Score the chat, query and knowledge phrasing paths (#395)
The nudge fixture only covered nudges. The shared persona block now goes into five prompts, and the three conversational ones were unmeasured — those are the long free-form replies where a persona break is most likely. Adds talk_v1.json (27 Russian cases, 9 per path) and ScoreTalk, reporting per-path as well as per-check so a chat regression can be told apart from a knowledge one. Reuses the persona checks; the nudge-only ones (length, mood, no questions) are left out, since a chat reply is allowed 1-3 sentences and a follow-up question. The LLM run is opt-in on MAVEN_LLM_URL as before. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
This commit is contained in:
@@ -574,12 +574,47 @@ func checkCringe(body string) Result {
|
||||
// checkOnTopic — the message must name the thing the rule is about. A nudge
|
||||
// that never mentions water leaves the operator with a chime and no action.
|
||||
func checkOnTopic(c Case, body string) Result {
|
||||
return checkOnTopicAny(c.WantAny, body)
|
||||
}
|
||||
|
||||
// checkOnTopicAny is the same test over a bare want-list, so the talk scorer can
|
||||
// reuse it without owning a nudge Case.
|
||||
func checkOnTopicAny(wantAny []string, body string) Result {
|
||||
low := strings.ToLower(body)
|
||||
for _, want := range c.WantAny {
|
||||
for _, want := range wantAny {
|
||||
if strings.Contains(low, strings.ToLower(want)) {
|
||||
return Result{CheckOnTopic, true, ""}
|
||||
}
|
||||
}
|
||||
return Result{CheckOnTopic, false,
|
||||
fmt.Sprintf("mentions none of %v", c.WantAny)}
|
||||
fmt.Sprintf("mentions none of %v", wantAny)}
|
||||
}
|
||||
|
||||
// --- shape checks for the free-form paths --------------------------------
|
||||
//
|
||||
// The nudge checks assume one short sentence. Chat and query replies are longer
|
||||
// by design, so the only shape worth testing there is that the model produced a
|
||||
// reply at all and did not trail off. Both are failure modes the fallbacks in
|
||||
// llmphraser.go hide: a truncated or empty generation still returns nil error.
|
||||
|
||||
const (
|
||||
CheckNonEmpty = "nonempty" // she said something
|
||||
CheckEllipsis = "ellipsis" // she finished the sentence
|
||||
)
|
||||
|
||||
func checkNonEmpty(body string) Result {
|
||||
if strings.TrimSpace(body) == "" {
|
||||
return Result{CheckNonEmpty, false, "empty reply"}
|
||||
}
|
||||
return Result{CheckNonEmpty, true, ""}
|
||||
}
|
||||
|
||||
// checkEllipsis — a reply ending in "…" or "..." is a generation that ran out of
|
||||
// tokens, not a stylistic pause. Mid-sentence ellipses are left alone.
|
||||
func checkEllipsis(body string) Result {
|
||||
trimmed := strings.TrimRight(strings.TrimSpace(body), `"'»)`)
|
||||
if strings.HasSuffix(trimmed, "…") || strings.HasSuffix(trimmed, "...") {
|
||||
return Result{CheckEllipsis, false, "reply trails off in an ellipsis — likely truncated"}
|
||||
}
|
||||
return Result{CheckEllipsis, true, ""}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user