mirror of
https://github.com/norandom/OpenUltraSAST.git
synced 2026-10-18 04:29:27 +00:00
feat(plane): scoring parity with the reference -- sites, ranges, triage cost
agree matched declared sites through benchmarks/independent/evaluate.py, which the runner image does not carry, so site matching would have been "not assessed". The generator now resolves the fix's old-side ranges (evaluate.hunks, line for line) into case.json, with the declared sites in the set and the reference's cost, and agree.matches_declared reproduces matches_v2; a parity test runs both over the recorded outputs of the 15 validation cases (200 probes, identical verdicts) and agree on those outputs returns the reference's 16 of 20 and $0.022. agree reports cost_per_candidate (plane spend) and cost_per_candidate_with_recorded_triage; Requirement 6.2 is judged on the latter (design.md). --runner-image re-pins the templates from ops/ax/up.sh's pin file; the committed manifests are regenerated at the current digest. Co-Authored-By: Claude Opus 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01EmM1j46qgKMh3zqD1QMwEo
This commit is contained in:
co-authored by
Claude Opus 5.5
parent
ac296ee3a4
commit
56b1717246
@@ -1,4 +1,4 @@
|
||||
# generated by `ousast plane workspaces benchmarks/independent/population-v2.toml --validation-set ~/ousast-results/independent-v2-sets/validation.json --candidates ~/ousast-results/independent-v2-modelsinks --triage ~/ousast-results/independent-v2-batched-check/scans --run validation-46`; do not edit, regenerate.
|
||||
# generated by `ousast plane workspaces benchmarks/independent/population-v2.toml --validation-set ~/ousast-results/independent-v2-sets/validation.json --candidates ~/ousast-results/independent-v2-modelsinks --triage ~/ousast-results/independent-v2-batched-check/scans --repos ~/.cache/openultrasast/independent --run validation-46 --runner-image ~/.cache/ousast/ax-src/runner-image`; do not edit, regenerate.
|
||||
apiVersion: ax.io/v1alpha1
|
||||
kind: Workspace
|
||||
metadata:
|
||||
@@ -17,7 +17,8 @@ spec:
|
||||
\n },\n {\n \"function\": \"run_job\",\n \"line\": 746,\n \"path\": \"web/pgadmin/browser/server_groups/servers/databases/dbms_job_scheduler/dbms_jobs/__init__.py\"\n },\n {\n \"function\": \"create\",\n \"line\": 365,\n \"path\": \"web/pgadmin/browser/server_groups/servers/databases/dbms_job_scheduler/dbms_schedules/__init__.py\"\n },\n {\n \"function\": \"msql\",\n \"line\": 454,\n \"path\": \"web/pgadmin/browser/server_groups/servers/databases/dbms_job_scheduler/dbms_schedules/__init__.py\"\n },\n {\n \"function\": \"sql\",\n \"line\": 492,\n \"path\": \"web/pgadmin/browser/server_groups/servers/databases/dbms_job_scheduler/dbms_schedules/__init__.py\"\n },\n {\n \"function\": \"msql\",\n \"line\": 623,\n \"path\": \"web/pgadmin/browser/server_groups/servers/databases/event_triggers/__init__.py\"\n },\n {\n \"function\": \"create\",\n \"line\": 290,\n \"path\": \"web/pgadmin/browser/server_groups/servers/databases/extensions/__init__.py\"\n },\n {\n \"function\"\
|
||||
: \"delete\",\n \"line\": 394,\n \"path\": \"web/pgadmin/browser/server_groups/servers/databases/extensions/__init__.py\"\n },\n {\n \"function\": \"get_extension_details\",\n \"line\": 30,\n \"path\": \"web/pgadmin/browser/server_groups/servers/databases/extensions/utils.py\"\n },\n {\n \"function\": \"delete\",\n \"line\": 601,\n \"path\": \"web/pgadmin/browser/server_groups/servers/databases/foreign_data_wrappers/__init__.py\"\n },\n {\n \"function\": \"create\",\n \"line\": 464,\n \"path\": \"web/pgadmin/browser/server_groups/servers/databases/foreign_data_wrappers/foreign_servers/__init__.py\"\n },\n {\n \"function\": \"create_maintenance_job\",\n \"line\": 222,\n \"path\": \"web/pgadmin/tools/maintenance/__init__.py\"\n }\n]\n"
|
||||
- path: case.json
|
||||
content: "{\n \"family\": \"injection\",\n \"id\": \"pgadmin-maintenance-sqli\",\n \"sites\": [\n \"web/pgadmin/tools/maintenance/__init__.py::create_maintenance_job\"\n ]\n}\n"
|
||||
content: "{\n \"cost\": {\n \"candidates_before_triage\": 27,\n \"recorded_triage_basis\": \"derived per file from the batched-check scans: recorded usd (triage + hunts) minus the recorded hunt usage priced at deepseek-flash list prices; the triage call's own usage was not recorded\",\n \"recorded_triage_usd\": 0.048665,\n \"recorded_usd\": 0.3949\n },\n \"family\": \"injection\",\n \"id\": \"pgadmin-maintenance-sqli\",\n \"ranges\": {\n \"web/pgadmin/tools/maintenance/__init__.py\": [\n [\n 12,\n 12\n ],\n [\n 150,\n 150\n ],\n [\n 171,\n 171\n ]\n ],\n \"web/pgadmin/tools/maintenance/templates/maintenance/sql/command.sql\": [\n [\n 16,\n 16\n ]\n ],\n \"web/pgadmin/tools/maintenance/tests/test_maintenance_create_job_unit_test.py\": [\n [\n 562,\n 562\n ],\n [\n 647,\n 647\n ],\n [\n 714,\n 714\n ],\n [\n 0,\n 0\n ]\n ]\n },\n \"ranges_basis\": \"git diff -U0 <vulnerable> <fixed>, old side: benchmarks/independent/evaluate.hunks(case,\
|
||||
\ 'old')\",\n \"sites\": [\n \"web/pgadmin/tools/maintenance/__init__.py::create_maintenance_job\"\n ],\n \"sites_in_set\": [\n \"web/pgadmin/tools/maintenance/__init__.py::create_maintenance_job\"\n ]\n}\n"
|
||||
- path: triage.json
|
||||
content: "{\n \"candidates\": [\n [\n \"web/pgadmin/authenticate/ldap.py\",\n \"login\",\n 169\n ],\n [\n \"web/pgadmin/authenticate/ldap.py\",\n \"search_ldap_user\",\n 288\n ],\n [\n \"web/pgadmin/browser/server_groups/servers/__init__.py\",\n \"create_restore_point\",\n 1881\n ],\n [\n \"web/pgadmin/browser/server_groups/servers/databases/__init__.py\",\n \"_check_rename_db_or_change_table_space\",\n 808\n ],\n [\n \"web/pgadmin/browser/server_groups/servers/databases/__init__.py\",\n \"_fetch_db_details\",\n 831\n ],\n [\n \"web/pgadmin/browser/server_groups/servers/databases/__init__.py\",\n \"create\",\n 761\n ],\n [\n \"web/pgadmin/browser/server_groups/servers/databases/__init__.py\",\n \"delete\",\n 1061\n ],\n [\n \"web/pgadmin/browser/server_groups/servers/databases/__init__.py\",\n \"get_ctypes\",\n 651\n ],\n [\n \"web/pgadmin/browser/server_groups/servers/databases/__init__.py\",\n \"get_encodings\",\n\
|
||||
\ 623\n ],\n [\n \"web/pgadmin/browser/server_groups/servers/databases/__init__.py\",\n \"get_sql\",\n 1107\n ],\n [\n \"web/pgadmin/browser/server_groups/servers/databases/__init__.py\",\n \"update\",\n 936\n ],\n [\n \"web/pgadmin/browser/server_groups/servers/databases/casts/__init__.py\",\n \"delete\",\n 546\n ],\n [\n \"web/pgadmin/browser/server_groups/servers/databases/dbms_job_scheduler/dbms_jobs/__init__.py\",\n \"_fetch_properties\",\n 362\n ],\n [\n \"web/pgadmin/browser/server_groups/servers/databases/dbms_job_scheduler/dbms_jobs/__init__.py\",\n \"create\",\n 412\n ],\n [\n \"web/pgadmin/browser/server_groups/servers/databases/dbms_job_scheduler/dbms_jobs/__init__.py\",\n \"enable_disable\",\n 662\n ],\n [\n \"web/pgadmin/browser/server_groups/servers/databases/dbms_job_scheduler/dbms_jobs/__init__.py\",\n \"get_job_args_value\",\n 779\n ],\n [\n \"web/pgadmin/browser/server_groups/servers/databases/dbms_job_scheduler/dbms_jobs/__init__.py\"\
|
||||
|
||||
Reference in New Issue
Block a user