erhan/abap-llm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Eval review v1: checklist, review helper, 24 tasks reviewed; G0002/G0022 tests fixed; I/E generator definitions

Browse Source 
- docs/eval-inceleme.md checklist; harness/review.py
- 19 accept, 1 fix pending (G0019), 4 flagged (I/E tasks solvable without legacy code)
- generator: categories I and E fix/refactor the seed object in place

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 06:23:38 +02:00
parent a12fa4dff6
commit 3550f0b651
38 changed files with 607 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
tasks_gen/eval/G0022/mutation.json
View File

@@ -5,11 +5,12 @@
"object": "{{P}}EXPENSE_VALIDATOR",
"mutant": "line 54: = -> <> (eq)",
"status": "killed",
"hidden": "3/12",
"hidden": "3/13",
"failed_tests": [
"COST_CENTER_NOT_REQUIRED",
"COST_CENTER_REQUIRED",
"FUTURE_DATE_REJECTED",
"OTHER_CURRENCIES_PASS",
"RECEIPT_NOT_REQUIRED_BELOW",
"RECEIPT_REQUIRED",
"RECEIPT_RULE_HAS_PRIORITY",
@@ -22,11 +23,12 @@
"object": "{{P}}EXPENSE_VALIDATOR",
"mutant": "line 54: abap_false -> abap_true (bool)",
"status": "killed",
"hidden": "3/12",
"hidden": "3/13",
"failed_tests": [
"COST_CENTER_NOT_REQUIRED",
"COST_CENTER_REQUIRED",
"FUTURE_DATE_REJECTED",
"OTHER_CURRENCIES_PASS",
"RECEIPT_NOT_REQUIRED_BELOW",
"RECEIPT_REQUIRED",
"RECEIPT_RULE_HAS_PRIORITY",
@@ -39,11 +41,12 @@
"object": "{{P}}EXPENSE_VALIDATOR",
"mutant": "line 61: > -> <= (rel)",
"status": "killed",
"hidden": "4/12",
"hidden": "4/13",
"failed_tests": [
"COST_CENTER_NOT_REQUIRED",
"COST_CENTER_REQUIRED",
"FUTURE_DATE_REJECTED",
"OTHER_CURRENCIES_PASS",
"RECEIPT_NOT_REQUIRED_BELOW",
"RECEIPT_REQUIRED",
"RECEIPT_RULE_HAS_PRIORITY",
@@ -55,10 +58,11 @@
"object": "{{P}}EXPENSE_VALIDATOR",
"mutant": "line 68: = -> <> (eq)",
"status": "killed",
"hidden": "6/12",
"hidden": "6/13",
"failed_tests": [
"COST_CENTER_NOT_REQUIRED",
"COST_CENTER_REQUIRED",
"OTHER_CURRENCIES_PASS",
"RECEIPT_REQUIRED",
"RECEIPT_RULE_HAS_PRIORITY",
"TODAY_IS_ACCEPTED",
@@ -68,13 +72,15 @@
{
"object": "{{P}}EXPENSE_VALIDATOR",
"mutant": "line 83: OR -> AND (logic)",
"status": "survived",
"hidden": "12/12",
"failed_tests": []
"status": "killed",
"hidden": "12/13",
"failed_tests": [
"OTHER_CURRENCIES_PASS"
]
}
],
"valid": 5,
"killed": 4,
"kill_rate": 0.8,
"killed": 5,
"kill_rate": 1.0,
"ok": true
}