{
  "schema_version": "2026-05-27.agent-task-receipts.v1",
  "name": "TokRepo Agent Task Receipts Eval",
  "canonical_url": "https://tokrepo.com/evals/agent-task-receipts.json",
  "updated_at": "2026-05-27",
  "generated_by": "node scripts/run_agent_task_receipts.mjs --json",
  "freshness_reference_time": "2026-05-27T07:20:00Z",
  "purpose": "Public, deterministic run receipts for long-running TokRepo agent tasks. Each receipt proves the last run time, next due time, freshness, verification command, evidence digest, outcome oracle, task verdict, and user effect.",
  "receipt_contract": {
    "required_fields": [
      "run_id",
      "receipt_id",
      "last_run_at",
      "next_due_at",
      "ttl_seconds",
      "freshness_status",
      "run_command",
      "verification_command",
      "evidence_digest",
      "outcome_oracle",
      "task_outcome_verdict",
      "user_effect"
    ],
    "accepted_verdicts": [
      "pass",
      "pass_with_warning",
      "pass_with_handoff"
    ],
    "freshness_boundary": "A task run is fresh only when its receipt is inside its next_due_at plus ttl_seconds window at the published reference time.",
    "privacy_boundary": "Receipts publish command names, public URLs, hashes, and summaries only. They must not include private task text, file contents, access tokens, cookies, or local secret values."
  },
  "metrics": {
    "receipts_total": 3,
    "receipts_fresh": 3,
    "fresh_receipt_pct": 100,
    "outcome_oracle_coverage_pct": 100,
    "task_outcome_accepted_pct": 100,
    "handoff_quality_pass_rate_pct": 100,
    "stale_receipts": 0
  },
  "task_receipts": [
    {
      "run_id": "taskrun_agent_discovery_smoke_daily",
      "receipt_id": "receipt_20260527_agent_discovery_smoke",
      "last_run_at": "2026-05-27T07:20:00Z",
      "next_due_at": "2026-05-28T07:20:00Z",
      "ttl_seconds": 172800,
      "run_command": "WEB_BASE=https://tokrepo.com API_BASE=https://api.tokrepo.com node scripts/production-agent-discovery-check.mjs",
      "verification_command": "WEB_BASE=https://tokrepo.com node scripts/verify_agent_task_economy_contract.mjs",
      "outcome_oracle": {
        "type": "machine_readable_surface_contract",
        "evaluator": "scripts/production-agent-discovery-check.mjs",
        "pass_condition": "All TokRepo agent discovery surfaces return HTTP 200, include the task-economy eval set, hosted MCP JSON-RPC tools answer without schema regressions, and the official MCP Registry latest active row matches the live MCP manifest."
      },
      "task_outcome_verdict": "pass",
      "user_effect": "Planning agents can discover the live TokRepo MCP, CLI, manifest, harness, ledger, official MCP Registry listing, and task-economy surfaces without GUI browsing or version-lag warnings.",
      "freshness_status": "fresh",
      "freshness_reference_time": "2026-05-27T07:20:00Z",
      "evidence_digest": {
        "algorithm": "sha256",
        "source_urls": [
          "https://tokrepo.com/.well-known/tokrepo.json",
          "https://registry.modelcontextprotocol.io/v0/servers?search=tokrepo",
          "https://tokrepo.com/evals/agent-task-ledger.json",
          "https://tokrepo.com/agent-task-economy.json"
        ],
        "summary": "Production discovery passed across machine-readable endpoints, hosted MCP JSON-RPC, llms-full size guard, official registry latest-version check, and workflow API probes with no warnings.",
        "digest": "sha256:cc8d8be2c9d198544d43aa526d2725a69eafb20873656091a31668cc1abf177c"
      },
      "coverage": {
        "pass": true,
        "checks": [
          {
            "id": "receipt_field:run_id",
            "pass": true
          },
          {
            "id": "receipt_field:receipt_id",
            "pass": true
          },
          {
            "id": "receipt_field:last_run_at",
            "pass": true
          },
          {
            "id": "receipt_field:next_due_at",
            "pass": true
          },
          {
            "id": "receipt_field:ttl_seconds",
            "pass": true
          },
          {
            "id": "receipt_field:freshness_status",
            "pass": true
          },
          {
            "id": "receipt_field:run_command",
            "pass": true
          },
          {
            "id": "receipt_field:verification_command",
            "pass": true
          },
          {
            "id": "receipt_field:evidence_digest",
            "pass": true
          },
          {
            "id": "receipt_field:outcome_oracle",
            "pass": true
          },
          {
            "id": "receipt_field:task_outcome_verdict",
            "pass": true
          },
          {
            "id": "receipt_field:user_effect",
            "pass": true
          },
          {
            "id": "freshness_is_fresh",
            "pass": true
          },
          {
            "id": "outcome_oracle_has_pass_condition",
            "pass": true
          },
          {
            "id": "evidence_digest_has_source_urls",
            "pass": true
          }
        ]
      }
    },
    {
      "run_id": "taskrun_private_harvest_review_weekly",
      "receipt_id": "receipt_20260527_private_harvest_review",
      "last_run_at": "2026-05-27T04:38:00Z",
      "next_due_at": "2026-06-03T04:38:00Z",
      "ttl_seconds": 691200,
      "run_command": "node scripts/run_agent_task_harness.mjs --check-public",
      "verification_command": "node scripts/verify_agent_task_economy_contract.mjs",
      "outcome_oracle": {
        "type": "quality_gate_receipt",
        "evaluator": "scripts/run_agent_task_harness.mjs",
        "pass_condition": "The private harvest case includes tokrepo_harvest and tokrepo_handoff_plan traces, keeps draft supply private by default, and passes the Grader checks."
      },
      "task_outcome_verdict": "pass",
      "user_effect": "Reusable work created during agent sessions can be reviewed as private package drafts with quality gates before any public push.",
      "freshness_status": "fresh",
      "freshness_reference_time": "2026-05-27T07:20:00Z",
      "evidence_digest": {
        "algorithm": "sha256",
        "source_urls": [
          "https://tokrepo.com/evals/agent-task-harness.json",
          "https://tokrepo.com/evals/handoff-quality.json"
        ],
        "summary": "Mini harness public eval still passes all three task-economy cases, including post-task private harvest and handoff planning.",
        "digest": "sha256:d27a4f80a242278fdd1115bc985fe762895fd742500d6b8b9ebbb92daeb1f389"
      },
      "coverage": {
        "pass": true,
        "checks": [
          {
            "id": "receipt_field:run_id",
            "pass": true
          },
          {
            "id": "receipt_field:receipt_id",
            "pass": true
          },
          {
            "id": "receipt_field:last_run_at",
            "pass": true
          },
          {
            "id": "receipt_field:next_due_at",
            "pass": true
          },
          {
            "id": "receipt_field:ttl_seconds",
            "pass": true
          },
          {
            "id": "receipt_field:freshness_status",
            "pass": true
          },
          {
            "id": "receipt_field:run_command",
            "pass": true
          },
          {
            "id": "receipt_field:verification_command",
            "pass": true
          },
          {
            "id": "receipt_field:evidence_digest",
            "pass": true
          },
          {
            "id": "receipt_field:outcome_oracle",
            "pass": true
          },
          {
            "id": "receipt_field:task_outcome_verdict",
            "pass": true
          },
          {
            "id": "receipt_field:user_effect",
            "pass": true
          },
          {
            "id": "freshness_is_fresh",
            "pass": true
          },
          {
            "id": "outcome_oracle_has_pass_condition",
            "pass": true
          },
          {
            "id": "evidence_digest_has_source_urls",
            "pass": true
          }
        ]
      }
    },
    {
      "run_id": "taskrun_delayed_chrome_mcp_recheck",
      "receipt_id": "receipt_20260527_chrome_mcp_recheck",
      "last_run_at": "2026-05-27T04:44:00Z",
      "next_due_at": "2026-05-27T05:14:00Z",
      "ttl_seconds": 86400,
      "run_command": "curl --noproxy \"*\" http://127.0.0.1:9401/proxy/status",
      "verification_command": "TOKREPO_ALLOW_SYSTEM_CHROME=1 WEB_BASE=https://tokrepo.com node scripts/production-overflow-check.mjs",
      "outcome_oracle": {
        "type": "browser_validation_fallback",
        "evaluator": "Chrome MCP proxy status plus System Chrome/Puppeteer production checks",
        "pass_condition": "Proxy status remains chromeConnected=true and the production browser validation matrix passes with System Chrome when the current MCP stdio transport is closed."
      },
      "task_outcome_verdict": "pass_with_handoff",
      "user_effect": "Browser-dependent TokRepo production validation remains executable even when the current Codex Chrome MCP stdio transport needs a session-level reconnect.",
      "freshness_status": "fresh",
      "freshness_reference_time": "2026-05-27T07:20:00Z",
      "evidence_digest": {
        "algorithm": "sha256",
        "source_urls": [
          "local:chrome-mcp-proxy-status",
          "https://tokrepo.com/en/agent-stats"
        ],
        "summary": "Chrome proxy health is green, older MCP processes were cleaned safely, and production System Chrome validation passed for agent-stats content and overflow.",
        "digest": "sha256:e6d852212930cd1bf3d70c6dcc35400c70c50bba8513e14d71607510081f0cb1"
      },
      "coverage": {
        "pass": true,
        "checks": [
          {
            "id": "receipt_field:run_id",
            "pass": true
          },
          {
            "id": "receipt_field:receipt_id",
            "pass": true
          },
          {
            "id": "receipt_field:last_run_at",
            "pass": true
          },
          {
            "id": "receipt_field:next_due_at",
            "pass": true
          },
          {
            "id": "receipt_field:ttl_seconds",
            "pass": true
          },
          {
            "id": "receipt_field:freshness_status",
            "pass": true
          },
          {
            "id": "receipt_field:run_command",
            "pass": true
          },
          {
            "id": "receipt_field:verification_command",
            "pass": true
          },
          {
            "id": "receipt_field:evidence_digest",
            "pass": true
          },
          {
            "id": "receipt_field:outcome_oracle",
            "pass": true
          },
          {
            "id": "receipt_field:task_outcome_verdict",
            "pass": true
          },
          {
            "id": "receipt_field:user_effect",
            "pass": true
          },
          {
            "id": "freshness_is_fresh",
            "pass": true
          },
          {
            "id": "outcome_oracle_has_pass_condition",
            "pass": true
          },
          {
            "id": "evidence_digest_has_source_urls",
            "pass": true
          }
        ]
      }
    }
  ]
}