npm - @bendyline/gilde - Versions diffs - 0.1.51 → 0.1.53 - Mend

@bendyline/gilde 0.1.51 → 0.1.53

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (585) hide show

package/data/craftbook-templates/pl/playtest-report/versions/1.0.3/test.json ADDED Viewed

@@ -0,0 +1,111 @@
+{
+  "schemaVersion": 1,
+  "title": "Playtest Report — repros, ranks, and the score-loop verdict",
+  "objective": "Measure whether the playtest-report craftbook finds the seeded flaws in a small arcade game (score not resetting between rounds; input handler stacking across restarts) and writes them up with repro steps in a ranked issue table.",
+  "tags": [
+    "corpus"
+  ],
+  "prompt": "can you playtest the arcade game properly before i send it to my freinds? write up whatever you find",
+  "setup": {
+    "projectName": "Star Catcher Arcade",
+    "about": "Web arcade project. The game under test is workspace/index.html; the playtest plan and notes go under workspace/notes and the findings to workspace/report.md.",
+    "missionObjectives": "A structured playtest with evidence: every finding carries repro steps, findings are ranked by player impact, and the score loop across game over and restart gets an explicit verdict. No live services, no real credentials.",
+    "files": [
+      {
+        "path": "index.html",
+        "content": "<!DOCTYPE html>\n<html lang=\"en\">\n<head>\n<meta charset=\"utf-8\">\n<title>Star Catcher</title>\n<style>\n  body { margin: 0; background: #101020; color: #eee; font-family: monospace;\n         display: flex; flex-direction: column; align-items: center; }\n  h1 { font-size: 18px; margin: 12px 0 4px; }\n  canvas { border: 1px solid #334; background: #181830; }\n  p { font-size: 12px; color: #99a; }\n</style>\n</head>\n<body>\n<h1>Star Catcher</h1>\n<canvas id=\"game\" width=\"480\" height=\"560\"></canvas>\n<p>Arrow keys to move the basket. Catch stars, miss three and it's over. Enter to restart.</p>\n<script>\nvar canvas = document.getElementById('game');\nvar ctx = canvas.getContext('2d');\nvar W = canvas.width, H = canvas.height;\n\nvar basket, stars, score = 0, missed, over, spawnTimer;\n\nfunction onKey(e) {\n  if (over) {\n    if (e.key === 'Enter') startGame();\n    return;\n  }\n  if (e.key === 'ArrowLeft') basket.x -= 24;\n  if (e.key === 'ArrowRight') basket.x += 24;\n  basket.x = Math.max(basket.w / 2, Math.min(W - basket.w / 2, basket.x));\n}\n\nfunction startGame() {\n  basket = { x: W / 2, y: H - 40, w: 64, h: 16 };\n  stars = [];\n  missed = 0;\n  over = false;\n  spawnTimer = 0;\n  document.addEventListener('keydown', onKey);\n}\n\nfunction spawnStar() {\n  stars.push({ x: 16 + Math.random() * (W - 32), y: -10, vy: 1.4 + Math.random() * 1.8 });\n}\n\nfunction update() {\n  if (over) return;\n  spawnTimer -= 1;\n  if (spawnTimer <= 0) {\n    spawnStar();\n    spawnTimer = 50;\n  }\n  for (var i = stars.length - 1; i >= 0; i--) {\n    var s = stars[i];\n    s.y += s.vy;\n    if (s.y > basket.y - 6 && s.y < basket.y + basket.h &&\n        Math.abs(s.x - basket.x) < basket.w / 2 + 6) {\n      stars.splice(i, 1);\n      score += 10;\n      continue;\n    }\n    if (s.y > H + 10) {\n      stars.splice(i, 1);\n      missed += 1;\n      if (missed >= 3) over = true;\n    }\n  }\n}\n\nfunction draw() {\n  ctx.clearRect(0, 0, W, H);\n  ctx.fillStyle = '#ffd75e';\n  for (var i = 0; i < stars.length; i++) {\n    var s = stars[i];\n    ctx.beginPath();\n    ctx.arc(s.x, s.y, 6, 0, Math.PI * 2);\n    ctx.fill();\n  }\n  ctx.fillStyle = '#7ec8ff';\n  ctx.fillRect(basket.x - basket.w / 2, basket.y, basket.w, basket.h);\n  ctx.fillStyle = '#eee';\n  ctx.font = '16px monospace';\n  ctx.fillText('Score: ' + score, 12, 24);\n  ctx.fillText('Missed: ' + missed + '/3', 12, 44);\n  if (over) {\n    ctx.font = '26px monospace';\n    ctx.fillText('GAME OVER', W / 2 - 70, H / 2 - 10);\n    ctx.font = '14px monospace';\n    ctx.fillText('Press Enter to play again', W / 2 - 96, H / 2 + 16);\n  }\n}\n\nfunction loop() {\n  update();\n  draw();\n  requestAnimationFrame(loop);\n}\n\nstartGame();\nloop();\n</script>\n</body>\n</html>\n"
+      }
+    ],
+    "worker": {
+      "name": "Roos",
+      "role": "Reviewer"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "tasks/eval/report.md is a ranked, repro-backed playtest report that catches the restart flaws — the score carrying over between rounds and the stacking input handler.",
+    "deliverables": [
+      {
+        "path": "tasks/eval/report.md",
+        "kind": "markdown-report",
+        "minBytes": 1200,
+        "checks": [
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+            "flags": "i"
+          },
+          {
+            "kind": "tableShape",
+            "file": "tasks/eval/report.md",
+            "requiredColumns": [
+              "Issue",
+              "Severity"
+            ],
+            "minRows": 1
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "repro|steps",
+            "flags": "i",
+            "label": "repros attached"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "score",
+            "flags": "i",
+            "label": "score loop covered"
+          },
+          {
+            "kind": "contains",
+            "file": "tasks/eval/report.md",
+            "pattern": "restart|play again|enter",
+            "flags": "i",
+            "label": "the restart path was exercised"
+          },
+          {
+            "kind": "judge",
+            "file": "tasks/eval/report.md",
+            "rubric": "Findings are specific and reproducible — concrete steps a stranger could follow — and ranked by player impact; the report catches that restarting does not reset the score and that input handling degrades across restarts.",
+            "sourceFiles": [
+              "index.html"
+            ],
+            "label": "finding quality"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "tasks/eval/report.md",
+      "kind": "markdown"
+    },
+    "axes": [
+      {
+        "name": "rigor",
+        "description": "The plan's mechanics and edge inputs were actually exercised — passes recorded alongside failures."
+      },
+      {
+        "name": "repro quality",
+        "description": "Each finding's steps reproduce it exactly; observed and expected behavior are both stated."
+      },
+      {
+        "name": "prioritization",
+        "description": "The table ranks by what ruins a play session, not by discovery order."
+      },
+      {
+        "name": "player empathy",
+        "description": "The report reads like someone who played the game, and says what is already good."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "seeded-flaw detection",
+    "repro discipline",
+    "ranked issue table"
+  ]
+}

package/data/craftbook-templates/po/podcast-chaptering/versions/1.0.3/craftbook.json ADDED Viewed

@@ -0,0 +1,276 @@
+{
+  "id": "podcast-chaptering",
+  "name": "Podcast Chapters & Show Notes",
+  "description": "Turn a podcast episode into navigable chapter markers plus publish-ready show notes — timestamped chapter titles, an episode summary, key takeaways, and linked mentions. Scopes the chapter format and show-notes structure FIRST, analyzes the transcript to find real topic boundaries with timestamps, then writes the listener-facing notes in the show's voice. Separating boundary-detection (analysis) from the write-up (copy) is what yields chapters that land on actual topic shifts and notes that read like a human wrote them.\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 chapters & notes (planner) — chapter format, count, show-notes sections, voice → gated on artifact `{{workPath}}/scope.md` (markdown-notes)\n2. Find chapter boundaries (developer) — detect topic shifts, assign timestamps + titles → gated on artifact `{{workPath}}/chapters.json` (json)\n3. Write show notes (copywriter) — summary, takeaways, chapter list, links in the show voice → gated on `show-notes.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": [
+    "podcast chapters",
+    "chapter markers for my episode",
+    "write show notes",
+    "timestamp my podcast",
+    "episode summary and chapters"
+  ],
+  "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 chapters & notes",
+      "description": "chapter format, count, show-notes sections, voice",
+      "prompt": "Define the deliverable BEFORE analyzing. Step 1: record the source (episode title, transcript path or audio, duration). Step 2: pick the chapter marker format — the widely-supported `HH:MM:SS Title` lines (Apple/YouTube style), where the FIRST chapter must be `00:00:00`. Step 3: set chapter density (e.g. 5-12 chapters, min ~60s apart, titles ≤ ~40 chars). Step 4: define the show-notes structure: one-paragraph episode summary, 3-6 key takeaways, the timestamped chapter list, and a 'mentioned in this episode' links list. Step 5: capture the show's voice. Write an acceptance-criteria checklist (first chapter is 00:00:00, timestamps monotonic and within duration, titles concise and descriptive, notes have all four sections, every claim traces to the transcript) and decisions to `{{workPath}}/scope.md` via write_task_note AND to 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": "analyze",
+      "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": "analyze",
+      "name": "Find chapter boundaries",
+      "description": "detect topic shifts, assign timestamps + titles",
+      "prompt": "Find where topics actually change. Step 1: read the transcript with its timestamps. Step 2: detect topic boundaries — points where the subject clearly shifts (new question, new segment, ad break, guest change) — not arbitrary fixed intervals. Step 3: for each boundary record the start timestamp (rounded to the second) and a short descriptive title; force the first to `00:00:00`. Step 4: enforce the scoped density/spacing/title-length rules, merging boundaries that are too close. Step 5: write the structured chapter list to `{{workPath}}/chapters.json` (each: start `HH:MM:SS`, title, a one-line topic note) via write_task_note AND the produces path so the writer has structured input. On a loop-back, adjust only the flagged boundaries.\n\nThe deliverable `{{workPath}}/chapters.json` 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": "developer",
+      "advanceWhen": {
+        "file": "{{workPath}}/chapters.json",
+        "minBytes": 1,
+        "sniff": "json-valid",
+        "artifact": true
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "{{workPath}}/chapters.json",
+            "bytes": 2,
+            "artifact": true
+          }
+        ],
+        "onReject": "analyze",
+        "maxAttempts": 3
+      },
+      "next": "write",
+      "toolPolicy": {
+        "disallowBuiltinToolsets": [
+          "ai-apps",
+          "archives",
+          "audio",
+          "browser-automation",
+          "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": "write",
+      "name": "Write show notes",
+      "description": "summary, takeaways, chapter list, links in the show voice",
+      "prompt": "Write the publish-ready notes from the analysis. Step 1: open with a one-paragraph episode summary in the show's voice. Step 2: list 3-6 key takeaways as tight bullets. Step 3: render the chapter list as plain `HH:MM:SS Title` lines (paste-ready into a podcast host / YouTube description) directly from `{{workPath}}/chapters.json`, first line `00:00:00`. Step 4: add a 'Mentioned in this episode' section with the people/links/resources referenced. Step 5: assemble all of it into `show-notes.md` with clear section headers. Do not invent facts not in the transcript. write_task_note the path and chapter count. On a loop-back, fix only the flagged sections.\n\nBefore working, open the artifact input `{{workPath}}/chapters.json` with `read_artifact`; do not look for it in the workspace.",
+      "suggestedRole": "copywriter",
+      "consumes": [
+        {
+          "file": "{{workPath}}/chapters.json",
+          "artifact": true
+        }
+      ],
+      "advanceWhen": {
+        "file": "show-notes.md",
+        "minBytes": 1,
+        "sniff": "nonempty"
+      },
+      "gate": {
+        "at": "completion",
+        "checks": [
+          {
+            "kind": "minBytes",
+            "file": "show-notes.md",
+            "bytes": 500
+          }
+        ],
+        "scripts": [
+          {
+            "name": "checkContains",
+            "scope": "standard",
+            "inputs": {
+              "file": "show-notes.md",
+              "pattern": "(?:^|\\n)#{1,3}\\s+\\S",
+              "flags": "i"
+            }
+          }
+        ],
+        "onReject": "write",
+        "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"
+        ],
+        "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": "Check the chapters and notes. Step 1: confirm the chapter list's FIRST line is `00:00:00` and all timestamps are monotonic, spaced per scope, and within the episode duration (PASS/FAIL). Step 2: spot-check 3 chapter timestamps against the transcript — does each land on a real topic shift? Step 3: confirm show-notes.md has all four sections (summary, takeaways, chapters, mentions). Step 4: confirm claims trace to the transcript (nothing invented) and the voice matches the show. Step 5: confirm titles are concise and descriptive. Write PASS/FAIL per criterion.\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": "show-notes.md"
+        }
+      ],
+      "next": "write",
+      "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"
+}

package/data/craftbook-templates/po/podcast-chaptering/versions/1.0.3/test.json ADDED Viewed

@@ -0,0 +1,103 @@
+{
+  "schemaVersion": 1,
+  "title": "Podcast Chapters & Show Notes smoke eval",
+  "objective": "Self-contained smoke eval for the Podcast Chapters & Show Notes craftbook using the media generic harness.",
+  "tags": [
+    "media"
+  ],
+  "prompt": "Our media files are all listd in source/media-index.csv. Can you put together the production plan for them as media-plan.json?",
+  "setup": {
+    "projectName": "Podcast Chapters & Show Notes Eval",
+    "about": "Self-contained eval project for podcast-chaptering. Seeded inputs are under workspace/source or workspace/fixtures; final deliverable is workspace/media-plan.json.",
+    "missionObjectives": "Use the Podcast Chapters & Show Notes craftbook/template, read the seeded local fixtures, and write media-plan.json without network calls, real credentials, or live services.",
+    "files": [
+      {
+        "path": "source/brief.md",
+        "content": "# Podcast Chapters & Show Notes 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: podcast-chaptering - Podcast Chapters & Show Notes.\n"
+      },
+      {
+        "path": "source/media-index.csv",
+        "content": "filename,type,duration_or_size,notes\npilot-interview.wav,audio,00:02:15,mentions response time and status silence\nreturns-desk.png,image,1600x900,shows intake form and photo evidence step\nlaunch-clip.mp4,video,00:01:05,shows barcode exception handling\n"
+      }
+    ],
+    "worker": {
+      "name": "Jules",
+      "role": "Producer"
+    }
+  },
+  "mocks": [],
+  "success": {
+    "summary": "media-plan.json is a valid JSON media-production manifest grounded in seeded fixture metadata.",
+    "deliverables": [
+      {
+        "path": "media-plan.json",
+        "kind": "json",
+        "minBytes": 700,
+        "checks": [
+          {
+            "kind": "sniff",
+            "file": "media-plan.json",
+            "sniff": "json-valid"
+          },
+          {
+            "kind": "contains",
+            "file": "media-plan.json",
+            "pattern": "pilot-interview\\.wav|returns-desk\\.png|launch-clip\\.mp4",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "media-plan.json",
+            "pattern": "outputs|assets|steps|cues|verification",
+            "flags": "i"
+          },
+          {
+            "kind": "contains",
+            "file": "media-plan.json",
+            "pattern": "accessibility|alt|caption|transcript|metadata",
+            "flags": "i"
+          }
+        ]
+      }
+    ]
+  },
+  "rubric": {
+    "artifact": {
+      "path": "media-plan.json",
+      "kind": "json"
+    },
+    "axes": [
+      {
+        "name": "completeness",
+        "description": "The manifest covers sources, outputs, and processing steps end to end."
+      },
+      {
+        "name": "grounding",
+        "description": "Only seeded media fixtures are referenced, with faithful metadata."
+      },
+      {
+        "name": "accessibility",
+        "description": "Alt text, captions, or transcripts are planned wherever the class requires."
+      },
+      {
+        "name": "precision",
+        "description": "Timestamps, crops, and cues are specific enough to execute."
+      }
+    ]
+  },
+  "qualityFocus": [
+    "media fixture handling",
+    "structured manifest",
+    "verification metadata"
+  ],
+  "extensions": {
+    "legacySimulators": [
+      {
+        "id": "podcast-chaptering-media-fixtures",
+        "kind": "data-source",
+        "status": "implemented",
+        "description": "Seeded local media index replacing real audio, video, image generation, and external media metadata services."
+      }
+    ]
+  }
+}