mirror of
https://github.com/norandom/OpenUltraSAST.git
synced 2026-10-17 12:09:27 +00:00
feat(plane): increment manifests for the 46-candidate validation run (task 7)
Model deepseek-flash (declared provider extension, endpoint prices in parameters, secretKey naming the DEEPSEEK_API_KEY secret), digest-pinned Task templates repo-facts / verify / agree, and a generator (plane/generate.py, `ousast plane workspaces --validation-set ...`) that emits per case the vulnerable-pin Workspace, a files-only inputs Workspace (recorded candidates after the recorded triage, declared sites, triage), per-case Tasks and one Run validation-46: facts -> verify a, verify b -> agree for the 15 cases, 46 candidates (43 kept), budgets 1.5x the recorded per-pass share. A Run entry cannot add a binding or env, and Run.inputs names only task artifacts, so the case is fixed by per-case Tasks. 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
1a69e50a68
commit
a35397c0ec
@@ -0,0 +1,16 @@
|
||||
# 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.
|
||||
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 \"family\": \"injection\",\n \"id\": \"cct-studio-server-cmdi\",\n \"sites\": [\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"
|
||||
Reference in New Issue
Block a user