Full-stack acceptance campaign

Runner Full-Stack E2E

Results across runner profiles and execution environments. Declared PNG screenshots and normalized results are retained with every published campaign; additional diagnostic evidence remains in the access-controlled workflow artifact.

2026-10-21T17:41:30.486Z6036cee2Source run ↗

0/2Passed
2Failed
2m 52sTest time
Campaign usage and spend
96,729Input tokens
4,849Output tokens
476,120Cached tokens
UnavailableLLM reported subtotal
$0.000000Daytona list estimate
2m 10sAgent execution time
0msDaytona lease time
0/4Runs provider-priced

Model spend is the provider-reported subtotal; unpriced or unavailable runs are excluded, never counted as free. Daytona runtime is a public-list-price estimate from captured lease time and pinned resources, before credits, discounts, storage allowance, or invoice adjustments. Local execution has no external runtime meter.

All results

Feature coverage 0 of 191 capabilities linked · 0 of 2 tests mapped

Associations use the current feature map. Counts describe linked test scenarios; a passing journey does not establish full coverage of a capability.

Getting started and access

FeatureCapabilities linkedLinked test results
Onboarding and first work 0/5 No mapped journey
Login, invitations, and access 0/5 No mapped journey
Companies and portability 0/8 No mapped journey

Tasks and conversations

FeatureCapabilities linkedLinked test results
Task creation and lifecycle 0/6 No mapped journey
Delegation, dependencies, and signoff 0/4 No mapped journey
Inbox, decisions, and search 0/5 No mapped journey
Agent conversations and project handoff 0/4 No mapped journey
Questions and approvals 0/8 No mapped journey
Steering and queued messages 0/7 No mapped journey
Documents, attachments, and work products 0/5 No mapped journey

Agents and reusable capabilities

FeatureCapabilities linkedLinked test results
Hiring, configuration, and organization 0/9 No mapped journey
Runs, harnesses, and model accounts 0/4 No mapped journey
Skills and Skill Studio 0/5 No mapped journey
Team packages and installation 0/4 No mapped journey

Projects and execution

FeatureCapabilities linkedLinked test results
Projects and repositories 0/5 No mapped journey
Goals and work alignment 0/3 No mapped journey
Workspaces, services, and files 0/5 No mapped journey
Execution environments 0/5 No mapped journey
Recovery 0/8 No mapped journey

Apps, channels, and extensions

FeatureCapabilities linkedLinked test results
Connection setup 0/8 No mapped journey
Assistant connections (MCP) 0/5 No mapped journey
App access and action permissions 0/5 No mapped journey
External chat and email 0/6 No mapped journey
Tool gateways and access profiles 0/5 No mapped journey
Secrets and proposals 0/5 No mapped journey
Plugins 0/4 No mapped journey

Automation and structured work

FeatureCapabilities linkedLinked test results
Routines, schedules, and triggers 0/5 No mapped journey
Cases 0/5 No mapped journey
Status cards 0/4 No mapped journey

Oversight and operation

FeatureCapabilities linkedLinked test results
Costs and budgets 0/6 No mapped journey
Dashboards and audit trails 0/6 No mapped journey
Navigation, profile, and announcements 0/6 No mapped journey
Instance operations 0/6 No mapped journey
CLI/API and local worktrees 0/6 No mapped journey

Contributor surfaces

FeatureCapabilities linkedLinked test results
Developer previews and diagnostic labs 0/4 No mapped journey

Test suite

followup-stop-resume

Suite discovered from retained campaign identities; full suite size is not known to this publisher.

Pass rate0.0%0/2 passed
Tokens577,69896,729 input · 4,849 output
Known spendUnavailablereported LLM + runtime estimate
Agent time2m 10s0ms lease
Execution2/20 retries · cleanup passed

followup-stop-resume

Inspect case ↗
Codie staging-model diagnosticIsolated localcodex · gpt-6.1-sol
followup-stop-resume failed
Overall failed · 2/5 behavioral checks passed

Failed checks:

  • followupStopResume.one-explicit-resumption — Only one user-triggered successor may complete the original task after Stop.
  • followupStopResume.retained-context-workspace-tools — The independently seeded context, earlier follow-up, workspace, production instructions and tool contract must survive without being restated in the resume message.
  • followupStopResume.accessible-resumed-result — One receipt-bound final reply must expose the independently verified result without a pending question.
See all behavioral checks (5)
ResultCheckDetail
PassfollowupStopResume.active-followup-before-stopOne ordinary user follow-up must persist while the original result-free provider run is still active.
PassfollowupStopResume.stop-remains-authoritativeThe acknowledged Stop must retain one cancelled run with no automatic continuation throughout the recorded quiet window before a real user resumes.
FailfollowupStopResume.one-explicit-resumptionOnly one user-triggered successor may complete the original task after Stop.
FailfollowupStopResume.retained-context-workspace-toolsThe independently seeded context, earlier follow-up, workspace, production instructions and tool contract must survive without being restated in the resume message.
FailfollowupStopResume.accessible-resumed-resultOne receipt-bound final reply must expose the independently verified result without a pending question.

candidate failure

Stopped waiting for one persisted final reply and its matching delivery receipt: Recovery produced duplicate final replies
Test details2/5 checks · 1m 20s
Tokens52,718 in · 1,442 out229,055 cached · 2/2 runs covered
LLM spendUnavailable0/2 runs provider-priced
ExecutionLocal · not metered58s agent
followup-stop-resume.runner-codex.local.followup-stop-resume
Attempt
1
Duration
1m 20s
Agent runtime
58s
Runtime
native
Provider
codex
Model
gpt-6.1-sol
Issue
RUN-1

No result artifact was uploaded

Startup reuse evidence
RunWarmthEnvironment/leaseWorkspaceRunnerProvider processProvider sessionProvider launches
90fe24a2-1b7a-4324-a906-d17782d509f2unknown unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing) unknown
c3afddf9-877d-45ec-8969-0bb61835027funknown unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing) unknown
ResultMatcherExpectationDetail
Pass json_path {"kind":"json_path","path":"followupStopResume.active-followup-before-stop","expected":true} One ordinary user follow-up must persist while the original result-free provider run is still active.
Pass json_path {"kind":"json_path","path":"followupStopResume.stop-remains-authoritative","expected":true} The acknowledged Stop must retain one cancelled run with no automatic continuation throughout the recorded quiet window before a real user resumes.
Fail json_path {"kind":"json_path","path":"followupStopResume.one-explicit-resumption","expected":true} Only one user-triggered successor may complete the original task after Stop.
Fail json_path {"kind":"json_path","path":"followupStopResume.retained-context-workspace-tools","expected":true} The independently seeded context, earlier follow-up, workspace, production instructions and tool contract must survive without being restated in the resume message.
Fail json_path {"kind":"json_path","path":"followupStopResume.accessible-resumed-result","expected":true} One receipt-bound final reply must expose the independently verified result without a pending question.
Usage and billing metadata
{
  "billing": {
    "llm": {
      "runCount": 2,
      "runsWithTokenUsage": 2,
      "runsWithReportedCost": 0,
      "inputTokens": 52718,
      "outputTokens": 1442,
      "cachedInputTokens": 229055,
      "totalTokens": 283215,
      "reportedCostUsd": 0,
      "costStatus": "unpriced"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 58491,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": {
    "runs": [
      {
        "runId": "90fe24a2-1b7a-4324-a906-d17782d509f2",
        "usage": {
          "model": "gpt-6.1-sol",
          "biller": "openai",
          "costUsd": null,
          "provider": "openai",
          "costStatus": "estimated",
          "billingType": "metered_api",
          "inputTokens": 27191,
          "ledgerScope": {
            "issueId": "47d02fa1-3917-44bf-b084-0be8db9ec0bd",
            "projectId": "77904efe-00ea-4201-ae97-b14c21601fb5",
            "billingCode": null
          },
          "usageSource": "per_run",
          "costUsdExact": "0.076432000",
          "freshSession": true,
          "outputTokens": 905,
          "usageByModel": null,
          "sessionReused": false,
          "budgetDispatch": {
            "admittedAt": "2026-10-21T17:39:21.399Z",
            "handedOffAt": "2026-10-21T17:39:21.423Z",
            "reservationId": "37eb1ed1-2cc6-4f2d-b0e3-b367102c30bb",
            "recoveryLeaseOwner": null
          },
          "budgetExposure": {
            "sequence": 9,
            "sourceId": "b1282141-3c66-4845-92b0-197d87f82ae0",
            "costCents": "7.6432000"
          },
          "rawInputTokens": 27191,
          "sessionRotated": false,
          "configFreshness": {
            "session": {
              "reset": true,
              "categories": [
                "adapter",
                "adapterConfig",
                "agentRuntimeConfig",
                "instructions",
                "issueOverrides",
                "workspaceConfig",
                "environment",
                "envBindings",
                "secrets",
                "runtimeSkills"
              ],
              "resetReasons": [
                "effective run configuration fingerprint metadata is missing"
              ],
              "nextFingerprint": "v1:sha256:c456d6f776ebc9649d4b7fcdf3be3fb2d8b9589b4deaa2428b95e1d8dfae527c",
              "changedCategories": [
                "adapter",
                "adapterConfig",
                "agentRuntimeConfig",
                "instructions",
                "issueOverrides",
                "workspaceConfig",
                "environment",
                "envBindings",
                "secrets",
                "runtimeSkills"
              ],
              "taskSessionReused": false,
              "fingerprintVersion": 1,
              "taskSessionAvailable": true,
              "storedFingerprintPresent": false
            },
            "version": 1,
            "workspace": {
              "action": "reuse",
              "reasons": [],
              "categories": [
                "mode",
                "projectWorkspace",
                "strategy",
                "repo",
                "lifecycleCommands",
                "runtimeServices",
                "environment",
                "realization"
              ],
              "reuseRequested": true,
              "nextFingerprint": "v1:sha256:bb1a16269dbbdce9be2c25e24e950560afac60c0478d1ae2e4345f6e671d02f4",
              "workspaceReused": true,
              "activeWorkspaceId": "45d88166-b3d3-46aa-a017-1cad32833a54",
              "changedCategories": [],
              "storedFingerprint": "v1:sha256:bb1a16269dbbdce9be2c25e24e950560afac60c0478d1ae2e4345f6e671d02f4",
              "fingerprintVersion": 1,
              "inferredFingerprint": null,
              "previousWorkspaceId": "45d88166-b3d3-46aa-a017-1cad32833a54",
              "configSnapshotRefreshed": false,
              "storedFingerprintPresent": true
            }
          },
          "rawOutputTokens": 905,
          "cacheWriteTokens": 0,
          "cachedInputTokens": 130000,
          "pricingProvenance": {
            "source": "rate_card",
            "version": "openai-standard-2026-09-30",
            "evidence": "https://developers.openai.com/api/docs/pricing; standard processing assumed; short per-request context assumed; cache writes reported",
            "contextTier": "short",
            "serviceTier": "standard",
            "inputCentsPerMillion": "200.0000000",
            "outputCentsPerMillion": "1000.0000000",
            "cacheWriteCentsPerMillion": "250.0000000",
            "cachedInputCentsPerMillion": "10.0000000"
          },
          "providerRequestId": null,
          "taskSessionReused": false,
          "persistedSessionId": "01a15f8b-dac3-7010-8991-8027043e1e79",
          "accountingReceiptId": "a09b3c41-da6b-47d0-96e5-af03ed67e5bc",
          "cacheAdjustedCostUsd": null,
          "rawCachedInputTokens": 130000,
          "sessionRotationReason": null,
          "accountingReceiptReady": true,
          "rawInputIncludesCached": false,
          "accountingReceiptSequence": 9,
          "accountingReceiptSourceId": "b1282141-3c66-4845-92b0-197d87f82ae0",
          "accountingReceiptReceivedAt": "2026-10-21T17:39:51.927Z"
        }
      },
      {
        "runId": "c3afddf9-877d-45ec-8969-0bb61835027f",
        "usage": {
          "model": "gpt-6.1-sol",
          "biller": "openai",
          "costUsd": null,
          "provider": "openai",
          "costStatus": "estimated",
          "billingType": "metered_api",
          "inputTokens": 25527,
          "ledgerScope": {
            "issueId": "47d02fa1-3917-44bf-b084-0be8db9ec0bd",
            "projectId": "77904efe-00ea-4201-ae97-b14c21601fb5",
            "billingCode": null
          },
          "usageSource": "per_run",
          "costUsdExact": "0.066329500",
          "outputTokens": 537,
          "usageByModel": null,
          "budgetDispatch": {
            "admittedAt": "2026-10-21T17:38:45.623Z",
            "handedOffAt": "2026-10-21T17:38:45.644Z",
            "reservationId": "c23bb0a5-c8d0-4204-a667-0a42b1e483b9",
            "recoveryLeaseOwner": null
          },
          "budgetExposure": {
            "sequence": 6,
            "sourceId": "1bfd1ceb-a8b6-4f31-a51b-a9548cd6c143",
            "costCents": "6.6329500"
          },
          "cacheWriteTokens": 0,
          "cachedInputTokens": 99055,
          "pricingProvenance": {
            "source": "rate_card",
            "version": "openai-standard-2026-09-30",
            "evidence": "https://developers.openai.com/api/docs/pricing; standard processing assumed; short per-request context assumed; cache writes reported",
            "contextTier": "short",
            "serviceTier": "standard",
            "inputCentsPerMillion": "200.0000000",
            "outputCentsPerMillion": "1000.0000000",
            "cacheWriteCentsPerMillion": "250.0000000",
            "cachedInputCentsPerMillion": "10.0000000"
          },
          "providerRequestId": null,
          "accountingReceiptId": "b7e502ee-e6eb-4b5f-affc-3689d91488f7",
          "cacheAdjustedCostUsd": null,
          "accountingReceiptReady": true,
          "accountingReceiptSequence": 6,
          "accountingReceiptSourceId": "1bfd1ceb-a8b6-4f31-a51b-a9548cd6c143",
          "accountingReceiptReceivedAt": "2026-10-21T17:39:12.407Z"
        }
      }
    ]
  }
}
Claude staging-model diagnosticIsolated localacpx · claude-opus-5-5
followup-stop-resume failed
Overall failed · 2/5 behavioral checks passed

Failed checks:

  • followupStopResume.one-explicit-resumption — Only one user-triggered successor may complete the original task after Stop.
  • followupStopResume.retained-context-workspace-tools — The independently seeded context, earlier follow-up, workspace, production instructions and tool contract must survive without being restated in the resume message.
  • followupStopResume.accessible-resumed-result — One receipt-bound final reply must expose the independently verified result without a pending question.
See all behavioral checks (5)
ResultCheckDetail
PassfollowupStopResume.active-followup-before-stopOne ordinary user follow-up must persist while the original result-free provider run is still active.
PassfollowupStopResume.stop-remains-authoritativeThe acknowledged Stop must retain one cancelled run with no automatic continuation throughout the recorded quiet window before a real user resumes.
FailfollowupStopResume.one-explicit-resumptionOnly one user-triggered successor may complete the original task after Stop.
FailfollowupStopResume.retained-context-workspace-toolsThe independently seeded context, earlier follow-up, workspace, production instructions and tool contract must survive without being restated in the resume message.
FailfollowupStopResume.accessible-resumed-resultOne receipt-bound final reply must expose the independently verified result without a pending question.

candidate failure

Stopped waiting for one persisted final reply and its matching delivery receipt: Recovery produced duplicate final replies
Test details2/5 checks · 1m 32s
Tokens44,011 in · 3,407 out247,065 cached · 2/2 runs covered
LLM spendUnavailable0/2 runs provider-priced
ExecutionLocal · not metered1m 12s agent
followup-stop-resume.runner-acpx-claude.local.followup-stop-resume
Attempt
1
Duration
1m 32s
Agent runtime
1m 12s
Runtime
native
Provider
acpx
Model
claude-opus-5-5
Issue
RUN-1

No result artifact was uploaded

Startup reuse evidence
RunWarmthEnvironment/leaseWorkspaceRunnerProvider processProvider sessionProvider launches
82be5917-71bd-40b2-a8a4-6c14fc27ac33unknown unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing) unknown
805dc036-f188-4a83-92ff-d655ab6b6a2aunknown unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing) unknown
ResultMatcherExpectationDetail
Pass json_path {"kind":"json_path","path":"followupStopResume.active-followup-before-stop","expected":true} One ordinary user follow-up must persist while the original result-free provider run is still active.
Pass json_path {"kind":"json_path","path":"followupStopResume.stop-remains-authoritative","expected":true} The acknowledged Stop must retain one cancelled run with no automatic continuation throughout the recorded quiet window before a real user resumes.
Fail json_path {"kind":"json_path","path":"followupStopResume.one-explicit-resumption","expected":true} Only one user-triggered successor may complete the original task after Stop.
Fail json_path {"kind":"json_path","path":"followupStopResume.retained-context-workspace-tools","expected":true} The independently seeded context, earlier follow-up, workspace, production instructions and tool contract must survive without being restated in the resume message.
Fail json_path {"kind":"json_path","path":"followupStopResume.accessible-resumed-result","expected":true} One receipt-bound final reply must expose the independently verified result without a pending question.
Usage and billing metadata
{
  "billing": {
    "llm": {
      "runCount": 2,
      "runsWithTokenUsage": 2,
      "runsWithReportedCost": 0,
      "inputTokens": 44011,
      "outputTokens": 3407,
      "cachedInputTokens": 247065,
      "totalTokens": 294483,
      "reportedCostUsd": 0,
      "costStatus": "unpriced"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 71536,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": {
    "runs": [
      {
        "runId": "82be5917-71bd-40b2-a8a4-6c14fc27ac33",
        "usage": {
          "model": "claude-opus-5-5",
          "biller": "anthropic",
          "costUsd": null,
          "provider": "anthropic",
          "costStatus": "estimated",
          "billingType": "metered_api",
          "inputTokens": 14613,
          "ledgerScope": {
            "issueId": "6751d436-8a79-437e-b176-26512b7d2979",
            "projectId": "8532a218-5d52-4a3a-ab56-6b57385e63f3",
            "billingCode": null
          },
          "usageSource": "per_run",
          "costUsdExact": "0.185528800",
          "freshSession": true,
          "outputTokens": 2080,
          "usageByModel": null,
          "sessionReused": false,
          "budgetDispatch": {
            "admittedAt": "2026-10-21T17:39:19.112Z",
            "handedOffAt": "2026-10-21T17:39:19.133Z",
            "reservationId": "39cf148c-1e3b-4b09-83cd-c728432e5c42",
            "recoveryLeaseOwner": null
          },
          "budgetExposure": {
            "sequence": 15,
            "sourceId": "e15d8f2e-98ab-4a3b-a9ef-72cc31fd4d1b",
            "costCents": "18.5528800"
          },
          "rawInputTokens": 14613,
          "sessionRotated": false,
          "configFreshness": {
            "session": {
              "reset": true,
              "categories": [
                "adapter",
                "adapterConfig",
                "agentRuntimeConfig",
                "instructions",
                "issueOverrides",
                "workspaceConfig",
                "environment",
                "envBindings",
                "secrets",
                "runtimeSkills"
              ],
              "resetReasons": [
                "effective run configuration fingerprint metadata is missing"
              ],
              "nextFingerprint": "v1:sha256:bf4ca7454229a1634d5cded87c2164ad9b87132c2dde9e37a0d07960e1ae3d90",
              "changedCategories": [
                "adapter",
                "adapterConfig",
                "agentRuntimeConfig",
                "instructions",
                "issueOverrides",
                "workspaceConfig",
                "environment",
                "envBindings",
                "secrets",
                "runtimeSkills"
              ],
              "taskSessionReused": false,
              "fingerprintVersion": 1,
              "taskSessionAvailable": true,
              "storedFingerprintPresent": false
            },
            "version": 1,
            "workspace": {
              "action": "reuse",
              "reasons": [],
              "categories": [
                "mode",
                "projectWorkspace",
                "strategy",
                "repo",
                "lifecycleCommands",
                "runtimeServices",
                "environment",
                "realization"
              ],
              "reuseRequested": true,
              "nextFingerprint": "v1:sha256:0c9476622b03f5ea97ac56767d2cf38a8d5f8d3e74631767839be85ef6b7eca1",
              "workspaceReused": true,
              "activeWorkspaceId": "bde5d18a-15d2-4a34-b215-bfcc281154b6",
              "changedCategories": [],
              "storedFingerprint": "v1:sha256:0c9476622b03f5ea97ac56767d2cf38a8d5f8d3e74631767839be85ef6b7eca1",
              "fingerprintVersion": 1,
              "inferredFingerprint": null,
              "previousWorkspaceId": "bde5d18a-15d2-4a34-b215-bfcc281154b6",
              "configSnapshotRefreshed": false,
              "storedFingerprintPresent": true
            }
          },
          "rawOutputTokens": 2080,
          "cacheWriteTokens": 14603,
          "cachedInputTokens": 135324,
          "pricingProvenance": {
            "source": "rate_card",
            "version": "anthropic-standard-2026-10-12",
            "evidence": "https://platform.claude.com/docs/en/about-claude/pricing; standard global API pricing assumed; cache-write TTL unavailable, one-hour upper rate used; not an invoice",
            "serviceTier": "standard",
            "inputCentsPerMillion": "400",
            "outputCentsPerMillion": "2000",
            "cacheWriteCentsPerMillion": "800",
            "cachedInputCentsPerMillion": "20"
          },
          "providerRequestId": null,
          "taskSessionReused": false,
          "persistedSessionId": "10b47446-6c9b-42f4-a0a4-3903e38c736f",
          "accountingReceiptId": "b5eaa3c1-0077-4965-af2d-2d60d4689953",
          "cacheAdjustedCostUsd": null,
          "rawCachedInputTokens": 135324,
          "sessionRotationReason": null,
          "accountingReceiptReady": true,
          "rawInputIncludesCached": false,
          "accountingReceiptSequence": 15,
          "accountingReceiptSourceId": "e15d8f2e-98ab-4a3b-a9ef-72cc31fd4d1b",
          "accountingReceiptReceivedAt": "2026-10-21T17:39:54.949Z"
        }
      },
      {
        "runId": "805dc036-f188-4a83-92ff-d655ab6b6a2a",
        "usage": {
          "model": "claude-opus-5-5",
          "biller": "anthropic",
          "costUsd": null,
          "provider": "anthropic",
          "costStatus": "estimated",
          "billingType": "metered_api",
          "inputTokens": 29398,
          "ledgerScope": {
            "issueId": "6751d436-8a79-437e-b176-26512b7d2979",
            "projectId": "8532a218-5d52-4a3a-ab56-6b57385e63f3",
            "billingCode": null
          },
          "usageSource": "per_run",
          "costUsdExact": "0.284032200",
          "outputTokens": 1327,
          "usageByModel": null,
          "budgetDispatch": {
            "admittedAt": "2026-10-21T17:38:35.479Z",
            "handedOffAt": "2026-10-21T17:38:35.500Z",
            "reservationId": "fff01413-4938-4d8d-9949-09db7bf7b512",
            "recoveryLeaseOwner": null
          },
          "budgetExposure": {
            "sequence": 14,
            "sourceId": "b582741f-34df-44f3-9129-6a88589bdacf",
            "costCents": "28.4032200"
          },
          "cacheWriteTokens": 29388,
          "cachedInputTokens": 111741,
          "pricingProvenance": {
            "source": "rate_card",
            "version": "anthropic-standard-2026-10-12",
            "evidence": "https://platform.claude.com/docs/en/about-claude/pricing; standard global API pricing assumed; cache-write TTL unavailable, one-hour upper rate used; not an invoice",
            "serviceTier": "standard",
            "inputCentsPerMillion": "400.0000000",
            "outputCentsPerMillion": "2000.0000000",
            "cacheWriteCentsPerMillion": "800.0000000",
            "cachedInputCentsPerMillion": "20.0000000"
          },
          "providerRequestId": null,
          "accountingReceiptId": "89625cc8-3a60-4468-a320-c2041bae32af",
          "cacheAdjustedCostUsd": null,
          "accountingReceiptReady": true,
          "accountingReceiptSequence": 14,
          "accountingReceiptSourceId": "b582741f-34df-44f3-9129-6a88589bdacf",
          "accountingReceiptReceivedAt": "2026-10-21T17:39:09.298Z"
        }
      }
    ]
  }
}
Screenshot evidence
Environment:
Duration Tokens Tests
Open original image ↗