{
  "schema": "vedokrok.public-item.v1",
  "release_id": "MHC-RPUB-20260920-75ad787a",
  "url": "/knowledge/re-test-old-harness-rules-when-the-model-changes",
  "id": "MHC-D-RESEARCH-0713",
  "version": "0.1.0",
  "title": "Re-test old harness rules when the model changes",
  "summary": "Yesterday's workaround can become tomorrow's tax.",
  "kind": "protocol",
  "body": "After a material model or harness upgrade, rerun representative evals while removing or simplifying one workaround at a time. Keep a component only if it still improves quality, reliability, cost or recovery. Do not preserve elaborate context resets, prompt rituals or reviewer loops merely because an earlier model needed them.",
  "limits": [
    "Change one component at a time where possible; removing several together can hide interactions and make regression diagnosis ambiguous."
  ],
  "topics": [
    "union-ai-coding-harness-work"
  ],
  "intents": [],
  "source_ids": [
    "RS-4CF3167EB387E6BE"
  ],
  "evidence": [
    {
      "claim": "Anthropic reports that context-reset scaffolding that helped one model could be removed for a stronger later model, illustrating that harness components should be re-tested as models change.",
      "source_id": "RS-4CF3167EB387E6BE",
      "role": "supports",
      "note": "Do not infer that resets or compaction are broadly obsolete; test on the actual model and task.",
      "locator": "Context resets and later simplification"
    }
  ],
  "use_when": [
    "A workflow has accumulated scaffolding, retries or context-reset tricks around an older model."
  ],
  "avoid_when": [
    "Change one component at a time where possible; removing several together can hide interactions and make regression diagnosis ambiguous."
  ],
  "example": "A forced context reset that prevented drift on an older coding model may be unnecessary after a model upgrade with stronger long-context behavior.",
  "check": "Every expensive harness component has current evidence of value on the model you actually run.",
  "steps": [
    "Choose a representative baseline suite.",
    "Remove or simplify one harness component.",
    "Run repeated comparable trials.",
    "Inspect quality, cost and failure mode changes.",
    "Keep, revise or retire the component."
  ],
  "sources": [
    {
      "id": "RS-4CF3167EB387E6BE",
      "title": "Harness design for long-running application development",
      "url": "https://www.anthropic.com/engineering/harness-design-long-running-apps"
    }
  ],
  "relations": [
    {
      "from": "MHC-D-RESEARCH-0713",
      "to": "MHC-D-RESEARCH-0371",
      "type": "useful_with",
      "url": "/knowledge/re-benchmark-ai-when-the-model-or-task-changes"
    }
  ],
  "collections": [
    {
      "id": "RC-A76353E5E9A33FE5",
      "title": "Make coding agents work in inspectable increments",
      "url": "/collections/make-coding-agents-work-in-inspectable-increments"
    }
  ]
}