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.

2026-11-02T18:05:32.999Z4a1c0c52Source run ↗

0/1Passed
1Failed
2m 18sSummed 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
33,331Input tokens
4,896Output tokens
574,523Cached tokens
UnavailableLLM reported subtotal
$0.4611LLM estimated subtotal
$0.008744Daytona list estimate
2m 18sObserved 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 34sAgent execution time
1m 58sDaytona 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 10sWorker execution time
223msWorker feedback time
5sWorker 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 rate0.0%0/1 passed
Tokens612,75033,331 input · 4,896 output
Known spend$0.4698reported LLM + model/runtime estimates estimate
Agent time1m 34s1m 58s lease
Execution1/10 retries · cleanup passed
Runner CodexDaytona warm reusable sandboxcodex · gpt-5.6-sol
Overall failed · 7/9 behavioral checks passed

Failed checks:

  • message_occurrences — expected {"kind":"message_occurrences","expected":"PAPERCLIP_E2E_WARM_T1_d16bbd10ed81-1","count":1}; observed 0
  • message_ordered — expected {"kind":"message_ordered","expected":["PAPERCLIP_E2E_WARM_T1_d16bbd10ed81-1","PAPERCLIP_E2E_WARM_T2_d16bbd10ed81-1","PAPERCLIP_E2E_WARM_T3_d16bbd10ed81-1"]}; observed "PAPERCLIP_E2E_WARM_T2_d16bbd10ed81-1\nPrepared Warm continuity turn 3 file for this response.\nPAPERCLIP_E2E_WARM_T3_d16bbd10ed81-1"
See all behavioral checks (9)
ResultCheckDetail
Failmessage_occurrencesexpected {"kind":"message_occurrences","expected":"PAPERCLIP_E2E_WARM_T1_d16bbd10ed81-1","count":1}; observed 0
Passmessage_occurrencesmatched
Passmessage_occurrencesmatched
Failmessage_orderedexpected {"kind":"message_ordered","expected":["PAPERCLIP_E2E_WARM_T1_d16bbd10ed81-1","PAPERCLIP_E2E_WARM_T2_d16bbd10ed81-1","PAPERCLIP_E2E_WARM_T3_d16bbd10ed81-1"]}; observed "PAPERCLIP_E2E_WARM_T2_d16bbd10ed81-1\nPrepared Warm continuity turn 3 file for this response.\nPAPERCLIP_E2E_WARM_T3_d16bbd10ed81-1"
Passfile_exactmatched
Passissue_statusmatched
Passrun_statusmatched
Passruntime_modematched
Passenvironmentmatched

candidate failure

Matcher failure: expected {"kind":"message_occurrences","expected":"PAPERCLIP_E2E_WARM_T1_d16bbd10ed81-1","count":1}; observed 0; expected {"kind":"message_ordered","expected":["PAPERCLIP_E2E_WARM_T1_d16bbd10ed81-1","PAPERCLIP_E2E_WARM_T2_d16bbd10ed81-1","PAPERCLIP_E2E_WARM_T3_d16bbd10ed81-1"]}; observed "PAPERCLIP_E2E_WARM_T2_d16bbd10ed81-1\nPrepared Warm continuity turn 3 file for this response.\nPAPERCLIP_E2E_WARM_T3_d16bbd10ed81-1"; run error: none none
Test details7/9 checks · 2m 18s
Environment
Daytona warm reusable sandbox
Model
gpt-5.6-sol
Runtime
native · codex
  • Failexpected {"kind":"message_occurrences","expected":"PAPERCLIP_E2E_WARM_T1_d16bbd10ed81-1","count":1}; observed 0
  • Passmatched
  • Passmatched
  • Failexpected {"kind":"message_ordered","expected":["PAPERCLIP_E2E_WARM_T1_d16bbd10ed81-1","PAPERCLIP_E2E_WARM_T2_d16bbd10ed81-1","PAPERCLIP_E2E_WARM_T3_d16bbd10ed81-1"]}; observed "PAPERCLIP_E2E_WARM_T2_d16bbd10ed81-1\nPrepared Warm continuity turn 3 file for this response.\nPAPERCLIP_E2E_WARM_T3_d16bbd10ed81-1"
  • Passmatched
  • Passmatched
  • Passmatched
  • Passmatched
  • Passmatched
Tokens33,331 in · 4,896 out574,523 cached · 3/3 runs covered
LLM spendUnavailable0/3 runs provider-priced
LLM estimate$0.4611Estimated from captured usage
Execution$0.008744 est.1m 34s agent · 1m 58s lease

Task chat

RUN-1: Create warm continuity turn 1 files · 21 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-d16bbd10ed81-1.txt with exactly this one line followed by a newline: T1-d16bbd10ed81-1 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-d16bbd10ed81-1.txt contains exactly these lines, once each and in order: T1-d16bbd10ed81-1. 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\_d16bbd10ed81-1",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 d16bbd10ed81-1
I’m creating the workspace file and the three personal continuity files, then I’ll verify exact sizes and bytes before submitting the required review disposition.
Runner E2E runner-codex d16bbd10ed81-1
The task title is saved. I’m now writing the exact text payloads and generating the fixed-size binary memory file; verification will inspect raw bytes, not just displayed text.
Runner E2E runner-codex d16bbd10ed81-1
All four files are written. I’m performing strict byte-level checks now: exact content and LF for both text lines, nine bytes with no newline for the temporary file, and 8,388,608 occurrences of byte `0x5d` for the binary file.
Runner E2E runner-codex d16bbd10ed81-1
Byte verification passed for every required file. I’m submitting the verified result for human review now.
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_d16bbd10ed81-1 Approve completion Continue work Status: rejected
YouResponse
rejected This is warm Daytona continuity turn 2 of 3. Work only in the current execution workspace. Before changing anything, read daytona-warm-d16bbd10ed81-1.txt and verify its content is exactly these prior lines in order, each followed by a newline: T1-d16bbd10ed81-1. Then append exactly T2-d16bbd10ed81-1 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-d16bbd10ed81-1.txt contains exactly these lines, once each and in order: T1-d16bbd10ed81-1 | T2-d16bbd10ed81-1. 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_d16bbd10ed81-1",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-d16bbd10ed81-1.txt",status:"passed"}]}. Wait for that tool call to succeed, then emit exactly PAPERCLIP_E2E_WARM_T2_d16bbd10ed81-1 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-d16bbd10ed81-1","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":"d16bbd10ed81-1-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_d16bbd10ed81-1","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_d16bbd10ed81-1 again as assistant text. Do not include PAPERCLIP_E2E_WARM_T2_d16bbd10ed81-1 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-d16bbd10ed81-1, each followed by a newline. Append exactly T2-d16bbd10ed81-1 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 d16bbd10ed81-1
I’m first validating the untouched turn-1 workspace file byte-for-byte. Once that prerequisite passes, I’ll append turn 2 and update the personal continuity state.
Runner E2E runner-codex d16bbd10ed81-1
The turn-1 workspace bytes are exact, including the final `0a` LF. I’m checking the retained personal files before editing them, then I’ll append one line to each text continuity file and remove the temporary marker.
Runner E2E runner-codex d16bbd10ed81-1
The turn-2 line is appended once to both continuity files, and the temporary personal file is removed. I’m now running the final raw-byte and preservation checks before review submission.
Runner E2E runner-codex d16bbd10ed81-1
Every turn-2 check passed: ordered text bytes and LF terminators, unchanged 8 MiB binary payload, and confirmed deletion. I’m submitting this revision for human review.
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_d16bbd10ed81-1 Approve completion Continue work Status: rejected
Runner E2E runner-codex d16bbd10ed81-1
PAPERCLIP_E2E_WARM_T2_d16bbd10ed81-1
YouResponse
rejected This is warm Daytona continuity turn 3 of 3. Work only in the current execution workspace. Before changing anything, read daytona-warm-d16bbd10ed81-1.txt and verify its content is exactly these prior lines in order, each followed by a newline: T1-d16bbd10ed81-1 | T2-d16bbd10ed81-1. Then append exactly T3-d16bbd10ed81-1 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-d16bbd10ed81-1.txt contains exactly these lines, once each and in order: T1-d16bbd10ed81-1 | T2-d16bbd10ed81-1 | T3-d16bbd10ed81-1. 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_d16bbd10ed81-1",completionClaim:{contractRevision:CURRENT_TURN_REVISION,objectiveSatisfied:true,criteria:[{criterionId:"objective",status:"satisfied",evidenceRefs:[]}],remainingWork:[]},attentionRequests:[],evidence:[],verification:[{commandOrCheck:"read daytona-warm-d16bbd10ed81-1.txt",status:"passed"}]}. Wait for that tool call to succeed, then emit exactly PAPERCLIP_E2E_WARM_T3_d16bbd10ed81-1 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_d16bbd10ed81-1"}. 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_d16bbd10ed81-1 again as assistant text. Do not include PAPERCLIP_E2E_WARM_T3_d16bbd10ed81-1 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-d16bbd10ed81-1 | T2-d16bbd10ed81-1, each followed by a newline. Append exactly T3-d16bbd10ed81-1 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 d16bbd10ed81-1
I’m validating the untouched two-line workspace file first. After that passes, I’ll append turn 3 and verify the full workspace and personal continuity state.
Runner E2E runner-codex d16bbd10ed81-1
The two existing workspace lines are exact and correctly LF-terminated. I’m checking the retained personal memory, preserved binary, and prior deletion before making the final append.
Runner E2E runner-codex d16bbd10ed81-1
The third line is appended once to both continuity files. I’m running the final byte-level checks now, including LF values, line order, binary preservation, and deleted-file absence.
Runner E2E runner-codex d16bbd10ed81-1
All final continuity checks passed. I’m recording the completed turn-3 result now.
Runner E2E runner-codex d16bbd10ed81-1
The completion gate requires the verified workspace file to be registered as accessible delivery evidence. I’m registering that exact 54-byte file, then I’ll resubmit the same completion claim with its evidence reference.
Runner E2E runner-codex d16bbd10ed81-1
Prepared Warm continuity turn 3 file for this response.
Runner E2E runner-codex d16bbd10ed81-1
PAPERCLIP_E2E_WARM_T3_d16bbd10ed81-1
Diagnostics

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 18s
Agent runtime
1m 34s
Environment lease
1m 58s
Runtime
native
Provider
codex
Model
gpt-5.6-sol
Issue
RUN-1
TurnRunLeaseSchedulerRun durationFinal settlement (legacy response field)
1 357989ab-8e07-4564-be35-68a2845678a2 created 4s 34s 38s
2 c8ffdcee-7d64-4079-a8d4-6ce6f3fc5398 resumed 343ms 28s 28s
3 7411c59b-bb49-4a3a-bfc9-832454b22c03 resumed 348ms 32s 32s
Startup reuse evidence
RunWarmthEnvironment/leaseWorkspaceRunnerProvider processProvider sessionProvider launches
357989ab-8e07-4564-be35-68a2845678a2unknown fresh (created)fresh (created)fresh (created)unknown (evidence_missing)fresh (created) unknown
c8ffdcee-7d64-4079-a8d4-6ce6f3fc5398partial_reuse reused (verified_reuse)reused (verified_reuse)reused (verified_reuse)unknown (evidence_missing)reused (verified_reuse) unknown
7411c59b-bb49-4a3a-bfc9-832454b22c03partial_reuse reused (verified_reuse)reused (verified_reuse)reused (verified_reuse)unknown (evidence_missing)reused (verified_reuse) unknown
ResultMatcherExpectationDetail
Fail message_occurrences {"kind":"message_occurrences","expected":"PAPERCLIP_E2E_WARM_T1_d16bbd10ed81-1","count":1} expected {"kind":"message_occurrences","expected":"PAPERCLIP_E2E_WARM_T1_d16bbd10ed81-1","count":1}; observed 0
Pass message_occurrences {"kind":"message_occurrences","expected":"PAPERCLIP_E2E_WARM_T2_d16bbd10ed81-1","count":1} matched
Pass message_occurrences {"kind":"message_occurrences","expected":"PAPERCLIP_E2E_WARM_T3_d16bbd10ed81-1","count":1} matched
Fail message_ordered {"kind":"message_ordered","expected":["PAPERCLIP_E2E_WARM_T1_d16bbd10ed81-1","PAPERCLIP_E2E_WARM_T2_d16bbd10ed81-1","PAPERCLIP_E2E_WARM_T3_d16bbd10ed81-1"]} expected {"kind":"message_ordered","expected":["PAPERCLIP_E2E_WARM_T1_d16bbd10ed81-1","PAPERCLIP_E2E_WARM_T2_d16bbd10ed81-1","PAPERCLIP_E2E_WARM_T3_d16bbd10ed81-1"]}; observed "PAPERCLIP_E2E_WARM_T2_d16bbd10ed81-1\nPrepared Warm continuity turn 3 file for this response.\nPAPERCLIP_E2E_WARM_T3_d16bbd10ed81-1"
Pass file_exact {"kind":"file_exact","path":"daytona-warm-d16bbd10ed81-1.txt","expected":"T1-d16bbd10ed81-1\nT2-d16bbd10ed81-1\nT3-d16bbd10ed81-1\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": 33331,
      "outputTokens": 4896,
      "cachedInputTokens": 574523,
      "totalTokens": 612750,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0.4610532,
      "costStatus": "estimated"
    },
    "runtime": {
      "provider": "daytona",
      "agentRunDurationMs": 93592,
      "leaseDurationMs": 117686,
      "leaseCount": 4,
      "cpuCores": 4,
      "memoryGiB": 4,
      "diskGiB": 10,
      "estimatedListCostUsd": 0.0087440698,
      "costStatus": "estimated",
      "costSource": "daytona_public_list_price",
      "pricingAsOf": "2026-08-27",
      "pricingUrl": "https://www.daytona.io/pricing"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0.0087440698,
    "observedAndEstimatedCostUsd": 0.4697972698,
    "complete": true
  },
  "rawUsage": {
    "runs": [
      {
        "runId": "7411c59b-bb49-4a3a-bfc9-832454b22c03",
        "usage": {
          "model": "gpt-5.6-sol",
          "biller": "openai",
          "costUsd": null,
          "provider": "openai",
          "costStatus": "estimated",
          "billingType": "metered_api",
          "inputTokens": 3944,
          "ledgerScope": {
            "issueId": "10b5db92-ae76-4869-a04f-edc5c1d65128",
            "projectId": "f436bebf-f464-4a4b-96d2-30bc789c94f9",
            "billingCode": null
          },
          "usageSource": "per_run",
          "costUsdExact": "0.166171200",
          "freshSession": false,
          "outputTokens": 1867,
          "usageByModel": null,
          "sessionReused": true,
          "budgetDispatch": {
            "admittedAt": "2026-11-02T18:03:18.712Z",
            "handedOffAt": "2026-11-02T18:03:18.723Z",
            "reservationId": "cb0629e5-bb74-42d2-ba15-08d6b47f46fe",
            "recoveryLeaseOwner": null
          },
          "budgetExposure": {
            "sequence": 239,
            "sourceId": "2487f2d4-e0e9-5cc5-a634-c682ee826132",
            "costCents": "16.6171200"
          },
          "rawInputTokens": 3944,
          "sessionRotated": false,
          "configFreshness": {
            "session": {
              "reset": false,
              "categories": [
                "adapter",
                "adapterConfig",
                "agentRuntimeConfig",
                "instructions",
                "issueOverrides",
                "workspaceConfig",
                "environment",
                "envBindings",
                "secrets",
                "runtimeSkills"
              ],
              "resetReasons": [],
              "nextFingerprint": "v1:sha256:939eb800b3898ee972e15223657a4e4155f6b0fee2765096f7082662704c9317",
              "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:sha256:04415b26251d2c9a0021115cbfcd8bc8fcef3b0ed8179aaf0ec21e05aecd0d7e",
              "workspaceReused": true,
              "activeWorkspaceId": "ac358e00-12fc-4120-bce6-d198e35c6f5c",
              "changedCategories": [],
              "storedFingerprint": "v1:sha256:04415b26251d2c9a0021115cbfcd8bc8fcef3b0ed8179aaf0ec21e05aecd0d7e",
              "fingerprintVersion": 1,
              "inferredFingerprint": null,
              "previousWorkspaceId": "ac358e00-12fc-4120-bce6-d198e35c6f5c",
              "configSnapshotRefreshed": false,
              "storedFingerprintPresent": true
            }
          },
          "rawOutputTokens": 1867,
          "cacheWriteTokens": 0,
          "cachedInputTokens": 282638,
          "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": "01a19d6d-0c82-7fb0-85b6-f4bcb4e5aac8",
          "accountingReceiptId": "87d40ab4-397a-5b27-a77f-d1a764fae5e0",
          "cacheAdjustedCostUsd": null,
          "rawCachedInputTokens": 282638,
          "sessionRotationReason": null,
          "accountingReceiptOwner": "native_producer",
          "accountingReceiptReady": true,
          "rawInputIncludesCached": false,
          "accountingReceiptSequence": 239,
          "accountingReceiptSourceId": "2487f2d4-e0e9-5cc5-a634-c682ee826132",
          "accountingReceiptReceivedAt": "2026-11-02T18:03:45.223Z"
        }
      },
      {
        "runId": "c8ffdcee-7d64-4079-a8d4-6ce6f3fc5398",
        "usage": {
          "model": "gpt-5.6-sol",
          "biller": "openai",
          "costUsd": null,
          "provider": "openai",
          "costStatus": "estimated",
          "billingType": "metered_api",
          "inputTokens": 3196,
          "ledgerScope": {
            "issueId": "10b5db92-ae76-4869-a04f-edc5c1d65128",
            "projectId": "f436bebf-f464-4a4b-96d2-30bc789c94f9",
            "billingCode": null
          },
          "usageSource": "per_run",
          "costUsdExact": "0.109970400",
          "freshSession": false,
          "outputTokens": 1517,
          "usageByModel": null,
          "sessionReused": true,
          "budgetDispatch": {
            "admittedAt": "2026-11-02T18:02:43.339Z",
            "handedOffAt": "2026-11-02T18:02:43.351Z",
            "reservationId": "7657b9c7-0ebb-46c3-907c-405b309c74ce",
            "recoveryLeaseOwner": null
          },
          "budgetExposure": {
            "sequence": 214,
            "sourceId": "9a9a3284-4740-5778-aa22-257e2f5ae9db",
            "costCents": "10.9970400"
          },
          "rawInputTokens": 3196,
          "sessionRotated": false,
          "configFreshness": {
            "session": {
              "reset": false,
              "categories": [
                "adapter",
                "adapterConfig",
                "agentRuntimeConfig",
                "instructions",
                "issueOverrides",
                "workspaceConfig",
                "environment",
                "envBindings",
                "secrets",
                "runtimeSkills"
              ],
              "resetReasons": [],
              "nextFingerprint": "v1:sha256:939eb800b3898ee972e15223657a4e4155f6b0fee2765096f7082662704c9317",
              "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:sha256:04415b26251d2c9a0021115cbfcd8bc8fcef3b0ed8179aaf0ec21e05aecd0d7e",
              "workspaceReused": true,
              "activeWorkspaceId": "ac358e00-12fc-4120-bce6-d198e35c6f5c",
              "changedCategories": [],
              "storedFingerprint": "v1:sha256:04415b26251d2c9a0021115cbfcd8bc8fcef3b0ed8179aaf0ec21e05aecd0d7e",
              "fingerprintVersion": 1,
              "inferredFingerprint": null,
              "previousWorkspaceId": "ac358e00-12fc-4120-bce6-d198e35c6f5c",
              "configSnapshotRefreshed": false,
              "storedFingerprintPresent": true
            }
          },
          "rawOutputTokens": 1517,
          "cacheWriteTokens": 0,
          "cachedInputTokens": 167116,
          "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": "01a19d6d-0c82-7fb0-85b6-f4bcb4e5aac8",
          "accountingReceiptId": "cb3c0809-d19b-5956-a4fd-46572a7cb57c",
          "cacheAdjustedCostUsd": null,
          "rawCachedInputTokens": 167116,
          "sessionRotationReason": null,
          "accountingReceiptOwner": "native_producer",
          "accountingReceiptReady": true,
          "rawInputIncludesCached": false,
          "accountingReceiptSequence": 214,
          "accountingReceiptSourceId": "9a9a3284-4740-5778-aa22-257e2f5ae9db",
          "accountingReceiptReceivedAt": "2026-11-02T18:03:05.500Z"
        }
      },
      {
        "runId": "357989ab-8e07-4564-be35-68a2845678a2",
        "usage": {
          "model": "gpt-5.6-sol",
          "biller": "openai",
          "costUsd": null,
          "provider": "openai",
          "costStatus": "estimated",
          "billingType": "metered_api",
          "inputTokens": 26191,
          "ledgerScope": {
            "issueId": "10b5db92-ae76-4869-a04f-edc5c1d65128",
            "projectId": "f436bebf-f464-4a4b-96d2-30bc789c94f9",
            "billingCode": null
          },
          "usageSource": "per_run",
          "costUsdExact": "0.184911600",
          "outputTokens": 1512,
          "usageByModel": null,
          "budgetDispatch": {
            "admittedAt": "2026-11-02T18:02:06.456Z",
            "handedOffAt": "2026-11-02T18:02:06.467Z",
            "reservationId": "27bf3e67-cc3b-4eaf-aa95-ff5ff1033d94",
            "recoveryLeaseOwner": null
          },
          "budgetExposure": {
            "sequence": 213,
            "sourceId": "63d4f60a-c2a0-5565-afa1-6a0343ab23df",
            "costCents": "18.4911600"
          },
          "cacheWriteTokens": 0,
          "cachedInputTokens": 124769,
          "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": "95acfd81-b106-5b63-ad33-2d38230fd7f4",
          "cacheAdjustedCostUsd": null,
          "accountingReceiptOwner": "native_producer",
          "accountingReceiptReady": true,
          "accountingReceiptSequence": 213,
          "accountingReceiptSourceId": "63d4f60a-c2a0-5565-afa1-6a0343ab23df",
          "accountingReceiptReceivedAt": "2026-11-02T18:02:30.001Z"
        }
      }
    ]
  },
  "workerTiming": {
    "version": 1,
    "scope": "worker",
    "status": "complete",
    "executionId": "daytona-warm-continuity.runner-codex.daytona.warm-three-turn",
    "attempt": 1,
    "startedAt": "2026-11-02T18:01:43.102Z",
    "finishedAt": "2026-11-02T18:04:01.193Z",
    "segments": [
      {
        "phase": "setup",
        "startedAt": "2026-11-02T18:01:43.102Z",
        "finishedAt": "2026-11-02T18:01:46.698Z"
      },
      {
        "phase": "execution",
        "startedAt": "2026-11-02T18:01:46.698Z",
        "finishedAt": "2026-11-02T18:03:56.259Z"
      },
      {
        "phase": "cleanup",
        "startedAt": "2026-11-02T18:03:56.259Z",
        "finishedAt": "2026-11-02T18:03:56.460Z"
      },
      {
        "phase": "feedback",
        "startedAt": "2026-11-02T18:03:56.460Z",
        "finishedAt": "2026-11-02T18:03:56.683Z"
      },
      {
        "phase": "cleanup",
        "startedAt": "2026-11-02T18:03:56.683Z",
        "finishedAt": "2026-11-02T18:04:01.193Z"
      },
      {
        "phase": "finalization",
        "startedAt": "2026-11-02T18:04:01.193Z",
        "finishedAt": "2026-11-02T18:04:01.193Z"
      }
    ]
  },
  "startupReuse": [
    {
      "runId": "357989ab-8e07-4564-be35-68a2845678a2",
      "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": "c8ffdcee-7d64-4079-a8d4-6ce6f3fc5398",
      "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": "7411c59b-bb49-4a3a-bfc9-832454b22c03",
      "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
    }
  ]
}