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:
Kral
2026-10-03 18:25:30 +02:00
parent 7351849a76
commit 92e30eb554
78 changed files with 1362 additions and 560 deletions

View File

@@ -1,18 +1,20 @@
{
"deepseek-v4.1-flash:cloud": {
"score": 85.0,
"parts": {
"correctness": 40.0,
"craft": 20.0,
"clean": 15.0,
"own_tests": 0.0,
"discipline": 10.0,
"total": 85.0,
"note": "own_tests: faulty-reference part not implemented in skeleton"
},
"hidden": "10/10",
"tool_calls": 11,
"seconds": 36.2,
"run_dir": "runs/emp/11029_G0159_llm_deepseek-v4.1-flash_cloud"
"_superseded": {
"deepseek-v4.1-flash:cloud@budget<60": {
"score": 85.0,
"parts": {
"correctness": 40.0,
"craft": 20.0,
"clean": 15.0,
"own_tests": 0.0,
"discipline": 10.0,
"total": 85.0,
"note": "own_tests: faulty-reference part not implemented in skeleton"
},
"hidden": "10/10",
"tool_calls": 11,
"seconds": 36.2,
"run_dir": "runs/emp/11029_G0159_llm_deepseek-v4.1-flash_cloud"
}
}
}

View File

@@ -6,8 +6,8 @@
"release_target": "v740sp05",
"expected_outcome": "implement",
"budget": {
"max_tool_calls": 40,
"max_activations": 10
"max_tool_calls": 60,
"max_activations": 15
},
"seed": [
{