@bendyline/gilde 0.1.50 → 0.1.52

package/data/craftbook-templates/da/data-viz-page/versions/1.0.3/test.json

@@ -0,0 +1,117 @@
+{
+  "schemaVersion": 1,
+  "title": "Source-grounded data visualization page",
+  "objective": "Measure whether the data-viz-page craftbook scopes a chart and builds a self-contained HTML visualization from seeded metrics.",
+  "tags": [
+    "html-page"
+  ],
+  "prompt": "In the `Data Viz Page Eval` project, read `source/metrics.csv` and build `index.html`: a responsive one-page visualization of weekly conversion rate by region. Include a chart using inline SVG or canvas, a legend for North/South/West, a short insight summary grounded in the data, and hover/click affordance text or tooltip behavior. Inline CSS/JS only, no external assets.",
+  "setup": {
+    "projectName": "Data Viz Page Eval",
+    "about": "Self-contained eval project for data-viz-page. Source metrics are in workspace/source/metrics.csv and the deliverable is workspace/index.html.",
+    "missionObjectives": "Build a self-contained chart page from the seeded conversion-rate data with grounded summary and visible chart/legend behavior.",
+    "files": [
+      {
+        "path": "source/metrics.csv",
+        "content": "week,region,conversion_rate\n2026-W01,North,0.41\n2026-W01,South,0.34\n2026-W01,West,0.29\n2026-W02,North,0.45\n2026-W02,South,0.36\n2026-W02,West,0.31\n2026-W03,North,0.53\n2026-W03,South,0.39\n2026-W03,West,0.35\n2026-W04,North,0.51\n2026-W04,South,0.47\n2026-W04,West,0.38\n"
+      }
+    ],
+    "worker": {
+      "name": "Daan",
+      "role": "Developer"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "index.html is a complete chart page grounded in the seeded regional conversion data.",
+    "deliverables": [
+      {
+        "path": "index.html",
+        "kind": "html-page",
+        "minBytes": 3400,
+        "checks": [
+          {
+            "kind": "cssMinBytes",
+            "bytes": 700,
+            "file": "index.html"
+          },
+          {
+            "kind": "jsParses",
+            "file": "index.html"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "svg|canvas",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "North",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "South",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "West",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "conversion",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "legend|tooltip|hover",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "index.html",
+            "pattern": "0\\.53|53%|0\\.47|47%",
+            "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": [
+    "data grounding",
+    "chart semantics",
+    "interactive HTML"
+  ]
+}

package/data/craftbook-templates/da/dataset-clean/versions/1.2.3/test.json

@@ -21,9 +21,6 @@
     "worker": {
       "name": "Jules",
       "role": "Developer"
-    },
-    "craftbookParams": {
-      "workPath": "tasks/eval"
     }
   },
   "mocks": [],

package/data/craftbook-templates/da/dataset-clean/versions/1.2.4/craftbook.json

@@ -0,0 +1,212 @@
+{
+  "id": "dataset-clean",
+  "name": "Clean a Dataset",
+  "description": "Profile, clean, and validate a messy CSV/TSV/JSON dataset into an analysis-ready table. Profiles the raw data FIRST (row/column counts, types, null rates, duplicates, outliers, encoding) so cleaning decisions are evidence-based, then applies deterministic transforms (dedup, type coercion, null handling, whitespace/case normalization, value standardization), then validates the cleaned output against the same profile so nothing was silently dropped or corrupted. Use this for data wrangling, tidying, deduplication, normalizing dirty spreadsheets, and prepping raw exports for charts or modeling.\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. Profile the raw data (data-analyst) — measure the data's shape, types, and defects before touching it → gated on artifact `{{workPath}}/profile.md` (markdown-notes)\n2. Clean the data (developer) — apply the planned deterministic transforms and emit the cleaned file → gated on `data/clean.csv` (data-file)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "profile",
+  "triggers": [
+    "clean this dataset",
+    "tidy a csv",
+    "deduplicate data",
+    "fix dirty data",
+    "prep data for analysis"
+  ],
+  "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": "profile",
+      "name": "Profile the raw data",
+      "description": "measure the data's shape, types, and defects before touching it",
+      "prompt": "Load the raw dataset and PROFILE it before deciding any fix. Step 1: report row count, column count, and the delimiter/encoding. Step 2: for EACH column report inferred type, % null/blank, # distinct values, and 3 sample values. Step 3: count exact-duplicate rows and flag candidate key columns. Step 4: list concrete defects you observe — mixed types in a column, inconsistent casing ('USA' vs 'usa'), stray whitespace, mojibake/encoding issues, impossible values (negative ages, dates in the future), and outliers (values > 3 stdev). Step 5: turn each defect into a planned, deterministic fix and write an acceptance-criteria checklist (e.g. 'no exact-duplicate rows', 'date column parses as ISO-8601', 'no nulls in key columns', 'cleaned row count >= 95% of raw unless dupes explain the drop'). Call write_task_note with the profile table + defects + fixes + checklist, and also write the same content to {{workPath}}/profile.md. No cleaning code yet.\n\nThe deliverable `{{workPath}}/profile.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": "data-analyst",
+      "advanceWhen": {
+        "file": "{{workPath}}/profile.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/profile.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/profile.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "profile",
+        "maxAttempts": 3
+      },
+      "next": "clean",
+      "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": "clean",
+      "name": "Clean the data",
+      "description": "apply the planned deterministic transforms and emit the cleaned file",
+      "prompt": "Apply EXACTLY the fixes the profile planned — no new undocumented transforms. Step 1: read the raw file with the correct encoding/delimiter. Step 2: in order, drop exact duplicates, coerce each column to its target type, normalize whitespace and casing, standardize known value variants to a canonical form, and handle nulls per the plan (impute, drop, or leave with a reason). Step 3: keep a running tally of rows-in vs rows-out and WHY any row was dropped. Step 4: write the cleaned dataset to data/clean.csv with a header row and consistent quoting. Step 5: call write_task_note with the path, the rows-in/rows-out delta, and which checklist items the output now satisfies. Do not lose columns the profile expected to keep.",
+      "suggestedRole": "developer",
+      "advanceWhen": {
+        "file": "data/clean.csv",
+        "minBytes": 1,
+        "sniff": "nonempty"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "data/clean.csv",
+            "bytes": 120
+          },
+          {
+            "kind": "sniff",
+            "file": "data/clean.csv",
+            "sniff": "data-table"
+          }
+        ],
+        "onReject": "clean",
+        "maxAttempts": 4
+      },
+      "next": "evaluate",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "artifacts",
+          "audio",
+          "browser-automation",
+          "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 that data/clean.csv is genuinely analysis-ready by re-profiling it. Step 1: confirm it parses as CSV, has a header row, and zero exact-duplicate rows. Step 2: confirm the key column(s) have no nulls and every column holds its declared type. Step 3: reconcile the row count — raw rows minus documented duplicates must equal the cleaned row count, and no column was dropped. Step 4: re-measure at least two of these numbers yourself rather than trusting the build note. Step 5: spot-check 5 rows against the raw source to confirm values were transformed, not corrupted. Write PASS/FAIL per acceptance criterion from the profile note; any FAIL loops back to clean.\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: \"clean\" })` 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": "data/clean.csv"
+        }
+      ],
+      "next": "clean",
+      "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": "1.2.4",
+  "releasedAt": "2026-09-01T20:00:00Z",
+  "minGezelVersion": "1.26233"
+}

package/data/craftbook-templates/da/dataset-clean/versions/1.2.4/test.json

@@ -0,0 +1,95 @@
+{
+  "schemaVersion": 1,
+  "title": "Messy CSV cleanup",
+  "objective": "Exercise the data-cleaning class with messy CSV fixtures, dedupe rules, date normalization, and deterministic JSON output.",
+  "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": "Clean a Dataset Eval",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Clean a Dataset 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: dataset-clean - Clean a Dataset.\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": "The hand-authored data-wrangle grader validates parseability, schema, normalization, dedupe, row count, ordering, and golden records.",
+    "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": [
+    "precision ETL",
+    "fixture-backed grading",
+    "single-gap feedback"
+  ]
+}

package/data/craftbook-templates/db/db-index-tuning/versions/1.0.2/test.json

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