@bendyline/gilde 0.1.50 → 0.1.52

package/data/craftbook-templates/al/album-curate/versions/1.0.3/craftbook.json

@@ -0,0 +1,250 @@
+{
+  "id": "album-curate",
+  "name": "Curate an Album",
+  "description": "Turn a thousand camera-roll photos into the forty that tell the story: cull the near-duplicates, keep the keepers for honest reasons, caption what matters, and leave an album manifest the family will actually revisit. Locks the occasion and the selection criteria FIRST, then curates the manifest one moment at a time, then writes the album's short story. Use for curating an album, photo culling, 'make an album from the weekend', picking the keepers, and turning imports into albums.\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 album (archivist) — occasion, size, and the selection criteria locked → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Curate the manifest (curator) — cluster the bursts, pick the best frames, write the manifest\n3. Write the album's story (copywriter) — the arc, the cuts worth mentioning, what to do next → 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": [
+    "curate an album",
+    "make an album from these photos",
+    "pick the keepers",
+    "cull the photos",
+    "album from the weekend"
+  ],
+  "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 album",
+      "description": "occasion, size, and the selection criteria locked",
+      "prompt": "Define the album before picking a photo. Step 1: read photos/index.json from the workspace — the imported photos with their timestamps — and read any caption notes alongside them (photos/*.txt) describing what the camera saw. Step 2: confirm the occasion and size with the owner — what the album is about, roughly how many photos it should hold, and anything that must be in or out. Step 3: lock the selection criteria — near-duplicates and bursts resolve to the single best frame; every pick carries a caption and an honest reason it made the cut; the picks in order tell the occasion's story, start to end. Step 4: write an acceptance-criteria checklist ('album within the agreed size', 'every pick exists in the photo index — nothing invented', 'each duplicate cluster contributes at most one frame', 'every pick has a caption and a reason', 'the sequence reads as the story of the occasion'). Call write_task_note with the photo count + target size + 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": "archivist",
+      "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": "select",
+      "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": "select",
+      "name": "Curate the manifest",
+      "description": "cluster the bursts, pick the best frames, write the manifest",
+      "prompt": "Curate the album manifest. Step 1: walk the index in time order and group the near-duplicates — bursts and retakes shot seconds apart are one moment, not five photos. Step 2: from each moment worth keeping, choose the single best frame, using the caption notes where they exist to judge what the frame actually shows. Step 3: order the picks so the album tells the occasion start to end. Step 4: write the album manifest into albums/ named for the occasion — a JSON array, one record per pick with file, caption, and reason, the file spelled exactly as the index spells it. Call write_task_note with the pick count and the moments you cut.",
+      "suggestedRole": "curator",
+      "next": "report",
+      "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": "report",
+      "name": "Write the album's story",
+      "description": "the arc, the cuts worth mentioning, what to do next",
+      "prompt": "Write the album's short story for whoever opens it. Step 1: the arc — what the occasion was and how the picks carry it, in a paragraph. Step 2: the cuts worth mentioning — the burst that became one frame, the beloved-but-blurry shot that did not make it — so the family knows the culling was care, not loss. Step 3: anything the owner should re-shoot, print, or ask about. Keep it warm and short. Write {{workPath}}/report.md and call write_task_note with the album path and the pick 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": 800,
+            "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 the album manifest in albums/, {{workPath}}/report.md, and photos/index.json and verify every criterion from {{workPath}}/scope.md: the album is within the agreed size, every pick's file appears in the photo index exactly (spot-check several — no invented or misspelled files), no duplicate cluster contributes more than one frame (check the picks' timestamps), every record carries a nonempty caption and reason, and the order tells the story. Write PASS/FAIL per criterion; on any failure, name the gap and loop back to select.\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: \"select\" })` 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": "select",
+      "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/al/album-curate/versions/1.0.3/test.json

@@ -0,0 +1,147 @@
+{
+  "schemaVersion": 1,
+  "title": "Curate an Album smoke eval",
+  "objective": "Task-specific eval for the Curate an Album craftbook: sixty lake-weekend photos with burst clusters and eight caption notes become a 12-15 pick album manifest whose every file exists in the index, plus a short album story.",
+  "tags": [
+    "data"
+  ],
+  "prompt": "can you curate the lake weekend album from the imported photos? maybe 12-15 picks with captions plese — call it lake-weekend",
+  "setup": {
+    "projectName": "Photo Curator — Album Curate Eval",
+    "about": "Self-contained eval project for album-curate. The watched-folder import has already indexed the weekend's photos into photos/index.json (files + timestamps), and the vision pass left caption notes for the standout frames as photos/IMG_NNNN.txt. The album manifest goes under albums/ and the album's story goes to tasks/eval/report.md.",
+    "missionObjectives": "Use the Curate an Album craftbook/template, pick from the seeded photo index only (bursts resolve to one frame), and finish with albums/lake-weekend.json plus tasks/eval/report.md. No live services or real photo tools — the index and caption notes are the whole record.",
+    "files": [
+      {
+        "path": "photos/index.json",
+        "content": "[\n  {\n    \"file\": \"IMG_4001.jpg\",\n    \"taken\": \"2026-06-19T17:40:00\"\n  },\n  {\n    \"file\": \"IMG_4002.jpg\",\n    \"taken\": \"2026-06-19T17:46:00\"\n  },\n  {\n    \"file\": \"IMG_4003.jpg\",\n    \"taken\": \"2026-06-19T17:51:00\"\n  },\n  {\n    \"file\": \"IMG_4004.jpg\",\n    \"taken\": \"2026-06-19T17:58:00\"\n  },\n  {\n    \"file\": \"IMG_4005.jpg\",\n    \"taken\": \"2026-06-19T17:58:08\"\n  },\n  {\n    \"file\": \"IMG_4006.jpg\",\n    \"taken\": \"2026-06-19T17:58:16\"\n  },\n  {\n    \"file\": \"IMG_4007.jpg\",\n    \"taken\": \"2026-06-19T18:10:00\"\n  },\n  {\n    \"file\": \"IMG_4008.jpg\",\n    \"taken\": \"2026-06-19T18:21:00\"\n  },\n  {\n    \"file\": \"IMG_4009.jpg\",\n    \"taken\": \"2026-06-19T18:35:00\"\n  },\n  {\n    \"file\": \"IMG_4010.jpg\",\n    \"taken\": \"2026-06-19T18:43:00\"\n  },\n  {\n    \"file\": \"IMG_4011.jpg\",\n    \"taken\": \"2026-06-19T18:55:00\"\n  },\n  {\n    \"file\": \"IMG_4012.jpg\",\n    \"taken\": \"2026-06-19T19:08:00\"\n  },\n  {\n    \"file\": \"IMG_4013.jpg\",\n    \"taken\": \"2026-06-20T08:05:00\"\n  },\n  {\n    \"file\": \"IMG_4014.jpg\",\n    \"taken\": \"2026-06-20T08:27:00\"\n  },\n  {\n    \"file\": \"IMG_4015.jpg\",\n    \"taken\": \"2026-06-20T08:52:00\"\n  },\n  {\n    \"file\": \"IMG_4016.jpg\",\n    \"taken\": \"2026-06-20T09:15:00\"\n  },\n  {\n    \"file\": \"IMG_4017.jpg\",\n    \"taken\": \"2026-06-20T09:15:07\"\n  },\n  {\n    \"file\": \"IMG_4018.jpg\",\n    \"taken\": \"2026-06-20T09:15:14\"\n  },\n  {\n    \"file\": \"IMG_4019.jpg\",\n    \"taken\": \"2026-06-20T09:15:21\"\n  },\n  {\n    \"file\": \"IMG_4020.jpg\",\n    \"taken\": \"2026-06-20T09:40:00\"\n  },\n  {\n    \"file\": \"IMG_4021.jpg\",\n    \"taken\": \"2026-06-20T10:05:00\"\n  },\n  {\n    \"file\": \"IMG_4022.jpg\",\n    \"taken\": \"2026-06-20T10:35:00\"\n  },\n  {\n    \"file\": \"IMG_4023.jpg\",\n    \"taken\": \"2026-06-20T10:55:00\"\n  },\n  {\n    \"file\": \"IMG_4024.jpg\",\n    \"taken\": \"2026-06-20T10:55:07\"\n  },\n  {\n    \"file\": \"IMG_4025.jpg\",\n    \"taken\": \"2026-06-20T10:55:14\"\n  },\n  {\n    \"file\": \"IMG_4026.jpg\",\n    \"taken\": \"2026-06-20T11:25:00\"\n  },\n  {\n    \"file\": \"IMG_4027.jpg\",\n    \"taken\": \"2026-06-20T11:50:00\"\n  },\n  {\n    \"file\": \"IMG_4028.jpg\",\n    \"taken\": \"2026-06-20T12:15:00\"\n  },\n  {\n    \"file\": \"IMG_4029.jpg\",\n    \"taken\": \"2026-06-20T12:45:00\"\n  },\n  {\n    \"file\": \"IMG_4030.jpg\",\n    \"taken\": \"2026-06-20T13:10:00\"\n  },\n  {\n    \"file\": \"IMG_4031.jpg\",\n    \"taken\": \"2026-06-20T13:10:07\"\n  },\n  {\n    \"file\": \"IMG_4032.jpg\",\n    \"taken\": \"2026-06-20T13:10:14\"\n  },\n  {\n    \"file\": \"IMG_4033.jpg\",\n    \"taken\": \"2026-06-20T13:10:21\"\n  },\n  {\n    \"file\": \"IMG_4034.jpg\",\n    \"taken\": \"2026-06-20T13:35:00\"\n  },\n  {\n    \"file\": \"IMG_4035.jpg\",\n    \"taken\": \"2026-06-20T14:00:00\"\n  },\n  {\n    \"file\": \"IMG_4036.jpg\",\n    \"taken\": \"2026-06-20T14:35:00\"\n  },\n  {\n    \"file\": \"IMG_4037.jpg\",\n    \"taken\": \"2026-06-20T15:05:00\"\n  },\n  {\n    \"file\": \"IMG_4038.jpg\",\n    \"taken\": \"2026-06-20T15:35:00\"\n  },\n  {\n    \"file\": \"IMG_4039.jpg\",\n    \"taken\": \"2026-06-20T16:05:00\"\n  },\n  {\n    \"file\": \"IMG_4040.jpg\",\n    \"taken\": \"2026-06-20T16:35:00\"\n  },\n  {\n    \"file\": \"IMG_4041.jpg\",\n    \"taken\": \"2026-06-20T16:35:07\"\n  },\n  {\n    \"file\": \"IMG_4042.jpg\",\n    \"taken\": \"2026-06-20T16:35:14\"\n  },\n  {\n    \"file\": \"IMG_4043.jpg\",\n    \"taken\": \"2026-06-20T17:05:00\"\n  },\n  {\n    \"file\": \"IMG_4044.jpg\",\n    \"taken\": \"2026-06-20T17:35:00\"\n  },\n  {\n    \"file\": \"IMG_4045.jpg\",\n    \"taken\": \"2026-06-21T07:55:00\"\n  },\n  {\n    \"file\": \"IMG_4046.jpg\",\n    \"taken\": \"2026-06-21T08:20:00\"\n  },\n  {\n    \"file\": \"IMG_4047.jpg\",\n    \"taken\": \"2026-06-21T08:55:00\"\n  },\n  {\n    \"file\": \"IMG_4048.jpg\",\n    \"taken\": \"2026-06-21T08:55:09\"\n  },\n  {\n    \"file\": \"IMG_4049.jpg\",\n    \"taken\": \"2026-06-21T08:55:18\"\n  },\n  {\n    \"file\": \"IMG_4050.jpg\",\n    \"taken\": \"2026-06-21T09:30:00\"\n  },\n  {\n    \"file\": \"IMG_4051.jpg\",\n    \"taken\": \"2026-06-21T10:05:00\"\n  },\n  {\n    \"file\": \"IMG_4052.jpg\",\n    \"taken\": \"2026-06-21T10:35:00\"\n  },\n  {\n    \"file\": \"IMG_4053.jpg\",\n    \"taken\": \"2026-06-21T11:05:00\"\n  },\n  {\n    \"file\": \"IMG_4054.jpg\",\n    \"taken\": \"2026-06-21T11:30:00\"\n  },\n  {\n    \"file\": \"IMG_4055.jpg\",\n    \"taken\": \"2026-06-21T11:55:00\"\n  },\n  {\n    \"file\": \"IMG_4056.jpg\",\n    \"taken\": \"2026-06-21T12:10:00\"\n  }\n]\n"
+      },
+      {
+        "path": "photos/IMG_4003.txt",
+        "content": "CAPTION NOTE (pre-extracted from IMG_4003.jpg)\n\nArrival at the cabin - the kids racing each other down to the dock, evening light, bags still on the porch.\n"
+      },
+      {
+        "path": "photos/IMG_4012.txt",
+        "content": "CAPTION NOTE (pre-extracted from IMG_4012.jpg)\n\nGrandpa teaching knots on the dock, all four kids leaning in, Ada holding the rope wrong on purpose.\n"
+      },
+      {
+        "path": "photos/IMG_4016.txt",
+        "content": "CAPTION NOTE (pre-extracted from IMG_4016.jpg)\n\nThe cannonball mid-air - sharpest frame of the burst, water still glass beneath him.\n"
+      },
+      {
+        "path": "photos/IMG_4027.txt",
+        "content": "CAPTION NOTE (pre-extracted from IMG_4027.jpg)\n\nCampfire circle, one marshmallow properly on fire, Ada laughing with her whole face.\n"
+      },
+      {
+        "path": "photos/IMG_4033.txt",
+        "content": "CAPTION NOTE (pre-extracted from IMG_4033.jpg)\n\nSunrise over the lake from the porch, mist on the water, one empty coffee mug on the rail.\n"
+      },
+      {
+        "path": "photos/IMG_4042.txt",
+        "content": "CAPTION NOTE (pre-extracted from IMG_4042.jpg)\n\nThe big catch - Milo holding the perch at arm's length, equal parts proud and horrified.\n"
+      },
+      {
+        "path": "photos/IMG_4049.txt",
+        "content": "CAPTION NOTE (pre-extracted from IMG_4049.jpg)\n\nBoard-game afternoon on the porch while the rain came through, everyone mid-argument about the rules.\n"
+      },
+      {
+        "path": "photos/IMG_4057.txt",
+        "content": "CAPTION NOTE (pre-extracted from IMG_4057.jpg)\n\nPacking the car Sunday - everyone sunburned, half asleep, nobody wanting to say it's over.\n"
+      }
+    ],
+    "worker": {
+      "name": "Loes",
+      "role": "Curator"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "albums/lake-weekend.json is a schema-clean manifest of 10+ picks that all exist in the photo index (no invented files, bursts collapsed), each with caption and reason, and tasks/eval/report.md tells the album's arc including the cuts.",
+    "deliverables": [
+      {
+        "path": "albums/lake-weekend.json",
+        "kind": "json",
+        "minBytes": 400,
+        "checks": [
+          {
+            "kind": "recordSchema",
+            "file": "albums/lake-weekend.json",
+            "fields": [
+              {
+                "name": "file",
+                "type": "nonempty"
+              },
+              {
+                "name": "caption",
+                "type": "nonempty"
+              },
+              {
+                "name": "reason",
+                "type": "nonempty"
+              }
+            ],
+            "minRows": 10
+          },
+          {
+            "kind": "valuesSubsetOf",
+            "file": "albums/lake-weekend.json",
+            "sourceFiles": [
+              "photos/index.json"
+            ],
+            "pattern": "(IMG_\\d{4}\\.jpg)",
+            "flags": "gi",
+            "minMatches": 10
+          }
+        ]
+      },
+      {
+        "path": "tasks/eval/report.md",
+        "kind": "markdown-report",
+        "minBytes": 500,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "dupl|near-dup|burst|similar",
+            "flags": "i",
+            "label": "the cull is explained — bursts and near-duplicates named"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "tasks/eval/report.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "curation",
+        "description": "The picks are the frames that carry the weekend — the caption-noted standouts are in, filler is out, and the count respects the asked size."
+      },
+      {
+        "name": "dedupe",
+        "description": "Each burst cluster (photos seconds apart) contributes at most one frame, chosen for a stated reason."
+      },
+      {
+        "name": "captions",
+        "description": "Captions are warm and specific to what the frame shows, leaning on the caption notes where they exist."
+      },
+      {
+        "name": "story-arc",
+        "description": "The pick order and the report's arc read as the weekend start to end — arrival to packing the car."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "no invented photos",
+    "burst dedupe",
+    "honest reasons per pick"
+  ]
+}

package/data/craftbook-templates/al/alert-rules/versions/1.0.2/test.json

@@ -19,9 +19,6 @@
     "worker": {
       "name": "Aafke",
       "role": "SRE"
-    },
-    "craftbookParams": {
-      "workPath": "tasks/eval"
     }
   },
   "mocks": [],

package/data/craftbook-templates/al/alert-rules/versions/1.0.3/craftbook.json

@@ -0,0 +1,213 @@
+{
+  "id": "alert-rules",
+  "name": "Monitoring Alert Rules",
+  "description": "Author a set of monitoring/alerting rules as a deployable config (Prometheus alerting rules, Grafana/Alertmanager YAML, or a CloudWatch-style spec): the right signals, thresholds, severities, for-durations, and routing labels. Scopes the SLOs and alert philosophy FIRST (what to alert on, symptom-vs-cause, thresholds and burn windows, severity ladder, noise budget), then a developer writes the rules config to that spec, then a reviewer validates for completeness, dedupe, and anti-flapping. Scoping thresholds and severities before writing YAML is what produces actionable, low-noise alerts instead of a wall of CPU-over-80% pages. Use for alerting rules, Prometheus alerts, SLO monitoring, on-call paging rules, and reducing alert fatigue.\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 alerts (planner) — lock signals, thresholds, severities, and routing → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Build the rules (developer) — write the alerting-rules config to the locked spec → gated on `alerts.yaml` (yaml-spec)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "scope",
+  "triggers": [
+    "write alert rules",
+    "prometheus alerts",
+    "monitoring rules",
+    "set up alerting",
+    "SLO alerts"
+  ],
+  "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 alerts",
+      "description": "lock signals, thresholds, severities, and routing",
+      "prompt": "Define the alerting philosophy before writing config. (1) List the services/SLOs to cover and, for each, the symptom-level signals that matter (latency p99, error rate, saturation, availability) — prefer alerting on user-facing symptoms over raw causes. (2) For every signal lock a threshold, an evaluation/for-duration (to suppress transient spikes), and a severity from a fixed ladder (page = wake someone, ticket = next business day, info = dashboard-only). (3) Define routing labels (team/service/severity) and which severities page. (4) State a noise budget (e.g. no more than N page-level rules) and require a runbook link annotation on every page-level alert. (5) Pick the output format (Prometheus alerting-rules YAML by default). Write an acceptance-criteria checklist ('every SLO has at least one symptom alert', 'every alert has expr + for + severity + summary + runbook annotation', 'no duplicate/overlapping alerts', 'page-level alerts within the noise budget', 'config is valid YAML for the target system') plus the table of signals/thresholds to {{workPath}}/scope.md via write_task_note AND the produces path. No YAML 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": "build",
+      "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": "build",
+      "name": "Build the rules",
+      "description": "write the alerting-rules config to the locked spec",
+      "prompt": "Write alerts.yaml as a valid alerting-rules config for the target system using the locked signals. For EACH alert author: a clear alert name, the metric expression (expr) implementing the threshold, a for: duration (non-zero, to suppress flapping), labels (severity + routing), and annotations (a one-line summary with templated context, a description, and a runbook_url for page-level alerts). Group related alerts. Keep thresholds and for-durations exactly as scoped. Ensure the file parses as YAML and matches the target's schema (e.g. groups[].rules[].alert/expr/for/labels/annotations for Prometheus). Cover every scoped SLO with at least one symptom-level alert, add no alerts that weren't scoped, avoid duplicate/overlapping rules, and do not exceed the page-level noise budget. On a loop-back fix only the flagged rules. Write the path and an alert count (by severity) to notes via write_task_note.",
+      "suggestedRole": "developer",
+      "advanceWhen": {
+        "file": "alerts.yaml",
+        "minBytes": 1,
+        "sniff": "nonempty"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "alerts.yaml",
+            "bytes": 200
+          },
+          {
+            "kind": "sniff",
+            "file": "alerts.yaml",
+            "sniff": "nonempty"
+          }
+        ],
+        "onReject": "build",
+        "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": "Validate alerts.yaml against every locked criterion. (1) Parse the YAML — invalid YAML or non-conformance to the target system's rule schema (e.g. groups[].rules[]) is an immediate FAIL. (2) Confirm every scoped SLO is covered by at least one symptom-level alert; FAIL on any missing SLO. (3) Check each alert carries expr, a non-zero for: duration, a severity from the ladder, routing labels, a summary, and — for page-level alerts — a runbook_url annotation. (4) Scan for duplicate or overlapping rules (two firing on the same condition) and flag them. (5) Confirm page-level alerts stay within the noise budget, and sanity-check 2-3 thresholds and for-durations against the scope. Write PASS/FAIL per criterion with the specific offending rule names.\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: \"build\" })` 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": "alerts.yaml"
+        }
+      ],
+      "next": "build",
+      "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"
+}