{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-09-18-015",
    "source_story_id": "tmp-sidebar-chronicle-cutpoint-replay",
    "edition_id": "mp-2026-09-18-morning-0071",
    "edition_url": "https://themachinepress.com/edition/2026-09-18",
    "position": 17,
    "story_type": "ticker",
    "section": "developer-tools",
    "editorial_classification": "editorial",
    "headline": "Recorded Agent Failures Became CI Tests",
    "slug": "recorded-agent-failures-became-ci-tests",
    "dek": "Chronicle replayed six incidents bit-stably and caught every unsafe tool mutation that crossed the chosen cut point.",
    "summary": "Chronicle replayed six incidents bit-stably and caught every unsafe tool mutation that crossed the chosen cut point.",
    "body_text": "Chronicle records non-deterministic model and tool boundaries as immutable envelopes. Full replay issued no model calls and remained bit-stable across 20 repetitions; cut-point replay served selected boundaries from the record while exercising new code at the others. In six incidents, the tests failed on faulty code and passed on guarded or benign changes.",
    "why_it_matters": "Chronicle replayed six incidents bit-stably and caught every unsafe tool mutation that crossed the chosen cut point.",
    "limitations": [],
    "importance": 8,
    "canonical_url": "https://themachinepress.com/story/mp-2026-09-18-015/recorded-agent-failures-became-ci-tests",
    "json_url": "https://themachinepress.com/story/mp-2026-09-18-015.json",
    "first_published_at": "2026-09-18T09:00:00.000-04:00",
    "modified_at": "2026-09-18T09:00:00.000-04:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-09-18-015-001",
        "text": "Chronicle replayed six incidents bit-stably and caught every unsafe tool mutation that crossed the chosen cut point.",
        "source_ids": [
          "source-2026-09-18-017"
        ],
        "qualification": null
      }
    ],
    "source_ids": [
      "source-2026-09-18-017"
    ],
    "tags": [
      "agent testing",
      "record replay",
      "continuous integration"
    ],
    "image_url": null,
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-09-18-017",
      "title": "arXiv preprint 2609.20625",
      "publisher": "arXiv",
      "url": "https://arxiv.org/abs/2609.20625",
      "canonical_url": "https://arxiv.org/abs/2609.20625",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-09-17T12:09:57.000-04:00",
      "accessed_at": "2026-09-18T08:26:40.599-04:00",
      "supports_claim_ids": [
        "claim-mp-2026-09-18-015-001"
      ]
    }
  ],
  "corrections": [],
  "publisher": {
    "name": "The Machine Press",
    "url": "https://themachinepress.com",
    "description": "A daily newspaper for the age of artificial intelligence."
  },
  "cite_this_report": {
    "title": "Recorded Agent Failures Became CI Tests",
    "publisher": "The Machine Press",
    "published_at": "2026-09-18T09:00:00.000-04:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-09-18-015/recorded-agent-failures-became-ci-tests"
  }
}