@bendyline/gilde 0.1.50 → 0.1.52

package/data/craftbook-templates/pr/press-release/versions/1.0.3/test.json

@@ -0,0 +1,356 @@
+{
+  "schemaVersion": 1,
+  "title": "AP-style press release from news brief",
+  "objective": "Measure whether the press-release craftbook scopes the five Ws and writes a factual, standard-format release with quote, boilerplate, contact, and end mark.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "In the `Press Release Eval` project, read `source/news-brief.md` and write `press-release.md`. Use a standard headline, subhead, dateline, inverted-pyramid lede, attributed quote, boilerplate, media contact, and closing ###. Keep it factual and avoid promotional hype. Use the source boilerplate sentence exactly, without expanding Boreal Desk beyond the brief.",
+  "setup": {
+    "projectName": "Press Release Eval",
+    "about": "Self-contained eval project for press-release. The approved news facts are in workspace/source/news-brief.md.",
+    "missionObjectives": "Write a factual AP-style press release from seeded facts with all standard structural elements.",
+    "files": [
+      {
+        "path": "source/news-brief.md",
+        "content": "# News brief\n\nCompany: Boreal Desk, maker of workflow software for independent design studios.\nNews: Boreal Desk is launching HarborCRM guided returns intake for Pro accounts.\nTiming: June 28, 2026.\nLocation/dateline: BOSTON, Mass.\nWhy now: a March pilot across 18 home-office accessory SKUs cut median first response from 18 hours to 6 hours and reduced preventable refund leakage from 14.2% to 8.9%.\nQuote: \"Guided intake gives support teams the context they need before the first reply,\" said Maya Chen, VP of Product at Boreal Desk.\nBoilerplate: Boreal Desk builds practical operations tools for independent design studios.\nMedia contact: press@borealdesk.example, Lena Moore.\n"
+      }
+    ],
+    "worker": {
+      "name": "Roos",
+      "role": "PR Writer"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "workspace/press-release.md follows standard release structure with dateline, lede, quote, metrics, boilerplate, contact, ###, and no hype.",
+    "deliverables": [
+      {
+        "path": "press-release.md",
+        "kind": "markdown-doc",
+        "minBytes": 1100,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "press-release.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "press-release.md",
+            "pattern": "BOSTON, Mass\\.?\\s*(?:,|[-\\u2013\\u2014])\\s*June 28, 2026",
+            "flags": "i",
+            "label": "include a dated dateline such as \"BOSTON, Mass., June 28, 2026\""
+          },
+          {
+            "kind": "contains",
+            "file": "press-release.md",
+            "pattern": "Maya Chen",
+            "flags": "i",
+            "label": "include the approved quote speaker Maya Chen"
+          },
+          {
+            "kind": "contains",
+            "file": "press-release.md",
+            "pattern": "VP of Product",
+            "flags": "i",
+            "label": "include Maya Chen title: VP of Product"
+          },
+          {
+            "kind": "contains",
+            "file": "press-release.md",
+            "pattern": "18\\s*hours",
+            "flags": "i",
+            "label": "include the source metric: 18 hours"
+          },
+          {
+            "kind": "contains",
+            "file": "press-release.md",
+            "pattern": "(?:6|six)\\s*hours",
+            "flags": "i",
+            "label": "include the source metric: 6 hours"
+          },
+          {
+            "kind": "contains",
+            "file": "press-release.md",
+            "pattern": "14\\.2%",
+            "flags": "i",
+            "label": "include the source metric: 14.2%"
+          },
+          {
+            "kind": "contains",
+            "file": "press-release.md",
+            "pattern": "8\\.9%",
+            "flags": "i",
+            "label": "include the source metric: 8.9%"
+          },
+          {
+            "kind": "contains",
+            "file": "press-release.md",
+            "pattern": "About Boreal Desk",
+            "flags": "i",
+            "label": "include an \"About Boreal Desk\" boilerplate heading"
+          },
+          {
+            "kind": "contains",
+            "file": "press-release.md",
+            "pattern": "Boreal Desk builds practical operations tools for independent design studios\\.",
+            "flags": "i",
+            "label": "include the approved boilerplate sentence exactly"
+          },
+          {
+            "kind": "notContains",
+            "file": "press-release.md",
+            "pattern": "Boreal Desk builds practical operations tools for independent design studios\\s*,",
+            "flags": "i",
+            "label": "do not expand the approved boilerplate sentence"
+          },
+          {
+            "kind": "contains",
+            "file": "press-release.md",
+            "pattern": "Media Contact|Media contact",
+            "flags": "i",
+            "label": "include a Media Contact block"
+          },
+          {
+            "kind": "contains",
+            "file": "press-release.md",
+            "pattern": "press@borealdesk\\.example",
+            "flags": "i",
+            "label": "include the approved media contact email"
+          },
+          {
+            "kind": "contains",
+            "file": "press-release.md",
+            "pattern": "(?:^|\\n)###\\s*$",
+            "flags": "i",
+            "label": "end the release with a standalone ### line"
+          },
+          {
+            "kind": "notContains",
+            "file": "press-release.md",
+            "pattern": "revolutioniz|game-changing|world-class|guaranteed|transformative|transforming|dramatic|innovative|moderniz|significant(?:ly)?|thorough|rigorous(?:ly)?|major (?:update|step)|massive (?:step|update)|slash(?:es|ed|ing)?|75%|proactive instead of reactive|custom-printed|specialized equipment|large enterprise(?:s)?|creative agencies|enterprise-level|price tag|555",
+            "flags": "i",
+            "label": "remove promotional hype and invented details not present in the brief"
+          },
+          {
+            "kind": "unsupportedClaims",
+            "file": "press-release.md",
+            "sourceFiles": [
+              "source/news-brief.md"
+            ],
+            "patterns": [
+              {
+                "pattern": "fundamentally(?: changes?| changing| changed)?",
+                "label": "avoid sweeping overclaims"
+              },
+              {
+                "pattern": "customer experience",
+                "label": "avoid invented benefit claims"
+              },
+              {
+                "pattern": "professional,?\\s+high-volume clients?",
+                "label": "avoid invented audience claims"
+              },
+              {
+                "pattern": "high-volume clients?",
+                "label": "avoid invented audience claims"
+              },
+              {
+                "pattern": "enhanc(?:e[sd]?|ing|ement|ements)?",
+                "label": "avoid vague benefit claims"
+              },
+              {
+                "pattern": "intuitive",
+                "label": "avoid invented ease-of-use claims"
+              },
+              {
+                "pattern": "efficien(?:cy|tly|t)",
+                "label": "avoid unsupported efficiency claims"
+              },
+              {
+                "pattern": "streamlin(?:e[sd]?|ing)|streamlined efficiency",
+                "label": "avoid unsupported efficiency claims"
+              },
+              {
+                "pattern": "moderniz(?:e[sd]?|ing|ation|ations)?",
+                "label": "avoid vague market claims"
+              },
+              {
+                "pattern": "successful(?:ly)?",
+                "label": "avoid unsupported outcome claims"
+              },
+              {
+                "pattern": "demonstrable|demonstrat(?:e[sd]?|ing)",
+                "label": "avoid unsupported proof claims"
+              },
+              {
+                "pattern": "effectively validate[sd]?|validat(?:e[sd]?|ing|ion)",
+                "label": "avoid unsupported validation claims"
+              },
+              {
+                "pattern": "major\\s+(?:step|update|milestone|move)",
+                "label": "avoid inflated importance claims"
+              },
+              {
+                "pattern": "powerful",
+                "label": "avoid vague promotional adjectives"
+              },
+              {
+                "pattern": "empower(?:s|ed|ing|ment)?",
+                "label": "avoid promotional benefit framing"
+              },
+              {
+                "pattern": "resolution times?",
+                "label": "avoid unsupported resolution claims"
+              },
+              {
+                "pattern": "enterprise complexity|enterprise-level|large enterprises?",
+                "label": "avoid invented market segment claims"
+              },
+              {
+                "pattern": "customer satisfaction",
+                "label": "avoid invented outcome claims"
+              },
+              {
+                "pattern": "customer refunds?",
+                "label": "avoid invented domain claims"
+              },
+              {
+                "pattern": "issue resolution|service quality|client service",
+                "label": "avoid invented service outcome claims"
+              },
+              {
+                "pattern": "back-and-forth communication",
+                "label": "avoid invented communication outcome claims"
+              },
+              {
+                "pattern": "critical context",
+                "label": "avoid invented urgency claims"
+              },
+              {
+                "pattern": "lost revenue",
+                "label": "avoid unsupported financial framing"
+              },
+              {
+                "pattern": "small businesses",
+                "label": "avoid invented audience claims"
+              },
+              {
+                "pattern": "growing independent businesses",
+                "label": "avoid invented audience claims"
+              },
+              {
+                "pattern": "financial management",
+                "label": "avoid invented domain claims"
+              },
+              {
+                "pattern": "e-?commerce operations?",
+                "label": "avoid invented domain claims"
+              },
+              {
+                "pattern": "complex projects?",
+                "label": "avoid invented domain claims"
+              },
+              {
+                "pattern": "complex business tasks?",
+                "label": "avoid invented domain claims"
+              },
+              {
+                "pattern": "client relations",
+                "label": "avoid invented domain claims"
+              },
+              {
+                "pattern": "project management",
+                "label": "avoid invented product-scope claims"
+              },
+              {
+                "pattern": "client communication",
+                "label": "avoid invented product-scope claims"
+              },
+              {
+                "pattern": "back-office infrastructure",
+                "label": "avoid invented product-scope claims"
+              },
+              {
+                "pattern": "integrated software solutions?",
+                "label": "avoid invented product-scope claims"
+              },
+              {
+                "pattern": "operational demands?",
+                "label": "avoid invented domain claims"
+              },
+              {
+                "pattern": "business processes?",
+                "label": "avoid invented domain claims"
+              },
+              {
+                "pattern": "unique workflow demands?",
+                "label": "avoid invented audience claims"
+              },
+              {
+                "pattern": "operate leanly",
+                "label": "avoid unsupported operating claims"
+              },
+              {
+                "pattern": "creative professionals",
+                "label": "avoid invented audience claims"
+              },
+              {
+                "pattern": "customiz(?:e[sd]?|able|ing|ation)",
+                "label": "avoid invented feature claims"
+              },
+              {
+                "pattern": "market-leading|best-in-class",
+                "label": "avoid unsupported ranking claims"
+              },
+              {
+                "pattern": "robust",
+                "label": "avoid vague promotional adjectives"
+              },
+              {
+                "pattern": "seamless",
+                "label": "avoid vague promotional adjectives"
+              },
+              {
+                "pattern": "scalable",
+                "label": "avoid unsupported capability claims"
+              }
+            ],
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "press-release.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "grounding",
+        "description": "Seeded facts appear faithfully and the source is cited."
+      },
+      {
+        "name": "structure",
+        "description": "Sections progress logically for the artifact class."
+      },
+      {
+        "name": "completeness",
+        "description": "Required elements (risks, next actions, scope) are all present."
+      },
+      {
+        "name": "tone",
+        "description": "The register fits the audience and artifact class."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "standard format",
+    "five Ws",
+    "factual tone"
+  ]
+}

package/data/craftbook-templates/pr/price-tracker/versions/1.0.2/test.json

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

package/data/craftbook-templates/pr/price-tracker/versions/1.0.3/craftbook.json

@@ -0,0 +1,220 @@
+{
+  "id": "price-tracker",
+  "name": "Track Prices Over Time",
+  "description": "Build a price tracker that records the price of one or more products/SKUs each time it runs, appending a timestamped history so you can see trends, drops, and the lowest price seen. Scopes the SKUs, the price-extraction rule, and the history-file schema FIRST, then builds the fetch-and-append routine that is idempotent per day and computes drop-from-previous and all-time-low. Schema-before-build keeps the history a clean append-only time series instead of a pile of inconsistent snapshots — the foundation any later chart or alert reads from.\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 tracker (planner) — SKUs, price-extraction rule, and history schema → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Build the tracker (developer) — fetch each SKU, append a row, compute drop + low → gated on `price_tracker.py` (code-module)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "scope",
+  "triggers": [
+    "track a price",
+    "price history tracker",
+    "watch product prices",
+    "log prices over time",
+    "price drop history"
+  ],
+  "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 tracker",
+      "description": "SKUs, price-extraction rule, and history schema",
+      "prompt": "Define the tracker before fetching. Step 1: list each product to track — a stable id/SKU, a label, and its URL or API. Step 2: define the price-extraction rule per source (which element/field holds the price) and the currency, and decide how to normalize (numeric, two decimals). Step 3: define the append-only history schema (e.g. CSV columns: timestamp, sku, label, price, currency, source_url) and the file path. Step 4: decide the run cadence and the idempotency rule (at most one row per sku per day — a re-run the same day updates rather than duplicates). Step 5: write an acceptance-criteria checklist ('every tracked SKU gets a row per run', 'prices are numeric and normalized', 'history is append-only and de-duplicated per day', 'drop-from-previous and all-time-low are computed', 'a failed fetch is logged, not silently dropped'). Call write_task_note with the SKU list + schema + checklist and write it to {{workPath}}/scope.md. No code 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": "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 the tracker",
+      "description": "fetch each SKU, append a row, compute drop + low",
+      "prompt": "Implement the tracker to the locked schema. Step 1: load the existing history file (or create it with the header). Step 2: for each SKU, fetch the source and extract the price with the scoped rule, normalizing to a number; on a fetch error, log it and continue (do not write a fake price). Step 3: enforce idempotency — if a row already exists for this SKU today, update it; otherwise append a new timestamped row. Step 4: for each SKU compute drop-from-previous (this price vs the prior recorded price) and the all-time-low across history, and surface those in a small summary. Step 5: write the runnable script (cron-friendly) and ensure the history file stays valid and append-only. Call write_task_note with the script path, the history path, and the per-SKU current/low summary.",
+      "suggestedRole": "developer",
+      "advanceWhen": {
+        "file": "price_tracker.py",
+        "minBytes": 1,
+        "sniff": "nonempty"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "price_tracker.py",
+            "bytes": 200
+          },
+          {
+            "kind": "sniff",
+            "file": "price_tracker.py",
+            "sniff": "nonempty"
+          },
+          {
+            "kind": "esmImports",
+            "file": "price_tracker.py"
+          },
+          {
+            "kind": "sourceParses",
+            "file": "price_tracker.py"
+          }
+        ],
+        "onReject": "build",
+        "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": "Run price_tracker.py (or trace it) and verify every criterion from {{workPath}}/scope.md against the produced history file. Confirm: each tracked SKU has a row this run, prices are numeric and normalized, the history is append-only with at most one row per SKU per day (a same-day re-run does not duplicate), drop-from-previous and all-time-low are computed correctly, and a simulated fetch failure is logged rather than written as a bogus price. Write PASS/FAIL per criterion; on any failure, name it and 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": "price_tracker.py"
+        }
+      ],
+      "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"
+}