@bendyline/gilde 0.1.50 → 0.1.52

package/data/craftbook-templates/in/incident-comms-templates/versions/1.0.3/test.json

@@ -0,0 +1,110 @@
+{
+  "schemaVersion": 1,
+  "title": "Incident Communication Templates smoke eval",
+  "objective": "Self-contained smoke eval for the Incident Communication Templates craftbook using the corpus generic harness.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "We need a incident communication templates 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": "Incident Communication Templates Eval",
+    "about": "Self-contained eval project for incident-comms-templates. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/report.md.",
+    "missionObjectives": "Use the Incident Communication Templates 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": "# Incident Communication Templates 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: incident-comms-templates - Incident Communication Templates.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Writer"
+    }
+  },
+  "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/in/incident-postmortem/versions/1.0.2/test.json

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

package/data/craftbook-templates/in/incident-postmortem/versions/1.0.3/craftbook.json

@@ -0,0 +1,288 @@
+{
+  "id": "incident-postmortem",
+  "name": "Incident Postmortem",
+  "description": "Write a blameless incident postmortem after a production outage or degradation — a structured, factual document covering the impact, a precise timeline (detection → diagnosis → mitigation → resolution), the root cause and contributing factors via a five-whys analysis, what went well and what went poorly, and concrete, owned, dated action items that prevent recurrence. A researcher assembles the verified timeline and evidence from logs/alerts/chat, a copywriter writes the blameless narrative and root-cause analysis, and a reviewer checks the timeline is accurate, the analysis reaches a true root cause, and every action item is specific and owned. Use this for outage retrospectives, severity-incident reviews, and any 'what happened and how do we prevent it' writeup.\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. Assemble the timeline (researcher) — build a verified, timestamped factual timeline → gated on artifact `{{workPath}}/timeline.md` (markdown-notes)\n2. Write the postmortem (copywriter) — blameless narrative, root-cause, and owned action items → gated on artifact `{{workPath}}/postmortem.md` (markdown-report)\n3. Review for accuracy and blamelessness (reviewer) — check root cause, timeline fidelity, and action quality → gated on artifact `{{workPath}}/review.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": "timeline",
+  "triggers": [
+    "write a postmortem",
+    "incident retrospective",
+    "outage writeup",
+    "root cause analysis",
+    "post-incident review"
+  ],
+  "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": "timeline",
+      "name": "Assemble the timeline",
+      "description": "build a verified, timestamped factual timeline",
+      "prompt": "1. Gather the raw record of the incident from every available source: alerts, monitoring graphs, deploy log, incident chat, error logs, and any commands run. 2. Reconstruct a precise, timestamped timeline of key moments: first impact, detection/alert, acknowledgement, diagnosis milestones, the mitigation action, full resolution, and the all-clear. 3. Quantify the impact factually: duration, who/what was affected, magnitude (error rate, users, revenue if known). 4. Note the detection method (alert vs customer report) and time-to-detect / time-to-mitigate. 5. Keep this BLAMELESS and factual — what happened and when, not who is at fault. 6. Good looks like: a chronological, timestamped timeline whose every entry is backed by evidence, plus a quantified impact statement. Write an acceptance-criteria checklist ('timeline is timestamped and chronological', 'impact is quantified with duration and scope', 'detection and mitigation times are stated', 'analysis must reach a true root cause via five-whys', 'every action item must be specific, owned, and dated', 'tone stays blameless') plus the timeline and impact to the notes file via write_task_note AND to {{workPath}}/timeline.md.\n\nThe deliverable `{{workPath}}/timeline.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": "researcher",
+      "advanceWhen": {
+        "file": "{{workPath}}/timeline.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/timeline.md",
+            "bytes": 120,
+            "artifact": true
+          },
+          {
+            "kind": "sniff",
+            "file": "{{workPath}}/timeline.md",
+            "sniff": "nonempty",
+            "artifact": true
+          }
+        ],
+        "onReject": "timeline",
+        "maxAttempts": 3
+      },
+      "next": "write",
+      "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",
+          "workspace-fs-write"
+        ],
+        "outputMedium": "artifact",
+        "additionalOutputMedia": [
+          "task-note"
+        ]
+      }
+    },
+    {
+      "id": "write",
+      "name": "Write the postmortem",
+      "description": "blameless narrative, root-cause, and owned action items",
+      "prompt": "1. Open {{workPath}}/timeline.md and write the postmortem with standard sections: Summary, Impact, Timeline, Root Cause, Contributing Factors, What Went Well, What Went Poorly, and Action Items. 2. In Root Cause, run a five-whys (or equivalent) from the symptom down to the systemic cause — not 'human made a mistake' but the system that allowed the mistake to cause an outage. 3. Keep the entire document BLAMELESS: describe systems and decisions, never blame individuals. 4. Make each Action Item concrete, with an explicit owner and a due date, and tied to a contributing factor — preventing recurrence, not vague 'be more careful'. 5. Lead with a tight executive Summary (what happened, impact, status) readable in 30 seconds. 6. Good looks like: a factual, blameless document where the root cause is systemic, the timeline matches {{workPath}}/timeline.md, and every action item is specific/owned/dated. Write the postmortem to {{workPath}}/postmortem.md.\n\nBefore working, open the artifact input `{{workPath}}/timeline.md` with `read_artifact`; do not look for it in the workspace.\n\nThe deliverable `{{workPath}}/postmortem.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": "copywriter",
+      "consumes": [
+        {
+          "file": "{{workPath}}/timeline.md",
+          "artifact": true
+        }
+      ],
+      "advanceWhen": {
+        "file": "{{workPath}}/postmortem.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/postmortem.md",
+            "bytes": 1500,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/postmortem.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i",
+            "label": "at least one markdown heading",
+            "artifact": true
+          }
+        ],
+        "onReject": "write",
+        "maxAttempts": 3
+      },
+      "next": "review",
+      "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"
+      }
+    },
+    {
+      "id": "review",
+      "name": "Review for accuracy and blamelessness",
+      "description": "check root cause, timeline fidelity, and action quality",
+      "prompt": "1. Open {{workPath}}/postmortem.md and cross-check its Timeline against {{workPath}}/timeline.md — every entry must be accurate and evidence-backed, nothing invented or reordered. 2. Pressure-test the Root Cause: does the five-whys actually reach a SYSTEMIC cause, or does it stop at 'someone erred'? If it stops short, it fails. 3. Verify the document is genuinely blameless — flag any individual-blaming language. 4. Audit each Action Item: is it specific, does it have an owner and a due date, and would it actually reduce recurrence of THIS class of incident? 5. Confirm Impact is quantified and the Summary is tight and accurate. 6. Write a PASS/FAIL per acceptance criterion with specifics; any failure routes back to the write phase. Write findings to {{workPath}}/review.md.\n\nBefore working, open the artifact inputs `{{workPath}}/timeline.md`, `{{workPath}}/postmortem.md` with `read_artifact`; do not look for them in the workspace.\n\nThe deliverable `{{workPath}}/review.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",
+      "consumes": [
+        {
+          "file": "{{workPath}}/timeline.md",
+          "artifact": true
+        },
+        {
+          "file": "{{workPath}}/postmortem.md",
+          "artifact": true
+        }
+      ],
+      "advanceWhen": {
+        "file": "{{workPath}}/review.md",
+        "minBytes": 1,
+        "sniff": "nonempty",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/postmortem.md",
+            "bytes": 1500,
+            "artifact": true
+          },
+          {
+            "kind": "contains",
+            "file": "{{workPath}}/postmortem.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i",
+            "label": "at least one markdown heading",
+            "artifact": true
+          }
+        ],
+        "onReject": "review",
+        "maxAttempts": 4
+      },
+      "next": "evaluate",
+      "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"
+      }
+    },
+    {
+      "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}}/postmortem.md and verify it against the criteria in {{workPath}}/timeline.md, PASS/FAIL each. Confirm: (a) it has Summary, Impact, Timeline, Root Cause, Contributing Factors, What Went Well/Poorly, and Action Items sections; (b) the timeline is chronological, timestamped, and matches the assembled evidence; (c) impact is quantified (duration + scope); (d) the root-cause analysis reaches a systemic cause via five-whys, not individual blame; (e) the document is blameless throughout; (f) every action item is specific, owned, and dated, and addresses a contributing factor. Any FAIL routes back to the write phase.\n\nThe deliverable lives in the project's artifacts drawer — open `{{workPath}}/postmortem.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: \"write\" })` 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}}/postmortem.md",
+          "artifact": true
+        }
+      ],
+      "next": "write",
+      "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": "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"
+}

package/data/craftbook-templates/in/incident-postmortem/versions/1.0.3/test.json

@@ -0,0 +1,109 @@
+{
+  "schemaVersion": 1,
+  "title": "Evidence-grounded incident postmortem",
+  "objective": "Measure whether a postmortem craftbook keeps a local model grounded in a dense evidence pack and produces ordered SRE sections.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "Theres a fake service set up for this so nothing real gets touched — details are in fixtures/fake-service.md. Can you work out the automation and write up how it woudl run in automation.md?",
+  "setup": {
+    "projectName": "Incident Postmortem Eval",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Incident Postmortem 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: incident-postmortem - Incident Postmortem.\n"
+      },
+      {
+        "path": "fixtures/fake-service.md",
+        "content": "# Fake Service Fixture\n\nThis eval must stay in dry-run mode.\n\nAvailable fake endpoints and commands:\n- GET /api/bookings/open returns BKG-1001, BKG-1002, BKG-1003.\n- POST /api/bookings/dry-run records a simulated submission and returns DRY_RUN_OK.\n- fake-ci status returns pending twice and success on the third poll.\n- fake-github pr create returns https://example.invalid/pull/42.\n\nThe deliverable must reference these fixture names instead of real services or credentials.\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Developer"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "The hand-authored incident-postmortem grader seeds five evidence files and checks ordered sections, evidence citations, timestamp citations, size, and blame-free language.",
+    "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"
+          }
+        ]
+      }
+    ]
+  },
+  "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": [
+    "dense reading",
+    "evidence grounding",
+    "ordered report structure",
+    "repair nudges"
+  ],
+  "extensions": {
+    "legacySimulators": [
+      {
+        "id": "incident-postmortem-fake-service-fixture",
+        "kind": "data-source",
+        "status": "implemented",
+        "description": "Seeded local fake service contract replacing live CLIs, HTTP APIs, credentials, and side effects."
+      }
+    ]
+  }
+}

package/data/craftbook-templates/in/insurance-inventory/versions/1.0.2/test.json

@@ -19,9 +19,6 @@
     "worker": {
       "name": "Casper",
       "role": "Curator"
-    },
-    "craftbookParams": {
-      "workPath": "tasks/eval"
     }
   },
   "mocks": [],