benchmarksPublic
benchmarksPublic
Commit f0c34b30
M
config/command_semantics.json
@@ -1,5 +1,5 @@
11
{2-
"version": "2026-09-10.3",2+
"version": "2026-09-18.1",33
"harness_tracks_note": "Machine-readable source of the exact commands each lane runs per subject kind and track. Harnesses load this via oakbench.command_semantics; changing any command requires a version bump (ADR-0005). {message} is substituted at run time.",44
"harness_tracks": {55
"git": {
A
docs/independent-workflow-readers.md
Loading diff…
A
docs/qa-integrity-2026-09-18.md
Loading diff…
M
scripts/agent_metrics_schema.py
Loading diff…
M
scripts/agent_workflow.py
Loading diff…
M
scripts/bench.py
Loading diff…
M
scripts/oakbench/agent_campaign.py
Loading diff…
M
scripts/oakbench/campaign_report.py
Loading diff…
M
scripts/oakbench/command_semantics.py
Loading diff…
A
scripts/oakbench/oak_sqlite_reader.py
Loading diff…
M
scripts/oakbench/output_semantics.py
Loading diff…
M
scripts/oakbench/populations.py
Loading diff…
M
scripts/oakbench/public_output.py
Loading diff…
M
scripts/oakbench/rows.py
Loading diff…
M
scripts/oakbench/workflow_oracles.py
Loading diff…
M
scripts/publish_gate.py
Loading diff…
M
scripts/workflow_ab.py
Loading diff…
M
tests/test_agent_campaign.py
Loading diff…
M
tests/test_agent_campaign_cli.py
Loading diff…
M
tests/test_agent_execution_limits.py
Loading diff…
A
tests/test_agent_outcome_attribution.py
Loading diff…
M
tests/test_campaign_report.py
Loading diff…
M
tests/test_command_semantics.py
Loading diff…
A
tests/test_core_oracle_sequence.py
Loading diff…
A
tests/test_oak_sqlite_reader.py
Loading diff…
M
tests/test_public_output.py
Loading diff…
M
tests/test_rows.py
Loading diff…
M
tests/test_schema_and_oracle.py
Loading diff…
M
tests/test_workflow_oracles.py
Loading diff…
A
tests/test_workflow_parity.py
Loading diff…
A
tests/test_workflow_publication_qualification.py
Loading diff…