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.

2026-11-06T17:16:07.556Z0252421dSource run ↗

0/8Passed
8Failed
60m 59sSummed attempt time
Campaign usage and spend
0 / 0Complaints / suggestions · retained attempts0 distinct items · 7 attempts with incomplete collection · 0 failed submissions · 0 unresolved submissions
8Retained attempts0 missing attempts · 0 out-of-scope artifacts
UnavailableInput tokens
UnavailableOutput tokens
UnavailableCached tokens
UnavailableLLM reported subtotal
$0.002587Daytona list estimate
31m 26sObserved attempt window8 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.

UnknownAgent execution time
UnknownDaytona lease time
0/8Runs 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.

Unknown (2m 55s observed)Worker setup time
Unknown (57m 58s observed)Worker execution time
Unknown (420ms observed)Worker feedback time
Unknown (2s observed)Worker cleanup time
Unknown (8ms observed)Worker finalization time

7/8 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 4 of 192 capabilities linked · 4 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

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
History 1/4 0/2 passed · 2 failed or incomplete
Questions and approvals 0/8 No mapped journey
Steering and queued messages 0/7 No mapped journey
Work products 1/5 0/2 passed · 2 failed or incomplete

Agents and reusable capabilities

FeatureCapabilities linkedLinked test results
Hiring, configuration, and organization 0/9 No mapped journey
Session 1/5 0/2 passed · 2 failed or incomplete
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
User continuation 1/8 0/2 passed · 2 failed or incomplete

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

Rolling control-plane web deployment (per-turn)

Overlap independent ephemeral web servers while a remote execution stays active; keep ordinary reads, saves, files and a later native continuation working.

Pass rate0.0%0/1 passed
TokensUnavailableUnavailable input · Unavailable output
Known spendUnavailablereported LLM + model/runtime estimates estimate
Agent timeUnknownUnknown lease
Execution1/10 retries · cleanup failed
Runner OpenCodeDaytona sandboxopencode · openrouter/deepseek/deepseek-v4-flash-0731
Overall failed · No behavioral checks recorded

permanent infrastructure

Playwright exited 1 before writing a result; isolated config could not be inspected after bootstrap failure: ENOENT: no such file or directory, open '/tmp/paperclip-runner-e2e-TN5XaR/paperclip-home/instances/runner-e2e-6b32aa0e854efa9d/config.json'; Temporary runner E2E state cleanup failed at /tmp/paperclip-runner-e2e-TN5XaR: Preserving private recovery state after unconfirmed cleanup: /tmp/paperclip-runner-e2e-TN5XaR
cleanup=failed
Test detailsNo checks recorded · 4s
Tested URL
Not recorded
Environment
Daytona sandbox
Model
openrouter/deepseek/deepseek-v4-flash-0731
Runtime
native · opencode
TokensUnavailable in · Unavailable outUnavailable cached · 0/1 runs covered
LLM spendUnavailable0/1 runs provider-priced
ExecutionUnavailable
Diagnostics

Worker phase timing: not captured.

Feedback was not captured for this attempt.

rolling-web-deployment.runner-opencode.daytona.recover-controller
Attempt
1
Duration
4s
Agent runtime
Unknown
Runtime
native
Provider
opencode
Model
openrouter/deepseek/deepseek-v4-flash-0731

cleanup=failed

Usage, billing and timing metadata
{
  "billing": {
    "llm": {
      "runCount": 1,
      "runsWithTokenUsage": 0,
      "runsWithReportedCost": 0,
      "runsWithEstimatedCost": 0,
      "runsWithPartialReportedCost": 0,
      "inputTokens": 0,
      "outputTokens": 0,
      "cachedInputTokens": 0,
      "totalTokens": 0,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0,
      "costStatus": "unavailable"
    },
    "runtime": {
      "provider": "daytona",
      "agentRunDurationMs": null,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "unavailable",
      "costSource": "provider_cost_unavailable"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": null,
  "workerTiming": null,
  "startupReuse": []
}

Test suite

Daytona warm controller outage continuity

Keep the original active native runner, reusable warm sandbox, task tools and saved files through five minutes without a controller, then continue the completed session after another replacement.

Pass rate0.0%0/1 passed
TokensUnavailableUnavailable input · Unavailable output
Known spend$0.000793 (partial)reported LLM + model/runtime estimates estimate
Agent timeUnknown11s lease
Execution1/10 retries · cleanup passed
Codie staging-model diagnosticDaytona warm reusable sandboxcodex · gpt-6.1-sol
Overall failed · No behavioral checks recorded

permanent infrastructure

Artifact sandbox qualification failed before task creation: {"passed": false, "checks": [{"id": "artifact-readable", "passed": false, "detail": "Command '['docker', 'version', '--format', '{{.Server.Version}}']' timed out after 10 seconds"}]}
Test detailsNo checks recorded · 1m 35s
Environment
Daytona warm reusable sandbox
Model
gpt-6.1-sol
Runtime
native · codex
TokensUnavailable in · Unavailable outUnavailable cached · 0/1 runs covered
LLM spendUnavailable0/1 runs provider-priced
Execution$0.000793 est. · 11s lease
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-restart-continuity.runner-codex.daytona.recover-controller
Attempt
1
Duration
1m 35s
Agent runtime
Unknown
Environment lease
11s
Runtime
native
Provider
codex
Model
gpt-6.1-sol
Usage, billing and timing metadata
{
  "billing": {
    "llm": {
      "runCount": 1,
      "runsWithTokenUsage": 0,
      "runsWithReportedCost": 0,
      "runsWithEstimatedCost": 0,
      "runsWithPartialReportedCost": 0,
      "inputTokens": 0,
      "outputTokens": 0,
      "cachedInputTokens": 0,
      "totalTokens": 0,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0,
      "costStatus": "unavailable"
    },
    "runtime": {
      "provider": "daytona",
      "agentRunDurationMs": null,
      "leaseDurationMs": 10677,
      "leaseCount": 2,
      "cpuCores": 4,
      "memoryGiB": 4,
      "diskGiB": 10,
      "estimatedListCostUsd": 0.0007933011000000001,
      "costStatus": "estimated",
      "costSource": "daytona_public_list_price",
      "pricingAsOf": "2026-08-27",
      "pricingUrl": "https://www.daytona.io/pricing"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0.0007933011000000001,
    "observedAndEstimatedCostUsd": 0.0007933011000000001,
    "complete": false
  },
  "rawUsage": {
    "runs": []
  },
  "workerTiming": {
    "version": 1,
    "scope": "worker",
    "status": "complete",
    "executionId": "daytona-restart-continuity.runner-codex.daytona.recover-controller",
    "attempt": 1,
    "startedAt": "2026-11-06T16:33:44.030Z",
    "finishedAt": "2026-11-06T16:35:18.759Z",
    "segments": [
      {
        "phase": "setup",
        "startedAt": "2026-11-06T16:33:44.030Z",
        "finishedAt": "2026-11-06T16:35:08.086Z"
      },
      {
        "phase": "execution",
        "startedAt": "2026-11-06T16:35:08.086Z",
        "finishedAt": "2026-11-06T16:35:18.621Z"
      },
      {
        "phase": "cleanup",
        "startedAt": "2026-11-06T16:35:18.621Z",
        "finishedAt": "2026-11-06T16:35:18.703Z"
      },
      {
        "phase": "feedback",
        "startedAt": "2026-11-06T16:35:18.703Z",
        "finishedAt": "2026-11-06T16:35:18.723Z"
      },
      {
        "phase": "cleanup",
        "startedAt": "2026-11-06T16:35:18.723Z",
        "finishedAt": "2026-11-06T16:35:18.758Z"
      },
      {
        "phase": "finalization",
        "startedAt": "2026-11-06T16:35:18.758Z",
        "finishedAt": "2026-11-06T16:35:18.759Z"
      }
    ]
  },
  "startupReuse": []
}

Test suite

Preserve completed work through finalization restart

Crash an owned isolated server after accepted provider output, then require real workspace recovery and one final delivery without provider replay.

Pass rate0.0%0/2 passed
TokensUnavailableUnavailable input · Unavailable output
Known spend$0.001221 (partial)reported LLM + model/runtime estimates estimate
Agent timeUnknown16s lease
Execution2/20 retries · cleanup passed
Codie staging-model diagnosticDaytona sandboxcodex · gpt-6.1-sol
Overall failed · No behavioral checks recorded

candidate failure

Stopped waiting for accepted result with unfinished workspace export: Finalization fault boundary was not exercised before settlement
Test detailsNo checks recorded · 5m 27s
Environment
Daytona sandbox
Model
gpt-6.1-sol
Runtime
native · codex
TokensUnavailable in · Unavailable outUnavailable cached · 0/1 runs covered
LLM spendUnavailable0/1 runs provider-priced
Execution$0.000652 est. · 9s lease

Task chat

RUN-1: Retain a generated data sample c8d3a8bff59e-1 · 2 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
Generate exactly 67108864 unpredictable bytes from the operating system random source in retained-data-c8d3a8bff59e-1.bin. Keep this binary file in the configured workspace; do not register or upload the binary as a deliverable. Generate a fresh 32-byte hexadecimal reference. Compute the SHA-256 of the complete binary file. Write retained-proof-c8d3a8bff59e-1.json as JSON with exactly three fields: reference (the fresh reference), byteSize (the binary file's exact byte count), and sha256 (the full lowercase file hash). Register retained-proof-c8d3a8bff59e-1.json as a downloadable artifact work product with that exact title and deliver its accessible link in this task. Retain both original files. Finish after verifying the proof. Do not create other tasks or agents.
System
Paperclip automatically retried continuation for this assigned `in_progress` issue during terminal run recovery, but it still has no live execution path. Moving it to `blocked` so it is visible for intervention.
Diagnostics

Worker phase timing: complete.

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

finalization-recovery.runner-codex.daytona.preserve-result-on-restart
Attempt
1
Duration
5m 27s
Agent runtime
Unknown
Environment lease
9s
Runtime
native
Provider
codex
Model
gpt-6.1-sol
Usage, billing and timing metadata
{
  "billing": {
    "llm": {
      "runCount": 1,
      "runsWithTokenUsage": 0,
      "runsWithReportedCost": 0,
      "runsWithEstimatedCost": 0,
      "runsWithPartialReportedCost": 0,
      "inputTokens": 0,
      "outputTokens": 0,
      "cachedInputTokens": 0,
      "totalTokens": 0,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0,
      "costStatus": "unavailable"
    },
    "runtime": {
      "provider": "daytona",
      "agentRunDurationMs": null,
      "leaseDurationMs": 8777,
      "leaseCount": 2,
      "cpuCores": 4,
      "memoryGiB": 4,
      "diskGiB": 10,
      "estimatedListCostUsd": 0.0006521311000000001,
      "costStatus": "estimated",
      "costSource": "daytona_public_list_price",
      "pricingAsOf": "2026-08-27",
      "pricingUrl": "https://www.daytona.io/pricing"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0.0006521311000000001,
    "observedAndEstimatedCostUsd": 0.0006521311000000001,
    "complete": false
  },
  "rawUsage": {
    "runs": []
  },
  "workerTiming": {
    "version": 1,
    "scope": "worker",
    "status": "complete",
    "executionId": "finalization-recovery.runner-codex.daytona.preserve-result-on-restart",
    "attempt": 1,
    "startedAt": "2026-11-06T16:33:53.005Z",
    "finishedAt": "2026-11-06T16:39:20.212Z",
    "segments": [
      {
        "phase": "setup",
        "startedAt": "2026-11-06T16:33:53.005Z",
        "finishedAt": "2026-11-06T16:35:09.448Z"
      },
      {
        "phase": "execution",
        "startedAt": "2026-11-06T16:35:09.448Z",
        "finishedAt": "2026-11-06T16:39:19.792Z"
      },
      {
        "phase": "cleanup",
        "startedAt": "2026-11-06T16:39:19.792Z",
        "finishedAt": "2026-11-06T16:39:20.032Z"
      },
      {
        "phase": "feedback",
        "startedAt": "2026-11-06T16:39:20.032Z",
        "finishedAt": "2026-11-06T16:39:20.147Z"
      },
      {
        "phase": "cleanup",
        "startedAt": "2026-11-06T16:39:20.147Z",
        "finishedAt": "2026-11-06T16:39:20.209Z"
      },
      {
        "phase": "finalization",
        "startedAt": "2026-11-06T16:39:20.209Z",
        "finishedAt": "2026-11-06T16:39:20.212Z"
      }
    ]
  },
  "startupReuse": []
}
Claude staging-model diagnosticDaytona sandboxacpx · claude-opus-5-5
Overall failed · No behavioral checks recorded

candidate failure

Timed out waiting for accepted result with unfinished workspace export; the observed state did not satisfy the condition. See the saved state evidence.
Test detailsNo checks recorded · 19m 31s
Environment
Daytona sandbox
Model
claude-opus-5-5
Runtime
native · acpx
TokensUnavailable in · Unavailable outUnavailable cached · 0/1 runs covered
LLM spendUnavailable0/1 runs provider-priced
Execution$0.000569 est. · 8s lease

Task chat

RUN-1: Retain a generated data sample 2ce671133004-1 · 1 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
Generate exactly 67108864 unpredictable bytes from the operating system random source in retained-data-2ce671133004-1.bin. Keep this binary file in the configured workspace; do not register or upload the binary as a deliverable. Generate a fresh 32-byte hexadecimal reference. Compute the SHA-256 of the complete binary file. Write retained-proof-2ce671133004-1.json as JSON with exactly three fields: reference (the fresh reference), byteSize (the binary file's exact byte count), and sha256 (the full lowercase file hash). Register retained-proof-2ce671133004-1.json as a downloadable artifact work product with that exact title and deliver its accessible link in this task. Retain both original files. Finish after verifying the proof. Do not create other tasks or agents.
Diagnostics

Worker phase timing: complete.

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

finalization-recovery.runner-acpx-claude.daytona.preserve-result-on-restart
Attempt
1
Duration
19m 31s
Agent runtime
Unknown
Environment lease
8s
Runtime
native
Provider
acpx
Model
claude-opus-5-5
Usage, billing and timing metadata
{
  "billing": {
    "llm": {
      "runCount": 1,
      "runsWithTokenUsage": 0,
      "runsWithReportedCost": 0,
      "runsWithEstimatedCost": 0,
      "runsWithPartialReportedCost": 0,
      "inputTokens": 0,
      "outputTokens": 0,
      "cachedInputTokens": 0,
      "totalTokens": 0,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0,
      "costStatus": "unavailable"
    },
    "runtime": {
      "provider": "daytona",
      "agentRunDurationMs": null,
      "leaseDurationMs": 7654,
      "leaseCount": 3,
      "cpuCores": 4,
      "memoryGiB": 4,
      "diskGiB": 10,
      "estimatedListCostUsd": 0.0005686921999999999,
      "costStatus": "estimated",
      "costSource": "daytona_public_list_price",
      "pricingAsOf": "2026-08-27",
      "pricingUrl": "https://www.daytona.io/pricing"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0.0005686921999999999,
    "observedAndEstimatedCostUsd": 0.0005686921999999999,
    "complete": false
  },
  "rawUsage": {
    "runs": []
  },
  "workerTiming": {
    "version": 1,
    "scope": "worker",
    "status": "complete",
    "executionId": "finalization-recovery.runner-acpx-claude.daytona.preserve-result-on-restart",
    "attempt": 1,
    "startedAt": "2026-11-06T16:34:10.187Z",
    "finishedAt": "2026-11-06T16:53:40.709Z",
    "segments": [
      {
        "phase": "setup",
        "startedAt": "2026-11-06T16:34:10.187Z",
        "finishedAt": "2026-11-06T16:34:11.697Z"
      },
      {
        "phase": "execution",
        "startedAt": "2026-11-06T16:34:11.697Z",
        "finishedAt": "2026-11-06T16:53:40.348Z"
      },
      {
        "phase": "cleanup",
        "startedAt": "2026-11-06T16:53:40.348Z",
        "finishedAt": "2026-11-06T16:53:40.554Z"
      },
      {
        "phase": "feedback",
        "startedAt": "2026-11-06T16:53:40.554Z",
        "finishedAt": "2026-11-06T16:53:40.636Z"
      },
      {
        "phase": "cleanup",
        "startedAt": "2026-11-06T16:53:40.636Z",
        "finishedAt": "2026-11-06T16:53:40.709Z"
      },
      {
        "phase": "finalization",
        "startedAt": "2026-11-06T16:53:40.709Z",
        "finishedAt": "2026-11-06T16:53:40.709Z"
      }
    ]
  },
  "startupReuse": []
}

Test suite

Everyday Paperclip Work

Real user requests, useful downloaded work, and durable continuation using production instructions.

Pass rate0.0%0/2 passed
TokensUnavailableUnavailable input · Unavailable output
Known spend$0.000450 (partial)reported LLM + model/runtime estimates estimate
Agent timeUnknownUnknown lease
Execution2/20 retries · cleanup passed
Runner CodexDaytona warm reusable sandboxcodex · gpt-5.6-sol
Overall failed · No behavioral checks recorded

permanent infrastructure

Native Codex image qualification was not recorded; agent creation was not attempted.
Test detailsNo checks recorded · 2s
Environment
Daytona warm reusable sandbox
Model
gpt-5.6-sol
Runtime
native · codex
TokensUnavailable in · Unavailable outUnavailable cached · 0/1 runs covered
LLM spendUnavailable0/1 runs provider-priced
ExecutionUnavailable
Diagnostics

Worker phase timing: complete.

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

everyday-workflows.runner-codex.daytona.recover-controller
  • Recovery · User continuation
  • Documents, attachments, and work products · Work products
Attempt
1
Duration
2s
Agent runtime
Unknown
Runtime
native
Provider
codex
Model
gpt-5.6-sol
Usage, billing and timing metadata
{
  "billing": {
    "llm": {
      "runCount": 1,
      "runsWithTokenUsage": 0,
      "runsWithReportedCost": 0,
      "runsWithEstimatedCost": 0,
      "runsWithPartialReportedCost": 0,
      "inputTokens": 0,
      "outputTokens": 0,
      "cachedInputTokens": 0,
      "totalTokens": 0,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0,
      "costStatus": "unavailable"
    },
    "runtime": {
      "provider": "daytona",
      "agentRunDurationMs": null,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "unavailable",
      "costSource": "provider_cost_unavailable"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": {
    "runs": []
  },
  "workerTiming": {
    "version": 1,
    "scope": "worker",
    "status": "complete",
    "executionId": "everyday-workflows.runner-codex.daytona.recover-controller",
    "attempt": 1,
    "startedAt": "2026-11-06T16:34:11.458Z",
    "finishedAt": "2026-11-06T16:34:13.289Z",
    "segments": [
      {
        "phase": "setup",
        "startedAt": "2026-11-06T16:34:11.458Z",
        "finishedAt": "2026-11-06T16:34:13.278Z"
      },
      {
        "phase": "cleanup",
        "startedAt": "2026-11-06T16:34:13.278Z",
        "finishedAt": "2026-11-06T16:34:13.288Z"
      },
      {
        "phase": "finalization",
        "startedAt": "2026-11-06T16:34:13.288Z",
        "finishedAt": "2026-11-06T16:34:13.289Z"
      }
    ]
  },
  "startupReuse": []
}
Runner ACPX ClaudeDaytona warm reusable sandboxacpx · claude-sonnet-5
Overall failed · No behavioral checks recorded

candidate failure

Timed out waiting for everyday recover-controller settled; the observed state did not satisfy the condition. See the saved state evidence.
Test detailsNo checks recorded · 30m 1s
Environment
Daytona warm reusable sandbox
Model
claude-sonnet-5
Runtime
native · acpx
TokensUnavailable in · Unavailable outUnavailable cached · 0/1 runs covered
LLM spendUnavailable0/1 runs provider-priced
Execution$0.000450 est. · 6s lease

Task chat

RUN-1: Build a small dependency-free Python command-line tool in slugify.py. It accepts one positional string and prints its sl · 1 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
Build a small dependency-free Python command-line tool in slugify.py. It accepts one positional string and prints its slug: trim whitespace, lowercase, replace each sequence outside ASCII a-z and 0-9 with one hyphen, then trim hyphens. Expose slugify(text) for reuse. Include a README and automated tests. Deliver the source and tests as a downloadable ZIP. Work in the project workspace.
Diagnostics

Worker phase timing: complete.

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

everyday-workflows.runner-acpx-claude.daytona.recover-controller
  • Recovery · User continuation
  • Documents, attachments, and work products · Work products
Attempt
1
Duration
30m 1s
Agent runtime
Unknown
Environment lease
6s
Runtime
native
Provider
acpx
Model
claude-sonnet-5
Issue
RUN-1
Usage, billing and timing metadata
{
  "billing": {
    "llm": {
      "runCount": 1,
      "runsWithTokenUsage": 0,
      "runsWithReportedCost": 0,
      "runsWithEstimatedCost": 0,
      "runsWithPartialReportedCost": 0,
      "inputTokens": 0,
      "outputTokens": 0,
      "cachedInputTokens": 0,
      "totalTokens": 0,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0,
      "costStatus": "unavailable"
    },
    "runtime": {
      "provider": "daytona",
      "agentRunDurationMs": null,
      "leaseDurationMs": 6059,
      "leaseCount": 3,
      "cpuCores": 4,
      "memoryGiB": 4,
      "diskGiB": 10,
      "estimatedListCostUsd": 0.00045018369999999996,
      "costStatus": "estimated",
      "costSource": "daytona_public_list_price",
      "pricingAsOf": "2026-08-27",
      "pricingUrl": "https://www.daytona.io/pricing"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0.00045018369999999996,
    "observedAndEstimatedCostUsd": 0.00045018369999999996,
    "complete": false
  },
  "rawUsage": null,
  "workerTiming": {
    "version": 1,
    "scope": "worker",
    "status": "complete",
    "executionId": "everyday-workflows.runner-acpx-claude.daytona.recover-controller",
    "attempt": 1,
    "startedAt": "2026-11-06T16:34:33.136Z",
    "finishedAt": "2026-11-06T17:04:34.581Z",
    "segments": [
      {
        "phase": "setup",
        "startedAt": "2026-11-06T16:34:33.136Z",
        "finishedAt": "2026-11-06T16:34:38.251Z"
      },
      {
        "phase": "execution",
        "startedAt": "2026-11-06T16:34:38.251Z",
        "finishedAt": "2026-11-06T17:04:33.884Z"
      },
      {
        "phase": "cleanup",
        "startedAt": "2026-11-06T17:04:33.884Z",
        "finishedAt": "2026-11-06T17:04:34.376Z"
      },
      {
        "phase": "feedback",
        "startedAt": "2026-11-06T17:04:34.376Z",
        "finishedAt": "2026-11-06T17:04:34.534Z"
      },
      {
        "phase": "cleanup",
        "startedAt": "2026-11-06T17:04:34.534Z",
        "finishedAt": "2026-11-06T17:04:34.580Z"
      },
      {
        "phase": "finalization",
        "startedAt": "2026-11-06T17:04:34.580Z",
        "finishedAt": "2026-11-06T17:04:34.581Z"
      }
    ]
  },
  "startupReuse": [
    {
      "runId": "91c33e6a-0648-448f-8f86-0b98a762a0b3",
      "warmth": "unknown",
      "layers": {
        "environment": {
          "state": "unknown",
          "reason": "evidence_missing"
        },
        "workspace": {
          "state": "unknown",
          "reason": "evidence_missing"
        },
        "runner": {
          "state": "unknown",
          "reason": "evidence_missing"
        },
        "provider_process": {
          "state": "unknown",
          "reason": "evidence_missing"
        },
        "provider_session": {
          "state": "unknown",
          "reason": "evidence_missing"
        }
      },
      "providerLaunchCount": null
    }
  ]
}

Test suite

Agent Chat Recovery and Coordination

Native chat startup cancellation, committed sends, hiring, grounded status, and remote continuity.

Pass rate0.0%0/2 passed
TokensUnavailableUnavailable input · Unavailable output
Known spend$0.000122 (partial)reported LLM + model/runtime estimates estimate
Agent timeUnknownUnknown lease
Execution2/20 retries · cleanup passed
Runner CodexDaytona warm reusable sandboxcodex · gpt-5.6-sol
Overall failed · No behavioral checks recorded

permanent infrastructure

Native Codex image qualification was not recorded; agent creation was not attempted.
Test detailsNo checks recorded · 2s
Environment
Daytona warm reusable sandbox
Model
gpt-5.6-sol
Runtime
native · codex
TokensUnavailable in · Unavailable outUnavailable cached · 0/1 runs covered
LLM spendUnavailable0/1 runs provider-priced
ExecutionUnavailable
Diagnostics

Worker phase timing: complete.

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

agent-chat-hardening.runner-codex.daytona.continuity-restart
  • Agent conversations and project handoff · History
  • Runs, harnesses, and model accounts · Session
Attempt
1
Duration
2s
Agent runtime
Unknown
Runtime
native
Provider
codex
Model
gpt-5.6-sol
Usage, billing and timing metadata
{
  "billing": {
    "llm": {
      "runCount": 1,
      "runsWithTokenUsage": 0,
      "runsWithReportedCost": 0,
      "runsWithEstimatedCost": 0,
      "runsWithPartialReportedCost": 0,
      "inputTokens": 0,
      "outputTokens": 0,
      "cachedInputTokens": 0,
      "totalTokens": 0,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0,
      "costStatus": "unavailable"
    },
    "runtime": {
      "provider": "daytona",
      "agentRunDurationMs": null,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "unavailable",
      "costSource": "provider_cost_unavailable"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": {
    "runs": []
  },
  "workerTiming": {
    "version": 1,
    "scope": "worker",
    "status": "complete",
    "executionId": "agent-chat-hardening.runner-codex.daytona.continuity-restart",
    "attempt": 1,
    "startedAt": "2026-11-06T16:34:00.316Z",
    "finishedAt": "2026-11-06T16:34:02.311Z",
    "segments": [
      {
        "phase": "setup",
        "startedAt": "2026-11-06T16:34:00.316Z",
        "finishedAt": "2026-11-06T16:34:02.291Z"
      },
      {
        "phase": "cleanup",
        "startedAt": "2026-11-06T16:34:02.291Z",
        "finishedAt": "2026-11-06T16:34:02.310Z"
      },
      {
        "phase": "finalization",
        "startedAt": "2026-11-06T16:34:02.310Z",
        "finishedAt": "2026-11-06T16:34:02.311Z"
      }
    ]
  },
  "startupReuse": []
}
Runner ACPX ClaudeDaytona warm reusable sandboxacpx · claude-sonnet-5
Overall failed · No behavioral checks recorded

candidate failure

Timed out waiting for chat turn settles to waiting; the observed state did not satisfy the condition. See the saved state evidence.
Test detailsNo checks recorded · 4m 17s
Environment
Daytona warm reusable sandbox
Model
claude-sonnet-5
Runtime
native · acpx
TokensUnavailable in · Unavailable outUnavailable cached · 0/1 runs covered
LLM spendUnavailable0/1 runs provider-priced
Execution$0.000122 est. · 2s lease

Task chat

RUN-1: Chat with Studio Lead 4edbdbdbb6eb-1 · 1 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.

You
For this conversation only, remember the phrase OLDCONTEXT4edbdbdbb6eb1. Just acknowledge briefly; no project or task is needed.
Diagnostics

Worker phase timing: complete.

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

agent-chat-hardening.runner-acpx-claude.daytona.continuity-restart
  • Agent conversations and project handoff · History
  • Runs, harnesses, and model accounts · Session
Attempt
1
Duration
4m 17s
Agent runtime
Unknown
Environment lease
2s
Runtime
native
Provider
acpx
Model
claude-sonnet-5
Issue
RUN-1
Usage, billing and timing metadata
{
  "billing": {
    "llm": {
      "runCount": 1,
      "runsWithTokenUsage": 0,
      "runsWithReportedCost": 0,
      "runsWithEstimatedCost": 0,
      "runsWithPartialReportedCost": 0,
      "inputTokens": 0,
      "outputTokens": 0,
      "cachedInputTokens": 0,
      "totalTokens": 0,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0,
      "costStatus": "unavailable"
    },
    "runtime": {
      "provider": "daytona",
      "agentRunDurationMs": null,
      "leaseDurationMs": 1646,
      "leaseCount": 1,
      "cpuCores": 4,
      "memoryGiB": 4,
      "diskGiB": 10,
      "estimatedListCostUsd": 0.0001222978,
      "costStatus": "estimated",
      "costSource": "daytona_public_list_price",
      "pricingAsOf": "2026-08-27",
      "pricingUrl": "https://www.daytona.io/pricing"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0.0001222978,
    "observedAndEstimatedCostUsd": 0.0001222978,
    "complete": false
  },
  "rawUsage": null,
  "workerTiming": {
    "version": 1,
    "scope": "worker",
    "status": "complete",
    "executionId": "agent-chat-hardening.runner-acpx-claude.daytona.continuity-restart",
    "attempt": 1,
    "startedAt": "2026-11-06T16:34:07.498Z",
    "finishedAt": "2026-11-06T16:38:24.832Z",
    "segments": [
      {
        "phase": "setup",
        "startedAt": "2026-11-06T16:34:07.498Z",
        "finishedAt": "2026-11-06T16:34:11.697Z"
      },
      {
        "phase": "execution",
        "startedAt": "2026-11-06T16:34:11.697Z",
        "finishedAt": "2026-11-06T16:38:24.345Z"
      },
      {
        "phase": "cleanup",
        "startedAt": "2026-11-06T16:38:24.345Z",
        "finishedAt": "2026-11-06T16:38:24.759Z"
      },
      {
        "phase": "feedback",
        "startedAt": "2026-11-06T16:38:24.759Z",
        "finishedAt": "2026-11-06T16:38:24.804Z"
      },
      {
        "phase": "cleanup",
        "startedAt": "2026-11-06T16:38:24.804Z",
        "finishedAt": "2026-11-06T16:38:24.831Z"
      },
      {
        "phase": "finalization",
        "startedAt": "2026-11-06T16:38:24.831Z",
        "finishedAt": "2026-11-06T16:38:24.832Z"
      }
    ]
  },
  "startupReuse": [
    {
      "runId": "e1faf64f-0cdc-4a1b-a07b-b0fd7bc16097",
      "warmth": "unknown",
      "layers": {
        "environment": {
          "state": "unknown",
          "reason": "evidence_missing"
        },
        "workspace": {
          "state": "unknown",
          "reason": "evidence_missing"
        },
        "runner": {
          "state": "unknown",
          "reason": "evidence_missing"
        },
        "provider_process": {
          "state": "unknown",
          "reason": "evidence_missing"
        },
        "provider_session": {
          "state": "unknown",
          "reason": "evidence_missing"
        }
      },
      "providerLaunchCount": null
    }
  ]
}