@lythos/skill-arena 0.9.9 → 0.9.10

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/package.json +1 -1
  2. package/src/runner.ts +5 -3
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@lythos/skill-arena",
3
- "version": "0.9.9",
3
+ "version": "0.9.10",
4
4
  "description": "Skill Arena — benchmark skill effectiveness with controlled-variable comparison",
5
5
  "keywords": [
6
6
  "ai-agent",
package/src/runner.ts CHANGED
@@ -130,12 +130,14 @@ export async function runArenaFromToml(opts: {
130
130
  if (!verdictsBySide.has(cell.side)) verdictsBySide.set(cell.side, [])
131
131
  verdictsBySide.get(cell.side)!.push(v)
132
132
  } catch (e) {
133
- if (!verdictsBySide.has(cell.side)) verdictsBySide.set(cell.side, [])
134
- verdictsBySide.get(cell.side)!.push({
133
+ const errVerdict: JudgeVerdict = {
135
134
  verdict: 'ERROR' as const,
136
135
  reason: `Runner exception: ${e instanceof Error ? e.message : String(e)}`,
137
136
  criteria: [],
138
- })
137
+ }
138
+ writeFileSync(join(cellDir, 'judge-verdict.json'), JSON.stringify(errVerdict, null, 2) + '\n')
139
+ if (!verdictsBySide.has(cell.side)) verdictsBySide.set(cell.side, [])
140
+ verdictsBySide.get(cell.side)!.push(errVerdict)
139
141
  }
140
142
  }
141
143