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.

2026-10-28T02:57:41.518Z33f99c6cSource run ↗Campaign summary ↗

2/5Passed
3Failed
12m 45sSummed attempt time
Campaign notes and coverage
# Merged-custody baseline: five real human-chat journeys

**Current production baseline: 5 measured scenarios, 2 qualified end-to-end passes, 3 failures, 239 not measured on this baseline, out of 244 catalog scenarios.** This is partial coverage. Implementation, saved intermediate work, and historical passes are not end-to-end pass credit.

Production is `39e811c9c5226979fce42e052a27cfb28301018a`, including merged credential-custody PR17949. Eval source is `33f99c6c5a7d6faae19cd8e47afd0d2f78882967`. All five actual cells used Paperclip Runner OpenCode with OpenRouter model `openrouter/deepseek/deepseek-v4.1-flash-1017`, actual AWS hosts and embedded PostgreSQL. [Actions run 40620786554](https://github.com/paperclipai/paperclip/actions/runs/40620786554).

The two previously passing controls were explicitly requested new-baseline comparisons; their original measurements remain historical. The three project journeys were genuinely unused initials. All five original results remain unchanged. Both passing cells have actual same-run source/build/native restore proof, exact definition identity, cleanup pass and clean packaged privacy manifests. Every cell cleaned up successfully and reported no packaged credential finding or missing mandatory evidence.

## What worked end to end

| Journey and actual human query | Result | Verified outcome |
| --- | --- | --- |
| **agents.change-manager** — “Have Morgan report to Riley from now on.” | **PASS, 9/9** | Saved manager relationship and actual org view changed to Riley, while task and permission invariants were preserved. |
| **projects.archive-project** — “Archive the Launch project but keep its history.” | **PASS, 10/10** | Actual Launch archive state and retained readable project/task/document history passed independent checks. |

## What failed and what was actually exercised

| Journey and actual human query | Overall result | Supported cause and limit |
| --- | --- | --- |
| **cli-operations.create-from-cli** — “Give me the CLI command to create a website task for Morgan in Launch.” | **FAIL** | Native execution succeeded. The returned supported CLI command created exactly one correct Morgan/Launch task as TODO. Subsequent system `recovery.reconcile_stranded_assigned_issue` moved the manually paused worker's task to BLOCKED. Two final-status equality assertions failed. This is an observed lifecycle/status assertion mismatch, not evidence of a provider outage. The original failed comparison remains retained. |
| **projects.create-project** — “Create a project called Launch for the new website.” | **FAIL** | One native execution succeeded and the CEO created Launch, but the response omitted the required usable project link. The first-phase condition did not settle, so the declared second human duplicate-safe retry was not sent. Actual project creation alone does not satisfy the full result-link and retry outcome. This was not a native execution timeout. |
| **projects.project-work** — “What is left in Launch, and create a task for Morgan to fix the mobile layout there.” | **FAIL** | The canonical request was sent and a correct Launch/Morgan mobile-layout task was saved in progress. CEO and Morgan runs were still running at the outer attempt deadline; no terminal native error was observed. No settled source reply, usable chat links or unfinished-work summary was available. The correct intermediate task is preserved as partial evidence, not a completed journey. |

The effective saved native policy was `timeoutSec: 0`, matching the product's default lack of an artificial active-turn deadline. Finite outer attempt, native/human counts, spend, privacy and cleanup bounds remained in force. No automatic retry ran. Metered usage is present but unpriced; unknown cost is not zero cost. Unexposed setup/probe usage is not assumed to be zero.

## What is next, and what is still not measured

The remaining **239 catalog scenarios have no current-baseline measurement in this report**. This includes unrun work, older measurements awaiting any explicitly allowed baseline requalification, external prerequisites, unmerged core dependencies and incomplete public paths. They are not silently reset, counted as failures, or all declared runnable.

A separately reviewed next selection contains twelve genuinely unused initial journeys: website task creation, attached-brief handoff, approved-design search, company switching, anchored-feedback resolution, goal hierarchy creation, existing-work alignment, weekday brief routine creation, other-owner routine boundary, dependency-cycle rejection, implementation-plan writing, and team-catalog discovery. Pending selection is not measured coverage. The attachment case tests an actual usable handoff to Morgan, not a finished website. A future announcement-delivery journey would require the real completed worker result to return to the original chat.

## Preserved earlier campaigns

[Previous OpenCode campaign and full 244-scenario disposition](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/gha-40584967834-1-final34-report/) preserves **57 distinct measured scenarios, 6 passes, 51 failures, 187 unrun and 62 attempts** on the older production baseline. Its original three credential-scan failures remain failures, and its run was intentionally cancelled after shared key-custody findings. Those six passes are historical evidence and are not carried into the two current-baseline passes above.

[Historical local Codex partial campaign](https://d1p6rlowie26tp.cloudfront.net/runner-e2e/campaigns/historical-local-codex-chat-catalog-20261027-158measured-86unrun/) separately preserves 17 historical passes, 141 failures and 86 unrun. Six catalog journeys remain incomplete or blocked by a missing public path. Neither catalog implementation nor an older model's result proves current end-to-end success.
Campaign usage and spend
0 / 0Complaints / suggestions · retained attempts0 distinct items · 5 attempts with incomplete collection · 0 failed submissions · 0 unresolved submissions
5Retained attempts0 missing attempts · 0 out-of-scope artifacts
346,870 (partial: 5/6 runs)Input tokens
16,209 (partial: 5/6 runs)Output tokens
1,816,064 (partial: 5/6 runs)Cached tokens
UnavailableLLM reported subtotal
$0.000000Daytona list estimate
22m 2sObserved attempt window5 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.

9m 12sAgent execution time
0msDaytona lease time
0/6Runs 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

0/5 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 5 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

Chat feature journeys

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

Pass rate40.0%2/5 passed
Tokens2,179,143 (partial: 5/6 runs)346,870 (partial: 5/6 runs) input · 16,209 (partial: 5/6 runs) output
Known spendUnavailablereported LLM + model/runtime estimates estimate
Agent time9m 12s0ms lease
Execution5/50 retries · cleanup passed
Native OpenCode OpenRouter DeepSeek V4.1 Flash 1017Isolated localopencode · openrouter/deepseek/deepseek-v4.1-flash-1017
Test details9/9 checks · 1m 37s
Overall passed · 9/9 behavioral checks passed

No behavioral matcher failed.

See all behavioral checks (9)
ResultCheckDetail
Passchat.complete-runtime-observationSaved agent configuration, attribution and actual rendered replies are independently required.
Passchat.saved-requested-managerMorgan reports to the real same-company Riley.
Passchat.reporting-tree-validEvery reporting chain terminates without a cycle or missing company manager.
Passchat.unrelated-config-and-tasks-retainedChanging the manager preserves accounts, permissions and existing tasks.
Passchat.attributed-agent-changeThe saved reporting-line change is independently attributed to the actual agent.
Passchat.catalog-complete-conditionsNo known catalog condition is omitted.
Passchat.catalog-original-human-queryThe persisted request preserves the catalog query with only audited public-fixture identity bindings; all human turns were declared.
Passchat.catalog-query-attachment-receiptsOnly declared production attachment suffixes are allowed, backed by same-source human receipts and independently retrieved matching bytes.
Passchat.catalog-bounded-native-runsObserved provider runs satisfy declared count, company, native runtime and allowed outcome bounds.
Tokens63,862 in · 753 out136,448 cached · 1/1 runs covered
LLM spendUnavailable0/1 runs provider-priced
ExecutionLocal · not metered36s agent

Worker phase timing: not captured.

Feedback was not captured for this attempt.

chat-features.runner-opencode.local.agents.change-manager
Attempt
1
Duration
1m 37s
Agent runtime
36s
Runtime
native
Provider
opencode
Model
openrouter/deepseek/deepseek-v4.1-flash-1017

All invariants passed

Startup reuse evidence
RunWarmthEnvironment/leaseWorkspaceRunnerProvider processProvider sessionProvider launches
4dc17692-b6ec-4206-9efc-72a15f28e97dunknown unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing) unknown
ResultMatcherExpectationDetail
Pass json_path {"kind":"json_path","path":"chat.complete-runtime-observation","expected":true} Saved agent configuration, attribution and actual rendered replies are independently required.
Pass json_path {"kind":"json_path","path":"chat.saved-requested-manager","expected":true} Morgan reports to the real same-company Riley.
Pass json_path {"kind":"json_path","path":"chat.reporting-tree-valid","expected":true} Every reporting chain terminates without a cycle or missing company manager.
Pass json_path {"kind":"json_path","path":"chat.unrelated-config-and-tasks-retained","expected":true} Changing the manager preserves accounts, permissions and existing tasks.
Pass json_path {"kind":"json_path","path":"chat.attributed-agent-change","expected":true} The saved reporting-line change is independently attributed to the actual agent.
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": 63862,
      "outputTokens": 753,
      "cachedInputTokens": 136448,
      "totalTokens": 201063,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0,
      "costStatus": "unpriced"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 35779,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": null,
  "workerTiming": null
}
Native OpenCode OpenRouter DeepSeek V4.1 Flash 1017Isolated localopencode · openrouter/deepseek/deepseek-v4.1-flash-1017
Overall failed · No behavioral checks recorded

candidate failure

Stopped waiting for cli-operations.create-from-cli: Settled scenario failed: saved-company-project-assignee, real-command-structured-result
Test detailsNo checks recorded · 1m 55s
Tokens126,190 in · 3,357 out343,552 cached · 1/1 runs covered
LLM spendUnavailable0/1 runs provider-priced
ExecutionLocal · not metered1m 9s agent

Worker phase timing: not captured.

Feedback was not captured for this attempt.

chat-features.runner-opencode.local.cli-operations.create-from-cli
Attempt
1
Duration
1m 55s
Agent runtime
1m 9s
Runtime
native
Provider
opencode
Model
openrouter/deepseek/deepseek-v4.1-flash-1017

No result artifact was uploaded

Startup reuse evidence
RunWarmthEnvironment/leaseWorkspaceRunnerProvider processProvider sessionProvider launches
40076454-f697-4b5f-b0a7-45b37846fdd3unknown 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": 126190,
      "outputTokens": 3357,
      "cachedInputTokens": 343552,
      "totalTokens": 473099,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0,
      "costStatus": "unpriced"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 69047,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": null,
  "workerTiming": null
}
Native OpenCode OpenRouter DeepSeek V4.1 Flash 1017Isolated localopencode · openrouter/deepseek/deepseek-v4.1-flash-1017
Test details10/10 checks · 1m 28s
Overall passed · 10/10 behavioral checks passed

No behavioral matcher failed.

See all behavioral checks (10)
ResultCheckDetail
Passchat.complete-independent-observationMissing API, document, audit or rendered-link evidence cannot pass.
Passchat.archived-not-deletedLaunch remains retrievable in the supported archived state.
Passchat.history-retainedThe original task, document bytes and creation audit survive archiving.
Passchat.attributed-project-updateThe saved lifecycle change belongs to the acting agent.
Passchat.historical-api-reachabilityThe actual archived project and retained task remain independently readable through their public resource APIs.
Passchat.truthful-archive-reportThe response reports saved archiving without falsely claiming resource deletion or task cancellation.
Passchat.catalog-complete-conditionsNo known catalog condition is omitted.
Passchat.catalog-original-human-queryThe persisted request preserves the catalog query with only audited public-fixture identity bindings; all human turns were declared.
Passchat.catalog-query-attachment-receiptsOnly declared production attachment suffixes are allowed, backed by same-source human receipts and independently retrieved matching bytes.
Passchat.catalog-bounded-native-runsObserved provider runs satisfy declared count, company, native runtime and allowed outcome bounds.
Tokens34,080 in · 617 out126,976 cached · 1/1 runs covered
LLM spendUnavailable0/1 runs provider-priced
ExecutionLocal · not metered42s agent

Worker phase timing: not captured.

Feedback was not captured for this attempt.

chat-features.runner-opencode.local.projects.archive-project
Attempt
1
Duration
1m 28s
Agent runtime
42s
Runtime
native
Provider
opencode
Model
openrouter/deepseek/deepseek-v4.1-flash-1017

All invariants passed

Startup reuse evidence
RunWarmthEnvironment/leaseWorkspaceRunnerProvider processProvider sessionProvider launches
352ddb3b-ddb3-4471-88a3-d9a071d52e2bunknown unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing) unknown
ResultMatcherExpectationDetail
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.archived-not-deleted","expected":true} Launch remains retrievable in the supported archived state.
Pass json_path {"kind":"json_path","path":"chat.history-retained","expected":true} The original task, document bytes and creation audit survive archiving.
Pass json_path {"kind":"json_path","path":"chat.attributed-project-update","expected":true} The saved lifecycle change belongs to the acting agent.
Pass json_path {"kind":"json_path","path":"chat.historical-api-reachability","expected":true} The actual archived project and retained task remain independently readable through their public resource APIs.
Pass json_path {"kind":"json_path","path":"chat.truthful-archive-report","expected":true} The response reports saved archiving without falsely claiming resource deletion or task cancellation.
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": 34080,
      "outputTokens": 617,
      "cachedInputTokens": 126976,
      "totalTokens": 161673,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0,
      "costStatus": "unpriced"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 42245,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": null,
  "workerTiming": null
}
Native OpenCode OpenRouter DeepSeek V4.1 Flash 1017Isolated localopencode · openrouter/deepseek/deepseek-v4.1-flash-1017
Overall failed · No behavioral checks recorded

candidate failure

Timed out waiting for Initial creation before explicit user retry; the observed state did not satisfy the condition. See the saved state evidence.
Test detailsNo checks recorded · 2m 49s
Tokens28,800 in · 838 out118,272 cached · 1/1 runs covered
LLM spendUnavailable0/1 runs provider-priced
ExecutionLocal · not metered38s agent

Worker phase timing: not captured.

Feedback was not captured for this attempt.

chat-features.runner-opencode.local.projects.create-project
Attempt
1
Duration
2m 49s
Agent runtime
38s
Runtime
native
Provider
opencode
Model
openrouter/deepseek/deepseek-v4.1-flash-1017

No result artifact was uploaded

Startup reuse evidence
RunWarmthEnvironment/leaseWorkspaceRunnerProvider processProvider sessionProvider launches
06c67909-f1f3-4320-9ed6-50a65e2a767cunknown 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": 28800,
      "outputTokens": 838,
      "cachedInputTokens": 118272,
      "totalTokens": 147910,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0,
      "costStatus": "unpriced"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 37561,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": null,
  "workerTiming": null
}
Native OpenCode OpenRouter DeepSeek V4.1 Flash 1017Isolated localopencode · openrouter/deepseek/deepseek-v4.1-flash-1017
Overall failed · No behavioral checks recorded

candidate failure

Timed out waiting for projects.project-work; retained-chat-and-links, launch-leftover-summary, catalog-settled-source-separate-work. See the saved state evidence.
Test detailsNo checks recorded · 4m 56s
Tokens93,938 (partial: 1/2 runs) in · 10,644 (partial: 1/2 runs) out1,090,816 (partial: 1/2 runs) cached · 1/2 runs covered
LLM spendUnavailable0/2 runs provider-priced
ExecutionLocal · not metered6m 7s agent

Worker phase timing: not captured.

Feedback was not captured for this attempt.

chat-features.runner-opencode.local.projects.project-work
Attempt
1
Duration
4m 56s
Agent runtime
6m 7s
Runtime
native
Provider
opencode
Model
openrouter/deepseek/deepseek-v4.1-flash-1017

No result artifact was uploaded

Startup reuse evidence
RunWarmthEnvironment/leaseWorkspaceRunnerProvider processProvider sessionProvider launches
7da4fec4-e8fa-4fb8-ba0d-f6db4ad7f7acunknown unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing)unknown (evidence_missing) unknown
4b347966-c39e-4d71-9aa9-3a2015e6ef24unknown 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": 2,
      "runsWithTokenUsage": 1,
      "runsWithReportedCost": 0,
      "runsWithEstimatedCost": 0,
      "runsWithPartialReportedCost": 0,
      "inputTokens": 93938,
      "outputTokens": 10644,
      "cachedInputTokens": 1090816,
      "totalTokens": 1195398,
      "reportedCostUsd": 0,
      "estimatedCostUsd": 0,
      "costStatus": "unpriced"
    },
    "runtime": {
      "provider": "local",
      "agentRunDurationMs": 367317,
      "leaseDurationMs": null,
      "leaseCount": 0,
      "costStatus": "not_metered",
      "costSource": "local_not_metered"
    },
    "reportedCostUsd": 0,
    "estimatedRuntimeCostUsd": 0,
    "observedAndEstimatedCostUsd": 0,
    "complete": false
  },
  "rawUsage": null,
  "workerTiming": null
}