Score the conversational phrasing paths, not just nudges #37

Closed
claude wants to merge 2 commits from overnight/talk-eval into overnight/prompt-context
2 changed files with 60 additions and 7 deletions
Showing only changes of commit 0110e9bc8c - Show all commits
@@ -0,0 +1,33 @@
package eval
import (
"strings"
"testing"
)
// TestAddressReportsEveryBreak — the real reply from a nudge eval run broke in
// two ways at once and the check named only the plural. Both must print: a
// half-reported failure reads as a milder problem than it is.
func TestAddressReportsEveryBreak(t *testing.T) {
body := "Смотрите на его потребление воды."
res := checkAddress(body)
if res.Pass {
t.Fatalf("checkAddress passed %q", body)
}
for _, want := range []string{"смотрите", "его"} {
if !strings.Contains(res.Detail, want) {
t.Errorf("detail %q does not name %q", res.Detail, want)
}
}
}
// One word repeated is one problem, so the detail must not say it twice.
func TestAddressDeduplicates(t *testing.T) {
res := checkAddress("Вам стоит поесть, вам это нужно.")
if res.Pass {
t.Fatal("expected failure")
}
if n := strings.Count(res.Detail, "formal"); n != 1 {
t.Errorf("detail repeats the same break %d times: %q", n, res.Detail)
}
}
+27 -7
View File
@@ -434,14 +434,26 @@ func looksVerb(w string) bool {
func checkAddress(body string) Result {
words := addressWordRE.FindAllString(strings.ToLower(body), -1)
// Every break, not just the first. A bad reply usually breaks in more than
// one way at once — "Смотрите на его потребление воды" is a plural imperative
// AND third person about him — and reporting only the first hid the second,
// which made the failure look milder than it was.
var breaks []string
seen := map[string]bool{}
add := func(msg string) {
if seen[msg] {
return // the same word twice in one message is one problem, not two
}
seen[msg] = true
breaks = append(breaks, msg)
}
for i, w := range words {
if formalPronouns[w] {
return Result{CheckAddress, false,
fmt.Sprintf("formal %q — she says ты/тебя/тебе", w)}
add(fmt.Sprintf("formal %q — she says ты/тебя/тебе", w))
}
if pluralVerb(w) && !(i > 0 && prepositions[words[i-1]]) {
return Result{CheckAddress, false,
fmt.Sprintf("plural imperative %q — she uses the singular", w)}
add(fmt.Sprintf("plural imperative %q — she uses the singular", w))
}
}
@@ -455,18 +467,26 @@ func checkAddress(body string) Result {
if !unicode.Is(unicode.Cyrillic, []rune(p)[0]) && !isLatinWord(p) {
continue // punctuation
}
if notAnAntecedent[p] || prepositions[p] || thirdPersonHim[p] || looksVerb(p) {
// pluralVerb as well as looksVerb: looksVerb knows the imperative in
// -й/-йте but not the -те plural ("смотрите"), so "Смотрите на его
// потребление воды" counted "смотрите" as the person being talked
// about and the "его" never printed. Third time a verb form has
// blinded this check — if a fourth turns up, the antecedent test
// wants a real morphology table, not another suffix.
if notAnAntecedent[p] || prepositions[p] || thirdPersonHim[p] || looksVerb(p) || pluralVerb(p) {
continue
}
named = true
break
}
if !named {
return Result{CheckAddress, false,
fmt.Sprintf("third person %q with nobody else named — she talks to him, not about him", w)}
add(fmt.Sprintf("third person %q with nobody else named — she talks to him, not about him", w))
}
}
if len(breaks) > 0 {
return Result{CheckAddress, false, strings.Join(breaks, " + ")}
}
return Result{CheckAddress, true, ""}
}