CodeBench: mallikohtainen golden example (profiles.json → golden kenttä)

qwen3-coder:30b → todo.md (annotaatiot)
qwen3:8b → todo-readme.md (GitHub README -muoto, tutuin koulutusdata)
Golden example ladataan dynaamisesti per malli pipelinen sisällä.

kipina-codebench/results/2026-04-14T10-59.json

@@ -0,0 +1,69 @@
+[
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 1,
+    "testsTotal": 11,
+    "testsPassed": 11,
+    "testsFailed": 0,
+    "totalDurationMs": 64124,
+    "totalTokens": 5689,
+    "avgTokPerSec": 98.61378134916481,
+    "promptChars": 12098,
+    "promptTokensEst": 3025,
+    "score": 90,
+    "stars": "★★★★★",
+    "error": null,
+    "profile": "small",
+    "promptName": "code-small",
+    "round": 1
+  },
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": true,
+    "specEntities": 2,
+    "validationIssues": 0,
+    "fixRounds": 3,
+    "testsTotal": 0,
+    "testsPassed": 0,
+    "testsFailed": 0,
+    "totalDurationMs": 126014,
+    "totalTokens": 11162,
+    "avgTokPerSec": 97.09858655726343,
+    "promptChars": 12101,
+    "promptTokensEst": 3025,
+    "score": 0,
+    "stars": "☆☆☆☆☆",
+    "error": "Testit kaatuivat",
+    "profile": "small",
+    "promptName": "code-small",
+    "round": 2
+  },
+  {
+    "model": "qwen3:8b",
+    "scenario": "blog",
+    "reqOk": true,
+    "specOk": false,
+    "specEntities": 0,
+    "validationIssues": 0,
+    "fixRounds": 0,
+    "testsTotal": 0,
+    "testsPassed": 0,
+    "testsFailed": 0,
+    "totalDurationMs": 0,
+    "totalTokens": 0,
+    "avgTokPerSec": 0,
+    "promptChars": 0,
+    "promptTokensEst": 0,
+    "score": 0,
+    "stars": "",
+    "error": "JSON-speksi epäonnistui",
+    "round": 3
+  }
+]