@bendyline/gilde 0.1.50 → 0.1.52

package/data/craftbook-templates/fe/feedback-widget/versions/1.0.3/craftbook.json

@@ -0,0 +1,281 @@
+{
+  "id": "feedback-widget",
+  "name": "Embeddable Feedback Widget",
+  "description": "Build a single-file embeddable feedback, contact, or rating widget — a floating button that opens a small panel with a rating, a message field, and validation, then shows a thank-you state and persists submissions to localStorage. Scopes the fields, validation, and submission behavior first, designs the floating launcher and panel, then implements an accessible, self-contained widget that drops into any page. Feedback widgets fail when submit does nothing, validation is missing, or the panel cannot be closed, so the scope phase locks the field set and the submit-and-thank-you flow before any markup.\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 (planner) — fields, validation, submit + thank-you behavior → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Design (designer) — launcher button, panel layout, states → gated on artifact `{{workPath}}/design.md` (markdown-notes)\n3. Build (developer) — implement the widget in index.html → 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": "scope",
+  "triggers": [
+    "feedback widget",
+    "contact widget",
+    "rating widget",
+    "feedback form",
+    "embeddable form",
+    "support widget"
+  ],
+  "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",
+      "description": "fields, validation, submit + thank-you behavior",
+      "prompt": "Scope the widget. (1) Define the fields: a rating (e.g. 1-5 stars or emoji), a message textarea, and an optional email — with which are required. (2) Specify validation and the inline error messages. (3) Define the launcher (a floating button) and the panel open/close behavior (and Escape/overlay-click to close). (4) Define submission: on valid submit, store the entry in localStorage and show a thank-you state with a reset/close. (5) Write an acceptance-criteria checklist of 6-8 items, e.g. 'a floating button toggles the panel open and closed', 'the panel can be dismissed', 'required fields block submit with an inline error', 'a valid submit shows a thank-you state', 'the submission persists to localStorage', 'the widget is keyboard-accessible (focus, Escape)', 'no console errors'. Write to {{workPath}}/scope.md and via write_task_note. No design or HTML 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": "design",
+      "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": "design",
+      "name": "Design",
+      "description": "launcher button, panel layout, states",
+      "prompt": "Design the widget UI. (1) Pick a palette (hex) and a fixed-position floating launcher (corner button with an icon/label). (2) Lay out the panel: heading, rating control, message field, optional email, and submit button. (3) Design the states: closed, open, validation-error, submitting, and thank-you. (4) Specify focus styles and that it overlays page content without breaking it (high z-index, contained styles). (5) Self-contained CSS, responsive. Write the visual spec to {{workPath}}/design.md and via write_task_note. No HTML yet.\n\nThe deliverable `{{workPath}}/design.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": "designer",
+      "advanceWhen": {
+        "file": "{{workPath}}/design.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/design.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/design.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "design",
+        "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",
+      "description": "implement the widget in index.html",
+      "prompt": "Implement the widget in index.html (inline CSS + JS) to the scope and design, dropped onto a minimal demo page. (1) Render the floating launcher; clicking it toggles the panel open/closed, and Escape or an overlay click closes it. (2) Build the rating control, message textarea, and optional email with the specified validation; block submit and show inline errors when invalid. (3) On valid submit, push the entry (with a timestamp) to a localStorage array and switch to the thank-you state with a reset/close. (4) Manage focus for accessibility (focus the panel on open, restore on close). (5) Keep styles contained (scoped class names, high z-index). Vanilla JS, no CDN. On a loop-back, fix only the named gaps without regressing passing criteria. write_task_note the path and passing criteria.",
+      "suggestedRole": "developer",
+      "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": "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": "Exercise the widget. Open index.html if possible: open and close the panel (button, Escape, overlay), try to submit empty, then submit a valid entry, and RELOAD to confirm persistence. Check EACH criterion from {{workPath}}/scope.md and write PASS/FAIL with a reason: does the floating button toggle the panel, can it be dismissed, do required fields block submit with an inline error, does a valid submit show the thank-you state, does the submission persist to localStorage across reload, is it keyboard-accessible (focus + Escape), zero console errors? A submit that does nothing, or a panel that will not close, is a FAIL — loop back to build.\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": "index.html"
+        }
+      ],
+      "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"
+}

package/data/craftbook-templates/fe/feedback-widget/versions/1.0.3/test.json

@@ -0,0 +1,97 @@
+{
+  "schemaVersion": 1,
+  "title": "Embeddable Feedback Widget smoke eval",
+  "objective": "Self-contained smoke eval for the Embeddable Feedback Widget craftbook using the html-page generic harness.",
+  "tags": [
+    "html-page"
+  ],
+  "prompt": "Can you biuld us a little page for this? The content notes are in source/page-content.md. Save it as index.html — one file, nothing fancy needed on our end.",
+  "setup": {
+    "projectName": "Embeddable Feedback Widget Eval",
+    "about": "Self-contained eval project for feedback-widget. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/index.html.",
+    "missionObjectives": "Use the Embeddable Feedback Widget craftbook/template, read the seeded local fixtures, and write index.html without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Embeddable Feedback Widget 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: feedback-widget - Embeddable Feedback Widget.\n"
+      },
+      {
+        "path": "source/page-content.md",
+        "content": "# Boreal Desk Support Board\n\nBuild content around a support operations board. Required labels: Open issues, Status silence, Response time, Refund leakage, Next action. Required metric text: 18 hours to 6 hours and 14.2% to 8.9%.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Developer"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "index.html is a source-grounded self-contained HTML page/tool.",
+    "deliverables": [
+      {
+        "path": "index.html",
+        "kind": "html-page",
+        "minBytes": 3000,
+        "checks": [
+          {
+            "kind": "cssMinBytes",
+            "bytes": 650,
+            "file": "index.html"
+          },
+          {
+            "kind": "jsParses",
+            "file": "index.html"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "Boreal|Support Board|returns",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "18\\s*hours|6\\s*hours|14\\.2%|8\\.9%",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "button|input|filter|tab|card|section|nav",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "index.html",
+      "kind": "html"
+    },
+    "axes": [
+      {
+        "name": "structure",
+        "description": "Layout and hierarchy fit the content; sections are scannable and coherent."
+      },
+      {
+        "name": "grounding",
+        "description": "Seeded source content is used faithfully — no invented facts or dropped requirements."
+      },
+      {
+        "name": "interactivity",
+        "description": "Controls and states the page claims to offer actually work."
+      },
+      {
+        "name": "polish",
+        "description": "Styling is intentional and responsive rather than unstyled or broken."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "self-contained UI",
+    "source grounding",
+    "responsive structure"
+  ]
+}

package/data/craftbook-templates/fl/flaky-test-fix/versions/1.0.0/test.json

@@ -38,7 +38,6 @@
       }
     ],
     "craftbookParams": {
-      "workPath": "tasks/eval",
       "scope": "The test 'a fresh session starts with no flags enabled' in tests/flags.test.mjs fails whenever the whole suite runs and passes by itself; see source/flake-report.md. Make the suite deterministic without weakening that test."
     }
   },
@@ -47,83 +46,83 @@
     "summary": "The order-dependence mechanism is removed with hygiene that covers every test, the pristine-session assertion survives unweakened, five consecutive suite runs are green, a late-appended probe still sees a pristine session, and restoring the original test file makes the suite fail again.",
     "deliverables": [
       {
-        "path": "tasks/eval/flake-evidence.md",
+        "path": "{{task.dir}}/flake-evidence.md",
         "kind": "markdown-notes",
         "artifact": true,
         "minBytes": 500,
         "checks": [
           {
             "kind": "contains",
-            "file": "tasks/eval/flake-evidence.md",
+            "file": "{{task.dir}}/flake-evidence.md",
             "pattern": "^##\\s+Symptom[\\s\\S]*^##\\s+Runs observed[\\s\\S]*^##\\s+Failure signature[\\s\\S]*^##\\s+Suspected class",
             "flags": "im",
             "label": "flake-evidence sections in order"
           },
           {
             "kind": "citationsResolve",
-            "file": "tasks/eval/flake-evidence.md",
+            "file": "{{task.dir}}/flake-evidence.md",
             "minCitations": 2,
             "artifact": true
           }
         ]
       },
       {
-        "path": "tasks/eval/diagnosis.md",
+        "path": "{{task.dir}}/diagnosis.md",
         "kind": "markdown-notes",
         "artifact": true,
         "minBytes": 600,
         "checks": [
           {
             "kind": "contains",
-            "file": "tasks/eval/diagnosis.md",
+            "file": "{{task.dir}}/diagnosis.md",
             "pattern": "^##\\s+Mechanism[\\s\\S]*^##\\s+Experiment[\\s\\S]*^##\\s+Defect site[\\s\\S]*^##\\s+Siblings checked",
             "flags": "im",
             "label": "diagnosis sections in order"
           },
           {
             "kind": "contains",
-            "file": "tasks/eval/diagnosis.md",
+            "file": "{{task.dir}}/diagnosis.md",
             "pattern": "tests/flags\\.test\\.mjs|src/flags\\.js",
             "label": "names the real site of the shared-state hazard"
           },
           {
             "kind": "citationsResolve",
-            "file": "tasks/eval/diagnosis.md",
+            "file": "{{task.dir}}/diagnosis.md",
             "minCitations": 2,
             "artifact": true
           }
         ]
       },
       {
-        "path": "tasks/eval/fix-notes.md",
+        "path": "{{task.dir}}/fix-notes.md",
         "kind": "markdown-notes",
         "artifact": true,
         "minBytes": 700,
         "checks": [
           {
             "kind": "contains",
-            "file": "tasks/eval/fix-notes.md",
+            "file": "{{task.dir}}/fix-notes.md",
             "pattern": "^##\\s+Problem[\\s\\S]*^##\\s+Change[\\s\\S]*^##\\s+Files touched[\\s\\S]*^##\\s+Regression coverage[\\s\\S]*^##\\s+Risk[\\s\\S]*^##\\s+How to verify",
             "flags": "im",
             "label": "fix-notes sections in order"
           },
           {
             "kind": "citationsResolve",
-            "file": "tasks/eval/fix-notes.md",
+            "file": "{{task.dir}}/fix-notes.md",
             "minCitations": 2,
             "artifact": true
           }
         ]
       },
       {
-        "path": "tasks/eval/validation.md",
+        "path": "{{task.dir}}/validation.md",
         "kind": "markdown-notes",
         "artifact": true,
         "minBytes": 300,
         "checks": [
           {
             "kind": "contains",
-            "file": "tasks/eval/validation.md",
+            "file": "{{task.dir}}/validation.md",
             "pattern": "^##\\s+Runs[\\s\\S]*^##\\s+Result",
             "flags": "im",
             "label": "validation sections in order"
@@ -131,14 +130,14 @@
         ]
       },
       {
-        "path": "tasks/eval/review.md",
+        "path": "{{task.dir}}/review.md",
         "kind": "markdown-report",
         "artifact": true,
         "minBytes": 400,
         "checks": [
           {
             "kind": "contains",
-            "file": "tasks/eval/review.md",
+            "file": "{{task.dir}}/review.md",
             "pattern": "Verdict:\\s*(?:PASS|REVISE)",
             "flags": "i",
             "label": "explicit reviewer verdict"
@@ -214,7 +213,7 @@
   },
   "rubric": {
     "artifact": {
-      "path": "tasks/eval/fix-notes.md",
+      "path": "{{task.dir}}/fix-notes.md",
       "kind": "markdown"
     },
     "axes": [