{
  "$schema": "runback.audit/v2",
  "manifest": {
    "run_id": "sbx-research-2c63e655603e",
    "generated_at": "2026-11-07T07:28:10.341Z",
    "event_count": 5,
    "algorithm": "sha256-chain",
    "content_digest": "2e09c4533196368fde511f2a94d6db7f720c1b5e7c34b2eca4fc8ab84003dfad",
    "replay": {
      "cassette_digest": "3d5dc3a802e8ac84abf76bbd77f6fa7911ab9aab01f2a61bd4c03532b8674177",
      "entry_count": 3,
      "algorithm": "oracle-chain/sha256",
      "note": "The run's oracle stream — every model response and tool output, hash-chained. Re-execute the agent against `events` with @runback/replay and the cassette digest must reproduce. This is proof the recording IS the deterministic input stream of the run — an audit you can re-run, not just read."
    },
    "signed": true,
    "signature": {
      "alg": "Ed25519",
      "value": "229aa1cdf7d8c21de3e34a928319356218eb560c5a49421650640a3da2bf37cba8cfe894bab05932df42e2ed3be5c7d764dff5ac02577f7f30edb7b5e896b104",
      "pubkey": "-----BEGIN PUBLIC KEY-----\nMCowBQYDK2VwAyEArDPmR+Gvu1HawnSvM6xjZao7BVPPQ80Qq3sa1hAYvDU=\n-----END PUBLIC KEY-----\n"
    },
    "verify": "Recompute the event chain h_i = SHA-256(h_{i-1} + canonical(event_i)) over `events` → must equal content_digest. Recompute the oracle-stream digest from `events` → must equal replay.cassette_digest. The signature covers `${content_digest}:${cassette_digest}`. Ed25519: verify with the public key embedded in manifest.signature.pubkey (no server key needed — fully offline-verifiable). HMAC-SHA256 (legacy): requires AUDIT_SIGNING_KEY. POST this record to /api/audit/verify.",
    "spec_url": "https://runback.dev/spec",
    "verifier_url": "https://runback.dev/verify"
  },
  "run": {
    "run_id": "sbx-research-2c63e655603e",
    "name": "research-agent",
    "status": "success",
    "input": "Summarise this week's trend in chargeback disputes and whether it needs attention.",
    "output": {
      "summary": "This week's trend in chargeback disputes shows a fluctuating pattern with counts of 71, 72, 95, 77, 87, 95, and 77 disputes per day. The peak of 95 disputes indicates a potential area of concern that may require attention."
    },
    "error": null,
    "metadata": {
      "agent": {
        "description": "Summarises incident and market trends. Runback demo agent: real model calls and real policy decisions; its tools act on a sandbox of synthetic customers, orders and accounts.",
        "systemOfRecord": "Runback demo sandbox (synthetic data)"
      },
      "model": "gpt-4o-mini",
      "demo_agent": true,
      "est_cost_usd": 0.000114,
      "sandbox_tools": true,
      "scenario_seed": "research-agent:2026-11-07:5"
    },
    "step_count": 2,
    "total_tokens": 517,
    "started_at": "2026-11-07T01:10:48.551+00:00",
    "ended_at": "2026-11-07T01:10:52.256+00:00",
    "actor_type": null,
    "actor_id": null
  },
  "events": [
    {
      "seq": 0,
      "name": "research-agent",
      "type": "run",
      "error": null,
      "input": "Summarise this week's trend in chargeback disputes and whether it needs attention.",
      "phase": "start",
      "output": null,
      "run_id": "sbx-research-2c63e655603e",
      "status": "running",
      "ts_end": "2026-11-07T01:10:52.256Z",
      "span_id": "r",
      "metadata": {
        "agent": {
          "description": "Summarises incident and market trends. Runback demo agent: real model calls and real policy decisions; its tools act on a sandbox of synthetic customers, orders and accounts.",
          "systemOfRecord": "Runback demo sandbox (synthetic data)"
        },
        "model": "gpt-4o-mini",
        "demo_agent": true,
        "est_cost_usd": 0.000114,
        "sandbox_tools": true,
        "scenario_seed": "research-agent:2026-11-07:5"
      },
      "ts_start": "2026-11-07T01:10:48.551Z",
      "parent_span_id": null,
      "schema_version": 1,
      "_hash": "5f991c7c1400eb2b185cd8f60e94f4bc7ae8909edab326138d06203021f1bd41"
    },
    {
      "seq": 1,
      "type": "llm",
      "error": null,
      "model": {
        "model_id": "gpt-4o-mini",
        "provider": "openai"
      },
      "usage": {
        "input_tokens": 187,
        "total_tokens": 210,
        "output_tokens": 23
      },
      "run_id": "sbx-research-2c63e655603e",
      "ts_end": "2026-11-07T01:10:50.567Z",
      "request": {
        "tools": [
          {
            "name": "search_incidents",
            "parameters": {
              "type": "object",
              "required": [
                "query",
                "days"
              ],
              "properties": {
                "days": {
                  "type": "number",
                  "description": "Look-back window in days"
                },
                "query": {
                  "type": "string",
                  "description": "Search terms"
                }
              },
              "additionalProperties": false
            },
            "description": "Search the incident log."
          },
          {
            "name": "get_metric",
            "parameters": {
              "type": "object",
              "required": [
                "name",
                "days"
              ],
              "properties": {
                "days": {
                  "type": "number",
                  "description": "Days"
                },
                "name": {
                  "type": "string",
                  "description": "Metric name"
                }
              },
              "additionalProperties": false
            },
            "description": "Get a daily metric series."
          }
        ],
        "params": {
          "temperature": 0,
          "max_output_tokens": 500
        },
        "system": "You are Acme's operations research agent. You are running in Runback's public demo sandbox: every customer, order, invoice and account is synthetic, and your tools act on test data only. Answer with a short, factual summary grounded only in what the tools return. Say plainly when the data is thin. Use the tools to act; when you are done, reply with a one-sentence summary of what you did.",
        "messages": [
          {
            "role": "user",
            "content": "Summarise this week's trend in chargeback disputes and whether it needs attention."
          }
        ]
      },
      "span_id": "l1",
      "response": {
        "text": null,
        "reasoning": null,
        "tool_calls": [
          {
            "input": {
              "days": 7,
              "name": "chargeback_disputes"
            },
            "tool_name": "get_metric",
            "tool_call_id": "call_TlFvGXWiW7Whxybmr6g1NasA"
          }
        ],
        "finish_reason": "tool-calls"
      },
      "ts_start": "2026-11-07T01:10:48.551Z",
      "latency_ms": 2016,
      "parent_span_id": "r",
      "schema_version": 1,
      "_hash": "560e3ef54d5d52d14f8bad92b8fdb24d5add9b83dc0f8d573f034a12b09a83f9"
    },
    {
      "seq": 2,
      "type": "tool",
      "error": null,
      "input": {
        "days": 7,
        "name": "chargeback_disputes"
      },
      "output": {
        "name": "chargeback_disputes",
        "unit": "count/day",
        "last_7_days": [
          71,
          72,
          95,
          77,
          87,
          95,
          77
        ]
      },
      "run_id": "sbx-research-2c63e655603e",
      "ts_end": "2026-11-07T01:10:50.715Z",
      "span_id": "t1",
      "ts_start": "2026-11-07T01:10:50.567Z",
      "tool_name": "get_metric",
      "latency_ms": 148,
      "tool_call_id": "call_TlFvGXWiW7Whxybmr6g1NasA",
      "parent_span_id": "l1",
      "schema_version": 1,
      "_hash": "57496369c13798d21ab543458934cbfc3d2f5de2e3b9e301610584fe395f72a1"
    },
    {
      "seq": 3,
      "type": "llm",
      "error": null,
      "model": {
        "model_id": "gpt-4o-mini",
        "provider": "openai"
      },
      "usage": {
        "input_tokens": 248,
        "total_tokens": 307,
        "output_tokens": 59
      },
      "run_id": "sbx-research-2c63e655603e",
      "ts_end": "2026-11-07T01:10:52.256Z",
      "request": {
        "tools": [
          {
            "name": "search_incidents",
            "parameters": {
              "type": "object",
              "required": [
                "query",
                "days"
              ],
              "properties": {
                "days": {
                  "type": "number",
                  "description": "Look-back window in days"
                },
                "query": {
                  "type": "string",
                  "description": "Search terms"
                }
              },
              "additionalProperties": false
            },
            "description": "Search the incident log."
          },
          {
            "name": "get_metric",
            "parameters": {
              "type": "object",
              "required": [
                "name",
                "days"
              ],
              "properties": {
                "days": {
                  "type": "number",
                  "description": "Days"
                },
                "name": {
                  "type": "string",
                  "description": "Metric name"
                }
              },
              "additionalProperties": false
            },
            "description": "Get a daily metric series."
          }
        ],
        "params": {
          "temperature": 0,
          "max_output_tokens": 500
        },
        "system": "You are Acme's operations research agent. You are running in Runback's public demo sandbox: every customer, order, invoice and account is synthetic, and your tools act on test data only. Answer with a short, factual summary grounded only in what the tools return. Say plainly when the data is thin. Use the tools to act; when you are done, reply with a one-sentence summary of what you did.",
        "messages": [
          {
            "role": "user",
            "content": "Summarise this week's trend in chargeback disputes and whether it needs attention."
          },
          {
            "role": "assistant",
            "content": [
              {
                "type": "tool-call",
                "input": {
                  "days": 7,
                  "name": "chargeback_disputes"
                },
                "toolName": "get_metric",
                "toolCallId": "call_TlFvGXWiW7Whxybmr6g1NasA"
              }
            ]
          },
          {
            "role": "tool",
            "content": [
              {
                "type": "tool-result",
                "output": {
                  "type": "json",
                  "value": {
                    "name": "chargeback_disputes",
                    "unit": "count/day",
                    "last_7_days": [
                      71,
                      72,
                      95,
                      77,
                      87,
                      95,
                      77
                    ]
                  }
                },
                "toolName": "get_metric",
                "toolCallId": "call_TlFvGXWiW7Whxybmr6g1NasA"
              }
            ]
          }
        ]
      },
      "span_id": "l2",
      "response": {
        "text": "This week's trend in chargeback disputes shows a fluctuating pattern with counts of 71, 72, 95, 77, 87, 95, and 77 disputes per day. The peak of 95 disputes indicates a potential area of concern that may require attention.",
        "reasoning": null,
        "tool_calls": [],
        "finish_reason": "stop"
      },
      "ts_start": "2026-11-07T01:10:50.715Z",
      "latency_ms": 1541,
      "parent_span_id": "r",
      "schema_version": 1,
      "_hash": "4794c0d27a677d66a79d09077785e458ccbfe2dd2b90ee24d5c088cd3a705e99"
    },
    {
      "seq": 4,
      "name": "research-agent",
      "type": "run",
      "error": null,
      "input": null,
      "phase": "end",
      "output": {
        "summary": "This week's trend in chargeback disputes shows a fluctuating pattern with counts of 71, 72, 95, 77, 87, 95, and 77 disputes per day. The peak of 95 disputes indicates a potential area of concern that may require attention."
      },
      "run_id": "sbx-research-2c63e655603e",
      "status": "success",
      "ts_end": "2026-11-07T01:10:52.256Z",
      "span_id": "re",
      "metadata": {
        "demo_agent": true,
        "sandbox_tools": true
      },
      "ts_start": "2026-11-07T01:10:52.256Z",
      "parent_span_id": null,
      "schema_version": 1,
      "_hash": "2e09c4533196368fde511f2a94d6db7f720c1b5e7c34b2eca4fc8ab84003dfad"
    }
  ]
}