Hand-written Russian nudge templates plus a picker

Nudge wording as data instead of generation. The wording lives in
internal/phraser/nudges_ru_v1.json (embedded), about 10 variants per rule:
water, meal, break, service_down, netdata_critical, routine:, morning:, plus
a contentless default. That JSON is long because it is data — the owner can
edit any line of Russian without touching Go.

The picker:
- random, but never the same variant twice in a row for the same rule
- deterministic when seeded (math/rand with an injectable source)
- fills {since} / {service} / {what} from the candidate, and skips any variant
  whose value is missing, so no raw placeholder can reach the piper voice
- {since} is spelled out in words ("полтора часа", "семь часов"), because
  "3 ч" is wrong in a Russian voice

Scores 15/15 on the existing nudge fixture, on every seed swept. Nothing is
wired yet — that is the next commit.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ
This commit is contained in:
kami
2026-07-31 18:18:55 +04:00
parent aa8f5b2ee2
commit 13e5170e9e
4 changed files with 618 additions and 0 deletions
+58
View File
@@ -0,0 +1,58 @@
package eval
import (
"context"
"math/rand"
"testing"
"github.com/kami/maven/internal/phraser"
)
// TestTemplateNudges scores the hand-written Russian templates on the same
// fixture the model is scored on. No model, no network — it runs in milliseconds.
//
// The bar is every case, not most of them: the templates are hand-written, so a
// failure is a bug in one line of Russian, not model variance.
func TestTemplateNudges(t *testing.T) {
f, err := Load()
if err != nil {
t.Fatalf("Load: %v", err)
}
// Fixed seed: the score must not depend on which variant came up.
nt, err := phraser.NewNudgeTemplates(rand.NewSource(20260731))
if err != nil {
t.Fatalf("NewNudgeTemplates: %v", err)
}
rep, err := Score(context.Background(), "ru templates", nt, f)
if err != nil {
t.Fatalf("Score: %v", err)
}
t.Log("\n" + rep.String())
t.Log("\n" + rep.Messages())
if rep.Passed != rep.Total {
t.Errorf("templates scored %d/%d, want every case:\n%s",
rep.Passed, rep.Total, rep.Failures())
}
}
// TestTemplateNudgesEverySeed — one seed passing could be luck. Every variant of
// every rule has to pass every check, so sweep seeds until each has been used.
func TestTemplateNudgesEverySeed(t *testing.T) {
f, err := Load()
if err != nil {
t.Fatalf("Load: %v", err)
}
for seed := int64(0); seed < 60; seed++ {
nt, err := phraser.NewNudgeTemplates(rand.NewSource(seed))
if err != nil {
t.Fatalf("NewNudgeTemplates: %v", err)
}
rep, err := Score(context.Background(), "ru templates", nt, f)
if err != nil {
t.Fatalf("Score: %v", err)
}
if rep.Passed != rep.Total {
t.Errorf("seed %d: %d/%d\n%s", seed, rep.Passed, rep.Total, rep.Failures())
}
}
}
+261
View File
@@ -0,0 +1,261 @@
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"
"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.
var hourWords = []string{
"ноль", "один", "два", "три", "четыре", "пять", "шесть", "семь", "восемь",
"девять", "десять", "одиннадцать", "двенадцать", "тринадцать",
"четырнадцать", "пятнадцать", "шестнадцать", "семнадцать", "восемнадцать",
"девятнадцать", "двадцать", "двадцать один", "двадцать два", "двадцать три",
}
// 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 >= len(hourWords) {
return "больше суток"
}
if h == 1 {
if m >= 15 {
return "полтора часа"
}
return "час"
}
if m >= 15 {
return hourWords[h] + " с половиной часа"
}
return hourWords[h] + " " + hourPlural(h)
}
+170
View File
@@ -0,0 +1,170 @@
package phraser
import (
"context"
"math/rand"
"strings"
"testing"
"time"
"github.com/kami/maven/internal/loop"
"github.com/kami/maven/internal/store"
)
// cand builds a candidate the way a tick would.
func cand(rule string, sinceMin int, factKey string) loop.Candidate {
now := time.Date(2026, 7, 31, 21, 40, 0, 0, time.UTC)
st := loop.State{Now: now, Facts: map[string]store.Fact{}}
if sinceMin > 0 || factKey != "" {
key := rule
if factKey != "" {
key = factKey
}
st.Facts[rule] = store.Fact{Key: key, Ts: now.Add(-time.Duration(sinceMin) * time.Minute)}
}
return loop.Candidate{Rule: loop.Rule{Name: rule, Severity: loop.Sev1}, Severity: loop.Sev1, State: st}
}
func newTestTemplates(t *testing.T, seed int64) *NudgeTemplates {
t.Helper()
nt, err := NewNudgeTemplates(rand.NewSource(seed))
if err != nil {
t.Fatalf("NewNudgeTemplates: %v", err)
}
return nt
}
func TestNudgeTemplatesLoad(t *testing.T) {
nt := newTestTemplates(t, 1)
for _, rule := range []string{"water", "meal", "break", "service_down", "netdata_critical", "routine", "morning", "default"} {
set, ok := nt.file.Rules[rule]
if !ok {
t.Errorf("no templates for %q", rule)
continue
}
if len(set.Variants) < 5 {
t.Errorf("%s: only %d variants", rule, len(set.Variants))
}
// Every rule needs one variant that needs no value, or a candidate
// without context has nothing to say. routine and morning are exempt:
// they always carry a name and must always say it.
plain := 0
seen := map[string]bool{}
for _, v := range set.Variants {
if !placeholderRE.MatchString(v) {
plain++
}
if seen[v] {
t.Errorf("%s: duplicate variant %q", rule, v)
}
seen[v] = true
}
if plain == 0 && rule != "routine" && rule != "morning" {
t.Errorf("%s: every variant needs a placeholder value", rule)
}
}
}
// The whole point of the picker: never the same words twice in a row.
func TestNudgeNoImmediateRepeat(t *testing.T) {
nt := newTestTemplates(t, 7)
prev := ""
for i := 0; i < 200; i++ {
body, _ := nt.Nudge(cand("water", 200, ""))
if body == prev {
t.Fatalf("repeat at %d: %q", i, body)
}
prev = body
}
}
// Same seed, same sequence — otherwise the fixture score would drift run to run.
func TestNudgeDeterministicWithSeed(t *testing.T) {
var runs [2][]string
for r := range runs {
nt := newTestTemplates(t, 42)
for i := 0; i < 20; i++ {
body, _ := nt.Nudge(cand("break", 100, ""))
runs[r] = append(runs[r], body)
}
}
for i := range runs[0] {
if runs[0][i] != runs[1][i] {
t.Fatalf("run %d differs: %q vs %q", i, runs[0][i], runs[1][i])
}
}
}
// A variant is only used when its value exists, and nothing half-filled ships.
func TestNudgeNoLeftoverPlaceholders(t *testing.T) {
nt := newTestTemplates(t, 3)
cases := []loop.Candidate{
cand("water", 0, ""), // no duration
cand("water", 30, ""), // under an hour
cand("water", 200, ""), // hours
cand("service_down", 3, "vaultwarden"),
cand("service_down", 3, ""), // no service name
cand("routine:таблетки", 0, ""),
cand("morning:утро", 0, ""),
cand("unknown_rule", 0, ""),
}
for _, c := range cases {
for i := 0; i < 40; i++ {
body, mood := nt.Nudge(c)
if body == "" {
t.Fatalf("%s: empty body", c.Rule.Name)
}
if strings.ContainsAny(body, "{}%") {
t.Fatalf("%s: unfilled template %q", c.Rule.Name, body)
}
if mood != "neutral" {
t.Fatalf("%s: mood %q", c.Rule.Name, mood)
}
}
}
}
// The routine name must actually land in the text.
func TestNudgeSubstitutesWhat(t *testing.T) {
nt := newTestTemplates(t, 11)
for i := 0; i < 40; i++ {
body, _ := nt.Nudge(cand("routine:таблетки", 0, ""))
if !strings.Contains(strings.ToLower(body), "таблетки") {
t.Fatalf("routine text lost the name: %q", body)
}
}
}
func TestRuSinceWords(t *testing.T) {
cases := []struct {
min int
want string
}{
{30, ""},
{60, "час"},
{95, "полтора часа"},
{150, "два с половиной часа"},
{190, "три часа"},
{240, "четыре часа"},
{430, "семь часов"},
{660, "одиннадцать часов"},
{60 * 30, "больше суток"},
}
for _, c := range cases {
got := ruSinceWords(time.Duration(c.min) * time.Minute)
if got != c.want {
t.Errorf("%d min: got %q want %q", c.min, got, c.want)
}
}
}
func TestNudgeTemplatesPhraseNudge(t *testing.T) {
nt := newTestTemplates(t, 5)
pn, err := nt.PhraseNudge(context.Background(), cand("water", 200, ""))
if err != nil {
t.Fatalf("PhraseNudge: %v", err)
}
if pn.Body == "" || pn.Summary != pn.Body || pn.Mood != "neutral" {
t.Fatalf("bad nudge: %+v", pn)
}
}
+129
View File
@@ -0,0 +1,129 @@
{
"schema_version": 1,
"name": "russian nudge templates v1",
"notes": [
"Hand-written Russian nudges. Edit the wording here, no Go changes needed.",
"Rules: she is feminine about herself, he is a man addressed as ты. Never вы/вас/ваш, never plural imperatives (выпейте), never он/его about him.",
"One short sentence. No questions, no emoji, no pet names, no emotional support.",
"Placeholders: {since} how long it has been (only used when it is at least an hour), {service} the service name, {what} the routine name. A variant whose placeholder has no value is skipped, so every rule needs at least one variant with no placeholder. The exception is routine and morning: those only exist for rules like routine:таблетки that always carry a name, and a routine nudge that drops the name is useless.",
"mood must be one of: neutral, happy, thinking, tired, confused."
],
"rules": {
"water": {
"mood": "neutral",
"variants": [
"Ты не пил воду {since} — выпей стакан.",
"Пора выпить воды.",
"Стакан воды не помешает.",
"Воду ты не пил уже {since}.",
"Напоминаю про воду.",
"Сходи за водой, дела подождут.",
"Сделай глоток воды, пока помнишь.",
"Между делом выпей воды.",
"Вода — простое дело: выпей стакан.",
"Отвлекись на стакан воды."
]
},
"meal": {
"mood": "neutral",
"variants": [
"Ты не ел {since} — поешь.",
"Пора поесть, сделай перекус.",
"Еда важнее ещё одного часа за столом.",
"Без еды уже {since}, поешь.",
"Напоминаю про еду — поешь.",
"Возьми перерыв на обед.",
"Сделай себе перекус, это пять минут.",
"Поешь, потом вернёшься к работе.",
"Поешь нормально, а не на ходу.",
"Еды не было {since} — разогрей что-нибудь."
]
},
"break": {
"mood": "neutral",
"variants": [
"Ты за столом {since} — встань и разомнись.",
"Пора сделать перерыв.",
"Встань на пять минут.",
"{since} без перерыва — отойди от экрана.",
"Напоминаю про перерыв.",
"Разомни спину, потом продолжишь.",
"Короткая пауза не сорвёт дела.",
"Отойди от компьютера на минуту.",
"Сидишь без перерыва {since}.",
"Встань, пройдись, вернись."
]
},
"service_down": {
"mood": "neutral",
"variants": [
"Сервис {service} не отвечает.",
"{service} упал — сервис не отвечает.",
"{service} не отвечает, сервис нужно поднимать.",
"Сервис {service} недоступен.",
"Проверь {service}: сервис не отвечает.",
"Сервис перестал отвечать.",
"Сервис {service} лежит, нужно смотреть.",
"{service} не отвечает уже {since}.",
"Мониторинг сообщает: {service} лежит.",
"Сервис {service} не отвечает, посмотри логи."
]
},
"netdata_critical": {
"mood": "neutral",
"variants": [
"Netdata: критический алярм, проверь диск.",
"Критический алярм в netdata — посмотри диск.",
"Netdata поднял тревогу по диску.",
"Проверь диск: netdata ругается.",
"Алярм от netdata, критический.",
"Netdata: критический уровень, дело в диске.",
"Диск требует внимания — критический алярм в netdata.",
"Критический алярм: проверь место на диске.",
"Netdata сообщает о критической проблеме с диском.",
"Открой netdata: там критический алярм по диску."
]
},
"routine": {
"mood": "neutral",
"variants": [
"По распорядку: {what}.",
"Пора — {what}.",
"Напоминаю: {what}.",
"В списке на сейчас: {what}.",
"{what} — сейчас самое время.",
"Не пропусти: {what}.",
"{what}: пора сделать.",
"Сейчас по плану {what}.",
"Твой распорядок: {what}.",
"{what} — по распорядку сейчас."
]
},
"morning": {
"mood": "neutral",
"variants": [
"{what} — пора начать день.",
"{what}: пройди утренний список.",
"Начни {what} со списка.",
"{what}. Осталось пройти чеклист.",
"Утренний список ещё не пройден: {what}.",
"{what}: первый пункт списка за тобой.",
"{what} идёт, а список стоит.",
"{what}: не забудь про утренние дела.",
"По утреннему чеклисту ещё есть дела: {what}.",
"{what} — утренний список дел ещё ждёт."
]
},
"default": {
"mood": "neutral",
"variants": [
"Напоминаю: есть дело.",
"Пора вернуться к отложенному делу.",
"Одно дело ждёт тебя.",
"Напоминаю про дело из списка.",
"В списке осталось дело.",
"Дело всё ещё не сделано."
]
}
}
}