@bendyline/gilde 0.1.50 → 0.1.52

package/data/craftbook-templates/mo/monthly-recording-review/versions/1.0.3/test.json

@@ -0,0 +1,120 @@
+{
+  "schemaVersion": 1,
+  "title": "Monthly Recording Review — July",
+  "objective": "Measure whether the monthly-recording-review craftbook assesses every recording in the index against last month's marks and lands on exactly one next-month focus.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "end of the month — can you go thru the recordings index and my notes and write the review? tasks/eval/report.md please",
+  "setup": {
+    "projectName": "Piano Practice",
+    "about": "Music practice project. Monthly practice recordings are indexed in workspace/recordings/index.json with a listening-notes file per recording; past monthly reviews live under workspace/reviews.",
+    "missionObjectives": "Once a month, review the recordings against last month's marks — proof over impression — and pick one focus for next month. Grounded in the seeded index and notes; no live services, no real credentials.",
+    "files": [
+      {
+        "path": "recordings/index.json",
+        "content": "[\n  {\n    \"file\": \"2026-07-05-nocturne.mp3\",\n    \"date\": \"2026-07-05\",\n    \"piece\": \"Chopin Nocturne Op. 9 No. 2\",\n    \"tasks/eval\": \"recordings/2026-07-05-nocturne.notes.md\"\n  },\n  {\n    \"file\": \"2026-07-12-nocturne.mp3\",\n    \"date\": \"2026-07-12\",\n    \"piece\": \"Chopin Nocturne Op. 9 No. 2\",\n    \"tasks/eval\": \"recordings/2026-07-12-nocturne.notes.md\"\n  },\n  {\n    \"file\": \"2026-07-19-bach-invention.mp3\",\n    \"date\": \"2026-07-19\",\n    \"piece\": \"Bach Invention No. 8\",\n    \"tasks/eval\": \"recordings/2026-07-19-bach-invention.notes.md\"\n  },\n  {\n    \"file\": \"2026-07-26-nocturne-full.mp3\",\n    \"date\": \"2026-07-26\",\n    \"piece\": \"Chopin Nocturne Op. 9 No. 2 (full run-through)\",\n    \"tasks/eval\": \"recordings/2026-07-26-nocturne-full.notes.md\"\n  }\n]\n"
+      },
+      {
+        "path": "recordings/2026-07-05-nocturne.notes.md",
+        "content": "# Listening notes — 2026-07-05 nocturne\n\nTempo 88 bpm. Left hand steadier than June — the arpeggios no longer bulge on beat three. Bar 12 ornaments still uneven, rushed on the second turn. Pedal is cleaner in the opening eight bars. Bar 32 run attempted at tempo: fell apart, restarted.\n"
+      },
+      {
+        "path": "recordings/2026-07-12-nocturne.notes.md",
+        "content": "# Listening notes — 2026-07-12 nocturne\n\nTempo 92 bpm. Bar 32 run holds at 85 in isolation but breaks in context. Dynamics are starting to appear — the first real crescendo shaping in bars 17-24. Ending chord voicing much better than the June recordings.\n"
+      },
+      {
+        "path": "recordings/2026-07-19-bach-invention.notes.md",
+        "content": "# Listening notes — 2026-07-19 bach invention\n\nFirst hands-together recording. 66 bpm, down from the 72 achieved hands-separate — expected. Evenness between the hands is good for a first attempt. Ornaments omitted for now. No memory slips.\n"
+      },
+      {
+        "path": "recordings/2026-07-26-nocturne-full.notes.md",
+        "content": "# Listening notes — 2026-07-26 nocturne full run-through\n\nFirst complete run-through ever recorded. 90 bpm working tempo. One stumble at bar 32 (recovered without stopping — new). Rubato in the middle section sounds intentional for the first time. The June recordings had no complete take at all.\n"
+      },
+      {
+        "path": "reviews/2026-06.md",
+        "content": "# Monthly review — June 2026\n\n## Marks\n\n- Chopin Nocturne Op. 9 No. 2 — 84 bpm working tempo, no complete take; left hand bulges on beat three; bar 32 run avoided entirely.\n- Bach Invention No. 8 — hands separate only, 72 bpm.\n\n## Focus for July\n\nOne focus: left-hand evenness in the nocturne. Everything else is secondary.\n"
+      }
+    ],
+    "worker": {
+      "name": "Iris",
+      "role": "Coach"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "tasks/eval/report.md assesses every indexed recording with concrete evidence, states deltas against the June review, gives a verdict on June's focus, and names exactly one focus for August.",
+    "deliverables": [
+      {
+        "path": "tasks/eval/report.md",
+        "kind": "markdown-report",
+        "minBytes": 1000,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "valuesSubsetOf",
+            "file": "tasks/eval/report.md",
+            "sourceFiles": [
+              "recordings/index.json"
+            ],
+            "pattern": "(\\d{4}-\\d{2}-\\d{2}-[a-z-]+\\.mp3)",
+            "flags": "i",
+            "minMatches": 2,
+            "label": "recordings referenced by their real filenames"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "focus",
+            "flags": "i",
+            "label": "next-month focus named"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "better|steadier|cleaner|slower|improved|regressed",
+            "flags": "i",
+            "label": "delta language versus last month"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "tasks/eval/report.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "honesty",
+        "description": "Progress and regressions are both stated plainly — no flattery, no doom."
+      },
+      {
+        "name": "specificity",
+        "description": "Observations name passages, tempos, and habits a teacher would point at — never a bare 'sounds better'."
+      },
+      {
+        "name": "comparison rigor",
+        "description": "Every piece gets a delta against the June marks, and June's focus (left-hand evenness) gets an explicit verdict."
+      },
+      {
+        "name": "encouragement",
+        "description": "The review makes the player want to practice tomorrow, and lands on exactly one focus for next month."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "evidence over impression",
+    "month-over-month deltas",
+    "single focus"
+  ]
+}

package/data/craftbook-templates/mo/moodboard/versions/1.0.2/test.json

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

package/data/craftbook-templates/mo/moodboard/versions/1.0.3/craftbook.json

@@ -0,0 +1,221 @@
+{
+  "id": "moodboard",
+  "name": "Visual Moodboard",
+  "description": "Compose a visual moodboard that captures a direction — palette, textures, type vibe, imagery, and reference tiles — from a written brief, so a team can align on a look before any production work begins. Lock the brief and the explicit dimensions of the mood (e.g. 'warm/editorial/handmade' vs 'cool/technical/precise') FIRST, then assemble a coherent grid of generated or sourced tiles plus a swatch strip and keyword callouts. Covers moodboards, style boards, visual direction, design inspiration, brand mood, and look-and-feel exploration.\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. Moodboard brief (visual-designer) — lock the mood dimensions, palette, and tile plan → gated on artifact `{{workPath}}/brief.md` (markdown-notes)\n2. Assemble the board (image-generator) — compose the coherent tile grid into one deliverable → gated on `index.html` (html-page)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "brief",
+  "triggers": [
+    "make a moodboard",
+    "create a style board",
+    "visual direction board",
+    "design inspiration board",
+    "look and feel board"
+  ],
+  "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": "brief",
+      "name": "Moodboard brief",
+      "description": "lock the mood dimensions, palette, and tile plan",
+      "prompt": "1) Distill the direction into 3-5 mood keywords (e.g. warm, editorial, handmade, calm). 2) Lock a palette with hex swatches and the type vibe (serif/sans, weight, feeling). 3) Plan the tile grid: enumerate the tiles you'll include — e.g. 2-3 imagery tiles, a texture tile, a typography specimen tile, a palette strip — and what each should evoke. 4) Note explicit anti-references (what this is NOT) so the board has a point of view. 5) Write an acceptance-criteria checklist: 'board expresses the 3-5 keywords', 'palette swatches show exact hex', 'a typography specimen is present', 'tiles are cohesive (one direction, not a scrapbook)', 'at least 6 tiles'. 6) Record brief + checklist via write_task_note AND to {{workPath}}/brief.md. No assembly yet.\n\nThe deliverable `{{workPath}}/brief.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": "visual-designer",
+      "advanceWhen": {
+        "file": "{{workPath}}/brief.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/brief.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/brief.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "brief",
+        "maxAttempts": 3
+      },
+      "next": "assemble",
+      "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": "assemble",
+      "name": "Assemble the board",
+      "description": "compose the coherent tile grid into one deliverable",
+      "prompt": "1) Read brief.md. 2) Generate or compose each planned tile to express the locked keywords and palette — imagery tiles via the image-generation capability (or curated solid/gradient/texture blocks if no image model is available), a swatch strip rendering the exact hex values, and a type specimen tile showing the chosen pairing with sample words. 3) Assemble everything into ONE deliverable: a single index.html grid (preferred — easy to render and tweak) laying out at least 6 cohesive tiles with the keyword list as a caption. 4) Keep the direction tight: every tile should feel like the same world. 5) Reference any generated files from assets/ if produced. 6) write_task_note the board path and tile count. Good looks like: someone could brief a designer from this board alone.",
+      "suggestedRole": "image-generator",
+      "advanceWhen": {
+        "file": "index.html",
+        "minBytes": 1,
+        "sniff": "html-complete"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "index.html",
+            "bytes": 800
+          },
+          {
+            "kind": "htmlLint",
+            "file": "index.html"
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkHtmlComplete",
+            "scope": "standard",
+            "inputs": {
+              "file": "index.html"
+            }
+          }
+        ],
+        "onReject": "assemble",
+        "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": "1) Open index.html and confirm it renders a grid of at least 6 tiles (PASS/FAIL). 2) Check it expresses the 3-5 mood keywords from brief.md — is the direction legible and cohesive, not a random scrapbook (PASS/FAIL)? 3) Confirm a palette swatch strip shows the exact hex values and a typography specimen is present. 4) Verify any referenced image files actually load. 5) Write PASS/FAIL per criterion. Incoherent/off-brief → loop back to assemble.\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: \"assemble\" })` 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": "index.html"
+        }
+      ],
+      "next": "assemble",
+      "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/mo/moodboard/versions/1.0.3/test.json

@@ -0,0 +1,103 @@
+{
+  "schemaVersion": 1,
+  "title": "Visual Moodboard smoke eval",
+  "objective": "Self-contained smoke eval for the Visual Moodboard 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": "Visual Moodboard Eval",
+    "about": "Self-contained eval project for moodboard. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/media-plan.json.",
+    "missionObjectives": "Use the Visual Moodboard 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": "# Visual Moodboard 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: moodboard - Visual Moodboard.\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": "moodboard-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/mo/morning-brief/versions/1.0.2/test.json

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