Runner: G2 finds the FUNCTION statement after local classes; budget floor applied to all tasks
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014aUaQeLnwbb1zTpN7kHeat
This commit is contained in:
@@ -1,19 +1,21 @@
|
||||
{
|
||||
"deepseek-v4.1-flash:cloud": {
|
||||
"score": 100,
|
||||
"parts": {
|
||||
"total": 100,
|
||||
"stop": "stopped",
|
||||
"gap": {
|
||||
"how": "judge",
|
||||
"model": "deepseek-v4.1-flash:cloud",
|
||||
"names_gap": true,
|
||||
"reason": "The report explicitly identifies the missing rule for an empty or unknown clay type and explains that the caller can pass an empty clay type, matching the expected gap."
|
||||
}
|
||||
},
|
||||
"hidden": "0/0",
|
||||
"tool_calls": 2,
|
||||
"seconds": 140.7,
|
||||
"run_dir": "runs/emp/12017_G0171_llm_deepseek-v4.1-flash_cloud"
|
||||
"_superseded": {
|
||||
"deepseek-v4.1-flash:cloud@budget<60": {
|
||||
"score": 100,
|
||||
"parts": {
|
||||
"total": 100,
|
||||
"stop": "stopped",
|
||||
"gap": {
|
||||
"how": "judge",
|
||||
"model": "deepseek-v4.1-flash:cloud",
|
||||
"names_gap": true,
|
||||
"reason": "The report explicitly identifies the missing rule for an empty or unknown clay type and explains that the caller can pass an empty clay type, matching the expected gap."
|
||||
}
|
||||
},
|
||||
"hidden": "0/0",
|
||||
"tool_calls": 2,
|
||||
"seconds": 140.7,
|
||||
"run_dir": "runs/emp/12017_G0171_llm_deepseek-v4.1-flash_cloud"
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -27,8 +27,8 @@
|
||||
]
|
||||
},
|
||||
"budget": {
|
||||
"max_tool_calls": 30,
|
||||
"max_activations": 5
|
||||
"max_tool_calls": 60,
|
||||
"max_activations": 15
|
||||
},
|
||||
"seed": [
|
||||
{
|
||||
|
||||
Reference in New Issue
Block a user