@bendyline/gilde 0.1.50 → 0.1.52

package/data/craftbook-templates/me/meeting-prep-brief/versions/1.0.3/test.json

@@ -0,0 +1,187 @@
+{
+  "schemaVersion": 1,
+  "title": "Meeting Prep Brief smoke eval",
+  "objective": "Task-specific eval for the Meeting Prep Brief craftbook: the vendor sync's attendees come from a live fake calendar service, the prior meeting's notes carry three commitments (one silently dropped), and tasks/eval/report.md is a one-page brief that surfaces all of it plus ranked questions.",
+  "tags": [
+    "external"
+  ],
+  "prompt": "ive got the vendor sync thursday — can you prep me a brief? last meetings notes are in tasks/eval/ and the event details come from the fake calender service, theres a probe script wired for it",
+  "setup": {
+    "projectName": "Calendar Desk — Meeting Prep Eval",
+    "about": "Self-contained eval project for meeting-prep-brief. The calendar is wired as a live fake service — endpoints in mocks/services.md, and the ready-made mock-probe project script fetches the upcoming events and the target event's detail. Prior meeting notes are seeded under tasks/eval/; the deliverable is tasks/eval/report.md.",
+    "missionObjectives": "Use the Meeting Prep Brief craftbook/template, pull the vendor sync's details (attendees included) from the fake calendar service through the provided probe, ground every claim in the prior notes, and write tasks/eval/report.md. No real services, credentials, or live calendars — only the wired mock.",
+    "files": [
+      {
+        "path": "tasks/eval/vendor-sync-2026-06.md",
+        "content": "# Vendor sync - Northwind Systems - 2026-06-18\n\nAttending: Dana Whitfield, Marcus Lee (Northwind); Priya Raman, me.\n\n## What happened\n- Walked the integration scope; Northwind demoed the sandbox tenant.\n- Pricing came up again - they hinted the per-seat tier could move if we commit by Q3.\n\n## Commitments\n- We send the revised pricing tiers by July 1. (sent June 30 - done)\n- Dana sends the data-migration timeline by June 25. (never arrived - still open)\n- Both sides name a launch owner. (ours is Priya, theirs is Marcus - done)\n\n## Parking lot\n- Sandbox rate limits looked tight for our nightly sync - nobody owned this.\n"
+      }
+    ],
+    "worker": {
+      "name": "Meike",
+      "role": "Planner"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [
+    {
+      "kind": "http",
+      "id": "calendar",
+      "description": "Fake calendar service for this eval. GET /api/events/upcoming lists the next events; GET /api/events/EVT-204 returns the vendor sync's full detail including attendees.",
+      "credential": {
+        "name": "mock.calendar"
+      },
+      "routes": [
+        {
+          "method": "GET",
+          "path": "/api/events/upcoming",
+          "body": {
+            "events": [
+              {
+                "id": "EVT-204",
+                "title": "Vendor sync - Northwind Systems",
+                "start": "2026-07-23T14:00",
+                "end": "2026-07-23T15:00",
+                "location": "video"
+              },
+              {
+                "id": "EVT-205",
+                "title": "Design review",
+                "start": "2026-07-24T09:30",
+                "end": "2026-07-24T10:30",
+                "location": "studio"
+              }
+            ]
+          }
+        },
+        {
+          "method": "GET",
+          "path": "/api/events/EVT-204",
+          "body": {
+            "id": "EVT-204",
+            "title": "Vendor sync - Northwind Systems",
+            "start": "2026-07-23T14:00",
+            "end": "2026-07-23T15:00",
+            "location": "video",
+            "attendees": [
+              "Dana Whitfield (Northwind, account lead)",
+              "Marcus Lee (Northwind, migration engineer)",
+              "Priya Raman (our launch owner)",
+              "you"
+            ],
+            "agenda": null
+          }
+        }
+      ]
+    },
+    {
+      "kind": "cli",
+      "id": "probe",
+      "description": "Provenance-trusted project script `mock-probe` that lists the upcoming events and fetches the vendor sync's detail from the fake calendar through http.authed.",
+      "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    'Probe the live fake calendar service for this eval: lists the upcoming events and fetches the full detail (attendees included) of the first one. Outputs the raw JSON responses as evidence for the brief.',\n  inputs: {},\n  outputs: {\n    upcoming: { type: 'string', description: 'Raw JSON body from the upcoming-events listing.' },\n    detail: { type: 'string', description: 'Raw JSON body of the first upcoming event, attendees included.' },\n  },\n  requires: ['workspace.read', 'network', 'credential:mock.calendar'],\n});\n\nconst services = JSON.parse(await gezel.fs.read('mocks/services.json'));\nconst base = (id) => {\n  const service = services.find((entry) => entry.id === id);\n  if (!service) throw new Error(`mock service \"${id}\" is not listed in mocks/services.json`);\n  return service.baseUrl;\n};\n\nconst upcoming = await gezel.http.authed(`${base('calendar')}/api/events/upcoming`, {\n  credential: 'mock.calendar',\n});\nif (!upcoming.ok) throw new Error(`upcoming listing failed: ${upcoming.status} ${upcoming.body}`);\n\nconst first = JSON.parse(upcoming.body).events[0];\nconst detail = await gezel.http.authed(`${base('calendar')}/api/events/${first.id}`, {\n  credential: 'mock.calendar',\n});\nif (!detail.ok) throw new Error(`event detail failed: ${detail.status} ${detail.body}`);\n\ngezel.output({ upcoming: upcoming.body, detail: detail.body });\n"
+      }
+    }
+  ],
+  "success": {
+    "summary": "tasks/eval/report.md is a one-page brief grounded in the live fake calendar and the prior notes: attendees match the calendar record, the never-delivered migration timeline resurfaces with its status, and at least two ranked questions are ready to ask aloud.",
+    "deliverables": [
+      {
+        "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": "Dana",
+            "flags": "i",
+            "label": "attendees come from the live calendar record"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "Marcus",
+            "flags": "i",
+            "label": "the second Northwind attendee is named"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "commit|promis|agreed|owe",
+            "flags": "i",
+            "label": "last-time commitments appear with status"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "migration|timeline",
+            "flags": "i",
+            "label": "the silently-dropped migration timeline resurfaces"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "\\?",
+            "label": "the brief asks real questions"
+          },
+          {
+            "kind": "judge",
+            "file": "tasks/eval/report.md",
+            "rubric": "The brief reads in under two minutes, and every claim traces to the prior meeting notes or the calendar detail — nothing invented. The never-delivered data-migration timeline is surfaced as an open item rather than forgotten.",
+            "sourceFiles": [
+              "tasks/eval/vendor-sync-2026-06.md"
+            ],
+            "label": "grounded and elevator-readable"
+          }
+        ]
+      }
+    ],
+    "mocks": [
+      {
+        "service": "calendar",
+        "minRequests": 1,
+        "requiredPaths": [
+          "^/api/events"
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "tasks/eval/report.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "grounding",
+        "description": "Every attendee, commitment, and claim traces to the calendar record or the prior notes — nothing from memory or imagination."
+      },
+      {
+        "name": "brevity",
+        "description": "One page, elevator-readable; the goal is one sentence near the top."
+      },
+      {
+        "name": "question-quality",
+        "description": "At least two ranked questions, phrased to say out loud, aimed at what actually matters."
+      },
+      {
+        "name": "follow-through",
+        "description": "The dropped commitment (the migration timeline that never arrived) is surfaced as the real business of the meeting."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "calendar grounding",
+    "commitment tracking",
+    "one-page discipline"
+  ]
+}

package/data/craftbook-templates/me/meeting-summary-audio/versions/1.0.2/test.json

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

package/data/craftbook-templates/me/meeting-summary-audio/versions/1.0.3/craftbook.json

@@ -0,0 +1,220 @@
+{
+  "id": "meeting-summary-audio",
+  "name": "Meeting Recording to Minutes & Actions",
+  "description": "Turn a meeting recording into structured minutes plus a clear action-item list — who agreed to do what by when — derived from the audio. Transcribes the recording FIRST (with speaker labels so attribution is possible), then summarizes into decisions, discussion, and assigned action items with owners and due dates. The transcribe-then-summarize ordering is essential: you cannot reliably attribute decisions and owners without first knowing who said what, and minutes without owners are useless.\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. Transcribe the meeting (developer) — STT with speaker labels + timestamps → gated on artifact `{{workPath}}/transcript.md` (markdown-doc)\n2. Summarize into minutes & actions (copywriter) — decisions, discussion, action items with owners + dates → gated on `minutes.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": "transcribe",
+  "triggers": [
+    "meeting minutes from recording",
+    "summarize this meeting",
+    "action items from a call",
+    "turn a recording into notes",
+    "who agreed to what"
+  ],
+  "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": "transcribe",
+      "name": "Transcribe the meeting",
+      "description": "STT with speaker labels + timestamps",
+      "prompt": "Get an attributable transcript BEFORE summarizing. Step 1: record the source (path, duration, and attendee names if known). Step 2: run speech-to-text over the WHOLE recording with diarization, labeling speakers (map to real names where you can infer them from introductions). Step 3: timestamp utterances so decisions/actions can cite a moment. Step 4: lightly clean filler for readability but keep commitments verbatim. Step 5: write the labeled transcript to `{{workPath}}/transcript.md` via write_task_note AND the produces path, and note its final timestamp vs the duration so coverage is checkable. On a loop-back, fix only flagged attribution/coverage gaps.\n\nThe deliverable `{{workPath}}/transcript.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": "{{workPath}}/transcript.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/transcript.md",
+            "bytes": 500,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/transcript.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i",
+            "label": "at least one markdown heading",
+            "artifact": true
+          }
+        ],
+        "onReject": "transcribe",
+        "maxAttempts": 3
+      },
+      "next": "summarize",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "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": "summarize",
+      "name": "Summarize into minutes & actions",
+      "description": "decisions, discussion, action items with owners + dates",
+      "prompt": "Write the minutes from the transcript. Step 1: lead with meeting metadata (title, date if known, attendees). Step 2: write a 'Decisions' section — each decision a tight bullet, with who made/agreed it. Step 3: write a 'Discussion' section summarizing key points by topic (not a re-transcription). Step 4: write an 'Action Items' section as a checklist where EVERY item has an explicit owner and a due date (write 'owner: TBD' / 'due: TBD' only if truly unstated — never silently drop the field). Step 5: add an 'Open Questions' section for anything unresolved. Do not invent commitments not in the transcript; attribute owners only when the transcript supports it. Write it all to `minutes.md` with clear headers. write_task_note the path and the action-item count. On a loop-back, fix only the flagged sections.",
+      "suggestedRole": "copywriter",
+      "advanceWhen": {
+        "file": "minutes.md",
+        "minBytes": 1,
+        "sniff": "nonempty"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "minutes.md",
+            "bytes": 500
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkContains",
+            "scope": "standard",
+            "inputs": {
+              "file": "minutes.md",
+              "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+              "flags": "i"
+            }
+          }
+        ],
+        "onReject": "summarize",
+        "maxAttempts": 4
+      },
+      "next": "evaluate",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "artifacts",
+          "audio",
+          "browser-automation",
+          "code-execution",
+          "craftbooks",
+          "data-tables",
+          "entity-intel",
+          "git",
+          "image-intel",
+          "images",
+          "role-delegation",
+          "role-delegation-escalation",
+          "security-intel",
+          "team-management",
+          "videos",
+          "web"
+        ],
+        "outputMedium": "workspace",
+        "additionalOutputMedia": [
+          "task-note"
+        ]
+      }
+    },
+    {
+      "id": "evaluate",
+      "name": "Evaluate",
+      "description": "Grade the deliverable against every acceptance criterion. All pass → finish; any fail → loop back and fix the gap.",
+      "prompt": "Check the minutes against the recording. Step 1: confirm `minutes.md` has Decisions, Discussion, Action Items, and Open Questions sections with metadata up top (PASS/FAIL). Step 2: confirm EVERY action item has an owner and a due-date field (explicit or TBD) — no item missing the fields. Step 3: spot-check 3 decisions/actions against the transcript — each is real and attributed correctly, nothing invented. Step 4: confirm the summary is condensed (not a re-transcription) yet covers the major topics. Step 5: confirm transcript coverage reached the end of the recording. Write PASS/FAIL per criterion.\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: \"summarize\" })` 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": "minutes.md"
+        }
+      ],
+      "next": "summarize",
+      "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/me/meeting-summary-audio/versions/1.0.3/test.json

@@ -0,0 +1,103 @@
+{
+  "schemaVersion": 1,
+  "title": "Meeting Recording to Minutes & Actions smoke eval",
+  "objective": "Self-contained smoke eval for the Meeting Recording to Minutes & Actions craftbook using the media generic harness.",
+  "tags": [
+    "media"
+  ],
+  "prompt": "Our media files are all listd in source/media-index.csv. Can you put together the production plan for them as media-plan.json?",
+  "setup": {
+    "projectName": "Meeting Recording to Minutes & Actions Eval",
+    "about": "Self-contained eval project for meeting-summary-audio. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/media-plan.json.",
+    "missionObjectives": "Use the Meeting Recording to Minutes & Actions craftbook/template, read the seeded local fixtures, and write media-plan.json without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Meeting Recording to Minutes & Actions 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: meeting-summary-audio - Meeting Recording to Minutes & Actions.\n"
+      },
+      {
+        "path": "source/media-index.csv",
+        "content": "filename,type,duration_or_size,notes\npilot-interview.wav,audio,00:02:15,mentions response time and status silence\nreturns-desk.png,image,1600x900,shows intake form and photo evidence step\nlaunch-clip.mp4,video,00:01:05,shows barcode exception handling\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Producer"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "media-plan.json is a valid JSON media-production manifest grounded in seeded fixture metadata.",
+    "deliverables": [
+      {
+        "path": "media-plan.json",
+        "kind": "json",
+        "minBytes": 700,
+        "checks": [
+          {
+            "kind": "sniff",
+            "file": "media-plan.json",
+            "sniff": "json-valid"
+          },
+          {
+            "kind": "contains",
+            "file": "media-plan.json",
+            "pattern": "pilot-interview\\.wav|returns-desk\\.png|launch-clip\\.mp4",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "media-plan.json",
+            "pattern": "outputs|assets|steps|cues|verification",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "media-plan.json",
+            "pattern": "accessibility|alt|caption|transcript|metadata",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "media-plan.json",
+      "kind": "json"
+    },
+    "axes": [
+      {
+        "name": "completeness",
+        "description": "The manifest covers sources, outputs, and processing steps end to end."
+      },
+      {
+        "name": "grounding",
+        "description": "Only seeded media fixtures are referenced, with faithful metadata."
+      },
+      {
+        "name": "accessibility",
+        "description": "Alt text, captions, or transcripts are planned wherever the class requires."
+      },
+      {
+        "name": "precision",
+        "description": "Timestamps, crops, and cues are specific enough to execute."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "media fixture handling",
+    "structured manifest",
+    "verification metadata"
+  ],
+  "extensions": {
+    "legacySimulators": [
+      {
+        "id": "meeting-summary-audio-media-fixtures",
+        "kind": "data-source",
+        "status": "implemented",
+        "description": "Seeded local media index replacing real audio, video, image generation, and external media metadata services."
+      }
+    ]
+  }
+}

package/data/craftbook-templates/me/memory-prompt-session/versions/1.0.2/test.json

@@ -27,9 +27,6 @@
     "worker": {
       "name": "Milan",
       "role": "Archivist"
-    },
-    "craftbookParams": {
-      "workPath": "tasks/eval"
     }
   },
   "mocks": [],