claude
4dfe106fe3
IntentFact used to persist whatever the model invented for a question-shaped utterance, at confidence 1.00, and index it for recall under the question's own text. Two such rows then claimed seven unrelated world questions and silently disabled world answering. A question now goes down the query chain, which is what he asked for. The second half is confidence: a value grounded in what he said stays 1.00, a value the model supplied for words he never said drops to 0.60 and says so in the log. Same reasoning as 'LLM output is not authorization' on the act path.
83 lines
2.6 KiB
Go
83 lines
2.6 KiB
Go
package main
|
|
|
|
import (
|
|
"log"
|
|
"strings"
|
|
"unicode"
|
|
)
|
|
|
|
// ungroundedConfidence — what a self fact is worth when its value appears
|
|
// nowhere in what he said. Below `query_min_score` is not the point (recall
|
|
// gates on vector distance, not on this number); the point is that
|
|
// `/history` and every future reader can tell a value he said from a value
|
|
// the model supplied.
|
|
const ungroundedConfidence = 0.6
|
|
|
|
// factConfidence scores a self fact by whether its value is grounded in the
|
|
// utterance it came from. Grounded stays 1.00, which is what a tapped fact
|
|
// has always been worth. Ungrounded drops, and says so in the log.
|
|
//
|
|
// An empty value is grounded by definition: the key alone carries the fact
|
|
// ("поужинал"), and there is nothing for the model to have invented.
|
|
func factConfidence(utterance, value string) float64 {
|
|
if strings.TrimSpace(value) == "" {
|
|
return 1.0
|
|
}
|
|
if valueGrounded(utterance, value) {
|
|
return 1.0
|
|
}
|
|
log.Printf("voice: fact value %q is not in %q — writing at confidence %.2f",
|
|
value, utterance, ungroundedConfidence)
|
|
return ungroundedConfidence
|
|
}
|
|
|
|
// valueGrounded reports whether every word of value traces back to a word he
|
|
// actually said. The comparison is on a 4-rune prefix, so the model's
|
|
// normalization survives ("пил воду" → "вода") while an invented value
|
|
// ("1.20" for a question about Go) does not.
|
|
func valueGrounded(utterance, value string) bool {
|
|
said := factTokens(utterance)
|
|
words := factTokens(value)
|
|
if len(words) == 0 {
|
|
return true
|
|
}
|
|
for _, w := range words {
|
|
if !anyTokenMatches(said, w) {
|
|
return false
|
|
}
|
|
}
|
|
return true
|
|
}
|
|
|
|
func anyTokenMatches(said []string, w string) bool {
|
|
for _, s := range said {
|
|
if s == w || sameStem(s, w) {
|
|
return true
|
|
}
|
|
}
|
|
return false
|
|
}
|
|
|
|
// sameStem is inflection tolerance and nothing more: it compares all but the
|
|
// last rune of the shorter word, and never fewer than three. Russian marks
|
|
// case on the ending, so "пил воду" and the stored "вода" are the same word he
|
|
// said, while "1.20" and "версия" are not. A word of three runes or fewer must
|
|
// match outright, where a shorter prefix would match half the language.
|
|
func sameStem(a, b string) bool {
|
|
ar, br := []rune(a), []rune(b)
|
|
shorter := min(len(ar), len(br))
|
|
n := shorter - 1
|
|
if n < 3 || len(ar) < n || len(br) < n {
|
|
return false
|
|
}
|
|
return string(ar[:n]) == string(br[:n])
|
|
}
|
|
|
|
// factTokens lowercases and splits on everything that is not a letter or a
|
|
// digit, the same shape planTokens uses in the router.
|
|
func factTokens(s string) []string {
|
|
return strings.FieldsFunc(strings.ToLower(s), func(r rune) bool {
|
|
return !unicode.IsLetter(r) && !unicode.IsDigit(r)
|
|
})
|
|
}
|