@bendyline/gilde 0.1.50 → 0.1.52

package/data/craftbook-templates/to/topic-explainer/versions/1.0.3/test.json

@@ -0,0 +1,110 @@
+{
+  "schemaVersion": 1,
+  "title": "Topic Explainer smoke eval",
+  "objective": "Self-contained smoke eval for the Topic Explainer craftbook using the corpus generic harness.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "We need a topic explainer 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": "Topic Explainer Eval",
+    "about": "Self-contained eval project for topic-explainer. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/report.md.",
+    "missionObjectives": "Use the Topic Explainer 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": "# Topic Explainer 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: topic-explainer - Topic Explainer.\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"
+  ]
+}

package/data/craftbook-templates/tr/transcribe-and-shownotes/versions/1.0.3/craftbook.json

@@ -0,0 +1,250 @@
+{
+  "id": "transcribe-and-shownotes",
+  "name": "Transcript to Shownotes",
+  "description": "Take a finished recording from raw transcript to publishable shownotes: a clean transcript on file, timestamped chapters, a summary listeners actually read, and the links mentioned — the per-episode ritual that turns audio into an archive. Locks the shownotes checklist FIRST (chapters timestamped, every link captured, names spelled right), then gets the transcript on file, then writes the shownotes from it. Use for episode shownotes, transcribing an episode, chapter timestamps, and 'turn this recording into shownotes'.\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 shownotes (planner) — locate the recording or transcript, lock the shownotes checklist → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Get the transcript on file (transcriber) — clean, speaker-labeled, timestamped transcript under transcripts/\n3. Write the shownotes (copywriter) — summary, timestamped chapters, links and mentions, pull quotes → gated on artifact `{{workPath}}/report.md` (markdown-report)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "scope",
+  "triggers": [
+    "turn the recording into shownotes",
+    "shownotes for the episode",
+    "transcribe the episode",
+    "episode chapters and shownotes",
+    "write the shownotes"
+  ],
+  "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 shownotes",
+      "description": "locate the recording or transcript, lock the shownotes checklist",
+      "prompt": "Define the job before touching the audio. Step 1: find the episode's recording or transcript — check the recordings folder and episodes.json for which episode is being shipped and what already exists on file. Step 2: confirm with the owner anything the transcript alone won't give you — guest name spellings, links they promised listeners, and where the shownotes get published. Step 3: write an acceptance-criteria checklist ('a clean, complete transcript is on file under transcripts/', 'every chapter has a timestamp that exists in the transcript', 'every link mentioned in the episode is captured', 'names spelled right throughout', 'the summary reads like the episode, not a form'). Call write_task_note with the episode + checklist and write {{workPath}}/scope.md.\n\nThe deliverable `{{workPath}}/scope.md` lands in the project's artifacts drawer — write it with `write_artifact` and read it back with `read_artifact`; the shipped workspace stays untouched.",
+      "suggestedRole": "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": "transcript",
+      "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": "transcript",
+      "name": "Get the transcript on file",
+      "description": "clean, speaker-labeled, timestamped transcript under transcripts/",
+      "prompt": "Get the transcript on file. Step 1: if a transcript already exists (a provided file in the recordings folder), start from that; otherwise produce one from the recording through the project's transcription capabilities. Step 2: clean it — fix obvious mis-hearings, label the speakers, keep the timestamps. Step 3: save the cleaned transcript in the transcripts/ folder named for the episode (for example transcripts/ep12.md). A real transcript is substantial — never a stub or a summary. Step 4: call write_task_note with the transcript path and an approximate word count.",
+      "suggestedRole": "transcriber",
+      "next": "shownotes",
+      "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": "shownotes",
+      "name": "Write the shownotes",
+      "description": "summary, timestamped chapters, links and mentions, pull quotes",
+      "prompt": "Write the shownotes from the transcript. Step 1: a short summary a listener actually reads — what the episode is about and why it's worth their hour, in the show's voice. Step 2: the chapter list — timestamped, one line per chapter, every timestamp taken from the transcript, never invented. Step 3: links and mentions — everything referenced in the episode, with where each one points. Step 4: two or three pull quotes worth sharing, verbatim from the transcript with their speaker. Step 5: write {{workPath}}/report.md and call write_task_note with the chapter count and the link count.\n\nThe deliverable `{{workPath}}/report.md` lands in the project's artifacts drawer — write it with `write_artifact` and read it back with `read_artifact`; the shipped workspace stays untouched.",
+      "suggestedRole": "copywriter",
+      "advanceWhen": {
+        "file": "{{workPath}}/report.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/report.md",
+            "bytes": 1500,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i",
+            "label": "at least one markdown heading",
+            "artifact": true
+          }
+        ],
+        "onReject": "shownotes",
+        "maxAttempts": 4
+      },
+      "next": "evaluate",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "artifact",
+        "additionalOutputMedia": [
+          "task-note"
+        ]
+      }
+    },
+    {
+      "id": "evaluate",
+      "name": "Evaluate",
+      "description": "Grade the deliverable against every acceptance criterion. All pass → finish; any fail → loop back and fix the gap.",
+      "prompt": "Open {{workPath}}/report.md and the transcript under transcripts/ and verify every criterion from {{workPath}}/scope.md: the transcript on file is complete and speaker-labeled, every chapter timestamp appears in the transcript (spot-check each one — a chapter that points at nothing is fabrication), every link mentioned in the episode is captured, names are spelled the way the owner confirmed, and the pull quotes are verbatim. Write PASS/FAIL per criterion; on any failure, name the gap and loop back to shownotes.\n\nThe deliverable lives in the project's artifacts drawer — open `{{workPath}}/report.md` with `read_artifact`, not `read_file`.\n\nThen route — this is the whole point of the loop:\n\n- **Every criterion PASSES →** call `advance_task_step({ ref, stepId: \"evaluate\", next: \"finish\" })`.\n- **Any criterion FAILS →** write the specific gaps to notes, then call `advance_task_step({ ref, stepId: \"evaluate\", next: \"shownotes\" })` to loop back. The builder fixes exactly those gaps.\n\nNever route to `finish` while any criterion is unmet. The build phase's completion gate already blocked a grossly-incomplete deliverable; your job is the judgment an automated check cannot make (does it actually work, read well, look right). After ~3 unproductive loops, stop and report DONE_WITH_CONCERNS so the user can step in.",
+      "suggestedRole": "reviewer",
+      "consumes": [
+        {
+          "file": "{{workPath}}/report.md",
+          "artifact": true
+        }
+      ],
+      "next": "shownotes",
+      "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/tr/transcribe-and-shownotes/versions/1.0.3/test.json

@@ -0,0 +1,101 @@
+{
+  "schemaVersion": 1,
+  "title": "Transcript to Shownotes — episode 12",
+  "objective": "Measure whether the transcribe-and-shownotes craftbook files a clean transcript and produces shownotes whose chapter timestamps, links, and quotes all trace to the transcript.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "weve got the raw transcript for episode 12 in recordings/ep12-transcript.txt — can you turn it into shownotes with chapters? tasks/eval/report.md is fine",
+  "setup": {
+    "projectName": "Shelf Life Podcast",
+    "about": "Podcast studio project for Shelf Life, a weekly show about books and the people who make them. Raw recordings and transcripts land under workspace/recordings; the episode store is workspace/episodes.json.",
+    "missionObjectives": "Turn shipped episodes into a publishable archive: clean transcript on file, timestamped chapters, links captured. Grounded in the seeded transcript — no live services, no real credentials.",
+    "files": [
+      {
+        "path": "recordings/ep12-transcript.txt",
+        "content": "Shelf Life — Episode 12 raw transcript (auto-generated, unedited)\nRecorded 2026-07-09. Host: Noor. Guests: Marta Velde (bookbinder), Daan Pols (apprentice).\n\n[00:00] NOOR: Welcome back to Shelf Life. Today we are in an actual bindery, which smells like glue and paper dust and, honestly, like heaven.\n[00:42] NOOR: Marta Velde has been binding books by hand for thirty-one years. Marta, welcome.\n[01:15] MARTA: Thank you. You are the first person to bring a microphone in here. Usually they bring broken books.\n[02:30] NOOR: Let's start there. What arrives on your bench in an average week?\n[03:48] MARTA: Family bibles, mostly. And cookbooks. People cry over cookbooks more than bibles, if you want the truth. The stains are the memories.\n[05:10] NOOR: How did you learn the trade?\n[06:55] MARTA: My teacher took me on in 1995. Four years sweeping floors before he let me sew a spine. I tell people that and they think it is cruelty. It was patience.\n[08:20] NOOR: And now you have an apprentice of your own. Daan, you are twenty-three. Why this trade?\n[09:45] DAAN: I was studying logistics and I hated every minute of it. I saw Marta repair a 1911 atlas on a video and I emailed her that night.\n[11:02] MARTA: He emailed me eleven times.\n[12:30] NOOR: Persistence is the trade, from what I am hearing. Marta, walk me through the atlas repair. What does a book like that need?\n[14:05] MARTA: First you take it apart completely. People are shocked by that. To save a book you must be willing to reduce it to sheets and thread.\n[15:40] MARTA: The spine linings come off with wheat starch paste and a bone folder. Slow. If you rush the paste you tear the paper and then you are not a binder, you are a butcher.\n[17:12] NOOR: How long does a full rebind take?\n[18:50] MARTA: Twenty hours for a simple case binding. The atlas took ninety. We charge less than the hours, always. Nobody pays what the hours cost. You do it because the book deserves it.\n[20:15] NOOR: Daan, what is the hardest skill so far?\n[21:48] DAAN: Sewing headbands. Marta makes it look like knitting. Mine look like a fishing accident.\n[23:30] NOOR: For listeners who want to try this — where do they start?\n[25:05] MARTA: We teach beginner classes at the bindery, first Saturday of every month. The schedule is at bindery-lane.example.com/classes.\n[26:40] NOOR: I will put that in the shownotes. What about materials? People always ask where to buy proper paper.\n[28:15] DAAN: Paper Road. It is a small mill shop, they ship everywhere. paperroad.example.org. Their 90-gram laid paper is what we sew practice blocks with.\n[29:50] NOOR: And if someone has a family book that needs repair but you are booked out?\n[31:20] MARTA: The guild keeps a directory of certified binders by region — guild-of-binders.example.net/directory. Anyone listed there will treat your book honestly.\n[33:00] NOOR: What is a book you refused to repair?\n[34:35] MARTA: A first edition someone wanted rebound in neon leather. I sent them away. Restoration is listening to the book, not shouting over it.\n[36:10] NOOR: Daan, where do you want to be in ten years?\n[37:45] DAAN: Running my own bench. Maybe here. Marta says the bindery outlives the binder, and I want that to be true.\n[39:20] MARTA: It is true. This bench was my teacher's bench. The scars in the wood are his.\n[40:55] NOOR: That gave me chills. Before we close — the mailbag question. A listener asks: are e-readers killing your trade?\n[42:30] MARTA: The opposite. The rarer the physical book becomes, the more the surviving ones matter. My waiting list has never been longer.\n[44:05] NOOR: Marta Velde, Daan Pols, thank you both. Come back with the apprentice's first solo binding.\n[45:40] DAAN: Deal. Give me a year.\n[46:52] NOOR: Shelf Life is back Monday. Bring us your broken cookbooks.\n[47:30] END OF RECORDING\n"
+      },
+      {
+        "path": "episodes.json",
+        "content": "{\n  \"show\": \"Shelf Life\",\n  \"cadence\": \"weekly — records Thursday, publishes Monday\",\n  \"targetMinutes\": 45,\n  \"episodes\": [\n    {\n      \"number\": 10,\n      \"title\": \"The Library Cart Economy\",\n      \"publishedAt\": \"2026-06-29\"\n    },\n    {\n      \"number\": 11,\n      \"title\": \"Why Paperbacks Survive\",\n      \"publishedAt\": \"2026-07-06\"\n    },\n    {\n      \"number\": 12,\n      \"title\": \"Interview: The Last Bookbinder\",\n      \"publishedAt\": \"2026-07-13\",\n      \"guests\": [\"Marta Velde\", \"Daan Pols\"]\n    }\n  ]\n}\n"
+      }
+    ],
+    "worker": {
+      "name": "Sanne",
+      "role": "Copywriter"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "tasks/eval/report.md is publishable shownotes — summary, timestamped chapters, links, pull quotes — and every timestamp in it exists in the seeded transcript (no fabricated chapters).",
+    "deliverables": [
+      {
+        "path": "tasks/eval/report.md",
+        "kind": "markdown-report",
+        "minBytes": 1500,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "\\d{1,2}:\\d{2}",
+            "label": "timestamped chapters"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "chapter",
+            "flags": "i"
+          },
+          {
+            "kind": "valuesSubsetOf",
+            "file": "tasks/eval/report.md",
+            "sourceFiles": [
+              "recordings/*.txt"
+            ],
+            "pattern": "(\\d{1,2}:\\d{2})",
+            "minMatches": 4,
+            "label": "every timestamp traces to the transcript"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "tasks/eval/report.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "fidelity",
+        "description": "Chapters, links, names, and quotes come from the transcript — nothing invented, names spelled as recorded."
+      },
+      {
+        "name": "chapter quality",
+        "description": "Chapter breaks land where the conversation actually turns, with titles that tell a listener what they will hear."
+      },
+      {
+        "name": "scannability",
+        "description": "A listener can skim the summary, chapters, and links in under a minute and decide to hit play."
+      },
+      {
+        "name": "tone",
+        "description": "The summary reads like the show's voice, not a form letter."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "timestamp fidelity",
+    "link capture",
+    "chapter craft"
+  ]
+}

package/data/craftbook-templates/tr/transcribe-audio/versions/1.0.2/test.json

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