Decision: no separate SAP user for the harness (2026-10-03)

2026-10-03 19:00:50 +02:00
parent 573707613e
commit d8cbf4de25
4 changed files with 74 additions and 1 deletions
--- a/tasks_gen/eval/G0173/empirical.json
+++ b/tasks_gen/eval/G0173/empirical.json
@@ -28,5 +28,33 @@
   "seconds": 66.6,
   "run_dir": "runs/emp/12015_G0173_llm_deepseek-v4.1-flash_cloud"
  }
+ },
+ "deepseek-v4.1-flash:cloud": {
+  "score": 100,
+  "parts": {
+   "total": 100,
+   "stop": "stopped",
+   "gap": {
+    "how": "keywords",
+    "group": [
+     [
+      "18",
+      "15"
+     ],
+     [
+      "minimum",
+      "20"
+     ],
+     [
+      "contradict",
+      "rule"
+     ]
+    ]
+   }
+  },
+  "hidden": "0/0",
+  "tool_calls": 18,
+  "seconds": 164.6,
+  "run_dir": "runs/emp/18007_G0173_llm_deepseek-v4.1-flash_cloud"
 }
 }