@bendyline/gilde 0.2.5 → 0.2.6

package/data/craftbook-templates/ic/icon-pack/versions/1.0.5/test.json

@@ -0,0 +1,94 @@
+{
+  "schemaVersion": 1,
+  "mode": "workflow",
+  "title": "Coherent Icon Pack workflow processability",
+  "objective": "Prove that a medium local model can parse and execute the Coherent Icon Pack craftbook, satisfy its declared runtime gates, and reach a terminal step using only local fixtures.",
+  "tags": [
+    "media"
+  ],
+  "prompt": "Use the `icon-pack` (Coherent Icon Pack) craftbook for this self-contained local evaluation. Open `source/craftbook-eval-brief.md` first, then follow the craftbook's actual steps and gates through its terminal step. Complete this request: Produce a coherent set of UI icons that look like they belong to one family — consistent grid, stroke weight, corner radius, optical sizing, and metaphor language — from a named list of concepts. Lock the style system (grid, stroke, padding, keyline shapes) BEFORE drawing any icon, because icon-set quality is almost entirely about consistency: a pack of individually-nice icons with mismatched strokes looks broken. Then generate every icon to the system and assemble a previewable sheet. Covers icon sets, UI icons, SVG icon libraries, glyph packs, and design systems.\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. Style scope (visual-designer) — lock grid, stroke, radius, padding, and the icon list → gated on artifact `{{workPath}}/style-scope.md` (markdown-notes)\n2. Generate icons (image-generator) — draw every icon to the locked system → gated on `assets` (image-set)\n3. Assemble the sheet (developer) — preview grid + usage snippet → 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 Produce `style-scope.md` in this task's artifact working folder, `assets`, `index.html`. Use only seeded project files and installed local simulators. Do not call a real external service, fetch live data, or claim an external side effect occurred; an explicit dry-run record is the correct result when a dependency is unavailable.",
+  "setup": {
+    "projectName": "Coherent Icon Pack Workflow Eval",
+    "about": "A hermetic workflow evaluation for the Coherent Icon Pack craftbook. No live dependency or external network is authorized.",
+    "missionObjectives": "Run the Coherent Icon Pack craftbook end to end, use the local evaluation brief and fixtures as truth, produce its declared outputs, and reach a terminal step without fabricating external effects.",
+    "managedWorkspaceWritePolicy": "allow",
+    "files": [
+      {
+        "path": "source/craftbook-eval-brief.md",
+        "content": "# Coherent Icon Pack — local evaluation brief\n\nThis is a hermetic processability evaluation of the `icon-pack` craftbook.\nDo not contact real services, use real credentials, or fetch live data. Treat\nthe project fixtures and installed local simulators as authoritative. If a\ndependency is intentionally unavailable, document an honest dry run instead\nof claiming a real side effect.\n\n## Request\n\nProduce a coherent set of UI icons that look like they belong to one family — consistent grid, stroke weight, corner radius, optical sizing, and metaphor language — from a named list of concepts. Lock the style system (grid, stroke, padding, keyline shapes) BEFORE drawing any icon, because icon-set quality is almost entirely about consistency: a pack of individually-nice icons with mismatched strokes looks broken. Then generate every icon to the system and assemble a previewable sheet. Covers icon sets, UI icons, SVG icon libraries, glyph packs, and design systems.\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. Style scope (visual-designer) — lock grid, stroke, radius, padding, and the icon list → gated on artifact `{{workPath}}/style-scope.md` (markdown-notes)\n2. Generate icons (image-generator) — draw every icon to the locked system → gated on `assets` (image-set)\n3. Assemble the sheet (developer) — preview grid + usage snippet → 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\n\n## Required workflow\n\n1. Style scope\n2. Generate icons\n3. Assemble the sheet\n4. Evaluate\n5. Finish (terminal)\n\n## Declared outputs\n\n- `style-scope.md` in this task's artifact working folder\n- `assets`\n- `index.html`\n"
+      },
+      {
+        "path": "source/brief.md",
+        "content": "# Coherent Icon Pack 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: icon-pack - Coherent Icon Pack.\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": "Craftbook Runner",
+      "role": "Workflow Operator",
+      "about": "Execute the assigned craftbook exactly. Read local fixtures, satisfy each runtime gate, record honest dry-run evidence for unavailable dependencies, and continue until a terminal step is active or the task is complete."
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "The attributed icon-pack task satisfied its own gates, produced its declared outputs, and reached a terminal step without using external services.",
+    "deliverables": [
+      {
+        "path": "{{task.dir}}/style-scope.md",
+        "kind": "markdown-report",
+        "artifact": true,
+        "minBytes": 120
+      },
+      {
+        "path": "assets",
+        "kind": "generic-file",
+        "minBytes": 1
+      },
+      {
+        "path": "index.html",
+        "kind": "html-page",
+        "minBytes": 800
+      }
+    ],
+    "taskGraph": {
+      "requireCraftbookTask": true,
+      "requireTerminalStep": true
+    }
+  },
+  "rubric": {
+    "artifact": {
+      "path": "{{task.dir}}/style-scope.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "workflow fidelity",
+        "description": "The result reflects the named craftbook sequence and its declared acceptance gates rather than a freehand substitute."
+      },
+      {
+        "name": "usefulness",
+        "description": "The deliverable is coherent, actionable, and suitable for the craftbook purpose stated in the local brief."
+      }
+    ],
+    "contextNote": "Advisory only. Deterministic pass/fail comes from the craftbook runtime gates, deliverable existence, attribution, and terminal progress."
+  },
+  "qualityFocus": [
+    "real icon-pack craftbook task attribution",
+    "declared runtime gate satisfaction",
+    "terminal workflow progress",
+    "offline fixture and simulator discipline"
+  ],
+  "extensions": {
+    "legacySimulators": [
+      {
+        "id": "icon-pack-media-fixtures",
+        "kind": "data-source",
+        "status": "implemented",
+        "description": "Seeded local media index replacing real audio, video, image generation, and external media metadata services."
+      }
+    ]
+  }
+}