mirror of
https://github.com/aiclientproxy/proxycast.git
synced 2026-09-01 15:30:52 +08:00
coso
96 lines
3.9 KiB
JSON
96 lines
3.9 KiB
JSON
{
|
|
"schemaVersion": "lime-deepswe-desktop-smoke-v1",
|
|
"status": "controlled_gate_b_verified_live_verifier_pending",
|
|
"sourceManifest": "internal/test/deepswe-coding-slice-v2.json",
|
|
"sourceCommit": "435ee89ec2f2e2289f33b0da4f992f0b7b7266b9",
|
|
"sourceSchemaVersion": "1.3",
|
|
"runner": "datacurve-pier==0.3.1",
|
|
"taskSourceRoot": ".lime/benchmark/sources/deep-swe/tasks",
|
|
"evidenceContract": {
|
|
"schemaVersion": "deepswe-desktop-trial-v1",
|
|
"trialKinds": ["controlled_product_smoke", "live_deepswe"],
|
|
"requiredToolPhases": ["read", "search", "patch", "test"],
|
|
"requiredGateB": [
|
|
"realElectronHost",
|
|
"preloadInvokeBridge",
|
|
"appServerHandleJsonLines",
|
|
"canonicalIdentity",
|
|
"terminalReadModel",
|
|
"visibleTerminal",
|
|
"visibleToolLifecycle",
|
|
"visibleDiffArtifact",
|
|
"artifactContentAvailable",
|
|
"coldRestart",
|
|
"productionMockFallbackZero",
|
|
"invokeErrorsZero",
|
|
"consoleErrorsZero",
|
|
"pageErrorsZero"
|
|
],
|
|
"verifierArtifacts": ["reward.json", "ctrf.json", "test-stdout.txt"],
|
|
"desktopCodingPass": "trialKind=live_deepswe AND GateBPass AND verifier.status=pass AND agent/verifier patchSha256 match"
|
|
},
|
|
"suiteRequirements": {
|
|
"languages": ["typescript", "go", "python", "rust", "javascript"],
|
|
"recoveryCoverage": [
|
|
"cancel_no_ghost_write",
|
|
"approval_resume",
|
|
"cold_restart"
|
|
],
|
|
"trialsPerTask": {
|
|
"bringup": 1,
|
|
"releaseCandidate": 3
|
|
}
|
|
},
|
|
"tasks": [
|
|
{
|
|
"id": "happy-dom-abort-pending-body-reads",
|
|
"language": "typescript",
|
|
"repository": "capricorn86/happy-dom",
|
|
"baseCommit": "82a0888cb2c87a6123e05424b528f8e8c9b3e426",
|
|
"instructionPath": ".lime/benchmark/sources/deep-swe/tasks/happy-dom-abort-pending-body-reads/instruction.md",
|
|
"taskTomlPath": ".lime/benchmark/sources/deep-swe/tasks/happy-dom-abort-pending-body-reads/task.toml",
|
|
"desktopRisks": ["long_turn", "cancel_no_ghost_write", "terminal_cleanup"]
|
|
},
|
|
{
|
|
"id": "go-genai-streamed-function-args",
|
|
"language": "go",
|
|
"repository": "googleapis/go-genai",
|
|
"baseCommit": "87c0e5a4f27d04569d927717769f34483e0ba475",
|
|
"instructionPath": ".lime/benchmark/sources/deep-swe/tasks/go-genai-streamed-function-args/instruction.md",
|
|
"taskTomlPath": ".lime/benchmark/sources/deep-swe/tasks/go-genai-streamed-function-args/task.toml",
|
|
"desktopRisks": ["streaming_tool_loop", "test_stdout", "diff_projection"]
|
|
},
|
|
{
|
|
"id": "httpx-multipart-response-parsing",
|
|
"language": "python",
|
|
"repository": "encode/httpx",
|
|
"baseCommit": "b5addb64f0161ff6bfe94c124ef76f6a1fba5254",
|
|
"instructionPath": ".lime/benchmark/sources/deep-swe/tasks/httpx-multipart-response-parsing/instruction.md",
|
|
"taskTomlPath": ".lime/benchmark/sources/deep-swe/tasks/httpx-multipart-response-parsing/task.toml",
|
|
"desktopRisks": ["multi_file_patch", "sync_async_parity", "test_stdout"]
|
|
},
|
|
{
|
|
"id": "fd-deterministic-multi-key-sorting",
|
|
"language": "rust",
|
|
"repository": "sharkdp/fd",
|
|
"baseCommit": "227883606023d62275fb48701aeac90f2b604143",
|
|
"instructionPath": ".lime/benchmark/sources/deep-swe/tasks/fd-deterministic-multi-key-sorting/instruction.md",
|
|
"taskTomlPath": ".lime/benchmark/sources/deep-swe/tasks/fd-deterministic-multi-key-sorting/task.toml",
|
|
"desktopRisks": ["approval_resume", "sandbox", "deterministic_patch"]
|
|
},
|
|
{
|
|
"id": "yjs-map-conflict-detection",
|
|
"language": "javascript",
|
|
"repository": "yjs/yjs",
|
|
"baseCommit": "7795050a749bd1111cbbdd9d0219b27226a8e710",
|
|
"instructionPath": ".lime/benchmark/sources/deep-swe/tasks/yjs-map-conflict-detection/instruction.md",
|
|
"taskTomlPath": ".lime/benchmark/sources/deep-swe/tasks/yjs-map-conflict-detection/task.toml",
|
|
"desktopRisks": [
|
|
"history_restore",
|
|
"artifact_reopen",
|
|
"deterministic_patch"
|
|
]
|
|
}
|
|
]
|
|
}
|