@bendyline/gilde 0.1.37 → 0.1.39

package/data/craftbook-templates/se/seasonal-maintenance-sweep/versions/1.0.2/craftbook.json

@@ -0,0 +1,152 @@
+{
+  "id": "seasonal-maintenance-sweep",
+  "name": "Seasonal Maintenance Sweep",
+  "description": "Run a season's home-care sweep against the project's systems roster: work out what care is due or overdue from each system's interval, plan the walkthrough in a sensible order with supplies, then log the completed care and flag what needs a professional — leaving the roster's due-tracking reset and a short sweep report. Locks the season's scope and the due list FIRST, then plans, then logs — so seasonal care becomes a checklist ritual instead of a vague worry. Use for spring/fall home maintenance, seasonal checkups, 'what does the house need', and pre-winter prep.\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 sweep (planner) — season, due and overdue list from the roster intervals → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Plan the walkthrough (planner) — ordered walkthrough with steps and supplies per system → gated on artifact `{{workPath}}/plan.md` (markdown-notes)\n3. Log the sweep (copywriter) — record completed care, flag findings, write the sweep report → 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": [
+    "seasonal maintenance sweep",
+    "what does the house need",
+    "fall home checkup",
+    "spring maintenance",
+    "pre-winter prep"
+  ],
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the sweep",
+      "description": "season, due and overdue list from the roster intervals",
+      "prompt": "Define the sweep before planning it. Step 1: read systems.json from the workspace and determine the current season and which systems' care is due or overdue from each record's interval and last-done date, plus anything already flagged for attention. Step 2: with the owner, add any season-specific care the roster doesn't carry yet (gutters before the rains, hose bibs before frost) so the roster grows with each sweep. Step 3: split the list into owner-doable versus needs-a-professional. Step 4: write an acceptance-criteria checklist ('every due or overdue system is in the plan or explicitly deferred with a reason', 'each completed item gets its care logged so the due-tracking resets', 'professional items produce a booking note, not a vague intention', 'the report states what was done, deferred, and flagged'). Call write_task_note with the due counts + 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": "plan"
+    },
+    {
+      "id": "plan",
+      "name": "Plan the walkthrough",
+      "description": "ordered walkthrough with steps and supplies per system",
+      "prompt": "Plan the walkthrough from the locked list. Step 1: order the due items into a sensible route (outside before weather turns, top of the house down, wet work last). Step 2: for each item, write the short concrete care steps and what supplies or tools it needs, so the owner can walk the list without stopping to think. Step 3: batch the supply needs into one shopping line. Step 4: for the professional items, draft the booking note per trade — what is wrong or due, and the questions to ask. Step 5: write the ordered plan to {{workPath}}/plan.md and call write_task_note with the item count and the supply list length.\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": "log"
+    },
+    {
+      "id": "log",
+      "name": "Log the sweep",
+      "description": "record completed care, flag findings, write the sweep report",
+      "prompt": "Close the sweep once the owner reports what got done. Step 1: for each completed item, log the maintenance through the project's house capabilities so the system's due-tracking resets. Step 2: for anything the walkthrough surfaced (a drip, a crack, a filter worse than expected), flag the system for attention with a note. Step 3: record what was deferred and why. Step 4: write the sweep report — done, deferred, flagged, and the professional bookings to make — short enough to read in a minute. Step 5: end with the next season's earliest due item so the ritual has a natural next date. Write {{workPath}}/report.md and call write_task_note with the done/deferred/flagged counts.\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": "log",
+        "maxAttempts": 4
+      },
+      "next": "evaluate"
+    },
+    {
+      "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 due or overdue system appears as done, deferred-with-reason, or flagged; every completed item's care was logged so its due-tracking reset (spot-check two against the roster); professional items carry a booking note; and the report states done/deferred/flagged plainly. Write PASS/FAIL per criterion; on any failure, name the gap and loop back to log.\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: \"log\" })` 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": "log"
+    },
+    {
+      "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
+    }
+  ],
+  "version": "1.0.2",
+  "releasedAt": "2026-08-21T00:00:00Z",
+  "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}}"
+      }
+    }
+  },
+  "minGezelVersion": "1.26233"
+}

package/data/craftbook-templates/se/seasonal-maintenance-sweep/versions/1.0.2/test.json

@@ -0,0 +1,113 @@
+{
+  "schemaVersion": 1,
+  "title": "Seasonal Maintenance Sweep smoke eval",
+  "objective": "Self-contained smoke eval for the Seasonal Maintenance Sweep craftbook using the external generic harness.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "Theres a fake service set up for this so nothing real gets touched — details are in fixtures/fake-service.md. Can you work out the automation and write up how it woudl run in automation.md?",
+  "setup": {
+    "projectName": "Seasonal Maintenance Sweep Eval",
+    "about": "Self-contained eval project for seasonal-maintenance-sweep. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/automation.md.",
+    "missionObjectives": "Use the Seasonal Maintenance Sweep craftbook/template, read the seeded local fixtures, and write automation.md without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Seasonal Maintenance Sweep 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: seasonal-maintenance-sweep - Seasonal Maintenance Sweep.\n"
+      },
+      {
+        "path": "fixtures/fake-service.md",
+        "content": "# Fake Service Fixture\n\nThis eval must stay in dry-run mode.\n\nAvailable fake endpoints and commands:\n- GET /api/bookings/open returns BKG-1001, BKG-1002, BKG-1003.\n- POST /api/bookings/dry-run records a simulated submission and returns DRY_RUN_OK.\n- fake-ci status returns pending twice and success on the third poll.\n- fake-github pr create returns https://example.invalid/pull/42.\n\nThe deliverable must reference these fixture names instead of real services or credentials.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Developer"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "automation.md is a dry-run external-automation artifact grounded in fake service fixtures.",
+    "deliverables": [
+      {
+        "path": "automation.md",
+        "kind": "markdown-report",
+        "minBytes": 900,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "automation.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "automation.md",
+            "pattern": "DRY_RUN_OK|dry-run|dry run",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "automation.md",
+            "pattern": "fake-ci|fake-github|/api/bookings",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "automation.md",
+            "pattern": "no real|credentials|safety|guard",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "automation.md",
+            "pattern": "success|failure|retry|abort",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "automation.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "safety",
+        "description": "Dry-run posture is explicit: no real credentials, clear stop-before-side-effect boundary."
+      },
+      {
+        "name": "mapping",
+        "description": "Fake endpoints/commands are mapped completely to the workflow steps."
+      },
+      {
+        "name": "signals",
+        "description": "Success, failure, retry, and abort conditions are all defined."
+      },
+      {
+        "name": "containment",
+        "description": "The plan cannot accidentally reach a real service from a mock context."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "dry-run safety",
+    "fake tool mapping",
+    "side-effect containment"
+  ],
+  "extensions": {
+    "legacySimulators": [
+      {
+        "id": "seasonal-maintenance-sweep-fake-service-fixture",
+        "kind": "data-source",
+        "status": "implemented",
+        "description": "Seeded local fake service contract replacing live CLIs, HTTP APIs, credentials, and side effects."
+      }
+    ]
+  }
+}