66 lines
8.7 KiB
JSON
66 lines
8.7 KiB
JSON
{
|
|
"schema": "paperclip.runner.stress-eval-traceability.v1",
|
|
"campaign": "2026-08-23-paperclip-runner-stress-campaign",
|
|
"expectedFindings": 44,
|
|
"workflows": [
|
|
"final-response",
|
|
"rich-activity",
|
|
"verification-policy",
|
|
"governed-interaction",
|
|
"steering-causality",
|
|
"planning-lifecycle",
|
|
"review-lifecycle",
|
|
"delegation-return",
|
|
"completion-robustness",
|
|
"restart-recovery",
|
|
"cancellation-permissions",
|
|
"trace-lineage"
|
|
],
|
|
"findings": [
|
|
{ "id": "STRESS-001", "classification": "workflow_eval", "workflowIds": ["governed-interaction"], "regressionTests": ["src/contracts/native-execution.test.ts"] },
|
|
{ "id": "STRESS-002", "classification": "workflow_eval", "workflowIds": ["restart-recovery"], "regressionTests": ["src/backends/harness-driver-backend.test.ts"] },
|
|
{ "id": "STRESS-003", "classification": "workflow_eval", "workflowIds": ["governed-interaction"], "regressionTests": ["src/contracts/native-execution.test.ts"] },
|
|
{ "id": "STRESS-004", "classification": "workflow_eval", "workflowIds": ["restart-recovery"], "regressionTests": ["../../server/src/__tests__/heartbeat-workspace-session.test.ts"] },
|
|
{ "id": "STRESS-005", "classification": "workflow_eval", "workflowIds": ["cancellation-permissions"], "regressionTests": ["src/drivers/acpx/codex-acpx-driver.test.ts"] },
|
|
{ "id": "STRESS-006", "classification": "workflow_eval", "workflowIds": ["final-response", "verification-policy"], "regressionTests": ["src/drivers/opencode/opencode-server-driver.test.ts"] },
|
|
{ "id": "STRESS-007", "classification": "workflow_eval", "workflowIds": ["completion-robustness"], "regressionTests": ["src/protocol/result-normalization.test.ts"] },
|
|
{ "id": "STRESS-008", "classification": "workflow_eval", "workflowIds": ["restart-recovery"], "regressionTests": ["src/native-session-runtime.test.ts"] },
|
|
{ "id": "STRESS-009", "classification": "workflow_eval", "workflowIds": ["completion-robustness"], "regressionTests": ["src/drivers/opencode/mcp-bridge.test.ts"] },
|
|
{ "id": "STRESS-010", "classification": "workflow_eval", "workflowIds": ["completion-robustness"], "regressionTests": ["../../server/src/__tests__/native-finalization-recovery.test.ts"] },
|
|
{ "id": "STRESS-011", "classification": "workflow_eval", "workflowIds": ["rich-activity"], "regressionTests": ["src/drivers/opencode/opencode-server-driver.test.ts"] },
|
|
{ "id": "STRESS-012", "classification": "workflow_eval", "workflowIds": ["final-response"], "regressionTests": ["src/drivers/opencode/opencode-server-driver.test.ts"] },
|
|
{ "id": "STRESS-013", "classification": "workflow_eval", "workflowIds": ["final-response", "restart-recovery"], "regressionTests": ["../../server/src/__tests__/heartbeat-run-summary.test.ts"] },
|
|
{ "id": "STRESS-014", "classification": "workflow_eval", "workflowIds": ["completion-robustness"], "regressionTests": ["../../server/src/__tests__/issue-recovery-actions.test.ts"] },
|
|
{ "id": "STRESS-015", "classification": "workflow_eval", "workflowIds": ["steering-causality"], "regressionTests": ["../../ui/src/components/TaskChatThread.test.tsx"] },
|
|
{ "id": "STRESS-016", "classification": "workflow_eval", "workflowIds": ["review-lifecycle"], "regressionTests": ["../../ui/src/components/IssueThreadInteractionCard.test.tsx"] },
|
|
{ "id": "STRESS-017", "classification": "workflow_eval", "workflowIds": ["cancellation-permissions"], "regressionTests": ["../../ui/src/components/task-chat/transcript-adapter.test.ts"] },
|
|
{ "id": "STRESS-018", "classification": "workflow_eval", "workflowIds": ["restart-recovery", "completion-robustness"], "regressionTests": ["../../server/src/services/native-runtime/native-session-executor.test.ts"] },
|
|
{ "id": "STRESS-019", "classification": "workflow_eval", "workflowIds": ["restart-recovery", "governed-interaction"], "regressionTests": ["src/backends/harness-driver-backend.test.ts"] },
|
|
{ "id": "STRESS-020", "classification": "workflow_eval", "workflowIds": ["completion-robustness"], "regressionTests": ["../../server/src/__tests__/heartbeat-process-recovery.test.ts", "../../server/src/__tests__/heartbeat-comment-wake-batching.test.ts"] },
|
|
{ "id": "STRESS-021", "classification": "workflow_eval", "workflowIds": ["governed-interaction"], "regressionTests": ["../../server/src/services/native-runtime/native-session-executor.test.ts"] },
|
|
{ "id": "STRESS-022", "classification": "workflow_eval", "workflowIds": ["governed-interaction", "restart-recovery"], "regressionTests": ["src/drivers/acpx/codex-acpx-driver.test.ts"] },
|
|
{ "id": "STRESS-023", "classification": "workflow_eval", "workflowIds": ["cancellation-permissions"], "regressionTests": ["../../server/src/services/native-runtime/native-session-executor.test.ts"] },
|
|
{ "id": "STRESS-024", "classification": "workflow_eval", "workflowIds": ["cancellation-permissions"], "regressionTests": ["src/drivers/acpx/codex-acpx-driver.test.ts"] },
|
|
{ "id": "STRESS-025", "classification": "workflow_eval", "workflowIds": ["review-lifecycle"], "regressionTests": ["../../ui/src/context/LiveUpdatesProvider.test.ts"] },
|
|
{ "id": "STRESS-026", "classification": "workflow_eval", "workflowIds": ["planning-lifecycle"], "regressionTests": ["../../server/src/__tests__/issue-thread-interaction-routes.test.ts"] },
|
|
{ "id": "STRESS-027", "classification": "workflow_eval", "workflowIds": ["delegation-return"], "regressionTests": ["../../server/src/__tests__/heartbeat-dependency-scheduling.test.ts"] },
|
|
{ "id": "STRESS-028", "classification": "workflow_eval", "workflowIds": ["delegation-return"], "regressionTests": ["../../server/src/services/native-runtime/native-session-resume.test.ts"] },
|
|
{ "id": "STRESS-029", "classification": "workflow_eval", "workflowIds": ["restart-recovery"], "regressionTests": ["../../server/src/__tests__/native-finalization-recovery.test.ts"] },
|
|
{ "id": "STRESS-030", "classification": "workflow_eval", "workflowIds": ["review-lifecycle"], "regressionTests": ["../../server/src/services/native-runtime/evidence-classifier.test.ts"] },
|
|
{ "id": "STRESS-031", "classification": "workflow_eval", "workflowIds": ["governed-interaction"], "regressionTests": ["../../server/src/__tests__/native-interaction-bridge.test.ts"] },
|
|
{ "id": "STRESS-032", "classification": "workflow_eval", "workflowIds": ["governed-interaction"], "regressionTests": ["../../server/src/services/native-runtime/native-session-executor.test.ts"] },
|
|
{ "id": "STRESS-033", "classification": "workflow_eval", "workflowIds": ["governed-interaction", "final-response"], "regressionTests": ["../../server/src/__tests__/heartbeat-run-summary.test.ts"] },
|
|
{ "id": "STRESS-034", "classification": "workflow_eval", "workflowIds": ["governed-interaction"], "regressionTests": ["src/drivers/opencode/opencode-server-driver.test.ts"] },
|
|
{ "id": "STRESS-035", "classification": "workflow_eval", "workflowIds": ["cancellation-permissions"], "regressionTests": ["src/drivers/opencode/opencode-server-driver.test.ts"] },
|
|
{ "id": "STRESS-036", "classification": "workflow_eval", "workflowIds": ["final-response"], "regressionTests": ["src/drivers/acpx/codex-acpx-driver.test.ts"] },
|
|
{ "id": "STRESS-037", "classification": "workflow_eval", "workflowIds": ["cancellation-permissions", "completion-robustness"], "regressionTests": ["src/drivers/acpx/runtime-host.test.ts"] },
|
|
{ "id": "STRESS-038", "classification": "workflow_eval", "workflowIds": ["trace-lineage"], "regressionTests": ["../../server/src/__tests__/provider-trace-store.test.ts"] },
|
|
{ "id": "STRESS-039", "classification": "workflow_eval", "workflowIds": ["trace-lineage"], "regressionTests": ["src/drivers/acpx/runtime-host.test.ts"] },
|
|
{ "id": "STRESS-040", "classification": "explicit_exclusion", "workflowIds": [], "regressionTests": [], "reason": "Campaign control cleanup is an operational hygiene check, not candidate behavior." },
|
|
{ "id": "STRESS-041", "classification": "workflow_eval", "workflowIds": ["final-response", "completion-robustness"], "regressionTests": ["../../server/src/__tests__/heartbeat-running-followup.test.ts"] },
|
|
{ "id": "STRESS-042", "classification": "regression_test", "workflowIds": [], "regressionTests": ["../../server/src/__tests__/openapi-routes.test.ts"], "reason": "Mounted-route documentation parity is deterministic API inventory." },
|
|
{ "id": "STRESS-043", "classification": "regression_test", "workflowIds": [], "regressionTests": ["../../server/src/__tests__/server-startup-feedback-export.test.ts"], "reason": "The HTTP listener test double is ordinary startup integration behavior." },
|
|
{ "id": "STRESS-044", "classification": "regression_test", "workflowIds": [], "regressionTests": ["../../server/src/__tests__/company-skills-service.test.ts"], "reason": "Filesystem path portability is deterministic service behavior." }
|
|
]
|
|
}
|