benchmarksPublic
benchmarksPublic
Commit 88e86b3f
A
.gitignore
1+
# Benchmark outputs and artifacts2+
results/3+
4+
# Local/generated benchmark workspaces5+
workdirs/6+
worktrees/7+
runs/8+
fixtures/9+
10+
# Python/tool caches11+
__pycache__/12+
*.py[cod]13+
.pytest_cache/14+
.mypy_cache/15+
.ruff_cache/16+
17+
# Local machine/editor files18+
.DS_Store19+
.env20+
.env.*21+
*.local
A
.oakignore
Loading diff…
A
AGENTS.md
Loading diff…
A
CONTEXT.md
Loading diff…
A
COORDINATION.md
Loading diff…
A
LEDGER.md
Loading diff…
A
README.md
Loading diff…
A
claims/launch/README.md
Loading diff…
A
claims/launch/branch_fleet_live_20260618.json
Loading diff…
A
cloudflare/package.json
Loading diff…
A
cloudflare/reporting.mjs
Loading diff…
A
cloudflare/reporting_parity.test.mjs
Loading diff…
A
cloudflare/schema.sql
Loading diff…
A
cloudflare/schema_v2.sql
Loading diff…
A
cloudflare/worker.js
Loading diff…
A
config/agents.toml
Loading diff…
A
config/bench-env.sh
Loading diff…
A
config/command_semantics.json
Loading diff…
A
config/fixtures.json
Loading diff…
A
config/git_modes.json
Loading diff…
A
config/netshapes.json
Loading diff…
A
config/platform_semantics.json
Loading diff…
A
config/runner_classes.json
Loading diff…
A
config/subject_kinds/git.json
Loading diff…
A
config/subject_kinds/jj.json
Loading diff…
A
config/subject_kinds/oak.json
Loading diff…
A
config/subjects.toml
Loading diff…
A
config/targets.json
Loading diff…
A
config/token_calibration.json
Loading diff…
A
docs/adding-a-subject.md
Loading diff…
A
docs/adding-benchmarks.md
Loading diff…
A
docs/adr/0001-stdlib-only-harness.md
Loading diff…
A
docs/adr/0002-null-means-unmeasured.md
Loading diff…
A
docs/adr/0003-results-never-committed.md
Loading diff…
A
docs/adr/0004-efficiency-gates-oak-baseline-only.md
Loading diff…
A
docs/adr/0005-scenario-operation-name-immutability.md
Loading diff…
A
docs/adr/0006-git-baseline-books.md
Loading diff…
A
docs/adr/0007-runner-identity-and-portability.md
Loading diff…
A
docs/adr/0008-target-scorecards.md
Loading diff…
A
docs/agent-workflow-benchmarks.md
Loading diff…
A
docs/benchmark-coverage.md
Loading diff…
A
docs/cloud.md
Loading diff…
A
docs/command-semantics.md
Loading diff…
A
docs/core-vcs-benchmarks.md
Loading diff…
A
docs/findings-2026-06-11-branch-lifecycle.md
Loading diff…
A
docs/findings-2026-06-11-real-agent-campaign.md
Loading diff…
A
docs/infrastructure-plan.md
Loading diff…
A
docs/mount-benchmarks.md
Loading diff…
A
docs/new-lane-template.md
Loading diff…
A
docs/plan-2026-06-accuracy-and-insight.md
Loading diff…
A
docs/platform-benchmarks.md
Loading diff…
A
docs/prior-art.md
Loading diff…
A
docs/publish-checklist.md
Loading diff…
A
docs/results-and-dashboard.md
Loading diff…
A
docs/runner-discipline.md
Loading diff…
A
docs/statistical-methodology.md
Loading diff…
A
docs/token-calibration-factors.md
Loading diff…
A
docs/tuned-git-baselines.md
Loading diff…
A
prompts/benchmark-changeset.md
Loading diff…
A
prompts/oak-fix-handoff.md
Loading diff…
A
prompts/optimization-orchestrator.md
Loading diff…
A
scenarios/agent.yaml
Loading diff…
A
scenarios/core.yaml
Loading diff…
A
scenarios/mount.yaml
Loading diff…
A
scenarios/platform.yaml
Loading diff…
A
scripts/agent_metrics_schema.py
Loading diff…
A
scripts/agent_workflow.py
Loading diff…
A
scripts/aws_bench.sh
Loading diff…
A
scripts/baseline_book.py
Loading diff…
A
scripts/baseline_campaign.py
Loading diff…
A
scripts/bench.py
Loading diff…
A
scripts/benchmark_stats.py
Loading diff…
A
scripts/branch_triage_fixture_lane.py
Loading diff…
A
scripts/conflict_resolution_lane.py
Loading diff…
A
scripts/crosscheck_hyperfine.py
Loading diff…
A
scripts/devloop.py
Loading diff…
A
scripts/fixture_ensure.py
Loading diff…
A
scripts/fleet_report.py
Loading diff…
A
scripts/import_gitgoodbench.py
Loading diff…
A
scripts/instruction_level_report.py
Loading diff…
A
scripts/make_branch_triage_fixture.py
Loading diff…
A
scripts/make_conflict_corpus.py
Loading diff…
A
scripts/make_large_fixture.py
Loading diff…
A
scripts/make_monorepo_fixture.py
Loading diff…
A
scripts/mount_probe.py
Loading diff…
A
scripts/mount_vs_clone.py
Loading diff…
A
scripts/netshape_bench.py
Loading diff…
A
scripts/oak_field_map.py
Loading diff…
A
scripts/oakbench/__init__.py
Loading diff…
A
scripts/oakbench/baseline_book.py
Loading diff…
A
scripts/oakbench/branch_triage_shape.py
Loading diff…
A
scripts/oakbench/byteproxy.py
Loading diff…
A
scripts/oakbench/cachectl.py
Loading diff…
A
scripts/oakbench/calibration.py
Loading diff…
A
scripts/oakbench/classify.py
Loading diff…
A
scripts/oakbench/command_semantics.py
Loading diff…
A
scripts/oakbench/configio.py
Loading diff…
A
scripts/oakbench/diskprobe.py
Loading diff…
A
scripts/oakbench/environment.py
Loading diff…
A
scripts/oakbench/envwatch.py
Loading diff…
A
scripts/oakbench/execution.py
Loading diff…
A
scripts/oakbench/fixture_registry.py
Loading diff…
A
scripts/oakbench/fixtures.py
Loading diff…
A
scripts/oakbench/gitserver.py
Loading diff…
A
scripts/oakbench/integrity.py
Loading diff…
A
scripts/oakbench/lane_contract.py
Loading diff…
A
scripts/oakbench/loadgen.py
Loading diff…
A
scripts/oakbench/netshape.py
Loading diff…
A
scripts/oakbench/output_semantics.py
Loading diff…
A
scripts/oakbench/perf_loop.py
Loading diff…
A
scripts/oakbench/platform_api.py
Loading diff…
A
scripts/oakbench/platform_clock.py
Loading diff…
A
scripts/oakbench/remotes.py
Loading diff…
A
scripts/oakbench/reporting.py
Loading diff…
A
scripts/oakbench/results.py
Loading diff…
A
scripts/oakbench/rows.py
Loading diff…
A
scripts/oakbench/runlock.py
Loading diff…
A
scripts/oakbench/runner.py
Loading diff…
A
scripts/oakbench/scenario_spec.py
Loading diff…
A
scripts/oakbench/scorecard.py
Loading diff…
A
scripts/oakbench/stats.py
Loading diff…
A
scripts/oakbench/stream_adapters.py
Loading diff…
A
scripts/oakbench/subject_kinds.py
Loading diff…
A
scripts/oakbench/subjects.py
Loading diff…
A
scripts/oakbench/thrash.py
Loading diff…
A
scripts/oakbench/tokens.py
Loading diff…
A
scripts/oakbench/vcs_shim.py
Loading diff…
A
scripts/opportunities.py
Loading diff…
A
scripts/parallel_contention.py
Loading diff…
A
scripts/perf_loop.py
Loading diff…
A
scripts/perf_scorecard.py
Loading diff…
A
scripts/platform_lifecycle.py
Loading diff…
A
scripts/power_check.py
Loading diff…
A
scripts/prepare-subjects.sh
Loading diff…
A
scripts/public_claim_gate.py
Loading diff…
A
scripts/public_readiness.py
Loading diff…
A
scripts/publish_gate.py
Loading diff…
A
scripts/regression_report.py
Loading diff…
A
scripts/repro_bundle.py
Loading diff…
A
scripts/repro_verify.py
Loading diff…
A
scripts/result_delta_report.py
Loading diff…
A
scripts/row_parity.py
Loading diff…
A
scripts/runner_calibration.py
Loading diff…
A
scripts/scorecard.py
Loading diff…
A
scripts/task_loop.py
Loading diff…
A
scripts/token_calibration.py
Loading diff…
A
scripts/token_calibration_campaign.py
Loading diff…
A
scripts/tperf_runner.py
Loading diff…
A
scripts/workflow_ab.py
Loading diff…
A
tests/__init__.py
Loading diff…
A
tests/fixtures/claude_stream.jsonl
Loading diff…
A
tests/fixtures/claude_stream_real.jsonl
Loading diff…
A
tests/fixtures/codex_stream.jsonl
Loading diff…
A
tests/fixtures/codex_stream_real.jsonl
Loading diff…
A
tests/fixtures/cursor_agent_stream.jsonl
Loading diff…
A
tests/fixtures/reporting_golden.json
Loading diff…
A
tests/test_agent_native_json_probe.py
Loading diff…
A
tests/test_agent_workflow.py
Loading diff…
A
tests/test_baseline_book.py
Loading diff…
A
tests/test_baseline_campaign.py
Loading diff…
A
tests/test_branch_triage_fixture.py
Loading diff…
A
tests/test_byteproxy.py
Loading diff…
A
tests/test_cachectl.py
Loading diff…
A
tests/test_calibration.py
Loading diff…
A
tests/test_classify.py
Loading diff…
A
tests/test_command_semantics.py
Loading diff…
A
tests/test_configio.py
Loading diff…
A
tests/test_conflict_resolution_lane.py
Loading diff…
A
tests/test_crosscheck_hyperfine.py
Loading diff…
A
tests/test_devloop.py
Loading diff…
A
tests/test_dirty_spectrum.py
Loading diff…
A
tests/test_environment.py
Loading diff…
A
tests/test_envwatch.py
Loading diff…
A
tests/test_envwatch_falsification.py
Loading diff…
A
tests/test_fixture_registry.py
Loading diff…
A
tests/test_fleet_lane.py
Loading diff…
A
tests/test_fleet_report.py
Loading diff…
A
tests/test_fleet_scenarios.py
Loading diff…
A
tests/test_gitserver.py
Loading diff…
A
tests/test_import_gitgoodbench.py
Loading diff…
A
tests/test_integration_lanes.py
Loading diff…
A
tests/test_integration_workflow.py
Loading diff…
A
tests/test_integrity_attestation.py
Loading diff…
A
tests/test_lane_contract.py
Loading diff…
A
tests/test_large_binary_lfs.py
Loading diff…
A
tests/test_loadgen.py
Loading diff…
A
tests/test_make_conflict_corpus.py
Loading diff…
A
tests/test_make_monorepo_fixture.py
Loading diff…
A
tests/test_mount_probe.py
Loading diff…
A
tests/test_mount_vs_clone.py
Loading diff…
A
tests/test_netshape.py
Loading diff…
A
tests/test_netshape_bench.py
Loading diff…
A
tests/test_new_instruments.py
Loading diff…
A
tests/test_oak_field_map.py
Loading diff…
A
tests/test_oakbench_calibration.py
Loading diff…
A
tests/test_opportunities.py
Loading diff…
A
tests/test_parallel_hygiene.py
Loading diff…
A
tests/test_perf_loop.py
Loading diff…
A
tests/test_platform_api.py
Loading diff…
A
tests/test_platform_clock.py
Loading diff…
A
tests/test_platform_lifecycle.py
Loading diff…
A
tests/test_platform_race.py
Loading diff…
A
tests/test_public_claim_gate.py
Loading diff…
A
tests/test_public_readiness.py
Loading diff…
A
tests/test_publish_gate.py
Loading diff…
A
tests/test_remotes.py
Loading diff…
A
tests/test_reporting_golden.py
Loading diff…
A
tests/test_repro_bundle.py
Loading diff…
A
tests/test_repro_verify.py
Loading diff…
A
tests/test_result_delta_report.py
Loading diff…
A
tests/test_review_fixes.py
Loading diff…
A
tests/test_rows.py
Loading diff…
A
tests/test_runlock.py
Loading diff…
A
tests/test_runner.py
Loading diff…
A
tests/test_runner_calibration.py
Loading diff…
A
tests/test_scenario_spec.py
Loading diff…
A
tests/test_schema_and_oracle.py
Loading diff…
A
tests/test_scorecard.py
Loading diff…
A
tests/test_stats.py
Loading diff…
A
tests/test_stats_upgrades.py
Loading diff…
A
tests/test_stream_adapters.py
Loading diff…
A
tests/test_subject_kinds.py
Loading diff…
A
tests/test_subjects.py
Loading diff…
A
tests/test_sync_recovery.py
Loading diff…
A
tests/test_sync_workflows.py
Loading diff…
A
tests/test_task_loop.py
Loading diff…
A
tests/test_thrash.py
Loading diff…
A
tests/test_token_calibration_campaign.py
Loading diff…
A
tests/test_tokens.py
Loading diff…
A
tests/test_tperf_runner.py
Loading diff…
A
tests/test_vcs_shim.py
Loading diff…