mirror of
https://github.com/merlinhu1/truthmark.git
synced 2026-08-25 07:53:25 +02:00
Merlin's CatGitHubCopilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>MerlinHCopilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>* feat: add workflow eval framework Add workflow evaluation scenarios, rubrics, schemas, and runner scripts for installed Truthmark workflows. Move research notes under docs/research and migrate tests from Vitest to node:test. * Potential fix for pull request finding 'CodeQL / Replacement of a substring with itself' Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com> --------- Co-authored-by: MerlinH <merlinh221@gmail.com> Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
28 lines
925 B
JSON
28 lines
925 B
JSON
{
|
|
"type": "object",
|
|
"required": ["status", "runDir", "scenario", "host", "deterministic", "judge", "usage"],
|
|
"properties": {
|
|
"status": { "enum": ["passed", "failed", "blocked", "not_evaluable"] },
|
|
"runDir": { "type": "string" },
|
|
"scenario": { "type": "string" },
|
|
"host": { "type": "string" },
|
|
"agentModel": { "type": "string" },
|
|
"judgeModel": { "type": "string" },
|
|
"deterministic": { "type": "object" },
|
|
"judge": { "type": "object" },
|
|
"usage": {
|
|
"type": "object",
|
|
"required": ["status", "agent", "judge", "total", "requirement"],
|
|
"additionalProperties": true,
|
|
"properties": {
|
|
"status": { "enum": ["measured", "unavailable", "invalid"] },
|
|
"agent": { "type": "object" },
|
|
"judge": { "type": "object" },
|
|
"total": { "type": "object" },
|
|
"requirement": { "type": "object" }
|
|
}
|
|
}
|
|
},
|
|
"additionalProperties": true
|
|
}
|