterion passed. Write a one-paragraph DONE summary to task notes via `write_task_note`: what was built, the deliverable path(s), and a one-line confirmation that each criterion is met. Then report DONE.",
+      "suggestedRole": "developer",
+      "terminal": true,
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "artifacts",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "task-note"
+      }
+    }
+  ],
+  "version": "1.0.3",
+  "releasedAt": "2026-09-01T20:00:00Z",
+  "minGezelVersion": "1.26233"
+}

package/data/craftbook-templates/li/literature-review/versions/1.0.3/test.json

@@ -0,0 +1,110 @@
+{
+  "schemaVersion": 1,
+  "title": "Literature Review smoke eval",
+  "objective": "Self-contained smoke eval for the Literature Review craftbook using the corpus generic harness.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "We need a literature review for the returns-desk work. The backgound info is in source/brief.md — have a look and write it up in report.md.",
+  "setup": {
+    "projectName": "Literature Review Eval",
+    "about": "Self-contained eval project for literature-review. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/report.md.",
+    "missionObjectives": "Use the Literature Review craftbook/template, read the seeded local fixtures, and write report.md without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Literature Review 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: literature-review - Literature Review.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Writer"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "report.md is a source-grounded markdown artifact with required facts and actions.",
+    "deliverables": [
+      {
+        "path": "report.md",
+        "kind": "markdown-report",
+        "minBytes": 1000,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "source/brief\\.md|Brief",
+            "flags": "i",
+            "label": "cite or name the seeded source"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "18\\b[\\s\\S]{0,30}\\bSKUs",
+            "flags": "i",
+            "label": "include the 18-SKU pilot scope"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "18\\s*hours|6\\s*hours",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "14\\.2%|8\\.9%",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "status silence|photo submission",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "automated status emails|barcode|Finance",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "report.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "grounding",
+        "description": "Seeded facts appear faithfully and the source is cited."
+      },
+      {
+        "name": "structure",
+        "description": "Sections progress logically for the artifact class."
+      },
+      {
+        "name": "completeness",
+        "description": "Required elements (risks, next actions, scope) are all present."
+      },
+      {
+        "name": "tone",
+        "description": "The register fits the audience and artifact class."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "source-grounded prose",
+    "section structure",
+    "next-action clarity"
+  ]
+}