E2E campaign

E2E tests

App and agent journeys across deployment targets, 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.

2026-11-02T18:31:28.188Z3b207a42Source run ↗

1/1Passed
0Failed
2m 32sSummed attempt time
Campaign usage and spend
0 / 0Complaints / suggestions · retained attempts0 distinct items · 0 attempts with incomplete collection · 0 failed submissions · 0 unresolved submissions
1Retained attempts0 missing attempts · 0 out-of-scope artifacts
37,253Input tokens
4,143Output tokens
563,526Cached tokens
UnavailableLLM reported subtotal
$0.4573LLM estimated subtotal
$0.009734Daytona list estimate
2m 32sObserved attempt window1 retained attempts · 0 missing attempts

Attempt durations include setup and cleanup captured inside each attempt. The observed window spans the earliest retained start to the latest retained finish, including gaps and overlap. Carried-forward evidence can span older runs, so this window is not the current workflow's duration. Neither measure is CI queue/setup time or provider-billed runtime.

1m 48sAgent execution time
2m 11sDaytona lease time
0/3Runs provider-priced

Campaign costs include retained attempts, including failed retries. Result cards show the selected attempt. Provider-reported amounts and model estimates are separate; unpriced or unavailable runs are excluded, never counted as free. Coverage describes captured usage; unobserved setup, subscriptions, tools, CI and storage require additional accounting. 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.

4sWorker setup time
2m 24sWorker execution time
219msWorker feedback time
4sWorker cleanup time
0msWorker finalization time

1/1 complete worker receipts; 0 partial; 0 missing attempts. Worker phases cover the test callback through finalization before result publication. Browser/server startup, parent cleanup, CI queue/build time and provider-billed runtime are outside these measurements. An interrupted phase has no inferred end time.

Campaign feedback review

0 distinct feedback items await review. Collection gaps and failed submissions remain separate findings.

Full bodies and review rationale stay in private evidence. Exact duplicate bodies are grouped once; related causes can be linked by a reviewed duplicate disposition.

All results

Feature coverage 0 of 192 capabilities linked · 0 of 1 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 0/5 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

Daytona Warm Continuity

Three browser-driven turns on one reusable Daytona sandbox for legacy and native Codex.

Pass rate100.0%1/1 passed
Tokens604,92237,253 input · 4,143 output
Known spend$0.4670reported LLM + model/runtime estimates estimate
Agent time1m 48s2m 11s lease
Execution1/10 retries · cleanup passed
Runner CodexDaytona warm reusable sandboxcodex · gpt-5.6-sol
Test details9/9 checks · 2m 32s
Environment
Daytona warm reusable sandbox
Model
gpt-5.6-sol
Runtime
native · codex
  • Passmatched
  • Passmatched
  • Passmatched
  • Passmatched
  • Passmatched
  • Passmatched
  • Passmatched
  • Passmatched
  • Passmatched
Tokens37,253 in · 4,143 out563,526 cached · 3/3 runs covered
LLM spendUnavailable0/3 runs provider-priced
LLM estimate$0.4573Estimated from captured usage
Execution$0.009734 est.1m 48s agent · 2m 11s lease

Task chat

RUN-1: Create warm continuity turn 1 files · 16 entries

Recorded task brief, messages, requests and answers, with native agent progress when available. This is a read-only recording of the saved task conversation.

Task brief
This is warm Daytona continuity turn 1 of 3. Work only in the current execution workspace. Create daytona-warm-147c0796dbeb-1.txt with exactly this one line followed by a newline: T1-147c0796dbeb-1 Each newline in this task means the actual LF character (byte 10), including in personal memory files. An escaped representation containing a literal backslash and n is not a newline. Verify the saved bytes against the requested line content and LF byte 10, independently of the string expression used to write them. After the write, verify daytona-warm-147c0796dbeb-1.txt contains exactly these lines, once each and in order: T1-147c0796dbeb-1. In a native runner, use the current turn completion revision and criterion IDs (CURRENT\_TURN\_REVISION below is a placeholder, not a literal), then call paperclip\_finish exactly once with {reportedWorkDisposition:"needs\_review",summary:"PAPERCLIP\_E2E\_WARM\_T1\_147c0796dbeb-1",completionClaim:{contractRevision:CURRENT\_TURN\_REVISION,objectiveSatisfied:true,criteria:\[{criterionId:"objective",status:"satisfied",evidenceRefs:\[]}],remainingWork:\[]},attentionRequests:\[{"kind":"review","ownerClass":"human","summary":"Review the verified turn 1 wor
Runner E2E runner-codex 147c0796dbeb-1
I’m creating the workspace file and the three personal continuity files, then I’ll verify their exact byte-level contents before submitting the required review disposition.
Runner E2E runner-codex 147c0796dbeb-1
The task title is saved. I’ve confirmed the active completion contract revision is `1`; I’m now writing the exact payloads and will validate sizes, hashes/byte values, and trailing-newline behavior independently.
Request
Review requested Review the verified turn 1 workspace file and decide whether this task is ready to complete or needs another revision. PAPERCLIP_E2E_WARM_T1_147c0796dbeb-1 Approve completion Continue work Status: rejected
Runner E2E runner-codex 147c0796dbeb-1
PAPERCLIP_E2E_WARM_T1_147c0796dbeb-1
YouResponse
rejected This is warm Daytona continuity turn 2 of 3. Work only in the current execution workspace. Before changing anything, read daytona-warm-147c0796dbeb-1.txt and verify its content is exactly these prior lines in order, each followed by a newline: T1-147c0796dbeb-1. Then append exactly T2-147c0796dbeb-1 followed by a newline. Each newline in this task means the actual LF character (byte 10), including in personal memory files. An escaped representation containing a literal backslash and n is not a newline. Verify the saved bytes against the requested line content and LF byte 10, independently of the string expression used to write them. After the write, verify daytona-warm-147c0796dbeb-1.txt contains exactly these lines, once each and in order: T1-147c0796dbeb-1 | T2-147c0796dbeb-1. In a native runner, use the current turn completion revision and criterion IDs (CURRENT_TURN_REVISION below is a placeholder, not a literal), then call paperclip_finish exactly once with {reportedWorkDisposition:"needs_review",summary:"PAPERCLIP_E2E_WARM_T2_147c0796dbeb-1",completionClaim:{contractRevision:CURRENT_TURN_REVISION,objectiveSatisfied:true,criteria:[{criterionId:"objective",status:"satisfied",evidenceRefs:[]}],remainingWork:[]},attentionRequests:[{"kind":"review","ownerClass":"human","summary":"Review the verified turn 2 workspace file and decide whether this task is ready to complete or needs another revision."}],evidence:[],verification:[{commandOrCheck:"read daytona-warm-147c0796dbeb-1.txt",status:"passed"}]}. Wait for that tool call to succeed, then emit exactly PAPERCLIP_E2E_WARM_T2_147c0796dbeb-1 once as the complete user-facing final response. In a legacy runner, after verification POST exactly one request_confirmation to /api/issues/$PAPERCLIP_TASK_ID/interactions with {"kind":"request_confirmation","idempotencyKey":"daytona-warm-review-T2-147c0796dbeb-1","resolverPolicy":"human_only","title":"Warm continuity turn 2","summary":"Review completed warm continuity turn 2.","continuationPolicy":"wake_assignee","payload":{"version":1,"prompt":"Is this warm continuity task ready to complete after turn 2?","acceptLabel":"Approve completion","rejectLabel":"Continue work","rejectRequiresReason":true,"allowDeclineReason":true,"supersedeOnUserComment":false,"target":{"type":"custom","key":"daytona_warm_turn_2","revisionId":"147c0796dbeb-1-T2","label":"Warm continuity turn 2"}}}. Capture the returned interaction id. Then make exactly one issue PATCH with {"status":"in_review","comment":"PAPERCLIP_E2E_WARM_T2_147c0796dbeb-1","reviewInteractionId":"<returned interaction id>"}. Include Authorization and X-Paperclip-Run-Id on both writes. If the issue PATCH fails, retry only that PATCH and never create another interaction. Do not POST a separate comment. After both writes succeed, end the response and heartbeat immediately; do not wait or poll because the reviewer action will start the next turn. In a legacy runner, the PATCH comment is the complete visible response. After its 2xx response, finish silently: do not print, echo, or emit PAPERCLIP_E2E_WARM_T2_147c0796dbeb-1 again as assistant text. Do not include PAPERCLIP_E2E_WARM_T2_147c0796dbeb-1 in any other visible response or write. Do not recreate, truncate, reorder, or duplicate prior lines. Also update your personal AGENT_HOME with ordinary filesystem tools. Do not edit the loaded AGENTS.md instructions and do not use an API to save these files. Read notes/warm-memory.txt under AGENT_HOME and verify it contains exactly the prior turn lines T1-147c0796dbeb-1, each followed by a newline. Append exactly T2-147c0796dbeb-1 and a newline. Verify notes/unchanged.bin still has 8388608 bytes, each equal to 93, and leave it unchanged. Delete notes/delete-me.txt. Perform these personal-file edits and verification before calling paperclip_finish. Paperclip saves them at the turn boundary.
Runner E2E runner-codex 147c0796dbeb-1
I’m first validating the preserved turn-1 workspace and personal-memory bytes exactly as required. Once confirmed, I’ll append only the turn-2 lines, remove the temporary personal file, and re-verify every continuity invariant.
Runner E2E runner-codex 147c0796dbeb-1
The preserved state passed: both text files are exactly 18 bytes ending in LF, the binary is exactly 8,388,608 bytes of value 93, and the nine-byte temporary file exists. I’m applying the minimal append/delete changes now.
Request
Review requested Review the verified turn 2 workspace file and decide whether this task is ready to complete or needs another revision. PAPERCLIP_E2E_WARM_T2_147c0796dbeb-1 Approve completion Continue work Status: rejected
Runner E2E runner-codex 147c0796dbeb-1
PAPERCLIP_E2E_WARM_T2_147c0796dbeb-1
YouResponse
rejected This is warm Daytona continuity turn 3 of 3. Work only in the current execution workspace. Before changing anything, read daytona-warm-147c0796dbeb-1.txt and verify its content is exactly these prior lines in order, each followed by a newline: T1-147c0796dbeb-1 | T2-147c0796dbeb-1. Then append exactly T3-147c0796dbeb-1 followed by a newline. Each newline in this task means the actual LF character (byte 10), including in personal memory files. An escaped representation containing a literal backslash and n is not a newline. Verify the saved bytes against the requested line content and LF byte 10, independently of the string expression used to write them. After the write, verify daytona-warm-147c0796dbeb-1.txt contains exactly these lines, once each and in order: T1-147c0796dbeb-1 | T2-147c0796dbeb-1 | T3-147c0796dbeb-1. In a native runner, use the current turn completion revision and criterion IDs (CURRENT_TURN_REVISION below is a placeholder, not a literal), then call paperclip_finish exactly once with {reportedWorkDisposition:"done",summary:"PAPERCLIP_E2E_WARM_T3_147c0796dbeb-1",completionClaim:{contractRevision:CURRENT_TURN_REVISION,objectiveSatisfied:true,criteria:[{criterionId:"objective",status:"satisfied",evidenceRefs:[]}],remainingWork:[]},attentionRequests:[],evidence:[],verification:[{commandOrCheck:"read daytona-warm-147c0796dbeb-1.txt",status:"passed"}]}. Wait for that tool call to succeed, then emit exactly PAPERCLIP_E2E_WARM_T3_147c0796dbeb-1 once as the complete user-facing final response. In a legacy runner, make exactly one public-API completion write after verification: PATCH /api/issues/$PAPERCLIP_TASK_ID with {"status":"done","comment":"PAPERCLIP_E2E_WARM_T3_147c0796dbeb-1"}. Include Authorization and X-Paperclip-Run-Id. Do not POST a separate comment. In a legacy runner, the PATCH comment is the complete visible response. After its 2xx response, finish silently: do not print, echo, or emit PAPERCLIP_E2E_WARM_T3_147c0796dbeb-1 again as assistant text. Do not include PAPERCLIP_E2E_WARM_T3_147c0796dbeb-1 in any other visible response or write. Do not recreate, truncate, reorder, or duplicate prior lines. Also update your personal AGENT_HOME with ordinary filesystem tools. Do not edit the loaded AGENTS.md instructions and do not use an API to save these files. Read notes/warm-memory.txt under AGENT_HOME and verify it contains exactly the prior turn lines T1-147c0796dbeb-1 | T2-147c0796dbeb-1, each followed by a newline. Append exactly T3-147c0796dbeb-1 and a newline. Verify notes/unchanged.bin still has 8388608 bytes, each equal to 93, and leave it unchanged. Verify notes/delete-me.txt is absent. Perform these personal-file edits and verification before calling paperclip_finish. Paperclip saves them at the turn boundary.
Runner E2E runner-codex 147c0796dbeb-1
I’m validating the exact two-line turn-2 state and all personal continuity artifacts before making the final append. Then I’ll verify the three-line byte layout and complete the task.
Runner E2E runner-codex 147c0796dbeb-1
The turn-2 state is intact: both text files contain exactly the two required LF-terminated lines, the binary remains unchanged at 8,388,608 bytes of value 93, and the deleted file remains absent. I’m appending the final line only.
Runner E2E runner-codex 147c0796dbeb-1
The byte checks passed, but completion was not accepted because the workspace file must be registered as an accessible deliverable. I’m registering that already-verified 54-byte file, then I’ll resubmit completion with its delivery evidence.
Runner E2E runner-codex 147c0796dbeb-1
Prepared Warm continuity turns 1–3 for this response.
Runner E2E runner-codex 147c0796dbeb-1
PAPERCLIP_E2E_WARM_T3_147c0796dbeb-1
Diagnostics
Overall passed · 9/9 behavioral checks passed

No behavioral matcher failed.

See all behavioral checks (9)
ResultCheckDetail
Passmessage_occurrencesmatched
Passmessage_occurrencesmatched
Passmessage_occurrencesmatched
Passmessage_orderedmatched
Passfile_exactmatched
Passissue_statusmatched
Passrun_statusmatched
Passruntime_modematched
Passenvironmentmatched

Worker phase timing: complete.

Feedback: 0 complaints · 0 suggestions · 0 distinct items; see campaign feedback review. Saved-feedback collection: complete; invocation coverage: complete. Tool receipts: 0 failed · 0 unresolved. Full bodies: access-controlled snapshots/agent-feedback.json or snapshots/agent-feedback-recovered.json.

daytona-warm-continuity.runner-codex.daytona.warm-three-turn
Attempt
1
Duration
2m 32s
Agent runtime
1m 48s
Environment lease
2m 11s
Runtime
native
Provider
codex
Model
gpt-5.6-sol
Issue
RUN-1
TurnRunLeaseSchedulerRun durationFinal settlement (legacy response field)
1 6b13cf6c-2358-4201-a099-d418524098a6 created 4s 46s 50s
2 b951c030-d7f6-46cb-aa2f-2b6133cc28f4 resumed 395ms 25s 25s
3 a06adea2-b0bd-4830-ad2b-a54f5eced954 resumed 354ms 37s 37s
Startup reuse evidence
RunWarmthEnvironment/leaseWorkspaceRunnerProvider processProvider sessionProvider launches
6b13cf6c-2358-4201-a099-d418524098a6unknown fresh (created)fresh (created)fresh (created)unknown (evidence_missing)fresh (created) unknown
b951c030-d7f6-46cb-aa2f-2b6133cc28f4partial_reuse reused (verified_reuse)reused (verified_reuse)reused (verified_reuse)unknown (evidence_missing)reused (verified_reuse) unknown
a06adea2-b0bd-4830-ad2b-a54f5eced954partial_reuse reused (verified_reuse)reused (verified_reuse)reused (verified_reuse)unknown (evidence_missing)reused (verified_reuse) unknown
ResultMatcherExpectationDetail
Pass message_occurrences {"kind":"message_occurrences","expected":"PAPERCLIP_E2E_WARM_T1_147c0796dbeb-1","count":1} matched
Pass message_occurrences {"kind":"message_occurrences","expected":"PAPERCLIP_E2E_WARM_T2_147c0796dbeb-1","count":1} matched
Pass message_occurrences {"kind":"message_occurrences","expected":"PAPERCLIP_E2E_WARM_T3_147c0796dbeb-1","count":1} matched
Pass message_ordered {"kind":"message_ordered","expected":["PAPERCLIP_E2E_WARM_T1_147c0796dbeb-1","PAPERCLIP_E2E_WARM_T2_147c0796dbeb-1","PAPERCLIP_E2E_WARM_T3_147c0796dbeb-1"]} matched
Pass file_exact {"kind":"file_exact","path":"daytona-warm-147c0796dbeb-1.txt","expected":"T1-147c0796dbeb-1\nT2-147c0796dbeb-1\nT3-147c0796dbeb-1\n"} matched
Pass issue_status {"kind":"issue_status","expected":"done"} matched
Pass run_status {"kind":"run_status","expected":"succeeded"} matched
Pass runtime_mode {"kind":"runtime_mode","expected":"native"} matched
Pass environment {"kind":"environment","expected":"daytona"} matched
Usage, billing and timing metadata
{
  "billing": {
    "llm": {
      "runCount": 3,
      "runsWithTokenUsage": 3,
      "runsWithReportedCost": 0,
      "runsWithEstimatedCost": 3,
      "runsWithPartialReportedCost": 0,
      "inputTokens": 37253,
      "outputTokens": 4143,
      "cachedInputTokens": 563526,
      "totalTokens": 604922,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0.4572824,
      "costStatus": "estimated"
    },
    "runtime": {
      "provider": "daytona",
      "agentRunDurationMs": 107854,
      "leaseDurationMs": 131008,
      "leaseCount": 4,
      "cpuCores": 4,
      "memoryGiB": 4,
      "diskGiB": 10,
      "estimatedListCostUsd": 0.0097338944,
      "costStatus": "estimated",
      "costSource": "daytona_public_list_price",
      "pricingAsOf": "2026-08-27",
      "pricingUrl": "https://www.daytona.io/pricing"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0.0097338944,
    "observedAndEstimatedCostUsd": 0.4670162944,
    "complete": true
  },
  "rawUsage": {
    "runs": [
      {
        "runId": "6b13cf6c-2358-4201-a099-d418524098a6",
        "usage": {
          "model": "gpt-5.6-sol",
          "biller": "openai",
          "costUsd": null,
          "provider": "openai",
          "costStatus": "estimated",
          "billingType": "metered_api",
          "inputTokens": 29205,
          "ledgerScope": {
            "issueId": "d72d45cc-e1a7-456b-8082-8c4c217ed366",
            "projectId": "5a3b15c6-6647-4a11-a46e-339b4d567de9",
            "billingCode": null
          },
          "usageSource": "per_run",
          "costUsdExact": "0.212989200",
          "outputTokens": 1571,
          "usageByModel": null,
          "budgetDispatch": {
            "admittedAt": "2026-11-02T18:28:04.491Z",
            "handedOffAt": "2026-11-02T18:28:04.522Z",
            "reservationId": "fd103424-3b14-4536-bba9-b7a3b0d053a2",
            "recoveryLeaseOwner": null
          },
          "budgetExposure": {
            "sequence": 149,
            "sourceId": "80c91efc-2f71-59e4-aeed-32cf0566caa3",
            "costCents": "21.2989200"
          },
          "cacheWriteTokens": 0,
          "cachedInputTokens": 161873,
          "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": "400.0000000",
            "outputCentsPerMillion": "2000.0000000",
            "cacheWriteCentsPerMillion": "500.0000000",
            "cachedInputCentsPerMillion": "40.0000000"
          },
          "providerRequestId": null,
          "accountingReceiptId": "4ef306f4-34e5-50e7-a7c3-bcf12eeba5d6",
          "cacheAdjustedCostUsd": null,
          "accountingReceiptOwner": "native_producer",
          "accountingReceiptReady": true,
          "accountingReceiptSequence": 149,
          "accountingReceiptSourceId": "80c91efc-2f71-59e4-aeed-32cf0566caa3",
          "accountingReceiptReceivedAt": "2026-11-02T18:28:39.009Z"
        }
      },
      {
        "runId": "b951c030-d7f6-46cb-aa2f-2b6133cc28f4",
        "usage": {
          "model": "gpt-5.6-sol",
          "biller": "openai",
          "costUsd": null,
          "provider": "openai",
          "costStatus": "estimated",
          "billingType": "metered_api",
          "inputTokens": 3797,
          "ledgerScope": {
            "issueId": "d72d45cc-e1a7-456b-8082-8c4c217ed366",
            "projectId": "5a3b15c6-6647-4a11-a46e-339b4d567de9",
            "billingCode": null
          },
          "usageSource": "per_run",
          "costUsdExact": "0.100067200",
          "freshSession": false,
          "outputTokens": 1134,
          "usageByModel": null,
          "sessionReused": true,
          "budgetDispatch": {
            "admittedAt": "2026-11-02T18:28:54.537Z",
            "handedOffAt": "2026-11-02T18:28:54.547Z",
            "reservationId": "ea090ead-0dcc-453f-a817-37cb7514f82b",
            "recoveryLeaseOwner": null
          },
          "budgetExposure": {
            "sequence": 146,
            "sourceId": "b78a9e0e-402c-5464-a0f9-551f054ea945",
            "costCents": "10.0067200"
          },
          "rawInputTokens": 3797,
          "sessionRotated": false,
          "configFreshness": {
            "session": {
              "reset": false,
              "categories": [
                "adapter",
                "adapterConfig",
                "agentRuntimeConfig",
                "instructions",
                "issueOverrides",
                "workspaceConfig",
                "environment",
                "envBindings",
                "secrets",
                "runtimeSkills"
              ],
              "resetReasons": [],
              "nextFingerprint": "v1:sha256:d66832ec0f52b75804319a400764595f0e37699638f960e83f01dff54eeab813",
              "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:sha256:71e7fc9cf72a59756c4c9e0b12ed1eb83f402e1dd95ead6010242af2025b34e8",
              "workspaceReused": true,
              "activeWorkspaceId": "7b2635df-57f7-4c0a-9164-fa84c0a0078a",
              "changedCategories": [],
              "storedFingerprint": "v1:sha256:71e7fc9cf72a59756c4c9e0b12ed1eb83f402e1dd95ead6010242af2025b34e8",
              "fingerprintVersion": 1,
              "inferredFingerprint": null,
              "previousWorkspaceId": "7b2635df-57f7-4c0a-9164-fa84c0a0078a",
              "configSnapshotRefreshed": false,
              "storedFingerprintPresent": true
            }
          },
          "rawOutputTokens": 1134,
          "cacheWriteTokens": 0,
          "cachedInputTokens": 155498,
          "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": "400.0000000",
            "outputCentsPerMillion": "2000.0000000",
            "cacheWriteCentsPerMillion": "500.0000000",
            "cachedInputCentsPerMillion": "40.0000000"
          },
          "providerRequestId": null,
          "taskSessionReused": true,
          "persistedSessionId": "01a19d84-d45c-7d73-a48a-dafc63260330",
          "accountingReceiptId": "4fc4b250-9888-5b21-a856-a2f248daa302",
          "cacheAdjustedCostUsd": null,
          "rawCachedInputTokens": 155498,
          "sessionRotationReason": null,
          "accountingReceiptOwner": "native_producer",
          "accountingReceiptReady": true,
          "rawInputIncludesCached": false,
          "accountingReceiptSequence": 146,
          "accountingReceiptSourceId": "b78a9e0e-402c-5464-a0f9-551f054ea945",
          "accountingReceiptReceivedAt": "2026-11-02T18:29:14.413Z"
        }
      },
      {
        "runId": "a06adea2-b0bd-4830-ad2b-a54f5eced954",
        "usage": {
          "model": "gpt-5.6-sol",
          "biller": "openai",
          "costUsd": null,
          "provider": "openai",
          "costStatus": "estimated",
          "billingType": "metered_api",
          "inputTokens": 4251,
          "ledgerScope": {
            "issueId": "d72d45cc-e1a7-456b-8082-8c4c217ed366",
            "projectId": "5a3b15c6-6647-4a11-a46e-339b4d567de9",
            "billingCode": null
          },
          "usageSource": "per_run",
          "costUsdExact": "0.144226000",
          "freshSession": false,
          "outputTokens": 1438,
          "usageByModel": null,
          "sessionReused": true,
          "budgetDispatch": {
            "admittedAt": "2026-11-02T18:29:26.591Z",
            "handedOffAt": "2026-11-02T18:29:26.609Z",
            "reservationId": "2e997581-129d-4359-8b1f-7c807052377a",
            "recoveryLeaseOwner": null
          },
          "budgetExposure": {
            "sequence": 200,
            "sourceId": "f7164627-fc34-57ca-a784-29eb5dfe71c5",
            "costCents": "14.4226000"
          },
          "rawInputTokens": 4251,
          "sessionRotated": false,
          "configFreshness": {
            "session": {
              "reset": false,
              "categories": [
                "adapter",
                "adapterConfig",
                "agentRuntimeConfig",
                "instructions",
                "issueOverrides",
                "workspaceConfig",
                "environment",
                "envBindings",
                "secrets",
                "runtimeSkills"
              ],
              "resetReasons": [],
              "nextFingerprint": "v1:sha256:d66832ec0f52b75804319a400764595f0e37699638f960e83f01dff54eeab813",
              "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:sha256:71e7fc9cf72a59756c4c9e0b12ed1eb83f402e1dd95ead6010242af2025b34e8",
              "workspaceReused": true,
              "activeWorkspaceId": "7b2635df-57f7-4c0a-9164-fa84c0a0078a",
              "changedCategories": [],
              "storedFingerprint": "v1:sha256:71e7fc9cf72a59756c4c9e0b12ed1eb83f402e1dd95ead6010242af2025b34e8",
              "fingerprintVersion": 1,
              "inferredFingerprint": null,
              "previousWorkspaceId": "7b2635df-57f7-4c0a-9164-fa84c0a0078a",
              "configSnapshotRefreshed": false,
              "storedFingerprintPresent": true
            }
          },
          "rawOutputTokens": 1438,
          "cacheWriteTokens": 0,
          "cachedInputTokens": 246155,
          "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": "400.0000000",
            "outputCentsPerMillion": "2000.0000000",
            "cacheWriteCentsPerMillion": "500.0000000",
            "cachedInputCentsPerMillion": "40.0000000"
          },
          "providerRequestId": null,
          "taskSessionReused": true,
          "persistedSessionId": "01a19d84-d45c-7d73-a48a-dafc63260330",
          "accountingReceiptId": "cb5693cf-46f5-5be6-a437-dafb2ccad740",
          "cacheAdjustedCostUsd": null,
          "rawCachedInputTokens": 246155,
          "sessionRotationReason": null,
          "accountingReceiptOwner": "native_producer",
          "accountingReceiptReady": true,
          "rawInputIncludesCached": false,
          "accountingReceiptSequence": 200,
          "accountingReceiptSourceId": "f7164627-fc34-57ca-a784-29eb5dfe71c5",
          "accountingReceiptReceivedAt": "2026-11-02T18:29:58.256Z"
        }
      }
    ]
  },
  "workerTiming": {
    "version": 1,
    "scope": "worker",
    "status": "complete",
    "executionId": "daytona-warm-continuity.runner-codex.daytona.warm-three-turn",
    "attempt": 1,
    "startedAt": "2026-11-02T18:27:40.585Z",
    "finishedAt": "2026-11-02T18:30:12.410Z",
    "segments": [
      {
        "phase": "setup",
        "startedAt": "2026-11-02T18:27:40.585Z",
        "finishedAt": "2026-11-02T18:27:44.367Z"
      },
      {
        "phase": "execution",
        "startedAt": "2026-11-02T18:27:44.367Z",
        "finishedAt": "2026-11-02T18:30:08.368Z"
      },
      {
        "phase": "cleanup",
        "startedAt": "2026-11-02T18:30:08.368Z",
        "finishedAt": "2026-11-02T18:30:08.587Z"
      },
      {
        "phase": "feedback",
        "startedAt": "2026-11-02T18:30:08.587Z",
        "finishedAt": "2026-11-02T18:30:08.806Z"
      },
      {
        "phase": "cleanup",
        "startedAt": "2026-11-02T18:30:08.806Z",
        "finishedAt": "2026-11-02T18:30:12.410Z"
      },
      {
        "phase": "finalization",
        "startedAt": "2026-11-02T18:30:12.410Z",
        "finishedAt": "2026-11-02T18:30:12.410Z"
      }
    ]
  },
  "startupReuse": [
    {
      "runId": "6b13cf6c-2358-4201-a099-d418524098a6",
      "warmth": "unknown",
      "layers": {
        "environment": {
          "state": "fresh",
          "reason": "created"
        },
        "workspace": {
          "state": "fresh",
          "reason": "created"
        },
        "runner": {
          "state": "fresh",
          "reason": "created"
        },
        "provider_process": {
          "state": "unknown",
          "reason": "evidence_missing"
        },
        "provider_session": {
          "state": "fresh",
          "reason": "created"
        }
      },
      "providerLaunchCount": null
    },
    {
      "runId": "b951c030-d7f6-46cb-aa2f-2b6133cc28f4",
      "warmth": "partial_reuse",
      "layers": {
        "environment": {
          "state": "reused",
          "reason": "verified_reuse"
        },
        "workspace": {
          "state": "reused",
          "reason": "verified_reuse"
        },
        "runner": {
          "state": "reused",
          "reason": "verified_reuse"
        },
        "provider_process": {
          "state": "unknown",
          "reason": "evidence_missing"
        },
        "provider_session": {
          "state": "reused",
          "reason": "verified_reuse"
        }
      },
      "providerLaunchCount": null
    },
    {
      "runId": "a06adea2-b0bd-4830-ad2b-a54f5eced954",
      "warmth": "partial_reuse",
      "layers": {
        "environment": {
          "state": "reused",
          "reason": "verified_reuse"
        },
        "workspace": {
          "state": "reused",
          "reason": "verified_reuse"
        },
        "runner": {
          "state": "reused",
          "reason": "verified_reuse"
        },
        "provider_process": {
          "state": "unknown",
          "reason": "evidence_missing"
        },
        "provider_session": {
          "state": "reused",
          "reason": "verified_reuse"
        }
      },
      "providerLaunchCount": null
    }
  ]
}