@bendyline/gilde 0.1.55 → 0.1.56

package/data/craftbook-templates/re/receipt-intake/versions/1.0.3/test.json

@@ -39,6 +39,9 @@
     "worker": {
       "name": "Nora",
       "role": "Clerk"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
     }
   },
   "mocks": [],
@@ -54,23 +57,27 @@
             "kind": "contains",
             "file": "tasks/eval/report.md",
             "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
-            "flags": "i"
+            "flags": "i",
+            "artifact": true
           },
           {
             "kind": "contains",
             "file": "tasks/eval/report.md",
             "pattern": "question|unsure|unclear|flag",
             "flags": "i",
-            "label": "ambiguous receipt surfaced as an owner question, not a guess"
+            "label": "ambiguous receipt surfaced as an owner question, not a guess",
+            "artifact": true
           },
           {
             "kind": "contains",
             "file": "tasks/eval/report.md",
             "pattern": "duplicate|already (in|entered|logged)|double[- ]?count",
             "flags": "i",
-            "label": "the repeat Office Depot receipt is flagged as a likely duplicate"
+            "label": "the repeat Office Depot receipt is flagged as a likely duplicate",
+            "artifact": true
           }
-        ]
+        ],
+        "artifact": true
       }
     ],
     "checks": [

package/data/craftbook-templates/re/receipt-ocr-ledger/versions/1.0.4/craftbook.json

@@ -0,0 +1,277 @@
+{
+  "id": "receipt-ocr-ledger",
+  "name": "Receipts to Expense Ledger",
+  "description": "Turn a folder of receipt photos/PDFs into a clean expense ledger: OCR each receipt, extract vendor, date, line items, tax, and total, assign an expense category, and reconcile that each extracted total matches its line items. Locks the per-receipt field schema, the category set, and the math/reconciliation rules FIRST, then OCRs and extracts each receipt into rows, then verifies every receipt was processed, totals reconcile, currencies/dates are normalized, and low-confidence reads are flagged for review. Defining the schema and the total-equals-line-items check before extraction is what keeps an expense ledger trustworthy for reimbursement or tax.\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 the ledger (planner) — per-receipt schema, categories, reconciliation rules → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. OCR and extract (developer) — read each receipt, extract fields, categorize, reconcile → gated on `ledger.json` (json)\n3. Verify the ledger (reviewer) — coverage, reconciliation, normalization, review flags → gated on artifact `{{workPath}}/verify.md` (markdown-notes)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "scope",
+  "triggers": [
+    "scan my receipts",
+    "receipts to a spreadsheet",
+    "extract receipt totals",
+    "expense report from receipts",
+    "OCR receipts into a ledger"
+  ],
+  "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 the ledger",
+      "description": "per-receipt schema, categories, reconciliation rules",
+      "prompt": "Define the ledger contract before reading receipts. Step 1: identify the receipts folder and the file types (jpg, png, pdf). Step 2: define the per-receipt schema (file, vendor, date, currency, line items[{desc, amount}], subtotal, tax, total, category, confidence, needs_review). Step 3: define the closed expense-category set (e.g. Meals, Travel, Supplies, Software, Other) — every receipt gets exactly one. Step 4: define the math/reconciliation rule — sum(line items) + tax should equal total within a small tolerance; a mismatch sets needs_review. Step 5: define normalization (dates → ISO, amounts numeric to two decimals, a single output currency or a currency column) and the confidence threshold below which a row is flagged. Step 6: write an acceptance-criteria checklist ('every receipt file produces a row', 'amounts numeric and dates ISO', 'total reconciles to line items + tax within tolerance else flagged', 'category is in-set', 'low-confidence reads flagged for review', 'a grand total across receipts is reported'). Call write_task_note with schema + categories + rules + checklist and write {{workPath}}/scope.md. No OCR 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",
+      "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"
+        ]
+      },
+      "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": "extract"
+    },
+    {
+      "id": "extract",
+      "name": "OCR and extract",
+      "description": "read each receipt, extract fields, categorize, reconcile",
+      "prompt": "Process every receipt into a ledger row to the locked schema. Step 1: list the folder and, for each receipt, use the available OCR/vision capability to read the text. Step 2: extract vendor, date, line items, subtotal, tax, and total; normalize dates to ISO and amounts to numbers. Step 3: assign exactly one in-set category from the vendor/items. Step 4: reconcile — check sum(line items)+tax ≈ total within tolerance; on mismatch or low OCR confidence, set needs_review with a note rather than silently trusting it. Step 5: write all rows to the output file (JSON), confirm it parses, and compute a grand total across receipts. Do not skip any receipt; if one is unreadable, still emit a row flagged needs_review. Call write_task_note with the output path, the receipt count, and how many are flagged.",
+      "suggestedRole": "developer",
+      "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"
+        ]
+      },
+      "advanceWhen": {
+        "file": "ledger.json",
+        "minBytes": 1,
+        "sniff": "json-valid"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "ledger.json",
+            "bytes": 2
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkJsonValid",
+            "scope": "standard",
+            "inputs": {
+              "file": "ledger.json"
+            }
+          }
+        ],
+        "onReject": "extract",
+        "maxAttempts": 3
+      },
+      "next": "verify"
+    },
+    {
+      "id": "verify",
+      "name": "Verify the ledger",
+      "description": "coverage, reconciliation, normalization, review flags",
+      "prompt": "Verify the ledger against scope. Step 1: confirm the file parses and there is one row per receipt file in the folder — none skipped. Step 2: confirm amounts are numeric to two decimals and dates are ISO. Step 3: confirm reconciliation ran — rows where line items + tax do not match the total within tolerance are flagged needs_review, and clean rows actually balance (re-check 3 by hand). Step 4: confirm categories are all in-set and low-confidence/unreadable receipts are flagged rather than silently accepted. Step 5: confirm the grand total equals the sum of the row totals. Write PASS/FAIL per criterion to {{workPath}}/verify.md and task notes; on failure, name the receipts and loop back to extract.\n\nThe deliverable `{{workPath}}/verify.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": "reviewer",
+      "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"
+        ]
+      },
+      "advanceWhen": {
+        "file": "{{workPath}}/verify.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "ledger.json",
+            "bytes": 2
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkJsonValid",
+            "scope": "standard",
+            "inputs": {
+              "file": "ledger.json"
+            }
+          }
+        ],
+        "onReject": "verify",
+        "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": "Open ledger.json and verify every criterion from {{workPath}}/scope.md: one row per receipt file (none skipped, unreadable ones flagged), amounts numeric to two decimals and dates ISO, reconciliation flags rows where line items + tax do not match the total within tolerance while clean rows balance (re-check 3 by hand), categories all in-set, low-confidence reads flagged, and the grand total equals the sum of row totals. Write PASS/FAIL per criterion; on any failure, name the receipts and loop back to extract.\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: \"extract\" })` 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",
+      "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"
+      },
+      "consumes": [
+        {
+          "file": "ledger.json"
+        }
+      ],
+      "next": "extract"
+    },
+    {
+      "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",
+      "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"
+      },
+      "terminal": true
+    }
+  ],
+  "version": "1.0.4",
+  "releasedAt": "2026-09-05T03:30:00Z",
+  "minGezelVersion": "1.26233"
+}

package/data/craftbook-templates/re/receipt-ocr-ledger/versions/1.0.4/test.json

@@ -0,0 +1,104 @@
+{
+  "schemaVersion": 1,
+  "title": "Receipts to Expense Ledger smoke eval",
+  "objective": "Self-contained smoke eval for the Receipts to Expense Ledger craftbook using the data generic harness.",
+  "tags": [
+    "data"
+  ],
+  "prompt": "I dropped our numbers in source/records.csv. Can you look at the data, analyze it, and put togehter some results in analysis.md?",
+  "setup": {
+    "projectName": "Receipts to Expense Ledger Eval",
+    "about": "Self-contained eval project for receipt-ocr-ledger. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/analysis.md.",
+    "missionObjectives": "Use the Receipts to Expense Ledger craftbook/template, read the seeded local fixtures, and write analysis.md without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Receipts to Expense Ledger 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: receipt-ocr-ledger - Receipts to Expense Ledger.\n"
+      },
+      {
+        "path": "source/records.csv",
+        "content": "customer,region,orders,revenue_usd,churn_risk\nAster,North,12,1440,low\nBoreal,South,8,720,medium\nCedar,West,15,2100,high\nDune,North,5,500,low\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Data Analyst"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "analysis.md is a seeded-data analysis with deterministic computed facts.",
+    "deliverables": [
+      {
+        "path": "analysis.md",
+        "kind": "markdown-report",
+        "minBytes": 900,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "analysis.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "analysis.md",
+            "pattern": "40\\b",
+            "flags": "i",
+            "label": "include total orders of 40"
+          },
+          {
+            "kind": "contains",
+            "file": "analysis.md",
+            "pattern": "\\$?4,?760\\b",
+            "flags": "i",
+            "label": "include total revenue of 4760"
+          },
+          {
+            "kind": "contains",
+            "file": "analysis.md",
+            "pattern": "Cedar",
+            "flags": "i",
+            "label": "identify Cedar as top revenue and high risk"
+          },
+          {
+            "kind": "contains",
+            "file": "analysis.md",
+            "pattern": "high",
+            "flags": "i",
+            "label": "include churn-risk finding"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "analysis.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "accuracy",
+        "description": "Computed figures are correct against the seeded records."
+      },
+      {
+        "name": "grounding",
+        "description": "Every claim traces to the seeded data — nothing invented."
+      },
+      {
+        "name": "structure",
+        "description": "Tables and sections make the analysis checkable at a glance."
+      },
+      {
+        "name": "actionability",
+        "description": "Recommendations follow from the findings and are concretely doable."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "seeded data reading",
+    "computed facts",
+    "recommendation grounding"
+  ]
+}

package/data/craftbook-templates/re/recipe-capture/versions/1.0.3/test.json

@@ -27,6 +27,9 @@
     "worker": {
       "name": "Bep",
       "role": "Archivist"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
     }
   },
   "mocks": [],
@@ -42,28 +45,33 @@
             "kind": "contains",
             "file": "tasks/eval/report.md",
             "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
-            "flags": "i"
+            "flags": "i",
+            "artifact": true
           },
           {
             "kind": "contains",
             "file": "tasks/eval/report.md",
             "pattern": "Oma|Riet",
-            "label": "provenance carried into the capture log"
+            "label": "provenance carried into the capture log",
+            "artifact": true
           },
           {
             "kind": "contains",
             "file": "tasks/eval/report.md",
             "pattern": "\\?",
-            "label": "questions for the family are actually asked"
+            "label": "questions for the family are actually asked",
+            "artifact": true
           },
           {
             "kind": "contains",
             "file": "tasks/eval/report.md",
             "pattern": "test[- ]?cook|try (it|the)|verify",
             "flags": "i",
-            "label": "test-cook needs named"
+            "label": "test-cook needs named",
+            "artifact": true
           }
-        ]
+        ],
+        "artifact": true
       }
     ],
     "checks": [

package/data/craftbook-templates/re/record-a-relative/versions/1.0.3/test.json

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