Mutation in generator; category H (stop) scoring and judge; category K variants and tool schema variant; evalset plan
- mutation.py: negation mutants, skip WHILE/DO blocks (endless loop blocked RFC ~8 min) - generator: accept only after mutation check; survivors go back as repair feedback - runner/judge.py: stop tasks scored 100/30/0; gap by keywords, else judge model - proxy: tool schema variant generic_v0 (draft); generator make_k_variant - evalset.py: 88 slots for step F (A-I, H, K) Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -40,7 +40,7 @@ def main():
|
||||
try:
|
||||
log = generate(tid, "eval", otype, cat, 2, "deepseek-v4.1-flash:cloud",
|
||||
os.environ.get("LLM_BASE_URL", "http://127.0.0.1:11434/v1"),
|
||||
run_base + 10 * k, topic)
|
||||
run_base + 40 * k, topic)
|
||||
except BudgetExceeded as e:
|
||||
print("BUDGET", e, flush=True)
|
||||
break
|
||||
|
||||
Reference in New Issue
Block a user