@bendyline/gilde 0.1.37 → 0.1.39

package/data/craftbook-templates/we/weekly-pipeline-review/versions/1.0.2/test.json

@@ -0,0 +1,107 @@
+{
+  "schemaVersion": 1,
+  "title": "Weekly Pipeline Review smoke eval",
+  "objective": "Self-contained smoke eval for the Weekly Pipeline Review 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": "Weekly Pipeline Review Eval",
+    "about": "Self-contained eval project for weekly-pipeline-review. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/analysis.md.",
+    "missionObjectives": "Use the Weekly Pipeline Review 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": "# Weekly Pipeline Review 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: weekly-pipeline-review - Weekly Pipeline Review.\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": "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/we/weekly-review/versions/1.0.2/craftbook.json

@@ -0,0 +1,119 @@
+{
+  "id": "weekly-review",
+  "name": "Personal / Team Weekly Review",
+  "description": "Assemble a reflective weekly review that pulls the week's done-list, metrics, and open loops into a structured retrospective with wins, misses, lessons, and next-week priorities. Scopes the review template and the inputs FIRST (the GTD-style sections, what data feeds each, the carry-over rule for unfinished items), then a copywriter writes the honest, concise review against that template. The scope-first ordering keeps the review consistent week over week and ensures open loops are carried forward rather than forgotten. Use for weekly reviews, personal retrospectives, GTD weekly review, end-of-week wrap-ups, and team retros.\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 review (planner) — lock the template, inputs, and carry-over rule → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Assemble the review (copywriter) — write the honest, grounded review to the template → gated on `review.md` (markdown-doc)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "scope",
+  "triggers": [
+    "weekly review",
+    "personal retro",
+    "end of week wrap-up",
+    "GTD weekly review",
+    "team retrospective"
+  ],
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the review",
+      "description": "lock the template, inputs, and carry-over rule",
+      "prompt": "Define the review structure before writing. (1) Lock the section template — This week's wins / Misses & what slipped / Metrics & progress / Lessons learned / Open loops carried forward / Next week's top 3 priorities. (2) Name the inputs feeding each section (completed tasks, the prior review's priorities, tracked metrics, {{workPath}}/journal). (3) Lock the carry-over rule: every item that was a priority last week and is still open MUST appear in Open loops and be explicitly resolved or re-prioritized — nothing silently dropped. (4) Set tone (honest, concise, first-person or team) and the reporting week. Write an acceptance-criteria checklist ('every template section present', 'wins and misses both populated honestly', 'last week\\'s open priorities each accounted for', 'next week is exactly three concrete priorities', 'grounded in real inputs, not generic') plus the template + input map to {{workPath}}/scope.md via write_task_note AND the produces path.\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": "assemble"
+    },
+    {
+      "id": "assemble",
+      "name": "Assemble the review",
+      "description": "write the honest, grounded review to the template",
+      "prompt": "Write review.md following the locked template, grounded in the named inputs. (1) Wins: specific, completed things — names and numbers, not vibes. (2) Misses & slipped: honest, with a one-line why each. (3) Metrics & progress: this-week values vs prior where available. (4) Lessons learned: 2-4 concrete takeaways tied to the wins/misses. (5) Open loops: apply the carry-over rule — list every still-open prior priority and mark it resolved, dropped (with reason), or carried. (6) Next week: EXACTLY three concrete, outcome-shaped priorities. Keep it tight and skimmable; invent no accomplishments. On a loop-back fix only the flagged sections. Write the path and a confirmation that all sections + the three priorities are present to notes via write_task_note.",
+      "suggestedRole": "copywriter",
+      "advanceWhen": {
+        "file": "review.md",
+        "minBytes": 1,
+        "sniff": "nonempty"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "review.md",
+            "bytes": 500
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkContains",
+            "scope": "standard",
+            "inputs": {
+              "file": "review.md",
+              "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+              "flags": "i"
+            }
+          }
+        ],
+        "onReject": "assemble",
+        "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": "QA review.md against the locked criteria. (1) Confirm every template section is present and in order. (2) Confirm wins and misses are both populated with specific, non-generic items grounded in the inputs. (3) Apply the carry-over check: every open priority from last week's inputs is accounted for in Open loops (resolved/dropped/carried) — FAIL on any silent drop. (4) Confirm Next week is exactly three concrete priorities. (5) Spot-check 2-3 wins/metrics against the inputs for honesty. Write PASS/FAIL per criterion with specifics.\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: \"assemble\" })` 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": "review.md"
+        }
+      ],
+      "next": "assemble"
+    },
+    {
+      "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/we/weekly-review/versions/1.0.2/test.json

@@ -0,0 +1,113 @@
+{
+  "schemaVersion": 1,
+  "title": "Personal / Team Weekly Review smoke eval",
+  "objective": "Self-contained smoke eval for the Personal / Team Weekly Review craftbook using the corpus generic harness.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "We need a personal / team weekly review for the returns-desk work. The backgound info is in source/brief.md — have a look and write it up in report.md.",
+  "setup": {
+    "projectName": "Personal / Team Weekly Review Eval",
+    "about": "Self-contained eval project for weekly-review. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/report.md.",
+    "missionObjectives": "Use the Personal / Team Weekly Review craftbook/template, read the seeded local fixtures, and write report.md without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Personal / Team Weekly Review 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: weekly-review - Personal / Team Weekly Review.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Writer"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "report.md is a source-grounded markdown artifact with required facts and actions.",
+    "deliverables": [
+      {
+        "path": "report.md",
+        "kind": "markdown-report",
+        "minBytes": 1000,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "source/brief\\.md|Brief",
+            "flags": "i",
+            "label": "cite or name the seeded source"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "18\\b[\\s\\S]{0,30}\\bSKUs",
+            "flags": "i",
+            "label": "include the 18-SKU pilot scope"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "18\\s*hours|6\\s*hours",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "14\\.2%|8\\.9%",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "status silence|photo submission",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "report.md",
+            "pattern": "automated status emails|barcode|Finance",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "report.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": [
+    "source-grounded prose",
+    "section structure",
+    "next-action clarity"
+  ]
+}

package/data/craftbook-templates/we/weekly-walkthrough/versions/1.0.2/craftbook.json

@@ -0,0 +1,152 @@
+{
+  "id": "weekly-walkthrough",
+  "name": "Weekly Garden Walkthrough",
+  "description": "Walk the beds once a week with a plan instead of a vague worry: what each bed needs this week derived from the plantings and the season, the walkthrough ordered so it actually gets done, and the observations and harvests logged so the almanac accrues. Locks the week's due list FIRST, then plans the route, then logs what happened and seeds next week. Use for weekly garden walkthroughs, 'what does the garden need this week', weekend garden sessions, and garden check-ins.\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 week (gardener) — per-bed due list from the plantings and the season → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Plan the walkthrough (planner) — ordered route, per-bed tasks, supplies gathered first → gated on artifact `{{workPath}}/plan.md` (markdown-notes)\n3. Log the walkthrough (gardener) — observations and harvests logged, week written up, next week seeded → gated on artifact `{{workPath}}/report.md` (markdown-report)\n\nThe gates never advance with an unmet criterion, and loop back to the\nowning phase to fix named gaps.\n",
+  "entryStepId": "scope",
+  "triggers": [
+    "weekly garden walkthrough",
+    "what does the garden need this week",
+    "garden check-in",
+    "walk the beds",
+    "weekend garden session"
+  ],
+  "steps": [
+    {
+      "id": "scope",
+      "name": "Scope the week",
+      "description": "per-bed due list from the plantings and the season",
+      "prompt": "Define the week before walking anywhere. Step 1: read garden.json from the workspace — the beds, what is planted where and since when, and the season parameters — plus the recent entries in journal.json and anything the owner has already reported. Step 2: derive what each bed needs this week from the plantings and the season — watering, feeding, thinning, staking, harvest windows opening or closing — tied to a specific planting, not generic garden advice. Step 3: split the list into this-week-or-it-matters versus can-wait. Step 4: write an acceptance-criteria checklist ('every bed considered, even the ones needing nothing', 'each due task tied to a planting or the season', 'observations and harvests logged so the almanac accrues', 'next week seeded in one line'). Call write_task_note with the due counts + checklist and write {{workPath}}/scope.md.\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": "gardener",
+      "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": "plan"
+    },
+    {
+      "id": "plan",
+      "name": "Plan the walkthrough",
+      "description": "ordered route, per-bed tasks, supplies gathered first",
+      "prompt": "Plan the walkthrough from the locked list. Step 1: order the beds into a sensible route and lay out the per-bed tasks so the owner can walk it without stopping to think. Step 2: for each task, one concrete line — what to do and what to bring. Step 3: batch the supplies into one gather-first line at the top. Step 4: leave room for what the walk itself turns up — the plan is a spine, not a cage. Write the ordered plan to {{workPath}}/plan.md and call write_task_note with the task count.\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": "log"
+    },
+    {
+      "id": "log",
+      "name": "Log the walkthrough",
+      "description": "observations and harvests logged, week written up, next week seeded",
+      "prompt": "Close the walkthrough once the owner reports what happened. Step 1: log each observation and harvest into the project's garden journal so the almanac accrues — dated and tied to its bed. Step 2: note what was done, what was deferred and why. Step 3: write {{workPath}}/report.md — the week in a few lines per bed: done, observed, deferred; anything spotted that needs watching; and next week's earliest due task as the closing line. Keep it warm and specific — this is the almanac's weekly page, not a chore-list autopsy. Call write_task_note with the done/observed/deferred counts.\n\nThe deliverable `{{workPath}}/report.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": "gardener",
+      "advanceWhen": {
+        "file": "{{workPath}}/report.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/report.md",
+            "bytes": 1000,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i",
+            "label": "at least one markdown heading",
+            "artifact": true
+          }
+        ],
+        "onReject": "log",
+        "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 {{workPath}}/report.md, {{workPath}}/plan.md, and the garden journal and verify every criterion from {{workPath}}/scope.md: every bed appears in the report, each planned task traces to a planting or the season, every observation and harvest the owner reported was logged with a date (spot-check the journal), deferrals carry reasons, and next week's seed line is present. Write PASS/FAIL per criterion; on any failure, name the gap and loop back to log.\n\nThe deliverable lives in the project's artifacts drawer — open `{{workPath}}/report.md` with `read_artifact`, not `read_file`.\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: \"log\" })` 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": "{{workPath}}/report.md",
+          "artifact": true
+        }
+      ],
+      "next": "log"
+    },
+    {
+      "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/we/weekly-walkthrough/versions/1.0.2/test.json

@@ -0,0 +1,141 @@
+{
+  "schemaVersion": 1,
+  "title": "Weekly Garden Walkthrough smoke eval",
+  "objective": "Task-specific eval for the Weekly Garden Walkthrough craftbook: a four-bed due list derived from the plantings, the owner's reported observations logged to the journal, and a warm weekly page with next week seeded.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "saturday garden time — whats due this week? walked through and the tomatos have some yellow leaves, two zuchini ready. write it up",
+  "setup": {
+    "projectName": "Garden Almanac — Weekly Walkthrough Eval",
+    "about": "Self-contained eval project for weekly-walkthrough. The garden lives at garden.json in the workspace (beds, plantings, season parameters) and the almanac's journal at journal.json. The weekly page goes to tasks/eval/report.md.",
+    "missionObjectives": "Use the Weekly Garden Walkthrough craftbook/template, derive the week from the seeded garden.json, log the owner's reported observations to journal.json, and write tasks/eval/report.md — no network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "garden.json",
+        "content": "{\n  \"zone\": \"8b\",\n  \"lastFrost\": \"2026-04-05\",\n  \"firstFrost\": \"2026-11-05\",\n  \"beds\": [\n    {\n      \"name\": \"North Bed\",\n      \"plantings\": [\n        { \"plant\": \"tomatoes\", \"variety\": \"San Marzano\", \"planted\": \"2026-05-02\" },\n        { \"plant\": \"basil\", \"planted\": \"2026-05-16\" }\n      ]\n    },\n    {\n      \"name\": \"Back Fence Bed\",\n      \"plantings\": [\n        { \"plant\": \"zucchini\", \"planted\": \"2026-05-09\" },\n        { \"plant\": \"pole beans\", \"planted\": \"2026-05-20\" }\n      ]\n    },\n    {\n      \"name\": \"Herb Spiral\",\n      \"plantings\": [\n        { \"plant\": \"thyme\", \"planted\": \"2025-04-12\" },\n        { \"plant\": \"parsley\", \"planted\": \"2026-03-28\" }\n      ]\n    },\n    {\n      \"name\": \"Berry Corner\",\n      \"plantings\": [\n        { \"plant\": \"raspberries\", \"planted\": \"2024-03-15\" }\n      ]\n    }\n  ]\n}\n"
+      },
+      {
+        "path": "journal.json",
+        "content": "[\n  { \"date\": \"2026-07-05\", \"bed\": \"North Bed\", \"note\": \"first tomato truss set; tied main stems to the stakes\" },\n  { \"date\": \"2026-07-11\", \"bed\": \"Back Fence Bed\", \"note\": \"zucchini flowering heavily; beans reached the top wire\" }\n]\n"
+      }
+    ],
+    "worker": {
+      "name": "Wim",
+      "role": "Gardener"
+    },
+    "craftbookParams": {
+      "workPath": "tasks/eval"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "tasks/eval/report.md covers all four beds with season-grounded tasks, the yellow-leaf and zucchini observations land in the journal, and next week is seeded.",
+    "deliverables": [
+      {
+        "path": "tasks/eval/report.md",
+        "kind": "markdown-report",
+        "minBytes": 700,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "North Bed",
+            "label": "North Bed covered"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "Back Fence",
+            "label": "Back Fence Bed covered"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "Herb Spiral",
+            "label": "Herb Spiral covered"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "Berry Corner",
+            "label": "Berry Corner covered"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "yellow",
+            "flags": "i",
+            "label": "the reported yellow leaves are captured"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "zucchini",
+            "flags": "i",
+            "label": "the zucchini harvest is captured"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "next week",
+            "flags": "i",
+            "label": "next week seeded"
+          }
+        ]
+      }
+    ],
+    "checks": [
+      {
+        "kind": "recordSchema",
+        "file": "journal.json",
+        "fields": [
+          {
+            "name": "date",
+            "type": "iso-date"
+          },
+          {
+            "name": "note",
+            "type": "nonempty"
+          }
+        ],
+        "minRows": 3
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "tasks/eval/report.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "seasonality",
+        "description": "Tasks derive from the actual plantings, their dates, and mid-July in zone 8b — not generic garden advice."
+      },
+      {
+        "name": "specificity",
+        "description": "Each bed gets concrete, walkable tasks; nothing vague like 'tend the garden'."
+      },
+      {
+        "name": "observation-capture",
+        "description": "The owner's reported observations and harvests are logged dated and tied to their beds."
+      },
+      {
+        "name": "encouragement",
+        "description": "The weekly page reads warm and doable — an almanac entry, not a chore audit."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "planting-grounded due list",
+    "journal accrual",
+    "next-week seeding"
+  ]
+}