Bakeoff

card retest after redeploy

1 profile · Jul 16, 2026, 10:26 AM UTC

Profile

card-retest

failed · QA fail
arm hero_tierexemplar art card swiss-signal-redhero tier anthropic/claude-opus-4.8 → gpt-5.6-luna · High-Contrast Swiss: One overscale index numeral that crops at section edges and orders the conversion path.source fallbackregen 0
card-retestfailed
26,551 in22,996 out$0.5395 cost workflow wall211.6s LLM call time

publish QA blocked (1 violations)

StepProvider:modelEffortPrompt variantTokensCostStep wall time
planopenrouter:anthropic/claude-opus-4.8default
art_directionopenrouter:anthropic/claude-opus-4.8default
theme_emitopenrouter:anthropic/claude-opus-4.8landing12,536 / 17,229$0.4934179.8s
hero_continuationopenai:gpt-5.6-lunalowlanding7,374 / 3,216$0.026716.3s
page_generateanthropic:claude-opus-4-8default
honesty_repairanthropic:claude-opus-4-8default
honesty_judgeopenrouter:anthropic/claude-haiku-4.5default6,641 / 2,551$0.019415.5s
restyleopenrouter:anthropic/claude-opus-4.8default
Submitted profile JSON
{
  "name": "card-retest",
  "workflowMode": "hero_tier",
  "steps": {
    "plan": {
      "provider": "openrouter",
      "model": "anthropic/claude-opus-4.8"
    },
    "restyle": {
      "provider": "openrouter",
      "model": "anthropic/claude-opus-4.8"
    },
    "honesty_judge": {
      "provider": "openrouter",
      "model": "anthropic/claude-haiku-4.5"
    },
    "theme_emit": {
      "provider": "openrouter",
      "model": "anthropic/claude-opus-4.8",
      "promptVariant": "landing",
      "maxTokens": 7000,
      "timeoutMs": 300000
    },
    "hero_continuation": {
      "provider": "openai",
      "model": "gpt-5.6-luna",
      "effort": "low",
      "promptVariant": "landing",
      "maxTokens": 16000,
      "timeoutMs": 240000
    }
  }
}
Resolved run profile
[
  {
    "step": "plan",
    "role": "plan",
    "provider": "openrouter",
    "model": "anthropic/claude-opus-4.8",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 8192,
    "temperature": 0.2,
    "timeoutMs": 120000
  },
  {
    "step": "art_direction",
    "role": "generation",
    "provider": "openrouter",
    "model": "anthropic/claude-opus-4.8",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 1600,
    "temperature": 0.4,
    "timeoutMs": 90000
  },
  {
    "step": "theme_emit",
    "role": "generation",
    "provider": "openrouter",
    "model": "anthropic/claude-opus-4.8",
    "effort": null,
    "promptVariant": "landing",
    "maxTokens": 7000,
    "temperature": 0.85,
    "timeoutMs": 300000
  },
  {
    "step": "hero_continuation",
    "role": "generation",
    "provider": "openai",
    "model": "gpt-5.6-luna",
    "effort": "low",
    "promptVariant": "landing",
    "maxTokens": 16000,
    "temperature": 0.85,
    "timeoutMs": 240000
  },
  {
    "step": "page_generate",
    "role": "generation",
    "provider": "anthropic",
    "model": "claude-opus-4-8",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 20000,
    "temperature": 0.85,
    "timeoutMs": 300000
  },
  {
    "step": "honesty_repair",
    "role": "generation",
    "provider": "anthropic",
    "model": "claude-opus-4-8",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 20000,
    "temperature": 0.85,
    "timeoutMs": 300000
  },
  {
    "step": "honesty_judge",
    "role": "claims_judge",
    "provider": "openrouter",
    "model": "anthropic/claude-haiku-4.5",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 4096,
    "temperature": 0,
    "timeoutMs": 60000
  },
  {
    "step": "restyle",
    "role": "plan",
    "provider": "openrouter",
    "model": "anthropic/claude-opus-4.8",
    "effort": null,
    "promptVariant": "default",
    "maxTokens": 8192,
    "temperature": 0.2,
    "timeoutMs": 120000
  }
]

result 126855a0-01aa-4a2b-a813-78d0c4259a7f job 7fea2a31-1d3e-4cb1-b9af-551748b9d94a site bo-site-126855a0-01aa-4a2b-a813-78d0c4259a7f

Workflow provenance

Git SHA
7755bdf
Captured
Jul 16, 2026, 10:26 AM UTC
  1. startValidate business data; mark the job and bakeoff result running.
  2. pipeline / planBuild the full SEO page plan through the selected plan profile.
  3. pipeline / generateGenerate the homepage theme and scoped pages, repairing or falling back safely.
  4. pipeline / assembleAssemble raw HTML/CSS/JS with shared SEO, navigation, business facts, and legal pages.
  5. pipeline / auditRun deterministic QA plus the independent honesty judge.
  6. pipeline / writeWrite the validated mutable draft and its source/provenance artifacts to tenant R2.
  7. finishFinalize generation job, site metadata, and page rows in D1.
  8. domainsBest-effort domain candidate discovery used by the real claim path.
  9. bakeoff-finalizeBakeoff-only: publish an immutable preview snapshot and roll up LLM usage.