@bendyline/gilde 0.1.50 → 0.1.52

package/data/craftbook-templates/we/week-plan/versions/1.0.3/craftbook.json

@@ -0,0 +1,276 @@
+{
+  "id": "week-plan",
+  "name": "Plan the Week",
+  "description": "Start Monday with the week already shaped: every meeting seen, the ones needing prep flagged, the conflicts and overload called out, and real focus blocks defended — a plan you made once, on purpose, instead of a calendar you react to all week. Locks the week's events and the planning rules FIRST, then shapes the days, then writes the plan with its prep queue. Use for weekly planning, monday morning planning, 'what does my week look like', calendar reviews, and defending focus time.\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 week (planner) — the week's events, the flags, the planning rules locked → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Shape the days (planner) — day-by-day plan, focus blocks placed, conflicts resolved on paper → gated on artifact `{{workPath}}/plan.md` (markdown-notes)\n3. Write the week plan (copywriter) — the Monday-morning page: days, prep queue, conflicts and calls → 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": [
+    "plan the week",
+    "plan my week",
+    "what does my week look like",
+    "monday planning",
+    "set up the week"
+  ],
+  "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 week",
+      "description": "the week's events, the flags, the planning rules locked",
+      "prompt": "Define the week before shaping a single day. Step 1: read the week's events — from calendar.json in the workspace when the calendar syncs to a file, or through the project's calendar capabilities when it is wired as a live service — and read followups.json for the open follow-ups carried into this week. Step 2: sweep the events for what needs attention: meetings with no agenda or unclear purpose (they need prep), pairs that overlap or butt against each other with no gap, and days so full that real work cannot happen. Step 3: lock the planning rules — every meeting that needs prep gets flagged with what to prepare, every conflict gets named with a proposed resolution, focus blocks get placed on the emptier days, and open follow-ups land on specific days. Step 4: write an acceptance-criteria checklist ('every event this week appears in the plan', 'each prep-needed meeting is flagged with what to prepare', 'every conflict named with a proposed fix', 'focus blocks placed in real gaps', 'the load picture is honest — no day pretends to have room it lacks'). Call write_task_note with the event count + flags + checklist and write {{workPath}}/scope.md. No planning yet.\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": "plan",
+      "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": "plan",
+      "name": "Shape the days",
+      "description": "day-by-day plan, focus blocks placed, conflicts resolved on paper",
+      "prompt": "Shape the week day by day against the locked rules. Step 1: lay out Monday through Friday — each day's meetings in order, with the gaps visible. Step 2: place the focus blocks into the real gaps, the biggest work into the biggest gap, and mark them as commitments, not leftovers. Step 3: for each flagged meeting, note what the prep is and which earlier day the prep happens. Step 4: resolve the conflicts on paper — which meeting moves, shortens, or gets a delegate — as a concrete proposal the owner can act on with one decision each. Step 5: distribute the open follow-ups onto specific days that have room for them. Write the day-by-day plan to {{workPath}}/plan.md and call write_task_note with the shape of the week in one line per day.\n\nThe deliverable `{{workPath}}/plan.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}}/plan.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/plan.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/plan.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "plan",
+        "maxAttempts": 3
+      },
+      "next": "report",
+      "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",
+          "videos",
+          "web",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "artifact",
+        "additionalOutputMedia": [
+          "task-note"
+        ]
+      }
+    },
+    {
+      "id": "report",
+      "name": "Write the week plan",
+      "description": "the Monday-morning page: days, prep queue, conflicts and calls",
+      "prompt": "Write the week plan the owner reads Monday morning. Step 1: open with the week in one honest paragraph — how heavy it is, where the crunch lands, where the room is. Step 2: the day-by-day plan — each weekday with its meetings, focus blocks, and follow-ups, readable at a glance. Step 3: the prep queue — every meeting needing prep, what to prepare, and the day the prep is scheduled. Step 4: the conflicts and calls — each overlap with its proposed fix, so resolving them is one decision each, not a puzzle. Step 5: keep it one page and warm; this is a plan made once, on purpose. Write {{workPath}}/report.md and call write_task_note with the focus-block count and the prep-queue length.\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": "report",
+        "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 {{workPath}}/plan.md and verify every criterion from {{workPath}}/scope.md: every event in the week's calendar appears in the plan (count them against the events you read), each prep-needed meeting carries a concrete prep note scheduled on an earlier day, every conflict is named with a proposed resolution, focus blocks sit in real gaps on the page, follow-ups have landed on specific days, and the load picture is honest. Write PASS/FAIL per criterion; on any failure, name the gap and loop back to report.\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: \"report\" })` 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": "report",
+      "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/we/week-plan/versions/1.0.3/test.json

@@ -0,0 +1,258 @@
+{
+  "schemaVersion": 1,
+  "title": "Plan the Week smoke eval",
+  "objective": "Task-specific eval for the Plan the Week craftbook: the week's eight events come from a live fake calendar service, and tasks/eval/report.md shapes the days with the agenda-less meetings flagged for prep, the Tuesday conflict named, and focus blocks defended.",
+  "tags": [
+    "external"
+  ],
+  "prompt": "monday again — can you pull the week from the calender service and lay out a plan in tasks/eval/report.md? theres a probe script wired to the fake calendar, and my open followups are in the workspace too",
+  "setup": {
+    "projectName": "Calendar Desk — Week Plan Eval",
+    "about": "Self-contained eval project for week-plan. The calendar is wired as a live fake service — endpoints in mocks/services.md, and the ready-made mock-probe project script fetches the week's events. Open follow-ups are seeded at followups.json; the deliverable is tasks/eval/report.md.",
+    "missionObjectives": "Use the Plan the Week craftbook/template, pull the week's events from the fake calendar service through the provided probe, fold in the open follow-ups, and write tasks/eval/report.md. No real services, credentials, or live calendars — only the wired mock.",
+    "files": [
+      {
+        "path": "followups.json",
+        "content": "[\n  {\n    \"id\": \"FU-11\",\n    \"what\": \"Send the revised SOW to Harborview before the demo\",\n    \"due\": \"2026-07-15\",\n    \"status\": \"open\"\n  },\n  {\n    \"id\": \"FU-12\",\n    \"what\": \"Chase Northwind for the data-migration timeline\",\n    \"due\": \"2026-07-13\",\n    \"status\": \"open\"\n  },\n  {\n    \"id\": \"FU-13\",\n    \"what\": \"Book the offsite room for August\",\n    \"due\": \"2026-07-17\",\n    \"status\": \"open\"\n  }\n]\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 returns the current week's events with times, attendees, and agendas (null agenda means nobody wrote one).",
+      "credential": {
+        "name": "mock.calendar"
+      },
+      "routes": [
+        {
+          "method": "GET",
+          "path": "/api/events",
+          "body": {
+            "week": "2026-07-13",
+            "events": [
+              {
+                "id": "EVT-101",
+                "title": "Team standup",
+                "start": "2026-07-13T09:00",
+                "end": "2026-07-13T09:15",
+                "attendees": [
+                  "you",
+                  "the team"
+                ],
+                "agenda": "standing sync"
+              },
+              {
+                "id": "EVT-102",
+                "title": "Vendor sync - Northwind Systems",
+                "start": "2026-07-13T14:00",
+                "end": "2026-07-13T15:00",
+                "attendees": [
+                  "you",
+                  "Dana Whitfield",
+                  "Priya Raman"
+                ],
+                "agenda": null
+              },
+              {
+                "id": "EVT-103",
+                "title": "Q3 budget review",
+                "start": "2026-07-14T10:00",
+                "end": "2026-07-14T11:00",
+                "attendees": [
+                  "you",
+                  "Marcus Lee",
+                  "Finance"
+                ],
+                "agenda": "walk the Q3 numbers"
+              },
+              {
+                "id": "EVT-104",
+                "title": "1:1 with Priya",
+                "start": "2026-07-14T10:30",
+                "end": "2026-07-14T11:00",
+                "attendees": [
+                  "you",
+                  "Priya Raman"
+                ],
+                "agenda": "weekly 1:1"
+              },
+              {
+                "id": "EVT-105",
+                "title": "Client demo - Harborview",
+                "start": "2026-07-15T13:00",
+                "end": "2026-07-15T14:00",
+                "attendees": [
+                  "you",
+                  "Harborview team"
+                ],
+                "agenda": null
+              },
+              {
+                "id": "EVT-106",
+                "title": "Design review",
+                "start": "2026-07-16T09:30",
+                "end": "2026-07-16T10:30",
+                "attendees": [
+                  "you",
+                  "design"
+                ],
+                "agenda": "review the onboarding flow"
+              },
+              {
+                "id": "EVT-107",
+                "title": "Sprint retro",
+                "start": "2026-07-17T11:00",
+                "end": "2026-07-17T12:00",
+                "attendees": [
+                  "you",
+                  "the team"
+                ],
+                "agenda": "retro board"
+              },
+              {
+                "id": "EVT-108",
+                "title": "All-hands",
+                "start": "2026-07-17T15:00",
+                "end": "2026-07-17T16:00",
+                "attendees": [
+                  "everyone"
+                ],
+                "agenda": "company update"
+              }
+            ]
+          }
+        }
+      ]
+    },
+    {
+      "kind": "cli",
+      "id": "probe",
+      "description": "Provenance-trusted project script `mock-probe` that fetches the week's events from the fake calendar through http.authed and returns the raw response.",
+      "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: fetches the weekly events and returns the raw JSON as evidence for the plan.',\n  inputs: {},\n  outputs: {\n    events: { type: 'string', description: 'Raw JSON body from the week events listing.' },\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 \"${id}\" is not listed in mocks/services.json`);\n  return service.baseUrl;\n};\n\nconst events = await gezel.http.authed(`${base('calendar')}/api/events`, {\n  credential: 'mock.calendar',\n});\nif (!events.ok) throw new Error(`events listing failed: ${events.status} ${events.body}`);\n\ngezel.output({ events: events.body });\n"
+      }
+    }
+  ],
+  "success": {
+    "summary": "tasks/eval/report.md is a Monday-morning week plan grounded in the live fake calendar: all five weekdays shaped, the agenda-less meetings in the prep queue, the Tuesday overlap named with a proposed fix, and focus blocks placed.",
+    "deliverables": [
+      {
+        "path": "tasks/eval/report.md",
+        "kind": "markdown-report",
+        "minBytes": 1200,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "Monday",
+            "flags": "i",
+            "label": "the week is laid out day by day, starting Monday"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "Friday",
+            "flags": "i",
+            "label": "the plan reaches the end of the week"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "prep",
+            "flags": "i",
+            "label": "a prep queue exists"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "conflict|overlap|double[- ]?book|clash",
+            "flags": "i",
+            "label": "the calendar conflict is called out"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "focus",
+            "flags": "i",
+            "label": "focus blocks are placed and defended"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "Vendor sync",
+            "flags": "i",
+            "label": "the agenda-less vendor sync from the live calendar is in the plan"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "Harborview",
+            "flags": "i",
+            "label": "the agenda-less client demo from the live calendar is in the plan"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "Priya",
+            "flags": "i",
+            "label": "the overlapping 1:1 is seen, not skipped"
+          }
+        ]
+      }
+    ],
+    "mocks": [
+      {
+        "service": "calendar",
+        "minRequests": 1,
+        "requiredPaths": [
+          "^/api/events"
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "tasks/eval/report.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "coverage",
+        "description": "Every event from the calendar week appears in the plan; nothing is silently dropped and nothing is invented."
+      },
+      {
+        "name": "prioritization",
+        "description": "Focus blocks land in real gaps, the biggest work gets the biggest gap, and follow-ups sit on days with room."
+      },
+      {
+        "name": "conflict-handling",
+        "description": "The overlapping pair is named with a concrete proposed fix the owner can accept in one decision."
+      },
+      {
+        "name": "realism",
+        "description": "The load picture is honest — heavy days are called heavy, and no day is over-packed to look tidy."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "calendar grounding",
+    "prep flagging",
+    "honest load picture"
+  ]
+}

package/data/craftbook-templates/we/weekly-menu-plan/versions/1.0.2/test.json

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