iop/scripts/agent_benchmark/__init__.py
toki 91dec43635 feat(benchmark): 비교 파이프라인 기반을 구축한다
caller와 모델 조합을 반복 비교할 때 실행·격리·재개 근거가 흔들리지 않도록 manifest, workspace, lifecycle, append-only attempt 기반과 project-local 진입점을 함께 고정한다.
2026-08-09 23:49:04 +09:00

115 lines
2.9 KiB
Python

"""
agent_benchmark - Closed manifest loader, validator, and workspace preparation.
This package is standard-library-only and exposes stable immutable
manifest and workspace preparation APIs consuming only frozen inputs.
All returned objects are frozen dataclasses.
"""
from scripts.agent_benchmark.manifest import (
AssetMapping,
ExpectedBinding,
Fixture,
IopCell,
Manifest,
ManifestDigestError,
ManifestError,
ManifestPathError,
ManifestValidationError,
MatrixCell,
Timeout,
Viewport,
digest_manifest_and_resolved_inputs,
digest_workspace_inputs,
load_manifest,
validate_manifest_bytes,
)
from scripts.agent_benchmark.workspace import (
AttemptIdentity,
PreparedWorkspace,
TestbedError,
TestbedProvenance,
WorkspaceChecksumError,
WorkspaceError,
WorkspacePathError,
WorkspaceValidationError,
inspect_testbed_provenance,
prepare_workspace,
validate_attempt_identity,
)
from scripts.agent_benchmark.lifecycle import (
COMPLETION_EXIT_AFTER_IDLE,
COMPLETION_STOP_AFTER_IDLE,
SUBMISSION_ARGV_TASK,
SUBMISSION_STDIN_ONCE,
CancellationToken,
CaptureStream,
InvocationResult,
InvocationSpec,
LifecycleError,
LifecycleProtocolError,
LifecycleRecoveryError,
LifecycleValidationError,
SupervisorLocator,
TerminalOutcome,
env_pairs,
exact_value_redactor,
read_locator,
recover_invocation,
run_invocation,
)
from scripts.agent_benchmark.attempts import (
Attempt, AttemptError, AttemptStateError, CapabilityUnavailable, RunBusyError,
RunIdentity, RunPathError, RunStore, Slot, run_slots,
)
__all__ = [
"Manifest",
"Timeout",
"Viewport",
"AssetMapping",
"Fixture",
"IopCell",
"ExpectedBinding",
"MatrixCell",
"ManifestError",
"ManifestValidationError",
"ManifestPathError",
"ManifestDigestError",
"load_manifest",
"validate_manifest_bytes",
"digest_workspace_inputs",
"digest_manifest_and_resolved_inputs",
"AttemptIdentity",
"TestbedProvenance",
"PreparedWorkspace",
"WorkspaceError",
"WorkspaceValidationError",
"WorkspacePathError",
"WorkspaceChecksumError",
"TestbedError",
"prepare_workspace",
"inspect_testbed_provenance",
"validate_attempt_identity",
"SUBMISSION_ARGV_TASK",
"SUBMISSION_STDIN_ONCE",
"COMPLETION_EXIT_AFTER_IDLE",
"COMPLETION_STOP_AFTER_IDLE",
"InvocationSpec",
"InvocationResult",
"CaptureStream",
"SupervisorLocator",
"TerminalOutcome",
"CancellationToken",
"LifecycleError",
"LifecycleValidationError",
"LifecycleProtocolError",
"LifecycleRecoveryError",
"run_invocation",
"recover_invocation",
"read_locator",
"env_pairs",
"exact_value_redactor",
"Attempt", "AttemptError", "AttemptStateError", "CapabilityUnavailable",
"RunBusyError", "RunIdentity", "RunPathError", "RunStore", "Slot", "run_slots",
]