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.

2026-10-21T14:48:54.335Zc4e409d8Source run ↗

6/8Passed

2Failed

12m 35sTest time

necessary-question 2/2 Passed
configured-repository 2/2 Passed
legacy-conversion 2/2 Passed
automatic-repository-configured-models 0/2 Needs attention

Campaign usage and spend

233,407Input tokens

17,563Output tokens

2,184,023Cached tokens

UnavailableLLM reported subtotal

$0.000000Daytona list estimate

9m 59sAgent execution time

0msDaytona lease time

0/10Runs 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 8 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

Feature	Capabilities linked	Linked 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

Feature	Capabilities linked	Linked 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

Feature	Capabilities linked	Linked 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

Feature	Capabilities linked	Linked 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

Feature	Capabilities linked	Linked 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

Feature	Capabilities linked	Linked 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

Feature	Capabilities linked	Linked 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

Feature	Capabilities linked	Linked test results
Developer previews and diagnostic labs	0/4	No mapped journey

Search tests Feature Agent profile Environment Suite Status

Test suite

necessary-question

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

Pass rate100.0%2/2 passed

Tokens693,21586,212 input · 3,188 output

Known spendUnavailablereported LLM + runtime estimate

Agent time1m 43s0ms lease

Execution2/20 retries · cleanup passed

necessary-free-text

Inspect case ↗

Runner CodexIsolated localcodex · gpt-5.6-sol

necessary-free-text passed

Test details19/19 checks · 1m 22s

Overall passed · 19/19 behavioral checks passed

No behavioral matcher failed.

See all behavioral checks (19)

Result	Check	Detail
Pass	`continuation.recorded-continuation`	Initial and final turns must both be recorded.
Pass	`continuation.initial.no-premature-output`	initial: only a plan may exist before the required answer/approval; documents=, attachments=0, status=in_review
Pass	`continuation.updated-output`	Durable output must contain the user's current word, without the superseded or injected word.
Pass	`continuation.completed-parent`	Final parent status: done
Pass	`continuation.successful-provider-turns`	Every recorded turn succeeded in the selected runtime.
Pass	`continuation.no-unrequested-children`	No checkpoint may contain an unrequested child task.
Pass	`continuation.lifecycle.evidence-present`	Every checkpoint must retain lifecycle evidence from the public task API.
Pass	`continuation.lifecycle.task-owner-preserved`	Waiting and resuming retain the same task and assigned agent.
Pass	`continuation.lifecycle.initial.durable-wait`	Waiting must have an identifiable pending interaction, not only an assistant message.
Pass	`continuation.lifecycle.initial.wait-state`	A settled wait is in_review with no execution lock, retry, recovery or monitor. A bound native provider question may keep its paused run and lock.
Pass	`continuation.lifecycle.final.no-active-path`	Completed work has no live run, execution lock, scheduled retry, recovery or monitor.
Pass	`continuation.lifecycle.final.no-pending-interaction`	Completion has no unresolved interaction.
Pass	`continuation.lifecycle.answer:580be468-768d-4f82-a469-d03c759a6e0b`	Every observed pending question retains exactly one answered identity, including later questions.
Pass	`continuation.lifecycle.final.preserved-runs`	All intermediate run receipts survive in the final snapshot without duplicated or empty IDs.
Pass	`continuation.necessary-question.form`	One bound text-only question must show the required prompt and its explanation before delivery.
Pass	`continuation.necessary-question.visible`	The browser must observe the actual question and context, not only its title.
Pass	`continuation.necessary-question.answer`	One real user answer must remain attached to the unchanged question.
Pass	`continuation.necessary-question.one-continuation`	The answer must resume its bound provider run or admit exactly one bound semantic successor, without duplicate work.
Pass	`continuation.necessary-question.result`	The final reply must open this task's saved confirmation and show its exact answer.

Tokens69,716 in · 1,568 out434,195 cached · 2/2 runs covered

LLM spendUnavailable0/2 runs provider-priced

ExecutionLocal · not metered52s agent

necessary-question.runner-codex.local.necessary-free-text

Attempt: 1
Duration: 1m 22s
Agent runtime: 52s
Runtime: native
Provider: codex
Model: gpt-6.1-sol
Issue: RUN-1

All invariants passed

Startup reuse evidence
Run	Warmth	Environment/lease	Workspace	Runner	Provider process	Provider session	Provider launches
`a84fb6cf-9944-497e-9477-366adf777729`	unknown	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown
`1f3618c8-9070-4ce8-bec8-8e643a272f71`	unknown	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown

Result	Matcher	Expectation	Detail
Pass	`json_path`	{"kind":"json_path","path":"continuation.recorded-continuation","expected":true}	Initial and final turns must both be recorded.
Pass	`json_path`	{"kind":"json_path","path":"continuation.initial.no-premature-output","expected":true}	initial: only a plan may exist before the required answer/approval; documents=, attachments=0, status=in_review
Pass	`json_path`	{"kind":"json_path","path":"continuation.updated-output","expected":true}	Durable output must contain the user's current word, without the superseded or injected word.
Pass	`json_path`	{"kind":"json_path","path":"continuation.completed-parent","expected":true}	Final parent status: done
Pass	`json_path`	{"kind":"json_path","path":"continuation.successful-provider-turns","expected":true}	Every recorded turn succeeded in the selected runtime.
Pass	`json_path`	{"kind":"json_path","path":"continuation.no-unrequested-children","expected":true}	No checkpoint may contain an unrequested child task.
Pass	`json_path`	{"kind":"json_path","path":"continuation.lifecycle.evidence-present","expected":true}	Every checkpoint must retain lifecycle evidence from the public task API.
Pass	`json_path`	{"kind":"json_path","path":"continuation.lifecycle.task-owner-preserved","expected":true}	Waiting and resuming retain the same task and assigned agent.
Pass	`json_path`	{"kind":"json_path","path":"continuation.lifecycle.initial.durable-wait","expected":true}	Waiting must have an identifiable pending interaction, not only an assistant message.
Pass	`json_path`	{"kind":"json_path","path":"continuation.lifecycle.initial.wait-state","expected":true}	A settled wait is in_review with no execution lock, retry, recovery or monitor. A bound native provider question may keep its paused run and lock.
Pass	`json_path`	{"kind":"json_path","path":"continuation.lifecycle.final.no-active-path","expected":true}	Completed work has no live run, execution lock, scheduled retry, recovery or monitor.
Pass	`json_path`	{"kind":"json_path","path":"continuation.lifecycle.final.no-pending-interaction","expected":true}	Completion has no unresolved interaction.
Pass	`json_path`	{"kind":"json_path","path":"continuation.lifecycle.answer:580be468-768d-4f82-a469-d03c759a6e0b","expected":true}	Every observed pending question retains exactly one answered identity, including later questions.
Pass	`json_path`	{"kind":"json_path","path":"continuation.lifecycle.final.preserved-runs","expected":true}	All intermediate run receipts survive in the final snapshot without duplicated or empty IDs.
Pass	`json_path`	{"kind":"json_path","path":"continuation.necessary-question.form","expected":true}	One bound text-only question must show the required prompt and its explanation before delivery.
Pass	`json_path`	{"kind":"json_path","path":"continuation.necessary-question.visible","expected":true}	The browser must observe the actual question and context, not only its title.
Pass	`json_path`	{"kind":"json_path","path":"continuation.necessary-question.answer","expected":true}	One real user answer must remain attached to the unchanged question.
Pass	`json_path`	{"kind":"json_path","path":"continuation.necessary-question.one-continuation","expected":true}	The answer must resume its bound provider run or admit exactly one bound semantic successor, without duplicate work.
Pass	`json_path`	{"kind":"json_path","path":"continuation.necessary-question.result","expected":true}	The final reply must open this task's saved confirmation and show its exact answer.

Usage and billing metadata

{
  "billing": {
    "llm": {
      "runCount": 2,
      "runsWithTokenUsage": 2,
      "runsWithReportedCost": 0,
      "inputTokens": 69716,
      "outputTokens": 1568,
      "cachedInputTokens": 434195,
      "totalTokens": 505479,
      "reportedCostUsd": 0,
      "costStatus": "unpriced"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 51886,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": {
    "runs": [
      {
        "runId": "a84fb6cf-9944-497e-9477-366adf777729",
        "usage": {
          "model": "gpt-6.1-sol",
          "biller": "openai",
          "costUsd": null,
          "provider": "openai",
          "costStatus": "estimated",
          "billingType": "metered_api",
          "inputTokens": 36092,
          "ledgerScope": {
            "issueId": "acb5becf-09ec-4c94-b259-8b6eb6e7d9a1",
            "projectId": null,
            "billingCode": null
          },
          "usageSource": "per_run",
          "costUsdExact": "0.108456600",
          "freshSession": false,
          "outputTokens": 922,
          "usageByModel": null,
          "sessionReused": true,
          "budgetDispatch": {
            "admittedAt": "2026-10-21T14:47:08.867Z",
            "handedOffAt": "2026-10-21T14:47:08.902Z",
            "reservationId": "03db837f-297a-4de6-b671-f25129813681",
            "recoveryLeaseOwner": null
          },
          "budgetExposure": {
            "sequence": 6,
            "sourceId": "697e4a0d-0ecb-4141-bf74-4f76ae9c55b0",
            "costCents": "10.8456600"
          },
          "rawInputTokens": 36092,
          "sessionRotated": false,
          "configFreshness": {
            "session": {
              "reset": false,
              "categories": [
                "adapter",
                "adapterConfig",
                "agentRuntimeConfig",
                "instructions",
                "issueOverrides",
                "workspaceConfig",
                "environment",
                "envBindings",
                "secrets",
                "runtimeSkills"
              ],
              "resetReasons": [],
              "nextFingerprint": "v1:sha256:d86546ada0e2727dd7e6f21bd23c63a2d832a5001c8adb255a0906f89fb553f6",
              "changedCategories": [],
              "taskSessionReused": true,
              "fingerprintVersion": 1,
              "taskSessionAvailable": true,
              "storedFingerprintPresent": true
            },
            "version": 1,
            "workspace": {
              "action": "reuse",
              "reasons": [],
              "categories": [
                "mode",
                "projectWorkspace",
                "strategy",
                "repo",
                "lifecycleCommands",
                "runtimeServices",
                "environment",
                "realization"
              ],
              "reuseRequested": true,
              "nextFingerprint": "v1:sha256:cdfeeff8aa564ce97d967bb60197e344137522996d1174cc2d1de2747db20738",
              "workspaceReused": true,
              "activeWorkspaceId": "e9eea465-4477-4f13-8c9f-3d7ba8e8b945",
              "changedCategories": [],
              "storedFingerprint": "v1:sha256:cdfeeff8aa564ce97d967bb60197e344137522996d1174cc2d1de2747db20738",
              "fingerprintVersion": 1,
              "inferredFingerprint": null,
              "previousWorkspaceId": "e9eea465-4477-4f13-8c9f-3d7ba8e8b945",
              "configSnapshotRefreshed": false,
              "storedFingerprintPresent": true
            }
          },
          "rawOutputTokens": 922,
          "cacheWriteTokens": 0,
          "cachedInputTokens": 270526,
          "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": true,
          "persistedSessionId": "01a15eed-8674-7ff0-99ed-4bc86f8b93e8",
          "accountingReceiptId": "9b52b6e9-ee7d-4945-95fa-bce145d8019e",
          "cacheAdjustedCostUsd": null,
          "rawCachedInputTokens": 270526,
          "sessionRotationReason": null,
          "accountingReceiptReady": true,
          "rawInputIncludesCached": false,
          "accountingReceiptSequence": 6,
          "accountingReceiptSourceId": "697e4a0d-0ecb-4141-bf74-4f76ae9c55b0",
          "accountingReceiptReceivedAt": "2026-10-21T14:47:25.468Z"
        }
      },
      {
        "runId": "1f3618c8-9070-4ce8-bec8-8e643a272f71",
        "usage": {
          "model": "gpt-6.1-sol",
          "biller": "openai",
          "costUsd": null,
          "provider": "openai",
          "costStatus": "estimated",
          "billingType": "metered_api",
          "inputTokens": 33624,
          "ledgerScope": {
            "issueId": "acb5becf-09ec-4c94-b259-8b6eb6e7d9a1",
            "projectId": null,
            "billingCode": null
          },
          "usageSource": "per_run",
          "costUsdExact": "0.090074900",
          "freshSession": true,
          "outputTokens": 646,
          "usageByModel": null,
          "sessionReused": false,
          "budgetDispatch": {
            "admittedAt": "2026-10-21T14:46:25.470Z",
            "handedOffAt": "2026-10-21T14:46:25.490Z",
            "reservationId": "41e5fc1d-0615-4cbd-a657-50fc5feb6ead",
            "recoveryLeaseOwner": null
          },
          "budgetExposure": {
            "sequence": 10,
            "sourceId": "3491d04f-f3ca-4999-82ba-0ce5333c45c8",
            "costCents": "9.0074900"
          },
          "rawInputTokens": 33624,
          "sessionRotated": false,
          "configFreshness": {
            "session": {
              "reset": true,
              "categories": [
                "adapter",
                "adapterConfig",
                "agentRuntimeConfig",
                "instructions",
                "issueOverrides",
                "workspaceConfig",
                "environment",
                "envBindings",
                "secrets",
                "runtimeSkills"
              ],
              "resetReasons": [],
              "nextFingerprint": "v1:sha256:d86546ada0e2727dd7e6f21bd23c63a2d832a5001c8adb255a0906f89fb553f6",
              "changedCategories": [],
              "taskSessionReused": false,
              "fingerprintVersion": 1,
              "taskSessionAvailable": false,
              "storedFingerprintPresent": false
            },
            "version": 1,
            "workspace": {
              "action": "create",
              "reasons": [],
              "categories": [
                "mode",
                "projectWorkspace",
                "strategy",
                "repo",
                "lifecycleCommands",
                "runtimeServices",
                "environment",
                "realization"
              ],
              "reuseRequested": false,
              "nextFingerprint": "v1:sha256:cdfeeff8aa564ce97d967bb60197e344137522996d1174cc2d1de2747db20738",
              "workspaceReused": false,
              "activeWorkspaceId": "e9eea465-4477-4f13-8c9f-3d7ba8e8b945",
              "changedCategories": [],
              "storedFingerprint": null,
              "fingerprintVersion": 1,
              "inferredFingerprint": null,
              "previousWorkspaceId": null,
              "configSnapshotRefreshed": false,
              "storedFingerprintPresent": false
            }
          },
          "rawOutputTokens": 646,
          "cacheWriteTokens": 0,
          "cachedInputTokens": 163669,
          "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": "01a15eed-8674-7ff0-99ed-4bc86f8b93e8",
          "accountingReceiptId": "3317fba6-fc55-4bf2-b00e-bbd3c0d80afa",
          "cacheAdjustedCostUsd": null,
          "rawCachedInputTokens": 163669,
          "sessionRotationReason": null,
          "accountingReceiptReady": true,
          "rawInputIncludesCached": false,
          "accountingReceiptSequence": 10,
          "accountingReceiptSourceId": "3491d04f-f3ca-4999-82ba-0ce5333c45c8",
          "accountingReceiptReceivedAt": "2026-10-21T14:46:58.493Z"
        }
      }
    ]
  }
}

Runner ACPX ClaudeIsolated localacpx · claude-sonnet-5

necessary-free-text passed

Test details19/19 checks · 1m 19s

Overall passed · 19/19 behavioral checks passed

No behavioral matcher failed.

See all behavioral checks (19)

Result	Check	Detail
Pass	`continuation.recorded-continuation`	Initial and final turns must both be recorded.
Pass	`continuation.initial.no-premature-output`	initial: only a plan may exist before the required answer/approval; documents=, attachments=0, status=in_review
Pass	`continuation.updated-output`	Durable output must contain the user's current word, without the superseded or injected word.
Pass	`continuation.completed-parent`	Final parent status: done
Pass	`continuation.successful-provider-turns`	Every recorded turn succeeded in the selected runtime.
Pass	`continuation.no-unrequested-children`	No checkpoint may contain an unrequested child task.
Pass	`continuation.lifecycle.evidence-present`	Every checkpoint must retain lifecycle evidence from the public task API.
Pass	`continuation.lifecycle.task-owner-preserved`	Waiting and resuming retain the same task and assigned agent.
Pass	`continuation.lifecycle.initial.durable-wait`	Waiting must have an identifiable pending interaction, not only an assistant message.
Pass	`continuation.lifecycle.initial.wait-state`	A settled wait is in_review with no execution lock, retry, recovery or monitor. A bound native provider question may keep its paused run and lock.
Pass	`continuation.lifecycle.final.no-active-path`	Completed work has no live run, execution lock, scheduled retry, recovery or monitor.
Pass	`continuation.lifecycle.final.no-pending-interaction`	Completion has no unresolved interaction.
Pass	`continuation.lifecycle.answer:3ee88864-7914-41f4-9485-fe555734a3c8`	Every observed pending question retains exactly one answered identity, including later questions.
Pass	`continuation.lifecycle.final.preserved-runs`	All intermediate run receipts survive in the final snapshot without duplicated or empty IDs.
Pass	`continuation.necessary-question.form`	One bound text-only question must show the required prompt and its explanation before delivery.
Pass	`continuation.necessary-question.visible`	The browser must observe the actual question and context, not only its title.
Pass	`continuation.necessary-question.answer`	One real user answer must remain attached to the unchanged question.
Pass	`continuation.necessary-question.one-continuation`	The answer must resume its bound provider run or admit exactly one bound semantic successor, without duplicate work.
Pass	`continuation.necessary-question.result`	The final reply must open this task's saved confirmation and show its exact answer.

Tokens16,496 in · 1,620 out169,620 cached · 2/2 runs covered

LLM spendUnavailable0/2 runs provider-priced

ExecutionLocal · not metered51s agent

necessary-question.runner-acpx-claude.local.necessary-free-text

Attempt: 1
Duration: 1m 19s
Agent runtime: 51s
Runtime: native
Provider: acpx
Model: claude-opus-5-5
Issue: RUN-1

All invariants passed

Startup reuse evidence
Run	Warmth	Environment/lease	Workspace	Runner	Provider process	Provider session	Provider launches
`369da056-8a06-4f1a-9a09-3cff2167c594`	unknown	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown
`7ecf69c0-b628-422f-b8ee-6adf44334c21`	unknown	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown

Result	Matcher	Expectation	Detail
Pass	`json_path`	{"kind":"json_path","path":"continuation.recorded-continuation","expected":true}	Initial and final turns must both be recorded.
Pass	`json_path`	{"kind":"json_path","path":"continuation.initial.no-premature-output","expected":true}	initial: only a plan may exist before the required answer/approval; documents=, attachments=0, status=in_review
Pass	`json_path`	{"kind":"json_path","path":"continuation.updated-output","expected":true}	Durable output must contain the user's current word, without the superseded or injected word.
Pass	`json_path`	{"kind":"json_path","path":"continuation.completed-parent","expected":true}	Final parent status: done
Pass	`json_path`	{"kind":"json_path","path":"continuation.successful-provider-turns","expected":true}	Every recorded turn succeeded in the selected runtime.
Pass	`json_path`	{"kind":"json_path","path":"continuation.no-unrequested-children","expected":true}	No checkpoint may contain an unrequested child task.
Pass	`json_path`	{"kind":"json_path","path":"continuation.lifecycle.evidence-present","expected":true}	Every checkpoint must retain lifecycle evidence from the public task API.
Pass	`json_path`	{"kind":"json_path","path":"continuation.lifecycle.task-owner-preserved","expected":true}	Waiting and resuming retain the same task and assigned agent.
Pass	`json_path`	{"kind":"json_path","path":"continuation.lifecycle.initial.durable-wait","expected":true}	Waiting must have an identifiable pending interaction, not only an assistant message.
Pass	`json_path`	{"kind":"json_path","path":"continuation.lifecycle.initial.wait-state","expected":true}	A settled wait is in_review with no execution lock, retry, recovery or monitor. A bound native provider question may keep its paused run and lock.
Pass	`json_path`	{"kind":"json_path","path":"continuation.lifecycle.final.no-active-path","expected":true}	Completed work has no live run, execution lock, scheduled retry, recovery or monitor.
Pass	`json_path`	{"kind":"json_path","path":"continuation.lifecycle.final.no-pending-interaction","expected":true}	Completion has no unresolved interaction.
Pass	`json_path`	{"kind":"json_path","path":"continuation.lifecycle.answer:3ee88864-7914-41f4-9485-fe555734a3c8","expected":true}	Every observed pending question retains exactly one answered identity, including later questions.
Pass	`json_path`	{"kind":"json_path","path":"continuation.lifecycle.final.preserved-runs","expected":true}	All intermediate run receipts survive in the final snapshot without duplicated or empty IDs.
Pass	`json_path`	{"kind":"json_path","path":"continuation.necessary-question.form","expected":true}	One bound text-only question must show the required prompt and its explanation before delivery.
Pass	`json_path`	{"kind":"json_path","path":"continuation.necessary-question.visible","expected":true}	The browser must observe the actual question and context, not only its title.
Pass	`json_path`	{"kind":"json_path","path":"continuation.necessary-question.answer","expected":true}	One real user answer must remain attached to the unchanged question.
Pass	`json_path`	{"kind":"json_path","path":"continuation.necessary-question.one-continuation","expected":true}	The answer must resume its bound provider run or admit exactly one bound semantic successor, without duplicate work.
Pass	`json_path`	{"kind":"json_path","path":"continuation.necessary-question.result","expected":true}	The final reply must open this task's saved confirmation and show its exact answer.

Usage and billing metadata

{
  "billing": {
    "llm": {
      "runCount": 2,
      "runsWithTokenUsage": 2,
      "runsWithReportedCost": 0,
      "inputTokens": 16496,
      "outputTokens": 1620,
      "cachedInputTokens": 169620,
      "totalTokens": 187736,
      "reportedCostUsd": 0,
      "costStatus": "unpriced"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 50764,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": {
    "runs": [
      {
        "runId": "369da056-8a06-4f1a-9a09-3cff2167c594",
        "usage": {
          "model": "claude-opus-5-5",
          "biller": "anthropic",
          "costUsd": null,
          "provider": "anthropic",
          "costStatus": "estimated",
          "billingType": "metered_api",
          "inputTokens": 3874,
          "ledgerScope": {
            "issueId": "f825f3f3-40f5-46ee-b66b-9baef189356f",
            "projectId": null,
            "billingCode": null
          },
          "usageSource": "per_run",
          "costUsdExact": "0.076726000",
          "freshSession": false,
          "outputTokens": 1030,
          "usageByModel": null,
          "sessionReused": true,
          "budgetDispatch": {
            "admittedAt": "2026-10-21T14:43:59.733Z",
            "handedOffAt": "2026-10-21T14:43:59.767Z",
            "reservationId": "6db5b106-85b9-447b-8e54-f156fd59a009",
            "recoveryLeaseOwner": null
          },
          "budgetExposure": {
            "sequence": 13,
            "sourceId": "50ce8ccb-1a23-4ca4-b099-21c083cb1dea",
            "costCents": "7.6726000"
          },
          "rawInputTokens": 3874,
          "sessionRotated": false,
          "configFreshness": {
            "session": {
              "reset": false,
              "categories": [
                "adapter",
                "adapterConfig",
                "agentRuntimeConfig",
                "instructions",
                "issueOverrides",
                "workspaceConfig",
                "environment",
                "envBindings",
                "secrets",
                "runtimeSkills"
              ],
              "resetReasons": [],
              "nextFingerprint": "v1:sha256:423aa0bd7c6a8883cdd42de7e1b5c94f284c2486cf91c1d703daf5bdab96cccd",
              "changedCategories": [],
              "taskSessionReused": true,
              "fingerprintVersion": 1,
              "taskSessionAvailable": true,
              "storedFingerprintPresent": true
            },
            "version": 1,
            "workspace": {
              "action": "reuse",
              "reasons": [],
              "categories": [
                "mode",
                "projectWorkspace",
                "strategy",
                "repo",
                "lifecycleCommands",
                "runtimeServices",
                "environment",
                "realization"
              ],
              "reuseRequested": true,
              "nextFingerprint": "v1:sha256:bd5dff28de3fe1cc71198f78eaf57d784f2983d358f705e36fe57fe5fa9198a3",
              "workspaceReused": true,
              "activeWorkspaceId": "4ca50dee-e0d5-417a-8a0b-66577685c8cf",
              "changedCategories": [],
              "storedFingerprint": "v1:sha256:bd5dff28de3fe1cc71198f78eaf57d784f2983d358f705e36fe57fe5fa9198a3",
              "fingerprintVersion": 1,
              "inferredFingerprint": null,
              "previousWorkspaceId": "4ca50dee-e0d5-417a-8a0b-66577685c8cf",
              "configSnapshotRefreshed": false,
              "storedFingerprintPresent": true
            }
          },
          "rawOutputTokens": 1030,
          "cacheWriteTokens": 3866,
          "cachedInputTokens": 125830,
          "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": true,
          "persistedSessionId": "41aedaa4-eb08-4997-a27d-58799e43483a",
          "accountingReceiptId": "903f19ee-8588-4499-bc90-4449af064ace",
          "cacheAdjustedCostUsd": null,
          "rawCachedInputTokens": 125830,
          "sessionRotationReason": null,
          "accountingReceiptReady": true,
          "rawInputIncludesCached": false,
          "accountingReceiptSequence": 13,
          "accountingReceiptSourceId": "50ce8ccb-1a23-4ca4-b099-21c083cb1dea",
          "accountingReceiptReceivedAt": "2026-10-21T14:44:24.935Z"
        }
      },
      {
        "runId": "7ecf69c0-b628-422f-b8ee-6adf44334c21",
        "usage": {
          "model": "claude-opus-5-5",
          "biller": "anthropic",
          "costUsd": null,
          "provider": "anthropic",
          "costStatus": "estimated",
          "billingType": "metered_api",
          "inputTokens": 12622,
          "ledgerScope": {
            "issueId": "f825f3f3-40f5-46ee-b66b-9baef189356f",
            "projectId": null,
            "billingCode": null
          },
          "usageSource": "per_run",
          "costUsdExact": "0.121518000",
          "freshSession": true,
          "outputTokens": 590,
          "usageByModel": null,
          "sessionReused": false,
          "budgetDispatch": {
            "admittedAt": "2026-10-21T14:43:27.343Z",
            "handedOffAt": "2026-10-21T14:43:27.361Z",
            "reservationId": "88bad1a1-0256-4ec8-958d-4ca0a6d90051",
            "recoveryLeaseOwner": null
          },
          "budgetExposure": {
            "sequence": 10,
            "sourceId": "f52d9e5a-f826-4711-944f-a43a709f62c5",
            "costCents": "12.1518000"
          },
          "rawInputTokens": 12622,
          "sessionRotated": false,
          "configFreshness": {
            "session": {
              "reset": true,
              "categories": [
                "adapter",
                "adapterConfig",
                "agentRuntimeConfig",
                "instructions",
                "issueOverrides",
                "workspaceConfig",
                "environment",
                "envBindings",
                "secrets",
                "runtimeSkills"
              ],
              "resetReasons": [],
              "nextFingerprint": "v1:sha256:423aa0bd7c6a8883cdd42de7e1b5c94f284c2486cf91c1d703daf5bdab96cccd",
              "changedCategories": [],
              "taskSessionReused": false,
              "fingerprintVersion": 1,
              "taskSessionAvailable": false,
              "storedFingerprintPresent": false
            },
            "version": 1,
            "workspace": {
              "action": "create",
              "reasons": [],
              "categories": [
                "mode",
                "projectWorkspace",
                "strategy",
                "repo",
                "lifecycleCommands",
                "runtimeServices",
                "environment",
                "realization"
              ],
              "reuseRequested": false,
              "nextFingerprint": "v1:sha256:bd5dff28de3fe1cc71198f78eaf57d784f2983d358f705e36fe57fe5fa9198a3",
              "workspaceReused": false,
              "activeWorkspaceId": "4ca50dee-e0d5-417a-8a0b-66577685c8cf",
              "changedCategories": [],
              "storedFingerprint": null,
              "fingerprintVersion": 1,
              "inferredFingerprint": null,
              "previousWorkspaceId": null,
              "configSnapshotRefreshed": false,
              "storedFingerprintPresent": false
            }
          },
          "rawOutputTokens": 590,
          "cacheWriteTokens": 12618,
          "cachedInputTokens": 43790,
          "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": "41aedaa4-eb08-4997-a27d-58799e43483a",
          "accountingReceiptId": "7e4c519c-1e88-4654-b5ce-bc01e38818c1",
          "cacheAdjustedCostUsd": null,
          "rawCachedInputTokens": 43790,
          "sessionRotationReason": null,
          "accountingReceiptReady": true,
          "rawInputIncludesCached": false,
          "accountingReceiptSequence": 10,
          "accountingReceiptSourceId": "f52d9e5a-f826-4711-944f-a43a709f62c5",
          "accountingReceiptReceivedAt": "2026-10-21T14:43:50.403Z"
        }
      }
    ]
  }
}

Test suite

configured-repository

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

Pass rate100.0%2/2 passed

Tokens359,66340,733 input · 3,643 output

Known spendUnavailablereported LLM + runtime estimate

Agent time1m 38s0ms lease

Execution2/20 retries · cleanup passed

repository-output

Inspect case ↗

Runner CodexIsolated localcodex · gpt-5.6-sol

repository-output passed

Test details6/6 checks · 1m 5s

Overall passed · 6/6 behavioral checks passed

No behavioral matcher failed.

See all behavioral checks (6)

Result	Check	Detail
Pass	`repositoryVerification.production-conversion`	Conversion must start with a real legacy agent and use its production runner transition.
Pass	`repositoryVerification.retained-configuration`	Configured model, source directory, secret references, timeout, runtime settings, environment, instructions, and equivalent permissions must survive.
Pass	`repositoryVerification.actual-native-runtime`	One actual native admission on the configured provider and model must commit the task result.
Pass	`repositoryVerification.retained-repository`	The independently seeded source reference must survive byte for byte in the configured checkout.
Pass	`repositoryVerification.independent-result`	Downloaded bytes must agree with the independent source-file and Git baseline.
Pass	`repositoryVerification.accessible-delivery`	The originating task must render the downloadable result with no unanswered interaction.

Tokens25,843 in · 900 out99,063 cached · 1/1 runs covered

LLM spendUnavailable0/1 runs provider-priced

ExecutionLocal · not metered44s agent

configured-repository.runner-codex.local.repository-output

Attempt: 1
Duration: 1m 5s
Agent runtime: 44s
Runtime: native
Provider: codex
Model: gpt-6.1-sol
Issue: RUN-1

All invariants passed

Startup reuse evidence
Run	Warmth	Environment/lease	Workspace	Runner	Provider process	Provider session	Provider launches
`0af54d1a-4306-4d61-88c4-b652d9ed0b99`	unknown	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown

Result	Matcher	Expectation	Detail
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.production-conversion","expected":true}	Conversion must start with a real legacy agent and use its production runner transition.
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.retained-configuration","expected":true}	Configured model, source directory, secret references, timeout, runtime settings, environment, instructions, and equivalent permissions must survive.
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.actual-native-runtime","expected":true}	One actual native admission on the configured provider and model must commit the task result.
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.retained-repository","expected":true}	The independently seeded source reference must survive byte for byte in the configured checkout.
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.independent-result","expected":true}	Downloaded bytes must agree with the independent source-file and Git baseline.
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.accessible-delivery","expected":true}	The originating task must render the downloadable result with no unanswered interaction.

Usage and billing metadata

{
  "billing": {
    "llm": {
      "runCount": 1,
      "runsWithTokenUsage": 1,
      "runsWithReportedCost": 0,
      "inputTokens": 25843,
      "outputTokens": 900,
      "cachedInputTokens": 99063,
      "totalTokens": 125806,
      "reportedCostUsd": 0,
      "costStatus": "unpriced"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 43991,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": {
    "model": "gpt-6.1-sol",
    "biller": "openai",
    "costUsd": null,
    "provider": "openai",
    "costStatus": "estimated",
    "billingType": "metered_api",
    "inputTokens": 25843,
    "ledgerScope": {
      "issueId": "8b59b4ae-7397-44dc-a601-9f70da0bf39a",
      "projectId": "45f0fc47-1158-4ba4-b80a-c13c30cfc833",
      "billingCode": null
    },
    "usageSource": "per_run",
    "costUsdExact": "0.070592300",
    "freshSession": true,
    "outputTokens": 900,
    "usageByModel": null,
    "sessionReused": false,
    "budgetDispatch": {
      "admittedAt": "2026-10-21T14:39:14.346Z",
      "handedOffAt": "2026-10-21T14:39:14.377Z",
      "reservationId": "dc4adea4-fba7-4d86-94fe-d5fac2780741",
      "recoveryLeaseOwner": null
    },
    "budgetExposure": {
      "sequence": 8,
      "sourceId": "5f01633c-dce1-46ef-a48b-12693c641b70",
      "costCents": "7.0592300"
    },
    "rawInputTokens": 25843,
    "sessionRotated": false,
    "configFreshness": {
      "session": {
        "reset": true,
        "categories": [
          "adapter",
          "adapterConfig",
          "agentRuntimeConfig",
          "instructions",
          "issueOverrides",
          "workspaceConfig",
          "environment",
          "envBindings",
          "secrets",
          "runtimeSkills"
        ],
        "resetReasons": [],
        "nextFingerprint": "v1:sha256:c427872fc0fdbd195c9dcc4e26ed585a5d66a273791195f28c50240bb8844e32",
        "changedCategories": [],
        "taskSessionReused": false,
        "fingerprintVersion": 1,
        "taskSessionAvailable": false,
        "storedFingerprintPresent": false
      },
      "version": 1,
      "workspace": {
        "action": "create",
        "reasons": [],
        "categories": [
          "mode",
          "projectWorkspace",
          "strategy",
          "repo",
          "lifecycleCommands",
          "runtimeServices",
          "environment",
          "realization"
        ],
        "reuseRequested": false,
        "nextFingerprint": "v1:sha256:9dc4b1925fc18d782dba0bcf80649bfb1a93688b46fd4dc38f3a4ea46d15d886",
        "workspaceReused": false,
        "activeWorkspaceId": "f4963e60-7124-47cc-8ee4-f55c4b1ddc0f",
        "changedCategories": [],
        "storedFingerprint": null,
        "fingerprintVersion": 1,
        "inferredFingerprint": null,
        "previousWorkspaceId": null,
        "configSnapshotRefreshed": false,
        "storedFingerprintPresent": false
      }
    },
    "rawOutputTokens": 900,
    "cacheWriteTokens": 0,
    "cachedInputTokens": 99063,
    "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": "01a15ee6-fe0d-7991-b129-c936d0739237",
    "accountingReceiptId": "4e106959-b764-4b51-89e6-77c4d71995dc",
    "cacheAdjustedCostUsd": null,
    "rawCachedInputTokens": 99063,
    "sessionRotationReason": null,
    "accountingReceiptReady": true,
    "rawInputIncludesCached": false,
    "accountingReceiptSequence": 8,
    "accountingReceiptSourceId": "5f01633c-dce1-46ef-a48b-12693c641b70",
    "accountingReceiptReceivedAt": "2026-10-21T14:39:56.313Z"
  }
}

Runner ACPX ClaudeIsolated localacpx · claude-sonnet-5

repository-output passed

Test details6/6 checks · 1m 12s

Overall passed · 6/6 behavioral checks passed

No behavioral matcher failed.

See all behavioral checks (6)

Result	Check	Detail
Pass	`repositoryVerification.production-conversion`	Conversion must start with a real legacy agent and use its production runner transition.
Pass	`repositoryVerification.retained-configuration`	Configured model, source directory, secret references, timeout, runtime settings, environment, instructions, and equivalent permissions must survive.
Pass	`repositoryVerification.actual-native-runtime`	One actual native admission on the configured provider and model must commit the task result.
Pass	`repositoryVerification.retained-repository`	The independently seeded source reference must survive byte for byte in the configured checkout.
Pass	`repositoryVerification.independent-result`	Downloaded bytes must agree with the independent source-file and Git baseline.
Pass	`repositoryVerification.accessible-delivery`	The originating task must render the downloadable result with no unanswered interaction.

Tokens14,890 in · 2,743 out216,224 cached · 1/1 runs covered

LLM spendUnavailable0/1 runs provider-priced

ExecutionLocal · not metered54s agent

configured-repository.runner-acpx-claude.local.repository-output

Attempt: 1
Duration: 1m 12s
Agent runtime: 54s
Runtime: native
Provider: acpx
Model: claude-opus-5-5
Issue: RUN-1

All invariants passed

Startup reuse evidence
Run	Warmth	Environment/lease	Workspace	Runner	Provider process	Provider session	Provider launches
`ceb5b4d6-6095-4c0b-8b9b-93ceaf57049e`	unknown	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown

Result	Matcher	Expectation	Detail
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.production-conversion","expected":true}	Conversion must start with a real legacy agent and use its production runner transition.
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.retained-configuration","expected":true}	Configured model, source directory, secret references, timeout, runtime settings, environment, instructions, and equivalent permissions must survive.
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.actual-native-runtime","expected":true}	One actual native admission on the configured provider and model must commit the task result.
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.retained-repository","expected":true}	The independently seeded source reference must survive byte for byte in the configured checkout.
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.independent-result","expected":true}	Downloaded bytes must agree with the independent source-file and Git baseline.
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.accessible-delivery","expected":true}	The originating task must render the downloadable result with no unanswered interaction.

Usage and billing metadata

{
  "billing": {
    "llm": {
      "runCount": 1,
      "runsWithTokenUsage": 1,
      "runsWithReportedCost": 0,
      "inputTokens": 14890,
      "outputTokens": 2743,
      "cachedInputTokens": 216224,
      "totalTokens": 233857,
      "reportedCostUsd": 0,
      "costStatus": "unpriced"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 54100,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": {
    "model": "claude-opus-5-5",
    "biller": "anthropic",
    "costUsd": null,
    "provider": "anthropic",
    "costStatus": "estimated",
    "billingType": "metered_api",
    "inputTokens": 14890,
    "ledgerScope": {
      "issueId": "ca068b91-83f5-4314-ab13-fda95aebd1f5",
      "projectId": "bd9ba52d-e579-4de7-a1b9-5bf5d25ffa2e",
      "billingCode": null
    },
    "usageSource": "per_run",
    "costUsdExact": "0.217160800",
    "freshSession": true,
    "outputTokens": 2743,
    "usageByModel": null,
    "sessionReused": false,
    "budgetDispatch": {
      "admittedAt": "2026-10-21T14:36:27.415Z",
      "handedOffAt": "2026-10-21T14:36:27.443Z",
      "reservationId": "51b54817-71f1-40ee-ad2f-142265cef24e",
      "recoveryLeaseOwner": null
    },
    "budgetExposure": {
      "sequence": 21,
      "sourceId": "055bfec3-3b91-4b0c-985e-0f2d3ddae5d5",
      "costCents": "21.7160800"
    },
    "rawInputTokens": 14890,
    "sessionRotated": false,
    "configFreshness": {
      "session": {
        "reset": true,
        "categories": [
          "adapter",
          "adapterConfig",
          "agentRuntimeConfig",
          "instructions",
          "issueOverrides",
          "workspaceConfig",
          "environment",
          "envBindings",
          "secrets",
          "runtimeSkills"
        ],
        "resetReasons": [],
        "nextFingerprint": "v1:sha256:78d3b91cfc15d3052e9aed050951c378d141f6263b033a23f29ff1f579d2c7c0",
        "changedCategories": [],
        "taskSessionReused": false,
        "fingerprintVersion": 1,
        "taskSessionAvailable": false,
        "storedFingerprintPresent": false
      },
      "version": 1,
      "workspace": {
        "action": "create",
        "reasons": [],
        "categories": [
          "mode",
          "projectWorkspace",
          "strategy",
          "repo",
          "lifecycleCommands",
          "runtimeServices",
          "environment",
          "realization"
        ],
        "reuseRequested": false,
        "nextFingerprint": "v1:sha256:6ad4cf13bbc00e8d7cb3a5b5c16c03b0ae0b42b274ed74977c00dcbb169ae05c",
        "workspaceReused": false,
        "activeWorkspaceId": "987c6b84-000d-431f-986a-ebde632c2298",
        "changedCategories": [],
        "storedFingerprint": null,
        "fingerprintVersion": 1,
        "inferredFingerprint": null,
        "previousWorkspaceId": null,
        "configSnapshotRefreshed": false,
        "storedFingerprintPresent": false
      }
    },
    "rawOutputTokens": 2743,
    "cacheWriteTokens": 14874,
    "cachedInputTokens": 216224,
    "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": "fa00582a-7d27-44b5-ab7d-f2d2af0a7c0b",
    "accountingReceiptId": "ff57f499-790d-4707-95af-34a564ac8ff4",
    "cacheAdjustedCostUsd": null,
    "rawCachedInputTokens": 216224,
    "sessionRotationReason": null,
    "accountingReceiptReady": true,
    "rawInputIncludesCached": false,
    "accountingReceiptSequence": 21,
    "accountingReceiptSourceId": "055bfec3-3b91-4b0c-985e-0f2d3ddae5d5",
    "accountingReceiptReceivedAt": "2026-10-21T14:37:19.285Z"
  }
}

Test suite

legacy-conversion

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

Pass rate100.0%2/2 passed

Tokens358,83540,523 input · 3,459 output

Known spendUnavailablereported LLM + runtime estimate

Agent time1m 23s0ms lease

Execution2/20 retries · cleanup passed

convert-and-deliver

Inspect case ↗

Runner CodexIsolated localcodex · gpt-5.6-sol

convert-and-deliver passed

Test details6/6 checks · 56s

Overall passed · 6/6 behavioral checks passed

No behavioral matcher failed.

See all behavioral checks (6)

Result	Check	Detail
Pass	`repositoryVerification.production-conversion`	Conversion must start with a real legacy agent and use its production runner transition.
Pass	`repositoryVerification.retained-configuration`	Configured model, source directory, secret references, timeout, runtime settings, environment, instructions, and equivalent permissions must survive.
Pass	`repositoryVerification.actual-native-runtime`	One actual native admission on the configured provider and model must commit the task result.
Pass	`repositoryVerification.retained-repository`	The independently seeded source reference must survive byte for byte in the configured checkout.
Pass	`repositoryVerification.independent-result`	Downloaded bytes must agree with the independent source-file and Git baseline.
Pass	`repositoryVerification.accessible-delivery`	The originating task must render the downloadable result with no unanswered interaction.

Tokens25,811 in · 908 out98,998 cached · 1/1 runs covered

LLM spendUnavailable0/1 runs provider-priced

ExecutionLocal · not metered37s agent

legacy-conversion.runner-codex.local.convert-and-deliver

Attempt: 1
Duration: 56s
Agent runtime: 37s
Runtime: native
Provider: codex
Model: gpt-6.1-sol
Issue: RUN-1

All invariants passed

Startup reuse evidence
Run	Warmth	Environment/lease	Workspace	Runner	Provider process	Provider session	Provider launches
`9821d219-0e2b-4ed2-a52b-6fdfe2d50f4e`	unknown	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown

Result	Matcher	Expectation	Detail
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.production-conversion","expected":true}	Conversion must start with a real legacy agent and use its production runner transition.
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.retained-configuration","expected":true}	Configured model, source directory, secret references, timeout, runtime settings, environment, instructions, and equivalent permissions must survive.
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.actual-native-runtime","expected":true}	One actual native admission on the configured provider and model must commit the task result.
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.retained-repository","expected":true}	The independently seeded source reference must survive byte for byte in the configured checkout.
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.independent-result","expected":true}	Downloaded bytes must agree with the independent source-file and Git baseline.
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.accessible-delivery","expected":true}	The originating task must render the downloadable result with no unanswered interaction.

Usage and billing metadata

{
  "billing": {
    "llm": {
      "runCount": 1,
      "runsWithTokenUsage": 1,
      "runsWithReportedCost": 0,
      "inputTokens": 25811,
      "outputTokens": 908,
      "cachedInputTokens": 98998,
      "totalTokens": 125717,
      "reportedCostUsd": 0,
      "costStatus": "unpriced"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 36645,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": {
    "model": "gpt-6.1-sol",
    "biller": "openai",
    "costUsd": null,
    "provider": "openai",
    "costStatus": "estimated",
    "billingType": "metered_api",
    "inputTokens": 25811,
    "ledgerScope": {
      "issueId": "b5b61b40-a748-4b81-9440-bcc56a489040",
      "projectId": "2a7b9013-bf66-45e1-8fb9-383e9be77348",
      "billingCode": null
    },
    "usageSource": "per_run",
    "costUsdExact": "0.070601800",
    "freshSession": true,
    "outputTokens": 908,
    "usageByModel": null,
    "sessionReused": false,
    "budgetDispatch": {
      "admittedAt": "2026-10-21T14:42:53.862Z",
      "handedOffAt": "2026-10-21T14:42:53.895Z",
      "reservationId": "456b3c17-e3d1-4781-882c-a73f7e6b267d",
      "recoveryLeaseOwner": null
    },
    "budgetExposure": {
      "sequence": 8,
      "sourceId": "f482531c-8ab0-4c12-8d78-d89edad2b219",
      "costCents": "7.0601800"
    },
    "rawInputTokens": 25811,
    "sessionRotated": false,
    "configFreshness": {
      "session": {
        "reset": true,
        "categories": [
          "adapter",
          "adapterConfig",
          "agentRuntimeConfig",
          "instructions",
          "issueOverrides",
          "workspaceConfig",
          "environment",
          "envBindings",
          "secrets",
          "runtimeSkills"
        ],
        "resetReasons": [],
        "nextFingerprint": "v1:sha256:350d4f8bd61f69d3a95855a4b1e1a181ebe48060f152848eb4fc12a15ad020dd",
        "changedCategories": [],
        "taskSessionReused": false,
        "fingerprintVersion": 1,
        "taskSessionAvailable": false,
        "storedFingerprintPresent": false
      },
      "version": 1,
      "workspace": {
        "action": "create",
        "reasons": [],
        "categories": [
          "mode",
          "projectWorkspace",
          "strategy",
          "repo",
          "lifecycleCommands",
          "runtimeServices",
          "environment",
          "realization"
        ],
        "reuseRequested": false,
        "nextFingerprint": "v1:sha256:3c72af5fd1f759c709072104b872fe681ebeed6fa1a7d2bc0b9894a17bbcacf7",
        "workspaceReused": false,
        "activeWorkspaceId": "28e54662-6e3e-49cc-8101-d50f6424d3e2",
        "changedCategories": [],
        "storedFingerprint": null,
        "fingerprintVersion": 1,
        "inferredFingerprint": null,
        "previousWorkspaceId": null,
        "configSnapshotRefreshed": false,
        "storedFingerprintPresent": false
      }
    },
    "rawOutputTokens": 908,
    "cacheWriteTokens": 0,
    "cachedInputTokens": 98998,
    "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": "01a15eea-5343-7f51-9c49-4196358f7527",
    "accountingReceiptId": "0aba9af7-acfb-49f5-b478-82645a24c431",
    "cacheAdjustedCostUsd": null,
    "rawCachedInputTokens": 98998,
    "sessionRotationReason": null,
    "accountingReceiptReady": true,
    "rawInputIncludesCached": false,
    "accountingReceiptSequence": 8,
    "accountingReceiptSourceId": "f482531c-8ab0-4c12-8d78-d89edad2b219",
    "accountingReceiptReceivedAt": "2026-10-21T14:43:28.545Z"
  }
}

Runner ACPX ClaudeIsolated localacpx · claude-sonnet-5

convert-and-deliver passed

Test details6/6 checks · 1m 4s

Overall passed · 6/6 behavioral checks passed

No behavioral matcher failed.

See all behavioral checks (6)

Result	Check	Detail
Pass	`repositoryVerification.production-conversion`	Conversion must start with a real legacy agent and use its production runner transition.
Pass	`repositoryVerification.retained-configuration`	Configured model, source directory, secret references, timeout, runtime settings, environment, instructions, and equivalent permissions must survive.
Pass	`repositoryVerification.actual-native-runtime`	One actual native admission on the configured provider and model must commit the task result.
Pass	`repositoryVerification.retained-repository`	The independently seeded source reference must survive byte for byte in the configured checkout.
Pass	`repositoryVerification.independent-result`	Downloaded bytes must agree with the independent source-file and Git baseline.
Pass	`repositoryVerification.accessible-delivery`	The originating task must render the downloadable result with no unanswered interaction.

Tokens14,712 in · 2,551 out215,855 cached · 1/1 runs covered

LLM spendUnavailable0/1 runs provider-priced

ExecutionLocal · not metered46s agent

legacy-conversion.runner-acpx-claude.local.convert-and-deliver

Attempt: 1
Duration: 1m 4s
Agent runtime: 46s
Runtime: native
Provider: acpx
Model: claude-opus-5-5
Issue: RUN-1

All invariants passed

Startup reuse evidence
Run	Warmth	Environment/lease	Workspace	Runner	Provider process	Provider session	Provider launches
`8ffc5b51-49ef-4716-a94b-8b001ab4cf32`	unknown	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown

Result	Matcher	Expectation	Detail
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.production-conversion","expected":true}	Conversion must start with a real legacy agent and use its production runner transition.
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.retained-configuration","expected":true}	Configured model, source directory, secret references, timeout, runtime settings, environment, instructions, and equivalent permissions must survive.
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.actual-native-runtime","expected":true}	One actual native admission on the configured provider and model must commit the task result.
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.retained-repository","expected":true}	The independently seeded source reference must survive byte for byte in the configured checkout.
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.independent-result","expected":true}	Downloaded bytes must agree with the independent source-file and Git baseline.
Pass	`json_path`	{"kind":"json_path","path":"repositoryVerification.accessible-delivery","expected":true}	The originating task must render the downloadable result with no unanswered interaction.

Usage and billing metadata

{
  "billing": {
    "llm": {
      "runCount": 1,
      "runsWithTokenUsage": 1,
      "runsWithReportedCost": 0,
      "inputTokens": 14712,
      "outputTokens": 2551,
      "cachedInputTokens": 215855,
      "totalTokens": 233118,
      "reportedCostUsd": 0,
      "costStatus": "unpriced"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 46369,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": {
    "model": "claude-opus-5-5",
    "biller": "anthropic",
    "costUsd": null,
    "provider": "anthropic",
    "costStatus": "estimated",
    "billingType": "metered_api",
    "inputTokens": 14712,
    "ledgerScope": {
      "issueId": "ed703ac9-9cd0-410c-a83d-3cc885e12047",
      "projectId": "e1a9d56a-5160-4324-a269-95701a899e9a",
      "billingCode": null
    },
    "usageSource": "per_run",
    "costUsdExact": "0.211823000",
    "freshSession": true,
    "outputTokens": 2551,
    "usageByModel": null,
    "sessionReused": false,
    "budgetDispatch": {
      "admittedAt": "2026-10-21T14:39:56.292Z",
      "handedOffAt": "2026-10-21T14:39:56.309Z",
      "reservationId": "4d6acb2e-f749-49e2-9846-34760a0b19e2",
      "recoveryLeaseOwner": null
    },
    "budgetExposure": {
      "sequence": 21,
      "sourceId": "e2924156-122e-43f9-8d2c-af97d85bb979",
      "costCents": "21.1823000"
    },
    "rawInputTokens": 14712,
    "sessionRotated": false,
    "configFreshness": {
      "session": {
        "reset": true,
        "categories": [
          "adapter",
          "adapterConfig",
          "agentRuntimeConfig",
          "instructions",
          "issueOverrides",
          "workspaceConfig",
          "environment",
          "envBindings",
          "secrets",
          "runtimeSkills"
        ],
        "resetReasons": [],
        "nextFingerprint": "v1:sha256:d9046c60e48cc647df7b52372fa94d87571077c7af1211ff812be737e292d34b",
        "changedCategories": [],
        "taskSessionReused": false,
        "fingerprintVersion": 1,
        "taskSessionAvailable": false,
        "storedFingerprintPresent": false
      },
      "version": 1,
      "workspace": {
        "action": "create",
        "reasons": [],
        "categories": [
          "mode",
          "projectWorkspace",
          "strategy",
          "repo",
          "lifecycleCommands",
          "runtimeServices",
          "environment",
          "realization"
        ],
        "reuseRequested": false,
        "nextFingerprint": "v1:sha256:2d2261e6b829049f9e9e2caba18c231167350dbc47db5841043d793f3698a426",
        "workspaceReused": false,
        "activeWorkspaceId": "37dc7e6a-c245-4420-a365-a5b44daacc22",
        "changedCategories": [],
        "storedFingerprint": null,
        "fingerprintVersion": 1,
        "inferredFingerprint": null,
        "previousWorkspaceId": null,
        "configSnapshotRefreshed": false,
        "storedFingerprintPresent": false
      }
    },
    "rawOutputTokens": 2551,
    "cacheWriteTokens": 14696,
    "cachedInputTokens": 215855,
    "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": "bf1e143f-3622-4862-9585-4187fc3bcf47",
    "accountingReceiptId": "e22c004b-cb9f-4883-9259-94a878106b16",
    "cacheAdjustedCostUsd": null,
    "rawCachedInputTokens": 215855,
    "sessionRotationReason": null,
    "accountingReceiptReady": true,
    "rawInputIncludesCached": false,
    "accountingReceiptSequence": 21,
    "accountingReceiptSourceId": "e2924156-122e-43f9-8d2c-af97d85bb979",
    "accountingReceiptReceivedAt": "2026-10-21T14:40:40.815Z"
  }
}

Test suite

automatic-repository-configured-models

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

Pass rate0.0%0/2 passed

Tokens1,023,28065,939 input · 7,273 output

Known spendUnavailablereported LLM + runtime estimate

Agent time5m 15s0ms lease

Execution2/20 retries · cleanup passed

automatic-repository-resume

Inspect case ↗

Runner CodexIsolated localcodex · gpt-5.6-sol

automatic-repository-resume failed

Overall failed · 0/6 behavioral checks passed

Failed checks:

automaticRepository.durable-completion — Two committed provider admissions must finish the requested result.
automaticRepository.server-owned-continuation — Repository setup must continue through the saved same-agent wake without a timer or user message.
automaticRepository.retained-workspace — Both admissions must retain the same task workspace and its prepared repository.
automaticRepository.retained-context — The first admission's independently downloaded unpredictable reference must survive setup byte for byte.
automaticRepository.independent-result — Downloaded result bytes must agree with the independently inspected checkout and original reference.
automaticRepository.accessible-delivery — The originating task must render its result link without an unanswered question.

See all behavioral checks (6)

Result	Check	Detail
Fail	`automaticRepository.durable-completion`	Two committed provider admissions must finish the requested result.
Fail	`automaticRepository.server-owned-continuation`	Repository setup must continue through the saved same-agent wake without a timer or user message.
Fail	`automaticRepository.retained-workspace`	Both admissions must retain the same task workspace and its prepared repository.
Fail	`automaticRepository.retained-context`	The first admission's independently downloaded unpredictable reference must survive setup byte for byte.
Fail	`automaticRepository.independent-result`	Downloaded result bytes must agree with the independently inspected checkout and original reference.
Fail	`automaticRepository.accessible-delivery`	The originating task must render its result link without an unanswered question.

transient infrastructure

Stopped waiting for repository setup and automatic result delivery: A provider admission failed

Test details0/6 checks · 3m 49s

Tokens27,686 in · 1,310 out507,223 cached · 1/1 runs covered

LLM spendUnavailable0/1 runs provider-priced

ExecutionLocal · not metered3m 38s agent

automatic-repository-configured-models.runner-codex.local.automatic-repository-resume

Attempt: 1
Duration: 3m 49s
Agent runtime: 3m 38s
Runtime: native
Provider: codex
Model: gpt-6.1-sol
Issue: RUN-1

No result artifact was uploaded

Startup reuse evidence
Run	Warmth	Environment/lease	Workspace	Runner	Provider process	Provider session	Provider launches
`ca3a2fd3-ade6-4015-bbfa-a14e7e9c11eb`	unknown	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown

Result	Matcher	Expectation	Detail
Fail	`json_path`	{"kind":"json_path","path":"automaticRepository.durable-completion","expected":true}	Two committed provider admissions must finish the requested result.
Fail	`json_path`	{"kind":"json_path","path":"automaticRepository.server-owned-continuation","expected":true}	Repository setup must continue through the saved same-agent wake without a timer or user message.
Fail	`json_path`	{"kind":"json_path","path":"automaticRepository.retained-workspace","expected":true}	Both admissions must retain the same task workspace and its prepared repository.
Fail	`json_path`	{"kind":"json_path","path":"automaticRepository.retained-context","expected":true}	The first admission's independently downloaded unpredictable reference must survive setup byte for byte.
Fail	`json_path`	{"kind":"json_path","path":"automaticRepository.independent-result","expected":true}	Downloaded result bytes must agree with the independently inspected checkout and original reference.
Fail	`json_path`	{"kind":"json_path","path":"automaticRepository.accessible-delivery","expected":true}	The originating task must render its result link without an unanswered question.

Usage and billing metadata

{
  "billing": {
    "llm": {
      "runCount": 1,
      "runsWithTokenUsage": 1,
      "runsWithReportedCost": 0,
      "inputTokens": 27686,
      "outputTokens": 1310,
      "cachedInputTokens": 507223,
      "totalTokens": 536219,
      "reportedCostUsd": 0,
      "costStatus": "unpriced"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 217822,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": {
    "model": "gpt-6.1-sol",
    "biller": "openai",
    "costUsd": null,
    "provider": "openai",
    "costStatus": "estimated",
    "billingType": "metered_api",
    "inputTokens": 27686,
    "ledgerScope": {
      "issueId": "e85c65a8-f23d-4241-a7f4-74515099f543",
      "projectId": null,
      "billingCode": null
    },
    "usageSource": "per_run",
    "costUsdExact": "0.119194300",
    "outputTokens": 1310,
    "usageByModel": null,
    "budgetDispatch": {
      "admittedAt": "2026-10-21T14:31:36.903Z",
      "handedOffAt": "2026-10-21T14:31:37.865Z",
      "reservationId": "6af60e4a-011c-49a6-93ff-775924bbc168",
      "recoveryLeaseOwner": null
    },
    "budgetExposure": {
      "sequence": 21,
      "sourceId": "a1a5af2f-3186-4569-b2b5-66dd9588ab95",
      "costCents": "11.9194300"
    },
    "cacheWriteTokens": 0,
    "cachedInputTokens": 507223,
    "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": "d571ef17-5be4-4351-b054-4211e1924747",
    "cacheAdjustedCostUsd": null,
    "accountingReceiptReady": true,
    "accountingReceiptSequence": 21,
    "accountingReceiptSourceId": "a1a5af2f-3186-4569-b2b5-66dd9588ab95",
    "accountingReceiptReceivedAt": "2026-10-21T14:35:05.607Z"
  }
}

Runner ACPX ClaudeIsolated localacpx · claude-sonnet-5

automatic-repository-resume failed

Overall failed · 0/6 behavioral checks passed

Failed checks:

automaticRepository.durable-completion — Two committed provider admissions must finish the requested result.
automaticRepository.server-owned-continuation — Repository setup must continue through the saved same-agent wake without a timer or user message.
automaticRepository.retained-workspace — Both admissions must retain the same task workspace and its prepared repository.
automaticRepository.retained-context — The first admission's independently downloaded unpredictable reference must survive setup byte for byte.
automaticRepository.independent-result — Downloaded result bytes must agree with the independently inspected checkout and original reference.
automaticRepository.accessible-delivery — The originating task must render its result link without an unanswered question.

See all behavioral checks (6)

Result	Check	Detail
Fail	`automaticRepository.durable-completion`	Two committed provider admissions must finish the requested result.
Fail	`automaticRepository.server-owned-continuation`	Repository setup must continue through the saved same-agent wake without a timer or user message.
Fail	`automaticRepository.retained-workspace`	Both admissions must retain the same task workspace and its prepared repository.
Fail	`automaticRepository.retained-context`	The first admission's independently downloaded unpredictable reference must survive setup byte for byte.
Fail	`automaticRepository.independent-result`	Downloaded result bytes must agree with the independently inspected checkout and original reference.
Fail	`automaticRepository.accessible-delivery`	The originating task must render its result link without an unanswered question.

candidate failure

Stopped waiting for repository setup and automatic result delivery: Repository setup stopped in blocked; see retained task state

Test details0/6 checks · 1m 49s

Tokens38,253 in · 5,963 out442,845 cached · 1/1 runs covered

LLM spendUnavailable0/1 runs provider-priced

ExecutionLocal · not metered1m 37s agent

automatic-repository-configured-models.runner-acpx-claude.local.automatic-repository-resume

Attempt: 1
Duration: 1m 49s
Agent runtime: 1m 37s
Runtime: native
Provider: acpx
Model: claude-opus-5-5
Issue: RUN-1

No result artifact was uploaded

Startup reuse evidence
Run	Warmth	Environment/lease	Workspace	Runner	Provider process	Provider session	Provider launches
`fa064376-32a9-4192-bbb7-fc74b7bb8f36`	unknown	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown

Result	Matcher	Expectation	Detail
Fail	`json_path`	{"kind":"json_path","path":"automaticRepository.durable-completion","expected":true}	Two committed provider admissions must finish the requested result.
Fail	`json_path`	{"kind":"json_path","path":"automaticRepository.server-owned-continuation","expected":true}	Repository setup must continue through the saved same-agent wake without a timer or user message.
Fail	`json_path`	{"kind":"json_path","path":"automaticRepository.retained-workspace","expected":true}	Both admissions must retain the same task workspace and its prepared repository.
Fail	`json_path`	{"kind":"json_path","path":"automaticRepository.retained-context","expected":true}	The first admission's independently downloaded unpredictable reference must survive setup byte for byte.
Fail	`json_path`	{"kind":"json_path","path":"automaticRepository.independent-result","expected":true}	Downloaded result bytes must agree with the independently inspected checkout and original reference.
Fail	`json_path`	{"kind":"json_path","path":"automaticRepository.accessible-delivery","expected":true}	The originating task must render its result link without an unanswered question.

Usage and billing metadata

{
  "billing": {
    "llm": {
      "runCount": 1,
      "runsWithTokenUsage": 1,
      "runsWithReportedCost": 0,
      "inputTokens": 38253,
      "outputTokens": 5963,
      "cachedInputTokens": 442845,
      "totalTokens": 487061,
      "reportedCostUsd": 0,
      "costStatus": "unpriced"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 97283,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": {
    "model": "claude-opus-5-5",
    "biller": "anthropic",
    "costUsd": null,
    "provider": "anthropic",
    "costStatus": "estimated",
    "billingType": "metered_api",
    "inputTokens": 38253,
    "ledgerScope": {
      "issueId": "95d0471d-45e7-4d38-aa7f-c5c8a9d3a22e",
      "projectId": null,
      "billingCode": null
    },
    "usageSource": "per_run",
    "costUsdExact": "0.513733000",
    "freshSession": true,
    "outputTokens": 5963,
    "usageByModel": null,
    "sessionReused": false,
    "budgetDispatch": {
      "admittedAt": "2026-10-21T14:31:45.925Z",
      "handedOffAt": "2026-10-21T14:31:45.943Z",
      "reservationId": "a2e5bbc7-14c3-4550-9125-e541609809bd",
      "recoveryLeaseOwner": null
    },
    "budgetExposure": {
      "sequence": 35,
      "sourceId": "851b147e-a3d4-4676-ab12-9b24ee3a49c6",
      "costCents": "51.3733000"
    },
    "rawInputTokens": 38253,
    "sessionRotated": false,
    "configFreshness": {
      "session": {
        "reset": true,
        "categories": [
          "adapter",
          "adapterConfig",
          "agentRuntimeConfig",
          "instructions",
          "issueOverrides",
          "workspaceConfig",
          "environment",
          "envBindings",
          "secrets",
          "runtimeSkills"
        ],
        "resetReasons": [],
        "nextFingerprint": "v1:sha256:46174eca6387cf8287b973313adce039f9540c4d60090b8d3dae984156c01471",
        "changedCategories": [],
        "taskSessionReused": false,
        "fingerprintVersion": 1,
        "taskSessionAvailable": false,
        "storedFingerprintPresent": false
      },
      "version": 1,
      "workspace": {
        "action": "create",
        "reasons": [],
        "categories": [
          "mode",
          "projectWorkspace",
          "strategy",
          "repo",
          "lifecycleCommands",
          "runtimeServices",
          "environment",
          "realization"
        ],
        "reuseRequested": false,
        "nextFingerprint": "v1:sha256:da5379dd974a4aee6b6845f65c0c668679f6e96c809d54dd08cdfcef8d053968",
        "workspaceReused": false,
        "activeWorkspaceId": "bd367424-5292-4b0f-b207-d3281b833850",
        "changedCategories": [],
        "storedFingerprint": null,
        "fingerprintVersion": 1,
        "inferredFingerprint": null,
        "previousWorkspaceId": null,
        "configSnapshotRefreshed": false,
        "storedFingerprintPresent": false
      }
    },
    "rawOutputTokens": 5963,
    "cacheWriteTokens": 38223,
    "cachedInputTokens": 442845,
    "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": "55354e33-9381-4194-9df6-dd6ebd5637c2",
    "accountingReceiptId": "8d6706c4-0c7d-4b5d-9147-17c795f911f4",
    "cacheAdjustedCostUsd": null,
    "rawCachedInputTokens": 442845,
    "sessionRotationReason": null,
    "accountingReceiptReady": true,
    "rawInputIncludesCached": false,
    "accountingReceiptSequence": 35,
    "accountingReceiptSourceId": "851b147e-a3d4-4676-ab12-9b24ee3a49c6",
    "accountingReceiptReceivedAt": "2026-10-21T14:33:21.253Z"
  }
}