mirror of
https://github.com/lukaszraczylo/llm-testbench.git
synced 2026-10-12 00:45:19 +00:00
fix(catalog): unify negation guard and harden round-2 evaluators
A shared NoUnnegatedMention primitive replaces four per-category implementations, with a bidirectional clause-scoped window and an adjectival cue set. The docker layer fixture drops WORKDIR, which creates a real layer and made the pinned answer wrong. The replica failover test now forces a JSON verdict so a negated answer cannot score. Remaining exact-answer tests migrate to ExactToken. Ordering prompts shuffle their candidate lists so echoing scores zero.
This commit is contained in:
@@ -44,8 +44,8 @@ func TestDBRedisStructureChoiceTest_Eval(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestDBRedisTTLEvictionTest_Eval(t *testing.T) {
|
||||
tc := dbRedisTTLEvictionTest()
|
||||
func TestDBRedisNoevictionWriteTest_Eval(t *testing.T) {
|
||||
tc := dbRedisNoevictionWriteTest()
|
||||
|
||||
tests := []struct {
|
||||
name string
|
||||
|
||||
Reference in New Issue
Block a user