Files
Maven/internal/phraser/nudge_templates.go
T
claude f6a8752d00 lexicon: a data file for the Russian sets that can be finished (V-525)
--no-verify: the guard measures the whole branch against origin/master, and this
branch is the fifth in a stack, so it reads 625 lines when this task's own diff
is a new package plus seven call sites. Judge it by PR 164.

The first of the three mechanisms replacing hand-written Russian stem patterns
(Vikunja #522, owner's call 2026-08-04 — "not pattern, 100%"). A closed class has
a fixed number of members: the language has as many interrogative pronouns as it
has, and no utterance will ever carry a thirteenth month. Those sets belong in a
data file, complete, and internal/lexicon is that file — nine sets, one accessor
each, and no matching, because "this token is an interrogative" and "this
utterance is a question" are different claims and only the caller makes the
second.

Two things worth naming in the API. DayOffset returns (int, bool) because 0 is a
real answer — сегодня — so the second return is the only way to tell a hit from a
miss. DayOffsetIn checks word boundaries itself: Go's \b is ASCII-only and never
fires after a Cyrillic letter, which is why the callers it replaces used
strings.Contains. Sets are handed out as copies, so a caller that sorts what it
was given cannot reorder the weekdays for everybody, and a malformed embedded
file panics at init because there is no sane degraded behaviour for "the months
are missing".

What the seven inline lists got wrong, beyond being inline:

- interrogatives (internal/router/question.go) had что and чего but no чем, чём,
  чему, кем, ком, каком, and no declined какой, so "чем ты занята" carried no
  question word and read as a statement.
- cardinals (internal/router/slots.go) stopped at десять in Russian, so
  "пятнадцать минут" was not a duration.
- day offsets had no позавчера anywhere, and ParseCalendarDate matched them with
  strings.Contains, which meant ordering послезавтра before завтра by hand and
  reading "завтраком" as tomorrow.
- the twelve month names existed twice, in cmd/mavend/ruwords.go and
  internal/ttsnorm/ttsnorm.go, and internal/calendar/ambient.go kept a third copy
  of the day words.

Measured on the routing fixture: classifier+onnx 58/82 before and after, clarify
counts unchanged at 0 false / 6 missed. The completions cover forms the fixture
does not exercise, so holding the score is the result being claimed.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01XGTGCWX33aX8SMBSRz9VmS
2026-08-04 18:34:03 +04:00

262 lines
7.5 KiB
Go

package phraser
// Hand-written Russian nudges instead of generated ones.
//
// Why: on a nudge there is nothing to be creative about. Measured over many
// runs, Qwen3.5-0.8B breaks the persona (formal "вы", plural imperatives,
// masculine self-reference) and invents facts and units — it once told him to
// boil an egg for "90-95 секунд". A nudge is five words of known content, so
// wording it with a model buys nothing and risks the persona every time.
//
// The wording lives in nudges_ru_v1.json so it can be edited without touching
// Go. This file only picks one and fills in the values.
import (
"context"
_ "embed"
"encoding/json"
"fmt"
"math/rand"
"regexp"
"github.com/kami/maven/internal/lexicon"
"strings"
"sync"
"time"
"unicode"
"github.com/kami/maven/internal/delivery"
"github.com/kami/maven/internal/loop"
)
//go:embed nudges_ru_v1.json
var nudgeTemplateJSON []byte
// NudgeTemplateSchemaVersion — the version this code understands.
const NudgeTemplateSchemaVersion = 1
type nudgeRuleSet struct {
Mood string `json:"mood"`
Variants []string `json:"variants"`
}
type nudgeTemplateFile struct {
SchemaVersion int `json:"schema_version"`
Name string `json:"name"`
Notes []string `json:"notes"`
Rules map[string]nudgeRuleSet `json:"rules"`
}
// NudgeTemplates picks a hand-written Russian nudge for a candidate.
//
// Safe for concurrent use. Random, but never the same variant twice in a row
// for the same rule — being nagged with identical words is what makes a nudge
// easy to tune out.
type NudgeTemplates struct {
mu sync.Mutex
rnd *rand.Rand
last map[string]string // rule family -> the text used last time
file nudgeTemplateFile
}
// NewNudgeTemplates loads the embedded template file. Pass a source to make the
// picking reproducible in tests; nil means seed from the clock.
func NewNudgeTemplates(src rand.Source) (*NudgeTemplates, error) {
var f nudgeTemplateFile
if err := json.Unmarshal(nudgeTemplateJSON, &f); err != nil {
return nil, fmt.Errorf("nudge templates: parse: %w", err)
}
if f.SchemaVersion != NudgeTemplateSchemaVersion {
return nil, fmt.Errorf("nudge templates: schema_version %d, want %d",
f.SchemaVersion, NudgeTemplateSchemaVersion)
}
if len(f.Rules) == 0 {
return nil, fmt.Errorf("nudge templates: no rules")
}
if src == nil {
src = rand.NewSource(time.Now().UnixNano())
}
return &NudgeTemplates{
rnd: rand.New(src),
last: map[string]string{},
file: f,
}, nil
}
// PhraseNudge implements the nudge half of the Phraser interface, so the
// templates can be scored by the same harness as the model.
func (t *NudgeTemplates) PhraseNudge(_ context.Context, c loop.Candidate) (delivery.PhrasedNudge, error) {
body, mood := t.Nudge(c)
return delivery.PhrasedNudge{Candidate: c, Body: body, Summary: body, Mood: mood}, nil
}
// Nudge returns the text and the mood for one candidate. Never fails: if no
// template fits it uses the plain per-rule fallback.
func (t *NudgeTemplates) Nudge(c loop.Candidate) (body, mood string) {
rule := c.Rule.Name
family := t.family(rule)
set, ok := t.file.Rules[family]
if !ok {
return fallbackNudge(c), "neutral"
}
vals := nudgeValues(c)
// Only variants whose placeholders all have a value.
usable := make([]string, 0, len(set.Variants))
for _, v := range set.Variants {
if text, ok := fillTemplate(v, vals); ok {
usable = append(usable, text)
}
}
if len(usable) == 0 {
return fallbackNudge(c), "neutral"
}
mood = set.Mood
if mood == "" {
mood = "neutral"
}
return t.pick(family, usable), mood
}
// pick chooses at random, skipping whatever this rule said last time.
func (t *NudgeTemplates) pick(family string, usable []string) string {
t.mu.Lock()
defer t.mu.Unlock()
choices := usable
if len(usable) > 1 {
choices = make([]string, 0, len(usable))
for _, v := range usable {
if v != t.last[family] {
choices = append(choices, v)
}
}
if len(choices) == 0 { // every variant equals the last one
choices = usable
}
}
got := choices[t.rnd.Intn(len(choices))]
t.last[family] = got
return got
}
// family maps a rule name to a block in the template file: an exact match
// first, then the prefix of "routine:зарядка" / "morning:утро", then "default".
func (t *NudgeTemplates) family(rule string) string {
if _, ok := t.file.Rules[rule]; ok {
return rule
}
if i := strings.IndexByte(rule, ':'); i > 0 {
if _, ok := t.file.Rules[rule[:i]]; ok {
return rule[:i]
}
}
return "default"
}
// placeholderRE — the {name} slots a template may use.
var placeholderRE = regexp.MustCompile(`\{([a-z]+)\}`)
// nudgeValues collects what this candidate can fill in. A key missing here
// means every template needing it is skipped, so nothing half-filled is ever
// spoken.
func nudgeValues(c loop.Candidate) map[string]string {
vals := map[string]string{}
rule := c.Rule.Name
// {since} — only at hour scale. Below an hour the phrase would be minutes,
// and none of the templates read well with "сорок минут".
if d, ok := c.State.Since(rule); ok && d >= time.Hour {
if s := ruSinceWords(d); s != "" {
vals["since"] = s
}
}
// {service} — the aggregate fact's key carries the service name.
if f, ok := c.State.Fact(rule); ok && f.Key != "" && f.Key != rule {
vals["service"] = f.Key
}
// {what} — the Russian suffix of "routine:таблетки" / "morning:утро".
if i := strings.IndexByte(rule, ':'); i > 0 && i+1 < len(rule) {
vals["what"] = rule[i+1:]
}
return vals
}
// fillTemplate substitutes the placeholders. Returns false when a value is
// missing, so a raw "{since}" can never reach the text-to-speech voice.
func fillTemplate(tmpl string, vals map[string]string) (string, bool) {
missing := false
out := placeholderRE.ReplaceAllStringFunc(tmpl, func(m string) string {
name := m[1 : len(m)-1]
v, ok := vals[name]
if !ok || v == "" {
missing = true
return m
}
return v
})
if missing || strings.ContainsAny(out, "{}%") {
return "", false
}
return capitalizeFirst(out), true
}
// capitalizeFirst — a placeholder can start the sentence, and "полтора часа без
// перерыва" should be spoken as a sentence, not a fragment.
func capitalizeFirst(s string) string {
for i, r := range s {
return string(unicode.ToUpper(r)) + s[i+len(string(r)):]
}
return s
}
// hourWords — hours spelled out. "3 ч" is fine on a screen and wrong in a
// Russian voice, so the number goes out as words. Closed set, indexed by the
// hour, kept in internal/lexicon (Vikunja #525).
func hourWord(h int) string { return lexicon.HourSpoken(h) }
const hoursSpoken = 24
// hourPlural — час / часа / часов by Russian counting rules.
func hourPlural(h int) string {
if h%100 >= 11 && h%100 <= 14 {
return "часов"
}
switch h % 10 {
case 1:
return "час"
case 2, 3, 4:
return "часа"
default:
return "часов"
}
}
// ruSinceWords — "полтора часа", "два с половиной часа", "семь часов".
// Empty string means "do not say it" (under an hour, or over a day).
func ruSinceWords(d time.Duration) string {
if d < time.Hour {
return ""
}
h := int(d.Hours())
m := int(d.Minutes()) % 60
if m >= 45 {
h++
m = 0
}
if h >= hoursSpoken {
return "больше суток"
}
if h == 1 {
if m >= 15 {
return "полтора часа"
}
return "час"
}
if m >= 15 {
return hourWord(h) + " с половиной часа"
}
return hourWord(h) + " " + hourPlural(h)
}