README.md
pyproject.toml
src/local_bench_ai.egg-info/PKG-INFO
src/local_bench_ai.egg-info/SOURCES.txt
src/local_bench_ai.egg-info/dependency_links.txt
src/local_bench_ai.egg-info/entry_points.txt
src/local_bench_ai.egg-info/requires.txt
src/local_bench_ai.egg-info/top_level.txt
src/localbench/__init__.py
src/localbench/__main__.py
src/localbench/_requests.py
src/localbench/_response.py
src/localbench/_scoring.py
src/localbench/_suite.py
src/localbench/_types.py
src/localbench/bounded_final_forcing.py
src/localbench/bounded_final_profiles.py
src/localbench/budget_forcing.py
src/localbench/campaign.py
src/localbench/campaign_checkpoints.py
src/localbench/campaign_records.py
src/localbench/cli.py
src/localbench/exit_codes.py
src/localbench/facet_backfill.py
src/localbench/http_errors.py
src/localbench/landing.py
src/localbench/lane_conformance.py
src/localbench/lane_spec.py
src/localbench/manifest.py
src/localbench/monitor_cli.py
src/localbench/monitor_records.py
src/localbench/monitoring.py
src/localbench/orchestrate.py
src/localbench/perf.py
src/localbench/persistence.py
src/localbench/progress.py
src/localbench/prompt_rendering.py
src/localbench/reasoning_leaks.py
src/localbench/reasoning_registry.py
src/localbench/release_test.py
src/localbench/run_plan.py
src/localbench/run_schema.py
src/localbench/runner.py
src/localbench/suite_bundle.py
src/localbench/suite_errors.py
src/localbench/suite_release.py
src/localbench/suite_resolver.py
src/localbench/suite_verify.py
src/localbench/supervisor.py
src/localbench/tc_json_v1_runner.py
src/localbench/version.py
src/localbench/appliance/__init__.py
src/localbench/appliance/handshake.py
src/localbench/appliance/manifest.py
src/localbench/appliance/native_apparmor.py
src/localbench/appliance/native_inventory.py
src/localbench/appliance/native_materialization.py
src/localbench/appliance/native_provisioner.py
src/localbench/appliance/native_worker.py
src/localbench/appliance/provisioner.py
src/localbench/appliance/runtime_identity.py
src/localbench/appliance/trust.py
src/localbench/appliance/worker.py
src/localbench/coding_exec/__init__.py
src/localbench/coding_exec/artifacts.py
src/localbench/coding_exec/ast_gate.py
src/localbench/coding_exec/extract.py
src/localbench/coding_exec/grading.py
src/localbench/coding_exec/orchestrate.py
src/localbench/coding_exec/program.py
src/localbench/coding_exec/receipt.py
src/localbench/coding_exec/runner.py
src/localbench/coding_exec/sandbox.py
src/localbench/coding_exec/score.py
src/localbench/data/board_sources.json
src/localbench/data/contracts/agentic-execution-contract-aw013p1-pypi28113a7a-v3-evidence.json
src/localbench/data/contracts/agentic-execution-contract-aw013p1-pypi28113a7a-v3.json
src/localbench/data/contracts/agentic-execution-contract-aw013p1-pypi28113a7a-v4.json
src/localbench/data/contracts/agentic-execution-contract-aw013p1-pypi28113a7a-v5.json
src/localbench/data/contracts/agentic-execution-contract-v1-evidence.json
src/localbench/data/contracts/agentic-execution-contract-v1.json
src/localbench/data/contracts/agentic-task-identity-run-excerpts-v1.json
src/localbench/data/licenses/MIT.txt
src/localbench/data/licenses/ODC-BY-1.0.txt
src/localbench/data/suites/core-text-v1/ATTRIBUTION.md
src/localbench/data/suites/core-text-v1/CHANGES.md
src/localbench/data/suites/core-text-v1/NOTICE
src/localbench/data/suites/core-text-v1/SCORECARD.json
src/localbench/data/suites/core-text-v1/SHA256SUMS
src/localbench/data/suites/core-text-v1/SOURCE_REVISIONS.md
src/localbench/data/suites/core-text-v1/ifbench.jsonl
src/localbench/data/suites/core-text-v1/itemsets.lock.json
src/localbench/data/suites/core-text-v1/mmlu_pro.jsonl
src/localbench/data/suites/core-text-v1/suite.json
src/localbench/data/suites/core-text-v1/tc_json_v1.jsonl
src/localbench/data/suites/core-text-v1/LICENSES/BFCL-Apache-2.0
src/localbench/data/suites/core-text-v1/LICENSES/IFBench-ODC-BY-1.0
src/localbench/data/suites/core-text-v1/LICENSES/IFEval-Apache-2.0
src/localbench/data/suites/core-text-v1/LICENSES/MMLU-Pro-MIT
src/localbench/data/suites/tiny-smoke-v1/ifbench.jsonl
src/localbench/data/suites/tiny-smoke-v1/itemsets.lock.json
src/localbench/data/suites/tiny-smoke-v1/mmlu_pro.jsonl
src/localbench/data/suites/tiny-smoke-v1/suite.json
src/localbench/kld/__init__.py
src/localbench/kld/churn.py
src/localbench/kld/parse.py
src/localbench/kld/run.py
src/localbench/one_shot/__init__.py
src/localbench/one_shot/catalog.py
src/localbench/one_shot/catalog_loader.py
src/localbench/one_shot/download.py
src/localbench/one_shot/plan_lock.py
src/localbench/one_shot/preflight.py
src/localbench/one_shot/raw_hf.py
src/localbench/one_shot/resolution.py
src/localbench/one_shot/runner.py
src/localbench/one_shot/runtime.py
src/localbench/one_shot/serve_plan.py
src/localbench/one_shot/sleep.py
src/localbench/one_shot/submission.py
src/localbench/one_shot/tokenizer_pin.py
src/localbench/one_shot/types.py
src/localbench/probe/__init__.py
src/localbench/probe/__main__.py
src/localbench/probe/_point_biserial.py
src/localbench/probe/discrimination.py
src/localbench/probe/gates.py
src/localbench/providers/__init__.py
src/localbench/providers/_anthropic.py
src/localbench/providers/_base.py
src/localbench/providers/_openai.py
src/localbench/scorers/__init__.py
src/localbench/scorers/_reasoning.py
src/localbench/scorers/lcb.py
src/localbench/scorers/math_numeric.py
src/localbench/scorers/math_symbolic.py
src/localbench/scorers/mcq.py
src/localbench/scorers/ruler.py
src/localbench/scorers/bfcl/NOTICE
src/localbench/scorers/bfcl/__init__.py
src/localbench/scorers/bfcl/_checker.py
src/localbench/scorers/bfcl/_checker_values.py
src/localbench/scorers/bfcl/_parser.py
src/localbench/scorers/bfcl/_prompt.py
src/localbench/scorers/bfcl/_types.py
src/localbench/scorers/bfcl/scorer.py
src/localbench/scorers/bfcl_multi_turn/NOTICE
src/localbench/scorers/bfcl_multi_turn/__init__.py
src/localbench/scorers/bfcl_multi_turn/_backend.py
src/localbench/scorers/bfcl_multi_turn/_executor.py
src/localbench/scorers/bfcl_multi_turn/_parser.py
src/localbench/scorers/bfcl_multi_turn/_prompt.py
src/localbench/scorers/bfcl_multi_turn/_sandbox.py
src/localbench/scorers/bfcl_multi_turn/_types.py
src/localbench/scorers/bfcl_multi_turn/scorer.py
src/localbench/scorers/ifbench/NOTICE
src/localbench/scorers/ifbench/__init__.py
src/localbench/scorers/ifbench/_checks_count.py
src/localbench/scorers/ifbench/_checks_custom.py
src/localbench/scorers/ifbench/_checks_format.py
src/localbench/scorers/ifbench/_checks_ratio.py
src/localbench/scorers/ifbench/_checks_repeat.py
src/localbench/scorers/ifbench/_checks_sentence.py
src/localbench/scorers/ifbench/_checks_words.py
src/localbench/scorers/ifbench/_types.py
src/localbench/scorers/ifbench/_util.py
src/localbench/scorers/ifbench/instructions.py
src/localbench/scorers/ifbench/scorer.py
src/localbench/scorers/ifeval/__init__.py
src/localbench/scorers/ifeval/_checks_format.py
src/localbench/scorers/ifeval/_checks_keywords.py
src/localbench/scorers/ifeval/_checks_length.py
src/localbench/scorers/ifeval/_checks_misc.py
src/localbench/scorers/ifeval/_shared.py
src/localbench/scorers/ifeval/_types.py
src/localbench/scorers/ifeval/_util.py
src/localbench/scorers/ifeval/instructions.py
src/localbench/scorers/ifeval/scorer.py
src/localbench/scorers/tc_json_v1/__init__.py
src/localbench/scorers/tc_json_v1/_parser.py
src/localbench/scorers/tc_json_v1/_types.py
src/localbench/scorers/tc_json_v1/scorer.py
src/localbench/scoring/__init__.py
src/localbench/scoring/axes.py
src/localbench/scoring/axis_status.py
src/localbench/scoring/benchmark_registry.py
src/localbench/scoring/board.py
src/localbench/scoring/board_manifest.py
src/localbench/scoring/board_scoring.py
src/localbench/scoring/board_sources.py
src/localbench/scoring/board_support.py
src/localbench/scoring/board_systems.py
src/localbench/scoring/board_types.py
src/localbench/scoring/bootstrap.py
src/localbench/scoring/comparison_guard.py
src/localbench/scoring/editorial.py
src/localbench/scoring/metadata.py
src/localbench/scoring/paired_delta.py
src/localbench/scoring/public_rescore.py
src/localbench/scoring/scorecard.py
src/localbench/scoring/season2_rescore.py
src/localbench/scoring/season_bridge.py
src/localbench/scoring/signed_score.py
src/localbench/scoring/subgroups.py
src/localbench/scoring/tc_json_conformance.py
src/localbench/scoring/web.py
src/localbench/scoring/agentic_exec/__init__.py
src/localbench/scoring/agentic_exec/adapter.py
src/localbench/scoring/agentic_exec/benchmark.py
src/localbench/scoring/agentic_exec/block_introspect.py
src/localbench/scoring/agentic_exec/block_parser.py
src/localbench/scoring/agentic_exec/chat_client.py
src/localbench/scoring/agentic_exec/config.py
src/localbench/scoring/agentic_exec/contract_crypto.py
src/localbench/scoring/agentic_exec/contract_scope.py
src/localbench/scoring/agentic_exec/contract_successor.py
src/localbench/scoring/agentic_exec/env_host.py
src/localbench/scoring/agentic_exec/execution_contract.py
src/localbench/scoring/agentic_exec/funnel.py
src/localbench/scoring/agentic_exec/hashing.py
src/localbench/scoring/agentic_exec/loop_config.py
src/localbench/scoring/agentic_exec/loop_types.py
src/localbench/scoring/agentic_exec/model_client.py
src/localbench/scoring/agentic_exec/observations.py
src/localbench/scoring/agentic_exec/parser.py
src/localbench/scoring/agentic_exec/prompt.py
src/localbench/scoring/agentic_exec/protocol.py
src/localbench/scoring/agentic_exec/protocol_c_loop.py
src/localbench/scoring/agentic_exec/rank_gate.py
src/localbench/scoring/agentic_exec/rank_gate_execution.py
src/localbench/scoring/agentic_exec/runner.py
src/localbench/scoring/agentic_exec/runner_bootstrap.py
src/localbench/scoring/agentic_exec/sandbox.py
src/localbench/scoring/agentic_exec/sandbox_policy.py
src/localbench/scoring/agentic_exec/sandbox_protocol.py
src/localbench/scoring/agentic_exec/score.py
src/localbench/scoring/agentic_exec/scripted_agent.py
src/localbench/scoring/agentic_exec/stub_appworld.py
src/localbench/scoring/agentic_exec/task_journal.py
src/localbench/scoring/agentic_exec/task_journal_core.py
src/localbench/scoring/agentic_exec/task_journal_digest.py
src/localbench/scoring/agentic_exec/task_journal_format.py
src/localbench/scoring/agentic_exec/task_journal_lock.py
src/localbench/scoring/agentic_exec/task_journal_result.py
src/localbench/scoring/agentic_exec/task_journal_sleep.py
src/localbench/scoring/agentic_exec/task_journal_types.py
src/localbench/scoring/agentic_exec/task_journal_validation.py
src/localbench/scoring/agentic_exec/task_pool.py
src/localbench/scoring/agentic_exec/types.py
src/localbench/scoring/agentic_exec/worker_config.py
src/localbench/scoring/agentic_exec/worker_identity.py
src/localbench/scoring/agentic_exec/worker_process_control.py
src/localbench/scoring/agentic_exec/worker_resolution.py
src/localbench/scoring/agentic_exec/wsl_bridge.py
src/localbench/scoring/agentic_exec/wsl_process.py
src/localbench/scoring/agentic_exec/wsl_proxy.py
src/localbench/scoring/agentic_exec/wsl_teardown.py
src/localbench/scoring/agentic_exec/wsl_worker.py
src/localbench/serving/__init__.py
src/localbench/serving/agentic_resume.py
src/localbench/serving/agentic_support.py
src/localbench/serving/assembly.py
src/localbench/serving/bench.py
src/localbench/serving/fingerprint.py
src/localbench/serving/job_object.py
src/localbench/serving/llama_cpp.py
src/localbench/serving/model_artifact.py
src/localbench/serving/options.py
src/localbench/serving/process.py
src/localbench/serving/provenance.py
src/localbench/serving/readiness.py
src/localbench/serving/runner.py
src/localbench/serving/sglang.py
src/localbench/serving/teardown.py
src/localbench/serving/vllm.py
src/localbench/submissions/__init__.py
src/localbench/submissions/admission_coding.py
src/localbench/submissions/archive.py
src/localbench/submissions/attestation.py
src/localbench/submissions/bundle.py
src/localbench/submissions/bundle_input.py
src/localbench/submissions/canon.py
src/localbench/submissions/client.py
src/localbench/submissions/client_projection.py
src/localbench/submissions/contracts.py
src/localbench/submissions/crypto.py
src/localbench/submissions/decision_log.py
src/localbench/submissions/dedup.py
src/localbench/submissions/divergence.py
src/localbench/submissions/foundation.py
src/localbench/submissions/foundation_scores.py
src/localbench/submissions/keys.py
src/localbench/submissions/origin.py
src/localbench/submissions/ports.py
src/localbench/submissions/projection.py
src/localbench/submissions/provenance.py
src/localbench/submissions/rescore.py
src/localbench/submissions/status_update.py
src/localbench/submissions/strict_json.py
src/localbench/submissions/submit_run.py
src/localbench/submissions/submit_run_inputs.py
src/localbench/submissions/submit_run_output.py
src/localbench/submissions/trust.py
src/localbench/submissions/validate.py
src/localbench/submissions/verify.py
src/localbench/submissions/schemas/__init__.py
src/localbench/submissions/schemas/accepted_result_projection_v1.schema.json
src/localbench/submissions/schemas/accepted_result_projection_v2.schema.json
src/localbench/submissions/schemas/result_bundle_v1.schema.json
src/localbench/submissions/schemas/submission_envelope_v1.schema.json
src/localbench/submissions/schemas/submission_item_v1.schema.json
src/localbench/submissions/schemas/submission_manifest_v1.schema.json
src/localbench/submissions/schemas/submission_verification_v1.schema.json
src/localbench/submissions/schemas/suite_release_manifest_v1.schema.json
tests/test_agentic_appworld_adapter.py
tests/test_agentic_execution_contract.py
tests/test_agentic_failure_policies.py
tests/test_agentic_fault_injection.py
tests/test_agentic_hash_stability.py
tests/test_agentic_native_bridge.py
tests/test_agentic_native_identity.py
tests/test_agentic_parser.py
tests/test_agentic_protocol_schema.py
tests/test_agentic_rank_gate.py
tests/test_agentic_resume_identity.py
tests/test_agentic_score_asr.py
tests/test_agentic_scripted_runner.py
tests/test_agentic_task_journal.py
tests/test_agentic_task_journal_integration.py
tests/test_agentic_task_pool.py
tests/test_agentic_wsl_bridge.py
tests/test_agentic_wsl_bridge_acceptance.py
tests/test_appliance_builder.py
tests/test_appliance_manifest.py
tests/test_appliance_native_apparmor.py
tests/test_appliance_native_lifecycle.py
tests/test_appliance_native_provisioner.py
tests/test_appliance_provisioner.py
tests/test_appliance_release_scanner.py
tests/test_appliance_runtime_identity.py
tests/test_appliance_trust.py
tests/test_appliance_worker.py
tests/test_appworld_c_funnel_units.py
tests/test_appworld_protocol_c_acceptance.py
tests/test_appworld_protocol_c_gauntlet.py
tests/test_appworld_protocol_c_units.py
tests/test_appworld_sandbox_acceptance.py
tests/test_appworld_sandbox_units.py
tests/test_axes_registry.py
tests/test_axis_measurement_status.py
tests/test_b2a_client_compat_manifest.py
tests/test_bfcl.py
tests/test_bfcl_multi_turn.py
tests/test_board.py
tests/test_board_cli.py
tests/test_board_manifest.py
tests/test_board_provenance.py
tests/test_board_timing_validator.py
tests/test_bounded_final_profiles.py
tests/test_budget_forcing.py
tests/test_build_v1_bfcl_multi_turn.py
tests/test_build_v1_mmlu_pro.py
tests/test_build_v2_bfcl_multi_turn.py
tests/test_c6_impact_scan.py
tests/test_cache_tokenizer_cli.py
tests/test_campaign.py
tests/test_campaign_contracts.py
tests/test_catalog_refresh_finetunes.py
tests/test_cheat_proxy.py
tests/test_cli_axis_measurement_status.py
tests/test_cli_bench_exit_codes.py
tests/test_cli_native_agentic.py
tests/test_coding_exec_artifacts.py
tests/test_coding_exec_extract.py
tests/test_coding_exec_forgery_fix.py
tests/test_coding_exec_gaming.py
tests/test_coding_exec_harness.py
tests/test_coding_exec_known_residual_forgery.py
tests/test_coding_exec_orchestrate.py
tests/test_coding_exec_sandbox.py
tests/test_contract_v4_payload_builder.py
tests/test_distribution_cli.py
tests/test_facet_backfill.py
tests/test_failfast_release_defaults.py
tests/test_finalize_agentic_execution_contract.py
tests/test_finalize_agentic_execution_contract_premark.py
tests/test_gemma_reasoning_mode.py
tests/test_genmath_gen.py
tests/test_genmath_private.py
tests/test_ifbench.py
tests/test_ifeval.py
tests/test_kld.py
tests/test_landing.py
tests/test_landing_receipt_byte_binding.py
tests/test_lane_conformance.py
tests/test_lane_enforcement.py
tests/test_lane_spec.py
tests/test_lcb.py
tests/test_manifest_version.py
tests/test_math_genmath_parity.py
tests/test_math_numeric.py
tests/test_math_symbolic.py
tests/test_math_symbolic_robustness.py
tests/test_mcq.py
tests/test_monitoring.py
tests/test_one_shot_download.py
tests/test_one_shot_preflight.py
tests/test_one_shot_runner.py
tests/test_one_shot_tokenizer_pin.py
tests/test_online_distribution.py
tests/test_orchestrate.py
tests/test_orchestrate_agentic.py
tests/test_packaging_differential.py
tests/test_perf.py
tests/test_probe_discrimination.py
tests/test_probe_gates.py
tests/test_progress.py
tests/test_prompt_rendering.py
tests/test_protocol_v4_2_manifest.py
tests/test_provider_orchestrate.py
tests/test_provider_profiles.py
tests/test_publication_merge.py
tests/test_ranked_gate_realistic.py
tests/test_reasoning_registry.py
tests/test_rehearse_provisioner_transaction.py
tests/test_release_evidence_c0v4_r1.py
tests/test_release_evidence_c0v5_r1.py
tests/test_release_test.py
tests/test_rescore_v42_tooling.py
tests/test_response.py
tests/test_response_wrapper_scoring.py
tests/test_revision_threading.py
tests/test_run_plan.py
tests/test_run_record_distribution_schema.py
tests/test_runner.py
tests/test_runner_reasoning.py
tests/test_scorecard.py
tests/test_scoring_aggregate.py
tests/test_scoring_reasoning_strip.py
tests/test_scoring_v1.py
tests/test_season2_editorial_bridge.py
tests/test_serving_bench.py
tests/test_serving_native_agentic.py
tests/test_serving_provenance.py
tests/test_serving_sglang.py
tests/test_serving_teardown.py
tests/test_serving_vllm.py
tests/test_site_parity.py
tests/test_submission_slice_d1_migration.py
tests/test_suite_bundle.py
tests/test_suite_release_manifest.py
tests/test_suite_resolver.py
tests/test_suite_v1_metadata_refreeze.py
tests/test_supervisor.py
tests/test_tc_json_conformance_gate.py
tests/test_tc_json_v1_items.py
tests/test_tc_json_v1_runner.py
tests/test_tc_json_v1_scorer.py
tests/test_tool_use_macro_axis.py
tests/test_v1_bfcl_axis.py
tests/test_v1_bfcl_items.py
tests/test_v1_bfcl_multi_turn_axis.py
tests/test_v1_bfcl_multi_turn_items.py
tests/test_v1_bigcodebench_items.py
tests/test_v1_ifbench_axis.py
tests/test_v1_ifbench_items.py
tests/test_v1_lcb_axis.py
tests/test_v1_lcb_items.py
tests/test_v1_math_axis.py
tests/test_v1_math_items.py
tests/test_v1_mmlu_pro_axis.py
tests/test_v1_mmlu_pro_items.py
tests/test_v1_ruler_axis.py
tests/test_v2_bfcl_multi_turn_items.py
tests/test_verdict_integrity_direct_finalize.py
tests/test_verify_release_evidence.py
tests/test_wave3_attestation_run_id.py
tests/test_wave3_cli_ux.py
tests/test_web_build_agentic.py
tests/test_web_build_data.py
tests/test_web_scorecard.py
tests/test_wsl_teardown.py