@bendyline/gilde 0.1.26 → 0.1.28

package/data/craftbook-templates/so/source-quality-audit/versions/1.0.1/test.json

@@ -0,0 +1,158 @@
+{
+  "schemaVersion": 1,
+  "title": "Source Quality Audit smoke eval",
+  "objective": "Task-specific eval for the Source Quality Audit craftbook: five roster sources against a month of briefs in which The Daily Splash caused two corrections and Materials Weekly never appeared — the verdict table covers all five with evidence.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "the brief has felt noisy latly — can you audit the sources this month and tell me what to drop?",
+  "setup": {
+    "projectName": "Topic Watch — Source Audit Eval",
+    "about": "Self-contained eval project for source-quality-audit. The source roster is seeded at sources.json and the month's briefs sit under briefs/ as the evidence base; the deliverable is report.md with the verdict table.",
+    "missionObjectives": "Use the Source Quality Audit craftbook/template, score every roster source against the month's briefs only, and write report.md. No live feeds, services, or outside data — the seeded briefs are the whole record.",
+    "files": [
+      {
+        "path": "sources.json",
+        "content": "[\n  {\n    \"id\": \"newsline\",\n    \"name\": \"Newsline\",\n    \"kind\": \"regional news\",\n    \"added\": \"2026-01-12\"\n  },\n  {\n    \"id\": \"capitol-wire\",\n    \"name\": \"Capitol Wire\",\n    \"kind\": \"state policy wire\",\n    \"added\": \"2026-02-03\"\n  },\n  {\n    \"id\": \"harbor-bulletin\",\n    \"name\": \"Harbor Bulletin\",\n    \"kind\": \"local bulletin\",\n    \"added\": \"2026-03-20\"\n  },\n  {\n    \"id\": \"daily-splash\",\n    \"name\": \"The Daily Splash\",\n    \"kind\": \"aggregator\",\n    \"added\": \"2026-05-08\"\n  },\n  {\n    \"id\": \"materials-weekly\",\n    \"name\": \"Materials Weekly\",\n    \"kind\": \"trade journal\",\n    \"added\": \"2026-04-14\"\n  }\n]\n"
+      },
+      {
+        "path": "briefs/2026-06-05.md",
+        "content": "# Morning brief - 2026-06-05\n\n## Municipal Broadband\n- Council schedules the broadband vote for July. (Newsline)\n- The Daily Splash claims the depot fiber build cut program costs 40%. (The Daily Splash)\n\n## Battery Recycling\n- Spring collection pilot wraps with volumes above plan. (Harbor Bulletin)\n"
+      },
+      {
+        "path": "briefs/2026-06-12.md",
+        "content": "# Morning brief - 2026-06-12\n\n## Municipal Broadband\n- Correction: the 40% cost figure The Daily Splash ran last week was wrong - the county puts the saving at 14%. (Harbor Bulletin)\n- State fiber office publishes the pilot application checklist. (Capitol Wire)\n\n## Battery Recycling\n- Port recycler files for the second-life pack permit. (Harbor Bulletin)\n"
+      },
+      {
+        "path": "briefs/2026-06-19.md",
+        "content": "# Morning brief - 2026-06-19\n\n## Municipal Broadband\n- Newsline breaks the story: the cost study's consultant missed two substations, delaying the vote. (Newsline)\n- The Daily Splash reported the Westport plant had closed; the plant says otherwise - treating as retracted. (The Daily Splash)\n\n## Battery Recycling\n- Fire marshal opens comment period on depot storage rules. (Capitol Wire)\n"
+      },
+      {
+        "path": "briefs/2026-06-26.md",
+        "content": "# Morning brief - 2026-06-26\n\n## Municipal Broadband\n- Council staff confirm the revised cost study lands mid-July. (Newsline)\n\n## Battery Recycling\n- Weekend depots extend hours for the summer. (Harbor Bulletin)\n- The Daily Splash runs six items on a viral battery-fire video; none add facts beyond the original report. (The Daily Splash)\n"
+      }
+    ],
+    "worker": {
+      "name": "Isa",
+      "role": "Editor"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "report.md carries a verdict table covering all five roster sources, verdicts from the fixed set with cited evidence: The Daily Splash's corrections and Materials Weekly's silence both show up in their rows.",
+    "deliverables": [
+      {
+        "path": "report.md",
+        "kind": "markdown-report",
+        "minBytes": 900,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "tableShape",
+            "file": "report.md",
+            "requiredColumns": [
+              "Source",
+              "Verdict"
+            ],
+            "minRows": 5
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "keep",
+            "flags": "i",
+            "label": "verdicts use the fixed set — keep"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "drop",
+            "flags": "i",
+            "label": "verdicts use the fixed set — drop"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "Newsline",
+            "flags": "i",
+            "label": "every roster source covered — Newsline"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "Capitol Wire",
+            "flags": "i",
+            "label": "every roster source covered — Capitol Wire"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "Harbor Bulletin",
+            "flags": "i",
+            "label": "every roster source covered — Harbor Bulletin"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "Daily Splash",
+            "flags": "i",
+            "label": "every roster source covered — The Daily Splash"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "Materials Weekly",
+            "flags": "i",
+            "label": "every roster source covered — Materials Weekly"
+          },
+          {
+            "kind": "judge",
+            "file": "report.md",
+            "rubric": "Every verdict cites at least one concrete example from the month's briefs or explicitly notes the source went unused. The Daily Splash's repeated corrections and Materials Weekly's total silence are both reflected in their verdicts.",
+            "sourceFiles": [
+              "briefs/2026-06-05.md",
+              "briefs/2026-06-12.md",
+              "briefs/2026-06-19.md",
+              "briefs/2026-06-26.md"
+            ],
+            "label": "verdicts earn their evidence"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "report.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "evidence",
+        "description": "Every verdict is backed by concrete examples from the briefs — items delivered, corrections caused, or documented silence."
+      },
+      {
+        "name": "fairness",
+        "description": "Sources are judged on the record, not vibes; a noisy source's genuine contributions still count."
+      },
+      {
+        "name": "decisiveness",
+        "description": "Verdicts come from the fixed set (keep, demote, drop) and the closing changes list matches them."
+      },
+      {
+        "name": "hygiene",
+        "description": "The report notes what dropping a source leaves uncovered and what might fill the gap."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "evidence-backed verdicts",
+    "full roster coverage",
+    "actionable changes"
+  ]
+}

package/data/craftbook-templates/sp/spa-dashboard/versions/1.0.1/craftbook.json

@@ -0,0 +1,143 @@
+{
+  "id": "spa-dashboard",
+  "name": "Metrics / Admin Dashboard",
+  "description": "Build a single-page metrics or admin dashboard with KPI summary cards, at least one chart, and a data table, rendered from sample or provided data. Locks the data model and which metrics matter first, then a scannable dashboard layout (grid of cards, chart placement, table), then builds the interactive HTML with a lightweight charting approach and a sortable/filterable table. Deciding the metrics and layout before coding prevents a small model from dumping raw data with no hierarchy; a dashboard's value is the at-a-glance summary up top.\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. Data scope (planner) — data model + which KPIs and views matter → gated on artifact `notes/data-scope.md` (markdown-notes)\n2. Layout design (designer) — card grid, chart placement, table, hierarchy → gated on artifact `notes/layout-design.md` (markdown-notes)\n3. Build (developer) — implement index.html with cards, chart, table → 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": "data-scope",
+  "triggers": [
+    "admin dashboard",
+    "metrics dashboard",
+    "analytics page",
+    "kpi dashboard",
+    "build a dashboard",
+    "data dashboard"
+  ],
+  "steps": [
+    {
+      "id": "data-scope",
+      "name": "Data scope",
+      "description": "data model + which KPIs and views matter",
+      "prompt": "Scope the data and the views. (1) Define the data shape: the records/rows and their fields (use provided data, or generate a realistic sample array embedded in the page). (2) Pick the 3-5 headline KPIs to show as summary cards and how each is computed. (3) Choose at least one chart (what it plots) and the table's columns. (4) Decide interactions: which column sorts, any filter/date-range. (5) Write an acceptance-criteria checklist of 5-8 items, e.g. 'KPI cards show computed values', 'the chart renders from the data', 'the table lists all rows', 'at least one column sorts', 'a filter narrows the table', 'responsive layout', 'no console errors'. Write to notes/data-scope.md and via write_task_note. No design or HTML yet.\n\nThe deliverable `notes/data-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": "notes/data-scope.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "notes/data-scope.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "notes/data-scope.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "data-scope",
+        "maxAttempts": 3
+      },
+      "next": "layout-design"
+    },
+    {
+      "id": "layout-design",
+      "name": "Layout design",
+      "description": "card grid, chart placement, table, hierarchy",
+      "prompt": "Design the dashboard layout for scannability. (1) Pick a calm palette (hex) with one accent for emphasis/positive-negative deltas. (2) Lay out KPI cards in a top row (value, label, delta), the chart below/beside, and the table at the bottom. (3) Specify card, chart, and table styling and the responsive reflow (cards stack on mobile). (4) Define the sort indicator and filter control look. (5) Self-contained CSS; charts via canvas or inline SVG (no chart-library CDN unless trivially inlined). Write the visual spec to notes/layout-design.md and via write_task_note. No HTML yet.\n\nThe deliverable `notes/layout-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": "notes/layout-design.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "notes/layout-design.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "notes/layout-design.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "layout-design",
+        "maxAttempts": 3
+      },
+      "next": "build"
+    },
+    {
+      "id": "build",
+      "name": "Build",
+      "description": "implement index.html with cards, chart, table",
+      "prompt": "Implement index.html with inline CSS/JS to the layout and data scope. (1) Embed the data array and compute the KPIs into the summary cards (show deltas in the accent color). (2) Render the chart from the data with canvas or inline SVG. (3) Render the full data table; implement click-to-sort on at least one column and a working filter/search that narrows rows. (4) Make it responsive (cards stack, table scrolls) at 375px and 1280px. (5) 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"
+    },
+    {
+      "id": "evaluate",
+      "name": "Evaluate",
+      "description": "Grade the deliverable against every acceptance criterion. All pass → finish; any fail → loop back and fix the gap.",
+      "prompt": "Evaluate the dashboard. Open/render index.html, sort the table, use the filter, and resize. Check EACH criterion from notes/data-scope.md and write PASS/FAIL with a reason: do KPI cards show correctly computed values, does the chart render from the data, does the table list all rows, does at least one column sort, does the filter narrow the table, is it responsive, zero console errors? Verify a KPI value by hand against the data. Wrong KPIs or a dead chart 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"
+    },
+    {
+      "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": "1.0.1",
+  "releasedAt": "2026-08-14T00:00:00Z"
+}

package/data/craftbook-templates/sp/spa-dashboard/versions/1.0.1/test.json

@@ -0,0 +1,97 @@
+{
+  "schemaVersion": 1,
+  "title": "Metrics / Admin Dashboard smoke eval",
+  "objective": "Self-contained smoke eval for the Metrics / Admin Dashboard 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": "Metrics / Admin Dashboard Eval",
+    "about": "Self-contained eval project for spa-dashboard. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/index.html.",
+    "missionObjectives": "Use the Metrics / Admin Dashboard 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": "# Metrics / Admin Dashboard 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: spa-dashboard - Metrics / Admin Dashboard.\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"
+  ]
+}