mirror of
https://github.com/norandom/OpenUltraSAST.git
synced 2026-10-16 03:49:26 +00:00
Marius CiepluchandClaude Opus 5.5
56b1717246
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
18 lines
3.2 KiB
YAML
18 lines
3.2 KiB
YAML
# 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:
|
|
name: cct-studio-server-cmdi-inputs
|
|
atespace: default
|
|
spec:
|
|
files:
|
|
- path: candidates.json
|
|
content: "{\n \"candidates\": [\n [\n \"cli-tool/src/sandbox-server.js\",\n \"checkAndInstallAgent\",\n 280\n ],\n [\n \"cli-tool/src/sandbox-server.js\",\n \"executeLocalTask\",\n 464\n ]\n ],\n \"family\": \"injection\",\n \"id\": \"cct-studio-server-cmdi\"\n}\n"
|
|
- path: functions.json
|
|
content: "[\n {\n \"function\": \"checkAndInstallAgent\",\n \"line\": 280,\n \"path\": \"cli-tool/src/sandbox-server.js\"\n },\n {\n \"function\": \"executeLocalTask\",\n \"line\": 464,\n \"path\": \"cli-tool/src/sandbox-server.js\"\n }\n]\n"
|
|
- path: case.json
|
|
content: "{\n \"cost\": {\n \"candidates_before_triage\": 2,\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\": 0.003055,\n \"recorded_usd\": 0.0242\n },\n \"family\": \"injection\",\n \"id\": \"cct-studio-server-cmdi\",\n \"ranges\": {\n \"CHANGELOG.md\": [\n [\n 7,\n 7\n ]\n ],\n \"cli-tool/package.json\": [\n [\n 3,\n 3\n ]\n ],\n \"cli-tool/src/sandbox-server.js\": [\n [\n 11,\n 11\n ],\n [\n 50,\n 50\n ],\n [\n 52,\n 52\n ],\n [\n 54,\n 54\n ],\n [\n 202,\n 202\n ],\n [\n 209,\n 209\n ],\n [\n 212,\n 214\n ],\n [\n 216,\n 217\n ],\n [\n 278,\n 278\n ],\n [\n 280,\n 280\n ],\n [\n 282,\n 283\n ],\n [\n 463,\n 464\n ],\n [\n 471,\n \
|
|
\ 471\n ],\n [\n 561,\n 562\n ]\n ],\n \"package.json\": [\n [\n 3,\n 3\n ]\n ]\n },\n \"ranges_basis\": \"git diff -U0 <vulnerable> <fixed>, old side: benchmarks/independent/evaluate.hunks(case, 'old')\",\n \"sites\": [\n \"cli-tool/src/sandbox-server.js::executeLocalTask\",\n \"cli-tool/src/sandbox-server.js::checkAndInstallAgent\"\n ],\n \"sites_in_set\": [\n \"cli-tool/src/sandbox-server.js::executeLocalTask\",\n \"cli-tool/src/sandbox-server.js::checkAndInstallAgent\"\n ]\n}\n"
|
|
- path: triage.json
|
|
content: "{\n \"candidates\": [\n [\n \"cli-tool/src/sandbox-server.js\",\n \"checkAndInstallAgent\",\n 280\n ],\n [\n \"cli-tool/src/sandbox-server.js\",\n \"executeLocalTask\",\n 464\n ]\n ],\n \"kept\": [\n [\n \"cli-tool/src/sandbox-server.js\",\n \"checkAndInstallAgent\",\n 280\n ],\n [\n \"cli-tool/src/sandbox-server.js\",\n \"executeLocalTask\",\n 464\n ]\n ],\n \"triage\": {\n \"cli-tool/src/sandbox-server.js::checkAndInstallAgent\": \"parameter\",\n \"cli-tool/src/sandbox-server.js::executeLocalTask\": \"request\"\n }\n}\n"
|