Files
PaperClipAI/tests/runner-e2e/native-completion-comparison.json
T

48 lines
2.8 KiB
JSON

{
"schema": "paperclip.native-completion.matched-baseline/v1",
"candidateSha": "ae34843731ac338bd806a4106cb447134bff402c",
"historicalInstructionSourceSha": "5837aa44425ea134fc33a96c502c22d6a32b6866",
"heldConstant": [
"merged native Codex base fix #14920",
"tiny default hire manual",
"reduced shared startup/resume prompts",
"all fixtures, models, effort, permissions, auth and behavioral graders"
],
"productionSourcesRestored": [
"packages/paperclip-runner/src/contracts/completion-result.ts",
"packages/paperclip-runner/src/drivers/codex/codex-driver-values.ts",
"packages/paperclip-runner/src/drivers/runner-tool-bridge.ts",
"packages/paperclip-runner/src/drivers/opencode/mcp-bridge.ts",
"server/src/services/native-runtime/native-session-resume.ts"
],
"historicalStructuralOracles": "Same authenticated/wire/catalog gates expect the explicit historical descriptions. The v13 baseline does not run the candidate-only v13-to-v14 rotation assertion; its prior compatibility cases remain mandatory. Candidate graders are unchanged.",
"behavioralSourceHashes": {
"tests/runner-e2e/native-completion-case.ts": "ebe9c5caeef5da5e0cdd82cbab8ed841b79e7d8bf54e891fbae78ad01cc7c8a7",
"tests/runner-e2e/native-completion-case.test.ts": "1889cecd7efef36020ce6d8c407f8375f3d79af7fd9351e1eb6b46f08bdbaa4e",
"tests/runner-e2e/context-integrity-cases.ts": "201d05f8257c1121a94dd9d8a22f08b9db80555e388013ffeabb65e301499fd2",
"tests/runner-e2e/context-integrity-flow.ts": "63bcb7bdba4c80b15ff5872f16383844456eab0c5a10627da5d3487a26821c6a",
"tests/runner-e2e/context-integrity-scoring.ts": "50d370044e45386ba87fb23ca63c228b96bb8373d67bb7e82e8b2a89eb23f252",
"tests/runner-e2e/matchers.ts": "852dc82ca9b4d5d1b2e902407c1df5ff0343313e71175805b6a444c55ff69957",
"tests/runner-e2e/runner.spec.ts": "14d57e0f9131b3f1981ac593464738d01362008eefe85ea836075c794681fa85",
"tests/runner-e2e/live-fixtures.ts": "1ef80209cc53cc514a8e58af4c2225e38ec15b20acf17ca7564506ca6617ac3e",
"tests/runner-e2e/catalog.ts": "7d6fd220dcac80296ba0c73a0febf9975a9b6f28085359d52ca605b598c40ec7",
"tests/runner-e2e/stock-harness.ts": "9ce135aabe82f532eca9f16bfd00689c3279bbacf9f68e247a4332ba8a0d4c3c",
"tests/runner-e2e/stock-harness-admission.ts": "4cad5e7e703029651d79b5ace4b22368da3b326fed46fe38366c6f95d24b4451",
"tests/runner-e2e/launch.ts": "b020d6fd8a4ae00e008215a49b937bbc65208e66341113a4e548c3d4b492ff4a"
},
"selection": {
"profiles": [
"runner-codex",
"runner-acpx-claude",
"runner-opencode"
],
"cases": [
"assigned-skill-explicit-invocation",
"native-blocked-report"
],
"expectedCells": 6,
"expectedProviderTurns": 6
},
"sharedGraderCorrection": "Requires visible owner, exact unblock action and a blocking explanation; same corrected grader in both variants."
}