{
  "schema": "varexis-public-evidence-record/0.3",
  "generated_at_utc": "2026-10-28T23:55:00.000Z",
  "record_id": "VXI-EXT-ICE04-CLAUDE-SESSION-BUDGET-OVERSHOOT-01-v1",
  "record_kind": "external_reference",
  "title": "Claude session budgets and final spend",
  "system": "Claude Managed Agents",
  "evidence_family": "vendor_evidence_review",
  "index_status": "PUBLIC_SAFE_SOURCE_REVIEW",
  "evidence_state": "PRIMARY_DOCUMENTATION_REVIEW_ONLY",
  "canonical_question": "Is a Claude Managed Agents max_list_cost budget an exact upper bound on final session cost?",
  "near_questions": [
    "Can Claude session spend finish above max_list_cost?",
    "Can tool calls continue after the request that crosses a budget?",
    "Does budget_reached mean the session was terminated?",
    "What margin is needed when interpreting a Managed Agents budget?"
  ],
  "supported_claims": [
    {
      "claim": "Claude documents that the model request crossing a session budget completes, potentially exceeding the cap by one model request per thread. Its returned tool calls still run and their search and runtime costs count. The budget bounds starting new work rather than guaranteeing an exact final charge; retain the usage snapshot and stop reason.",
      "reliance": "DOCUMENTED_CAPABILITY_ONLY"
    }
  ],
  "not_demonstrated_claims": [
    "No exact charge ceiling, invoice amount or verified stop behavior is established by a configured budget alone.",
    "Buyer implementation, live runtime enforcement, settled payment, certification or permission to act are not established.",
    "No expanded capabilities or licences for existing INDEX executables."
  ],
  "public_summary": "Claude documents that the model request crossing a session budget completes, potentially exceeding the cap by one model request per thread. Its returned tool calls still run and their search and runtime costs count. The budget bounds starting new work rather than guaranteeing an exact final charge; retain the usage snapshot and stop reason.",
  "related_record_ids": [],
  "source_review": {
    "source_type": "official_external_documentation",
    "source_title": "Claude Managed Agents: Budgets",
    "source_url": "https://platform.claude.com/docs/en/managed-agents/budgets.md",
    "checked_on": "2026-10-28",
    "candidate_record_id": "VXI-EXT-ICE04-CLAUDE-SESSION-BUDGET-OVERSHOOT-01-v1",
    "candidate_record_sha256": "f0c1820b5929e07d2cb4f2e8730ac0779bb5f7f98c3c78904954b95518312199",
    "method": "Primary documentation reviewed for the published bounded statement.",
    "deployment_tested_by_varexis": false,
    "revalidation": "The delivered snapshot preserves the review date shown. Recheck current primary documentation and deployment context before relying on present applicability; payment does not trigger fresh research."
  },
  "answer_policy": {
    "classification": "DOCUMENTED_WITH_DEPLOYMENT_BOUNDARY",
    "bounded_answer": "Claude documents that the model request crossing a session budget completes, potentially exceeding the cap by one model request per thread. Its returned tool calls still run and their search and runtime costs count. The budget bounds starting new work rather than guaranteeing an exact final charge; retain the usage snapshot and stop reason.",
    "required_buyer_context": "Session budget and thread inventory; Consumed list cost and stop reason; Crossing requests, tool work and applicable billing evidence. Buyer deployment not inspected.",
    "missing_evidence": "A broader claim needs evidence matching the intended use. Payment does not upgrade the evidence state."
  },
  "private_boundary": "Raw logs, thresholds, private paths, source code, protected mechanisms and reconstruction-level details are excluded from public and paid delivery.",
  "decision_profile": {
    "schema": "varexis-vendor-evidence-review/1",
    "review_status": "documentation_review_only",
    "checked_on": "2026-10-28",
    "claim_to_check": "Is a Claude Managed Agents max_list_cost budget an exact upper bound on final session cost?",
    "documented_statement": {
      "status": "documented",
      "statement": "Claude documents that the model request crossing a session budget completes, potentially exceeding the cap by one model request per thread. Its returned tool calls still run and their search and runtime costs count. The budget bounds starting new work rather than guaranteeing an exact final charge; retain the usage snapshot and stop reason.",
      "source_ids": [
        "claude-budget"
      ]
    },
    "review_inference": {
      "status": "review_inference",
      "statement": "Review claude session budgets and final spend before accepting the buyer claim. Per-session request-boundary stopping differs from organization or workspace monthly caps. This is a documentation-review judgment, not an observed deployment outcome.",
      "source_ids": [
        "claude-budget"
      ]
    },
    "buyer_evidence_required": [
      "Session budget and thread inventory",
      "Consumed list cost and stop reason",
      "Crossing requests, tool work and applicable billing evidence"
    ],
    "review_condition": {
      "status": "varexis_review_policy",
      "statement": "No exact charge ceiling, invoice amount or verified stop behavior is established by a configured budget alone."
    },
    "unknowns": "Buyer configuration, effective authority, complete usage and final business outcomes were not inspected.",
    "unknown_finding": {
      "status": "unknown",
      "statement": "Buyer configuration, effective authority, complete usage and final business outcomes were not inspected."
    },
    "evidence_sources": [
      {
        "source_id": "claude-budget",
        "url": "https://platform.claude.com/docs/en/managed-agents/budgets.md",
        "final_url": "https://platform.claude.com/docs/en/managed-agents/budgets.md",
        "status": 200,
        "captured_at_utc": "2026-10-28T23:49:42.510295+00:00",
        "sha256": "90245eadd5c551c9a01408a9004071e7cde78a4f4e051066056d94a32e034a72",
        "bytes": 28561,
        "content_type": "text/markdown; charset=utf-8",
        "title": "Claude Managed Agents: Budgets",
        "hash_basis": "SHA-256 of captured HTTP response body bytes",
        "checked_on": "2026-10-28",
        "capture_status": 200,
        "claim_review_completed": true,
        "reviewed_sections": [
          "When a session reaches its budget",
          "Monitor spend"
        ],
        "version_context": "Rolling official documentation captured 2026-10-28; exact response hash is pinned, not a stable vendor release. Verify the deployed API/version and account feature availability. Managed Agents beta API; required headers and supported surfaces are defined in the captured Availability section.",
        "rights_review": "Original factual paraphrase and attributed source metadata only. Captured documentation and code remain private; no source prose, examples, images or vendor marks are redistributed. No licence to vendor software or buyer assurance is granted."
      }
    ],
    "observed_deployment": false,
    "commercial_reliance_boundary": "Source documentation supports only the stated boundary. Existing licensed checkers analyse supported supplied declarations; they do not query these providers, verify live systems, settle payments or certify compliance.",
    "paid_value": {
      "decision_context": "Review claude session budgets and final spend before accepting the buyer claim. Per-session request-boundary stopping differs from organization or workspace monthly caps.",
      "free": "Complete review, practical questions, source references and limitations; freely accessible and locally saveable.",
      "single_request": "Unavailable for this publication-only record; historical saved retrieval remains unchanged.",
      "evidence_receipt": "Unavailable for this publication-only record; no new paid retrieval entitlement.",
      "excluded": [
        "Fresh vendor research",
        "Live provider inspection",
        "Runtime enforcement or certification",
        "Expanded executable schemas or licences",
        "Executable AI cost reconciliation"
      ],
      "integrity": "Hashes identify content versions; they do not prove truth or provide a signature."
    },
    "revalidation": {
      "trigger": "Recheck the source and applicable API, account and configuration before current reliance. No monitoring or fresh research is included.",
      "specific_watch": "When a session reaches its budget"
    },
    "buyer_relevance": "Review claude session budgets and final spend before accepting the buyer claim. Per-session request-boundary stopping differs from organization or workspace monthly caps.",
    "refusal_conditions": [
      "No exact charge ceiling, invoice amount or verified stop behavior is established by a configured budget alone.",
      "Do not infer buyer deployment conformance or successful business outcomes from source documentation."
    ]
  },
  "niche": {
    "niche_id": "ice04-ai-cost-usage-invoice-assurance",
    "label": "AI Cost, Usage & Invoice Assurance",
    "classification_id": "ai-cost-usage-invoice-assurance",
    "classification_label": "AI Cost, Usage & Invoice Assurance",
    "topic_id": "ai-cost-usage-invoice-assurance",
    "buyer_intent": "Review claude session budgets and final spend before accepting the buyer claim. Per-session request-boundary stopping differs from organization or workspace monthly caps.",
    "comparison_role": "supplementary_discovery"
  },
  "paid_access_note": "The full published answer and boundaries are free. Paid access saves the selected route and source versions, with an unsigned receipt when purchased. Preview coverage before paying. Fresh research, bespoke assessment and protected evidence are excluded.",
  "service_route": {
    "request_guide": "/varexis-index/request.html",
    "request_workflow": "/varexis-index/request-workflow.json",
    "service_id": "single_request",
    "service_routes_url": "/varexis-index/service-routes.json",
    "payment_required": true,
    "availability_endpoint": "/api/index/capabilities",
    "operational_status": "AUTOMATIC_SERVICE_CAPABILITIES_GATED",
    "checkout_url": "/index-access"
  },
  "authority_boundary": "VAREXIS-INDEX informs evidence reliance. It does not provide advice, certification, deployment authority, security assurance, production approval, or guarantee.",
  "human_page": "/varexis-index/catalog.html#claude-session-budget-overshoot",
  "machine_readable_record": "/varexis-index/records/claude-session-budget-overshoot.json"
}