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.

2026-10-27T20:54:34.205Z50d9ecadSource run ↗Campaign summary ↗

1/10Passed

9Failed

17m 4sSummed attempt time

Campaign notes and coverage

## What works, what failed, and what is still future

Status from authenticated retained measurements at 2026-10-27T20:57:55.429743+00:00. Current remote results use OpenCode/OpenRouter model `deepseek/deepseek-v4.1-flash-1017`. Historical Codex passes are separate and contribute no current pass credit.

| Current remote status | Scenarios |
|---|---:|
| Live passes | 3 |
| Live failures pending reviewed disposition or final correction | 15 |
| Permanently failed after the one correction | 1 |
| Implemented but not yet run | 177 |
| Future: explicit external prerequisite missing | 42 |
| Future: incomplete journey or missing public product path | 6 |
| **Total frozen denominator** | **244** |

**19 distinct measured scenarios; 20 attempts (3 passed, 17 failed).** Latest allowed outcomes are 3 passed / 16 failed / 225 unrun. First attempts remain immutable: tasks.create-backlog failed both its initial and sole correction. All other measured scenarios currently have one attempt.

A pending, queued, held, or unadmitted cancelled job is not a measured scenario. The 188-cell selection is not 188 completed journeys. “Pending reviewed disposition or final correction” requires review; it does not authorize a retry. An actual material correction is required. “Permanently failed” means the single correction budget is exhausted.

The first ten authenticated completions from [bulk run 40580283071](https://github.com/paperclipai/paperclip/actions/runs/40580283071) contain one pass and nine failures. All ten cleanup checks passed. New paid approvals are held after a shared descriptor mismatch was found; already admitted jobs drain. Remaining jobs retain their unrun status until actual framework evidence is imported.

New measurements bind source `50d9ecad91ba9dee6c4a8c8335ad053fd93517f4`, production `50b932a142216331b8d476042b454bc123739c40`, actual AWS lifecycle, embedded database, and original framework start times. Historical remote baseline 8373 remains preserved separately. Live passes have genuine build/native proof; final selected-definition and baseline eligibility remains distinct. No heartbeat usage does not establish zero setup/hello usage or zero cost.

### First bulk cohort: observed stages and causes

| Scenario | Outcome | Observed stage | Evidence-supported cause | Correction allowance |
|---|---|---|---|---|
| activity.audit-change | Passed 9/9 | Canonical observation and one native run | Independent audit provenance and state checks passed | No correction needed |
| access.sign-in | Failed | Browser boundary; zero native runs | Invalidated-session boundary assertion failed; status semantics under review | One, only after reviewed correction |
| activity.agent-feedback | Failed | Pre-query validation; zero native runs | Runtime sourceFiles descriptor drift; definition evidence absent | One, after coherent metadata correction |
| access.private-resource | Failed | Canonical observation and one run | Observed provider run failed; underlying cause unknown | One, only if a material correction is justified |
| access.other-company | Failed | Canonical observation and one run | Observed provider run failed; underlying cause unknown | One, only if a material correction is justified |
| access.cli-authorization | Failed | Initial identity-response phase; one run | Initial response failed; CLI authorization phase not proven | One, only if a material correction is justified |
| activity.work-timeline | Failed | Setup guard; zero native runs | Known invitation prerequisite blocked before token-path acceptance | One, after prerequisite is safely available |
| activity.find-runs | Failed | Canonical observation; three run IDs | Settled exact-task-and-agent-run-links assertion failed | One, only if a material correction is justified |
| agent-chat.chat-disabled | Failed | Browser boundary; zero native runs | Ordinary-agent-cannot-change-instance-gate assertion failed | One, only if a material correction is justified |
| activity.company-overview | Failed | Canonical observation and one run | Settled grounded-blocker assertion failed | One, only if a material correction is justified |

Finally-captured oracle observations are retained separately from proof that a normal terminal matcher was reached. Run IDs are not automatically native executions; queued/cancelled work remains distinct.

### Live passes (3)

- `activity.audit-change`
- `agents.change-manager`
- `companies.rename-company`

### Live failures pending reviewed disposition or final correction (15)

- `access.cli-authorization`
- `access.other-company`
- `access.private-resource`
- `access.sign-in`
- `activity.agent-feedback`
- `activity.company-overview`
- `activity.find-runs`
- `activity.work-timeline`
- `agent-chat.chat-disabled`
- `agents.hire-denied`
- `inbox-search.archive-without-grant`
- `inbox-search.show-my-work`
- `tasks.ambiguous-task`
- `tasks.comment-with-reference`
- `tasks.delegate-announcement`

### Permanently failed after the one correction (1)

- `tasks.create-backlog`

### Implemented but not yet run (177)

- `agent-chat.conference-room`
- `agent-chat.multiple-handoffs`
- `agent-chat.remember-and-follow-up`
- `agent-chat.reopen-conversation`
- `agent-chat.track-delegated-work`
- `agents.agent-api-key`
- `agents.choose-primary`
- `agents.configure-required-agent`
- `agents.edit-instructions`
- `agents.hire-needs-approval`
- `agents.managed-profile`
- `agents.pause-agent`
- `agents.resume-agent`
- `agents.retire-agent`
- `app-permissions.ask-before-action`
- `app-permissions.new-quarantined-action`
- `app-permissions.read-allowed-write-off`
- `app-permissions.test-as-agent`
- `assistant-connections.consent-read-only`
- `assistant-connections.decline-consent`
- `assistant-connections.device-login`
- `assistant-connections.revoke-personal-grant`
- `budgets-costs.explain-hard-stop`
- `budgets-costs.repair-cost-recording`
- `budgets-costs.resolve-budget`
- `budgets-costs.set-budget`
- `budgets-costs.spend-breakdown`
- `cases.browse-cases`
- `cases.case-history`
- `cases.cases-disabled`
- `cases.close-case`
- `cases.create-case`
- `cases.handoff-same-task`
- `cases.related-work`
- `cases.update-case-facts`
- `chat-channels.provider-disabled`
- `cli-operations.choose-cli-context`
- `cli-operations.create-from-cli`
- `cli-operations.export-document-cli`
- `cli-operations.feedback-bundle`
- `cli-operations.inspect-run-cli`
- `cli-operations.owned-dev-instance`
- `companies.agent-observability`
- `companies.archive-company`
- `companies.configure-decision-model`
- `companies.export-company`
- `companies.fast-responses`
- `companies.import-preview`
- `companies.prompt-injection-guard`
- `companies.switch-company`
- `connection-setup.choose-provider`
- `connection-setup.notion-declined`
- `connection-setup.secure-api-key`
- `connection-setup.unreachable-mcp`
- `connection-setup.wrong-person-resolves`
- `developer-labs.component-reference`
- `developer-labs.gated-lab`
- `developer-labs.interaction-fixture`
- `developer-labs.long-thread-performance`
- `documents-artifacts.find-artifact`
- `documents-artifacts.private-download`
- `documents-artifacts.produce-download`
- `documents-artifacts.resolve-feedback`
- `documents-artifacts.restore-document`
- `documents-artifacts.revise-delivery`
- `documents-artifacts.write-plan`
- `execution-environments.choose-capable-target`
- `gateways-profiles.connect-client`
- `gateways-profiles.create-gateway`
- `gateways-profiles.inspect-gateway-error`
- `gateways-profiles.rotate-token`
- `goals.align-existing-work`
- `goals.create-goal-tree`
- `goals.explain-purpose`
- `inbox-search.archive-done`
- `inbox-search.archive-partial-failure`
- `inbox-search.find-design`
- `inbox-search.notification-audience`
- `inbox-search.restore-archive`
- `inbox-search.show-decisions`
- `instance-operations.backup-and-restore`
- `instance-operations.diagnose-health`
- `instance-operations.instance-settings`
- `instance-operations.provision-runtime`
- `instance-operations.restart-service`
- `instance-operations.update-instance`
- `navigation-preferences.broken-link`
- `navigation-preferences.dismiss-announcement`
- `navigation-preferences.edit-profile`
- `navigation-preferences.find-project-view`
- `navigation-preferences.quick-search`
- `navigation-preferences.sidebar-order`
- `onboarding.first-work`
- `plugins.configure-plugin`
- `plugins.disable-plugin`
- `plugins.install-plugin`
- `plugins.use-plugin-tool`
- `projects.archive-project`
- `projects.create-project`
- `projects.private-project`
- `projects.project-defaults`
- `projects.project-work`
- `projects.share-project`
- `questions-and-approvals.accept-one-proposal`
- `questions-and-approvals.ambiguous-yes`
- `questions-and-approvals.approve-tool-once`
- `questions-and-approvals.decline-tool`
- `questions-and-approvals.defer-and-reopen`
- `questions-and-approvals.duplicate-answer`
- `questions-and-approvals.formal-hire-revision`
- `questions-and-approvals.multi-part-question`
- `questions-and-approvals.necessary-question`
- `questions-and-approvals.reject-and-revise`
- `questions-and-approvals.review-plan`
- `questions-and-approvals.wrong-reviewer`
- `recovery.browser-reconnect`
- `recovery.controller-restart`
- `recovery.explain-stall`
- `recovery.post-stop-message`
- `recovery.retry-exhausted`
- `recovery.source-action`
- `routines.create-daily-brief`
- `routines.manage-other-owner`
- `routines.pause-owned`
- `routines.plugin-managed-routine`
- `routines.read-history`
- `routines.run-now`
- `routines.webhook-trigger`
- `runs-adapters.inspect-failed-run`
- `runs-adapters.list-model-options`
- `runs-adapters.reset-session`
- `secrets.ask-for-plaintext`
- `secrets.configure-company-secret`
- `secrets.least-scope-delivery`
- `secrets.personal-secret`
- `secrets.secret-proposal`
- `skills.author-skill`
- `skills.explicit-restriction`
- `skills.find-and-install`
- `skills.fork-read-only`
- `skills.review-update`
- `skills.studio-test`
- `status-cards.archive-card`
- `status-cards.create-card`
- `status-cards.explain-card`
- `status-cards.other-authors-card`
- `status-cards.refresh-card`
- `steering.approval-delivery`
- `steering.discard-queued-message`
- `steering.edit-queued-message`
- `steering.interrupt-with-direction`
- `steering.preserve-draft`
- `steering.queue-follow-up`
- `steering.steer-active`
- `steering.stop-versus-pause`
- `task-coordination.block-on-design`
- `task-coordination.delegate-with-context`
- `task-coordination.independent-review`
- `task-coordination.pause-tree`
- `task-coordination.reject-dependency-cycle`
- `tasks.assignment-conflict`
- `tasks.attachment-brief`
- `tasks.completion-with-gate`
- `tasks.edit-properties`
- `tasks.organize-open-work`
- `tasks.private-task`
- `tasks.share-private-task`
- `tasks.website-task`
- `tasks.website-without-project`
- `teams.configure-team`
- `teams.find-team`
- `teams.install-team`
- `teams.preview-install`
- `workspaces.close-and-reopen`
- `workspaces.inspect-git`
- `workspaces.locate-files`
- `workspaces.preview-service`

### Future: explicit external prerequisite missing (42)

- `agents.ambiguous-cloud-code`
- `agents.existing-grok-bot`
- `agents.hire-claude-code`
- `agents.hire-needs-account`
- `app-permissions.grant-one-agent`
- `app-permissions.revoke-account`
- `assistant-connections.connect-external-assistant`
- `assistant-connections.use-scoped-client`
- `chat-channels.channel-file`
- `chat-channels.connect-slack`
- `chat-channels.link-sender`
- `chat-channels.outbound-email`
- `chat-channels.repair-endpoint`
- `chat-channels.reply-in-thread`
- `chat-channels.reply-to-email`
- `connection-setup.channel-prerequisites`
- `connection-setup.notion-agent-unassigned`
- `connection-setup.notion-connected`
- `connection-setup.notion-expired`
- `connection-setup.notion-missing`
- `connection-setup.notion-wrong-account`
- `connection-setup.return-from-login`
- `connection-setup.save-and-resume`
- `execution-environments.add-computer`
- `execution-environments.assign-computer`
- `execution-environments.prepare-image`
- `execution-environments.test-computer`
- `gateways-profiles.define-profile`
- `onboarding.choose-first-runtime`
- `onboarding.new-company`
- `onboarding.new-instance`
- `onboarding.resume-wizard`
- `projects.add-repository`
- `projects.replace-repository`
- `recovery.unknown-email-outcome`
- `recovery.workspace-repair`
- `runs-adapters.upgrade-runner`
- `runs-adapters.validate-hire`
- `secrets.vault-reference`
- `workspaces.prepare-repository`
- `workspaces.private-repository-no-access`
- `workspaces.recover-lost-sandbox`

### Future: incomplete journey or missing public product path (6)

- `access.invite-teammate`
- `access.manage-membership`
- `activity.routine-audit`
- `agents.restore-instructions`
- `budgets-costs.subscription-fees`
- `skills.enable-for-agent`


## Historical local Codex:17 original initial passes

These are original local one-time measurements of provider `codex`, model `gpt-5.6-sol`, production baseline8373 with original per-attempt source/definition identities. They are **not current OpenCode or updated-production qualification**. Across158 attempted IDs:17 initial passes,141 initial failures,159 retained measurements including one historical correction, and86 unrun. [Immutable historical report](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/historical-local-codex-chat-catalog-20261027-158measured-86unrun/) and [original summary](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/historical-local-codex-chat-catalog-20261027-158measured-86unrun/summary.md). Unpriced cost is unknown, not zero.

- access.private-resource
- agents.agent-api-key
- assistant-connections.decline-consent
- chat-channels.provider-disabled
- companies.archive-company
- companies.rename-company
- inbox-search.archive-partial-failure
- instance-operations.instance-settings
- projects.project-work
- questions-and-approvals.accept-one-proposal
- questions-and-approvals.ambiguous-yes
- runs-adapters.list-model-options
- steering.preserve-draft
- task-coordination.reject-dependency-cycle
- tasks.create-backlog
- tasks.delegate-announcement
- tasks.website-task

Chat feature journeys 1/10 Needs attention

Campaign usage and spend

0 / 0Complaints / suggestions · retained attempts0 distinct items · 10 attempts with incomplete collection · 0 failed submissions · 0 unresolved submissions

10Retained attempts0 missing attempts · 0 out-of-scope artifacts

443,867 (partial: 5/12 runs)Input tokens

22,964 (partial: 5/12 runs)Output tokens

3,229,952 (partial: 5/12 runs)Cached tokens

UnavailableLLM reported subtotal

$0.000000Daytona list estimate

4m 19sObserved attempt window10 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

0/12Runs 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

0/10 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 10 tests mapped

Associations use the current feature map. Counts describe linked test scenarios; a passing journey does not establish full coverage of a capability.

Getting started and access

Feature	Capabilities linked	Linked test results
Onboarding and first work	0/5	No mapped journey
Login, invitations, and access	0/5	No mapped journey
Companies and portability	0/8	No mapped journey

Tasks and conversations

Feature	Capabilities linked	Linked test results
Task creation and lifecycle	0/6	No mapped journey
Delegation, dependencies, and signoff	0/4	No mapped journey
Inbox, decisions, and search	0/5	No mapped journey
Agent conversations and project handoff	0/4	No mapped journey
Questions and approvals	0/8	No mapped journey
Steering and queued messages	0/7	No mapped journey
Documents, attachments, and work products	0/5	No mapped journey

Agents and reusable capabilities

Feature	Capabilities linked	Linked test results
Hiring, configuration, and organization	0/9	No mapped journey
Runs, harnesses, and model accounts	0/5	No mapped journey
Skills and Skill Studio	0/5	No mapped journey
Team packages and installation	0/4	No mapped journey

Projects and execution

Feature	Capabilities linked	Linked test results
Projects and repositories	0/5	No mapped journey
Goals and work alignment	0/3	No mapped journey
Workspaces, services, and files	0/5	No mapped journey
Execution environments	0/5	No mapped journey
Recovery	0/8	No mapped journey

Apps, channels, and extensions

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

Automation and structured work

Feature	Capabilities linked	Linked test results
Routines, schedules, and triggers	0/5	No mapped journey
Cases	0/5	No mapped journey
Status cards	0/4	No mapped journey

Oversight and operation

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

Contributor surfaces

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

Search tests Feature Agent profile Environment Suite Status

Test suite

Chat feature journeys

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

Pass rate10.0%1/10 passed

Tokens3,696,783 (partial: 5/12 runs)443,867 (partial: 5/12 runs) input · 22,964 (partial: 5/12 runs) output

Known spendUnavailablereported LLM + model/runtime estimates estimate

Agent timeUnknown0ms lease

Execution10/100 retries · cleanup passed

access.cli-authorization

Inspect case ↗

Native OpenCode OpenRouter DeepSeek V4.1 Flash 1017Isolated localopencode · openrouter/deepseek/deepseek-v4.1-flash-1017

access.cli-authorization failed

Overall failed · No behavioral checks recorded

candidate failure

Stopped waiting for initial identity response: Initial response failed

Test detailsNo checks recorded · 2m 42s

TokensUnavailable in · Unavailable outUnavailable cached · 0/1 runs covered

LLM spendUnavailable0/1 runs provider-priced

ExecutionLocal · not metered2m 25s agent

Worker phase timing: not captured.

Feedback was not captured for this attempt.

chat-features.runner-opencode.local.access.cli-authorization

Attempt: 1
Duration: 2m 42s
Agent runtime: 2m 25s
Runtime: native
Provider: opencode
Model: openrouter/deepseek/deepseek-v4.1-flash-1017

No result artifact was uploaded

Startup reuse evidence
Run	Warmth	Environment/lease	Workspace	Runner	Provider process	Provider session	Provider launches
`b3ea9980-0d1e-41d1-8916-a9b0d18c0e50`	unknown	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown

No matcher result was recorded.

Usage, billing and timing metadata

{
  "billing": {
    "llm": {
      "runCount": 1,
      "runsWithTokenUsage": 0,
      "runsWithReportedCost": 0,
      "runsWithEstimatedCost": 0,
      "runsWithPartialReportedCost": 0,
      "inputTokens": 82201,
      "outputTokens": 4399,
      "cachedInputTokens": 996608,
      "totalTokens": 1083208,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0,
      "costStatus": "unavailable"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 144604,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": null,
  "workerTiming": null
}

access.other-company

Inspect case ↗

Native OpenCode OpenRouter DeepSeek V4.1 Flash 1017Isolated localopencode · openrouter/deepseek/deepseek-v4.1-flash-1017

access.other-company failed

Overall failed · No behavioral checks recorded

transient infrastructure

Stopped waiting for access.other-company: Observed provider run failed

Test detailsNo checks recorded · 2m 42s

TokensUnavailable in · Unavailable outUnavailable cached · 0/1 runs covered

LLM spendUnavailable0/1 runs provider-priced

ExecutionLocal · not metered2m 22s agent

Worker phase timing: not captured.

Feedback was not captured for this attempt.

chat-features.runner-opencode.local.access.other-company

Attempt: 1
Duration: 2m 42s
Agent runtime: 2m 22s
Runtime: native
Provider: opencode
Model: openrouter/deepseek/deepseek-v4.1-flash-1017

No result artifact was uploaded

Startup reuse evidence
Run	Warmth	Environment/lease	Workspace	Runner	Provider process	Provider session	Provider launches
`0d16452c-9bc3-4a65-adc0-23701bb9fdad`	unknown	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown

No matcher result was recorded.

Usage, billing and timing metadata

{
  "billing": {
    "llm": {
      "runCount": 1,
      "runsWithTokenUsage": 0,
      "runsWithReportedCost": 0,
      "runsWithEstimatedCost": 0,
      "runsWithPartialReportedCost": 0,
      "inputTokens": 53476,
      "outputTokens": 4196,
      "cachedInputTokens": 975616,
      "totalTokens": 1033288,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0,
      "costStatus": "unavailable"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 141766,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": null,
  "workerTiming": null
}

access.private-resource

Inspect case ↗

Native OpenCode OpenRouter DeepSeek V4.1 Flash 1017Isolated localopencode · openrouter/deepseek/deepseek-v4.1-flash-1017

access.private-resource failed

Overall failed · No behavioral checks recorded

transient infrastructure

Stopped waiting for access.private-resource: Observed provider run failed

Test detailsNo checks recorded · 2m 42s

TokensUnavailable in · Unavailable outUnavailable cached · 0/1 runs covered

LLM spendUnavailable0/1 runs provider-priced

ExecutionLocal · not metered2m 22s agent

Worker phase timing: not captured.

Feedback was not captured for this attempt.

chat-features.runner-opencode.local.access.private-resource

Attempt: 1
Duration: 2m 42s
Agent runtime: 2m 22s
Runtime: native
Provider: opencode
Model: openrouter/deepseek/deepseek-v4.1-flash-1017

No result artifact was uploaded

Startup reuse evidence
Run	Warmth	Environment/lease	Workspace	Runner	Provider process	Provider session	Provider launches
`d608f7df-5977-4afc-9593-658902161763`	unknown	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown

No matcher result was recorded.

Usage, billing and timing metadata

{
  "billing": {
    "llm": {
      "runCount": 1,
      "runsWithTokenUsage": 0,
      "runsWithReportedCost": 0,
      "runsWithEstimatedCost": 0,
      "runsWithPartialReportedCost": 0,
      "inputTokens": 43757,
      "outputTokens": 4657,
      "cachedInputTokens": 548224,
      "totalTokens": 596638,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0,
      "costStatus": "unavailable"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 142482,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": null,
  "workerTiming": null
}

access.sign-in

Inspect case ↗

Native OpenCode OpenRouter DeepSeek V4.1 Flash 1017Isolated localopencode · openrouter/deepseek/deepseek-v4.1-flash-1017

access.sign-in failed

Overall failed · No behavioral checks recorded

transient infrastructure

Browser boundary failed: real-invalidated-human-session

Test detailsNo checks recorded · 26s

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.access.sign-in

Attempt: 1
Duration: 26s
Agent runtime: Unknown
Runtime: native
Provider: opencode
Model: openrouter/deepseek/deepseek-v4.1-flash-1017

No result artifact was uploaded

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
}

activity.agent-feedback

Inspect case ↗

Native OpenCode OpenRouter DeepSeek V4.1 Flash 1017Isolated localopencode · openrouter/deepseek/deepseek-v4.1-flash-1017

activity.agent-feedback failed

Overall failed · No behavioral checks recorded

candidate failure

Runtime descriptor drift: activity.agent-feedback.sourceFiles

Test detailsNo checks recorded · 19s

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.activity.agent-feedback

Attempt: 1
Duration: 19s
Agent runtime: Unknown
Runtime: native
Provider: opencode
Model: openrouter/deepseek/deepseek-v4.1-flash-1017

No result artifact was uploaded

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
}

activity.audit-change

Inspect case ↗

Native OpenCode OpenRouter DeepSeek V4.1 Flash 1017Isolated localopencode · openrouter/deepseek/deepseek-v4.1-flash-1017

activity.audit-change passed

Test details9/9 checks · 1m 26s

Overall passed · 9/9 behavioral checks passed

No behavioral matcher failed.

See all behavioral checks (9)

Result	Check	Detail
Pass	`chat.complete-independent-observation`	Missing API, document, audit or rendered-link evidence cannot pass.
Pass	`chat.real-two-change-history`	Both fixture priority changes remain visible on the exact task.
Pass	`chat.attribution-and-values`	Recorded actors bind each actual transition, including a truthful common actor header; wrong actors, tasks or changes cannot pass.
Pass	`chat.recorded-event-times`	Reported calendar and clock times match the actual retained events in UTC or the browser's declared timezone.
Pass	`chat.read-only-history`	Reading task audit does not mutate the task or manufacture audit records.
Pass	`chat.catalog-complete-conditions`	No known catalog condition is omitted.
Pass	`chat.catalog-original-human-query`	The persisted request preserves the catalog query with only audited public-fixture identity bindings; all human turns were declared.
Pass	`chat.catalog-query-attachment-receipts`	Only declared production attachment suffixes are allowed, backed by same-source human receipts and independently retrieved matching bytes.
Pass	`chat.catalog-bounded-native-runs`	Observed provider runs satisfy declared count, company, native runtime and allowed outcome bounds.

Tokens70,227 in · 1,142 out126,848 cached · 1/1 runs covered

LLM spendUnavailable0/1 runs provider-priced

ExecutionLocal · not metered48s agent

Worker phase timing: not captured.

Feedback was not captured for this attempt.

chat-features.runner-opencode.local.activity.audit-change

Attempt: 1
Duration: 1m 26s
Agent runtime: 48s
Runtime: native
Provider: opencode
Model: openrouter/deepseek/deepseek-v4.1-flash-1017

All invariants passed

Startup reuse evidence
Run	Warmth	Environment/lease	Workspace	Runner	Provider process	Provider session	Provider launches
`c3cd183e-1111-4c73-be88-bc20b709fdcc`	unknown	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown

Result	Matcher	Expectation	Detail
Pass	`json_path`	{"kind":"json_path","path":"chat.complete-independent-observation","expected":true}	Missing API, document, audit or rendered-link evidence cannot pass.
Pass	`json_path`	{"kind":"json_path","path":"chat.real-two-change-history","expected":true}	Both fixture priority changes remain visible on the exact task.
Pass	`json_path`	{"kind":"json_path","path":"chat.attribution-and-values","expected":true}	Recorded actors bind each actual transition, including a truthful common actor header; wrong actors, tasks or changes cannot pass.
Pass	`json_path`	{"kind":"json_path","path":"chat.recorded-event-times","expected":true}	Reported calendar and clock times match the actual retained events in UTC or the browser's declared timezone.
Pass	`json_path`	{"kind":"json_path","path":"chat.read-only-history","expected":true}	Reading task audit does not mutate the task or manufacture audit records.
Pass	`json_path`	{"kind":"json_path","path":"chat.catalog-complete-conditions","expected":true}	No known catalog condition is omitted.
Pass	`json_path`	{"kind":"json_path","path":"chat.catalog-original-human-query","expected":true}	The persisted request preserves the catalog query with only audited public-fixture identity bindings; all human turns were declared.
Pass	`json_path`	{"kind":"json_path","path":"chat.catalog-query-attachment-receipts","expected":true}	Only declared production attachment suffixes are allowed, backed by same-source human receipts and independently retrieved matching bytes.
Pass	`json_path`	{"kind":"json_path","path":"chat.catalog-bounded-native-runs","expected":true}	Observed provider runs satisfy declared count, company, native runtime and allowed outcome bounds.

Usage, billing and timing metadata

{
  "billing": {
    "llm": {
      "runCount": 1,
      "runsWithTokenUsage": 1,
      "runsWithReportedCost": 0,
      "runsWithEstimatedCost": 0,
      "runsWithPartialReportedCost": 0,
      "inputTokens": 70227,
      "outputTokens": 1142,
      "cachedInputTokens": 126848,
      "totalTokens": 198217,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0,
      "costStatus": "unpriced"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 48443,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": null,
  "workerTiming": null
}

activity.company-overview

Inspect case ↗

Native OpenCode OpenRouter DeepSeek V4.1 Flash 1017Isolated localopencode · openrouter/deepseek/deepseek-v4.1-flash-1017

activity.company-overview failed

Overall failed · No behavioral checks recorded

candidate failure

Stopped waiting for activity.company-overview: Settled scenario failed: grounded-blocker

Test detailsNo checks recorded · 2m 47s

Tokens34,265 in · 3,281 out207,488 cached · 1/1 runs covered

LLM spendUnavailable0/1 runs provider-priced

ExecutionLocal · not metered2m 3s agent

Worker phase timing: not captured.

Feedback was not captured for this attempt.

chat-features.runner-opencode.local.activity.company-overview

Attempt: 1
Duration: 2m 47s
Agent runtime: 2m 3s
Runtime: native
Provider: opencode
Model: openrouter/deepseek/deepseek-v4.1-flash-1017

No result artifact was uploaded

Startup reuse evidence
Run	Warmth	Environment/lease	Workspace	Runner	Provider process	Provider session	Provider launches
`7bc0c454-2ace-414b-b493-8bbe5457b2d5`	unknown	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown

No matcher result was recorded.

Usage, billing and timing metadata

{
  "billing": {
    "llm": {
      "runCount": 1,
      "runsWithTokenUsage": 1,
      "runsWithReportedCost": 0,
      "runsWithEstimatedCost": 0,
      "runsWithPartialReportedCost": 0,
      "inputTokens": 34265,
      "outputTokens": 3281,
      "cachedInputTokens": 207488,
      "totalTokens": 245034,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0,
      "costStatus": "unpriced"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 123157,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": null,
  "workerTiming": null
}

activity.find-runs

Inspect case ↗

Native OpenCode OpenRouter DeepSeek V4.1 Flash 1017Isolated localopencode · openrouter/deepseek/deepseek-v4.1-flash-1017

activity.find-runs failed

Overall failed · No behavioral checks recorded

candidate failure

Stopped waiting for activity.find-runs: Settled scenario failed: exact-task-and-agent-run-links

Test detailsNo checks recorded · 3m 25s

Tokens159,941 in · 5,289 out375,168 cached · 3/3 runs covered

LLM spendUnavailable0/3 runs provider-priced

ExecutionLocal · not metered2m 35s agent

Worker phase timing: not captured.

Feedback was not captured for this attempt.

chat-features.runner-opencode.local.activity.find-runs

Attempt: 1
Duration: 3m 25s
Agent runtime: 2m 35s
Runtime: native
Provider: opencode
Model: openrouter/deepseek/deepseek-v4.1-flash-1017

No result artifact was uploaded

Startup reuse evidence
Run	Warmth	Environment/lease	Workspace	Runner	Provider process	Provider session	Provider launches
`218b6eff-20dd-4292-97b5-eebfcd2643ad`	unknown	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown
`82081bd4-e739-4759-87d6-63d1ad91e073`	unknown	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown
`bd4abb7d-a738-41cd-96cd-1c9de91de02c`	unknown	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown (evidence_missing)	unknown

No matcher result was recorded.

Usage, billing and timing metadata

{
  "billing": {
    "llm": {
      "runCount": 3,
      "runsWithTokenUsage": 3,
      "runsWithReportedCost": 0,
      "runsWithEstimatedCost": 0,
      "runsWithPartialReportedCost": 0,
      "inputTokens": 159941,
      "outputTokens": 5289,
      "cachedInputTokens": 375168,
      "totalTokens": 540398,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0,
      "costStatus": "unpriced"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 155098,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": null,
  "workerTiming": null
}

activity.work-timeline

Inspect case ↗

Native OpenCode OpenRouter DeepSeek V4.1 Flash 1017Isolated localopencode · openrouter/deepseek/deepseek-v4.1-flash-1017

activity.work-timeline failed

Overall failed · No behavioral checks recorded

candidate failure

Invitation enrollment prerequisite blocked before token-path acceptance; corePR17848 remains unmerged. No native dispatch from prerequisite; original closed guard evidence retained privately.

Test detailsNo checks recorded · 17s

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.activity.work-timeline

Attempt: 1
Duration: 17s
Agent runtime: Unknown
Runtime: native
Provider: opencode
Model: openrouter/deepseek/deepseek-v4.1-flash-1017

No result artifact was uploaded

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
}

agent-chat.chat-disabled

Inspect case ↗

Native OpenCode OpenRouter DeepSeek V4.1 Flash 1017Isolated localopencode · openrouter/deepseek/deepseek-v4.1-flash-1017

agent-chat.chat-disabled failed

Overall failed · No behavioral checks recorded

transient infrastructure

Browser boundary failed: ordinary-agent-cannot-change-instance-gate

Test detailsNo checks recorded · 18s

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.agent-chat.chat-disabled

Attempt: 1
Duration: 18s
Agent runtime: Unknown
Runtime: native
Provider: opencode
Model: openrouter/deepseek/deepseek-v4.1-flash-1017

No result artifact was uploaded

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
}