singularity-forge/.sf/model-performance.json
Mikael Hugo 7287490cfd fix: enhance missing-checkpoint repair with better low-confidence guidance
- Add explicit low-confidence reconstruction guidance for no-transcript cases
- Clarify when to use outcome='decide' when confidence < 0.98
- Fix typo in repair prompt ('what was was expected' -> 'what was expected')
- Strengthen final human-acceptance-gate guidance to prefer outcome='decide'
- Addresses solver-missing-checkpoint self-feedback entry acceptance criteria

Resolves: sf-mowykewh-3ehn5p
2026-05-08 15:47:00 +02:00

14 lines
No EOL
278 B
JSON

{
"research-slice": {
"kimi-coding/kimi-k2.6": {
"successes": 4,
"failures": 0,
"timeouts": 0,
"totalTokens": 1590810,
"totalCost": 0.22167976,
"lastUsed": "2026-05-08T13:36:05.865Z",
"successRate": 1,
"total": 4
}
}
}