@bendyline/gilde 0.1.38 → 0.1.39

package/data/craftbook-templates/sc/schema-migration/versions/1.0.2/craftbook.json

@@ -0,0 +1,156 @@
+{
+  "id": "schema-migration",
+  "name": "Schema / Type Migration",
+  "description": "Plan and execute a multi-file schema or type migration safely — changing a data model, type definition, or interface across the codebase while keeping everything compiling and consistent. Plans the migration FIRST — the before/after shape, every call-site and file touched, the ordering that never leaves the tree broken, and the backout — then applies the change file-by-file, then a reviewer verifies the tree still builds and nothing referencing the old shape remains. Covers find-all-references, safe edit ordering, backward-compatibility shims, codemod-style changes, and compile/test-green verification.\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. Plan the migration (planner) — lock before/after, touched files, ordering, backout → gated on artifact `{{workPath}}/plan.md` (markdown-notes)\n2. Apply the migration (developer) — edit each touched file in the planned order → gated on `MIGRATION.md` (markdown-doc)\n3. Verify the tree (reviewer) — confirm it compiles, tests pass, old shape is gone → 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": "plan",
+  "triggers": [
+    "migrate a schema",
+    "change a type everywhere",
+    "multi-file migration",
+    "rename a model across the codebase",
+    "type migration"
+  ],
+  "steps": [
+    {
+      "id": "plan",
+      "name": "Plan the migration",
+      "description": "lock before/after, touched files, ordering, backout",
+      "prompt": "Plan the migration before changing a line. Step 1: Document the BEFORE shape and the exact AFTER shape (fields, types, names) of the thing being migrated. Step 2: Find every reference: search the codebase for all call-sites, definitions, and files that touch the old shape, and list them. Step 3: Decide the edit ordering that keeps the tree compiling at each step (e.g. add-new-alongside-old → migrate call-sites → remove-old), and whether a temporary compatibility shim is needed. Step 4: Note the backout/rollback approach. Step 5: Write a numbered acceptance-criteria checklist of 5-9 items (e.g. 'the project compiles after the migration', 'no reference to the old shape remains', 'existing tests still pass', 'behavior is unchanged'). `write_task_note` the plan (with the file list) + checklist and write the same to the produces path.\n\nThe deliverable `{{workPath}}/plan.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}}/plan.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/plan.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/plan.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "plan",
+        "maxAttempts": 3
+      },
+      "next": "migrate"
+    },
+    {
+      "id": "migrate",
+      "name": "Apply the migration",
+      "description": "edit each touched file in the planned order",
+      "prompt": "Execute the migration following the planned ordering. Step 1: Apply the change file-by-file in the order that keeps the tree compiling, using the file list from the plan as a checklist. Step 2: Update every call-site to the new shape; remove the old shape (and any shim) only once nothing references it. Step 3: After each batch, confirm the project still compiles/type-checks. Step 4: Do a final search to prove no reference to the old shape remains. Capture the migration summary (files changed, references updated) to the produces path. On a loop-back, fix only the files the reviewer flagged. `write_task_note` the summary and which criteria now pass.",
+      "suggestedRole": "developer",
+      "advanceWhen": {
+        "file": "MIGRATION.md",
+        "minBytes": 1,
+        "sniff": "nonempty"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "MIGRATION.md",
+            "bytes": 500
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkContains",
+            "scope": "standard",
+            "inputs": {
+              "file": "MIGRATION.md",
+              "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+              "flags": "i"
+            }
+          }
+        ],
+        "onReject": "migrate",
+        "maxAttempts": 3
+      },
+      "next": "verify"
+    },
+    {
+      "id": "verify",
+      "name": "Verify the tree",
+      "description": "confirm it compiles, tests pass, old shape is gone",
+      "prompt": "Verify the migration is complete and clean. Step 1: Run the build/type-check and confirm it passes with no errors. Step 2: Run the existing test suite and confirm it is still green (behavior preserved). Step 3: Search the whole codebase for any lingering reference to the old shape/name and confirm there are none. Step 4: Spot-check a couple of migrated call-sites for correctness. Write a verification note with the build/test result and the search result to the produces path.\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",
+      "advanceWhen": {
+        "file": "{{workPath}}/verify.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "MIGRATION.md",
+            "bytes": 500
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkContains",
+            "scope": "standard",
+            "inputs": {
+              "file": "MIGRATION.md",
+              "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+              "flags": "i"
+            }
+          }
+        ],
+        "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": "Build the project and run the tests. For EACH acceptance criterion: confirm the project compiles/type-checks cleanly, confirm the test suite is green, confirm a codebase search finds NO reference to the old shape, and confirm behavior is unchanged. Write PASS/FAIL per criterion; any lingering old-shape reference or build break is a FAIL.\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: \"migrate\" })` 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": "MIGRATION.md"
+        }
+      ],
+      "next": "migrate"
+    },
+    {
+      "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": "1.0.2",
+  "releasedAt": "2026-08-21T00:00:00Z",
+  "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}}"
+      }
+    }
+  },
+  "minGezelVersion": "1.26233"
+}

package/data/craftbook-templates/sc/schema-migration/versions/1.0.2/test.json

@@ -0,0 +1,106 @@
+{
+  "schemaVersion": 1,
+  "title": "Coordinated TypeScript schema migration",
+  "objective": "Measure whether the migration craftbook drives planning, multi-file edits, tests, and verification on a seeded TypeScript codebase.",
+  "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": "Schema / Type Migration Eval",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Schema / Type Migration 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: schema-migration - Schema / Type Migration.\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"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "The hand-authored schema-migration grader seeds a TS codebase and requires clean typecheck, no stale .name references, tests, and MIGRATION.md.",
+    "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": [
+    "planning gate",
+    "multi-file migration",
+    "compiler feedback",
+    "verification loop"
+  ]
+}

package/data/craftbook-templates/sc/scrape-to-structured/versions/1.0.3/craftbook.json

@@ -0,0 +1,152 @@
+{
+  "id": "scrape-to-structured",
+  "name": "Scrape a Site to Structured Data",
+  "description": "Turn one or more web pages into a clean, structured dataset (JSON or CSV) with a fixed schema — product listings, directory entries, articles, tables, or job posts. Scopes the exact fields and a sample-row target FIRST so extraction is verifiable, then crawls and parses each page into rows, then validates that every row matches the schema, types are coerced, required fields are non-empty, and there are no duplicates. The scope-before-scrape ordering is the point: a small model that locks the field list and one hand-written sample row extracts consistently instead of inventing keys per page.\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 extraction (planner) — lock target URLs, the field schema, and a sample row → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Scrape and parse (developer) — fetch each page and extract rows to the schema → gated on `data.json` (json)\n3. Validate the dataset (reviewer) — schema, types, completeness, and dedup checks → gated on artifact `{{workPath}}/validate.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": [
+    "scrape a website",
+    "extract data from a site",
+    "turn a page into JSON",
+    "crawl and structure",
+    "pull a table from the web"
+  ],
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the extraction",
+      "description": "lock target URLs, the field schema, and a sample row",
+      "prompt": "Define exactly what to extract before fetching anything. Step 1: list the target URL(s) or the URL pattern to crawl, and note pagination (how to reach page 2..N) if any. Step 2: define the output schema as a flat field list — for each field give a name, a type (string/number/boolean/date/url), and whether it is required. Step 3: hand-write ONE fully-populated sample row in the chosen format so the build phase has a concrete target to match. Step 4: decide output format (JSON array of objects, or CSV) and the file path. Step 5: write an acceptance-criteria checklist (e.g. 'every page in scope is fetched', 'every row has all required fields non-empty', 'numeric/date fields are typed not strings', 'no duplicate rows by the key field', 'row count is within the expected range'). Call write_task_note with the schema, the sample row, and the checklist, and also write that same content to {{workPath}}/scope.md. No scraping 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": "scrape"
+    },
+    {
+      "id": "scrape",
+      "name": "Scrape and parse",
+      "description": "fetch each page and extract rows to the schema",
+      "prompt": "Fetch each in-scope page (use the available fetch/browser capability) and parse out the fields defined in the schema. Step 1: fetch page 1, locate the repeating record container, and map each schema field to its selector/pattern. Step 2: extract every record on the page into an object keyed exactly by the schema field names — never invent or rename keys. Step 3: follow pagination and repeat until all in-scope pages are done. Step 4: coerce types as you go (parse numbers, normalize dates to ISO, absolutize relative URLs) and trim whitespace. Step 5: write all rows to the scoped output file in the chosen format and confirm it parses. Stage progress so a partial run is observable. Call write_task_note with the output path and the row count.",
+      "suggestedRole": "developer",
+      "advanceWhen": {
+        "file": "data.json",
+        "minBytes": 1,
+        "sniff": "json-valid"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "data.json",
+            "bytes": 2
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkJsonValid",
+            "scope": "standard",
+            "inputs": {
+              "file": "data.json"
+            }
+          }
+        ],
+        "onReject": "scrape",
+        "maxAttempts": 3
+      },
+      "next": "validate"
+    },
+    {
+      "id": "validate",
+      "name": "Validate the dataset",
+      "description": "schema, types, completeness, and dedup checks",
+      "prompt": "Validate the produced dataset against the locked schema and checklist. Step 1: confirm the file parses and is the chosen format. Step 2: for every row, confirm all required fields are present and non-empty and that types match (numbers are numbers, dates are ISO, urls are absolute). Step 3: check coverage — the row count is within the expected range and pages were not silently skipped. Step 4: check for duplicate rows by the key field and flag any. Step 5: spot-check 3 rows against the live source to confirm values are correct, not hallucinated. Write a PASS/FAIL line per criterion to {{workPath}}/validate.md and to task notes. If anything fails, list the exact rows/fields and loop back to scrape.\n\nThe deliverable `{{workPath}}/validate.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",
+      "advanceWhen": {
+        "file": "{{workPath}}/validate.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "data.json",
+            "bytes": 2
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkJsonValid",
+            "scope": "standard",
+            "inputs": {
+              "file": "data.json"
+            }
+          }
+        ],
+        "onReject": "validate",
+        "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 data.json and verify it against every acceptance criterion from {{workPath}}/scope.md. Confirm it parses as valid JSON. For each row, check required fields are non-empty and types are correct (numbers typed, dates ISO, urls absolute). Verify there are no duplicate rows by the key field and the row count is in range. Spot-check 3 rows against the source. Write PASS/FAIL per criterion; on any failure, name the offending rows/fields and loop back to scrape.\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: \"scrape\" })` 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.json"
+        }
+      ],
+      "next": "scrape"
+    },
+    {
+      "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": "1.0.3",
+  "releasedAt": "2026-08-21T00:00:00Z",
+  "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}}"
+      }
+    }
+  },
+  "minGezelVersion": "1.26233"
+}

package/data/craftbook-templates/sc/scrape-to-structured/versions/1.0.3/test.json

@@ -0,0 +1,165 @@
+{
+  "schemaVersion": 1,
+  "title": "Scrape a Site to Structured Data smoke eval",
+  "objective": "Self-contained smoke eval for the Scrape a Site to Structured Data craftbook using the external generic harness.",
+  "tags": [
+    "external"
+  ],
+  "prompt": "Theres a fake ops service wired up for this so nothing real gets touched — the endpoints are in mocks/services.md, and the ready-made mock-probe script talks to them for you. Can you run the automation against it and write up how it went in automation.md?",
+  "setup": {
+    "projectName": "Scrape a Site to Structured Data Eval",
+    "about": "Self-contained eval project for scrape-to-structured. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/automation.md.",
+    "missionObjectives": "Use the Scrape a Site to Structured Data craftbook/template, read the seeded local fixtures, and write automation.md without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Scrape a Site to Structured Data 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: scrape-to-structured - Scrape a Site to Structured Data.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Developer"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [
+    {
+      "kind": "http",
+      "id": "ops",
+      "description": "Fake operations service for this eval. GET /api/bookings/open lists the open work items; POST /api/bookings/dry-run records a simulated submission and returns DRY_RUN_OK.",
+      "credential": {
+        "name": "mock.ops"
+      },
+      "routes": [
+        {
+          "method": "GET",
+          "path": "/api/bookings/open",
+          "body": {
+            "items": [
+              "BKG-1001",
+              "BKG-1002",
+              "BKG-1003"
+            ]
+          }
+        },
+        {
+          "method": "POST",
+          "path": "/api/bookings/dry-run",
+          "status": 201,
+          "body": {
+            "status": "DRY_RUN_OK",
+            "recorded": 3
+          }
+        }
+      ]
+    },
+    {
+      "kind": "webhook",
+      "id": "notify",
+      "description": "Notification receiver. POST a JSON completion notice here when the run finishes.",
+      "path": "/hooks/notify"
+    },
+    {
+      "kind": "cli",
+      "id": "probe",
+      "description": "Provenance-trusted project script `mock-probe` that exercises the fake ops service through http.authed and returns the raw responses.",
+      "shim": {
+        "path": "scripts/mock-probe.ts",
+        "content": "import { defineScript, gezel } from '@bendyline/gezel-sdk';\n\nexport const meta = defineScript({\n  name: 'mock-probe',\n  description:\n    'Probe the live fake ops service for this eval: lists the open work items and records a dry-run submission. Outputs the raw JSON responses as evidence for the write-up.',\n  inputs: {},\n  outputs: {\n    open: { type: 'string', description: 'Raw JSON body from the open-items listing.' },\n    dryRun: { type: 'string', description: 'Raw JSON body from the dry-run submission.' },\n  },\n  requires: ['workspace.read', 'network', 'credential:mock.ops'],\n});\n\nconst services = JSON.parse(await gezel.fs.read('mocks/services.json'));\nconst base = (id) => {\n  const service = services.find((entry) => entry.id === id);\n  if (!service) throw new Error(`mock service \"${id}\" is not listed in mocks/services.json`);\n  return service.baseUrl;\n};\n\nconst open = await gezel.http.authed(`${base('ops')}/api/bookings/open`, {\n  credential: 'mock.ops',\n});\nif (!open.ok) throw new Error(`open-items listing failed: ${open.status} ${open.body}`);\n\nconst dryRun = await gezel.http.authed(`${base('ops')}/api/bookings/dry-run`, {\n  credential: 'mock.ops',\n  method: 'POST',\n  body: JSON.stringify({ items: JSON.parse(open.body).items, mode: 'dry-run' }),\n});\nif (!dryRun.ok) throw new Error(`dry-run submission failed: ${dryRun.status} ${dryRun.body}`);\n\ngezel.output({ open: open.body, dryRun: dryRun.body });\n"
+      }
+    }
+  ],
+  "success": {
+    "summary": "automation.md is grounded in live fake-service responses: the open items were actually listed and a dry-run actually recorded (request-log assertions), with safety guards and signals described.",
+    "deliverables": [
+      {
+        "path": "automation.md",
+        "kind": "markdown-report",
+        "minBytes": 900,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "automation.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "automation.md",
+            "pattern": "DRY_RUN_OK|dry-run|dry run",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "automation.md",
+            "pattern": "fake-ci|fake-github|/api/bookings",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "automation.md",
+            "pattern": "no real|credentials|safety|guard",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "automation.md",
+            "pattern": "success|failure|retry|abort",
+            "flags": "i"
+          }
+        ]
+      }
+    ],
+    "mocks": [
+      {
+        "service": "ops",
+        "minRequests": 2,
+        "requiredPaths": [
+          "^/api/bookings/open$",
+          "^/api/bookings/dry-run$"
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "automation.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "safety",
+        "description": "Dry-run posture is explicit: no real credentials, clear stop-before-side-effect boundary."
+      },
+      {
+        "name": "mapping",
+        "description": "Fake endpoints/commands are mapped completely to the workflow steps."
+      },
+      {
+        "name": "signals",
+        "description": "Success, failure, retry, and abort conditions are all defined."
+      },
+      {
+        "name": "containment",
+        "description": "The plan cannot accidentally reach a real service from a mock context."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "dry-run safety",
+    "fake tool mapping",
+    "side-effect containment"
+  ],
+  "extensions": {
+    "legacySimulators": [
+      {
+        "id": "scrape-to-structured-fake-service-fixture",
+        "kind": "data-source",
+        "status": "implemented",
+        "description": "Seeded local fake service contract replacing live CLIs, HTTP APIs, credentials, and side effects."
+      }
+    ]
+  }
+}