Full-stack acceptance campaign

Runner Full-Stack E2E

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

2026-10-27T16:17:59.953Z0dd8e418Source run ↗

0/1Passed
1Failed
16sSummed attempt time
Campaign usage and spend
0 / 0Complaints / suggestions · retained attempts0 distinct items · 1 attempts with incomplete collection · 0 failed submissions · 0 unresolved submissions
1Retained attempts0 missing attempts · 0 out-of-scope artifacts
UnavailableInput tokens
UnavailableOutput tokens
UnavailableCached tokens
UnavailableLLM reported subtotal
$0.000000Daytona list estimate
16sObserved 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.

UnknownAgent execution time
0msDaytona lease time
0/1Runs 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.

UnknownWorker setup time
UnknownWorker execution time
UnknownWorker feedback time
UnknownWorker cleanup time
UnknownWorker finalization time

0/1 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 191 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 0/4 No mapped journey
Skills and Skill Studio 0/5 No mapped journey
Team packages and installation 0/4 No mapped journey

Projects and execution

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

Apps, channels, and extensions

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

Automation and structured work

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

Oversight and operation

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

Contributor surfaces

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

Test suite

Chat feature journeys

Executable catalog requests through Agent Chat, with independently graded persisted state.

Pass rate0.0%0/1 passed
TokensUnavailableUnavailable input · Unavailable output
Known spendUnavailablereported LLM + model/runtime estimates estimate
Agent timeUnknown0ms lease
Execution1/10 retries · cleanup passed
Native OpenCode OpenRouter DeepSeek V4.1 Flash 1017Isolated localopencode · openrouter/deepseek/deepseek-v4.1-flash-1017
Overall failed · No behavioral checks recorded

candidate failure

SETUP FAILURE before canonical query: agent lifecycle reported harness_test_failed. Feature grading did not return. Automatic hello provider calls/tokens/cost are UNKNOWN; zero heartbeat runs is not zero model usage. Underlying hello stderr was not retained; no model-behavior attribution.
Actual setup readiness failure; canonical query not sent.
Test detailsNo checks recorded · 16s
TokensUnavailable in · Unavailable outUnavailable cached · 0/1 runs covered
LLM spendUnavailable0/1 runs provider-priced
ExecutionLocal · not meteredUnknown agent

Worker phase timing: not captured.

Feedback was not captured for this attempt.

chat-features.runner-opencode.local.create-backlog
Attempt
1
Duration
16s
Agent runtime
Unknown
Runtime
native
Provider
opencode
Model
openrouter/deepseek/deepseek-v4.1-flash-1017

Actual setup readiness failure; canonical query not sent.

No matcher result was recorded.

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": "local",
      "agentRunDurationMs": null,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": null,
  "workerTiming": null
}